System and methods thereof for recommending tags for multimedia content elements based on context

Abstract

A system and method for recommending tags for a multimedia content element to be tagged. The method includes obtaining a plurality of signatures for the multimedia content element to be tagged, wherein each of the generated signatures represents a concept, wherein each concept is a collection of signatures and metadata representing the concept; correlating between the plurality of signatures to determine at least one context of the multimedia content element to be tagged; searching for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context; and identifying at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; generating a recommendation including the identified at least one tag.

Description

TECHNICAL FIELD

The present disclosure relates generally to contextual analysis of multimedia content elements, and more specifically to context-based recommendation of tags for multimedia content elements.

BACKGROUND

Since the advent of digital photography and, in particular, after the rise of social networks, the Internet has become inundated with uploaded images, videos, and other content.

Due to the large amount of content available online, people generally only look at a small fraction of the content that their contacts in the social network publish. In an effort to address the problem, some people manually tag multimedia content in order to indicate subject matter of such content in an effort to encourage users seeking content featuring the tagged subject matter to view the tagged content. The tags may be textual or other identifiers included in metadata of the multimedia content, thereby associating the textual identifiers with the multimedia content. Users may subsequently search for multimedia content elements with respect to tags by providing queries indicating desired subject matter. Tags therefore make it easier for users to find content related to a particular topic.

A popular textual tag is the hashtag. A hashtag is a type of label or typically used on social networking websites, chats, forums, microblogging services, and the like. Users create and use hashtags by placing the hash character (or number sign) # in front of a word or unspaced phrase, either in the main text of a message associated with content, or at the end. Searching for that hashtag will then present each message and, consequently, each multimedia content element, that has been tagged with it.

Accurate and complete listings of hashtags can massively increase exposure of users to a certain multimedia content. Existing solutions for tagging typically rely on user inputs to provide identifications of subject matter. However, such manual solutions may result in inaccurate or incomplete tagging. Further, although some automatic tagging solutions exist, such solutions face challenges in efficiently and accurately identifying subject matter of multimedia content. Moreover, such solutions typically only recognize superficial expressions of subject matter in multimedia content and, therefore, fail to account for context in tagging multimedia content.

It would be therefore advantageous to provide a solution for accurately recommending tags that matches the multimedia content elements.

SUMMARY

A summary of several example embodiments of the disclosure follows. This summary is provided for the convenience of the reader to provide a basic understanding of such embodiments and does not wholly define the breadth of the disclosure. This summary is not an extensive overview of all contemplated embodiments, and is intended to neither identify key or critical elements of all embodiments nor to delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more embodiments in a simplified form as a prelude to the more detailed description that is presented later. For convenience, the term “some embodiments” or “certain embodiments” may be used herein to refer to a single embodiment or multiple embodiments of the disclosure.

Certain embodiments disclosed herein include a method for recommending tags for a multimedia content element to be tagged. The method comprises obtaining a plurality of signatures for the multimedia content element to be tagged, wherein each of the generated signatures represents a concept, wherein each concept is a collection of signatures and metadata representing the concept; correlating between the plurality of signatures to determine at least one context of the multimedia content element to be tagged; searching for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context; and identifying at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; generating a recommendation including the identified at least one tag.

Certain embodiments disclosed herein also include a non-transitory computer readable medium having stored thereon causing a processing circuitry to execute a process, the process comprising: obtaining a plurality of signatures for the multimedia content element to be tagged, wherein each of the generated signatures represents a concept, wherein each concept is a collection of signatures and metadata representing the concept; correlating between the plurality of signatures to determine at least one context of the multimedia content element to be tagged; searching for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context; and identifying at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; generating a recommendation including the identified at least one tag.

Certain embodiments disclosed herein also include a system for method for recommending tags for a multimedia content element to be tagged. The system comprises: a processing circuitry; and a memory connected to the processing circuitry, the memory containing instructions that, when executed by the processing circuitry, configure the system to: obtain a plurality of signatures for the multimedia content element to be tagged, wherein each of the generated signatures represents a concept, wherein each concept is a collection of signatures and metadata representing the concept; correlate between the plurality of signatures to determine at least one context of the multimedia content element to be tagged; search for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context; and identify at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; generate a recommendation including the identified at least one tag.

BRIEF DESCRIPTION OF THE DRAWINGS

The subject matter that is regarded as the disclosure is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other objects, features, and advantages of the disclosed embodiments will be apparent from the following detailed description taken in conjunction with the accompanying drawings.

FIG. 1 is a network diagram utilized to describe the various disclosed embodiments herein.

FIG. 2 is a flowchart illustrating a method for recommending tags for a multimedia content element according to an embodiment.

FIG. 3 is a flowchart illustrating a method for selecting recommended tags of a plurality of potential tags as recommendations to the user device according to an embodiment.

FIG. 4 is a block diagram depicting the basic flow of information in the signature generator system.

FIG. 5 is a diagram showing the flow of patches generation, response vector generation, and signature generation in a large-scale speech-to-text system.

FIG. 6 is a block diagram of a tag recommender according to an embodiment.

DETAILED DESCRIPTION

It is important to note that the embodiments disclosed herein are only examples of the many advantageous uses of the innovative teachings herein. In general, statements made in the specification of the present application do not necessarily limit any of the various claimed inventions. Moreover, some statements may apply to some inventive features but not to others. In general, unless otherwise indicated, singular elements may be in plural and vice versa with no loss of generality. In the drawings, like numerals refer to like parts through several views.

A system and method for recommending tags for multimedia content elements based on context. A plurality of signatures is generated to a multimedia content element. Each of the generated signatures represents a concept. The concepts of the generated signatures are correlated. Based on the correlation, a context of the multimedia content element is determined. Based on the context, a recommendation of at least one tag is generated. Generating the at least one tag may include searching for existing tags associated with contextually related multimedia content elements.

FIG. 1 is an example network diagram 100 utilized to describe the various embodiments disclosed. The network diagram 100 includes a user device 120, a tag recommender 130, a database 150, a deep content classification (DCC) system 160, and a plurality of data sources 170-1 through 170-m (hereinafter referred to individually as a data source 170 and collectively as data sources 170, merely for simplicity purposes) communicatively connected via a network 110. The network 110 may be, but is not limited to, the Internet, the world-wide-web (WWW), a local area network (LAN), a wide area network (WAN), a metro area network (MAN), and other networks capable of enabling communication between the elements of the network diagram 100.

The user device 120 may be, but is not limited to, a personal computer (PC), a personal digital assistant (PDA), a mobile phone, a smart phone, a tablet computer, a wearable computing device and other kinds of wired and mobile appliances, equipped with browsing, viewing, listening, filtering, managing, and other capabilities that are enabled as further discussed herein below. The user device 120 may have installed thereon an application 125 such as, but not limited to, a web browser. The application 125 may be configured to store multimedia content elements in, for example, the data sources 170. For example, the application 125 may be a web browser through which a user of the user device 120 accesses a social media website and uploads multimedia content elements when one of the data sources 170 is associated with the social media website.

The database 150 may be a context database storing information such as, but not limited to, multimedia content elements, clusters of multimedia content elements, previously determined contexts, signatures previously analyzed, a combination thereof, and the like. The database 150 may further store concepts, where the concepts may represent the previously determined contexts.

In an embodiment, the tag recommender 130 includes a processing circuitry coupled to a memory (e.g., the processing circuitry 610 and the memory 620 as shown in FIG. 6). The memory contains instructions that can be executed by the processing circuitry. In a further embodiment the tag recommender 130 may include an array of at least partially statistically independent computational cores configured as described in more detail herein below.

In an embodiment, the tag recommender 130 is communicatively connected to a signature generator system (SGS) 140, which is utilized by the tag recommender 130 to perform the various disclosed embodiments. Specifically, the signature generator system 140 is configured to generate signatures to multimedia content elements and includes a plurality of computational cores, each computational core having properties that are at least partially statistically independent of each other core, where the properties of each core are set independently of the properties of each other core.

The signature generator system 140 may be communicatively connected to the tag recommender 130 directly (as shown), or through the network 110 (not shown). In another embodiment, the tag recommender 130 may further include the signature generator system 140, thereby allowing the tag recommender 130 to generate signatures for multimedia content elements.

In an embodiment, the tag recommender 130 is communicatively connected to the deep content classification system 160, which is utilized by the tag recommender 130 to perform the various disclosed embodiments. Specifically, the deep content classification system 160 is configured to create, automatically and in an unsupervised fashion, concepts for a wide variety of multimedia content elements. To this end, the deep content classification system 160 may be configured to inter-match patterns between signatures for a plurality of multimedia content elements and to cluster the signatures based on the inter-matching. The deep content classification system 160 may be further configured to reduce the number of signatures in a cluster to a minimum that maintains matching and enables generalization to new multimedia content elements. Metadata of the multimedia content elements is collected to form, together with the reduced clusters, a concept. An example deep content classification system is described further in U.S. Pat. No. 8,266,185, assigned to the common assignee, the contents of which are hereby incorporated by reference.

The deep content classification system 160 may be communicatively connected to the tag recommender 130 directly (not shown), or through the network 110 (as shown). In another embodiment, the tag recommender 130 may further include the deep content classification system 160, thereby allowing the tag recommender 130 to create a concept database and to match concepts from the concept database to multimedia content elements.

In an embodiment, the tag recommender 130 is configured to receive, from the user device 120, a multimedia content element to be tagged. In another embodiment, the tag recommender 130 is configured to receive, from the user device 120, an indicator of a location of the multimedia content element to be tagged in storage (e.g., in the data source 170). In a further embodiment, the tag recommender 130 is configured to retrieve the multimedia content element to be tagged based on the indicator. The multimedia content element may be, but is not limited to, an image, a graphic, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, an image of signals (e.g., spectrograms, phasograms, scalograms, etc.), combinations thereof, portions thereof, and the like.

In an embodiment, the tag recommender 130 is configured to send the multimedia content element to be tagged to the signature generator system 140, to the deep content classification system 160, or both. In a further embodiment, the tag recommender 130 is configured to receive a plurality of signatures generated to the multimedia content element from the signature generator system 140, to receive a plurality of signatures (e.g., signature reduced clusters) of concepts matched to the multimedia content element from the deep content classification system 160, or both. In another embodiment, the tag recommender 130 may be configured to generate the plurality of signatures, identify the plurality of signatures (e.g., by determining concepts associated with the signature reduced clusters matching the multimedia content element to be tagged), or a combination thereof.

Each signature represents a concept, and may be robust to noise and distortion. Each concept is a collection of signatures representing multimedia content elements and metadata describing the concept, and acts as an abstract description of the content to which the signature was generated. As a non-limiting example, a ‘Superman concept’ is a signature-reduced cluster of signatures describing elements (such as multimedia elements) related to, e.g., a Superman cartoon: a set of metadata representing proving textual representation of the Superman concept. As another example, metadata of a concept represented by the signature generated for a picture showing a bouquet of red roses is “flowers”. As yet another example, metadata of a concept represented by the signature generated for a picture showing a bouquet of wilted roses is “wilted flowers”.

In an embodiment, the tag recommender 130 is configured to correlate among the received signatures of the multimedia content element to be tagged and to determine, based on the correlation, at least one context of the multimedia content element. Each context is determined by correlating among the plurality of signatures of the multimedia content element. A context is determined as the correlation between a plurality of concepts. A strong context may be determined, e.g., when there are at least a threshold number of concepts that satisfy the same predefined condition. As a non-limiting example, by correlating a signature of a person in a baseball uniform with a signature of a baseball stadium, a context representing a “baseball player” may be determined. Correlations among the concepts of a plurality of multimedia content elements can be achieved using probabilistic models by, e.g., identifying a ratio between signatures' sizes, a spatial location of each signature, and the like. Determining contexts for multimedia content elements is described further in the above-referenced U.S. patent application Ser. No. 13/770,603.

It should be noted that using signatures for determining the context ensures more accurate identification of trending multimedia content than, for example, based on metadata alone.

In an embodiment, the tag recommender 130 is configured to search for at least one contextually related multimedia content element based on the determined at least one context. To this end, in a further embodiment, the tag recommender 130 is configured to search through the data sources 170. The data sources 170 may include, but are not limited to, a search engine, a content provider server, a vertical comparison engine, a content publisher server, a mobile application installed on the user device, a social network, a content website, or any other storage including multimedia content elements and associated tags.

In an embodiment, the tag recommender 130 is configured to generate at least one query, where the search is performed using the at least one query. Each query may include, but is not limited to, a textual representation of the determined at least one context of the multimedia content element to be tagged. In a further embodiment, generating the query may include identifying text associated with the determined at least one context in, e.g., the database 150. In yet a further embodiment, the tag recommender 130 may be configured to customize each query with respect to a type of data source (e.g., a social media network, an image or video repository, a forum, etc.) or with respect to a particular data source (e.g., Facebook®, Instagram®, Twitter®, Youtube®, etc.) to which the query will be sent. The queries may be customized such that, for example, each query is in a format that is acceptable to or optimized for the data sources 170 to which the query will be sent.

In an embodiment, the tag recommender 130 is configured to generate the at least one query by identifying concepts matching the determined at least one context (e.g., concepts stored in the database 150 that represent previously determined contexts), where the textual representation of the context includes text of metadata of the identified concepts (i.e., metadata representing the identified concepts). In a further embodiment, the tag recommender 130 is configured to search the database 150 for previously determined contexts matching the determined at least one context of the multimedia content element to be tagged, where the identified concepts represent the matching contexts.

In an embodiment, the tag recommender 130 is configured to generate a recommendation of tags for the multimedia content element. The recommendation may include, but is not limited to, the tags found during the search or a group of tags selected from among the tags found during the search. The tags may be, but are not limited to, textual or graphical inputs that are associated with multimedia content elements The tags may be, for example, hashtags (e.g., “#vacation”).

In a further embodiment, the tag recommender 130 may be configured to select the tags to be included in the recommendation based on, for example, a trendiness of each tag (i.e., such that each selected tag is a trending tag). In yet a further embodiment, the trendiness of a tag may be determined based on a number of uses of the tag in the data sources 170 (e.g., a number of posts by users including the tag), positive feedback related to the tag (e.g., a number of likes or comments including known positive language associated with a multimedia content element having the tag), both, and the like.

In another embodiment, the selected tags may exclude duplicates of selected tags (e.g., tags matching a selected tag above a predetermined threshold such as, for example, tags that differ by fewer than 3 characters). In a further embodiment, identifying duplicate tags may include generating signatures to the found tags and comparing the generated tag signatures, where tags having signature matching above a predetermined threshold are identified as duplicates.

In an embodiment, the tag recommender 130 is configured to send the generated recommendation to, e.g., the user device 120. The user of the user device 120 may review the recommended tags and may tag the multimedia content element with the recommended tags, may modify any of the recommended tags, and the like. In another embodiment, the tag recommender 130 is configured to store the recommended tags in, e.g., one or more of the data sources 170.

As a non-limiting example, an image in which a plurality of people are shown wearing green shirts, smiling and raising a toast is received by the tag recommender 130 from the user device 120. The image is sent to the signature generator generator system 140, the deep content classification system 160, or both, and a plurality of signatures are received. The received signatures represent concepts such as “people”, “party”, “drinks”, and “green shirts”. The signatures are then correlated and the context is determined as “friends drinking with green shirts”. A query of “friends drinking with green shirts and Mar. 17, 2016” is generated. According to an embodiment, the query may customized respective of a type of data source 170 through which the search is performed, i.e., different queries shall be sent to the Facebook® website and to the Instagram® application program. The search result may indicate that a popular tag associated with the query is “#HappySaintPatrickDay,” i.e., a tag indicating a feast of a religious and cultural celebration which often involves people drinking beers wearing green shirts and other Irish symbols. A recommendation including the “#HappySaintPatrickDay” tag is provided by the tag recommender 130 to the user device 120.

It should be noted that only one user device 120 and one application 125 are described herein above with reference to FIG. 1 merely for the sake of simplicity and without limitation on the disclosed embodiments. Multiple user devices may provide multimedia content elements via multiple applications 125, and tags for each multimedia content element may be recommended to the sending user device, without departing from the scope of the disclosure.

FIG. 2 depicts an example flowchart 200 illustrating a method for recommending tags for a multimedia content element according to an embodiment. In an embodiment, the method may be performed by the tag recommender 130.

At S210, a multimedia content element to be tagged is obtained. In an embodiment, S210 may include receiving a request including the multimedia content element to be tagged. The request may further include one or more potential tags received from a user device. The request may be received by the agent 125 installed on the user device 120.

At S220, a plurality of signatures is generated or obtained. The signatures are generated as described below with respect to FIGS. 4 and 5. The signatures may be robust to noise and distortion.

In an embodiment, S220 includes generating the signatures via a plurality of at least partially statistically independent computational cores, where the properties of each core are set independently of the properties of the other cores. In another embodiment, S220 includes sending the multimedia content element to a signature generator system, to a deep content classification system, or both, and receiving the plurality of signatures. The signature generator system includes a plurality of at least statistically independent computational cores as described further herein. The deep content classification system is configured to create concepts for a wide variety of multimedia content elements, automatically and in an unsupervised fashion.

At S230, a recommendation of at least one tag for the multimedia content element is generated. In an embodiment, S230 includes correlating between concepts of the signatures generated or obtained at S220 and determining, based on the correlations, at least one context of the multimedia content element. In a further embodiment, S230 also includes searching for the at least one tag based on the determined contexts. Generating recommendations of tags for multimedia content elements is described further herein below with respect to FIG. 3.

In an embodiment, the recommendation only includes found tags that match (e.g., above a predetermined threshold) the received potential tags. The matching may include comparing the tags, comparing signatures generated to the tags, and the like. Accordingly, the recommendation may be utilized to verify whether a proposed tag from a user is appropriate for the multimedia content element.

At S240, the generated recommendation is provided. Providing the generated recommendation may include, but is not limited to, sending the generated recommendation (e.g., to a user device), storing the generated recommendation in a storage, both, and the like.

In S250, it is checked whether additional received multimedia content elements are to be tagged, and if so, execution continues with S210; otherwise, execution terminates.

FIG. 3 depicts an example flowchart S230 illustrating a method for generating a recommendation of at least one tag for a multimedia content element according to an embodiment. In an embodiment, the method is performed based on a plurality of signatures representing concepts of the multimedia content element.

At S310, the signatures for the multimedia content element are correlated. In an embodiment, S310 includes correlating among the concepts of a plurality of multimedia content elements using probabilistic models by, e.g., identifying a ratio between signatures' sizes, a spatial location of each signature, and the like. In an embodiment, S310 may further include querying a DCC system with the signatures. The deep content classification system may be configured to identify and return at least one matching concept.

At S320, based on the correlation, at least one context of the multimedia content element is determined. A context is determined as the correlation between a plurality of concepts. A strong context may be determined, e.g., when there are at least a threshold number of concepts that satisfy the same predefined condition.

At S330, based on the at least one context, at least one tag is identified. In an embodiment, S330 includes searching through one or more data sources for multimedia content elements that are contextually related to the multimedia content element to be tagged. In an embodiment, the searching includes generating at least one query based on the context, where the at least one query is utilized during the search. In a further embodiment, the at least one query includes a textual representation of the determined at least one context. To this end, in yet a further embodiment, S330 may include searching in a context database for at least one matching context related to the determined context, where each context in the context database is represented by a concept having metadata including text representing the context. The text of the identified concept metadata may be included in the query. In another further embodiment, the queries may be customized for different data sources to be searched. Each query includes a textual representation of the at least one context or a portion thereof.

At optional S340, at least one tag may be selected from among the determined at least one tag. In an embodiment, the selection may be of at least one trendy tag. To this end, the selection may be based on, but not limited to, a number of mentions of each tag in social media posts, a number of inclusions of each tag in comments, a matching level between each tag and the determined at least one context, or a combination thereof. In another embodiment, the selection may result in excluding duplicate tags (e.g., tags that are identical or nearly identical as determined based on, for example, matching text, matching signatures, etc.). In an optional embodiment, only the selected tags may be included in a recommendation for the multimedia content element. Alternatively, the recommendation may include all tags found during the search.

FIGS. 4 and 5 illustrate the generation of signatures for the multimedia content elements by the SGS 140 according to one embodiment. An exemplary high-level description of the process for large scale matching is depicted in FIG. 4. In this example, the matching is for a video content.

Video content segments 2 from a Master database (DB) 6 and a Target DB 1 are processed in parallel by a large number of independent computational Cores 3 that constitute an architecture for generating the Signatures (hereinafter the “Architecture”). Further details on the computational Cores generation are provided below. The independent Cores 3 generate a database of Robust Signatures and Signatures 4 for Target content-segments 5 and a database of Robust Signatures and Signatures 7 for Master content-segments 8. An exemplary and non-limiting process of signature generation for an audio component is shown in detail in FIG. 4. Finally, Target Robust Signatures and/or Signatures are effectively matched, by a matching algorithm 9, to Master Robust Signatures and/or Signatures database to find all matches between the two databases.

To demonstrate an example of the signature generation process, it is assumed, merely for the sake of simplicity and without limitation on the generality of the disclosed embodiments, that the signatures are based on a single frame, leading to certain simplification of the computational cores generation. The Matching System is extensible for signatures generation capturing the dynamics in-between the frames. In an embodiment the server 130 is configured with a plurality of computational cores to perform matching between signatures.

The Signatures' generation process is now described with reference to FIG. 5. The first step in the process of signatures generation from a given speech-segment is to breakdown the speech-segment to K patches 14 of random length P and random position within the speech segment 12. The breakdown is performed by the patch generator component 21. The value of the number of patches K, random length P and random position parameters is determined based on optimization, considering the tradeoff between accuracy rate and the number of fast matches required in the flow process of the server 130 and SGS 140. Thereafter, all the K patches are injected in parallel into all computational Cores 3 to generate K response vectors 22, which are fed into a signature generator system 23 to produce a database of Robust Signatures and Signatures 4.

In order to generate Robust Signatures, i.e., Signatures that are robust to additive noise L (where L is an integer equal to or greater than 1) by the Computational Cores 3 a frame ‘i’ is injected into all the Cores 3. Then, Cores 3 generate two binary response vectors: {right arrow over (S)} which is a Signature vector, and {right arrow over (RS)} which is a Robust Signature vector.

For generation of signatures robust to additive noise, such as White-Gaussian-Noise, scratch, etc., but not robust to distortions, such as crop, shift and rotation, etc., a core Ci={n_i} (1≤i≤L) may consist of a single leaky integrate-to-threshold unit (LTU) node or more nodes. The node n_i equations are:

$V_i=\sum _j{w}_{\mathrm{ij}}{k}_j$ $n_i=\theta \left(\mathrm{Vi}-{\mathrm{Th}}_x\right)$

where, θ is a Heaviside step function; w_ij is a coupling node unit (CNU) between node i and image component j (for example, grayscale value of a certain pixel j); kj is an image component ‘j’ (for example, grayscale value of a certain pixel j); Th_X is a constant Threshold value, where ‘x’ is ‘S’ for Signature and ‘RS’ for Robust Signature; and Vi is a Coupling Node Value.

The Threshold values Th_X are set differently for Signature generation and for Robust Signature generation. For example, for a certain distribution of Vi values (for the set of nodes), the thresholds for Signature (Th_S) and Robust Signature (Th_RS) are set apart, after optimization, according to at least one or more of the following criteria:

1: For: V_i>Th_RS 1−p(V>Th_S)−1−(1−ε)^l<<1i.e., given that/nodes (cores) constitute a Robust Signature of a certain image I, the probability that not all of these I nodes will belong to the Signature of same, but noisy image, Ĩ is sufficiently low (according to a system's specified accuracy).

2: p(V_i>Th_RS)≈l/L

i.e., approximately/out of the total L nodes can be found to generate a Robust Signature according to the above definition.

3: Both Robust Signature and Signature are generated for certain frame i.

It should be understood that the generation of a signature is unidirectional, and typically yields lossless compression, where the characteristics of the compressed data are maintained but the uncompressed data cannot be reconstructed. Therefore, a signature can be used for the purpose of comparison to another signature without the need of comparison to the original data. The detailed description of the Signature generation can be found in U.S. Pat. Nos. 8,326,775 and 8,312,031, assigned to the common assignee, which are hereby incorporated by reference.

A Computational Core generation is a process of definition, selection, and tuning of the parameters of the cores for a certain realization in a specific system and application. The process is based on several design considerations, such as:

(a) The Cores should be designed so as to obtain maximal independence, i.e., the projection from a signal space should generate a maximal pair-wise distance between any two cores' projections into a high-dimensional space.

(b) The Cores should be optimally designed for the type of signals, i.e., the Cores should be maximally sensitive to the spatio-temporal structure of the injected signal, for example, and in particular, sensitive to local correlations in time and space. Thus, in some cases a core represents a dynamic system, such as in state space, phase space, edge of chaos, etc., which is uniquely used herein to exploit their maximal computational power.

(c) The Cores should be optimally designed with regard to invariance to a set of signal distortions, of interest in relevant applications.

A detailed description of the Computational Core generation and the process for configuring such cores is discussed in more detail in the co-pending U.S. patent application Ser. No. 12/084,150 referenced above.

FIG. 6 is an example block diagram of the trending content recommendation generator 130 according to an embodiment. The trending content recommendation generator 130 includes a processing circuitry 610 coupled to a memory 620, a storage 630, and a network interface 640. In an embodiment, the components of the trending content recommendation generator 130 may be communicatively connected via a bus 650.

The processing circuitry 610 may be realized as one or more hardware logic components and circuits. For example, and without limitation, illustrative types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), Application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), general-purpose microprocessors, microcontrollers, digital signal processors (DSPs), and the like, or any other hardware logic components that can perform calculations or other manipulations of information. In an embodiment, the processing circuitry 610 may be realized as an array of at least partially statistically independent computational cores. The properties of each computational core are set independently of those of each other core, as described further herein above.

The memory 620 may be volatile (e.g., RAM, etc.), non-volatile (e.g., ROM, flash memory, etc.), or a combination thereof. In one configuration, computer readable instructions to implement one or more embodiments disclosed herein may be stored in the storage 630.

In another embodiment, the memory 620 is configured to store software. Software shall be construed broadly to mean any type of instructions, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Instructions may include code (e.g., in source code format, binary code format, executable code format, or any other suitable format of code). The instructions, when executed by the processing circuitry 610, cause the processing circuitry 610 to perform the various processes described herein. Specifically, the instructions, when executed, cause the processing circuitry 610 to provide recommendations of trending content based on context as described herein.

The storage 630 may be magnetic storage, optical storage, and the like, and may be realized, for example, as flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVDs), or any other medium which can be used to store the desired information.

The network interface 640 allows the trending content recommendation generator 130 to communicate with the signature generator system 140 for the purpose of, for example, sending multimedia content elements, receiving signatures, and the like. Further, the network interface 640 allows the trending content recommendation generator to communicate with the user device 120 for the purpose of, for example, receiving queries, sending recommendations of content, and the like. Additionally, the network interface 640 allows the trending content recommendation generator 130 to communicate with the data sources 170 in order to search for multimedia content elements.

It should be understood that the embodiments described herein are not limited to the specific architecture illustrated in FIG. 6, and other architectures may be equally used without departing from the scope of the disclosed embodiments. In particular, the trending content recommendation generator 130 may further include a signature generator system configured to generate signatures as described herein without departing from the scope of the disclosed embodiments.

The various embodiments disclosed herein can be implemented as hardware, firmware, software, or any combination thereof. Moreover, the software is preferably implemented as an application program tangibly embodied on a program storage unit or computer readable medium consisting of parts, or of certain devices and/or a combination of devices. The application program may be uploaded to, and executed by, a machine comprising any suitable architecture. Preferably, the machine is implemented on a computer platform having hardware such as one or more central processing units (“CPUs”), a memory, and input/output interfaces. The computer platform may also include an operating system and microinstruction code. The various processes and functions described herein may be either part of the microinstruction code or part of the application program, or any combination thereof, which may be executed by a CPU, whether or not such a computer or processor is explicitly shown. In addition, various other peripheral units may be connected to the computer platform such as an additional data storage unit and a printing unit. Furthermore, a non-transitory computer readable medium is any computer readable medium except for a transitory propagating signal.

All examples and conditional language recited herein are intended for pedagogical purposes to aid the reader in understanding the disclosed embodiments and the concepts contributed by the inventor to furthering the art, and are to be construed as being without limitation to such specifically recited examples and conditions. Moreover, all statements herein reciting principles, aspects, and embodiments of the invention, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future, i.e., any elements developed that perform the same function, regardless of structure.

It should be understood that any reference to an element herein using a designation such as “first,” “second,” and so forth does not generally limit the quantity or order of those elements. Rather, these designations are generally used herein as a convenient method of distinguishing between two or more elements or instances of an element. Thus, a reference to first and second elements does not mean that only two elements may be employed there or that the first element must precede the second element in some manner. Also, unless stated otherwise, a set of elements comprises one or more elements.

As used herein, the phrase “at least one of” followed by a listing of items means that any of the listed items can be utilized individually, or any combination of two or more of the listed items can be utilized. For example, if a system is described as including “at least one of A, B, and C,” the system can include A alone; B alone; C alone; A and B in combination; B and C in combination; A and C in combination; or A, B, and C in combination.

Claims

1. A method for recommending tags for a multimedia content element to be tagged, comprising: obtaining a plurality of signatures for the multimedia content element to be tagged, wherein each of the plurality of represents a concept, wherein each concept is a collection of signatures and metadata representing the concept;correlating between the plurality of signatures to determine at least one context of the multimedia content element to be tagged;searching for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context;identifying at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; andgenerating a recommendation including the identified at least one tag.

2. The method of claim 1, wherein obtaining the plurality of signatures further comprises: generating, by a signature generator system, the plurality of signatures for the multimedia content element, wherein the signature generator system includes a plurality of at least partially statistically independent computational cores, wherein the properties of each core are set independently of the properties of each other core.

3. The method of claim 1, wherein searching for the at least one contextually related multimedia content element further comprises: generating, based on the determined at least one context, at least one query, wherein the search is based on the at least one query.

4. The method of claim 3, wherein the at least one query includes a textual representation of the at least one context.

5. The method of claim 1, wherein identifying the at least one tag further comprising: determining at least one trendy tag from among tags associated with the at least one contextually related multimedia content element, wherein the identified at least one tag is the determined at least one trendy tag.

6. The method of claim 5, wherein determining the at least one trendy tag further comprises at least one of: calculating a number of mentions of each tag associated with the at least one contextually related multimedia content element, and analyzing comments including each tag associated with the at least one contextually related multimedia content element.

7. The method of claim 1, further comprising at least one of: sending the generated recommendation to a user device, and storing the generated recommendation in a storage.

8. The method of claim 1, wherein obtaining the plurality of signatures further comprises: sending, to a deep content classification system, the multimedia content element to be tagged, wherein the deep content classification system is configured to create concepts for a wide variety of multimedia content elements; andreceiving, from the deep content classification system, the plurality of signatures, wherein the plurality of signatures includes signature reduced clusters representing concepts related to the multimedia content element to be tagged.

9. The method of claim 1, wherein the context is determined as the correlation between a plurality of concepts represented by the obtained plurality of signatures.

10. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising: obtaining a plurality of signatures for the multimedia content element to be tagged, wherein each of the generated signatures represents a concept, wherein each concept is a collection of signatures and metadata representing the concept;correlating between the plurality of signatures to determine at least one context of the multimedia content element to be tagged;searching for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context;identifying at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; and

11. A system for recommending tags for a multimedia content element to be tagged, comprising: a processing circuitry; anda memory connected to the processing circuitry, the memory containing instructions that, when executed by the processing circuitry; configure the system to:obtain a plurality of signatures for the multimedia content element to be tagged, wherein each of the generated signatures represents a concept, wherein each concept is a collection of signatures and metadata representing the concept;correlate between the plurality of signatures to determine at least one context of the multimedia content element to be tagged;search for at least one contextually related multimedia content element, wherein each contextually related multimedia content element matches at least one of the determined at least one context;identify at least one tag, wherein each identified tag is associated with at least one of the at least one contextually related multimedia content element; andgenerate a recommendation including the identified at least one tag.

12. The system of claim 11, further comprising: a signature generator system including a plurality of at least partially statistically independent computational cores, wherein the properties of each core are set independently of the properties of each other core, wherein the system is further configured to: generate, by the signature generator system, the plurality of signatures for the multimedia content element.

13. The system of claim 11, wherein the system is further configured to: generate, based on the determined at least one context, at least one query, wherein the search is based on the at least one query.

14. The system of claim 13, wherein the at least one query includes a textual representation of the at least one context.

15. The system of claim 11, wherein the system is further configured to: determine at least one trendy tag from among tags associated with the at least one contextually related multimedia content element, wherein the identified at least one tag is the determined at least one trendy tag.

16. The system of claim 15, wherein the system is further configured to perform at least one of: calculate a number of mentions of each tag associated with the at least one contextually related multimedia content element, and analyze comments including each tag associated with the at least one contextually related multimedia content element.

17. The system of claim 11, wherein the system is further configured to perform at least one of: send the generated recommendation to a user device, and store the generated recommendation in a storage.

18. The system of claim 11, wherein the system is further configured to: send, to a deep content classification system, the multimedia content element to be tagged, wherein the deep content classification system is configured to create concepts for a wide variety of multimedia content elements; andreceive, from the deep content classification system, the plurality of signatures, wherein the plurality of signatures includes signature reduced clusters representing concepts related to the multimedia content element to be tagged.

19. The system of claim 11, wherein the context is determined as the correlation between a plurality of concepts represented by the obtained plurality of signatures.