Patent Application
20250232351
Wealth advisors work with clients to develop investment strategies, retirement plans, wealth-building plans, and the like. In many cases, an advisor will speak with clients during meetings, phone calls, teleconferences, and the like, which are conducted using meeting software. The meeting software may display a dashboard with information about assets to help the client understand and make informed wealth management decisions. Over time, the advisor and the client may establish their preferences for the dashboard. For example, users may have preferences for the type of content they prefer to see on the dashboard and locations for the type of content within the dashboard.
One example embodiment provides an apparatus that may include a memory, and a processor coupled to the memory, the processor configured to connect a local user profile hosted within a software application hosted by a first platform with a profile hosted by a data source on a second platform, extract a first set of profile features from the profile hosted by the data source and a second set of profile features from the local user profile, determine a new profile feature to add to the local user profile based on an execution of an artificial intelligence (AI) model on a combination of the first and second sets of profile features, and display information about the new profile feature on a user interface of the first or second platform.
Another example embodiment provides a method that includes one or more of connecting a local user profile hosted within a software application hosted by a first platform with a profile hosted by a data source on a second platform, extracting a first set of profile features from the profile hosted by the data source and a second set of profile features from the local user profile, determining a new profile feature to add to the local user profile based on the execution of an artificial intelligence (AI) model on a combination of the first and second sets of profile features, and displaying information about the new profile feature on a user interface of the first or second platform.
A further example embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of connecting a local user profile hosted within a software application hosted by a first platform with a profile hosted by a data source on a second platform, extracting a first set of profile features from the profile hosted by the data source and a second set of profile features from the local user profile, determining a new profile feature to add to the local user profile based on the execution of an artificial intelligence (AI) model on a combination of the first and second sets of profile features, and displaying information about the new profile feature on a user interface of the first or second platform.
A further example embodiment provides an apparatus that may include a memory, and a processor coupled to the memory, the processor configured to one or more of ingest profile data of a user from an external data source, identify a plurality of features of a profile hosted by the external data source based on execution of an artificial intelligence (AI) model on the ingested profile data of the user from the external data source, identify a feature from among the plurality of features of the profile hosted by the external data source that is not connected to a local user profile of the user, and display a connection request on a user interface, wherein the connection request includes a link to a page associated with the identified feature hosted by the external data source.
A further example embodiment provides a method that includes one or more of ingesting profile data of a user from an external data source, identifying a plurality of features of a profile hosted by the external data source based on execution of an artificial intelligence (AI) model on the ingested profile data of the user from the external data source, identifying a feature from among the plurality of features of the profile hosted by the external data source that is not connected to a local user profile of the user, and displaying a connection request on a user interface, wherein the connection request includes a link to a page associated with the identified feature hosted by the external data source.
A further example embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of ingesting profile data of a user from an external data source, identifying a plurality of features of a profile hosted by the external data source based on execution of an artificial intelligence (AI) model on the ingested profile data of the user from the external data source, identifying a feature from among the plurality of features of the profile hosted by the external data source that is not connected to a local user profile of the user, and displaying a connection request on a user interface, wherein the connection request includes a link to a page associated with the identified feature hosted by the external data source.
A further example embodiment provides an apparatus that may include a memory, and a processor coupled to the memory, the processor configured to establish a communication session between a first user device and a second user device from among the plurality of user devices, train an artificial intelligence (AI) model to learn user interface preferences of a plurality of user devices during the communication session, receive a description associated with the communication session, generate a plurality of windows of content and display the plurality of windows of content on a user interface of the first user device during the communication session based on execution of the AI model on the description associated with the communication session, and generate a second plurality of windows of content and display the second plurality of windows of content on a user interface of the second user device based on an execution of the AI model on the description associated with the communication session.
A further example embodiment provides a method that includes one or more of establishing a communication session between a first user device and a second user device from among the plurality of user devices, training an artificial intelligence (AI) model to learn user interface preferences of a plurality of user devices during the communication session, receiving a description associated with the communication session, generating a plurality of windows of content and displaying the plurality of windows of content on a user interface of the first user device during the communication session based on execution of the AI model on the description associated with the communication session, and generating a second plurality of windows of content and displaying the second plurality of windows of content on a user interface of the second user device based on an execution of the AI model on the description associated with the communication session.
A further example embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of establishing a communication session between a first user device and a second user device from among the plurality of user devices, training an artificial intelligence (AI) model to learn user interface preferences of a plurality of user devices during the communication session, receiving a description associated with the communication session, generating a plurality of windows of content and displaying the plurality of windows of content on a user interface of the first user device during the communication session based on execution of the AI model on the description associated with the communication session, and generating a second plurality of windows of content and displaying the second plurality of windows of content on a user interface of the second user device based on an execution of the AI model on the description associated with the communication session.
A further example embodiment provides an apparatus that may include a memory, and a processor coupled to the memory, the processor configured to render a graphical user interface within a software application including a plurality of elements, modify locations of the plurality of elements within the graphical user interface based on user inputs on the graphical user interface, generate a dynamic mapping of the graphical user interface including the modified locations of the plurality of elements based on an execution of an artificial intelligence (AI) model on the rendered graphical user interface, and store the dynamic mapping of the graphical user interface within a storage.
A further example embodiment provides a method that includes one or more of rendering a graphical user interface within a software application including a plurality of elements, modifying locations of the plurality of elements within the graphical user interface based on user inputs on the graphical user interface, generating a dynamic mapping of the graphical user interface including the modified locations of the plurality of elements based on an execution of an artificial intelligence (AI) model on the rendered graphical user interface, and storing the dynamic mapping of the graphical user interface within a storage.
A further example embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of rendering a graphical user interface within a software application including a plurality of elements, modifying locations of the plurality of elements within the graphical user interface based on user inputs on the graphical user interface, generating a dynamic mapping of the graphical user interface including the modified locations of the plurality of elements based on an execution of an artificial intelligence (AI) model on the rendered graphical user interface, and storing the dynamic mapping of the graphical user interface within a storage.
A further example embodiment provides an apparatus that may include a memory, and a processor coupled to the memory, the processor configured to store portfolio content from a plurality of users, receive a portfolio of a user during a call, determine that the user is similar to a subset of users from among the plurality of users based on execution of an artificial intelligence (AI) model on the portfolio of the user and the portfolio content from the plurality of users, identify an item that is included in portfolios of the subset of users which is not included in the portfolio of the user, and display content about the item on a user interface.
A further example embodiment provides a method that includes one or more of storing portfolio content from a plurality of users, receiving a portfolio of a user during a call, determining that the user is similar to a subset of users from among the plurality of users based on execution of an artificial intelligence (AI) model on the portfolio of the user and the portfolio content from the plurality of users, identifying an item that is included in portfolios of the subset of users which is not included in the portfolio of the user, and displaying content about the item on a user interface.
A further example embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of storing portfolio content from a plurality of users, receiving a portfolio of a user during a call, determining that the user is similar to a subset of users from among the plurality of users based on execution of an artificial intelligence (AI) model on the portfolio of the user and the portfolio content from the plurality of users, identifying an item that is included in portfolios of the subset of users which is not included in the portfolio of the user, and displaying content about the item on a user interface.
A further example embodiment provides an apparatus that may include a memory, and a processor coupled to the memory, the processor configured to one or more of log user actions with respect to placement of objects of content on a user interface including respective content types of the objects of content, train an artificial intelligence (AI) model to learn location preferences for a content type on the user interface based on the logged user actions including the respective content types, receive a request to open an object on the user interface with the content type, determine a display location on the user interface for the object based on execution of the AI model on the content type, and display the object at the determined display location on the user interface.
A further example embodiment provides a method that includes one or more of logging user actions with respect to placement of objects of content on a user interface including respective content types of the objects of content, training an artificial intelligence (AI) model to learn location preferences for a content type on the user interface based on the logged user actions including the respective content types, receiving a request to open an object on the user interface with the content type, determining a display location on the user interface for the object based on execution of the AI model on the content type, and displaying the object at the determined display location on the user interface.
A further example embodiment provides a computer-readable medium comprising instructions, that when read by a processor, cause the processor to perform one or more of logging user actions with respect to placement of objects of content on a user interface including respective content types of the objects of content, training an artificial intelligence (AI) model to learn location preferences for a content type on the user interface based on the logged user actions including the respective content types, receiving a request to open an object on the user interface with the content type, determining a display location on the user interface for the object based on execution of the AI model on the content type, and displaying the object at the determined display location on the user interface.
It is to be understood that although this disclosure includes a detailed description of cloud computing, implementation of the instant solution recited herein is not limited to a cloud computing environment. Rather, embodiments of the instant solution are capable of being implemented in conjunction with any other type of computing environment now known or later developed.
The example embodiments are directed to a platform that can ingest content from a graphical user interface (GUI) and learn preferences for locations of content types within the GUI based on generative artificial intelligence (GenAI). In some embodiments, a GenAI model may be trained to understand a correlation between content types and GUI locations (e.g., X-, Y-, Z-coordinates, etc.). For example, the training may include logged GUI activity of the user. Furthermore, the GenAI model may also render content within a GUI based on the GUI preferences learned by the GenAI model.
According to various embodiments, the GenAI model may be a large language model (LLM), such as a multimodal large language model. As another example, the GenAI model may be a transformer neural network (“transformer”), or the like. The GenAI model is capable of understanding connections between coordinate points on a GUI and content types (e.g., income, retirement, savings, banking, etc.). For example, the GenAI model may include libraries and deep learning frameworks that enable the GenAI model to create realistic display content on the GUI including dynamically generated image and text content.
Technological advancements typically build upon the fundamentals of predecessor technologies, such is the case with Artificial Intelligence (AI). An AI classification system describes the stages of AI progression. The first classification is known as “Reactive Machines,” followed by present-day AI classification “Limited Memory Machines” (also known as “Artificial Narrow Intelligence”), then progressing to “Theory of Mind” (also known as “Artificial General Intelligence”), and reaching the AI classification “Self Aware” (also known as “Artificial Superintelligence”).
Present-day Limited Memory Machines are a growing group of AI models built upon the foundation of its predecessor, Reactive Machines. Reactive Machines emulate human responses to stimuli; however, they are limited in their capabilities as they cannot typically learn from prior experience. Once the AI model's learning abilities emerged, its classification was promoted to Limited Memory Machines. In this present-day classification, AI models learn from large volumes of data, detect patterns, solve problems, generate and predict data, and the like, while inheriting all of the capabilities of Reactive Machines.
Examples of AI models classified as Limited Memory Machines include, but are not limited to, Chatbots, Virtual Assistants, Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), Generative AI (GenAI) models, and any future AI models that are yet to be developed possessing the characteristics of Limited Memory Machines.
Generative AI models are a combination of Limited Memory Machine technologies, incorporating ML and DL, and, in turn, form the foundational building blocks of future AI models. For example, Theory of Mind is the next progression of AI that will be able to perceive, connect, and react by generating appropriate reactions in response to the entity with which the AI model is interacting; all these capabilities rely on the fundamentals of Generative AI. Furthermore, in an evolution into the Self Aware classification, AI models will be able to understand and evoke emotions in the entities they interact with, as well as possessing their own emotions, beliefs, and needs, all of which rely on Generative AI fundamentals of learning from experiences to generate and draw conclusions about itself and its surroundings. Generative AI models are integral and core to future artificial intelligence models. As described herein, Generative AI refers to present-day Generative AI models and future AI models.
The GenAI model may also analyze a type of content that is to be displayed, for example, a page of content that is about to be loaded into a web browser, software application, etc. Here, the GenAI model may determine a location for the page of content within the browser or other user interface based on the content type. The GenAI model can apply what it has learned through its training to choose a display location/placement of the page/window of the content type on the screen. Furthermore, the GenAI model may be retrained as the user changes preferences for content types and display locations. Data from the user's activity on the GUI can be logged and ingested by the GenAI model to learn updated display location preferences of the user over time.
In addition, the example embodiments may also leverage open banking protocols and connect profiles across host platforms. For example, a feature (such as an account, etc.) of a user hosted by an external computing platform may be connected to an account/profile of the user hosted locally by a host computing platform. Here, the GenAI model may analyze account/profile data from the external computing platform to identify a feature (such as a payment account, loan, credit card, savings account, etc.) which can be connected to a user profile hosted locally by the host computing platform.
Here, the host platform 120 may host a software application 121 and make it accessible to the user device 110 and the user device 130 at the same time over a computer network such as the Internet. For example, the software application 121 may include a mobile application that includes a front-end which is installed on the user device 110 (and the user device 130), and a back-end which is installed on the host platform 120. As another example, the software application 121 may be a progressive web application (PWA) that is hosted by the host platform 120 and made accessible via a browser on the user device 110 and/or the user device 130 via an address on the web. In one example, the software application 121 is a teleconferencing software application, however, embodiments are not limited thereto.
In the example embodiments, the host platform 120 may include a GenAI model 122 which is capable of learning a user's preferences for display locations of content types and for applying the user's preferences when new content is opened on the screen. The host platform 120 may also include one or more additional models, including one or more machine learning models, one or more artificial intelligence (AI) models, one or more additional GenAI models, and the like. The models, including the GenAI model 122 may be held by the host platform 120 within a model repository (not shown).
In the example embodiments, the GenAI model 122 may be trained based on GUI history data of one or more users, profile data of one or more users, portfolio data of one or more users, asset data from open sources, such as publicly available sources on the web, and the like. The GenAI model 122 may be trained to generate GUI content that can be depicted on a user interface of the meeting software, such as windows of content, cards, modules, menus, buttons, checkboxes, radio buttons, and the like. The GUI content may be generated based on user preferences that the GenAI model 122 has learned from user activities on the GUI. Thus, the GenAI model 122 can learn where a user prefers particular content types. The GenAI model can also dynamically size the content based on preferences of the user and a type of display device where the content is being output.
The training data for training the GenAI model 122 may be obtained from a data store 124 that includes historical GUI data of the user, such as logged user activities on the GUI including movement of GUI objects and content types. The historical GUI data may include coordinate points (e.g., X, Y, and Z) which represent dimensional locations of the objects with respect to an outer perimeter of the GUI.
In the example of
As an example, a dashboard may be output by the software application 121 on the user interface 111 of the user device 110 and the user interface 131 of the user device 130. Here, the dashboard may include content that is visible to both of the user devices 110 and 130 and/or content that is only visible to one of the user devices. The software application 121 may control which device sees which content and create different experiences on the user interface for each of the user devices 110 and 130 during the meeting. Furthermore, the GenAI model 122 may ingest the content recorded from the meeting and generate additional content that can be displayed during the meeting, as well as additional content that can be used after the meeting, such as a call script, a call list, and the like. The GenAI model 122 may use profile data from a data store 123 and portfolio data from a data store 125 to generate recommendations of features, assets, products, and the like, for a client.
Furthermore, according to various embodiments, the host platform 120 may also connect a user profile stored within the software application 121 with a feature hosted by an external data source 140, such as an external server, website, etc. The external data source 140 may provide history of the user to the host platform 120. The history can be analyzed by the GenAI model 122 to identify product recommendations based on a combination of history from the user's external profile and the user's locally held profile.
In
In some embodiments, the payload of data may be in a format that cannot be input to the model 224 nor read by a computer processor. For example, the payload of data may be in text format, image format, audio format, and the like. In response, the AI engine 222 may convert the payload of data into a format that is readable by the model 224, such as a vector or other encoding. The vector may then be input into the model 224.
In some embodiments, the software application 210 may display a user interface which enables a user thereof to provide feedback on the output provided by the model 224. For example, a user may input a confirmation that the GUI placement of an object by a GenAI model is correct or is liked. This information may be added to the results of execution and stored within a log 225. The log 225 may include an identifier of the input, an identifier of the output, an identifier of the model used, and feedback from the recipient. This information may be used to subsequently retrain the model.
The IDE 310 may be used to design a model (via a user interface of the IDE), such as a GenAI model that can receive text as input and generate custom imagery, text, etc., which can be displayed on a user interface/dashboard of a software application that displays content during meetings between user devices. The model can be executed/trained based on the training data established via the user interface. For example, the user interface may be used to build a new model. The training data for such a new model may be provided from a training data store, such as a database 324, which includes training samples from the web, from customers, and the like. As another example, the training data may be pulled from one or more external data stores 330, such as publicly available sites, etc.
During training, the GenAI model 322 may be executed on training data via an AI engine 321 of the host platform 320. The training data may include a large corpus of generic images and text that is related to those images. In the example embodiments, the training data may include coordinate locations on a GUI and content types mapped to each other. The GenAI model 322 may learn mappings/connections between locations on the GUI and content types and thus dynamically place content within the GUI based on content type. When the model is fully trained, it may be stored within the model repository 323 via the IDE 310 or the like.
As another example, the IDE 310 may be used to retrain the GenAI model 322 after the model has already been deployed. Here, the training process may use executional results that have already been generated/output by the GenAI model 322 in a live environment (including any customer feedback, etc.) to retrain the GenAI model 322. For example, predicted outputs/GUI placements that are custom generated by the GenAI model 322 and the user feedback of the placements may be used to retrain the model to further enhance the images that are generated for all users. The responses may include indications of whether the generated content is correct, and if not, what aspects of the placement are incorrect. This data may be captured and stored within a runtime log 325 or other data store within the live environment and can be subsequently used to retrain the GenAI model 322.
The script 326 may iteratively retrieve additional training data sets from the database 324 and iteratively input the additional training data sets into the GenAI model 322 during the execution of the model to continue to train the model. The script may continue the process until instructions within the script inform the script to terminate, which may be based on a number of iterations (training loops), total time elapsed during the training process, etc.
In the example of
Prompt engineering is the process of structuring sentences (prompts) so that they are understood by the GenAI model. A prompt may include a description of a goal, such as a goal of purchasing a particular type of asset. The prompt may also provide an amount to purchase, a price range at which to purchase, and the like. All of this information may be input into the GenAI model and used to create custom content about the asset to enable the user to visualize the asset and understand how to add the asset to their portfolio, such as the steps to take to obtain the asset. Part of the prompting process may include delays/waiting times that are intentionally included within the script, such that the model has time to think/understand the input data.
The GenAI model 422 may receive an input from the user device 410. For example, the user may enter a response into a field 414 of the user interface 411 with an answer to the question 413 which is submitted to the software application 421. Here, the software application 421 may combine the question 413 and the response from the field 414 and generate a prompt that is input to the GenAI model 422 and used to predict a GUI location of a display object, such as a window of content. Referring to
In the example of
In some embodiments, the software application 421 may deliberately add waiting times between submitting prompts to the GenAI model 422 to ensure that the model has enough time to “think” about the answer. The waiting times may be integrated into the code of the software application 421, or they may be modified/configured via a user interface. Furthermore, the ordering of the prompts and the follow-up questions may differ depending on the answers received during the previous prompt or prompts. Each prompt may include multiple components including one or more of context, an instruction, input data, and an expected response/output.
For example, the software application 521 may query an application 502 installed on the user device 510 for information about an upcoming call/teleconference. The application 502 may be a calendar application, a meeting application, an email application, a message application, a chat application, and the like. Here, a meeting summary 504 of an upcoming meeting is retrieved from an electronic calendar within the application 502. In response to receiving the meeting summary 504, the software application 521 may transfer the meeting summary (e.g., the text content) to the GenAI model 522, which can generate display content for the upcoming meeting. Here, the GenAI model 522 may access profile data of the user in a data store 523, GUI history data of the user in a data store 524, portfolio data of the user in a data store 525, and the like.
According to various embodiments, the GenAI model 522 may be trained to identify content types and locations of such content types that are preferred on the respective user interfaces of the different devices. The training process may be performed differently for each device using different instances of the GenAI model 522. As another example, the same GenAI model may learn the preferences of multiple users.
For example,
Here, the preferences are learned by the GenAI model 522 during the training prior to the meeting being conducted. The training may include previous meetings conducted between the user device 510 and the user device 530, including call content, visual content, etc. As such, the GenAI model 522 is already familiar with the preferences of the user device 510 and the user device 530 when the meeting is conducted. In this example, the GenAI model 522 determines to display windows of content 541, 542, and 543 on the user interface 512 of the user device 510 and the user interface 532 of the user device 530. Here, the GenAI model 522 determines the arrangement of the windows of content 541, 542, and 543 in different locations on the user interface 512 and the user interface 532 based on the learned preferences. Furthermore, the GenAI model 522 may also determine the size, shape, etc. of the windows of content 541, 542, and 543 for the different users.
In addition, in this example, the GenAI model 522 displays an additional window of content 544 on the user interface 532 that is not shown on the user interface 512 of the user device 510 based on the learned preferences. In this example, the GenAI model 522 can rearrange the locations based on changes to preferences that are learned over time. The model can be retrained using logged data from a live runtime environment.
The user interface 610 may periodically log user interface positions of windows of content, along with a content type of the windows of content, and send them to a software application 622 hosted by a host platform 620. Here, the software application 622 may record the logged GUI data within a data store 624. The logged data may include pixel locations of the window 612 and the window 614, changes to the pixel locations of the window 612 and the window 614 (e.g., deltas, etc.), content types of the window 612 and the window 614, and the like. The logged data may be used to train a GenAI model as shown in
For example,
The content types may be limited to a predefined set of content types (e.g., a predetermined set of 25 possible content types, 50 content types, 100 content types, etc.). The GenAI model 628 may learn both location and size preferences as well. In the example of
In this example, the user may submit the portfolio of the target user 712 to the software application 722, which in turn forwards content from the portfolio of the target user 712 to a GenAI model 724, also hosted on the host platform 720. The user may submit the portfolio by uploading a file via a user interface 711 of the user device 710 or by identifying a storage location of the portfolio within a portfolio data store 728 of the host platform 720. Here, the GenAI model 724 may ingest the portfolio of the target user 712 and identify one or more portfolios of other users 730 that are similar to the target user 712.
For example,
According to various embodiments, the locations and content types of the display elements 811, 812, 813, and 814 may be submitted to the software application 822 in response to a request, at periodic intervals, in response to a condition, or the like. The software application 822 may transfer the display locations and content types of the display elements 811, 812, 813, and 814 to a GenAI model 824, which generates a bitmap 826 of the locations of the display elements 811, 812, 813, and 814, with respect to an outer perimeter of the user interface 810. The bitmap 826 may include a digital image that preserves the sizes and the locations of the display elements 811, 812, 813, and 814. The bitmap may include a rectangular mesh of pixels that contains location values and content type values. In some embodiments, the bitmap may even include color values within the pixels.
Furthermore, when the software application receives a request for the user interface 810, the software application 822 may instantiate the user interface 810 by selecting one of the bitmaps and instantiating the display elements at positions based on the selected bitmap. For example,
In this example, the software application 922 may receive the user's access credentials with an external host system 930 which hosts the external user profile 936. In response, the software application 922 may query an endpoint 932 of the external host system 930 based on the user credentials and request access to profile content and features within the external user profile 936 hosted by the external host system 930. In this example, the software application 922 may “connect” an external account hosted by the external host system 930 or other external feature identified from the external user profile 936 of the user to the local user profile 928, thereby enabling access (view, transact, etc.) for the user to the external account while logged into the software application 922.
According to various embodiments, the software application 922 may pass the external user profile 936 to a GenAI model 924. In addition, the GenAI model 924 may retrieve the local user profile 928 from the data store 926 and execute on the received profiles to identify a product feature, such as an account or a benefit that can be added to the local user profile 928 from the external user profile 936. For example,
For example, referring to
In the example of
The software application 922 may extract a set of active features from the external user profile 936 and a set of active features from the local user profile 928 hosted by the host platform 920 and determine the new profile (e.g., new recommended content to add to the portfolio, etc.) based on executing the GenAI model 924 on each set of active features. The new portfolio may include a feature of interest hosted by the host platform that is not included in the local user profile and not included in the profile hosted by the external host system based on executing the GenAI model on the combination of the profile features extracted from the profile hosted by the external host system and the profile features extracted from the local user profile.
In some embodiments, the logging may include logging horizontal and vertical pixel locations and content types of the window objects within the user interface. In some embodiments, the training may include training the AI model to learn spatial locations of the objects of content within the user interface with respect to an outer perimeter of the user interface. In some embodiments, the method may further include identifying movement of the object from the determined display location to a different display location on the user interface and storing a log of the identified movement within a log file. In some embodiments, the method may include retraining the AI model based on the log of the identified movement of the object from the determined display location to the different display location on the user interface.
In some embodiments, the method may further include receiving an input on a different window object already positioned within the user interface and in response, rearranging a position of the different window object within the user interface based on a content type of the different window object. In some embodiments, the rearranging may include determining a new position for the different window object based on executing the AI model on the content type of the different window object and moving the different window object to the new position on the user interface. In some embodiments, the method may further include capturing locations and content types of the objects currently displayed on the user interface and dynamically rearranging the locations of the objects on the user interface based on executing the AI model on the content types of the objects.
In some embodiments, the receiving may include opening the portfolio of the user within a software application, and the displaying may include displaying the content about the item within a page of the software application. In some embodiments, the determining may include determining that a set of assets included in the portfolio of the user matches a set of assets included in the portfolio content from the plurality of users. In some embodiments, the identifying may include identifying an asset to be added to the user's portfolio based on executing the AI model on the set of assets included in the user's portfolio. In some embodiments, the method may further include determining an amount of the item to add to the portfolio of the user based on executing the AI model on an identifier of the item and the portfolio of the user.
In some embodiments, the method may further include querying an external data store for performance data of the item and generating a graphic illustration that represents the performance of the asset of interest. In some embodiments, the method may further include conducting the call via a software application and displaying the graphic illustration within a user interface of the software application that is conducting the call. In some embodiments, the generating of the graphic illustration may include generating one or more of a chart or a graph showing the performance of the asset of interest in the future based on executing an AI model on the performance data of the item.
In some embodiments, the method may further include receiving a request to open a software application comprising a display window, and in response, determining locations of user interface elements within the display window of the software application based on the stored dynamic image of the graphical user interface. In some embodiments, the method may further include identifying a device type of a user device where the software application is being opened and generating the image of the graphical user interface based on executing the AI model on the device type of the user device. In some embodiments, the method may further include identifying a device type of a user device where the software application is being opened and further determining the locations of the user interface elements within the display window based on the device type of the user device.
In some embodiments, the plurality of elements may include a plurality selected from a group of elements, including a button, a slider, a text field, a combo box, a menu, and the like, which are displayed within the graphical user interface. In some embodiments, the method may further include receiving a request for the graphical user interface, and in response, reconstructing the graphical user interface with the modified locations of the plurality of elements based on the stored dynamic image of the graphical user interface. In some embodiments, the method may further include training the AI model prior to generating the dynamic image of the graphical user interface, wherein the training comprises executing the AI model based on historical locations of user interface elements of a software application for a user. In some embodiments, the method may further include modifying locations of user interface elements within a software application of a second user based on the AI model.
In 1034, the method may include generating a plurality of windows of content and displaying the plurality of windows of content on a user interface of the first user device during the communication session based on execution of the AI model on the description associated with the communication session. In 1035, the method may include generating a second plurality of windows of content and displaying the second plurality of windows of content on a user interface of the second user device based on an execution of the AI model on the description associated with the communication session.
In some embodiments, the training may include executing the AI model on call content and visual content from previous meetings between the first user device and the second user device. In some embodiments, the receiving of the call may include receiving an audio feed and a video feed from a meeting application on one or more of the first user device and the second user device. In some embodiments, receiving the description may include receiving a meeting summary of the call with a summary description of content to be discussed during the call between the first user device and the second user device. In some embodiments, the generating of the second plurality of windows of content may include generating at least one window of content for the second plurality of windows of content that is not included in the plurality of windows of content displayed on the user interface of the first user device.
In some embodiments, the generating of the second plurality of windows of content may include generating a same plurality of windows of content for the first and second user interfaces and arranging the second plurality of windows of content in different locations on the user interface of the second user device than the first plurality of windows of content on the user interface of the first user device based on different preferences of the second user device. In some embodiments, the different preferences are determined based on executing the AI model on call content and visual content from previous meetings between the first and second user devices. In some embodiments, the displaying of the second plurality of windows of content on the user interface of the second user device may include displaying the second plurality of windows of content on the user interface of the second user device simultaneously while displaying the plurality of windows of content on the user interface of the first user device.
In some embodiments, the ingesting may include querying an endpoint associated with the external data source for an external user profile hosted at the external host system. In some embodiments, the method may further include outputting a query about the profile data from the external data source on the user interface of a user device of the user based on executing the AI model on the ingested profile data. In some embodiments, the method may further include receiving a response to the query, which is input via the user interface, and the identifying further comprises identifying the features hosted by the external host system that is not connected to the local user profile based on executing the AI model on the query and the received response to the query.
In some embodiments, the identifying of the plurality of features may include identifying a plurality of profile features of the user within a user profile from the external data source. In some embodiments, the identifying of the feature that is not connected may include identifying a profile feature from among the plurality of profile features that has not been added to a local profile of the user hosted by a host platform, and the displaying may include displaying a link to a landing page of the profile feature at the external host system.
In some embodiments, the method may further include ingesting profile data of the user from a second external data source and identifying a list of profile features that are active at the second external data source based on executing the AI model on the profile data of the user from the second external data source. In some embodiments, the method may further include identifying a feature that is active within the profile data of the user at the second external data source that is not connected to the local user profile and displaying a connection request on the user interface with a link to a page of the feature within the profile data at the second external data source. In one embodiment, a connection to open banking accesses the external data source. The connection may call out to secured external data requiring authentication to access.
In 1053, the method may include determining a new profile feature to add to the local user profile based on the execution of an artificial intelligence (AI) model on a combination of the first and second sets of profile features. In 1054, the method may include displaying information about the new profile feature on a user interface of the first or second platform. In some embodiments, the connecting may include receiving credentials for a user profile from the external data source via the user interface and submitting the credentials to the external host system to connect the profile from the external data source to the software application.
In some embodiments, the extracting may include extracting a set of active features within the profile from the external data source and a set of active features within the local user profile hosted by the host platform and determining the new profile feature based on executing the AI model on each set of active features. In some embodiments, the determining may include identifying a feature of interest hosted by the host platform that is not included in the local user profile and not included in the profile from the external data source based on executing the AI model on the combination of the profile features extracted from the profile from the external data source and the profile features extracted from the local user profile.
In some embodiments, the method may further include training the AI model based on profiles of other users hosted by the host platform and features included in the profiles of the other users. In some embodiments, the method may further include displaying user interface controls within the user interface and receiving feedback about the new profile feature from the user interface based on inputs with respect to the user interface controls. In some embodiments, the method may further include retraining the AI model based on the new profile feature and the feedback about the new profile feature received from the user interface.
In one embodiment, the system is extended to a cloud-based platform wherein users can seamlessly integrate multiple profiles from various external data sources. The cloud platform allows centralized processing, making the execution of the AI model faster and more efficient, ensuring that profile features extracted from different sources are stored, processed, and updated in real time. Users connect to the cloud platform using secure credentials and select the external data sources they wish to integrate, and the cloud-based system automatically extract, process, and update profile features. The system harnesses the computational power and scalability advantages of cloud architectures. Users can effortlessly amalgamate multiple profiles sourced from a range of external data repositories by situating the method on a cloud platform. This centralized approach ensures swift and streamlined processing, allowing the AI model to execute tasks efficiently. In one embodiment, the system can constantly update and process profile attributes from diverse sources in a real-time setting. Users initiate a connection to the cloud platform via secure authentication methods. Once authenticated, they are presented with an interface where they can elect the external databases they intend to assimilate. Following this selection, the cloud system takes over, automatically reaching out to the chosen databases, retrieving the necessary profile components, processing this data, and ensuring that the profile features are constantly updated, ensuring that the user's integrated profile remains current and comprehensive.
In one embodiment, the system focuses on privacy preservation. Before extracting features from the external data source, the system employs encryption and/or other privacy-preserving techniques, ensuring that user data remains confidential. Only after this functionality would the AI model process the encrypted data. The system utilizes Homomorphic Encryption or Differential Privacy that is employed to protect the user's data during the feature extraction and processing phases. The system is tailored to safeguard user data even before feature extraction from external data sources commences. The system ensures that the user's data remains concealed and untouched from any potential breaches or unauthorized access. Only post this protective measure does the AI model proceed to decipher and process the encrypted data, ensuring that the original, unencrypted data never gets exposed to the model or any other entity. Techniques such as Homomorphic Encryption are employed. This method allows computations to be carried out on the encrypted data without ever needing to decrypt it, ensuring user data confidentiality throughout the processing phase. Additionally, Differential Privacy is used to add statistical noise to the user's data, ensuring that individual data points cannot be singled out, thus maintaining the user's anonymity.
In one embodiment, the system employs a user feedback mechanism. Once the new profile feature is displayed, the software application prompts the user with specific questions about relevance, accuracy, or utility, further refining the AI model's understanding. The system may incorporate pop-up surveys or sliders for users to rate the new profile features, which then feed back into the AI model for continuous learning. Upon the display of the new profile feature within the software application, it takes an extra step to engage the user actively. Rather than passively presenting information, the system proactively prompts the user with specific questions, probing insights about the newly presented profile feature's relevance, accuracy, or overall utility. Such a method is to garner user response and refine and enhance the AI model's comprehension and accuracy over time. In one embodiment, the system deploys pop-up surveys post the display of new profile features. These surveys could be designed with pointed questions, gauging user sentiment about the utility and relevance of the provided feature. Alternatively, sliders could be used, offering users an intuitive way to rate their satisfaction or agreement level with the feature on a continuum, be it from “Not Relevant” to “Highly Relevant” or any other relevant scale. These user inputs, once gathered, feed directly back into the AI model, allowing for continuous learning by the AI model. Every user interaction becomes a learning opportunity, allowing the AI model to iteratively fine-tune its predictions and outcomes, aligning more closely with user expectations, and ensuring enhanced user satisfaction in subsequent interactions.
In one embodiment, a multi-layered profile integration system is implemented. This system categorizes profile features into primary, secondary, and tertiary layers based on their relevance, giving users a more structured view of their integrated profile. The AI model ranks features based on a combination of factors such as source reliability, user feedback, and relevance scores. Instead of presenting users with a monolithic amalgamation of profile features, this approach brings more structure and hierarchy to the integrated profile. The system categorizes and presents profile features within three distinct layers: primary, secondary, and tertiary. Each of these layers is reflective of the relevance and importance of the features contained within. The AI model is responsible for ranking and segregating features across these layers. The ranking process is not arbitrary but is determined based on a meticulously designed combination of factors. For example, the reliability of the source from which the feature was extracted plays a crucial role. A feature from a trusted and verified source might naturally find its place in the primary layer, while one from a less reliable source might be relegated to the secondary or tertiary layers.
Furthermore, the system harnesses the power of user feedback, as further discussed herein in the interactive feedback mechanism. Features that consistently receive positive feedback or are deemed highly relevant by users might be elevated to higher layers, while those that fail to resonate with users might be moved down the hierarchy. Additionally, an intrinsic relevance score, computed by the AI model based on contextual factors and historical data, can further guide the categorization process.
In one embodiment, the system predicts potential future profile features based on patterns identified across multiple users and their external data sources. The AI model, trained on extensive user datasets, analyzes patterns and trends to forecast and suggest possible future profile additions or changes. Instead of solely aggregating and integrating current features, the system is designed to forecast potential future features. This is achieved by discerning patterns and commonalities identified across a broad spectrum of users and their respective external data sources. The AI model is trained on vast and diverse datasets encompassing a multitude of users. This training equips the model to identify overarching patterns, trends, and trajectories in profile feature evolutions. For example, if a significant proportion of users in a certain age bracket or geographical location begin to exhibit a particular new profile feature, the AI can extrapolate this data to predict that similar users might also adopt or showcase this feature in the near future.
Furthermore, by analyzing the historical data of individual users, the AI model can also gauge personal growth trajectories or changing interests. If a user's profile has shown an increasing inclination towards eco-friendly activities over the past year, the AI might predict and suggest features related to sustainable practices or green technologies for the upcoming months.
These predictive insights offer multiple benefits. For one, users can be better prepared for potential shifts in their profiles, giving them a foresight that can be advantageous in various scenarios, be it personal branding, career planning, or social networking. Additionally, by receiving these predictive insights, users might become more proactive, either embracing the predicted changes or consciously altering their trajectories based on the foresight provided.
In one embodiment, the system focuses on dynamic profile updates. Instead of a one-time extraction and integration, the system continuously monitors the external data sources for any changes and updates the local user profile accordingly. Using functionality such as web scrapers or API calls, the system remains connected to external sources, ensuring the user's profile within the software application remains up to date. In the current embodiment, the focus shifts from a static, one-off profile integration to an agile and dynamic approach, ensuring the user's profile remains perpetually current and reflective of any changes occurring in external data sources. The continuous monitoring ensures that any modifications, additions, or deletions in the external sources are promptly identified and mirrored in the local user profile within the software application. For example, if a user garners a new certification or alters their job position in an external professional networking site, this change would be automatically detected and replicated in the user's integrated profile. The operational engine driving this real-time synchronization can be powered by web scrapers or, more efficiently, by leveraging API calls. These tools can be scheduled to run at regular intervals or even be triggered by certain events, ensuring the timeliness of updates. Additionally, the system might incorporate notification mechanisms to maintain user trust and prevent potential data overload. Users are alerted whenever significant changes are identified and integrated, offering them the choice to review, accept, or reject these updates.
In one embodiment, an originating processor located within the host platform recognizes the need to integrate an external profile with the local user profile. Upon detecting a user's intent (possibly through a user interface action) or a predefined instruction, the processor sends a connection request message to a destination processor overseeing the external data source. This message may contain metadata about the local user profile, credentials for accessing the external data source, and other necessary details to facilitate the connection. Upon receipt of the connection request, the destination processor (within the external data source) validates the credentials and, if authenticated, sends a profile data message back to the originating processor. This message includes relevant profile features and any associated metadata from the external data source. After receiving the profile data message, the originating processor extracts the necessary features from the external and local user profiles. The processor then initiates the AI model to determine potential new features. To do this, it may send an AI processing request message to a dedicated AI module or a co-processor specifically designed for AI computations. This message contains a combination of profile features extracted from both the local user profile and the external data source. Upon completing the computations, the AI co-processor identifies the new profile feature(s) and sends back a feature identification message to the originating processor. This message conveys details of the new profile feature and any relevant insights or recommendations associated with it. Lastly, the originating processor, equipped with the new profile feature data, commands the software application's user interface module to display the feature. It does so by dispatching a UI update message, instructing the UI to update and showcase the new feature details to the user.
In one embodiment, the originating processor within the host platform triggers a credential request message to the user interface, prompting users to input their profile credentials for the external data source. Once the user submits the credentials through the user interface, the UI sends a credential submission message back to the originating processor. This message contains the user's credentials for the external profile. The originating processor then sends a profile connection message to the destination processor in the external data source containing the user's credentials. Upon successful validation of these credentials by the destination processor, an authentication acknowledgment message is relayed back, permitting the connection and subsequent data exchange between the host platform and the external data source.
In one embodiment, the originating processor sends a feature extraction request message to both the local profile's storage module and the destination processor at the external data source.
Once the features are extracted, the external data source's processor sends an active feature data message to the originating processor. This message provides details about the active features present in the external profile. Upon collating active features from both profiles, the originating processor dispatches an AI active feature processing request message to the dedicated AI co-processor or module. This message contains both sets of active features, prompting the AI to determine the new profile feature.
In one embodiment, after extracting profile features from both sources, the originating processor seeks to identify any unique features not present in either profile. To achieve this, it sends a feature comparison request message to the AI co-processor, containing profile features from both the local user profile and the external data source. The AI co-processor then performs a comparative analysis, identifying any “features of interest” missing from both profiles. Upon completion, it sends back a feature identification message to the originating processor. This message provides details of the identified features of interest and relevant data, or metadata associated with them.
In one embodiment, the system trains the AI model with profiles of other users. The originating processor in the host platform sends an AI training request message to the dedicated AI co-processor or module. This message instructs the AI module to initiate a training session using stored profiles. Subsequently, the originating processor sends a user profile data collection message to the data storage module, which contains profiles of other users. The storage module then retrieves these profiles and sends back a profile data response message comprising features from multiple user profiles. Once the AI co-processor receives this bulk of data, it commences the training process. Upon completion, the AI module sends a training completion acknowledgment message to the originating processor, confirming that the model is now updated and trained based on the combined user data.
In one embodiment, the originating processor dispatches UI controls to display messages to the user interface module. This message prompts the display of specific controls that allow users to give feedback on the new profile feature. Once the user interacts with these controls and provides feedback, the user interface sends a user feedback message back to the originating processor. This message contains the user's inputs and opinions on the new profile feature.
In one embodiment, the system refines the AI model. Upon receipt of the user feedback message, the originating processor sends an AI retraining request message to the AI co-processor. This message comes with the new profile feature details and user feedback. Having received instructions to retrain, the AI co-processor assimilates the new data and feedback to refine its predictions and recommendations. Upon the completion of the retraining process, the AI co-processor sends back a retraining completion acknowledgment message to the originating processor, confirming that the AI model has been successfully updated based on user feedback.
In one embodiment, the primary apparatus consists of a processor linked with a memory. The processor, on initiation, sends a message (Message A) to an external data source's processor, requesting user profile data. Once this data is received, the processor employs an AI model, processing the data to recognize distinct features. If a feature not connected to the local profile is found, the processor sends a display request (Message B) to the user interface processor, prompting it to show a connection request with a relevant link. After the primary processor ingests user profile data, it sends another message (Message C) to query an endpoint related to the external data source. This message asks for more comprehensive details of the user's profile hosted externally. Upon receiving the query, the external source's processor fetches the requested profile and sends it back. Post data ingestion and AI analysis, the primary processor may generate a query about the external profile data. It then sends a display request (Message D) to the user interface processor, prompting it to present this query on the user's device interface for further clarification or feedback. When the user interacts with the query displayed, their input is captured by the user interface processor and sent (Message E) to the primary processor. The processor then utilizes the AI model again, combining the user's response with the previously ingested data to further identify unlinked features from the external source. The primary processor uses the AI model to analyze the ingested external user profile data. If multiple features within the external profile are identified, it catalogs them for future reference or actions. Post the identification of multiple features; the processor determines any feature not added to the local profile. Once such a feature is found, a display request (Message F) is sent to the user interface processor, prompting it to showcase a direct link to the unadded feature's landing page on the external source. The primary processor, in addition to the first external data source, sends a data request (Message G) to a second external data source's processor. Once the user profile data from this second source is ingested, the AI model is again used to determine active profile features specific to this source. When the processor identifies an active feature in the second external source's data not connected to the local profile, it dispatches another display request (Message H) to the user interface processor. This message prompts the display of a connection request, complete with a link that leads to the feature's specific page on the second external source.
In one embodiment, when the processor trains the AI model on user interface (UI) preferences, it might send a “Training Initiation” message to secondary processors responsible for managing the UI. Upon receiving a call between two devices, a “Call Detected” message can be sent to the AI model, prompting it to access recent training data. When generating and displaying content windows, the processor sends a “Display Request” message to each device's processor, detailing the content to be displayed. When executing the AI model on previous meetings' content, the processor sends a “Data Retrieval” message to storage processors, requesting past calls and visual content between the two devices. This information is utilized to refine and train the AI model further. For audio and video feeds, the processor sends a “Feed Request” message to the processors of the devices (first and/or second user device) to obtain real-time data streams. These streams are processed and used as input for displaying relevant content windows. Upon a call's initiation, the processor may send a “Meeting Summary Request” message to the originating device, asking for an overview or agenda. The returned summary then influences the content windows that will be displayed. For generating unique content windows for the second device, a “Unique Window Generation” message is sent from the main processor to the AI model, which determines and sends back the unique content based on its training. When generating content for both devices, the main processor sends a “Layout Preference Query” message to each device's processor. This is to gather UI preferences and arrange content accordingly. The devices' processors respond with a “Preference Data” message containing the necessary UI details. The main processor sends a “Historical Data Request” message to storage processors to determine unique device preferences, requesting data from previous interactions between the two devices. The AI model uses this data to discern and predict UI layout preferences. The main processor sends concurrent “Display Request” messages to both the first and second user devices to ensure simultaneous display. This ensures that content windows appear on both devices' interfaces at the same time, enhancing the synchronized user experience.
In one embodiment, the apparatus's processor (Processor A) receives a command to display the graphical user interface (GUI). Processor A sends a message to the memory requesting the standard layout of the GUI. Upon receiving user input to modify the GUI, Processor A instructs an AI model processor (Processor B) to generate a dynamic mapping or dynamic image of the updated GUI. Processor B, after processing, sends back a mapping or image, which Processor A then commands to be stored in the memory. When a request comes to open a software application, Processor A queries the memory for the stored dynamic mapping or image of the GUI. Once retrieved, Processor A sends a message to the software application's processor (Processor C) with instructions on how to configure the user interface elements based on the retrieved dynamic mapping or image. Upon recognizing a software launch request, Processor A communicates with a device identification processor (Processor D) to determine the type of device in use. With this information, Processor A and Processor B collaborate to adjust the GUI's configuration in accordance with the device type. Processor D proactively identifies the device type and communicates this to Processor A. Using this data, Processor A collaborates with Processor C to adjust the GUI elements' positions, ensuring optimal compatibility with the recognized device. This claim underscores the various elements within the GUI. When these elements are interacted with or modified, Processor A sends element-specific messages to Processor B, guiding the AI model's decisions in real-time. When a request to view the GUI is received, Processor A communicates with the memory to fetch the dynamic mapping or image. This mapping or image is then dispatched to Processor C (software application processor) to reconstruct and display the most recent GUI configuration. Processor A commands Processor B to undergo training before creating the dynamic mapping or image. Processor A sends historical user data from the memory to Processor B. Processor B processes this data, training the AI model to better predict user preferences based on historical interactions. Processor B, once trained, isn't confined to serving a single user. When a second user's GUI interaction is detected by Processor A, it communicates with Processor B, instructing it to use the trained AI model. Processor B then modifies the second user's GUI elements within their software application, ensuring a personalized user experience based on the shared knowledge.
In one embodiment, the core apparatus consists of a memory and a processor (referred to as Processor A). Processor A has multiple functionalities, primarily centered on portfolio analysis and display adjustments based on the results of an AI model. This model could be executed on a specialized AI processor, referred to herein as Processor B. Additionally, an external data store, managed by Processor C, can be involved when querying for additional data. Processor A initializes by storing portfolios from multiple users. When a user shares their portfolio during a call, Processor A packages this portfolio data and sends a message to Processor B, asking for a similarity analysis. The message might be formatted as: [Request: Similarity Analysis; Data: User Portfolio; Stored Portfolios]. After executing the AI model, Processor B returns a subset of users deemed similar. Processor A then cross-references the user's portfolio against these similar ones to find missing items and prepares to display content related to the missing item. Upon receiving a command to display content within a specific software application in the user's portfolio, Processor A retrieves the content related to the identified item and embeds it within the software application, ensuring a seamless user experience. Processor A reviews the user's portfolio and detects asset matches with the stored portfolio content. This might involve a message within Processor A like: [Action: Asset Match; Data: User Portfolio; Stored Portfolios], facilitating internal cross-referencing and asset identification. With the user's asset set identified, Processor A sends another message to Processor B: [Request: Asset Recommendation; Data: User Asset Set]. Processor B uses the AI model to determine possible asset additions and responds with suitable recommendations. Upon determining a potential item to add to the user's portfolio, Processor A consults Processor B on the volume or amount of the item. The message might be: [Request: Asset Volume Analysis; Data: Item Identifier, User Portfolio]. Processor B evaluates the request and provides an appropriate amount based on the AI model's outcomes. Processor A sends a query to Processor C: [Request: Performance Data; Data: Item Identifier] for a detailed analysis of an item's performance. Processor C searches its databases and sends back the performance data. Processor A creates a graphical representation with this data to illustrate the item's performance. When a software application is maintaining the call, Processor A integrates the graphical representation within this application's interface, enhancing the user's context during the call. To predict an asset's future performance, Processor A communicates with Processor B using the message: [Request: Future Performance Prediction; Data: Item Performance Data]. Processor B executes the AI model, analyzes the historical performance data, and sends back predictive graphical content like charts or graphs.
In one embodiment, a primary Processor A (managing user interactions and content display) and an auxiliary Processor B (handling AI operations and predictions) is presented. When a user positions or interacts with content objects on a user interface, Processor A captures these actions, documenting each with its associated content type. This data is accumulated for the training of an AI model. Once a user requests to open a content object on the user interface, Processor A dispatches a message to Processor B, which might be framed as: [Action: Predict Placement; Data: Content Type]. Using its trained AI model, Processor B calculates the optimal placement and communicates back with the preferred location. Processor A then ensures the object is displayed at that recommended position on the user interface. Processor A's data recording routine captures the x-y coordinates (horizontal and vertical pixel locations) of content objects on the user interface, associating each position with its relevant content type. This granular data aids the AI model in developing more precise placement predictions. For the AI model to understand the spatial context of user placements, Processor A sends spatial positioning data to Processor B. This information emphasizes positions relative to the user interface's boundary or outer perimeter, allowing the AI model to recognize patterns and preferences in proximity to edges. When a user manually relocates a content object, Processor A notices this shift, especially if it's from an AI-recommended location. This movement, and its associated metadata, are then documented for further model refinement. Recognizing potential discrepancies between user behavior and AI suggestions, Processor A may periodically initiate AI model retraining. It communicates with Processor B via a message like: [Action: Retrain; Data: Movement Logs]. Processor B adjusts the AI model, using these logs to better align predictions with user behavior. On detecting user input on an existing object in the user interface, Processor A sends a query to Processor B with the structure: [Request: Adjust Position; Data: Content Type]. Given the existing AI data and the content type in question, this determines whether the item's position should be modified. For repositioning already-placed objects, Processor A dispatches another message to Processor B: [Action: Determine New Position; Data: Content Type of Object]. Processor B consults the AI model, deduces a new optimal position, and conveys this back. Processor A then commands the UI to shift the object to this new location. Processor A takes a snapshot of current object placements and their content types to dynamically reconfigure the user interface. It sends this bulk data to Processor B as [Action: Dynamic Rearrangement; Data: Current Positions and Types]. Processor B evaluates the data, uses the AI model to suggest a new layout, and communicates this back. Processor A enacts these changes, ensuring the user interface reflects the updated, optimal object arrangement.
In one embodiment, the system maps the user interface elements, not an image of the user interface. This mapping allows for both a wider repositioning of the elements within the application, and provisioning of the AI-generated GUI.
The above embodiments may be implemented in hardware, in a computer program executed by a processor, in firmware, or in a combination of the above. A computer program may be embodied on a computer readable medium, such as a storage medium. For example, a computer program may reside in random access memory (“RAM”), flash memory, read-only memory (“ROM”), erasable programmable read-only memory (“EPROM”), electrically erasable programmable read-only memory (“EEPROM”), registers, hard disk, a removable disk, a compact disk read-only memory (“CD-ROM”), or any other form of storage medium known in the art.
An exemplary storage medium may be coupled to the processor such that the processor may read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (“ASIC”). In the alternative, the processor and the storage medium may reside as discrete components. For example,
Computer system/server 1102 may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, and so on, that perform particular tasks or implement particular abstract data types. Computer system/server 1102 may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
A distributed cloud computing environment represents a sophisticated evolution of cloud services, breaking away from the traditional centralized model and pushing applications, data, and computing power to more localized environments. This architecture is inherently spread across multiple distinct geographical locations, implying that computing resources, storage, and networking capabilities can be located at the edge of the cloud network, reducing latency, bandwidth use, and data sovereignty concerns.
In such an environment, public cloud providers leverage a mix of their own and third-party infrastructure to support the distribution of public cloud services to different physical locations. However, the services are still managed centrally. Customers can use and access these services locally, enjoying the benefits of a public cloud service, including scalability, elasticity, and up-to-date feature sets, while also experiencing lower latency and data processing closer to the point of origin, often critical for compliance-bound data processing or latency-sensitive applications.
An integral component of this distributed approach includes edge computing, which allows for the processing of data closer to its source, or “edge” of the network, rather than relying on a centralized data-processing warehouse.
Underpinning these services is a network of data centers or processing nodes, often micro data centers, that are interconnected via high-speed communication networks. This ensures not only rapid data transfer but also resilience and redundancy, as the distributed nature of these resources means that they are less susceptible to single points of failure. The management plane of this distributed cloud remains centralized, providing a uniform method of deploying, operating, and monitoring the services, thus ensuring consistent security, policy, and governance across the ecosystem.
As shown in
The bus represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer system/server 1102 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer system/server 1102, and it includes both volatile and non-volatile media, removable and non-removable media. The system memory 1106, in one embodiment, implements the flow diagrams of the other figures. The system memory 1106 can include computer system readable media in the form of volatile memory, such as random-access memory (RAM) 1110 and/or cache memory 1112. Computer system/server 1102 may further include other removable/non-removable, volatile/non-volatile computer system storage media. By way of example only, storage system 1114 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a “hard drive”). Although not shown, a magnetic disk drive for reading from and writing to a removable, non-volatile magnetic disk (e.g., a “floppy disk”), and an optical disk drive for reading from or writing to a removable, non-volatile optical disk, such as a CD-ROM, DVD-ROM or other optical media, can be provided. In such instances, each can be connected to the bus by one or more data media interfaces. As will be further depicted and described below, the system memory 1106 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of various embodiments of the application.
Program/utility 1116, having a set (at least one) of program modules 1118, may be stored in the system memory 1106 by way of example, and not limitation, as well as an operating system, one or more application programs, other program modules, and program data. Each of the operating system, one or more application programs, other program modules, and program data or some combination thereof, may include an implementation of a networking environment. Program modules 1118 generally carry out the functions and/or methodologies of various embodiments of the application as described herein.
As will be appreciated by one skilled in the art, aspects of the present application may be embodied as a system, method, or computer program product. Accordingly, aspects of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.), or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects of the present application may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.
Computer system/server 1102 may also communicate with one or more external devices 1120, such as a keyboard, a pointing device, a display 1122, etc.; one or more devices that enable a user to interact with computer system/server 1102; and/or any devices (e.g., network card, modem, etc.) that enable computer system/server 1102 to communicate with one or more other computing devices. Such communication can occur via input/output (I/O) interfaces 1124. Still yet, computer system/server 1102 can communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and/or a public network (e.g., the Internet) via network adapter 1126. As depicted, network adapter 1126 communicates with the other components of computer system/server 1102 via a bus. It should be understood that although not shown, other hardware and/or software components could be used in conjunction with computer system/server 1102. Examples include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, redundant array of independent disks (RAID) systems, tape drives, and data archival storage systems, etc.
Although an exemplary embodiment of at least one of a system, method, and computer readable medium has been illustrated in the accompanying drawings and described in the foregoing detailed description, it will be understood that the application is not limited to the embodiments disclosed but is capable of numerous rearrangements, modifications, and substitutions as set forth and defined by the following claims. For example, the system's capabilities of the various figures can be performed by one or more of the modules or components described herein or in a distributed architecture and may include a transmitter, receiver, or pair of both. For example, all or part of the functionality performed by the individual modules may be performed by one or more of these modules. Further, the functionality described herein may be performed at various times and in relation to various events, internal or external to the modules or components. Also, the information sent between various modules can be sent between the modules via at least one of: a data network, the Internet, a voice network, an Internet Protocol network, a wireless device, a wired device and/or via a plurality of protocols. Also, the messages sent or received by any of the modules may be sent or received directly and/or via one or more of the other modules.
One skilled in the art will appreciate that a “system” could be embodied as a personal computer, a server, a console, a personal digital assistant (PDA), a cell phone, a tablet computing device, a smartphone, or any other suitable computing device, or combination of devices. Presenting the above-described functions as being performed by a “system” is not intended to limit the scope of the present application in any way but is intended to provide one example of many embodiments. Indeed, methods, systems, and apparatuses disclosed herein may be implemented in localized and distributed forms consistent with computing technology.
It should be noted that some of the system features described in this specification have been presented as modules in order to more particularly emphasize their implementation independence. For example, a module may be implemented as a hardware circuit comprising custom very large-scale integration (VLSI) circuits or gate arrays, off-the-shelf semiconductors, such as logic chips, transistors, or other discrete components. A module may also be implemented in programmable hardware devices, such as field programmable gate arrays, programmable array logic, programmable logic devices, graphics processing units, or the like.
A module may also be at least partially implemented in software for execution by various types of processors. An identified unit of executable code may, for instance, comprise one or more physical or logical blocks of computer instructions that may, for instance, be organized as an object, procedure, or function. Nevertheless, the executables of an identified module need not be physically located together but may comprise disparate instructions stored in different locations which, when joined logically together, comprise the module and achieve the stated purpose for the module. Further, modules may be stored on a computer-readable medium, which may be, for instance, a hard disk drive, flash device, random access memory (RAM), tape, or any other such medium used to store data.
Indeed, a module of executable code could be a single instruction or many instructions and may even be distributed over several different code segments, among different programs, and across several memory devices. Similarly, operational data may be identified and illustrated herein within modules and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set or may be distributed over different locations, including over different storage devices, and may exist, at least partially, merely as electronic signals on a system or network.
It will be readily understood that the components of the application, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments is not intended to limit the scope of the application as claimed but is merely representative of selected embodiments of the application.
One having ordinary skill in the art will readily understand that the above may be practiced with steps in a different order and/or with hardware elements in configurations that are different from those which are disclosed. Therefore, although the application has been described based upon these preferred embodiments, it would be apparent to those of skill in the art that certain modifications, variations, and alternative constructions would be apparent.
While preferred embodiments of the present application have been described, it is to be understood that the embodiments described are illustrative only, and the scope of the application is to be defined solely by the appended claims when considered with a full range of equivalents and modifications (e.g., protocols, hardware devices, software platforms, etc.) thereto.
