System and method for generating analytics for entities depicted in multimedia content

Abstract

A system and method for generating analytics for entities depicted in multimedia content, including: identifying at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to a predetermined social pattern threshold, wherein each social linking score is generated based on contexts of at least one multimedia content element (MMCE) in which at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold; and generating, based on the identified at least one social pattern, analytics for the plurality of entities depicted in the social linking graph.

Description

TECHNICAL FIELD

The present disclosure relates generally to contextual analysis of multimedia content elements, and more specifically to identifying patterns from entities depicted in multimedia content based on the contextual analysis of multimedia content.

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. Often, individuals wish to identify persons captured in images, videos and other content, as well as identify relationships between various identified persons.

Some people manually tag multimedia content in order to indicate the persons shown in images and videos in an effort to assists users seeking content featuring the persons to view the tagged content. The tags may be textual or include other identifiers 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 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 increase the likelihood of a successful search for 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, including individuals presented within the 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.

Additionally, tagging often fails to demonstrate certain analytics, such as relationships between subjects within one or multiple multimedia content items. For example, a set of images showing two individuals may appear on a user profile of a social media account, but the social media platform may be unaware of the relationship between the two individuals. Further, it may be difficult to visualize the relationship among a larger group of individuals based on multimedia content items when relying on manual tagging to identify subjects within the multimedia content item or to determine underlying patterns among the relationships between the individuals.

It would therefore be advantageous to provide a solution that would overcome the challenges noted above.

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” may be used herein to refer to a single embodiment or multiple embodiments of the disclosure.

Certain embodiments disclosed herein include a method for generating analytics for entities depicted in multimedia content, including: identifying at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to a predetermined social pattern threshold, wherein each social linking score is generated based on contexts of at least one multimedia content element (MMCE) in which at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold; and generating, based on the identified at least one social pattern, analytics for the plurality of entities depicted in the social linking graph.

Certain embodiments disclosed herein also include a non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process, the process including: identifying at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to a predetermined social pattern threshold, wherein each social linking score is generated based on contexts of at least one multimedia content element (MMCE) in which at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold; and generating, based on the identified at least one social pattern, analytics for the plurality of entities depicted in the social linking graph.

Certain embodiments disclosed herein also include a system for generating analytics for entities depicted in multimedia content, including a processing circuitry; and a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to: identify at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to a predetermined social pattern threshold, wherein each social linking score is generated based on contexts of at least one multimedia content element (MMCE) in which at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold; and generate, based on the identified at least one social pattern, analytics for the plurality of entities depicted in the social linking graph.

BRIEF DESCRIPTION OF THE DRAWINGS

The subject matter disclosed herein 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 an example network diagram utilized for describing certain embodiment of the system for determining a social relativeness between entities.

FIG. 2 is an example diagram of a Deep Content Classification system for creating concepts according to an embodiment.

FIG. 3 is a block diagram depicting the basic flow of information in the signature generator system.

FIG. 4 is a diagram showing the flow of patches generation, response vector generation, and signature generation in a large-scale speech-to-text system.

FIG. 5 is a flowchart of a method for generating social linking scores for persons shown in multimedia content elements according to an embodiment.

FIG. 6 is a flowchart illustrating a method of analyzing an MMCE according to an embodiment.

FIG. 7 is a flowchart illustrating a method of generating a social linking score in an embodiment.

FIG. 8 is an example diagram of a social linking graph in an embodiment.

FIG. 9 is a flowchart illustrating a method of generating analytics based on social patterns according to an embodiment.

FIG. 10 is an example diagram of a social linking graph indicating groupings based on analytics in 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 embodiments. 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.

The various disclosed embodiments include a method and system for analyzing multimedia content elements and generating social linking scores of individuals represented in the multimedia content items. Signatures are generated for each multimedia content element. Based on the generated signatures, one or more individuals shown in the multimedia content element are identified.

One or more contexts are generated based on the generated signatures. Based on the generated context and associated metadata, a social linking score is generated for each person shown in the multimedia content element. The generated social linking score may be based on, for example, an amount of multimedia content elements in which a person is shown, a time stamp associated with a first appearance in a multimedia content element, a time stamp associated with a last appearance in a multimedia content element, physical interaction with the user in the multimedia content elements (e.g., kissing, hugging, shaking hands, etc.), a location coordinate identified based on the analysis, other persons identified therein, tags, comments, and the like. In an embodiment, a social linking graph is generated based on the generated scores.

FIG. 1 is an example network diagram 100 utilized for describing certain embodiments disclosed herein. A user device 120, a database (DB) 130, a server 140, a signature generator system (SGS) 150, and a Deep Content Classification (DCC) system 160 are connected to a network 110. The network 110 may be, but is not limited to, a local area network (LAN), a wide area network (WAN), a metro area network (MAN), the world wide web (WWW), the Internet, a wired network, a wireless network, and the like, as well as any combination thereof.

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 devices capable of capturing, uploading, browsing, viewing, listening, filtering, and managing multimedia content elements 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 downloaded from an application repository, such as the AppStore®, Google Play®, or any repositories hosting software applications. The application 125 may be pre-installed in the user device 120.

The application 125 may be configured to store and access multimedia content elements within the user device, such as on an internal storage (not shown), as well as to access multimedia content elements from an external source, such as the database or a social media website. 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 thereto.

The database 130 is configured to store MMCEs, signatures generated based on MMCEs, concepts that have been generated based on signatures, contexts that have been generated based on concepts, social linking scores, social linking graphs, or a combination thereof. The database 130 is accessible by the server 140, either via the network 110 (as shown in FIG. 1) or directly (not shown).

The server 140 is configured to communicate with the user device 120 via the network 110. The server 140 may include a processing circuitry such as a processing circuitry and a memory (both not shown). The processing circuitry 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 memory 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 one or more processors, cause the processing circuitry to perform the various processes described herein. Specifically, the instructions, when executed, configure the processing circuitry to determine social linking scores, as discussed further herein below.

In an embodiment, the server 140 is configured to access to a plurality of multimedia content elements (MMCEs), for example, from the user device 120 via the application 125 installed thereon, that are associated with a user of the user device 120. The MMCEs may be, for example, an image, a graphic, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, and/or combinations thereof and portions thereof. The MMCEs may be captured by a sensor (not shown) of the user device 120. The sensor may be, for example, a still camera, a video camera, a combination thereof, etc. Alternatively, the MMCEs may be accessed from a web source over the network 110, such as a social media website, or from the database 140.

The server 140 is configured to analyze the plurality of MMCEs and generate signatures based on each of the MMCEs. In an embodiment, the MMCEs are sent to the SGS 150 over the network 110. In an embodiment, the SGS 150 is configured to generate at least on signature for each MMCE, based on content of the received MMCE as further described herein. The signatures may be robust to noise and distortion as discussed below.

According to further embodiment, the server 140 may further be configured to identify metadata associated with each of the MMCEs. The metadata may include, for example, a time stamp of the capturing of the MMCE, the device used for the capturing, a location pointer, tags or comments, and the like.

The Deep Content Classification (DCC) system 160 is configured to identify at least one concept based on the generated signatures. Each concept is a collection of signatures representing MMCEs 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”.

The server 140 is further configured to generate one or more contexts for each MMCE in which a person is shown. Each context is determined by correlating among the signatures, the concepts, or both. 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 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, assigned to the common assignee, which is hereby incorporated by reference. It should be noted that using signatures for determining the context ensures more accurate reorganization of multimedia content than, for example, when using metadata.

Based on the generated contexts and associated metadata, or both, the server 140 is configured to generate a social linking score associated with each person depicted in the MMCEs. The social linking score is a value representing the social relativeness of two or more entities, where the social relativeness indicates how close the entities are within a social sphere. The entities may include, but are not limited to, people. As a non-limiting example, upon identifying a certain person as the user's son, the social linking score shall be higher than, for example, a colleague of the user. The generation of the social linking score is further described herein below with respect to FIG. 7.

In an embodiment, based on the social linking scores, the server 140 is configured to generate a social linking graph representative of the persons shown in the MMCEs and their respective social linking scores. An example of the social linking graph is shown herein below in FIG. 8. In a further embodiment, the server 140 is configured to generate analytics based on the social linking scores, the social linking graphs, the MMCEs, combinations thereof, portions thereof, and the like. Analytics may include, but are not limited to, a social relationship and social status between two or more entities.

It should be noted that only one user device 120 and one application 125 are discussed with reference to FIG. 1 merely for the sake of simplicity. However, the embodiments disclosed herein are applicable to a plurality of user devices that can communicate with the server 130 via the network 110, where each user device includes at least one application.

FIG. 2 shows an example diagram of a DCC system 160 for creating concepts. The DCC system 160 is configured to receive a first MMCE and at least a second MMCE, for example from the server 140 via a network interface 260.

The MMCEs are processed by a patch attention processor (PAP) 210, resulting in a plurality of patches that are of specific interest, or otherwise of higher interest than other patches. A more general pattern extraction, such as an attention processor (AP) (not shown) may also be used in lieu of patches. The AP receives the MMCE that is partitioned into items; an item may be an extracted pattern or a patch, or any other applicable partition depending on the type of the MMCE. The functions of the PAP 210 are described herein below in more detail.

The patches that are of higher interest are then used by a signature generator, e.g., the SGS 150 of FIG. 1, to generate signatures based on the patch. A clustering processor (CP) 230 inter-matches the generated signatures once it determines that there are a number of patches that are above a predefined threshold. The threshold may be defined to be large enough to enable proper and meaningful clustering. With a plurality of clusters, a process of clustering reduction takes place so as to extract the most useful data about the cluster and keep it at an optimal size to produce meaningful results. The process of cluster reduction is continuous. When new signatures are provided after the initial phase of the operation of the CP 230, the new signatures may be immediately checked against the reduced clusters to save on the operation of the CP 230. A more detailed description of the operation of the CP 230 is provided herein below.

A concept generator (CG) 240 is configured to create concept structures (hereinafter referred to as concepts) from the reduced clusters provided by the CP 230. Each concept comprises a plurality of metadata associated with the reduced clusters. The result is a compact representation of a concept that can now be easily compared against a MMCE to determine if the received MMCE matches a concept stored, for example, in the database 130 of FIG. 1. This can be done, for example and without limitation, by providing a query to the DCC system 160 for finding a match between a concept and a MMCE.

It should be appreciated that the DCC system 160 can generate a number of concepts significantly smaller than the number of MMCEs. For example, if one billion (10⁹) MMCEs need to be checked for a match against another one billon MMCEs, typically the result is that no less than 10⁹×10⁹=10¹⁸ matches have to take place. The DCC system 160 would typically have around 10 million concepts or less, and therefore at most only 2×10⁶×10⁹=2×10¹⁵ comparisons need to take place, a mere 0.2% of the number of matches that have had to be made by other solutions. As the number of concepts grows significantly slower than the number of MMCEs, the advantages of the DCC system 160 would be apparent to one with ordinary skill in the art.

FIGS. 3 and 4 illustrate the generation of signatures for the multimedia content elements by the SGS 150 according to an embodiment. An example high-level description of the process for large scale matching is depicted in FIG. 3. 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. 4. 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 140 and SGS 150. 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); Thx 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 Thx 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 l 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/Li.e., approximately l 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. No. 8,326,775, assigned to the common assignee, which is 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 U.S. Pat. No. 8,655,801 referenced above, the contents of which are incorporated by reference.

Signatures are generated by the Signature Generator System based on patches received either from the PAP 210, or retrieved from the database 130, as discussed herein above. It should be noted that other ways for generating signatures may also be used for the purpose the DCC system 160. Furthermore, as noted above, the array of computational cores may be used by the PAP 210 for the purpose of determining if a patch has an entropy level that is of interest for signature generation according to the principles of the invention.

FIG. 5 illustrates a flowchart of a method 500 for generating social linking scores for persons shown in multimedia content elements according to an embodiment. In an embodiment, the method may be performed by the server 140, FIG. 1.

At S510, a plurality of MMCEs are received. At S520, the MMCEs are analyzed. In an embodiment, the analysis includes generating signatures, concepts, contexts, or a combination thereof, based on the received MMCEs as further described herein with respect to FIGS. 1 and 6.

At S530, a social linking score is generated for each person shown in the received MMCEs based on the analysis. Generating social linking scores is further described herein below with respect to FIG. 7.

At optional S540, a social linking graph is generated based on the generated social linking scores, where the social linking graph is a visual representation of the connections and relationship between persons identified within the received MMCEs. At optional S550, the social linking graph is sent to, for example, a user device (e.g., the user device 120, FIG. 1). At S560, it is checked whether additional MMCEs are to be analyzed and if so, execution continues with S520; otherwise, execution terminates.

FIG. 6 is a flowchart illustrating a method S520 of analyzing an MMCE according to an embodiment. At S610, at least one signature is generated for the MMCE, as described above with respect to FIG. 1, where signatures represent at least a portion of the MMCE. At S620, metadata associated with the MMCE is collected. The metadata may include, for example, a time stamp of the capturing of the MMCE, the device used for the capturing, a location pointer, tags or comments associated therewith, and the like.

At S630, based on the generated signatures and collected metadata, it is determined if at least one person is shown or depicted within the MMCE. If so, execution continues with S640; otherwise, execution terminates. In an embodiment, S630 includes comparing the generated signatures to reference signatures representing people, where it is determined that at least one person is shown when at least a portion of the generated signatures matches the reference signatures above a predetermined threshold.

At S640, when it is determined that a person is depicted in the MMCE, concepts are generated, where a concept is a collection of signatures representing elements of the unstructured data and metadata describing the concept. Each generated concept represents a person depicted in the MMCE. At S650, a context is generated based on correlation between the generated concepts. A context is determined as the correlation between a plurality of concepts.

FIG. 7 is a flowchart illustrating a method S530 of generating a social linking score in an embodiment. At S710, the generated context of each MMCE having a person shown therein is analyzed. At S720, metadata associated with the MMCEs is identified. At S730, based on the generated context and the identified metadata, the social relativeness between two or more persons shown in each MMCE and the user is determined. At S740, a social linking score is generated based on the social relativeness determination, and execution terminates. Each social linking score represents a closeness between two persons. For example, family members may have a higher social linking score than friends or acquaintances.

The generated social linking score may be based on, for example, an amount of multimedia content elements in which a person is shown, a time stamp associated with a first appearance in a multimedia content element, a time stamp associated with a last appearance in a multimedia content element, physical interaction with the user in the multimedia content elements (e.g., kissing, hugging, shaking hands, etc.), a location coordinate identified based on the analysis, other persons therein, tags and comments, a combination thereof, and the like.

In an embodiment, the social linking score may be determined based on weighted scoring. For example, if person A and person B only appear in one MMCE where they are kissing, while person A and person C appear in twenty MMCEs without physical contact, it may be determined that persons A and B are related or have a very close relationship, whereas persons A and C are not closely connected. Accordingly, the social linking score generated for persons A and B may be higher than the social linking score generated for persons B and C. In a further example, if persons A and D appear in an MMCE together where they are the only persons identified within the MMCE, and persons A and E appear together in large group picture, it may be determined that persons A and D have a closer relationship that persons A and E, and the social linking score generated for persons A and D may be higher than the social linking score generated for persons A and E.

FIG. 8 is an example diagram of a social linking graph 800 in an embodiment. The social linking graph 800 visually represents the social relativeness of each person shown in the MMCEs associated with the user of a user device, for example, the user device 120. Each circle 810 represents a person identified in the MMCEs. In an embodiment, lines 820 are shown extending between circles to represent connection between persons shown in the MMCEs. In some implementations, different colors, shading, line thickness, and other visual markers may be utilized to differentiate among individuals having higher social linking scores than individuals having lower social linking scores.

FIG. 9 is a flowchart illustrating a method 900 for generating analytics based on social patterns according to an embodiment. In an embodiment, the method may be performed by the server 140, FIG. 1.

At S910, a request is received to generate analytics. In some implementations, the request may be received from a user device.

At S920, a social linking graph is obtained. In an embodiment, the social linking graph is retrieved from a database, e.g., the database 130 of FIG. 1. The social linking graph indicates entities and social linking scores, where each entity is associated with social linking scores indicating the social relativeness between the entity and other entities of the social linking graph.

At S930, a social pattern is identified based on the social linking graph. The social pattern may be determined by analyzing the social linking graph, the social linking scores, MMCEs associated with the social linking graph, a combination thereof, a portion thereof, and the like. To this end, S930 may include determining whether one or more predetermined social pattern thresholds are met. The social pattern threshold may be, but is not limited to, a social linking score, number of connections, a number of MMCEs in which two or more of the same entities appear and the like.

The social pattern may include social characteristics such as connections between two or more entities, locations depicted in MMCEs, dates of MMCEs, number of MMCEs in which two or more of the same entities appear therein, number of MMCEs in which each of two entities appear therein with a third entity, a combination thereof, and the like. For example, a social pattern may indicate that person A and person B appear in at least 25 images together, where the location is determined to be an office building. In an embodiment, the MMCEs are embedded with location data, such as Global Positioning System (GPS) coordinates, which may be matched to a public mapping database to determine the location of the capture of an MMCE. The location data may be included in, e.g., metadata associated with the MMCEs.

At S940, analytics are generated based on the social pattern. Analytics may include a social relationship between entities such as, but not limited to, a familial relationship, a friend relationship, a professional relationship, and the like. The social relationship may be determined based on the social linking score between the entities, e.g., where a social linking score between two entities above a first predetermined threshold may indicate a professional relationship, a social linking score above a second predetermined threshold may indicate a friend relationship, and a social linking score above a third predetermined threshold may indicate a familial relationship.

In a further embodiment, the analytics may be further generated based on one or more demographic parameters, names, and the like, of each entity (e.g., demographic parameters indicated in social media profiles of the entities, stored in a database, etc.). As a non-limiting example, if last names of the entities match (e.g., the entities are named “John Smith” and Mary Smith”) and the social linking score is above a threshold, a familial relationship may be determined.

In another embodiment, signatures generated from MMCEs associated with the social linking graph may be utilized to identify objects that indicate a type of location in which the entities appear together, e.g., a couch indicating a home location and a desk with a computer indicating an office location. As a non-limiting example, if a social pattern indicates that person C and person D have a social linking score above 0.8, are depicted together in at least 25 images, wherein the majority of those images show a house, and the person C is at least 20 years older than person D, the analytics may be generated to indicate that person C is a parent of person D. In an embodiment, the generated analytics may be sent to a user device for display.

In a further embodiment, the analytics may include additional characteristics associated with the entities. Additional characteristics may include the hierarchy or position of a relationship, such as an older sibling and a younger sibling or an employer and employee. The additional characteristics may further include other shared information related to the relationship between the entities such as, but not limited to, same place of work, same positions of employment, sameworking groups, same location of residence, and the like. The additional characteristics may be determined based on the depicted ages of the entities within the MMCEs, dynamics displayed within the MMCEs (e.g., an older person behind a desk indicating an employer, and a younger person standing in front of the desk indicating an employee), and the like. In some implementations, the additional characteristics may be determined based further on the type of relationship. As a non-limiting example, ages may only be compared when a familial relationship is determined.

In some implementations, S940 may further include comparing signatures representing one entity to signatures representing another entity to determine whether there is a similarity in appearance among the entities. The signatures of each entity may include portions of signatures generated for MMCEs associated with the social linking graph showing the respective entities. For example, if the signatures of the two entities match above a predetermined threshold, a similarity in appearance may be determined. The analytics may be generated based further on any determined similarities in appearance. For example, when the social linking score between two entities is above a threshold and the entities demonstrate a similarity in appearance, a familial relationship may be determined.

At S950, it is checked if more patterns are to be identified from the social linking graph. If so, execution continues with S930; otherwise, execution terminates. In some implementations, execution continues until no more patterns are identified.

FIG. 10 is an example diagram illustrating the social linking graph 800 indicating groupings 1010 and 1020. The social linking graph 800 indicates entities 810 representing entities identified in MMCEs, and the groupings 1010 and 1020 indicate the entities demonstrating social patterns. An analysis of the social patterns enables the discovery of analytics, such as the type of relationship between two or more entities. In some implementations, differences in color, shading, line thickness, and other visual markers may be utilized to visually differentiate among the various groupings shown in the social linking graph 800.

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.

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.

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 principles of the disclosed embodiment 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 disclosed embodiments, 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.

Claims

1. A method for generating analytics for entities depicted in multimedia content, comprising: accessing, by a server and over a network, at least one multimedia content element (MMCE);identifying, by a server, at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to at least one predetermined social pattern threshold, wherein each social linking score is generated, by the server, based on contexts of the at least one MMCE, wherein in each of the at least one MMCE at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold;wherein the identifying at least one social pattern further comprises:determining the plurality of concepts for each MMCE by a deep content classification system, wherein each concept is a collection of signatures representing MMCEs and metadata describing the concept, wherein each context of each MMCE is determined by correlating among the determined plurality of concepts of the MMCE; and wherein the signatures are robust to noise and distortion; andgenerating, based on the identified at least one social pattern and by the server, analytics for the plurality of entities depicted in the social linking graph.

2. The method of claim 1, wherein the plurality of entities is identified in the at least one MMCE based on the signatures generated for the at least one MMCE.

3. The method of claim 1, wherein the at least one social pattern includes at least one of: connections among the plurality of entities, locations depicted in the at least one MMCE, dates associated with the at least one MMCE, a number of MMCEs of the at least one MMCE in which each set of two of the plurality of entities appear, and a number of MMCEs of the at least one MMCE in which each set of two entities of the plurality of entities appear with a third entity.

4. The method of claim 1, wherein the analytics include at least one social relationship between two of the plurality of entities.

5. The method of claim 4, further comprising: determining at least one additional characteristic of each social relationship, wherein the analytics further include the determined at least one additional characteristic of each social relationship, wherein each additional characteristic is determined based on at least one of: demographic parameters of the at least two entities, at least one identified object in the at least one MMCE, and comparison between signatures representing the at least two entities.

6. The method of claim 1, wherein each social linking score is generated based further on at least one of: a number of MMCEs in which the at least two entities are shown, a time stamp associated with a first appearance of one of the at least two entities in the at least one MMCE, a time stamp associated with a last appearance of one of the at least two entities in the at least one MMCE, a physical interaction between the at least two entities depicted in at least one of the at least one MMCE, a location coordinate associated with each of the at least one MMCE, other entities depicted in the at least one MMCE, and tags of the at least one MMCE.

7. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry of a server to perform a process, the process comprising: accessing over a network at least one multimedia content element (MMCE);identifying at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to at least one predetermined social pattern threshold, wherein each social linking score is generated based on contexts of the at least one MMCE, wherein in each of the at least one MMCE at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold;wherein the identifying at least one social pattern further comprises:determining the plurality of concepts for each MMCE by a deep content classification system, wherein each concept is a collection of signatures representing MMCEs and metadata describing the concept, wherein each context of each MMCE is determined by correlating among the determined plurality of concepts of the MMCE; and wherein the signatures are robust to noise and distortion;andgenerating, based on the identified at least one social pattern, analytics for the plurality of entities depicted in the social linking graph.

8. A server for determining a social relativeness between at least two entities depicted in at least one multimedia content element (MMCE), comprising: a processing circuitry; anda memory, the memory containing instructions that, when executed by the processing circuitry, configure the server to:access over a network at least one multimedia content element (MMCE);identify at least one social pattern based on social linking scores of a plurality of entities indicated in a social linking graph, wherein each social pattern is identified at least by comparing one of the social linking scores to at least one predetermined social pattern threshold, wherein each social linking score is generated based on contexts of the at least one MMCE, wherein in each of the at least one MMCE at least two of the plurality of entities are depicted, wherein each context is determined based on a plurality of concepts of one of the at least one MMCE, wherein each concept matches at least one signature generated for the at least one MMCE above a predetermined threshold;wherein the identifying at least one social pattern further comprises:determining the plurality of concepts for each MMCE by a deep content classification system, wherein each concept is a collection of signatures representing MMCEs and metadata describing the concept, wherein each context of each MMCE is determined by correlating among the determined plurality of concepts of the MMCE; and wherein the signatures are robust to noise and distortion; andgenerate, based on the identified at least one social pattern, analytics for the plurality of entities depicted in the social linking graph.

9. The server of claim 8, wherein the plurality of entities is identified in the at least one MMCE based on the signatures generated for the at least one MMCE.

10. The server of claim 8, wherein the at least one social pattern includes at least one of: connections among the plurality of entities, locations depicted in the at least one MMCE, dates associated with the at least one MMCE, a number of MMCEs of the at least one MMCE in which each set of two of the plurality of entities appear, and a number of MMCEs of the at least one MMCE in which each set of two entities of the plurality of entities appear with a third entity.

11. The server of claim 8, wherein the analytics include at least one social relationship between two of the plurality of entities.

12. The server of claim 11, that is configured to: determine at least one additional characteristic of each social relationship, wherein the analytics further include the determined at least one additional characteristic of each social relationship, wherein each additional characteristic is determined based on at least one of: demographic parameters of the at least two entities, at least one identified object in the at least one MMCE, and comparison between signatures representing the at least two entities.

13. The server of claim 8, that is configured to identify at least one social pattern by: determining the plurality of concepts for each MMCE, wherein each concept is a collection of signatures representing the content within the MMCE and metadata describing the concept, wherein each context of each MMCE is determined by correlating among the determined plurality of concepts of the MMCE.

14. The server of claim 8, wherein each social linking score is generated based further on at least one of: a number of MMCEs in which the at least two entities are shown, a time stamp associated with a first appearance of one of the at least two entities in the at least one MMCE, a time stamp associated with a last appearance of one of the at least two entities in the at least one MMCE, a physical interaction between the at least two entities depicted in at least one of the at least one MMCE, a location coordinate associated with each of the at least one MMCE, other entities depicted in the at least one MMCE, and tags of the at least one MMCE.

15. The method according to claim 1 comprising assigning a first social linking score to two of the plurality of entities when only the two of the plurality of entities appear together in the at least one MMCE; and assigning a second social linking score to the two of the plurality of entities when the two of the plurality of entities and additional entities appear together in the at least one MMCE; wherein the first social linking score is higher than the second social linking score.

16. The method according to claim 1 comprising assigning social linking score to two of the plurality of entities, the social linking score is based on (a) a number of the at least one MMCE, and (b) a physical interaction between the two of the plurality of entities that is captured in the at least one MMCE.

17. The method of claim 1, wherein the at least one social pattern includes locations depicted in the at least one MMCE.

18. The method according to claim 1 comprising assigning social linking score to two of the plurality of entities, the social linking score is based on whether the at least one MMCE captures a kissing of the two of the plurality of entities.

19. The method according to claim 1 wherein the accessing comprises accessing a user device to retrieve the at least one MMCE.