# US 8,572,097 B1 · Media content discovery and character organization techniques > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,572,097 B1 - Document ID: US8572097B1 - Status: Granted - Kind: B1 - Application number: 13/844,125 - Filed: 2013-03-15 - Granted: 2013-10-29 - Earliest claimed: 2013-03-15 - Applicants: FEM, Inc. - Inventors: Rachel Payne; Meghana Bhatt; Natasha Mohanty - Web page: https://patentgrep.com/patent/US8572097B1 ## CPC - G06F 16/435: Filtering based on additional data, e.g. user or group profiles - G06F 16/24578: {using ranking} - G06F 16/3334: {Selection or weighting of terms from queries, including natural language queries} - G06F 16/43: Querying - G06F 16/44: Browsing; Visualisation therefor - G06F 16/48: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually - G06F 16/7867: {using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings} - G06F 16/68: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually - G06F 16/78: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Techniques for recommending media are described. A character preference function comprising a plurality of preference coefficients is accessed. A first character model comprises a first set of attribute values for the plurality of attributes of a first character. The first and second characters are associated with a first and second salience value, respectively. A second character model comprises a second set of attribute values for the plurality of attributes of a second character of the plurality of characters. A first character rating is calculated using the plurality of preference coefficients and the first set of attribute values. A second character rating of the second character is calculated using the plurality of preference coefficients with the second set of attribute values. A media rating is calculated based on the first and second salience values and the first and second character ratings. A media is recommended based on the media rating. ## Claims ### Claim 1 A method implemented by a computer comprising at least one processor for recommending media content, the method comprising: accessing a set of salience values for a plurality of characters appearing in a media content, the set of salience values associated with the media content; accessing a character preference function of a user, the character preference function comprising information identifying a plurality of preference coefficients, each preference coefficient of the plurality of preference coefficients associated with at least one attribute of interest of a plurality of attributes; accessing a first character model, the first character model comprising information identifying a first set of attribute values for the plurality of attributes of a first character of the plurality of characters; calculating a first salience value of the set of salience values based on the on-screen time of the first character in the media content, wherein the first character is associated with the first salience value of the set of salience values; accessing a second character model, the second character model comprising information identifying a second set of attribute values for the plurality of attributes of a second character of the plurality of characters; calculating a second salience value of the set of salience values based on the on-screen time of the second character in the media content, wherein the second character is associated with the second salience value of the set of salience values; calculating a first character rating of the first character by performing a summation of the products of the plurality of preference coefficients with the first set of attribute values; calculating a second character rating of the second character by performing a summation of the products of the plurality of preference coefficients with the second set of attribute values; calculating a media content rating, the media content rating calculated based on the first salience value, the second salience value, the first character rating, and the second character rating; and recommending the media content to the user based on the media content rating. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: determining a total on-screen time value, the total on-screen time value determined by summing on-screen times of at least the first character in the media content and the second character in the media content; calculating the first salience value of the first character of the plurality of characters by dividing the on-screen time of the first character by the determined total on-screen time value; and calculating the second salience value of the second character of the plurality of characters by dividing the on-screen time of the second character by the determined total on-screen time value. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, further comprising: determining the first character model in part by: identifying textual content associated with the first character, the textual content contained in an electronic source; aggregating a plurality of attribute terms associated with the first character from the textual content; mapping at least some of the plurality of attribute terms to at least some of the plurality of attributes; and updating attribute values of the first character based on the plurality of attribute terms. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein each of the at least some of the plurality of attribute terms is associated with a corresponding strength value; and updating attribute values of the first character is based on the corresponding strength values. ### Claim 5 (depends on 3) The computer-implemented method of claim 3, further comprising: storing the updated attribute values of the first character in a database as a vector, the vector associated with the first character. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising: accessing a minimum content rating value; comparing the media content rating to the minimum content rating value, wherein the media content rating is numerical and the minimum content rating value is numerical; and determining the media content rating is greater than the minimum content rating value. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein: the character preference function is a second order function associating at least one of the plurality of preference coefficients with two or more attributes of interest of the plurality of attributes; calculating the first character rating of the first character further comprises determining the product of the at least one of the plurality of preference coefficients with each attribute value of the first set of attribute values of the two or more attributes of interest of the plurality of attributes; and calculating the second character rating of the second character further comprises determining the product of the at least one of the plurality of preference coefficients with each attribute value of the second set of attribute values of the two or more attributes of interest of the plurality of attributes. ### Claim 8 A non-transitory computer-readable storage medium comprising computer-executable instructions for recommending media content, the computer-executable instructions comprising instructions for: accessing a set of salience values for a plurality of characters appearing in a media content, the set of salience values associated with the media content; accessing a character preference function of a user, the character preference function comprising information identifying a plurality of preference coefficients, each preference coefficient of the plurality of preference coefficients associated with at least one attribute of interest of a plurality of attributes; accessing a first character model, the first character model comprising information identifying a first set of attribute values for the plurality of attributes of a first character of the plurality of characters; calculating a first salience value of the set of salience values based on the on-screen time of the first character in the media content, wherein the first character is associated with the first salience value of the set of salience values; accessing a second character model, the second character model comprising information identifying a second set of attribute values for the plurality of attributes of a second character of the plurality of characters; calculating a second salience value of the set of salience values based on the on-screen time of the second character in the media content, wherein the second character is associated with the second salience value of the set of salience values; calculating a first character rating of the first character by performing a summation of the products of the plurality of preference coefficients with the first set of attribute values; calculating a second character rating of the second character by performing a summation of the products of the plurality of preference coefficients with the second set of attribute values; calculating a media content rating, the media content rating calculated based on the first salience value, the second salience value, the first character rating, and the second character rating; and recommending the media content to the user based on the media content rating. ### Claim 9 (depends on 8) The non-transitory computer-readable storage medium of claim 8, further comprising instructions for: determining a total on-screen time value, the total on-screen time value determined by summing on-screen times of at least the first character in the media content and the second character in the media content; calculating the first salience value of the first character of the plurality of characters by dividing the on-screen time of the first character by the determined total on-screen time value; and calculating the second salience value of the second character of the plurality of characters by dividing the on-screen time of the second character by the determined total on-screen time value. ### Claim 10 (depends on 8) The non-transitory computer-readable storage medium of claim 8, further comprising instructions for: determining the first character model in part by: identifying textual content associated with the first character, the textual content contained in an electronic source; aggregating a plurality of attribute terms associated with the first character from the textual content; mapping at least some of the plurality of attribute terms to at least some of the plurality of attributes; and updating attribute values of the first character based on the plurality of attribute terms. ### Claim 11 (depends on 10) The non-transitory computer-readable storage medium of claim 10, wherein each of the at least some of the plurality of attribute terms is associated with a corresponding strength value; and updating attribute values of the first character is based on the corresponding strength values. ### Claim 12 (depends on 10) The non-transitory computer-readable storage medium of claim 10, further comprising instructions for: storing the updated attribute values of the first character in a database as a vector, the vector associated with the first character. ### Claim 13 (depends on 8) The non-transitory computer-readable storage medium of claim 8, further comprising instructions for: accessing a minimum content rating value; comparing the media content rating to the minimum content rating value, wherein the media content rating is numerical and the minimum content rating value is numerical; and determining the media content rating is greater than the minimum content rating value. ### Claim 14 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein: the character preference function is a second order function associating at least one of the plurality of preference coefficients with two or more attributes of interest of the plurality of attributes; calculating the first character rating of the first character further comprises determining the product of the at least one of the plurality of preference coefficients with each attribute value of the first set of attribute values of the two or more attributes of interest of the plurality of attributes; and calculating the second character rating of the second character further comprises determining the product of the at least one of the plurality of preference coefficients with each attribute value of the second set of attribute values of the two or more attributes of interest of the plurality of attributes. ### Claim 15 An apparatus for recommending media content, the apparatus comprising: a memory configured to a character preference function of a user; and one or more computer processors configured to: access a set of salience values for a plurality of characters appearing in a media content, the set of salience values associated with the media content; access the character preference function of a user, the character preference function comprising information identifying a plurality of preference coefficients, each preference coefficient of the plurality of preference coefficients associated with at least one attribute of interest of a plurality of attributes; access a first character model, the first character model comprising information identifying a first set of attribute values for the plurality of attributes of a first character of the plurality of characters; calculate a first salience value of the set of salience values based on the on-screen time of the first character in the media content, wherein the first character is associated with the first salience value of the set of salience values; access a second character model, the second character model comprising information identifying a second set of attribute values for the plurality of attributes of a second character of the plurality of characters; calculate a second salience value of the set of salience values based on the on-screen time of the second character in the media content, wherein the second character is associated with the second salience value of the set of salience values; calculate a first character rating of the first character by performing a summation of the products of the plurality of preference coefficients with the first set of attribute values; calculate a second character rating of the second character by performing a summation of the products of the plurality of preference coefficients with the second set of attribute values; calculate a media content rating, the media content rating calculated based on the first salience value, the second salience value, the first character rating, and the second character rating; and recommend the media content to the user based on the media content rating. ### Claim 16 (depends on 15) The apparatus of claim 15, the one or more computer processors further configured to: determine a total on-screen time value, the total on-screen time value determined by summing on-screen times of at least the first character in the media content and the second character in the media content; calculate the first salience value of the first character of the plurality of characters by dividing the on-screen time of the first character by the determined total on-screen time value; and calculate the second salience value of the second character of the plurality of characters by dividing the on-screen time of the second character by the determined total on-screen time value. ### Claim 17 (depends on 15) The apparatus of claim 15, the one or more computer processors further configured to: determine the first character model in part by: identifying textual content associated with the first character, the textual content contained in an electronic source; aggregating a plurality of attribute terms associated with the first character from the textual content; mapping at least some of the plurality of attribute terms to at least some of the plurality of attributes; and updating attribute values of the first character based on the plurality of attribute terms. ### Claim 18 (depends on 17) The apparatus of claim 17, wherein: each of the at least some of the plurality of attribute terms is associated with a corresponding strength value; and updating attribute values of the first character is based on the corresponding strength values. ### Claim 19 (depends on 17) The apparatus of claim 17, the one or more computer processors further configured to: store the updated attribute values of the first character in a database as a vector, the vector associated with the first character. ### Claim 20 (depends on 15) The apparatus of claim 15, the one or more computer processors further configured to: access a minimum content rating value; compare the media content rating to the minimum content rating value, wherein the media content rating is numerical and the minimum content rating value is numerical; and determine the media content rating is greater than the minimum content rating value. ### Claim 21 (depends on 15) The apparatus of claim 15, wherein: the character preference function is a second order function associating at least one of the plurality of preference coefficients with two or more attributes of interest of the plurality of attributes; calculating the first character rating of the first character further comprises determining the product of the at least one of the plurality of preference coefficients with each attribute value of the first set of attribute values of the two or more attributes of interest of the plurality of attributes; and calculating the second character rating of the second character further comprises determining the product of the at least one of the plurality of preference coefficients with each attribute value of the second set of attribute values of the two or more attributes of interest of the plurality of attributes.