Information-processing apparatus, method, system, computer- readable medium and method for automatically recording or recommending content

Abstract

A program vector can represent attributes of a program to be generated. EPG data can be received, and metadata necessary for generation of a program vector PP can be extracted from the EPG data. A morphological analysis can be carried out on contents and title included in the metadata to disassemble the contents and the title into words. Items included in the metadata can be subjected to a vector creation process to generate the program vector PP. An effect vector can be extracted on the basis of a genre of a program associated with the metadata. The extracted effect vector can be associated with the generated program vector PP and the processing can be ended. This can be applied to a distribution server for distributing contents.

What is claimed is: 
     
         1 . An information processing apparatus, comprising:
 an attribute information acquiring unit configured to acquire attribute information of contents, the attribute information including items that describe one or more aspects of the contents;   an item similarity calculating unit configured to calculate a degree of similarity between the acquired attribute information and user preference information, the user preference information including items that describe one or more aspects of the contents that are preferred by a user; and   a contribution estimating unit configured to estimate a degree of contribution of the items of the attribute information that describes one or more aspects of the contents, wherein   the item similarity calculating unit calculates the degree of similarity between the acquired attribute information and the user preference information based on the degree of contribution estimated by the contribution estimating unit.   
     
     
         2 . The apparatus according to  claim 1 , wherein the item similarity calculating unit is configured to calculate a first degree of similarity between a first content and the user preference information based on a first degree of contribution that is estimated based on a first genre of the first content. 
     
     
         3 . The apparatus according to  claim 2 , wherein the first degree of contribution is a weighting factor applied to one or more of items of first attribute information of the first content. 
     
     
         4 . The apparatus according to  claim 2 , wherein a degree of contribution varies between contents of different genres, such that a level of importance of one or more items of attribute information of the contents of different genres, in calculating a degree of similarity between the contents of different genres and the user preference, differs based on genres. 
     
     
         5 . The apparatus according to  claim 1 , wherein the items of the attribute information include textual items, including a title of one or more of the contents. 
     
     
         6 . The apparatus according to  claim 1 , further comprising:
 a user preference information generating unit configured to generate the user preference information.   
     
     
         7 . The apparatus according to  claim 6 , wherein the user preference information generating unit is configured to generate the user preference information based on a history of the user. 
     
     
         8 . The apparatus according to  claim 7 , wherein the history of the user includes a positive history, which indicates the user's likes, and a negative history, which indicates the user's dislikes. 
     
     
         9 . The apparatus according to  claim 6 , wherein the user preference information generating unit is configured to generate the user preference information based on a pre-selection of particular items, by an input of the user. 
     
     
         10 . The apparatus according to  claim 1 , further comprising:
 a recommendation unit configured to recommend one or more of the contents to the user based on an output of the item similarity calculating unit.   
     
     
         11 . The apparatus according to  claim 1 , wherein:
 for at least a content of the contents, the attribute information is a content vector that includes items that describe one or more aspects of the content as elements of the content vector;   the user preference information is a preference vector that includes the items that are preferred by the user as elements of the preference vector; and   the degree of contribution, of the items of the attribute information that describe one or more aspects of the content, is a contribution vector that includes weighting factors, as elements of the contribution vector, for one or more of the items of the attribute information.   
     
     
         12 . The apparatus according to  claim 11 , wherein:
 the items included as elements of the content vector include words;   the weighting factors included as elements of the contribution vector include numbers; and   the item similarity calculating unit is configured to calculate the degree of similarity between the content and the user preference information by multiplying the content vector with the contribution vector to generate a weighted content vector that includes elements that each include a corresponding number from the contribution vector and a corresponding word from the content vector.   
     
     
         13 . The apparatus according to  claim 12 , wherein:
 the preference vector is a weighted preference vector in which the elements each include a number and a word, in which the number corresponds to a relative preference of the word with respect to other words in the weight preference vector; and   the item similarity calculating unit is configured to calculate a cosine difference between one or more of elements of the weighted preference vector and the weighted content vector, and calculate the degree of similarity based on the cosine difference.   
     
     
         14 . The apparatus according to  claim 1 , wherein:
 for at least a content of the contents, the attribute information acquiring unit is configured to acquire a title of the content and disassemble the title into separate words; and   the attribute information is a content vector that includes items that describe one or more aspects of the content as elements of the content vector, in which the elements include one or more the separate words of the title.   
     
     
         15 . An information processing apparatus, comprising:
 means for acquiring acquire attribute information of contents, the attribute information including items that describe one or more aspects of the contents;   means for calculating a degree of similarity between the acquired attribute information and user preference information, the user preference information including items that describe one or more aspects of the contents that are preferred by a user; and   means for estimating a degree of contribution of the items of the attribute information that describes one or more aspects of the contents, wherein   the means for calculating calculates the degree of similarity between the acquired attribute information and the user preference information based on the degree of contribution estimated by the means for estimating.   
     
     
         16 . An information processing method, comprising:
 acquiring acquire attribute information of contents, the attribute information including items that describe one or more aspects of the contents;   calculating a degree of similarity between the acquired attribute information and user preference information, the user preference information including items that describe one or more aspects of the contents that are preferred by a user; and   estimating a degree of contribution of the items of the attribute information that describes one or more aspects of the contents, wherein   the calculating includes calculating the degree of similarity between the acquired attribute information and the user preference information based on the degree of contribution estimated by the estimating.   
     
     
         17 . A non-transitory computer readable medium including executable instructions, which when executed by one or more processors, causes an information processing apparatus to execute the method according to  claim 16 . 
     
     
         18 . A computer server including the apparatus according to  claim 1  and a network controller configured to transmit recommended content information, based an output of the item similarity calculating unit, to a user device.