WO2004053736A1 - 情報処理装置および方法、記録媒体、並びにプログラム - Google Patents
情報処理装置および方法、記録媒体、並びにプログラム Download PDFInfo
- Publication number
- WO2004053736A1 WO2004053736A1 PCT/JP2003/015927 JP0315927W WO2004053736A1 WO 2004053736 A1 WO2004053736 A1 WO 2004053736A1 JP 0315927 W JP0315927 W JP 0315927W WO 2004053736 A1 WO2004053736 A1 WO 2004053736A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- content
- program
- grouping
- group
- preference information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
- H04N21/8405—Generation or processing of descriptive data, e.g. content descriptors represented by keywords
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/26603—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/2665—Gathering content from different sources, e.g. Internet and satellite
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programmes or purchase activity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
Definitions
- the present invention relates to an information processing apparatus and method, a recording medium, and a program, and particularly to an information processing apparatus and method, a recording medium, and a program that can efficiently and effectively recommend content.
- the attribute eg, genre
- the content is recommended for each attribute.
- the present invention has been made in view of such a situation, and enables a content recommendation side to group contents by using contents attributes and to recommend contents for each group. Things.
- the information processing apparatus is configured such that a grouping item including one or more attribute items among attribute items representing attributes of content to be distributed has the same group as content having similarity with a certain degree of similarity or more.
- Generating means for generating user preference information indicating user preferences based on the usage frequency calculated by the calculating means; and recommending means for recommending content based on the user preference information generated by the generating means It is characterized by having.
- a grouping item consisting of an attribute item indicating the broadcast time zone and at least one other attribute item is set, and the grouping means should group the content based on the grouping item. Can be.
- a grouping item including at least an attribute item indicating a broadcast time zone and a grouping item including other attribute items are set, and the grouping unit groups the contents based on the grouping items. It can be performed.
- the grouping means can perform a morphological analysis of the content of the attribute item of the content, and determine the similarity of the content of the grouping item based on the result.
- the generation unit can prevent the use frequency of the group whose use state of the content belonging to the group does not satisfy the predetermined condition from being used for generating the user preference information.
- the recommendation means determines whether or not the usage frequency calculated by the calculation means is higher than a predetermined value.
- the determination means determines that the usage frequency is higher than a predetermined value.
- setting means for setting a standard flag indicating that the content is frequently viewed content in the recommendation information of the content can be provided.
- the generating means includes extracting means for acquiring metadata of the content of the group whose usage frequency calculated by the calculating means is higher than a preset value, and extracting a solid representing the characteristic amount of the metadata;
- the preference information can be generated based on the vector extracted by the above.
- the generation unit includes a standard determination unit that determines whether the content of the group whose use frequency calculated by the calculation unit is higher than a preset value is the content corresponding to the content recommendation information with the standard flag set.
- the standard determination means the content is determined by the content corresponding to the content recommendation information for which the standard flag is set. If it is determined that there is no metadata, the extraction unit can acquire the metadata of the content and extract a vector representing the feature amount of the metadata.
- the preference information can be configured by a plurality of attributes and values indicating the importance of the attributes.
- the generating means includes a familiarity setting means for setting the familiarity of the content based on the use frequency calculated by the calculating means, and weights a value representing the importance of the preference information based on the familiarity. Can be.
- the generating means includes a searching means for searching for the content used the number of times equal to or less than a predetermined value based on the usage history of the content, and a special preference information based on the metadata of the content searched by the searching means. And special preference information generating means for generating.
- Vectors extracted by the second extraction means can be selected by a predetermined number in descending order of degree, and content can be recommended based on the metadata of the selected vectors.
- a grouping item consisting of one or more attribute items among attribute items representing attributes of distributed content is assigned to a content having the same group with a certain degree of similarity.
- the program of the recording medium according to the present invention is characterized in that a grouping item consisting of one or more attribute items among the attribute items representing the attributes of the content to be distributed is the same as content having similarity with a certain degree of similarity or more.
- a grouping control step that controls the grouping of contents by assigning a group ID, a calculation control step that controls the calculation of the content usage frequency for each group ID, and a calculation control step Controlling the generation of user preference information indicating the user's preference based on the usage frequency, and controlling the content recommendation based on the user preference information generated in the processing of the generation control step.
- a recommendation control step that controls the grouping of contents by assigning a group ID, a calculation control step that controls the calculation of the content usage frequency for each group ID, and a calculation control step Controlling the generation of user preference information indicating the user's preference based on the usage frequency, and controlling the content recommendation based on the user preference information generated in the processing of the generation control step.
- a recommendation control step that controls the group
- the program according to the present invention assigns the same group ID to contents in which one or more attribute items among attribute items representing attributes of distributed content are similar with a certain degree of similarity or more.
- Grouping control step for controlling content grouping a calculation control step for controlling calculation of content usage frequency for each group ID, and a usage frequency calculated in the processing of the calculation control step.
- FIG. 1 shows a configuration example of a content recommendation system to which the present invention is applied.
- FIG. 2 is a diagram illustrating an example of metadata.
- FIG. 3 is a diagram illustrating grouping of contents.
- FIG. 4 is another diagram illustrating grouping of contents.
- FIG. 5 is a diagram illustrating an example of metadata to which a group ID is assigned.
- FIG. 6 is a diagram showing an example of the usage history.
- FIG. 7 is a block diagram showing a configuration example of the content recommendation server of FIG.
- FIG. 8 is a block diagram illustrating a configuration example of the client device in FIG.
- FIG. 9 is a flowchart illustrating the user preference information generation processing.
- FIG. 10 is a diagram illustrating a method of calculating the use frequency.
- FIG. 11A is another diagram illustrating a method of calculating the usage frequency.
- FIG. 11B is another diagram illustrating a method of calculating the usage frequency.
- FIG. 12 is a diagram for explaining a use state confirmation process.
- FIG. 13 is another diagram for explaining the use state confirmation process.
- FIG. 14 is another diagram for explaining the use state confirmation process.
- FIG. 15 is a flowchart illustrating the content recommendation information generation processing.
- FIG. 16 is a diagram showing a display example of content recommendation information.
- FIG. 17 is a diagram showing a display example of other content recommendation information.
- FIG. 18 is a flowchart illustrating title grouping processing 1.
- FIG. 19 is a flowchart illustrating the title grouping process 2.
- FIG. 20 is a flowchart for explaining the title grouping process 3.
- FIG. 21 is a flowchart illustrating title grouping processing 4.
- FIG. 22 is a flowchart illustrating the standard program setting process.
- FIG. 23 is a flowchart illustrating the preference information extraction process 1.
- FIG. 24 is a diagram showing a configuration example of a program vector.
- FIG. 25 is a diagram illustrating a configuration example of preference information.
- FIG. 26 is a flowchart illustrating the preference information extraction process 2.
- FIG. 27 is a flowchart illustrating the preference information extraction process 3.
- FIG. 28 is a flowchart illustrating the preference information change process.
- FIG. 29 is a flowchart illustrating the special preference information generation processing.
- FIG. 30 is a block diagram showing a functional configuration example of the CPU of FIG.
- FIG. 31 is a flowchart illustrating the recommended information search process.
- FIG. 32 is a flowchart illustrating the special recommendation information search processing. BEST MODE FOR CARRYING OUT THE INVENTION
- FIG. 1 shows a configuration example of a content recommendation system to which the present invention is applied.
- the distribution server 3 acquires the streaming data from the streaming data database 1 and distributes it to the client device 5 via the network 6 including the Internet and other networks.
- the distribution server 3 also acquires the content metadata from the metadata database 2 and supplies it to the content recommendation server 4 via the network 6.
- the content recommendation server 4 has a certain degree of similarity (elements of each item constituting the grouping item) of the grouping items set by one or more items (the elements of each item are all the same). , A partial match, or a value indicating a certain degree of similarity is equal to or more than a certain value) Assign the same group ID to the content (group into the same group).
- the content is divided into a set of each element of the item "broadcast station", the item “broadcast start time”, and the item “broadcast end time”, which constitute the grouping item. Are grouped.
- the content is grouped for each combination of the element “genre” and the item “performer” constituting the grouping item.
- one content may belong to multiple groups depending on the content item.
- a program that is broadcast between 00: 00 and 06: 00, and in which the talent A appears in variety includes "8 ch (broadcasting station), 00: 00 (broadcast) Start time) ⁇ 06: 00 (broadcast end time) "and the group ID of" variety (genre), talent A (performer) "( Figure 4) are assigned. It will belong to the group.
- the content recommendation server 4 transmits the metadata (for example, FIG. 5) in which the group ID is set as described above to the client device 5 as appropriate.
- the content recommendation server 4 also appropriately obtains a usage history including the content's group ID from the client device 5, and calculates the usage frequency for each group based on the usage history. Then, the content recommendation server 4 uses the calculated use frequency as an indication of the user's preference, and recommends the content for each group. For example, information on contents belonging to a group of high use frequency is transmitted to the client device 5 as content recommendation information.
- the client device 5 uses the content distributed from the distribution server 3, and uses, for example, metadata (a group ID is set) as shown in FIG. It is supplied to the content recommendation server 4 as appropriate.
- the client device 5 displays the content recommendation information supplied from the content recommendation server 4 and presents it to the user.
- the user can select the content that suits his or her taste by referring to it.
- FIG. 7 shows a configuration example of the content recommendation server 4.
- Processing Unit 11 Performs predetermined processing in accordance with, for example, a program for content recommendation, which is considered in ROM (Read Only Memory) 12.
- ROM Read Only Memory
- a RAM Random Access Memory 13 stores data and the like necessary for the CPU 11 to execute the processing.
- An input / output interface 15 is connected to the CPU 11 via a bus 14.
- the input / output interface 15 includes an input unit 16 including a keyboard and a mouse, an output unit 17 including an LCD (Liquid Crystal Display), a storage unit 18 for storing metadata and the like, and a network 6.
- a communication unit 19 that communicates with the distribution server 3 or the client device 5 through the communication unit 19 is connected.
- a drive 20 is appropriately connected to the input / output interface 15 and the CPU 11 is connected to a magnetic disk 31, an optical disk 32, a magneto-optical disk 33, or a semiconductor memory 34 mounted thereon. Transfer data between the two.
- Examples of the functional configuration of the CPU 11 include, for example, a preference information acquisition unit that acquires user preference information, a metadata acquisition unit that acquires program metadata from the distribution server 3, and content recommendation information. It is also possible to configure it with a recommendation information generating unit to generate.
- FIG. 8 shows a configuration example of the client device 5. This configuration is basically the same as the configuration of the content recommendation server 4, and a description thereof will be omitted.
- step S1 the CPU 11 of the content recommendation server 4 determines whether or not it is time to generate the user preference information, and if it is determined that it is the time, proceeds to step S2. For example, when the provision of content recommendation information (described later) is requested from the client device 5, or when a predetermined time (for example, a predetermined time every week) comes, the process proceeds to step S2.
- a predetermined time for example, a predetermined time every week
- step S2 the CPU 11 acquires a predetermined use history from the client device 5 via the communication unit 19.
- the metadata of the content that has been used in the past week (with group ID set) is acquired.
- the CPU 11 calculates the content use frequency (number of times) for each group.
- the program broadcasted on 20 ch from 20: 0 to 21: 0 on 8 ch, and the program on 10 ch from 10 o 0 to 20 on 0 ch.
- the program broadcasted at 0 is most viewed (7 times each), followed by the program broadcasted between 22: 0 00 and 23: 00 on 8 channels (6 times). You can see that it is done.
- the contents of the grouping item are included in each metadata.
- the content usage frequency (number of times) is calculated for each content (group of elements of each item), as shown in Fig. 11A.
- Figure 11A shows that, from the number of uses for each group, variety programs with talent D appear the most (10 times), followed by news programs (8 times) with talent D and talent C. It can be seen that the variety programs (5 times) that perform are often viewed.
- the number of uses is normalized by the number of contents distributed during the period corresponding to the use history acquired in step S2.
- a tenth program in which talent D appears is distributed during the period (in this case, one week), and a use program in which talent D appears is
- the number of uses in Fig. 11A would be as shown in Fig. 11B.
- step S3 the CPU 11 of the content editing server 4 detects, for each grouping item, (a group ID of) a group for which the number of times of use (use frequency) is equal to or greater than a predetermined threshold. I do.
- the example of FIG. 10 shows “8ch, 20: Two groups of “0 0 to 21: 00” and “10 ch, 19: 00 to 20: 00” are detected.
- threshold value for the grouping item consisting of the item “genre” and the item “performer” is 0.06, in the example of FIG. 11B, “variety, talent D”, “news, talent D”, And “variety, talent C” are detected.
- step S4 the CPU 11 determines whether or not the content of each group detected in step S3 matches the user's preference. For example, based on the distribution list of the content belonging to the group, it is confirmed whether the content has not been used continuously for a predetermined number of times (for example, three times) retroactively. It is determined that the content of the group does not match the user's preference.
- step S5 the CPU 11 detects a group of contents matching the user's preference from the determination result in step S4.
- step S6 the CPU 11 stores the group ID of the group detected in step S5 in the storage unit 18 as user preference information.
- step S21 the CPU 11 of the content recommendation server 4 waits until the client device 5 requests the provision of the content recommendation information.
- the process proceeds to step S22, and the storage is performed.
- the user preference information generated as described above is obtained from the unit 18.
- step S23 the CPU 11 determines from the metadata (contents for which the group ID has been set) of the content to be distributed from now on, the meta data for which the same group ID as the group ID as the user preference information has been set. Extract the data. The CPU 11 generates content recommendation information from the extracted metadata.
- the metadata of the content to which any group ID is assigned can be extracted.
- step S24 the CPU 11 transmits the content recommendation information generated in step S23 to the client device 5 via the communication unit 19.
- the client device 5 displays the content recommendation information transmitted from the content recommendation server 4 on the output unit 57.
- FIG. 16 and FIG. 17 show display examples of content recommendation information.
- the items “Broadcaster”, “Broadcast start time”, and “Broadcast end time” are grouped into items “8ch, 20: 0 00 to 21: 00” and Information (such as the title) of programs belonging to the group “10ch, 19:00:00 to 20:00:00” is displayed.
- the usage frequency for grasping the user's preference is calculated for each group using the group ID, so that the usage frequency is calculated as compared to the case of calculating the usage frequency for each metadata item.
- the amount of calculation can be reduced.
- the content recommendation information is displayed collectively for each group, the content recommendation information can be appropriately displayed even on the client device 5 having a small display space.
- grouping was performed using the metadata items “broadcast station”, item “broadcast start time”, and item “broadcast end time”, as well as item “genre” and item “performers”.
- grouping can also be performed using other items such as the item “Title” and the item “Content”.
- a rebroadcast or special edition program can be treated as content belonging to the same group as the original program, so that whether the program is original or rebroadcast, If viewed, the usage history can be reflected in the generation of user preference information.
- step S61 the content recommendation server 4 extracts a title from the metadata.
- step S62 the content recommendation server 4 morphologically analyzes the title and breaks it down into words.
- step S63 the content recommendation server 4 extracts one of the analyzed word or a word group composed of a plurality of words, and stores the extracted word in the storage unit 1.
- the word group composed of a plurality of words is a word group generated by a combination of words obtained by morphological analysis.
- words obtained by morphological analysis include “Tokaido”, “ In the case of "Mitani” and “Kaidan”, the words are “Tokaido-Mitani”, “Tokaido 'Kaidan”, and "Mitani'Kaidan”.
- step S64 the content recommendation server 4 determines whether the group ID has been extracted.
- step S64 If it is determined in step S64 that the corresponding group ID has not been extracted, the extracted word or a group of words composed of a plurality of words has not yet been assigned a group ID.
- step S65 a new group ID is assigned to the extracted word or a word group composed of a plurality of words. Further, the content recommendation server 4 stores a word or a word group composed of a plurality of words and a group ID corresponding to the word group.
- step S66 content recommendation server 4 executes It is determined whether or not a group ID has been extracted for a word or a word group composed of a plurality of words.
- step S66 If it is determined in step S66 that the group ID has not been extracted for all words constituting the title or for a word group including a plurality of words, the process returns to step S63. Subsequent processing is repeated.
- step S66 if it is determined that the group ID has been extracted for all words constituting the title or for a word group composed of a plurality of words, in step S67, the content recommendation server 4 The process is terminated by associating the extracted or assigned group ID with the metadata.
- programs having similar titles may be included in the same group.
- the title was set so that the serial drama titled "Two Years A Gumi Ginpachi-sensei” and the special program titled “Two Years A Gumi Ginpachi-sensei Special” could be grouped as the same group
- the match rate of words is calculated on a round robin basis in a program title for a predetermined period such as a week, a month, a half year, etc., and if the word match rate is equal to or higher than a predetermined value, the words may be grouped together. Good.
- step S401 and step S402 processing similar to that in step S61 and step S62 described with reference to FIG. 18 is executed. That is, the content recommendation server 4 extracts the title from the metadata, analyzes the title, and decomposes it into words.
- step S403 the content recommendation server 4 calculates, based on the analyzed words, the degree of matching between words between titles, that is, the matching rate indicating the rate of matching between words.
- the title “Two Years A Ginpachi Ginpachi-sensei” and the title “Two Years A Ginpachi Ginpachi Special” are “2”, “Year”, “A” “Gumi”, and “Ginpachi”, respectively.
- the matching rate of the words that make up the titles of these two programs is It becomes 85.7% in 6/7.
- step S404 the content recommendation server 4 determines whether the words match at least a predetermined value such as 70%, for example.
- a predetermined value such as 70%
- the threshold value of the coincidence rate may be any numerical value other than 70%.
- step S404 If it is determined in step S404 that the word matches at least a predetermined value such as 70%, in step S405, the content recommendation server 4 determines that the program is identical to those programs. Map the group ID of The content recommendation server 4 stores the matched word or word group and the corresponding group ID. ' If it is determined in step S404 that the match rate is equal to or less than a predetermined value such as 70%, or if the processing in step S405 ends, the content is determined in step S406. The recommendation server 4 determines whether or not the brute force of the title has been completed.
- step S 406 If it is determined in step S 406 that the brute force of the title has not been completed, the process returns to step S 403, and the subsequent processes are repeated.
- step S406 If it is determined in step S406 that the brute force of the title has been completed, the process is terminated.
- a group ID based on the matching rate of words constituting a title is associated, so that programs having similar titles such as a serial drama and a special program are processed as the same group.
- determining the group based on the matching rate of the words that compose the title for example, in the metadata, one-byte and two-byte numbers, or one-byte and two-byte alphabetic characters, or uppercase and lowercase characters Even if there is a spelling shift, programs with the same title can be detected as the same group.
- a broadcast station for example, a broadcast station, a program genre, or a broadcast start time may be added to the grouping condition.
- the title is composed of a small number of words including "news". Therefore, the processing described with reference to FIG.
- the same group since the same group may be detected, the same group may be used if the broadcast stations also match in addition to the word match rate.
- a title grouping process 3 (item “Title” and item “Title”) in which grouping is performed based on the matching rate of words constituting titles with the condition of matching broadcasting stations as conditions.
- the grouping item consisting of the item “broadcasting station” will be explained. .
- steps S421 to S424 the same processing as steps S401 to S404 described using FIG. 19 is performed. That is, the content recommendation server 4 extracts the title from the metadata, performs morphological analysis, and decomposes the word into words. Then, the content recommendation server 4 calculates the degree of matching of the words between the titles based on the analyzed words, and determines whether the words match at least a predetermined value such as 70%, for example. I do.
- step S425 the content recommendation server 4 determines whether the broadcast station of the program is It is determined whether or not matches.
- step S425 If it is determined in step S425 that the broadcasting stations of these programs match, in step S425, the content recommendation server 4 associates the same group ID with those programs. Further, the content recommendation server 4 stores the matched word or word group, and the corresponding broadcast station and group ID.
- step S424 If it is determined in step S424 that the match rate is equal to or less than a predetermined value such as 70%, if it is determined in step S425 that the broadcast stations of these programs do not match, Alternatively, after the processing in step S 426 is completed, in step S 427, the content recommendation server 4 determines whether or not the round robin of the title has been completed.
- a predetermined value such as 70%
- step S 427 If it is determined in step S 427 that the brute force of the title has not been completed, the process returns to step S 423, and the subsequent processes are repeated.
- step S 427 If it is determined in step S 427 that the brute force of the title has been completed, the processing is terminated.
- the group ID based on the match rate of the broadcast stations and the match rate of the words constituting the title is associated. For example, when programs having similar titles are set to the same group, It is possible to prevent the -use programs of a station from being in the same group. Note that, in FIG. 20, it has been described that the grouping is performed on the condition that the same broadcasting station is used in addition to the matching rate of the words constituting the title. Needless to say, the grouping may be performed with the broadcast time zone, genre, and the like as conditions other than the match rate of the words constituting the title.
- the broadcast start time of a serial drama or a band program is shifted due to a sports broadcast or a special program, etc.
- the condition may be determined based on whether or not the broadcast time matches within a predetermined time range such as one hour, for example.
- the grouping is performed based on the matching rate of words constituting the title, with the condition that the broadcast time is within a predetermined time range or not.
- the title grouping process 4 (grouping process by a grouping item including the item “title” and the item “broadcast start time”) will be described.
- steps S444 to S444 processing similar to that of steps S401 to S404 described with reference to FIG. 19 is performed. That is, the content recommendation server 4 extracts a title from the metadata, performs morphological analysis, and decomposes the word into words. Then, the content recommendation server 4 calculates the degree of matching of the words between the titles based on the analyzed words, and determines whether the words match at least a predetermined value such as 70%, for example. I do.
- step S444 If it is determined in step S444 that the words match at least a predetermined value such as 70%, in step S445, the content recommendation server 4 starts broadcasting the program. It is determined whether or not the times coincide with each other with a shift of a predetermined range ⁇ such as one hour, for example.
- step S445 If it is determined in step S445 that the broadcast start times of the programs match within a predetermined range, the content recommendation server 4 determines in step S446 that the broadcast start times of the programs match. To the same group ID. Also, The ten recommendation server 4 stores the matched word or word group, the range of the corresponding broadcast start time, and the group ID.
- step S444 If it is determined in step S444 that the matching rate is equal to or less than a predetermined value such as 70%, in step S444, the broadcast start times of those programs are shifted beyond a predetermined range. Is determined, or after the process of step S446 is completed, in step S446, the content recommendation server 4 determines whether or not the total number of titles has been completed. ⁇
- step S444 If it is determined in step S444 that the brute force of the title has not been completed, the process returns to step S444, and the subsequent processes are repeated. If it is determined in step S447 that the brute force of the title has been completed, the processing is terminated.
- a match including a deviation of a broadcast start time within a predetermined range is associated with a group ID based on a match rate of words constituting a title.
- the programs are in the same group, it is possible to prevent programs that should be detected as being in the same group from being detected as being in the same group due to a change in broadcast time due to a special program or the like.
- the content recommendation server 4 performs the user preference information generation process (FIG. 9) and the content recommendation information processing (FIG. 15).
- the client device 5 uses the content recommendation server. Using the metadata (grouping information) provided with the group ID provided by 4 and generating the user preference information by calculating the usage frequency of each group, content recommendation information is generated based on this. It can also be generated.
- step S501 the CPU 11 analyzes the usage history.
- the metadata of the content used in the predetermined period (in which the group ID is set) is acquired from the client device 5, and the number of times of use ( Figure 10) or usage frequency ( Figure 1 IB) is analyzed.
- step S502 the CPU 11 determines whether or not there is a group whose use count (viewing count) exceeds a predetermined threshold.
- a staple flag indicating that this program is a staple is set in the content recommendation information of a program belonging to the group (a program whose usage count exceeds the threshold).
- step S502 it is determined whether there is a group whose viewing frequency exceeds the threshold. If it is determined that there is a program whose usage frequency exceeds the threshold, in step S503, the group is determined.
- the standard flag may be set in the content recommendation information of the program belonging to.
- step S502 If it is determined in step S502 that there is no group in which the number of times of viewing exceeds the threshold, the process ends.
- the content recommendation information with the standard flag set is transmitted to the client device 5 by the content recommendation information generation processing of FIG. This allows the client device 5 to automatically record, for example, a program corresponding to the content recommendation information for which the standard flag is set.
- the group ID is stored as the user preference information, but more detailed preference information is generated based on a plurality of attributes included in the metadata of the program. Then, the program can be recommended based on the generated preference information.
- a description will be given of a preference information extraction process 1, which is a first example of generating more detailed preference information based on a plurality of attributes included in program metadata.
- This processing is executed in the content recommendation server 4 at a predetermined time (a predetermined time every week), for example.
- step S522 the CPU 11 analyzes the usage history. At this time, as in the case of step S2 in FIG.
- the metadata of the content used in the predetermined period (in which the group ID is set) is acquired from the client device 5, and the number of times of use ( ( Figure 10) or usage frequency ( Figure 11B).
- the CPU 11 searches for a group whose use count (use frequency) is equal to or greater than a predetermined threshold. Note that a group whose usage frequency is equal to or higher than a predetermined threshold may be searched.
- step S 523 the CPU 11 determines whether or not the group has been searched. If it is determined that the group has been searched, the process proceeds to step S 524, where the meta data of the program belonging to the searched group is determined. Analyze the data. At this time, if there are multiple programs, the metadata of the multiple programs is analyzed. In step S525, the CPU 11 generates a program vector based on the metadata of the program analyzed in step S524.
- FIG. 24 shows a configuration example of the program vector PP generated at this time.
- the elements Tm, Gm, Pm, Sm, Hm,... are also configured as vectors with multiple elements.
- the vector Hm corresponding to the attribute “time zone” can also be obtained in the same manner as the vector Sm of the attribute “broadcasting station” and the vector Gm of the “genre”. '
- (personA-1) and (personB-3) indicate that personA and personB were detected once or three times, respectively, as words constituting the metadata attribute "performer".
- step S522 When a plurality of programs are searched in step S522, a program vector is generated for each program in step S525.
- step S526 the CPU 11 integrates the program vectors generated in step S525 to generate preference information.
- the respective attributes of the plurality of program betattles are added to generate preference information.
- FIG. 25 shows an example of the preference information generated at this time.
- the preference information is generated as a vector, and the attributes “program name (title)” (Tup), “genre” (Gup), “performer” (Pup), and “broadcasting station” (Sup ), "Time zone”
- the elements Tup, Gup, Pup, Sup, Hup, ⁇ ⁇ ⁇ are also configured as a vector with multiple elements.
- the attribute "program name” of the preference information includes the elements “title 1" and “title 2”, and their importance has been set to “1 2" and "3”, respectively.
- the importance indicates the degree of preference of the user for the element.
- the program vectors included in the same element are added, the importance is added by one. For example, if the preference information is generated based on 20 program vectors PP1 to PP20, three program vectors PP5, PP10, and PP17 are generated. , If “title2” is included in the attribute Tm, the importance of the element “title2” of Tup is set to “3”.
- step S525 If it is determined in step S525 that no group whose viewing count is equal to or greater than the threshold has been searched, the processing of steps S524 to S526 is skipped, and the processing ends.
- the preference information is generated. Since the preference information is generated based on the metadata of the program used only a predetermined number of times or frequency, the preference information can accurately reflect the user's preference. Note that the preference information may be generated for each user by analyzing the usage history of a specific user in step S521, or the usage history of a plurality of users may be generated in step S522. The analysis may generate general (common to a plurality of users) preference information.
- the importance is added each time a program vector including the same element is added, so that the program frequently viewed by the user is
- the importance of elements included in metadata may become extremely high, resulting in biased preference information. For example, if a user watches a program that is broadcast every day (Monday through Friday), the importance of an element included in the metadata of the program (for example, talent A) can be compared with other elements. And it becomes extremely high. It is also possible to prevent the metadata of such frequently viewed programs (so-called standard programs) from being reflected in the preference information.
- a preference information extraction process 2 is a second example of generating preference information based on a plurality of attributes included in the metadata of a program.
- step S544 the CPU 11 determines whether the program belonging to the group searched in step S5452 is a standard program.
- whether or not the program is a standard program is determined based on the standard flag set by the standard program setting process described above with reference to FIG.
- step S544 If it is determined in step S544 that the searched program is not a standard program, the process proceeds to step S545. Then, in a manner similar to the processing of steps S524 to S525 in FIG. 23, the metadata of the program is analyzed in step S545, and a program vector is generated in step S546. In step S 547, preference information is generated.
- step S544 determines whether the searched program is a standard program. If it is determined in step S544 that the searched program is a standard program, the processes in steps S545 to S545 are skipped. By doing so, preference information is not generated based on a standard program, and generation of biased preference information can be prevented.
- program vectors are generated for programs belonging to a group that is watched a predetermined number of times (or frequency) or more, and the preference information is generated.
- programs B 1, B 2, B 3, ⁇ ⁇ ⁇ ⁇ (programs belonging to one group each). For example, if the threshold of each group is three times, program A viewed three times The same applies to the program B (the series in which 10 serialized programs were watched) and the program B (the series in which 10 serialized programs were viewed). Is generated.
- step S566 the CPU 11 specifies the familiarity of the program. Familiarity is specified based on the frequency of use of series programs (ie, groups) analyzed in step S5661. At this time, three levels of familiarity are set according to the frequency of use of the series program. For example, if the usage frequency is “0.1” or more, the familiarity level is set to “high” and the usage frequency is Power S “0.05” or more and less than “0.1” are set to “medium” familiarity, and those whose usage frequency is less than “0.05” are set to “low” familiarity. Is done.
- the classification of familiarity is not limited to three levels.
- the familiarity may be set as a numerical value without being classified by stage.
- the familiarity level may be set based on the number of uses instead of the frequency of use.
- the CPU 11 weights the thread and the title generated in step S565 based on the familiarity.
- the importance of the preference information which is generated based on the elements included in the program vector of “high” familiarity, is set to three times, and the program vector of “medium” familiarity is set.
- the importance of the preference information generated based on the elements included in the program information is set to double, and the importance of the preference information generated based on the elements included in the program vector with low familiarity Is set to 1 time.
- preference information reflecting the familiarity is generated.
- the preference information may be generated in units of users by analyzing the usage history of a specific user in step S561, or the usage information of a plurality of users may be generated in step S561.
- general (common to multiple users) preference information may be generated. For example, for a user whose viewing history has not been accumulated yet, a program (content) can be recommended based on general preference information.
- the preference information is generated by reflecting the familiarity of the program. Rather than recommending high-reliability programs, highly reliable programs can be recommended to users.
- the importance of the preference information is added each time the program is viewed. However, in some cases, it is necessary to subtract the importance.
- the user can cancel the recording reservation for the standard program for which automatic recording has been reserved in the client device 5.
- the program whose recording reservation has been canceled is the program whose recording reservation was canceled only for that time even though it was frequently viewed before that time. It is assumed that the content did not match the tastes of the people. Therefore, in the present invention, the preference information of the user is changed based on the metadata of the program whose recording reservation has been canceled.
- the preference information change process will be described with reference to FIG.
- This processing is performed when the CPU 51 of the client device 5 detects the release of the automatic recording reservation, and sends the information of the program whose automatic recording reservation has been released to the content recommendation server 4 on the network 6. Is executed by the content recommendation server 4 when notified via the.
- the CPU 11 obtains metadata of the program for which the automatic recording reservation has been canceled (for example, the third program in a series of 10 broadcasts),
- the attribute of the acquired metadata is analyzed.
- the CPU 11 compares the attribute of the preference information of the program for which the automatic recording reservation has been set with the attribute of the metadata of the program for which the automatic recording reservation has been canceled. In 4, detect negative elements.
- step S585 the CPU 11 changes the user preference information based on the negative element detected in step S585. At this time, the importance of the negative element is subtracted.
- the vector information Pup power corresponding to the attribute “performer” of the preference information, Pup ⁇ (personA-5), (personB-5),
- the preference information is changed.
- the importance of the attributes that the user does not like is changed to be lower, so that when recommending a program (content) to the user, it is possible to recommend a program (content) that more closely matches the user's preference. it can.
- preference information is generated based on metadata of a series program in which the number of times of viewing is equal to or greater than a predetermined number
- a recommendation of a program based on the preference information generated in this manner is made. If done continuously, the user may get bored. Therefore, in the present invention, attention is paid to the program that the user has watched for the first time (not watched in the past). Since the user may have a special interest in the program viewed for the first time, special preference information is generated based on the metadata of the program.
- This process may be executed, for example, when a predetermined command is input by the user, or may be automatically executed at a predetermined cycle (for example, one week). ,.
- step S601 the CPU 11 searches for a usage history.
- the client device 5 uses the computer that has been used for a predetermined period (for example, the last 6 months).
- the metadata of the content (the group ID is set) is obtained, and the number of uses ( Figure 10) for each group is analyzed.
- step S602 the CPU 11 detects a series program that has been viewed once (a group in which only one of the programs belonging to the group is viewed).
- step S603 the CPU 11 determines whether or not a series program with one viewing has been detected. If it is determined that a series program has been detected, the CPU 11 proceeds to step S604.
- the special preference information is generated based on the metadata of the program belonging to the detected series program. At this time, a program vector is generated based on the metadata of the program, and special preference information is generated based on the program vector, similarly to steps S524 to S526 in FIG. . If it is determined in step S603 that a program with one viewing has not been detected, the process of step S604 is skipped.
- FIG. 30 shows the functions of the CPU 11 of the content recommendation server 4 when recommending content based on the preference information generated by the processing described above with reference to FIGS. 23, 26, and 27.
- FIG. 2 is a block diagram showing a typical configuration example.
- a metadata acquisition unit 111 for acquiring metadata of a program and a preference information acquisition unit 112 for acquiring preference information of a specific user are provided.
- the metadata of the program acquired by the metadata acquisition unit 111 is output to the program vector extraction unit 113, and the program vector extraction unit 113 extracts the program vector. Further, the preference information acquired by the preference information acquisition unit 112 is output to the preference vector extraction unit 114, and a preference vector based on the preference information is extracted. Extraction of the program vector extracted by the program vector extraction unit 113 and the preference vector The preference vector extracted by the unit 114 is output to the matching processing unit 115, and the matching processing unit 115 calculates the similarity between the program vector and the preference vector.
- Similarity between one preference vector and a plurality of program vectors is calculated, and the matching processing unit 115 selects a predetermined number of program vectors in descending order of similarity, and selects The metadata of the program corresponding to the selected program vector is output to the information output unit 116.
- the information output unit 116 causes the storage unit 18 to store the metadata of the program selected by the matching processing unit 115, for example.
- step S6221 the metadata acquisition unit 111 acquires the metadata of the content (program). At this time, metadata of a plurality of programs (for example, programs to be broadcast in the next week) is acquired based on a predetermined criterion.
- step S622 the program vector extraction unit 113 extracts a program vector based on the metadata of the program acquired in step S622. At this time, similarly to the program vector described above with reference to FIG. 24, program vectors of a plurality of programs are extracted.
- preference vector extraction section 114 acquires preference information. At this time, preference information of a specific user is obtained. In step S624, the preference vector extraction unit 114 generates a preference vector.
- the preference vector may be such that the preference information as shown in FIG. 25 is directly generated as a preference vector, or a specific attribute constituting the preference information is extracted and the preference vector is extracted. It may be generated as such.
- the similarity between the preference vector UP and the program vector PP is calculated. It should be noted that the similarity between a plurality of program vectors PP and one preference vector UP is calculated. Thus, the similarity between the metadata of each program and the user's preference information is calculated.
- step S626 the matching processing unit 115 selects metadata of a program having a high degree of similarity, and outputs it to the information output unit 116.
- a predetermined number for example, 10
- program vectors PP are selected in descending order of similarity, that is, in descending order of Sim value, based on the similarity calculated in step S625.
- the metadata of the program corresponding to the selected program vector PP is output. Note that all program vectors PP having a similarity greater than a predetermined value may be selected, and metadata of a program corresponding to the selected program vector PP may be output.
- step S627 the information output unit 116 transmits the content recommendation information of the program extracted in step S626 to the client device 5. In this way, the recommendation of the program based on the preference information is performed.
- the recommendation of a program can also be performed based on the special preference information generated by the processing described with reference to FIG.
- the special recommendation information search processing by the content recommendation server 4 will be described with reference to FIG. This processing may be executed, for example, when a predetermined command is input by the user, or may be automatically executed at a predetermined cycle (for example, one week).
- steps S641 and S642 Since the processing in steps S641 and S642 is the same as the processing in steps S621 and S622 in FIG. 31, the description is omitted.
- step S643 preference vector extraction section 114 acquires special preference information. At this time, the special preference information generated by the special preference information generation processing described above with reference to FIG. 29 is obtained. Then, in step S644, the preference vector extraction unit 114 generates a preference vector based on the special preference information acquired in step S643.
- steps S645 and S646 is the same as the processing in steps S625 and S626 in FIG. 23, and a description thereof is omitted.
- step S 627 the information output unit 116 transmits the content recommendation information of the program extracted in step S 646 to the client device 5.
- the special preference information is generated based on the metadata of the program that the user has watched for the first time.
- the series of processes described above can also be executed by software.
- the software can be a computer that has its programs built into dedicated hardware, or can execute various functions by installing various programs, such as a general-purpose personal computer. Installed from a recording medium to a computer. As shown in FIGS. 7 and 8, this recording medium is distributed in order to provide the program to the user.
- the program is recorded on a magnetic disk 31 or 71 (including a flexible disk) and an optical disk 32.
- 72 including compact disk-read only memory (CD-ROM) and digital versatile disk (DVD)
- magneto-optical disk 33 or 73 magneto-optical disk 33 or 73 (MD (mini-disk) (trademark)
- packaged media comprising semiconductor memory 34 or 74 or the like.
- steps for describing a program recorded on a recording medium are not limited to processing performed in chronological order in the order described, but are not necessarily performed in chronological order. Alternatively, it also includes processing that is executed individually.
- system refers to an entire device including a plurality of devices.
- content recommendation can be performed based on the use frequency of each group in the grouping item generated from the item representing the attribute of the content.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Computer Graphics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP03778860A EP1571561A4 (en) | 2002-12-12 | 2003-12-12 | DATA PROCESSING DEVICE AND METHOD, RECORDING MEDIUM AND PROGRAM |
| US10/538,658 US7873798B2 (en) | 2002-12-12 | 2003-12-12 | Information processing device and method, recording medium, and program |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2002361540 | 2002-12-12 | ||
| JP2002-361540 | 2002-12-12 | ||
| JP2003-285030 | 2003-08-01 | ||
| JP2003285030A JP2004206679A (ja) | 2002-12-12 | 2003-08-01 | 情報処理装置および方法、記録媒体、並びにプログラム |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2004053736A1 true WO2004053736A1 (ja) | 2004-06-24 |
Family
ID=32510667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2003/015927 Ceased WO2004053736A1 (ja) | 2002-12-12 | 2003-12-12 | 情報処理装置および方法、記録媒体、並びにプログラム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US7873798B2 (ja) |
| EP (1) | EP1571561A4 (ja) |
| JP (1) | JP2004206679A (ja) |
| KR (1) | KR101073948B1 (ja) |
| WO (1) | WO2004053736A1 (ja) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1646233A2 (en) * | 2004-10-11 | 2006-04-12 | Topfield Co., Ltd. | Apparatus and method for performing reserved recording function |
| US20070201822A1 (en) * | 2005-02-07 | 2007-08-30 | Yoshiaki Kusunoki | Recommended Program Extracting Apparatus And Recommended Program Extracting Method |
Families Citing this family (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100745995B1 (ko) * | 2003-06-04 | 2007-08-06 | 삼성전자주식회사 | 메타 데이터 관리 장치 및 방법 |
| US8943537B2 (en) * | 2004-07-21 | 2015-01-27 | Cox Communications, Inc. | Method and system for presenting personalized television program recommendation to viewers |
| JP4617805B2 (ja) * | 2004-09-28 | 2011-01-26 | ソニー株式会社 | 情報配信システムおよび情報配信方法、情報処理装置および情報処理方法、受信装置および受信方法、並びにプログラム |
| WO2006043498A1 (ja) * | 2004-10-18 | 2006-04-27 | Pioneer Corporation | 情報処理装置、統計情報データベースのデータ構造、情報生成装置、情報処理方法、情報生成方法、情報処理プログラム、およびそのプログラムを記録した記録媒体 |
| JP4529632B2 (ja) * | 2004-10-19 | 2010-08-25 | ソニー株式会社 | コンテンツ処理方法およびコンテンツ処理装置 |
| KR100677601B1 (ko) * | 2004-11-11 | 2007-02-02 | 삼성전자주식회사 | 메타 데이터를 포함하는 영상 데이터를 기록한 저장매체,그 재생장치 및 메타 데이터를 이용한 검색방법 |
| US7707209B2 (en) | 2004-11-25 | 2010-04-27 | Kabushiki Kaisha Square Enix | Retrieval method for contents to be selection candidates for user |
| WO2006064877A1 (ja) * | 2004-12-17 | 2006-06-22 | Matsushita Electric Industrial Co., Ltd. | コンテンツ推薦装置 |
| JP4655200B2 (ja) * | 2005-02-01 | 2011-03-23 | ソニー株式会社 | 情報処理装置および方法、並びにプログラム |
| JP4752623B2 (ja) * | 2005-06-16 | 2011-08-17 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
| JP2007104312A (ja) * | 2005-10-04 | 2007-04-19 | Toshiba Corp | 電子ガイド情報を用いた情報処理方法およびその装置 |
| JP2007281602A (ja) * | 2006-04-03 | 2007-10-25 | Canon Inc | 受信装置及び番組予約方法 |
| KR100714727B1 (ko) | 2006-04-27 | 2007-05-04 | 삼성전자주식회사 | 메타 데이터를 이용한 미디어 컨텐츠의 탐색 장치 및 방법 |
| KR20090015063A (ko) * | 2006-04-27 | 2009-02-11 | 교세라 가부시키가이샤 | 휴대 전화 단말, 서버 및 그룹 통화 시스템 |
| JP4847797B2 (ja) * | 2006-06-09 | 2011-12-28 | ヤフー株式会社 | 付加情報データを送信する方法、サーバおよびプログラム |
| JP2008219342A (ja) * | 2007-03-02 | 2008-09-18 | Sony Corp | 情報処理装置および方法、並びにプログラム |
| JP4721066B2 (ja) * | 2007-03-16 | 2011-07-13 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
| US9179086B2 (en) * | 2007-05-07 | 2015-11-03 | Yahoo! Inc. | System and method for providing dynamically updating applications in a television display environment |
| JP4717871B2 (ja) | 2007-11-06 | 2011-07-06 | シャープ株式会社 | コンテンツ視聴装置及びコンテンツ推薦方法 |
| WO2009076852A1 (zh) * | 2007-12-03 | 2009-06-25 | Huawei Technologies Co., Ltd. | 对用户进行分类的方法、行为采集分析方法与装置 |
| JP4568323B2 (ja) * | 2007-12-07 | 2010-10-27 | 富士通株式会社 | 放送番組の記録装置 |
| CN101472117A (zh) * | 2007-12-25 | 2009-07-01 | 深圳Tcl新技术有限公司 | 对节目进行选择录制的装置与方法 |
| JP4600521B2 (ja) | 2008-06-03 | 2010-12-15 | ソニー株式会社 | 情報処理装置、情報処理方法、プログラム |
| JP4596044B2 (ja) | 2008-06-03 | 2010-12-08 | ソニー株式会社 | 情報処理システム、情報処理方法 |
| JP4596043B2 (ja) | 2008-06-03 | 2010-12-08 | ソニー株式会社 | 情報処理装置、情報処理方法、プログラム |
| JP5387860B2 (ja) * | 2008-06-26 | 2014-01-15 | 日本電気株式会社 | コンテンツ話題性判定システム、その方法及びプログラム |
| US8037011B2 (en) * | 2008-09-15 | 2011-10-11 | Motorola Mobility, Inc. | Method and apparatus for recommending content items |
| JP4650552B2 (ja) * | 2008-10-14 | 2011-03-16 | ソニー株式会社 | 電子機器、コンテンツ推薦方法及びプログラム |
| KR20110091382A (ko) * | 2010-02-05 | 2011-08-11 | 삼성전자주식회사 | 방송 수신 장치, 방송 프로그램 선택 방법 및 그 저장 매체 |
| US10805102B2 (en) | 2010-05-21 | 2020-10-13 | Comcast Cable Communications, Llc | Content recommendation system |
| WO2011152072A1 (ja) * | 2010-06-04 | 2011-12-08 | パナソニック株式会社 | コンテンツ出力装置、コンテンツ出力方法、プログラム、プログラム記録媒体及びコンテンツ出力集積回路 |
| JP5578040B2 (ja) * | 2010-11-15 | 2014-08-27 | ソニー株式会社 | 情報処理装置および方法、情報処理システム、並びに、プログラム |
| JP5854286B2 (ja) * | 2010-11-15 | 2016-02-09 | 日本電気株式会社 | 行動情報収集装置及び行動情報送信装置 |
| US20120272156A1 (en) * | 2011-04-22 | 2012-10-25 | Kerger Kameron N | Leveraging context to present content on a communication device |
| US8620917B2 (en) * | 2011-12-22 | 2013-12-31 | Telefonaktiebolaget L M Ericsson (Publ) | Symantic framework for dynamically creating a program guide |
| JP5846898B2 (ja) * | 2011-12-22 | 2016-01-20 | ニフティ株式会社 | 情報処理装置、情報処理方法、情報処理システム、及び、プログラム |
| JP6105555B2 (ja) * | 2012-03-30 | 2017-03-29 | ソニー株式会社 | 制御装置、制御方法、プログラムおよび制御システム |
| FR3006542A1 (fr) * | 2013-05-30 | 2014-12-05 | France Telecom | Programmation d'enregistrement de contenus audiovisuels presents dans une grille de programmes electronique |
| US9916362B2 (en) * | 2013-11-20 | 2018-03-13 | Toyota Jidosha Kabushiki Kaisha | Content recommendation based on efficacy models |
| JP6185379B2 (ja) * | 2013-12-02 | 2017-08-23 | 株式会社Nttドコモ | レコメンド装置およびレコメンド方法 |
| JP6147682B2 (ja) * | 2014-02-14 | 2017-06-14 | 株式会社Nttドコモ | レコメンド装置及びレコメンド方法 |
| US11455086B2 (en) | 2014-04-14 | 2022-09-27 | Comcast Cable Communications, Llc | System and method for content selection |
| US11553251B2 (en) | 2014-06-20 | 2023-01-10 | Comcast Cable Communications, Llc | Content viewing tracking |
| US10776414B2 (en) * | 2014-06-20 | 2020-09-15 | Comcast Cable Communications, Llc | Dynamic content recommendations |
| US10051036B1 (en) * | 2015-01-23 | 2018-08-14 | Clarifai, Inc. | Intelligent routing of media items |
| US10362978B2 (en) | 2015-08-28 | 2019-07-30 | Comcast Cable Communications, Llc | Computational model for mood |
| CN105787759A (zh) * | 2016-02-23 | 2016-07-20 | 北京金山安全软件有限公司 | 一种获取用户属性的方法、装置及电子设备 |
| WO2017174833A1 (es) * | 2016-04-06 | 2017-10-12 | Telefónica Digital España, S.L.U. | Método y sistema para descubrimiento de contenido multimedia para dispositivos capaces de mostrar contenido multimedia |
| GB2584251B (en) * | 2018-01-11 | 2022-11-16 | Editorji Tech Private Limited | Method and system for customized content |
| JP6902636B1 (ja) * | 2020-01-28 | 2021-07-14 | 株式会社電通 | 予測装置、予測方法、及び予測プログラム |
| JP7090777B1 (ja) | 2021-04-30 | 2022-06-24 | 株式会社ビデオリサーチ | コンテンツ推奨装置、及びコンテンツ推奨方法 |
| JP7822337B2 (ja) * | 2023-03-07 | 2026-03-02 | Kddi株式会社 | 情報処理装置、情報処理方法及びプログラム |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06124309A (ja) * | 1992-10-14 | 1994-05-06 | Hitachi Ltd | 情報サービスシステムおよび放送受信システム |
| JPH11196389A (ja) * | 1997-12-26 | 1999-07-21 | Jisedai Joho Hoso System Kenkyusho:Kk | 蓄積型情報放送システムと、このシステムの受信端末装置 |
| WO2000005884A1 (en) | 1998-07-20 | 2000-02-03 | Mate - Media Access Technologies Ltd. | A method of automatic selection of video channels |
| JP2001092832A (ja) * | 1999-09-21 | 2001-04-06 | Matsushita Electric Ind Co Ltd | 情報推薦方法 |
| EP1137292A2 (en) | 1999-12-31 | 2001-09-26 | Nokia Mobile Phones Ltd. | Measurement of illumination conditions |
| JP2002320159A (ja) * | 2001-04-23 | 2002-10-31 | Nec Corp | 番組推薦システムおよび番組推薦方法 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6163316A (en) * | 1997-01-03 | 2000-12-19 | Texas Instruments Incorporated | Electronic programming system and method |
| US6020880A (en) | 1997-02-05 | 2000-02-01 | Matsushita Electric Industrial Co., Ltd. | Method and apparatus for providing electronic program guide information from a single electronic program guide server |
| US6370526B1 (en) * | 1999-05-18 | 2002-04-09 | International Business Machines Corporation | Self-adaptive method and system for providing a user-preferred ranking order of object sets |
| US7019778B1 (en) * | 1999-06-02 | 2006-03-28 | Eastman Kodak Company | Customizing a digital camera |
| JP4608740B2 (ja) * | 2000-02-21 | 2011-01-12 | ソニー株式会社 | 情報処理装置および方法、並びにプログラム格納媒体 |
| SE0000988L (sv) | 2000-03-22 | 2001-09-23 | Nokia Corp | Kommunikationssätt samt system och terminal som utnyttjar detta sätt |
| US7581237B1 (en) * | 2000-10-30 | 2009-08-25 | Pace Plc | Method and apparatus for generating television program recommendations based on prior queries |
| WO2002042959A2 (en) * | 2000-11-22 | 2002-05-30 | Koninklijke Philips Electronics N.V. | Television program recommender with interval-based profiles for determining time-varying conditional probabilities |
| AU2002323413A1 (en) * | 2001-08-27 | 2003-03-10 | Gracenote, Inc. | Playlist generation, delivery and navigation |
| KR100438857B1 (ko) * | 2001-09-26 | 2004-07-05 | 엘지전자 주식회사 | 사용자 선호도 기반 멀티미디어 검색 시스템 |
| US6987221B2 (en) * | 2002-05-30 | 2006-01-17 | Microsoft Corporation | Auto playlist generation with multiple seed songs |
-
2003
- 2003-08-01 JP JP2003285030A patent/JP2004206679A/ja active Pending
- 2003-12-12 US US10/538,658 patent/US7873798B2/en not_active Expired - Fee Related
- 2003-12-12 EP EP03778860A patent/EP1571561A4/en not_active Withdrawn
- 2003-12-12 KR KR1020057010032A patent/KR101073948B1/ko not_active Expired - Fee Related
- 2003-12-12 WO PCT/JP2003/015927 patent/WO2004053736A1/ja not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06124309A (ja) * | 1992-10-14 | 1994-05-06 | Hitachi Ltd | 情報サービスシステムおよび放送受信システム |
| JPH11196389A (ja) * | 1997-12-26 | 1999-07-21 | Jisedai Joho Hoso System Kenkyusho:Kk | 蓄積型情報放送システムと、このシステムの受信端末装置 |
| WO2000005884A1 (en) | 1998-07-20 | 2000-02-03 | Mate - Media Access Technologies Ltd. | A method of automatic selection of video channels |
| JP2001092832A (ja) * | 1999-09-21 | 2001-04-06 | Matsushita Electric Ind Co Ltd | 情報推薦方法 |
| EP1137292A2 (en) | 1999-12-31 | 2001-09-26 | Nokia Mobile Phones Ltd. | Measurement of illumination conditions |
| JP2002320159A (ja) * | 2001-04-23 | 2002-10-31 | Nec Corp | 番組推薦システムおよび番組推薦方法 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP1571561A4 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1646233A2 (en) * | 2004-10-11 | 2006-04-12 | Topfield Co., Ltd. | Apparatus and method for performing reserved recording function |
| US20070201822A1 (en) * | 2005-02-07 | 2007-08-30 | Yoshiaki Kusunoki | Recommended Program Extracting Apparatus And Recommended Program Extracting Method |
Also Published As
| Publication number | Publication date |
|---|---|
| US20060047678A1 (en) | 2006-03-02 |
| EP1571561A4 (en) | 2010-03-03 |
| JP2004206679A (ja) | 2004-07-22 |
| US7873798B2 (en) | 2011-01-18 |
| EP1571561A1 (en) | 2005-09-07 |
| KR20050085317A (ko) | 2005-08-29 |
| KR101073948B1 (ko) | 2011-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2004206679A (ja) | 情報処理装置および方法、記録媒体、並びにプログラム | |
| US8073848B2 (en) | Methods and systems for selecting and presenting content based on user preference information extracted from an aggregate preference signature | |
| KR101802332B1 (ko) | 컨텐츠 제공 방법 및 그 시스템 | |
| JP6235556B2 (ja) | コンテンツ提示方法、コンテンツ提示装置及びプログラム | |
| US20060271958A1 (en) | TV program selection support system | |
| US20100030645A1 (en) | Advertisement distributing system, advertising distributing server, advertisement distributing method, program and recording medium | |
| US20110093337A1 (en) | Methods and system for providing viewing recommendations | |
| CN106131703A (zh) | 一种视频推荐的方法和终端 | |
| US20150178379A1 (en) | Information-processing apparatus, method, system, computer-readable medium and method for automatically recording or recommending content | |
| EP2563014A2 (en) | Method for content presentation | |
| KR20030029034A (ko) | 정보 처리 시스템, 정보 출력 장치와 방법, 정보 처리장치와 방법, 기록 매체, 및 프로그램 | |
| US20090271403A1 (en) | Information processing apparatus and presenting method of related items | |
| JP4947709B2 (ja) | コンテンツ配信システム | |
| US20120284283A1 (en) | Information Processing Method, Apparatus, and Computer Program | |
| US20110008020A1 (en) | Related scene addition apparatus and related scene addition method | |
| US20060085416A1 (en) | Information reading method and information reading device | |
| JP5417049B2 (ja) | 番組情報提供装置、番組情報提供システム、番組情報提供方法 | |
| JP2002171231A (ja) | 放送番組案内システム、放送番組案内方法、放送番組案内装置及び放送端末装置と、それらの装置の実現に用いられるプログラム記録媒体 | |
| JP4182743B2 (ja) | 画像処理装置および方法、記録媒体、並びにプログラム | |
| JPH11164217A (ja) | 嗜好統計番組検索テレビシステム | |
| JP4732815B2 (ja) | 情報推薦装置、情報推薦方法、及びプログラム | |
| JP2003199084A (ja) | 番組編集システム、番組情報検索システム、番組情報取得システム及び番組編集プログラム、並びに番組編集方法 | |
| Echigo et al. | Personalized delivery of digest video managed on MPEG-7 | |
| CN100524297C (zh) | 信息处理设备、信息处理方法、记录介质和程序 | |
| JP2001326860A (ja) | ディジタル放送における嗜好データ管理方法,ディジタル放送受信装置および嗜好データ管理用プログラムの記録媒体 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| AK | Designated states |
Kind code of ref document: A1 Designated state(s): CN KR US |
|
| AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
| WWE | Wipo information: entry into national phase |
Ref document number: 1020057010032 Country of ref document: KR |
|
| ENP | Entry into the national phase |
Ref document number: 2006047678 Country of ref document: US Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 10538658 Country of ref document: US Ref document number: 20038A56926 Country of ref document: CN |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2003778860 Country of ref document: EP |
|
| WWP | Wipo information: published in national office |
Ref document number: 1020057010032 Country of ref document: KR |
|
| WWP | Wipo information: published in national office |
Ref document number: 2003778860 Country of ref document: EP |
|
| WWP | Wipo information: published in national office |
Ref document number: 10538658 Country of ref document: US |