Patent Application
20130117375
The present invention relates generally to a method for granular tagging of multimedia content in a connected network, and more particularly, to a system that has an ability to add meaningful contextual and personalized information to the content in a granular fashion.
With the growth of connected infrastructure, social networking has become more ubiquitous in everyday lives. A large part of our lives is being dictated by online or otherwise accessible content, and how this content is influenced by the tools and the network that connect us. Recent examples include the changes in platforms like Facebook where they are using services like Spotify to deliver content to match people's preferences, partnership of Netflix with Facebook to make their content repository more ‘social’, Hulu's existing social media tools, and other similar services.
While the above attempts are steps towards making content more relevant for classification, these still don't address a few fundamental issues: (a) how to pin-point specific areas in a content (video or audio) file that could highlight the usefulness of the content in a particular context, (b) some indication of the “True” reactions of individuals, groups of individuals, or a large demography of people to a particular content, or a specific area of the content, (c) a method, or platform to make such granular tagging, rating, and search of content happen in a generic and scalable way.
In light of above, a method and a system for a scalable platform is provided that enables granular tagging of any multimedia or other web content over connected networks. The method of the invention provides an ability to go in much more granular within a content and enable a way to add meaningful contextual and personalized information to it, that could then be used in searching, classifying, or analyzing the particular content in a variety of ways, and in a variety of applications.
It is a primary object of the invention to provide a system for tagging the content based on the individual and personal cues of the users. One example of these cues is emotional profile or emotional score of the users.
It is a further object of the invention to provide a method for tagging a multimedia content in granular manner.
It is still a further object of the invention to provide a system that provides a uniform way of continuous and granular tagging of the multimedia content via individual cues, emotional profiles, or emotional scores.
A further and related object of the invention is to provide a method of tagging the content with an instantaneous Emotional Score, an instantaneous Emotional Profile, or an individual cues score based on a specific user's reaction and at a specific time stamp of the content.
Accordingly in an aspect of the present invention, a system for tagging multimedia content based on individual cues, emotional score or emotional profile is provided. The system comprises of a network of client devices having access to shared multimedia content in a cloud network. The client device has a module to continuously record the individual cues, emotional score or reaction of the user while viewing the content. The central database stores individual score related to individual cues, emotional score or profile of the entire user as a result of watching the content and in this manner tag the content.
In another aspect of present invention, a method for granular individual cues tagging or emotional tagging of multimedia content is provided. The method comprises of capturing a user's instantaneous reaction to the content by Emotion detection or individual cues detection module; generating an instantaneous emotional score or individual cues score with function of time; tagging the content with an instantaneous Emotional Score or individual cues score based on a specific user's reaction and at a specific time stamp of the content; characterize the content in a very granular manner; and sharing the granular tagging characteristics of the content in the network.
The invention will hereinafter be described in conjunction with the figures provided herein to further illustrate various non-limiting embodiments of the invention, wherein like designations denote like elements, and in which:
In the following detailed description of embodiments of the invention, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of invention. However, it will be obvious to a person skilled in art that the embodiments of invention may be practiced with or without these specific details. In other instances well known methods, procedures and components have not been described in details so as not to unnecessarily obscure aspects of the embodiments of the invention.
Furthermore, it will be clear that the invention is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions and equivalents will be apparent to those skilled in the art, without parting from the spirit and scope of the invention.
Nowadays with the increase in use of social networking and multimedia content repository, the content is rated based on the individuals liking and disliking of the content. Typically most rating and tagging of content are limited to the option whereby user manually enters the feedback either in form of “like” or in “dislike”. The present invention provides a system and method that includes individual's cues, emotional scores or profiles to tag a multimedia content in a granular manner. The system combines individual cues score, emotional profile or emotional score of the user in a social networking set up to make a more powerful impact on the user's consumption habit. The present invention further extends the concept of individual cues score, Emotional Score or Emotional Profile tagging of content to a more granular level within a specific content and provides a method and a system to achieve this process in a uniform way, including ways to use such tagging for various methods of analytics and monetization models. The inclusion of individual cues scores, Emotional Scores or Emotional Profiles adds a very unique behavioral aspect to content that may then be used for searching, analytics and various kinds of monetization models for the particular content. The individual cue scores, Emotional Score or Profile is a combination of the emotion, behavior, response, attention span, gestures, hand and head movement, or other reactions or stimuli of the user collected through the sensors available in the client devices and then processed.
In an embodiment of the present invention, the content A 108 tagged by the individual cues scores, Emotional Scores, or Emotional Profiles of a number of users may be used in multiple ways to increase the relevance of the content on an application specific, user specific, or delivery specific contexts.
In an embodiment of the present invention the client device 102 comprises of a single module or a plurality of modules to capture the input data from the individual, to process the input data for feature extraction and a decision phase for generating the profile of the user. Some examples of these input modules may be webcams, voice recorders, tactile sensors, haptic sensors, and any other kind of sensory modules.
In another embodiment of the present invention, the client devices 102, 112 and 116 include but is not limited to being a mobile phone, a Smartphone, a laptop, a camera with WiFi connectivity, a desktop, tablets (iPAD or iPAD like devices), connected desktops or other sensory devices with connectivity.
In another embodiment of the present invention, the individual cues score, emotional profile or emotional score corresponds to the emotion, behavior, response, attention span, gestures, hand and head movement, or other reactions or stimuli of the user.
In an embodiment of the present invention, the content 204 to be emotionally tagged is divided into a number of time segments, the segments being equally spaced. When the content 204 is tagged by the emotional score of a large number of users, the average emotional score for a particular time segment of the content 204 may be created. This in turn provides a unique way to classify different part of a TV show with very useful information about the user's reactions or Emotional Score tagged with respect to time segment of the TV show. In another embodiment of the present invention the tags may be individual cues of specific users that may include attention span, gestures, head and hand movements and other sensory inputs given by the users while watching a specific content.
In an embodiment of the present invention, the tagged information may be used in multiple ways to increase the relevance of the content on an application specific, user specific, or delivery specific contexts.
The interface 402 shows an output of the module that detects instantaneous reaction, individual cues score, or Emotional Score in a system of the invention. The interface 402 comprises of various regions that shows the outcome of the granular individual cues or emotional tagging of the multimedia content. The region 406 provides the details of video content that has been viewed by the user and is tagged thereafter. The region 406 provides the content details along with metadata that links the content to its source, and the rating given by the user with its intensity and the rating detected by the system through its module. The interface 402 shows the output to the Emotional Score generator module for a specific content (“Epic Chicken Burger Combo” (a YouTube video)).The user's reaction on watching this video is generated by the Emotion Detection module 104. The reaction may be based on a variety of sensors (webcam, voice recording, tactile or haptic sensors, or other sensory modules). The instantaneous Emotional Score of the user is generated as a function of time as shown in region 404. The time axis is synchronized with the time stamps of the content (“Epic Chicken Burger Combo”). The instantaneous score is the normalized Emotion displayed by the user and may have a number of different emotions at any given instance. The graph in the region 404 provides the users emotional score while viewing the content in a continuous granular manner with respect to different time segments. The interface 402 further comprises of region 408 that provides a D-graph displaying the average value of the emotional score of content 406 and a region 410 that displays a D-graph showing the peak values for the emotional score that has been generated while the user had watched the content 406.
In an embodiment of the present invention the intensity of the detected emotions vary from the range of 0 to 1 and the different types of emotions used to predict the behavior of the user may be one of 7. The detected emotional state includes Happy, Surprised, Fearful, Normal, Angry, Disgusted, and Sad.
In another embodiment or application, the different emotions may be a smaller subset and may have scores in a different scale. This provides a method of tagging the content with an instantaneous Emotional Score based on a specific user's reaction and at a specific time stamp of the content. Thus, a uniform way of continuous and granular Emotional tagging of any content may be done. In another embodiment of the present invention the tags may be individual cues scores instead of Emotional Scores. These individual cues may include attention span, gestures, head and hand movements and other sensory inputs given by the users while watching a specific content
In another embodiment of the present invention, the granular tagging of a variety of content may be done by a large number of users. The granular emotional tagging may then be used to provide a characteristic feature to large multimedia repositories that may then be used in a multiple ways to characterize the content in a very granular manner.
Once there is a uniform method of granular tagging of a content repository as described above, there are numerous applications of using the content tagged in the above fashion. Some of these applications are described below, and other related applications are readily apparent to one of skill in the art based on the ideas described herein.
In an exemplary embodiment of the present invention the granular emotional tagging of the multimedia content is used to identify the segment which is of concern to the users. The graph of emotional score with respect to time 404 on the reaction of content 406 being watched is used to identify the time segment of interest to the users. For instance, the different time segments of the content 306 are be analyzed to find out the scene of interest based on a query that asks to identify the segments of the video that have displayed the Emotion “Anger”>0.4. This brings out the two identified segments as shown in region 412. These kinds of queries may be generalized over a whole set of videos comprising a content repository like Netflix, or YouTube videos.
In another embodiment of the present invention, the system of the present invention is used to identify specific segments of videos that have displayed the highest time averaged specific Emotion (say, “Happy”), or specific segments from a repository that have scored (averaged over all users) a score of “Surprised>0.6”
The method of the present invention may be used to create Movie Trailers for audience based on some initial feedback from a focus group. The system may be used to pick a given set of segments with the same video of content that have scored, say “Happy>0.5”, averaged over all users, or all users in a specific age demography. The selected particular segment may be used to create a movie trailer.
