Patent Application
20250131319
Aspects of the disclosure generally relate to training machine learning models to perform pattern analysis and using the machine learning model to determine information and/or attributes based on the pattern analysis.
Businesses may provide information about themselves, such as operating hours and maps, via their websites. Moreover, information aggregators, such as Google and Apple, may collect business information and display the business information in response to searches for a particular business. However, the information provided by both the businesses and information aggregators may be incorrect and/or out-of-date. In this regard, the information is only as accurate as the information provided by users. Moreover, the computer systems of the businesses and/or the information aggregators are unable to ascertain accurate information associated with the business. This is further compounded when the information (e.g., operating hours) may change, for example, due to holidays or inclement weather. Similarly, the information (e.g., maps) may be outdated, for example, due to remodeling. Accordingly, there is a need in the art for businesses and/or information aggregators to collect information and provide accurate information when requested via a search.
The following presents a simplified summary of various aspects described herein. This summary is not an extensive overview, and is not intended to identify key or critical elements or to delineate the scope of the claims. The following summary merely presents some concepts in a simplified form as an introductory prelude to the more detailed description provided below.
Aspects described herein may relate to training machine learning models to determine one or more attributes and/or information associated with a location based on location traffic and/or connectivity information. After the machine learning model is trained and deployed, the machine learning model may determine one or more attributes and/or information about a location based on received location traffic and/or connectivity information.
Further aspects of the present disclosure describe a computer-implemented method that receives a first location of a user device connected to a network associated with a commercial establishment. The first location may comprise a first timestamp. Additionally, the first location may be determined based on a first distance the user device is from at least a first access point of the mesh network. The computer-implemented method may receive a second location of the first user device connected to the mesh network associated with the commercial establishment. The second location may comprise a second timestamp. Further the second location may be determined based on a second distance the user device is from at least a second access point that is different from the first access point. The computer-implemented may generate, based on pattern analysis using a machine learning algorithm, a mapping of the commercial establishment. The mapping may indicate one or more areas of the commercial establishment. The computer-implemented method may also compare the first timestamp and the second timestamp to publicly available information associated with the commercial establishment. The computer-implemented method may determine, based on a comparison of the first timestamp and the second timestamp to publicly available operating hours for the commercial establishment, actual operating hours of the commercial establishment. The computer-implemented method may provide, based on a request for information associated with the commercial establishment, a response indicating the mapping and the actual operating hours.
Additional aspects of the disclosure describe a computer-implemented method that receives a first indication of a first user device connected to a mesh network associated with a commercial establishment. The indication may comprise a first timestamp and a first location of the first user device that is determined based on a first distance the first user device is from at least a first access point of the mesh network. The computer-implemented method may receive a second indication of a second user device connected to the mesh network associated with the commercial establishment. The second indication may comprise a second timestamp and a second location of the second user device that is determined based on a second distance the second user device is from at least the first access point of the mesh network. The computer-implemented method may generate, based on pattern analysis of at least the first user device and the second user device and using a machine learning algorithm, a mapping of the commercial establishment that indicates one or more areas of the commercial establishment. The computer-implemented method may provide, based on a request for information associated with the commercial establishment, a response indicating the mapping.
Further aspects of the disclosure describe a computer-implemented method that receives a first indication of a first user device connected to a mesh network associated with a commercial establishment. The first indication may comprise a first timestamp. The computer-implemented method may receive a second indication of a second user device connected to the mesh network associated with the commercial establishment. The second indication may comprise a second timestamp, different from the first timestamp. The computer-implemented method may determine, based on pattern analysis using a machine learning algorithm and based on the first timestamp and based on the second timestamp, a plurality of times during which user devices connect to the mesh network. The computer-implemented method may compare the plurality of times during which user devices connect to the mesh network to publicly available information associated with the commercial establishment. The computer-implemented method may determine, based on a comparison of the plurality of times during which user devices connect to the mesh network to the publicly available operating hours for the commercial establishment, actual operating hours of the commercial establishment. The computer-implemented method may provide, based on a request for information associated with the commercial establishment, a response indicating the actual operating hours.
These features, along with many others, are discussed in greater detail below.
The present disclosure is illustrated by way of example and not limited in the accompanying figures in which like reference numerals indicate similar elements and in which:
In the following description of the various embodiments, reference is made to the accompanying drawings, which form a part hereof, and in which is shown by way of illustration various embodiments in which aspects of the disclosure may be practiced. It is to be understood that other embodiments may be utilized and structural and functional modifications may be made without departing from the scope of the present disclosure. Aspects of the disclosure are capable of other embodiments and of being practiced or being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein are for the purpose of description and should not be regarded as limiting. Rather, the phrases and terms used herein are to be given their broadest interpretation and meaning. The use of “including” and “comprising” and variations thereof is meant to encompass the items listed thereafter and equivalents thereof as well as additional items and equivalents thereof.
By way of introduction, aspects described herein may relate to training machine learning models to determine one or more attributes and/or information associated with a location based on location traffic and/or connectivity information. The machine learning models may be trained, for example, using historical connectivity information. The historical connectivity information may comprise information about user devices connecting to one or more access points associated with a location. For example, the historical connectivity information may indicate an order in which user devices connect to each of the access points or a signal strength between a user device and one or more access points. The historical connectivity information may also comprise a duration of how long each user device was connected to each access point. The machine learning models may be trained to identify patterns from the historical connectivity information and determine one or more attributes about a location.
Additional aspects described herein may relate to using the trained machine learning model to learn one or more attributes (e.g., operating hours, a map of the location, etc.) of a location. Computing systems suffer from a technical problem of being unable to obtain information about a location on their own. Rather, computing systems can only use the information that is inputted by one or more users. The present disclosure provides a solution to that problem by allowing computing systems to determine attributes and/or information about a location based on location traffic and/or connectivity information of devices connected to a network associated with a location. In order to arrive at the solution, a computing device may receive first connectivity information associated with a user device connected to a network associated with the location. The computing device may also receive second connectivity information of the user device connected to the network. The computing device may determine one or more attributes of the location using the machine learning model. In this regard, the machine learning model may perform a pattern analysis using at least the first connectivity information and the second connectivity information. The one or more attributes determined by the machine learning model may be compared to publicly available information. For example, the one or more attributes may comprise actual operating hours (e.g., when the store is actually opened), which may be compared to the posted operating hours. This improves the system's ability to determine operating hours, for example, during holidays. When there are differences between the one or more attributes and the publicly available information, one or more remedial actions may be taken to correct the discrepancy. By using the location traffic and/or connectivity information of devices connected to a network, the computing devices are better able to determine information associated with a location. This improves over prior techniques, which require a user to manually enter information. This may cause the information to become stale and/or out-of-date. The techniques described herein allow a computer to automatically determine information about a location based on location traffic and/or connectivity information of devices connected to a network associated with the location. This improves the system's ability to provide up-to-date information associated with various location without requiring a user to input the information.
First user device 110 may be a mobile device, such as a cellular phone, a mobile phone, a smart phone, a tablet, a laptop, or an equivalent thereof. First user device 110 may provide a first user with access to various applications and services. For example, first user device 110 may provide the first user with access to the Internet. Additionally, first user device 110 may provide the first user with one or more applications (“apps”) located thereon. The one or more applications may provide the first user with a plurality of tools and access to a variety of services. In some embodiments, the one or more applications may include a banking application that provides access to the first user's banking information, as well as perform routine banking functions, such as checking the first user's balance, paying bills, transferring money between accounts, withdrawing money from an automated teller machine (ATM), and wire transfers. The banking application may comprise an authentication process to verify (e.g., authenticate) the identity of the first user prior to granting access to the banking information.
Second user device 120 may be a computing device configured to allow a user to execute software for a variety of purposes. Second user device 120 may belong to the first user that accesses first user device 110, or, alternatively, second user device 120 may belong to a second user, different from the first user. Second user device 120 may be a desktop computer, laptop computer, or, alternatively, a virtual computer. The software of second user device 120 may include one or more web browsers that provide access to websites on the Internet. These websites may include banking websites that allow the user to access his/her banking information and perform routine banking functions. In some embodiments, second user device 120 may include a banking application that allows the user to access his/her banking information and perform routine banking functions. The banking website and/or the banking application may comprise an authentication component to verify (e.g., authenticate) the identity of the second user prior to granting access to the banking information.
Server 130 may be any server capable of executing banking application 132. Additionally, server 130 may be communicatively coupled to database 140. In this regard, server 130 may be a stand-alone server, a corporate server, or a server located in a server farm or cloud-computer environment. According to some examples, server 130 may be a virtual server hosted on hardware capable of supporting a plurality of virtual servers.
Banking application 132 may be server-based software configured to provide users with access to their account information and perform routing banking functions. In some embodiments, banking application 132 may be the server-based software that corresponds to the client-based software executing on first user device 110 and second user device 120. Additionally, or alternatively, banking application 132 may provide users access to their account information through a website accessed by first user device 110 or second user device 120 via network 150. The banking application 132 may comprise an authentication module to verify users before granting access to their banking information. Additionally or alternatively, banking application 132 may comprise an automated customer service solution, such as a chatbot or an automated answering service.
Database 140 may be configured to store information on behalf of application 132. The information may include, but is not limited to, personal information, account information, and user-preferences. Personal information may include a user's name, address, phone number (i.e., mobile number, home number, business number, etc.), social security number, username, password, employment information, family information, and any other information that may be used to identify the first user. Account information may include account balances, bill pay information, direct deposit information, wire transfer information, statements, and the like. User-preferences may define how users receive notifications and alerts, spending notifications, and the like. Additionally or alternatively, database 140 may store a plurality of multi-party dialogues, including, for examples, recorded conversations between a customer and a service agent, transcribed conversations, interactions between a customer and a chatbot, etc. Database 140 may include, but are not limited to relational databases, hierarchical databases, distributed databases, in-memory databases, flat file databases, XML databases, NoSQL databases, graph databases, and/or a combination thereof.
Network 150 may include any type of network. In this regard, network 150 may include the Internet, a local area network (LAN), a wide area network (WAN), a wireless telecommunications network, and/or any other communication network or combination thereof. It will be appreciated that the network connections shown are illustrative and any means of establishing a communications link between the computers may be used. The existence of any of various network protocols such as TCP/IP, Ethernet, FTP, HTTP and the like, and of various wireless communication technologies such as GSM, CDMA, WiFi, and LTE, is presumed, and the various computing devices described herein may be configured to communicate using any of these network protocols or technologies. The data transferred to and from various computing devices in system 100 may include secure and sensitive data, such as confidential documents, customer personally identifiable information, and account data. Therefore, it may be desirable to protect transmissions of such data using secure network protocols and encryption, and/or to protect the integrity of the data when stored on the various computing devices. For example, a file-based integration scheme or a service-based integration scheme may be utilized for transmitting data between the various computing devices. Data may be transmitted using various network communication protocols. Secure data transmission protocols and/or encryption may be used in file transfers to protect the integrity of the data, for example, File Transfer Protocol (FTP), Secure File Transfer Protocol (SFTP), and/or Pretty Good Privacy (PGP) encryption. In many embodiments, one or more web services may be implemented within the various computing devices. Web services may be accessed by authorized external devices and users to support input, extraction, and manipulation of data between the various computing devices in the system 100. Web services built to support a personalized display system may be cross-domain and/or cross-platform, and may be built for enterprise use. Data may be transmitted using the Secure Sockets Layer (SSL) or Transport Layer Security (TLS) protocol to provide secure connections between the computing devices. Web services may be implemented using the WS-Security standard, providing for secure SOAP messages using XML encryption. Specialized hardware may be used to provide secure web services. For example, secure network appliances may include built-in features such as hardware-accelerated SSL and HTTPS, WS-Security, and/or firewalls. Such specialized hardware may be installed and configured in system 100 in front of one or more computing devices such that any external devices may communicate directly with the specialized hardware.
Any of the devices and systems described herein may be implemented, in whole or in part, using one or more computing devices described with respect to
Input/output (I/O) device 209 may comprise a microphone, keypad, touch screen, and/or stylus through which a user of the computing device 200 may provide input, and may also comprise one or more speakers for providing audio output and a video display device for providing textual, audiovisual, and/or graphical output. Software may be stored within memory 215 to provide instructions to processor 203 allowing computing device 200 to perform various actions. For example, memory 215 may store software used by the computing device 200, such as an operating system 217, application programs 219, and/or an associated internal database 221. The various hardware memory units in memory 215 may comprise volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. Memory 215 may comprise one or more physical persistent memory devices and/or one or more non-persistent memory devices. Memory 215 may comprise random access memory (RAM) 205, read only memory (ROM) 207, electronically erasable programmable read only memory (EEPROM), flash memory or other memory technology, optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store the desired information and that may be accessed by processor 203.
Accelerometer 211 may be a sensor configured to measure accelerating forces of computing device 200. Accelerometer 211 may be an electromechanical device. Accelerometer may be used to measure the tilting motion and/or orientation computing device 200, movement of computing device 200, and/or vibrations of computing device 200. The acceleration forces may be transmitted to the processor to process the acceleration forces and determine the state of computing device 200.
GPS receiver/antenna 213 may be configured to receive one or more signals from one or more global positioning satellites to determine a geographic location of computing device 200. The geographic location provided by GPS receiver/antenna 213 may be used for navigation, tracking, and positioning applications. In this regard, the geographic may also include places and routes frequented by the first user.
Communication interface 223 may comprise one or more transceivers, digital signal processors, and/or additional circuitry and software, protocol stack, and/or network stack for communicating via any network, wired or wireless, using any protocol as described herein.
Processor 203 may comprise a single central processing unit (CPU), which may be a single-core or multi-core processor, or may comprise multiple CPUs. Processor(s) 203 and associated components may allow the computing device 200 to execute a series of computer-readable instructions (e.g., instructions stored in RAM 205, ROM 207, memory 215, and/or other memory of computing device 215, and/or in other memory) to perform some or all of the processes described herein. Although not shown in
Although various components of computing device 200 are described separately, functionality of the various components may be combined and/or performed by a single component and/or multiple computing devices in communication without departing from the disclosure.
In step 310, a computing device may train one or more machine learning models to determine (e.g., identify) one or more attributes of a physical location. As will be discussed in greater detail below, the one or more attributes of the physical location may be determined, for example, based on location data of one or more user devices within the location. Additionally or alternatively, the one or more attributes may be determined, for example, based on publicly available information, such as operating hours, locations, maps of the location, etc. Preferably, the one or more machine learning models are transformer-based models (e.g., sequence-to-sequence (Seq2Seq), etc.) or an equivalent thereof. Additionally or alternatively, the one or more machine learning models may be a neural network, such as a convolutional neural network (CNN), a recurrent neural network, a recursive neural network, a long short-term memory (LSTM), a gated recurrent unit (GRU), an unsupervised pre-trained network, a space invariant artificial neural network, a generative adversarial network (GAN), or a consistent adversarial network (CAN), such as a cyclic generative adversarial network (C-GAN), a deep convolutional GAN (DC-GAN), GAN interpolation (GAN-INT), GAN-CLS, a cyclic-CAN (e.g., C-CAN), or any equivalent thereof. Additionally or alternatively, the one or more machine learning models may comprise one or more decision trees. In some instances, the one or more machine learning models may comprise a Hidden Markov Model. The one or more machine learning models may be trained using supervised learning, unsupervised learning, back propagation, transfer learning, Adam stochastic optimization, stochastic gradient descent, learning rate decay, dropout, max pooling, batch normalization, long short-term memory, skip-gram, or any equivalent deep learning technique. The one or more machine learning models may be trained using self-supervised learning (e.g., contrastive learning) to decouple the embedding spaces of the negative and positive examples. The one or more machine learning models may be trained, for example, using historical connectivity information. In this regard, the location may comprise a network with one or more access points. In some examples, the network is a mesh network. The mesh network may be associated with a commercial establishment or a point-of-interest, such as a museum. The historical connectivity information may comprise one or more locations of access points. Additionally or alternatively, the historical connectivity information may comprise information about user devices connecting to each of the access points. For example, the historical connectivity information may indicate an order in which user devices connect to each of the access points. The historical connectivity information may also include a signal strength between a user device and one or more access points to indicate (e.g., triangulate) a location of the user device within the commercial establishment or the point-of-interest. The historical connectivity information may also comprise a duration of how long each user device was connected to each access point. The corpus of historical connectivity information may be divided into training data and testing data. Preferably, 65% to 85% of the corpus would form the training data, while the remaining 15% to 35% of the corpus would be test data. The one or more machine learning models may be trained using the training data, while the test data would be used to help the machine learning model achieve convergence (i.e., an error range with an acceptable tolerance). The one or more machine learning models may be trained to identify patterns from the historical connectivity information. That is, the one or more machine learning models may perform pattern analysis on the connectivity information to determine one or more attributes about a location. Once the one or more machine learning models are trained to determine one or more attributes about a location, the one or more machine learning models may be deployed, for example, on one or more servers.
In step 320, the computing device may receive first connectivity information of a user device connected to a network. The computing device may comprise one or more servers, such as a back-end server, on which the one or more machine learning models are deployed. The one or more servers may receive first connectivity information from one or more applications executing on the user device. Additionally or alternatively, the one or more servers may receive first connectivity information from the network. That is, the network may provide connectivity information of one or more user devices to the back-end server. In some instances, the network may provide connectivity information of the one or more user devices over a period of time. The connectivity information may comprise a first location of a user device within the location. The first location may be determined based on the user device being connected to a network, such as a mesh network, associated with the location. The mesh network may comprise a plurality of Internet-of-Things (IoT) devices, such as a point-of-sale terminal, a security device, a security camera, a thermostat, a kiosk, a lighting controller, vending machines, digital signage, monitoring systems, an employee device, or the like. The first location may be determined, for example, based on a first distance the user device is from at least a first access point of the network. The first distance may be determined, for example, using a round trip time and/or a signal strength between the user device and the first access point. In some examples, the first connectivity information may be determined, for example, based on how far the user device is from a plurality of access points. That is, the location may be triangulated based on the distances between the user device and each respective access point of the plurality of access points. In some instances, the first connectivity information may also comprise a first timestamp. The first connectivity information may comprise a first indication that the user device is connected to the network associated with the location. In some instance, the first connectivity information may include an identifier (e.g., SSID, network identifier, etc.) that identifies the location.
In step 330, the computing device may receive second connectivity information of the user device. The second connectivity information may comprise a second location of the user device at the location. The second location may be determined, for example, based on the user device being connected to the network. The second location may be determined, for example, based on a second distance the user device is from at least a second access point that is different from the first access point. The second connectivity information may also comprise a second timestamp. It will be appreciated that the second connectivity information may include the same, or substantially the same, information as the first connectivity information, discussed above. While
In step 340, the computing device may generate one or more attributes about a location, for example, based on the first connectivity information and the second connectivity information. For example, the computing device may use the one or more machine learning models to identify the one or more attributes. The one or more attributes may be generated, for example, based on pattern analysis of the first connectivity information and the second connectivity information. The one or more attributes may comprise a map of the location. The map may indicate one or more areas of a commercial establishment, such as an entrance, a fitting room, a point-of-sale terminal, an office, etc. In some instances, the computing device may generate a real-time location of one or more user devices. The real-time location of the one or more user devices may be useful in determining whether a user associated with a device needs assistance. In this regard, a user device may remain in a single location for an extended period of time. Remaining in a single location for an extended period of time may indicate that a customer is considering purchasing an item and needs assistance from a sales representative. Alternatively, remaining in a single location for an extended period of time may indicate that a customer needs medical assistance. In either scenario, an employee may be notified. The notification may be an electronic communication, such as a push notification, a text message, an email alert, a pop-up on a terminal (e.g., a point-of-sale terminal), and the like. The one or more machine learning models may be able to identify peak times (e.g., busy) associated with the location. In some instances, the one or more machine learning models may be able to determine whether the actual operating hours match posted operating hours, for example, based on the pattern analysis. In further examples, the one or more machine learning models may identify user devices that are associated with employees and/or managers, for example, based on a frequency with which a device connects to the network. A determination of the actual operating hours may be based on a presence or absence of the device associated with the employee. In still further examples, the one or more machine learning models may provide suggestions for improving a layout of the location, for example, by determining a location for a kiosk.
In step 350, the computing device may compare the one or more determined attributes to publicly available information associated with the location. As noted above, the one or more determined attributes may comprise actual operating hours of a commercial establishment, which may be determined based on at least timestamp information received with the connectivity information. The actual operating hours may be compared to publicly available information about the posted operating hours. In further examples, the one or more attributes may comprise a map of the location. The map may be compared to a publicly available map. The publicly available information may be obtained, for example, from a website using a scraping algorithm. In some instances, the connectivity information may include an identifier (e.g., SSID, network identifier, etc.) that identifies the location. The publicly available information may be retrieved, for example, using the identifier. Additionally or alternatively, the publicly available information may be received directly from the location. That is, the location may provide the publicly available information directly to the back-end servers via one or more electronic communications.
In step 360, the computing device may determine whether the one or more determined attributes match the publicly available information. For example, the computing device may determine whether the actual operating hours match the posted operating hours. In another example, the computing device may determine whether a map of the location matches a publicly available map of the location. If the one or more determined attributes do not match the publicly available information, the process may proceed to step 370. In some instance, the computing device may determine whether the one or more determined attributes match the previously recorded information about the location. That is, the computing device may generate an alert and/or determine that the determined attributes do not match previously stored information, for example, if the one or more determined attributes (e.g., an actual sequence of device location, sequence of location data, etc.) is significantly different from a predicted sequence of events.
In step 370, the computing device may update information associated with the location, for example, based on a determination that the one or more determined attributes do not match publicly available information. In some examples, the computing device may update information associated with the location in a database. The attributes and/or information in the database may be provided to one or more customers and/or users, for example, in response to one or more search queries for the location. Additionally or alternatively, the computing device may modify information of the location, for example, via one or more user interfaces. In some instances, the information of the location may be provided, for example, in response to detecting a user device approaching and/or near the location. The information may be provided via one or more electronic communications, such as a push notification via one or more mobile applications, a text message, an email alert, and the like.
In step 380, the computing device may receive a request for information associated with the location. The computing device may provide a response indicating the information, for example, in response to receiving the request for information. As noted above, the information may comprise at least one of a mapping of the location, operating hours of the location, or peak times of the location. As noted above, the information may be provided, for example, in response to detecting a user device approaching and/or near the location. The computing device may receive a physical location of the user device from the GPS/receiver antenna 213 of the user device. Based on the physical location of the user device, the computing device may determine that the user is at the location. The computing device may provide the information associated with the location, for example, based on a determination that the user is at the location. The information may be provided via one or more electronic communications, such as a push notification via one or more mobile applications, a text message, an email alert, and the like.
By using the techniques described above, the system is able to collect information and provide accurate information when requested via a search. As noted above, information provided by websites and/or information aggregators is only as good as the information provided by users. That is, the computing devices are unable to obtain information about the location on their own. Using the techniques discussed herein, computing devices are able to ascertain location information based on location traffic and/or device connectivity. The techniques herein improve a computing device's ability to obtain information about a location using crowdsourcing, location traffic, and/or connectivity information.
As noted above, the machine learning model may be trained identify information based on pattern analysis of device connectivity to one or more access points in a network.
As shown in
Finally,
The machine learning model described herein may determine one or more attributes and/or information about a location.
As shown in
Using the techniques described above, the present disclosure uses machine learning models to perform pattern analysis of user devices connecting to a local network. This pattern analysis allows the machine learning models to determine one or more attributes and/or information about a location that would otherwise be unobtainable.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
