JP4333254B2 - Information processing apparatus and method, recording medium, and program - Google Patents

Description

  The present invention relates to an information processing apparatus and method, a recording medium, and a program, and more particularly to an information processing apparatus and method, a recording medium, and a program that can recommend a program that suits the user's preference when recording the program. About.

  When making a recording reservation for a program using a recording device such as a so-called video recorder or HDD (Hard Disc Drive) recorder that records the broadcasted program, the program to be reserved for recording is recommended based on user preferences. Service is spreading.

  A method for determining a recommended program to be presented at the time of recording reservation is, for example, displaying a predetermined number of programs extracted as recommended programs by a plurality of algorithms, or switching programs extracted by the respective algorithms. It is recommended to display it as a recorded program.

  As the above-mentioned algorithm, for example, the user's preference is registered by registering program information (program metadata) such as a broadcasting station (channel) and broadcasting time in advance, and is included in an EPG (Electronic Program Guide). Compared to the metadata of each program, a program that matches is extracted as a recommended program.

In addition, as other algorithms, an n-dimensional attribute vector is added in advance as attribute information of a broadcast program, and user preference information registered in advance or attributes of a program reproduced or reserved by a user are recorded. There is also a method of extracting a recommended program by comparing a selection vector generated based on an average value of each attribute item of a vector with an attribute vector (see, for example, Patent Document 1).
JP 2001-160955 A

  However, as described above, when a plurality of algorithms are used and, for example, five programs are extracted and presented as recommended programs, based on any one of the desired algorithms, For a user who only needs to recommend a program, presentation of five programs individually recommended by a plurality of undesired algorithms is unnecessary, and there is a possibility that presenting as a recommended program may be troublesome. there were.

  In addition, in order to solve the above-described problems, when the program is switched so that the program is recommended only by an algorithm desired by the user and presented, for example, a program broadcast in a predetermined same time zone However, since the program is not presented unless it matches the user's preference, programs that are broadcast in the same time zone and cannot be presented with the desired algorithm will not be presented. Even if there is a program that you want to record during the time period, it is not presented because it is a program that differs from the previous preferences, and as a result, there is a risk that you may fail to reserve the program you wanted to record. It was.

  The present invention has been made in view of such a situation, and according to a change in user's preference, recommends a program by switching an algorithm so that an optimum program for the user can be recommended.

The information processing apparatus according to the present invention includes metadata acquisition means for acquiring metadata of a plurality of programs, and which of the programs recommended so far for each of the plurality of algorithms is accepted and reserved for recording. An operation history acquisition means for acquiring an operation history indicating the number of programs, a program number determination means for determining the number of programs recommended by each of the plurality of algorithms from the operation history , metadata of the plurality of programs, and each of the plurality of algorithms And extracting means for extracting programs by a plurality of algorithms on the basis of the number of programs recommended in the above, and recommendation means for recommending the programs extracted by the extracting means .

According to the information processing method of the present invention, a metadata acquisition step for acquiring metadata of a plurality of programs, and which of the programs recommended so far are accepted for each of the plurality of algorithms, and whether or not the recording is reserved. An operation history acquisition step for acquiring an operation history indicating the number of programs, a program number determination step for determining the number of programs recommended by each of the plurality of algorithms from the operation history , metadata of the plurality of programs, and each of the plurality of algorithms Based on the number of programs to be recommended, and an extraction step for extracting a program by a plurality of algorithms, and a recommendation step for recommending the program extracted by the processing of the extraction step.

The recording medium program of the present invention is recommended for each of a plurality of algorithms based on an operation history indicating whether a program has been accepted and reserved for recording among programs recommended so far for each of a plurality of algorithms. A program number determining step for determining the number of programs, an extracting step for extracting a program with a plurality of algorithms based on metadata of the plurality of programs and the number of programs recommended by each of the plurality of algorithms, and an extracting step to perform the recommendation step of recommending a program extracted by processing in a computer.

The program of the present invention is the number of programs recommended by each of a plurality of algorithms based on an operation history indicating whether a program has been accepted and reserved for recording among programs recommended so far for each of a plurality of algorithms. The number of programs determining step, the extraction step of extracting a program with a plurality of algorithms based on the metadata of the plurality of programs and the number of programs recommended by each of the plurality of algorithms, and the processing of the extraction step A recommendation step of recommending the extracted program is executed by a computer.

In the information processing apparatus, method, and program of the present invention, a plurality of algorithms from an operation history indicating whether a program has been accepted and a recording reservation has been made among programs recommended so far for each of a plurality of algorithms. each number of programs to be recommended is determined by the, and metadata of a plurality of programs, on the basis of the number of programs to be recommended in each of the plurality of algorithms, programs are extracted by a plurality of algorithms, the extracted program Recommended.

  The information processing apparatus of the present invention may be an independent apparatus or a block that performs information processing.

  According to the present invention, it is possible to recommend a program according to the user's preference.

  Embodiments of the present invention will be described below. The correspondence relationship between the invention described in this specification and the embodiments of the invention is exemplified as follows. This description is intended to confirm that the embodiments supporting the invention described in this specification are described in this specification. Therefore, although there is an embodiment which is described in the embodiment of the invention but is not described here as corresponding to the invention, it means that the embodiment is not It does not mean that it does not correspond to the invention. Conversely, even if an embodiment is described herein as corresponding to an invention, that means that the embodiment does not correspond to an invention other than the invention. Absent.

  Further, this description does not mean all the inventions described in this specification. In other words, this description is for the invention described in the present specification, which is not claimed in this application, that is, for the invention that will be applied for in the future or that will appear and be added by amendment. It does not deny existence.

That is, the information processing apparatus according to the present invention includes a metadata acquisition unit (for example, the data acquisition unit 41 in FIG. 3) that acquires metadata of a plurality of programs, and a program that has been recommended so far for each of a plurality of algorithms. An operation history acquisition unit (for example, the operation log acquisition unit 46 in FIG. 3) that acquires an operation history indicating whether a program has been accepted and a recording reservation has been made, and a plurality of algorithms are recommended from the operation history. Based on the program number determining means for determining the number of programs (for example, the recommended program determining unit 49 in FIG. 3), the metadata of the plurality of programs, and the number of programs recommended by each of the plurality of algorithms , extracting means for extracting a program with an algorithm (e.g., similar system program recommendation section 43, and, staple-based program recommendation section 53 of FIG. 3) recommending means (eg for recommending and, the program extracted by the extraction means If, characterized in that it comprises a recommended program determining unit 49) and FIG.

The information processing method according to the present invention includes a metadata acquisition step for acquiring metadata of a plurality of programs (for example, the process of step S41 in FIG. 5), and a program that has been recommended so far for each of a plurality of algorithms. An operation history acquisition step (for example, processing in step S43 in FIG. 5) for acquiring an operation history indicating whether or not a program has been accepted and a recording reservation has been made, and the number of programs recommended by each of a plurality of algorithms from the operation history The number of programs is determined by a plurality of algorithms based on the number of programs determination step (for example, the process of step S112 in FIG. 17), the metadata of the plurality of programs, and the number of programs recommended by each of the plurality of algorithms. extracting (for example, step S113, S114 of FIG. 17) and recommendations, the program extracted by processing in the extraction step That recommendation step (for example, step S115 in FIG. 17), characterized in that it comprises a.

  Since the correspondence relationship between the recording medium and the program of the present invention is the same as that of the information processing method, the description thereof is omitted.

  FIG. 1 is a diagram showing a configuration of an embodiment of a distribution system to which the present invention is applied.

  The distribution servers 12-1 to 12-n distribute programs to the recording / playback apparatuses 14-1 to 14-n via the network 11 such as the Internet. Further, in FIG. 1, the distribution servers 12-1 to 12-n are provided with, for example, broadcasting facilities so as to distribute a program using terrestrial waves or satellite waves via an antenna or a satellite (not shown). It may be. Further, when distributing the program, the distribution servers 12-1 to 12-n distribute an EPG (Electronic Program Guide) including metadata in the distributed signal as necessary. Information about the data is also distributed to the recommendation server 13. In the following description, the distribution servers 12-1 to 12-n are simply referred to as the distribution server 12 unless otherwise distinguished, and the same applies to other configurations.

  The recommendation server 13 is an EPG that is information related to a program broadcast from the distribution server 12, or metadata including more detailed information than the EPG, and a user supplied from each of the recording / playback apparatuses 14-1 to 14-n. When a program recording reservation operation is performed on the basis of the operation log, information for recommending a program that suits the user's preference is provided to the recording / playback apparatuses 14-1 to 14-n.

  When the amount of EPG information superimposed on a general broadcast signal is sufficient information for the processing described below, the same EPG that is superimposed on the general broadcast signal is used for the processing. Anyway. In addition, when the amount of EPG information superimposed on a general broadcast signal is not sufficient information for the processing described below, the processing is performed in addition to the EPG superimposed on a general broadcast signal. Alternatively, the metadata may be used alone. Hereinafter, in this embodiment, EPG including metadata is used, and this information is referred to as EPG data or metadata.

  The recording / playback apparatuses 14-1 to 14-n record a program distributed from the distribution server 12 via the network 11 on a mounted recording medium or a built-in recording medium (for example, a hard disk), and The recorded program is supplied to a television receiver (not shown) and reproduced. Further, the recording / reproducing apparatus 14 acquires EPG data (metadata) distributed from the distribution server 12 and accepts a recording reservation. At this time, the user's operation log is supplied to the recommendation server 13 in response to the recording reservation operation of the broadcast program, and the recommended program information supplied from the recommendation server 13 is received based on the operation log. Is displayed at the time of the recording reservation operation as appropriate. Therefore, the user can execute the recording reservation operation while viewing the information of the recommended program supplied from the recommendation server 13 when operating the recording / playback apparatus 14 to execute the recording reservation of the program. The recording / reproducing apparatus 14 may be a so-called hard disk recorder having a large-capacity hard disk as a recording medium.

  FIG. 2 is a block diagram illustrating a configuration of the distribution server 12.

  The data acquisition unit 21 acquires data from the metadata database 26 (hereinafter also referred to as the metadata DB 26) and the streaming data database 27 (hereinafter also referred to as the streaming data DB 27), supplies the data to the data transmission unit 25, and EPG data (Metadata) is supplied to the metadata extraction unit 22. In addition, the data acquisition unit 21 executes processing for grouping EPG data registered in the metadata database 26 according to the content thereof.

  The metadata extraction unit 22 extracts data necessary for generating the program vector PP from the EPG data supplied from the data acquisition unit 21 and supplies the data to the program vector generation unit 23. The program vector generation unit 23 generates a program vector PP based on the metadata, associates the program-side effect vector EfPP stored in the data storage unit 24 with the data, and supplies it to the data transmission unit 25 as necessary. To do.

  The data storage unit 24 stores the program side effect vector EfPP, which is information necessary for generating the program vector PP, as necessary.

  Based on the viewpoint of the production side and the broadcast side on how to earn the audience rating, for example, the characteristic that the element of genre and content is strong in the educational program, and the characteristic that the element of the performer is strong in the variety program etc. In drama, etc., there is a characteristic that the elements of performers and screenwriters are strong. In order to correctly extract program characteristics, it is necessary to use these characteristics. That is, of the elements constituting the program vector PP, which element is important in the matching process executed to recommend a program (similar recommended program) that matches the user's preference depends on the genre of the program. Different.

  That is, when the genre of the program is “Liberal Arts / Documents”, the important item is not the performer but the contents and title. On the other hand, when the program genre is “variety”, the important item is a performer, and when the program genre is “drama”, the important items are a performer and a screenwriter. When these are used to generate the program vector PP, a program-side effect vector that defines the degree of contribution in the matching process for each item is set for each genre of the program and stored in the data storage unit 24.

  The data transmission unit 25 receives the EPG data and streaming data supplied from the data acquisition unit 21, and the program vector PP and the program side effect vector EfPP supplied from the program vector generation unit 23 via the network 11. To the recommendation server 13 and the recording / playback apparatuses 14-1 to 14-n.

  Next, the configuration of the recommendation server 13 will be described with reference to the block diagram of FIG.

  The data acquisition unit 41 acquires EPG data together with the program vector PP transmitted from the distribution server 12 and the program side effect vector EfPP corresponding to the program vector PP. The program vector extraction unit 42 extracts a program vector PP necessary for matching processing or a program vector PP necessary for user model generation from the program vector PP acquired by the data acquisition unit 41, and if necessary, The program side effect vector EfPP corresponding to the program vector PP is supplied to the similar program recommendation unit 43. The metadata extraction unit 52 extracts the EPG data acquired by the data acquisition unit 41, that is, metadata, and supplies the extracted EPG data to the standard program recommendation unit 53.

  The operation input unit 44 includes input devices such as a keyboard, a touch pad, and a mouse, for example. The operation input unit 44 receives initial registration information input based on a user report and a topic input for generating a user vector. The data is output to the registration storage unit 45. The initial registration storage unit 45 registers initial registration contents supplied from the operation input unit 44 and topics for generating user vectors, and an operation log acquisition unit 46 or a similar program recommendation unit as necessary. 43. Further, the content stored in the initial registration storage unit 45 is obtained by inputting information previously listened to by the user from the operation input unit 44.

  The operation log acquisition unit 46 acquires an operation log from the recording / playback device 14 and stores the information in the history storage unit 47 as an operation history.

  Here, the operation history is information indicating which of the programs recommended by the recommended program determining unit 49 has been accepted and reserved for recording. Further, the operation history is information indicating whether a standard recommended program or a similar recommended program, which will be described later, has been accepted and actually reserved for recording.

  The similar program recommendation unit 43 extracts a recommended program based on matching between the program vector extracted from the program vector extraction unit 42 and the user vector UP supplied from the initial registration storage unit 45 and determines a recommended program. Supplied to the unit 49.

  When the program vector PP and the user vector UP are vectorized by arranging all the detailed elements in one column, the title, keyword, etc. are composed of a plurality of words. Items such as genres have the same weight in the vector. Therefore, the normalization processing unit 61 of the similar program recommendation unit 43 normalizes the title and contents, which are items constituted by words, by dividing the word by the number of words for each program. For example, when the title Tm = {Tokaido-1, Mitani-1, Kaidan-1}, the title Tm = {Tokaido: 0.33, Mitani: 0.33, Kaidan: 0.33} is normalized. As a result, both the title and the content have a total weight of 1 in the item, so that no inconvenience occurs in the matching process.

  The vector calculation unit 62 executes a matching process between the program vector PP and the user vector UP for each program, and based on these results, recommends a program having a high similarity between the program vector PP and the user vector UP. The program is supplied to the recommended program determination unit 49 as a program.

  When the program vector PP and the user vector UP are represented by a vector in which all the elements of the detailed items are arranged in one column, the vector calculation unit 62 calculates the cosine distance between the user vector UP and the program vector PP ( cos θ), the similarity SimUP between the program vector PP and the user vector UP is obtained as shown in the following equation (1). The cosine distance is a value obtained by dividing the inner product of two vectors by the product of the absolute values of the vectors, as shown in Equation (1).

    SimUP = cosθ = ((ef × UP) · PP) / (| ef × UP | × | PP |) (1)

  In Equation (1), PP represents the program vector PP, UP represents the user vector UP, and ef represents the program side effect vector efPP or the user side effect vector efUP. “·” Indicates an inner product, “×” indicates element multiplication (scalar operation), and the same applies hereinafter.

  Further, when the program vector PP and the user vector UP are vectorized for each large item, the vector calculation unit 62 calculates the similarity SimUP between the program vector PP and the user vector UP for each large item. Can do. For example, in the large item “title” broken down into words, the user vector UP is the title Tup = {school-1, ghost story-1, toilet-1}, and the supplied program vector PP is the title Tm = In the case of {Tokaido-1, Mitani-1, Kaidan-1}, if the unit vector length is 1, the vector length (absolute value) is the square root of the sum of the squares of the elements. When the vector is {1, 1, 1}, the cosine distance cos θ, which is the similarity between the titles, is calculated as in the following equation (2).

    cosθ = (1 ・ 1) / (√3 × √3) = 1/3 (2)

  For example, when the user vector UP is the user vector UP = {title Tup, genre Gup, performer Pup, screenplay / original / production Aup, content (keyword) Kup}, Since similarity is obtained for each large item by the same calculation, the similarity SimUP is calculated as the similarity Sim of the following equation (3).

      Sim = cosθt + cosθg + cosθp + cosθa + cosθk (3)

  Here, cosθt is a cosine distance between the program vector PP and the user vector UP in the large item “title”, and cosθg is a cosine distance between the program vector PP and the user vector UP in the large item “genre”. Cosθp is a cosine distance between the program vector PP and the user vector UP in the large item “performer”, and cosθa is the program vector PP and the user vector in the large item “screenplay / original / production”. The cosine distance with UP, and cos θk is the cosine distance between the program vector PP and the user vector UP in the major item “content”.

  When the similarity SimUP is calculated as the sum of the calculation results for each large item, there is no weight bias between items, which is synonymous with normalization. Therefore, unlike a vector in which all elements are arranged in one column, normalization processing by the normalization processing unit 61 may not be performed.

  That is, when normalization is used and a vector in which all elements are arranged in one column is used, items such as titles and contents are easily compared with items such as broadcast stations and genres, which are likely to accumulate in frequency. In, as the history increases, the number of words increases, but the frequency of each word hardly increases.

  For this reason, when all elements are used and the total is taken for each element, the influence of items such as broadcast stations and genres that tend to overlap frequently increases, so the user is a fan of commentator A, for example. So, if you like to watch “Live broadcast of the game of Team B that commentator A explains”, the information “Live broadcast of baseball” that is a genre is easy to overlap as a history. The information “Explanator A” is difficult to overlap as history. Therefore, there may be a case where the live broadcast of the game of the team B which is explained by another commentator is recommended and the variety program in which the commentator A appears is not recommended.

  On the other hand, by performing normalization or calculating the sum of the calculation results for each major item as the similarity SimUP, the commentator A is not affected by the magnitude of the history frequency. It is possible to recommend a variety program appearing, and to reflect the user's preference more accurately.

  The vector calculation unit 62 generates the user initial registration information stored in the initial registration storage unit 45, the program side effect vector EfPP transmitted in association with the program vector PP, or the user information registration unit 63. The similarity SimUP can also be calculated by weighting with the registered user side effect vector EfUP.

  Based on the similarity SimUP calculated by the method as described above, the vector calculation unit 62 outputs recommended information, for example, by using the upper predetermined number (for example, 10) programs having high similarity to the user vector as recommended programs. To the unit 50.

  The user information registration unit 63 generates and stores the user side effect vector EfUP based on the initial registration contents of the user supplied from the initial registration storage unit 45 or the user vector UP supplied from the history storage unit 47. To do. The user-side effect vector EfUP is a vector that indicates to the user which elements of the major items are important for program selection and items that are weighted for program selection, or , A vector indicating the user's preference in each item.

  In other words, the user-side effect vector EfUP defines which item contributes greatly in matching between the program vector PP and the user vector UP.

  The user side effect vector EfUP may be set by the user or may use a predetermined value, but may be generated based on the initial registration contents of the user registered in the initial registration storage unit 45. Anyway.

  Specifically, when the user side effect vector EfUP is information indicating which of the major items is important for the user in selecting a program, the program vector PP = {title Tm, genre Gm , Time zone Hm, broadcast station Sm, performer Pm, screenplay / original / production Am, content Km}, if the genre is important to the user, for example, the effect vector EfUP = (1, 5, 1, 1, 1 , 1, 1). On the other hand, when the performer and the genre are important for the user, for example, the effect vector EfUP = (1, 3, 1, 1, 5, 1, 1) is set.

  When the user side effect vector EfUP is a vector indicating the user's preference in each item, the large item genre Gm = {drama, variety, sports, movie, music, children / education, education / documents, news / When the genre of the program that the user thinks preferable in the news report, etc. is education / document, the user effect vector EfUP is, for example, the genre Gm = {0, 0, 0, 0, 0, 0, 5, 0,0}.

  Further, the user side effect vector EfUP may be generated based on the user vector UP or by counting programs viewed by the user for a certain period. Further, the user-side effect vector EfUP can be generated for each genre.

  In this specification, the user-side effect vector efUP and the program-side effect vector efPP can be selected, and they are collectively referred to as the effect vector ef without any particular distinction.

  That is, the similar program recommendation unit 43 resembles a program extracted by an algorithm that extracts a recommended program based on a similarity based on a cosine distance between a user effect vector obtained by multiplying the user vector UP by the effect vector and the program vector PP. It outputs to the recommended program determination part 49 as a system recommended program.

  The recommended information output unit 50 registers the recommended program information supplied by the recommended program determining unit 49 in the recommended program list 51 and supplies it to the recording / reproducing apparatus 14 via the network 11.

  The metadata extraction unit 52 extracts the metadata of each program from the data distributed from the distribution server 12 acquired by the data acquisition unit 41 and supplies the extracted metadata to the standard system recommendation unit 53. Based on the metadata for each program supplied from the metadata extraction unit 52, the standard program recommendation unit 53 stores the large items corresponding to the preferences of the large items initially registered in the initial registration storage unit 45. For each piece of information, the extracted program is supplied to the recommended program determining unit 49 as a standard recommended program by an algorithm that extracts a program with the same metadata.

  Based on the history information stored in the history storage unit 47, the acceptance rate calculation unit 48 receives the acceptance rates of the program recommended by the standard program recommendation unit 53 and the program recommended by the similar system recommendation unit 43. That is, the ratio of programs actually reserved for recording by the user with respect to the number of recommended programs is obtained and output to the recommended program determination unit 49.

  The recommended program determining unit 49 determines the number of standard recommended programs supplied from the standard program recommending unit 53 for the number of programs that can be displayed on the display unit 90 (FIG. 4) of the recording / playback device 14, and similar programs. The ratio of the number of similar recommended programs supplied from the recommendation unit 43 is determined based on the acceptance rate, and the determined number of standard recommended programs and similar recommended programs are extracted from each to determine the final recommendation A program is determined and supplied to the recommendation information output unit 50.

  That is, the recommendation server 13 determines the ratio of the number of programs to the total number of recommended programs that can be displayed based on the acceptance rate based on the recommended programs extracted by the two types of algorithms, the standard recommended program and the similar recommended program. Determine the recommended program.

  Next, the configuration of the recording / playback apparatus 14 will be described with reference to the block diagram of FIG.

  The operation input unit 81 receives an operation input from the user, supplies a control signal corresponding to the user's operation input to each unit of the recording / playback device 14, and supplies the operation content of the user to the operation log list 82 for storage. . The operation log of the user stored in the operation log list 82 is acquired by the operation log acquisition unit 46 of the recommendation server 13 described with reference to FIG.

  The recording setting unit 83 displays EPG data (metadata) supplied from the distribution server 13 as an EPG image on the display unit 90 (or a television receiver (not shown), etc.), and displays a recommended program as necessary. The image is read from the recommended program display image 89 and displayed. Further, the recording setting unit 83, based on the displayed EPG image and recommended program information, the broadcast start time and broadcast end time of the program to be recorded, which is input by operating the operation input unit 81 by the user, and Information necessary for recording processing such as broadcast channels is extracted. When the user operation input supplied from the operation input unit 81 is a recording reservation, the recording setting unit 83 registers information necessary for performing the recording process in the recording reservation list 84 and is supplied from the operation input unit 81. If the user's operation input is a recording process of a program that is currently being broadcast, information necessary for performing the recording process is supplied to the recording control unit 85.

  The recording control unit 85 is based on the information required for performing the recording process supplied from the recording setting unit 83 or the recording corresponding to the current time among the recording reservation information registered in the recording reservation list 84. By extracting the reservation information, a control signal indicating a broadcast channel of a program to be recorded (a signal specifying the distribution server 12) is generated and supplied to the recording / playback processing unit 87, and control for executing the recording process A signal is generated and supplied to the recording / playback processing unit 87.

  The data input unit 86 receives an input of a broadcast signal distributed via the network 11 such as the Internet and supplies it to the recording / playback processing unit 87. The recording / playback processing unit 87 is configured such that a recording medium such as a magnetic tape, an optical disk, a magnetic disk, a magneto-optical disk, or a semiconductor memory can be mounted therein, for example, a hard disk, A recording medium such as a semiconductor memory is provided, and a broadcast program signal supplied from the data input unit 86 can be recorded on the recording medium, and information can be reproduced from the recording medium. Specifically, when the recording medium that can be attached to the recording / playback processing unit 87 is a magnetic tape, the recording / playback processing unit 87 has a magnetic head, and receives a broadcast signal supplied from the data input unit 86 to the magnetic tape. Information is recorded (that is, recorded) or information recorded on the magnetic tape is reproduced and supplied to a television receiver (not shown) for reproduction.

  Next, the recording reservation process will be described with reference to FIG.

  In step S <b> 1, the data acquisition unit 21 of the distribution server 12 acquires EPG data composed of metadata from the metadata database 26, and supplies the EPG data to the data transmission unit 25 and the metadata extraction unit 22.

  In step S <b> 2, the metadata extraction unit 22 receives EPG data acquired by the data acquisition unit 21 from the metadata DB 26, extracts metadata necessary for generating the program vector PP, and sends it to the program vector generation unit 23. Output.

  FIG. 6 shows an example of metadata. The metadata includes, for example, “movie-Japanese movie” as the genre, “Tokaido Mitani Kaidan” as the title of the movie, date of broadcasting and distribution source data, date and time of broadcasting, name of broadcasting station, and broadcasting The time is included. Further, the metadata includes data such as a director name, a screenwriter name, a photographer (cameraman), a music representative, a performer, etc., and a description of a movie as the contents of the program.

  In step S3, the program vector generation unit 23 performs morphological analysis on titles, contents, and the like included in the metadata as necessary, and breaks them down into words. Specifically, the program vector generation unit 23 uses the title of the movie included in the metadata as a title and breaks it down into three words “Tokaido”, “Mitani”, and “Kaidan”. In addition, the program vector generation unit 23, in the metadata, as a movie commentary, as shown in FIG. 5, is a masterpiece of a Japanese movie horror that depicts the world of “'59 Mitani Kaidan”, which is famous for its beautiful '59 Shinsaiho style. ”Is extracted, the words included in the commentary are extracted and“ Seiho ”,“ Style ”,“ Beauty ”,“ Plenty ”,“ Famous ”,“ Mitani ”,“ Kaidan ” ”,“ World ”,“ Draw ”,“ Japanese Film ”,“ Horror ”,“ Masterpiece ”.

  In step S4, the program vector generation unit 23 vectorizes each item included in the metadata to generate a program vector PP. The generated program vector PP is output to the data transmission unit 25 and transmitted to the recommendation server 13 and the recording / playback device 14 via the network 11. The item vectorization may be such that all the detailed elements are arranged in one column, or may be vectorized for each major item after being separated into major items.

  When vectorization is performed for each major item, for example, as shown in FIG. 7, the major item is divided into seven items of title, genre, time zone, broadcast station, performer, screenplay / original / production, and content. The vector PP = (Tm, Gm, Pm, Am, Km) is generated. The contents of each item are title Tm = {title1, title2,...}, Genre Gm = {drama, variety, sports, movie, music, children / education, education / documents, News / News, Other}, Hour Hm = {Morning, Noon, Evening, Golden, Late Night}, Broadcasting Station (TV Station) Sm = {NNK General, NNK Education, Asia TV, TTS, Buji, Tele-day , Higashi, NNK Satellite 1, NNK Satellite 2, WOWO}, Performer (Person) Pm = {person A, person B, ...} Screenplay / Original / Director, etc. (Author) Am = {person a, person b,...} Contents (Keyword) Km = {kw1, kw2,.

  Among the seven major items described above, the major items “genre”, “broadcasting station”, and “time zone” can be fixed in type, so that detailed elements can be represented by numerical vectors. In the case of a broadcasting station, for example, in the broadcasting station Sm = {NNK General, NNK Education, Asia TV, TTS, Buji, Tele-day, East Tokyo, NNK Satellite 1, NNK Satellite 2, WOWO} Is WOWO, the broadcast station vector can be represented by broadcast station Sm = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1}. In the case of a genre, for example, in the genre Gm = {drama, variety, sport, movie, music, for children / education, education / documents, news / reports, etc.}, the corresponding program genre was education / documents. In this case, the genre vector can be represented by genre Gm = {0, 0, 0, 0, 0, 0, 1, 0, 0}.

  On the other hand, for items that cannot be represented by numeric vectors, such as the major items “title”, “performer”, “screenplay / original / production”, “content”, the item value depends on the frequency of words contained in the vector. (Word) and weight (numerical value) are associated with each other. For example, the major item “title” is represented by elements each composed of a word and a numerical value, such as title Tm = {Tokaido-1, Mitani-1, Kaidan-1}. In this example, for example, “Tokaido-1” means that the frequency of the word “Tokaido” is 1.

  Through such processing, a program vector PP is generated and distributed to the recommendation server 13 and the recording / recording apparatus 14. Specifically, when the program vector PP is generated from the program metadata described with reference to FIG. 6, the program vector PP = {title Tm = {Tokaido-1, Mitani-1, Kaidan-1}, genre Gm = {0,0,0,1,0,0,0,0,0}, time zone Hm = {0,0,0,0,1}, broadcast station Sm = {0,0,0,0,0 , 0, 0, 0, 0, 1}, performer Pm = {Katsumi Wakasugi-1, Shigeru Amami-1, Toshihiko Emi-1, Ryujiro Nakamura-1, Noriko Nishizawa}, Screenplay / Original / Director Am = {Nobuo Nakagawa-1, Masakazu Onuki-1, Yoshihiro Ishida-1, Shoji Nishimoto-1, Sota Watanabe-1}, Content Km = {Nishiho-1, Style-1, Beauty-1, Plenty-1, Famous-1, Mitani-1, Kaidan-1, World-1, Drawing-1, Japanese film-1, Horror-1, Masterpiece-1}} are generated, and the recommendation server 13 and the video recording device 14 is transmitted.

  In the program vector PP generated in this way, for example, the starring is weighted out of the constituent elements of the performer Pm, or the director is weighted out of the constituent elements of the script / original / production Am, and the program vector PP is You may make it produce | generate. In such a case, the constituent elements of the program vector PP are, for example, performers Pm = {Katsumi Wakasugi-3, Shigeru Amami-2, Toshihiko Emi-1, Ryujiro Nakamura-1, Noriko Nishizawa-1}, Screenplay / Original / Production Am = {Nobuo Nakagawa-3, Shoichi Onuki-1, Yoshihiro Ishida-1, Shoji Nishimoto-1, Sota Watanabe-1}.

  In addition, as described above, which element is important for generating the program vector PP depends on the genre of the program. When the program side effect vector EfPP indicating what elements are important for each genre is stored in the data storage unit 24 as program side effect vector information, the program side effect vector EfPP is converted into the program vector PP. You may make it transmit in response to. The program side effect vector EfPP is set corresponding to the major items of the program vector PP.

  In the case of the program vector PP = {title Tm, genre Gm, time zone Hm, broadcast station Sm, performer Pm, screenplay / original / production Am, content Km}, for example, if the genre of the program is “Education / Document”, Since the important items are the contents and title (when the weighting value is 3), the program side effect vector EfPP = {3, 1, 1, 1, 1, 1, 3}. On the other hand, when the genre of the program is “variety”, the important item is the performer (when the weighting value is 5), so the program side effect vector EfPP = {1, 1, 1, 1, 5, 1,1}. Also, when the program genre is “drama”, the important items are the performer (when the weighting value is 2) and the screenwriter, especially when the screenwriter is important (when the weighting value is 3). The program side effect vector EfPP = {1, 1, 1, 1, 2, 3, 1}.

  In step S <b> 5, the program vector generation unit 23 extracts the corresponding effect vector from the effect vector information stored in the data storage unit 24 based on the genre of the supplied metadata program. For example, when the genre of the program is “variety”, an effect vector EfPP = {1, 1, 1, 1, 5, 1, 1} for weighting performers is extracted from the data storage unit 24.

  In step S6, the program vector generation unit 23 associates the effect vector EfPP extracted in step S5 with the program vector PP generated in step S14 and distributes it together with the EPG data via the data transmission unit 25.

  By such processing, a program vector PP is generated, and a program side effect vector EfPP for weighting important items is associated with the recommendation server 13 via the network 11 based on the genre of the program. And to the recording / recording apparatus 14.

  In step S21, the recording setting unit 83 determines whether or not a recording reservation operation is requested by the operation input unit 81 being operated by the user, and the process is repeated until the recording reservation operation is requested. If it is determined that a recording reservation operation is requested, the process proceeds to step S22.

  In step S <b> 22, the recording setting unit 83 acquires EPG data distributed from the distribution server 13. That is, the EPG data distributed from the distribution server 12 is extracted and acquired by the processes in steps S11 to S16.

  In step S23, the recording setting unit 83 executes an EPG display process for displaying an EPG screen on the display unit 90 or a television receiver (not shown).

  Here, the EPG display processing will be described with reference to the flowchart of FIG.

  In step S61, the recording setting unit 83 acquires information on the current date and time from a real time clock (not shown).

  In step S62, the displayable range of the display unit 90 or a television receiver (not shown) is acquired. For the display range of the display unit 90, information on the size of the display image is stored in advance, and the display range is acquired based on the information. For a television receiver (not shown), the television receiver is inquired to obtain information on the size of the display screen (information such as the number of pixels in the horizontal direction and the vertical direction).

  In step S63, the recording setting unit 83 acquires setting information related to EPG display. The setting information related to the EPG display is information set by the processing in step S25 described later, and is stored in a memory (not shown) by the recording setting unit 83, and sets the EPG display method. In a state in which the setting information is not operated (a state in which the setting information is not operated by the user), that is, in a default state, the EPG data is displayed without being processed, so that it is considered that no setting information exists.

  In step S64, the recording setting unit 83 determines whether setting information exists. That is, as described above, when the setting information is not operated by the user, it is considered that the setting information does not exist. Therefore, the recording setting unit 83 actually sets the setting information to the default value. Based on whether or not there is an operation on the setting information, it is determined that the setting information exists. Conversely, when no operation is added to the setting information, it is determined that the setting information does not exist. Is done.

  For example, in step S64, when the setting information is operated by the process of step S25 described later, it is determined that the setting information exists, and the process proceeds to step S65.

  In step S65, the recording setting unit 83 reads the EPG data corresponding to the date and time acquired in the process of step S61, processes the EPG data corresponding to the setting information, and generates a display screen. In step S66, the display setting is displayed. The EPG display image is displayed on the unit 90 or a television receiver (not shown).

  On the other hand, if it is determined in step S64 that the setting information does not exist, that is, the operation is not performed in the default state, the process of step S65 is skipped, and the EPG display screen corresponding to the information of the EPG data itself is displayed. Is displayed.

  Now, the description returns to the flowchart of FIG.

  In step S24, the recording setting unit 83 determines whether or not an instruction to change the setting information has been given. For example, when the operation input unit 81 is instructed to change the setting information by viewing the EPG display screen displayed by the process of step S23 and the user performing some processing, the process is Proceeding to S25, a setting information changing process is executed.

  Here, with reference to the flowchart of FIG. 9, the setting information change process related to the display of EPG will be described.

  In step S81, the recording setting unit 83 displays a setting information setting screen as shown in FIG. 10 on the display unit 90 or a television receiver (not shown), for example. In FIG. 10, genre setting, time zone setting, and performer setting are displayed from the top in the figure, and each display area can be designated by selecting with a pointer or the like.

  In step S82, the recording setting unit 83 makes an inquiry to the input operation unit 81 to determine whether or not the genre setting on the setting screen in FIG. 10 is selected. For example, the genre setting on the setting screen in FIG. If it is determined that the process has been performed, the process proceeds to step S83.

  In step S83, the recording setting unit 83 displays a genre setting screen as shown in FIG. 11 on the display unit 90 or a television receiver (not shown). In FIG. 11, three types of genres “drama”, “sports”, and “news” are displayed from the top in the figure, and a round radio button is displayed at the left end of each display area. , Can be selected with a pointer or the like.

  In step S84, the recording setting unit 83 makes an inquiry to the operation input unit 81 to determine which genre has been selected, and the same processing is repeated until it is determined that one has been selected. For example, as shown in FIG. 11, the radio button provided on the left side of “drama” is selected (in the figure, it is shown that it is selected with a black circle), and “drama” is selected. If it is determined that the recording has been made, the recording setting unit 83 stores the selected genre as setting information in step S85, and the process proceeds to step S86. All information on the operation input unit 81 operated by the user, including information on selecting these genres as setting information, is accumulated in the operation log list 82.

  If it is determined in step S86 that the time zone setting in FIG. 10 has been selected, the process proceeds to step S87.

  In step S87, the recording setting unit 83 displays a time zone setting screen on the display unit 90 or a television receiver (not shown). The time zone setting screen is basically the same as the genre setting display screen shown in FIG. 11. For example, instead of the genres of “drama”, “sports”, and “news”, “ “0:00 to 6:00”, “6:00 to 12:00”, and the like are displayed, and a radio button for selecting one can be selected with a pointer or the like, and is not shown.

  In step S88, the recording setting unit 83 makes an inquiry to the operation input unit 81 to determine which time zone has been selected, and the same processing is repeated until it is determined that one has been selected. If it is determined that one of the time zones has been selected, in step S89, the recording setting unit 83 stores the selected time zone as setting information, and the process proceeds to step S90.

  If it is determined in step S90 that the performer setting in FIG. 10 has been selected, the process proceeds to step S91.

  In step S91, the recording setting unit 83 displays a performer setting screen on the display unit 90 or a television receiver (not shown). The performer setting screen is basically the same as the genre setting display screen shown in FIG. 11. For example, instead of the genres “drama”, “sports”, and “news”, “ “Wakasugi Katsumi”, “Tenkai Shigeru” and the like are displayed, and a radio button for selecting one can be selected with a pointer or the like, and is not shown.

  In step S92, the recording setting unit 83 makes an inquiry to the operation input unit 81 to determine whether any performer has been selected, and the same processing is repeated until it is determined that any performer has been selected. If it is determined that any performer has been selected, in step S93, the recording setting unit 83 stores the selected performer as setting information, and the process proceeds to step S94.

  In step S94, the recording setting unit 83 makes an inquiry to the input operation unit 81 to determine whether or not the end of the setting information change process is instructed. If it is determined that the end is instructed, the process is as follows. , And returns to the process of step S23 of FIG.

  If the genre is not selected in step S82, the processes in steps S83 to S85 are skipped, and the process proceeds to step S86.

  If the time zone is not selected in step S86, the processing in steps S87 to S89 is skipped, and the processing proceeds to step S90.

  If no performer is selected in step S90, the processes in steps S91 to S93 are skipped, and the process proceeds to step S94.

  If it is determined in step S94 that the setting information change process has not been instructed to end, the process returns to step S81, and the subsequent processes are repeated.

  That is, the setting information can be changed until the end is instructed. Further, after the setting information changing process is performed, the setting information is again instructed in the process of step S24 in FIG. Steps S23 to S25 can be repeated until an EPG display screen on which only the desired program is displayed is displayed, or until a desired program is found.

  The setting information change process described with reference to the flowchart of FIG. 9 changes the EPG display screen displayed by the EPG display process described with reference to the flowchart of FIG.

  More specifically, for example, when the setting information is not changed, an EPG display screen as shown in FIG. 12 is displayed. That is, in the EPG display screen shown in FIG. 12, in the time zone of 16:00 and 17:00, in the case of four types of channels, 6ch (TS TV) is “drama 1” from “16:00 to 17:00”, “ “Weather Forecast 1” and “Drama 2”, 8ch (FJ TV) is “Talk Show 1” and “Weather Forecast 2” at 16 o'clock, “News 1” at 17 o’clock and 10ch (AS TV) ) Is “Drama 3” and “Weather Forecast 3” at 16 o'clock, “News 2” at 17 o'clock including 16 o'clock, and “Talk Show 2” at 16 o'clock in 12ch (TK TV) "Weather forecast 4", and the 17:00 zone is "News 3." In addition, each program is displayed with an EPG that includes a brief description of the program and the name of the performer along with the title. At this time, a program to be reserved for recording can be selected by selecting the display area of each program by operating a pointer or the like with the input operation unit 81.

  Here, for example, when “drama” is selected as the genre as in the genre setting screen shown in FIG. 11, the recording setting unit 83 processes the EPG data by the process of step S65 in the flowchart of FIG. As shown in FIG. 13, the contents of “drama 1” and “drama 2” from 16:00 to 17:00 on 6ch (TS TV) and “drama 3” at 16:00 on 10ch (AS TV). Generate an EPG display screen that displays the selected content. As a result, as shown in FIG. 13, “Talk Show 1”, “Talk Show 2”, “News 1” other than “Drama 1”, “Drama 2”, and “Drama 3” corresponding to “Drama” selected as the genre. "News 2", "News 3", "Weather Forecast 1", "Weather Forecast 2", "Weather Forecast 3", and "Weather Forecast 4" are processed and generated as EPG display screens that are not displayed.

Similarly, when “news” is selected as the genre as in the genre setting screen shown in FIG. 14, the recording setting unit 83 processes the EPG data by the processing in step S65 of the flowchart of FIG. As shown in FIG. 15, “News 1”, “News 2”,
Generate an EPG display screen that is hidden except for “News 3”.

  By changing the EPG display screen as described above, the user can selectively display only the programs that he / she is interested in. As a result, the user can quickly find the program he / she wants to make a recording reservation for. Become.

  In the above processing, as the items to be set, only the genre, the time zone, and the performers have been exemplified, but it goes without saying that, for example, the items correspond to the large items in the program vector and the user vector described above. , Title, broadcast station, screenplay, or content may be set, and other items may be set.

  In addition, the genre includes only three types of items such as “drama”, “news”, and “sports”. However, the genre is not limited to this, but “variety”, “movie”, “ Items such as “music”, “for children”, “education, culture”, or “report” may be used.

  Furthermore, in the above, the case where the program other than the program corresponding to the set item is not displayed on the EPG display screen has been described. For example, the program display font other than the selected item can be reduced, Any method may be used as long as the program of the selected item is displayed so that it can be easily visually recognized.

  Now, the description returns to the flowchart of FIG.

  If it is determined in step S24 that change of the setting information has not been instructed, in step S26, the recording setting unit 83 inquires of the input operation unit 81 and determines whether or not a recorded program has been selected. For example, if any program on the EPG display screen is not selected by the pointer, the process returns to step S23, and the state in which the EPG display screen is displayed and the setting information can be changed is repeated. On the other hand, if it is determined in step S26 that the recorded program has been selected, in step S27, the recording setting unit 83 transmits information indicating that the program to be reserved for recording has been selected to the recommendation server 13, and For example, a confirmation screen as shown in FIG. 16 is displayed. At this time, the recording setting unit 83 supplies the operation log list 82 to the recommendation server 13.

  That is, in FIG. 16, “Do you want to make a recording reservation with the following settings?” Is displayed, and below that, information on the currently selected program is “date and time: 4/4 19: 30-20: 30”. And “Channel: 12ch”, and “Program name:“ Anyone artist ”” is selected.

  In the recommendation server 13, in step S41, the data acquisition unit 41 receives the EPG data and the program vector (including the program side effect vector) transmitted by the processing in steps S1 to S6 described above, and the corresponding program The vector extraction unit 42 extracts a program vector (including the program side effect vector) from this and supplies it to the similar program recommendation unit 43. Similarly, the metadata extraction unit 52 uses the metadata (EPG data). Extract and supply to the standard program recommendation unit 53

  In step S42, the data acquisition unit 41 determines whether a notification notifying that a recorded program has been selected has been received, and repeats the process until the notification is received. For example, if a notification indicating that a recorded program has been selected is transmitted by the process of step S27, it is determined that a notification notifying that a recorded program has been selected has been received, and the process proceeds to step S43. .

  In step S43, the operation log acquisition unit 46 reads out and acquires the operation log list 82 by inquiring of the recording / playback device 14 that has notified that the recorded program has been selected, and the user logs based on the acquired operation log 82. The operation history is stored in the history storage unit 47.

  In step S44, recommended program display screen generation processing is executed.

  Here, the recommended program display screen generation processing will be described with reference to the flowchart of FIG.

  In step S <b> 111, the standard program recommendation unit 53, the similar program recommendation unit 43, and the acceptance rate calculation unit 48 each read the operation history stored in the history storage unit 47.

  In step S112, algorithm-specific recommended program number determination processing is executed.

  Here, the algorithm-specific recommended program number determination process will be described with reference to the flowchart of FIG.

  In step S131, the acceptance rate calculation unit 48 calculates the acceptance rate for each algorithm, and supplies it to the recommended program determination unit 49. More specifically, in the operation history, a standard recommended program for each item recommended by an algorithm for extracting a program that matches predetermined metadata, which will be described later, and a program vector and user vector multiplied by an effect vector An acceptance rate when a similar recommended program recommended by an algorithm for extracting a program based on the degree of coincidence with the effect vector is recommended, that is, a ratio of the recommended program actually reserved for recording is calculated. Actually, programs recommended by any algorithm may not be reserved for recording, but here, the ratio of the recommended programs accepted by each algorithm to the total number of programs accepted as recommended programs is Acceptance rate. Accordingly, in the operation history, the number of times that any recommended program among the recommended programs and similar recommended programs for each item of the standard recommended program is reserved for recording is X, and the standard recommended program, for example, The number of times that the recommended program selected in the time zone is reserved for recording is Y1, the standard recommended program, for example, the number of times that the recommended program selected in the genre is reserved for recording is Y2, and the number of times that a similar recommended program is reserved Is Z, the acceptance rate of the algorithm extracted in the time zone of the standard recommended programs is Y1 / X, and the acceptance rate of the algorithm extracted in the genre of the standard recommended programs is Y2 / X. The acceptance rate of similar recommended programs is Z / X.

  In step S132, the recommended program determining unit 49 multiplies the total recommended program number R by the respective acceptance rate, and recommends each item of the number of programs to be recommended by each algorithm, that is, the number of standard recommended programs. The number of programs and the number of similar recommended programs are determined. More specifically, in the case described above, when the total recommended program number R, the standard recommended program number, for example, the recommended program number selected in the time zone is R × Y1 / X, the standard recommended program number, for example, The number of recommended programs selected by genre is R × Y2 / X, and the number of similar recommended programs is R × Z / X.

  Through the above process, based on the operation history, the program recommended by the algorithm based on the proportion of the user's recommendation program for each item of the standard recommended program and the similar recommended program. The number can be determined. In other words, it can be said that the priority of the algorithm serving as a reference for the recommended program is determined by the above processing.

  Now, the description returns to the flowchart of FIG.

  After the number of recommended programs for each algorithm is determined by the process of step S112, the standard system recommended program process is executed in step S113.

  Here, the standard recommended program determination process will be described with reference to the flowchart of FIG.

  In step S151, the standard program recommendation unit 53 extracts a program in the same time zone as the program for which the recording reservation has been set from the EPG data, and supplies it to the recommended program determination unit 49 as a standard system recommended program. Therefore, for example, in the case of EPG data (metadata) for generating an EPG display screen as shown in FIG. 12, when drama 1 is selected as a reserved program, the same time from 16:00 to 17:00 The bands “Drama 1”, “Talk Show 1”, “Drama 3”, and “Talk Show 2” are extracted.

  In step S152, the standard program recommendation unit 53 extracts a program of the same genre as the program for which the recording reservation is set from the EPG data, and supplies it to the recommended program determination unit 49 as a standard system recommended program. Therefore, for example, in the case of EPG data (metadata) for generating an EPG display screen as shown in FIG. 12, when drama 1 is selected as a reserved program, “drama 1”, “drama 2”, “Drama 3” is extracted.

  In step S153, the standard program recommendation unit 53 extracts a program including the same performer as the program performer for which the recording reservation is set, from the EPG data, and supplies it to the recommended program determination unit 49 as the standard recommended program. .

  In step S154, the recommended program determining unit 49 determines the standard program determined by the algorithm-specific recommended program number determining process described with reference to the flowchart of FIG. 18 from the programs sequentially recommended for each item in the processes of steps S151 to S153. The number of system recommended programs is extracted and set as standard system recommended programs. If the number of programs recommended in the processes of steps S151 to S153 is smaller than the determined number, all the recommended programs are set as standard recommended programs. Therefore, in such a case, the number of recommended programs may decrease. Conversely, if there are more than the number determined, give priority to programs recommended under multiple conditions, or assign a serial number to each program at random, up to the number corresponding to the number determined from the top May be recommended.

  Now, the description returns to the flowchart of FIG.

  When the standard recommended program is determined by the process in step S113, a similar recommended program determination process is executed in step S114.

  Here, with reference to the flowchart of FIG. 20, the similar system recommended program determination processing will be described.

  In step S171, the vector calculation unit 62 of the similar program recommendation unit 43 acquires the effect vector ef. At this time, the effect vector ef acquired by the vector calculation unit 62 may be either the program-side effect vector efPP or the user-side effect vector efUP, and may be switched by setting.

  In step S172, the vector calculation unit 62 multiplies the effect vector ef by the user vector UP to generate a user effect vector ef × UP. More specifically, the vector calculation unit 62 extracts the program vector including the topic stored in the initial registration storage unit 45 from the program vector of the program to be generated by the user vector supplied from the program vector extraction unit 42. Then, a user vector is generated by normalizing the sum of the extracted program vectors as necessary, and is registered in the user information registration unit 63. Therefore, the vector calculation unit 62 reads the user vector registered in the user information registration unit 63 and multiplies the read user vector UP by the effect vector ef.

  In step S173, for each program included in the EPG, the vector calculation unit 62 obtains the cosine distance between the program vector and the user effect vector according to the above equation (1), calculates the similarity, and associates it with the program. The data is output to the recommended program determination unit 49.

  In step S174, the vector calculation unit 62 determines whether or not the similarity is obtained for all the programs. If it is determined that the similarity is not obtained for all the programs, the process proceeds to step S173. Return. That is, the processes in steps S173 and S174 are repeated until it is determined that the similarity is obtained for all the EPG programs.

  If it is determined in step S174 that similarities have been obtained for all programs, in step S175, the recommended program determining unit 49 determines the highest n-th similarity (n is determined by the process of the flowchart of FIG. 18). Programs up to the number of similar recommended programs n) are determined as similar recommended programs.

  That is, the vector calculation unit 62 performs vector matching between the program vector and the user effect vector for each program included in the EPG using the cosine distance, and the recommended program determination unit 49 has a high matching degree (matching degree). The programs up to the top n-th place, that is, programs up to the n-th place with high similarity with a small cosine distance are determined as similar recommended programs.

  Now, the description returns to the flowchart of FIG.

  In step S115, the recommended program determining unit 49 generates a recommended program display screen corresponding to, for example, a date based on the information of the standard recommended program and the similar recommended program determined by the processing in steps S113 and S114. To the recommended program information output unit 50.

  More specifically, for example, as shown in FIG. 21, when the standard recommended program and the similar recommended program are determined, the following is performed.

  In FIG. 21, programs in the same time zone as the program selected by the user are extracted from the standard recommended programs in the upper program group 101 in the figure, and “4/1 23: 00-23: 30 8ch “Today's News”, and two programs with “4/4 19: 00-20: 00 10ch“ Mystery Case Book ”” in the lower row are recommended. Here, the time zone is a time zone obtained by dividing a day every 6 hours. Therefore, they are 0:00 to 6:00, 6:00 to 12:00, 12:00 to 18:00, and 18:00 to 24:00.

  Further, in the program group 102, for example, as a case where the genre of the program selected by the user is “variety”, a program with a genre of “variety” is extracted from the standard recommended programs. “4/1 19: 00-21: 00 4ch“ Professional Baseball Rare Play SP ”” and “4/4 19: 00-20: 00 8ch“ What if Variety ”” in the lower row 2 Two programs are recommended.

  Furthermore, in the program group 103, for example, as an example when the performer of the program selected by the user is “talent A”, the program with the performer “talent A” is extracted from the standard recommended programs. "4/1 21: 00-22: 00 8ch" Talent A laughter talk "" at the top, "4/4 19: 00-20: 00 4ch" Talent A exciting TV "at the bottom Two programs marked "" are recommended.

  The program group 104 includes, for example, vector matching, that is, the top six ranked programs among similar recommended programs, which are listed as similar recommended programs. 4/2 19: 00-21 : 00 4ch “Professional baseball broadcast”, 2nd place 4/1 16: 00-17: 00 6ch “Drama B (re)”, 3rd place 4/4 19: 30-20: 00 6ch “World trip discovery ”4th place, 4/2 21: 00-23: 00 8ch“ Wednesday Western Theater ”5th place, 4/4 19: 00-21: 00 4ch“ Professional Baseball Rare Play SP ”, 6th place 4/1 21: 00-22: 00 8ch "Talent A laughter conversation" is described respectively.

  In such a case, in the present example, the algorithm is a total of 4 algorithms including the algorithm extracted for each item of time zone, genre, and performer in the standard recommended program, and the algorithm that extracts the similar recommended program. It is a piece.

  Therefore, in the case of the first display, that is, when the ratio that the recommended programs extracted by any algorithm are reserved for recording is uniform according to the past history, all of the recommended programs that can be displayed R are all R / 4 programs will be displayed. Therefore, when the number of programs that can be displayed as recommended programs is four, one program is selected for each program selected by each algorithm.

  Therefore, when recommended programs such as the program groups 101 to 104 as shown in FIG. 21 are extracted, in the process of step S115, for example, a program recommendation screen as shown in FIG. 22 is generated. Become.

  In FIG. 22, tabs 111 to 113 are displayed, and “4/4 (night)”, “4/5 (morning)”, and “4/5 (daytime)” are displayed for each tab. The tab indicates the recommended program on the night of April 4, the recommended program on the morning of April 5, and the recommended program on the afternoon of April 5, and the tab is displayed from an early time zone. In each tab, the recommended programs belonging to the time zone, up to a maximum of 4 recommended programs, are displayed. On the 4/4 (night) tab, the program group 101 in FIG. “4/4 19: 00-20: 00 10ch“ Mystery Case Book ””, and “4/4 19: 00-20: 00 8ch“ What Variety ”” from the program group 102 in FIG. Below that, from the program group 103 in FIG. 21, “4/4 19: 00-20: 00 4ch“ Talent A Wakuwaku Television ”” is displayed, and from the program group 104 in FIG. 30-20: 00 6ch “World Travel Discovery” is selected and displayed, and one recommended program is displayed for each algorithm. Similarly, recommended programs are displayed for the other tabs.

  Furthermore, as shown in FIG. 23, the display areas 111a to 111d of the recommended programs on the tab 111 show information that is the basis for selecting each recommended program when the pointer or the like is moved to that position. . That is, for example, when the pointer is moved to the display area 111a, a balloon window as shown in FIG. 24 is displayed. In FIG. 24, “It is a program you always watch!” Is displayed, and “4/4 19: 00-20: 00 10ch“ Mystery Case Book ”” displayed in the display area 111a is shown in FIG. Based on the time zone information of the selected program indicated by 16, it can be suggested to the user that the program is recommended by the algorithm extracted in the time zone among the standard recommended programs.

  For example, when the pointer is moved to the display area 111b, a balloon window as shown in FIG. 25 is displayed. In FIG. 25, “Do you like variety programs?” Is displayed, and “4/4 19: 00-20: 00 8ch“ What Variety ”” displayed in the display area 111b is shown in FIG. Program selected by the algorithm extracted by the genre among the standard recommended programs based on the genre information of the selected program (the program “Anyone Artist” is a program belonging to variety) This can be suggested to the user.

  Further, for example, when the pointer is moved to the display area 111c, a balloon window as shown in FIG. 26 is displayed. In FIG. 26, “You like talent A?” Is displayed, and “4/4 19: 00-20: 00 4ch“ Talent A exciting TV ”” displayed in the display area 111c is shown in FIG. The algorithm extracted by the performer among the standard recommended programs based on the information of the performer of the selected program shown by 16 (assuming that the talent A will appear in the program “Anyone Artist”) It is possible to suggest to the user that the program is recommended.

  Further, for example, when the pointer is moved to the display area 111d, a balloon window as shown in FIG. 27 is displayed. In FIG. 27, “It suits your recent taste!” Is displayed, and “4/4 19: 00-20: 00 6ch“ World Travel Discovery ”” displayed in the display area 111d is the program. Based on the vector and user vector information, it is possible to suggest to the user that the program is recommended by an algorithm that extracts similar recommended programs.

  In each of the display areas 111a to 111d, a recording reservation can be made by selecting a program with a pointer or the like.

  By displaying in this way, the user simply selects one program for recording reservation, and the user's preference obtained from the selected program and the user's preference input in advance are displayed. Since it is possible to receive the recommended programs extracted by a plurality of various algorithms that are taken into consideration, it is possible to reduce the possibility of failing to make a recording reservation for a program that was intended to be inadvertently viewed. In addition, since it is possible to present information indicating the basis of recommendation for a recommended program, the user can accurately examine a program that is actually scheduled for recording from among the recommended programs. .

  Now, the description returns to the flowchart of FIG.

  When the recommended program display screen as described above is generated in step S44, the recommended program information output unit 50 of the recommendation server 13 records the data of the generated recommended program display screen via the network 11 in step S45. Transmit to the playback device 14.

  In step S28, the recording setting unit 81 of the recording / playback apparatus 14 receives the recommended program display screen data transmitted from the recommendation server 13, and displays the recommended program as described with reference to FIGS. The screen is displayed on the display unit 90 or a television receiver (not shown). At this time, it is displayed separately from the display screen selected to make the recording reservation shown in FIG.

  In step S29, the recording setting unit 81 determines whether or not the recorded program has been confirmed. For example, if it is determined that the recorded program has not been confirmed, the process returns to step S23, and the subsequent processes are repeated.

  If it is determined in step S29 that the recorded program has been confirmed, in step S30, the recording setting unit 83 completes the recording reservation by adding the program for which the recording reservation has been confirmed to the recording reservation list, and ends the processing. To do.

  Through the above processing, the user's preference is displayed by changing the number of recommended programs recommended for each algorithm based on each item of the program selected for the recording reservation by the user while changing according to the acceptance rate of the user. It is possible to recommend a program to be reserved for recording while adapting to. In other words, it is possible to recommend a program while adapting to the user's preference by changing the priority of the algorithm when recommending the program according to the acceptance rate of the user.

  In the above, as described with reference to the flowchart of FIG. 18, the number of recommended programs is determined for each algorithm. However, according to the processing of the flowchart of FIG. It is conceivable that the number of recommended programs will become zero as the above process is repeated. Once the recommended program becomes 0, the number of programs recommended by the algorithm remains 0, so the acceptance rate remains 0 and is recommended by the algorithm as a result. There is a risk that the program will disappear. Therefore, when the number of recommended programs has reached zero, the minimum number of programs may be displayed.

  In FIG. 28, when the number of recommended programs recommended by a predetermined algorithm becomes zero, a recommended program display screen for generating only one program is generated after that. The structure of the recommendation server 13 is shown. In addition, about the structure demonstrated with reference to FIG. 3, the same number is attached | subjected and the description shall be abbreviate | omitted suitably.

  28 differs from the configuration of FIG. 3 in that a recommended program determining unit 201 is provided in place of the recommended program determining unit 49. The function of the recommended program determining unit 201 is basically the same as that of the recommended program determining unit 49. However, as described above, the number of recommended programs recommended by a predetermined algorithm is counted as 0. A zero state counter (not shown) is provided, and when the number of recommended programs recommended by a predetermined algorithm is 0, when the zero state counter is 2 or more, that is, when it continues twice, after that, The number of recommended programs for each algorithm is determined so that one program is displayed as the recommended program.

  With reference to the flowchart of FIG. 29, the algorithm-specific recommended program number determination processing by the recommendation server 13 of FIG. 28 will be described. Note that the processing in steps S201 and S202 in the flowchart in FIG. 29 is the same as the processing in steps S131 and S132 in the flowchart in FIG.

  In step S203, the recommended program determination unit 201 determines whether the number of standard recommended programs of any item or the number of similar recommended programs is 0, that is, the number of programs recommended by any algorithm. For example, if it is determined that the number of programs recommended by any algorithm is 0, the process proceeds to step S204.

  In step S204, the recommended program determining unit 201 increments a zero state counter N (not shown) by one.

  In step S205, the recommended program determination unit 201 determines whether or not the zero state counter N is 2 or more. When the recommended program determination unit 201 determines that it is 2 or more, in step S206, the number of algorithms in the zero state is For C, each of the C algorithms has a recommended program of 1, and the total number of programs recommended by the other algorithms is (RC).

  If it is determined in step S203 that the number of programs recommended by any algorithm is not 0, the recommended program determination unit 201 resets the zero state counter N to 0 in step S207, and the process ends. .

  If it is determined in step S205 that the zero state counter N is not 2 or more, the process of step S206 is skipped and the process ends.

  With the above processing, if the number of programs recommended by any algorithm becomes zero or more, the number of programs recommended by the algorithm can be set to 1, so that a plurality of users are always present. It is possible to present a recommended program based on the user's preference.

  In the above example, the number of recommended programs for each algorithm is changed based on the acceptance rate for the recommended programs for each algorithm of the user. However, the recommended programs for each algorithm is used instead of the recommended programs for each algorithm. The user interface (hereinafter also referred to as UI) (configuration of the recommended program display screen) may be changed.

  FIG. 30 shows the configuration of the recommendation server 13 in which the UI for presenting a recommended program for each algorithm is changed according to the acceptance rate. In addition, about the structure demonstrated with reference to FIG. 3, the same number is attached | subjected and the description shall be abbreviate | omitted suitably.

  30 differs from the configuration of FIG. 3 in that a recommended program determining unit 211 is provided in place of the recommended program determining unit 49. The function of the recommended program determining unit 211 is basically the same as that of the recommended program determining unit 49, but differs in that the UI for presenting the recommended program for each algorithm is changed according to the acceptance rate as described above. . More specifically, the recommended program determining unit 211 generates a recommended program display screen including a character screen as a UI for a recommended program recommended by an algorithm having the highest acceptance rate for each algorithm, and other recommended programs. As for UI, a recommended program display screen including the list screen shown in FIGS. 22 to 27 is generated as a UI.

  Here, the recommended program display screen generation processing by the recommendation server 13 of FIG. 30 will be described with reference to the flowchart of FIG. Note that the processing in steps S251 through S254 in FIG. 31 is the same as the processing in steps S111 through S114 in the flowchart in FIG.

  In step S <b> 255, the recommended program determination unit 211 extracts an algorithm having the highest acceptance rate based on the acceptance rate information input from the acceptance rate calculation unit 48.

  In step S256, for the recommended program recommended by the algorithm with the highest acceptance rate, the recommended program determining unit 211 generates, as a UI, a recommended program display screen using characters as shown in FIG. For other recommended programs, the list display screen described with reference to FIGS. 22 to 27 is generated as a UI.

  In FIG. 32, information indicating a program recommended by the algorithm having the highest acceptance rate is written in the character recommended program display screen 221. In this case, “2003/4/1 19: 00-21: 00“ Professional baseball rare play SP ”” is indicated, and in addition to the character 223, a blowout 224 from the character 223 is provided. It ’s a program that you ’re likely to like. ” This display indicates that the program “2003/4/1 19: 00-21: 00“ Professional baseball rare play SP ”” is a program recommended by the algorithm with the highest acceptance rate.

  That is, a recommended program extracted by an algorithm with a high acceptance rate is highly likely to be a program desired by the user, and is expected to be a program having a higher priority than other recommended programs. Therefore, as described above, it is necessary to search for a desired program from a list of recommended programs displayed by displaying a high priority program on a higher priority screen that is easier for the user to recognize. Therefore, it is possible to quickly present a program that is highly likely to be desired.

  In the above example, two types of recommended program display screens (UI), ie, a recommended program display screen using characters and a list display screen showing a list of recommended programs, have been shown. And the recommended program display screen (UI) may be switched in accordance with the priority set based on the acceptance rate.

  In the above example, when performing the recording reservation process, the recommended program extracted by each algorithm is displayed according to the priority of the algorithm for the user, thereby reducing the burden on the user in the recording reservation operation. However, for example, after the recording reservation is completed, it is possible to confirm the program reserved for recording by presenting the information of the program in the same time zone of the program reserved for recording again immediately before the recording reservation time. You may do it.

  FIGS. 33 and 34 show a recommendation server 13 that presents information on programs in the same time zone of the program reserved for recording again immediately before the recording reservation time so that the program reserved for recording can be confirmed. The structure of the recording / reproducing apparatus 14 is shown. In addition, about the structure demonstrated with reference to FIG. 3, FIG. 4, the same number is attached | subjected and the description shall be abbreviate | omitted suitably.

  33 differs from the recommended server 13 of FIG. 3 in that a recommended program determining unit 231 is provided instead of the recommended program determining unit 49. Similarly, in FIG. 34, the recording / playback apparatus of FIG. 14 is that a recording setting unit 241 is provided instead of the recording setting unit 83.

  The recommended program determining unit 231 has the same basic function as the recommended program determining unit 49 in FIG. 3, but based on the information stored in the history storage unit 47, the recommended program determining unit 231 immediately before the recording reserved time ( For example, at 5 minutes ago, a recommended program display screen is generated, supplied to the recommended information output unit 50, and transmitted to the recording / reproducing apparatus 14 of FIG.

  The recording setting unit 241 in the recording / playback apparatus 14 in FIG. 34 displays the recommended program display screen transmitted from the recommendation server 13 immediately before the scheduled recording time on the display unit 90 or a television receiver (not shown).

  Here, with reference to the flowchart of FIG. 35, the recording confirmation processing by the recommendation server 13 and the recording / playback apparatus 14 of FIGS. 33 and 34 will be described. Note that the processing in steps S272 and S273 in FIG. 35 is the same as the processing in step S131 in FIG. 18 and the processing in step S255 in FIG.

  In step S271, the recommended program determination unit 231 obtains recording reservation information based on the operation history stored in the history storage unit 47, further determines the recording reservation time, and 5 minutes before the recording reservation time. The process is repeated until it is determined that it is five minutes ago. If it is determined in step S271 that the scheduled recording time is 5 minutes before, the process proceeds to step S272.

  In step S274, the recommended program determination unit 231 displays a screen showing information of programs currently reserved for recording and recommends programs recommended by the algorithm with the highest acceptance rate as shown in FIG. A recommended program display screen using a character is generated, and for other recommended programs, a confirmation screen including the list display screen described with reference to FIGS. 22 to 27 is generated, and a recommended information output unit 50 to transmit to the recording / reproducing apparatus 14.

  On the other hand, in step S281, the recording setting unit 241 of the recording / playback device 14 determines whether or not a confirmation screen has been transmitted from the recommendation server 13, and for example, it is determined that the confirmation screen has been transmitted by the process of step S274. If so, the process proceeds to step S282.

  In step S282, the recording setting unit 241 displays the supplied confirmation screen on the display unit 90 or a television receiver (not shown).

  In step S283, the recording setting unit 241 determines whether or not a predetermined time (for example, about 3 minutes) has elapsed, and repeats the process until it is determined that the predetermined time has elapsed. If it is determined that the time elapses, the process proceeds to step S284.

  In step S284, the recording setting unit 241 ends the display of the confirmation screen.

  With the processing as described above, a confirmation screen can be displayed on the recording / playback apparatus 14 immediately before the recording reservation, so that the user can confirm whether or not the desired program has been reliably reserved for recording immediately before the recording reservation time. It can be confirmed without particular awareness. Further, as described above, the recommended screen having a high algorithm priority is displayed on the confirmation screen by a display screen having a higher priority (in this embodiment, it is displayed as a recommended program display screen using characters). Since it is displayed together with the program in the middle, it is possible to quickly confirm whether or not a recording reservation has been made, and it is possible to suppress forgetting to record a desired program.

  In the above, the recommended program extracted by each algorithm is determined according to the acceptance rate. For example, the time slot for recording reservation is the time slot with the largest number of viewers (generally referred to as golden time). In such a time zone, for example, a time zone such as 18:00 to 23:00), the recommended program display screen may be configured by increasing the number of recommended programs in the same time zone. .

  In FIG. 36, the reservation time of a program to be reserved for recording is a time zone with the largest number of viewers (here, 18:00 to 23:00, but this time zone may be in the vicinity of this time zone. The recommended server 13 is configured such that the recommended program display screen is configured by increasing the number of recommended programs in the same time period. In addition, about the structure demonstrated with reference to FIG. 3, the same number is attached | subjected and the description shall be abbreviate | omitted suitably.

  36 differs from the recommended server 13 of FIG. 3 in that a recommended program determining unit 251 is provided in place of the recommended program determining unit 49.

  The recommended program determining unit 251 basically has the same function as the recommended program determining unit 49, but the reserved time of the program to be reserved for recording is the time zone with the most viewers (here In the case of 18:00 to 23:00, it may be in the vicinity of this time zone, but is not limited to this time zone), the number of recommended programs in the same time zone is increased. To generate a recommended program display screen.

  Here, with reference to the flowchart of FIG. 37, the algorithm-specific recommended program number determination processing by the recommendation server 13 of FIG. 36 will be described. Note that the processing in steps S301 and S304 in the flowchart in FIG. 37 is the same as the processing in steps S131 and S132 in the flowchart in FIG.

  In step S302, the recommended program determination unit 251 determines whether or not the program time zone selected as the recording reservation program is 18:00 to 23:00, for example, the program time zone selected as the recording reservation program Is determined not to be 18:00 to 23:00, the process proceeds to step S304.

  On the other hand, if it is determined in step S302 that the program time zone selected as the scheduled recording program is 18:00 to 23:00, in step S303, the recommended program determination unit 251 determines the standard system recommendation by time zone. The ratio of the number of programs and the number of recommended programs other than that is set to 9: 1, and when the total recommended program number R, the number of programs of R × 0.9 is set as the number of standard recommended programs by time zone, The total number of other recommended programs is R × 0.1, and for recommended programs other than the standard recommended programs by time zone, among the R × 0.1 programs, recommended programs according to the acceptance rate Set the number.

  With the above processing, it is possible to change the priority of the algorithm according to the time zone and display it as a recommended program.

  In the above description, when the user operates the recording / playback device 14 to make a recording reservation operation, the recommendation server 13 performs information on the recommended program. For example, the user uses the recording / playback device 14. You may make it provide at the timing which finished the recorded program. Alternatively, a recommended program display screen may be provided in response to a user request at an arbitrary timing.

  The recommendation server 13 in FIG. 38 and the recording / playback apparatus 14 in FIG. 39 show the respective configurations in the case where the recommended program information is provided when the user finishes playing the recorded program. . In addition, about the structure demonstrated with reference to FIG. 3, FIG. 4, the same number is attached | subjected and the description shall be abbreviate | omitted suitably.

  The recommendation server 13 in FIG. 38 differs from the recommendation server 13 in FIG. 3 in that a recommended program determination unit 261 is provided instead of the recommended program determination unit 49. The recommended program determining unit 261 basically has the same function as the recommended program determining unit 49 in FIG. 3, but the recommended program determining unit 261 recommends when the recording of the recorded program in the recording / reproducing apparatus 14 is finished. Provide program information.

  39 is different from the recording / reproducing apparatus 14 in FIG. 4 in that the recording setting unit 271 and the recording / reproducing unit 272 are replaced with the recording setting unit 84 and the recording / reproducing processing unit 87. This is the point. The recording setting unit 271 and the recording / playback processing unit 272 basically have the same functions as the recording setting unit 84 and the recording / playback processing unit 87, but the recording / playback processing unit 272 When the reproduction of the recorded program is completed, the recording setting unit 271 is notified to acquire information of the operation log list 82 indicating the completion of the reproduction. Based on this notification, the recording setting unit 271 makes a similar notification to the recommendation server 13 in FIG. 39, and displays information on the recommended program transmitted along with this notification on the display unit 90 or not shown. Display on a television receiver.

  Next, with reference to the flowchart of FIG. 40, the recommended program display process when the reproduction of the recorded program ends will be described.

  In step S321, the recording setting unit 271 of the recording / reproducing apparatus 14 in FIG. 39 inquires of the recording / reproducing processing unit 272 to determine whether or not the reproduction of the recorded program has ended, and the reproduction of the recorded program is performed. The process is repeated until it is determined that the process has been completed. If it is determined that the reproduction of the recorded program has ended, the recording setting unit 271 notifies the recommendation server 13 of a notification indicating that the reproduction has ended via the network 11 in step S322. The recording setting unit 271 notifies the operation log list 82 as information indicating that reproduction has ended.

  In step S331, the operation log acquisition unit 46 of the recommendation server 13 in FIG. 38 determines whether or not the end of reproduction has been notified based on whether or not an operation log indicating the end of reproduction has been acquired. The process is repeated until it is determined that the notification has been received. If it is determined in step S322 that the end of playback has been notified, in step S332, the acceptance rate calculation unit 48 calculates the acceptance rate for each algorithm and supplies the calculation result to the recommended program determination unit 26. To do.

  In step S333, the recommended program determining unit 261 extracts programs recommended by an algorithm with a high acceptance rate as recommended programs. In step S 334, the recommended program determining unit 261 generates a recommended program display screen composed of programs recommended by an algorithm with a high acceptance rate, and transmits the recommended program display screen from the recommended information output unit 50 to the recording / playback device 14.

  In step S323, the recording setting unit 271 determines whether or not a recommended program display screen has been supplied from the recommendation server 13, and the processing is performed until it is determined that the recommended program display screen has been supplied from the recommendation server 13. repeat. If it is determined that the recommended program display screen has been supplied from the recommendation server 13, the recommended program display screen supplied from the recommendation server 13 is displayed on the display unit 90 or a television receiver (not shown) in step S324. Display on the machine.

  With this process, a new recommended program can be presented at the timing when the recorded program has been played back, so that a new recording reservation cannot be made unless the recorded program is viewed (for example, In a state in which the program is recorded until the storage capacity of the recording / playback processing unit 87 is completely used up), after the recorded program has been played back, the recording reservation process can be performed continuously. Forgetting to schedule recording can be suppressed. In addition, for example, it is suppressed that the user forgets to reserve the next drama after finishing a continuous drama.

  In the above example, the recommended program display screen is generated by determining the number of display programs from the standard recommended program and the similar recommended program for each item, but for example, similar to the standard recommended program In the system recommended program, since the algorithm for extracting each recommended program is completely different, the same program may be extracted as the recommended program.

  That is, as shown in FIG. 41, a set of standard recommended programs recFIT and a set of similar recommended programs recSIM may exist as a set of common recommended programs recCAP that overlap each other. Accordingly, when the recommended program display screen is generated by the above-described method, a plurality of programs belonging to the set of common recommended programs are displayed in the same recommended program list as programs extracted by different algorithms. There is a risk.

  Therefore, the program selected as both the standard recommended program and the similar recommended program may be regarded as a recommended program extracted by another algorithm as a common recommended program.

  FIG. 42 shows a configuration of the recommendation server 13 in which a program selected as a standard recommended program or a similar recommended program is regarded as a recommended program extracted by another algorithm as a common recommended program. In addition, about the structure demonstrated with reference to FIG. 3, the same number is attached | subjected and the description shall be abbreviate | omitted suitably.

  42 differs from the recommendation server 13 of FIG. 3 in that a recommended program determination unit 281 is provided instead of the recommended program determination unit 49, and an acceptance rate is substituted for the acceptance rate calculation unit 48. The calculation unit 282 is provided.

  The recommended program determining unit 281 is basically the same as the recommended program determining unit 49, but the acceptance rate calculating unit 282 is commonly recommended in addition to the recommended program and the similar recommended program for each item of the standard recommended program. Since the acceptance rate is calculated for each program, in addition to the recommended program for each item of the standard recommended program and the similar recommended program, the common recommended program is determined, and the recommended program display screen corresponding to them is determined. Is generated.

  The acceptance rate calculation unit 282 basically has the same function as the acceptance rate calculation unit 48. However, as described above, the acceptance rate calculation unit 282 includes a recommended program for each item of the standard recommended program and a similar recommended program. In addition, for each common recommended program, the acceptance rate is calculated and supplied to the recommended program determining unit 281.

  Next, the recommended program display screen generation processing by the recommendation server 13 in FIG. 42 will be described with reference to the flowchart in FIG. Note that the processing in steps S351 to S354 in FIG. 43 is the same as the processing in steps S111, S113, S114, and S112 described with reference to the flowchart in FIG. Since the common recommended program cannot be specified unless the processes of steps S352 and S353 are completed, the number of recommended programs is determined for each algorithm in the process of step S354. Since the processing contents are the same, the description thereof is omitted.

  In step S355, the recommended program determining unit 281 determines a recommended program for each algorithm according to the number of recommended programs in each algorithm including the common recommended program determined by the process in step S354, and displays a recommended program display screen. It is generated and transmitted from the recommended information output unit 50 to the recording / reproducing apparatus 14.

  Next, the standard recommended program determination process by the recommendation server 13 of FIG. 42 will be described with reference to the flowchart of FIG. Note that the processing of steps S371 to S373 in the flowchart of FIG. 44 is the same as the processing of steps S151 to S153 in the flowchart of FIG. That is, since the number of recommended programs for each algorithm is a subsequent process, the process corresponding to step S154 in the flowchart of FIG. 19 is included in the process of step S355.

  Next, similar system recommendation program determination processing by the recommendation server 13 of FIG. 42 will be described with reference to the flowchart of FIG. Note that the processing in steps S391 to S394 in the flowchart in FIG. 45 is the same as the processing in steps S171 to S174 in the flowchart in FIG. That is, since the number of recommended programs for each algorithm is a subsequent process, the process corresponding to step S175 in the flowchart of FIG. 20 is included in the process of step S355.

  Next, the algorithm-specific recommended program number determination process by the recommendation server 13 of FIG. 42 will be described with reference to the flowchart of FIG. Note that the processing in step S411 in the flowchart in FIG. 46 is the same as the processing in step S131 in the flowchart in FIG.

  In step S412, the recommended program determination unit 281 multiplies the total recommended program number R by the respective acceptance rate, and recommends the number of programs to be recommended by each algorithm, that is, the recommended number of standard recommended programs for each item. The number of programs, the number of similar recommended programs, and the number of common recommended programs are determined.

  Since the algorithm for extracting each recommended program is completely different by the above processing, the same program is not extracted as a plurality of recommended programs, so many recommended programs are displayed on the recommended program display screen. It becomes possible.

  In the above, the display screen of the recommended program is generated based on the number of recommended programs for each algorithm including the common recommended program. The common recommended program may be either a standard recommended program or a similar recommended program. Therefore, it can be considered that the priority is higher than other recommended programs. Therefore, it is possible to extract only the common recommended programs and display the recommended programs.

  In addition, in the above, the number of recommended programs for each algorithm is determined based on the acceptance rate (it can be said that the priority for each algorithm is determined), and a display screen for displaying the recommended programs has been generated. For example, as described above, the recommended program may be displayed by switching the UI based on the acceptance rate for each UI when the recommended program is displayed by switching the UI (based on the priority of the UI).

  FIG. 47 shows the configuration of the recommendation server 13 in which the priority of the UI is determined based on the UI acceptance rate, and the recommended program display screen is generated using the determined UI. In addition, about the structure demonstrated with reference to FIG. 3, the same number is attached | subjected and the description shall be abbreviate | omitted suitably. The UI here is, for example, a recommended program list display screen described with reference to FIGS. 22 to 27, or a recommended program display screen using characters described with reference to FIG.

  47 differs from the recommendation server 13 of FIG. 3 in that an acceptance rate calculation unit 291 is provided in place of the acceptance rate calculation unit 48, and a recommended program in place of the recommended program determination unit 49. The determination unit 292 is provided.

  The acceptance rate calculation unit 291 calculates the acceptance rate for each UI based on the operation history stored in the history storage unit 47, and outputs it to the recommended program determination unit 292.

  The recommended program determination unit 292 basically has the same function as the recommended program determination unit 49, but obtains a common recommended program from the recommended programs in each algorithm and supplies the UI supplied from the acceptance rate calculation unit 291. Based on another acceptance rate, the priority of the UI is set, and the display image for displaying the common recommended program is generated by switching the UI randomly at the set priority ratio.

  Next, recording reservation processing by the recommendation server 13 of FIG. 47 will be described with reference to the flowchart of FIG. Note that the processing of steps S431 to S435 in the flowchart of FIG. 48 is basically the same as the processing of steps S41 to S45 of FIG. 5, but the operation log list 82 is acquired in the processing of step S433. In this case, the operation log list 82 including information on the number of times of acceptance for each UI on which the recommended program is displayed is acquired.

  Next, the recommended program display screen generation processing by the recommendation server 13 in FIG. 47 will be described with reference to the flowchart in FIG. The processes in steps S451 to S453 are the same as the processes in steps S111, S113, and S114 in FIG.

  In step S454, the acceptance rate calculation unit 291 determines whether or not the process is the first process. If it is determined that the process is the first process, in step S455, the acceptance rate for each UI is set equally for all UIs. Then, it is output to the recommended program determining unit 292.

  In step S456, the recommended program determining unit 292 extracts a common recommended program.

  In step S457, the recommended program determining unit 292 generates a display screen for displaying the recommended program by switching the UI at random with the ratio of the UI acceptance rate of the common recommended program. Accordingly, in this case, when there are two types of UI, each UI is displayed at a ratio of 1: 1, and a screen on which the common recommended program is displayed as the recommended program is generated.

  On the other hand, when it is determined in step S454 that the process is not the first time, the acceptance rate calculation unit 291 reads out the number of acceptances for each UI from the history storage unit 47 and obtains the respective acceptance rates. That is, for example, the recommended program list display screen described with reference to FIGS. 22 to 27 is accepted V1 times, and the recommended program display screen using the character described with reference to FIG. 32 is accepted V2 times. In this case, the acceptance rates of the list display screen and the display screen using characters are V1 / (V1 + V2) and V2 / (V1 + V2), respectively.

  Therefore, in this case, in step S457, the UI consisting of the list display screen and the UI consisting of the character display screen are switched and displayed at a ratio of V1: V2, and the common recommended program is displayed. Is generated.

  Through the above process, common recommended programs with a relatively high priority are displayed by switching the UI at a priority ratio according to the acceptance rate of a plurality of UIs. A display screen that displays the common recommendation number by switching the UI at a predetermined frequency is generated.

  As a result, it is possible to present a recommended program that is easy for the user to accept with a UI that is easy for the user to accept.

  In the above, an example has been described in which the number of programs recommended by each algorithm is determined based on the acceptance rate of each algorithm, that is, the priority based on the acceptance rate of each algorithm. May be individually set, and a recommended program to be displayed on the recommended program display screen may be determined from programs recommended by each algorithm based on the priority.

  FIG. 50 shows a recommendation server in which priorities for each algorithm are individually set, and recommended programs to be displayed on the recommended program display screen are determined from programs recommended by the algorithms based on the priorities. 13 configurations are shown. The configurations described with reference to FIG. 3 are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

  Here, the configuration of the recommendation server 13 in FIG. 50 differs from the configuration of the recommendation server 13 in FIG. 3 in that an initial storage unit 301 and a recommendation program are replaced with the initial storage unit 45 and the recommended program determination unit 49. The program determination unit 302 is provided. Moreover, the acceptance rate calculation part 48 is deleted.

  The initial storage unit 301 is basically the same as the initial storage unit 45, but stores the priority for each algorithm input from the operation input unit 44 in advance. This priority is indicated by a value from 0 to 100, for example, and the higher the value, the higher the priority. The recommended program determination unit 302 has the same basic functions as the recommended program determination unit 49, but reads the priority stored in the initial storage unit 301 and is recommended by the standard program recommendation unit 51. For each program of the standard recommended program for each item and the similar recommended program recommended by the similar program recommendation unit 43, the priority ranking is obtained based on the read priority, and the priority ranking is obtained. The recommended top R programs are extracted to determine a recommended program, a recommended program display screen is generated, the recommended information output unit 50 is controlled, and transmitted to the recording / reproducing apparatus 14 via the network 11.

  Next, the recommended program display screen generation processing by the recommendation server 13 in FIG. 50 will be described with reference to the flowchart in FIG. In addition, since the process of step S481, S482 in the flowchart of FIG. 51 is the same as the process of step S352, S353 of FIG. 43, the description is abbreviate | omitted.

  In step S <b> 483, the recommended program determination unit 302 reads priority information registered in advance in the initial registration storage unit 301.

  In step S484, the priority of the similar recommended program is multiplied by the matching coefficient.

  In step S485, a display screen for displaying recommended programs up to the top R ranks of priority of all recommended programs in the same time zone (the number of recommended programs displayed is R) is generated, and the recommended information output unit 50 is displayed. Then, the data is transmitted to the recording / reproducing apparatus 14 via the network 11.

  That is, for example, as shown in the column 311 of FIG. 52, it is assumed that the priority by algorithm is set. In column 311, the priority of time zone (standard recommended program) is 100, the priority of genre (standard recommended program) is 60, the priority of performer (standard recommended program) is 80, vector The priority of matching (similar recommended program) is set to 90, respectively.

  Therefore, the “4/1 23: 00-23: 30 8ch“ Today's News ”” and “4/4 19: 00-20: 00 10ch “Mystery Case Book” has a priority set to 100 as shown in column 312 of FIG.

  In addition, among the standard recommended programs of the genre recommended by the standard program recommending section 53, the “4/1 19: 00-21: 00 4ch“ Professional Baseball Rare Play SP ”” is a program whose genre is “Variety”. , And “4/4 19: 00-20: 00 8ch“ What Variety ””, the priority is set to 60, as indicated by the column 313 in FIG.

  Furthermore, among the standard recommended programs of the performers recommended by the standard program recommending section 53, “4/1 21: 00-22: 00 8ch” “Talent A lol” “Interview” ”and“ 4/4 19: 00-20: 00 4ch “Talent A Wakuwaku Television” ”are each set with a priority of 80, as shown in column 314 of FIG.

  In the column 315, programs recommended by the similar program recommendation unit 43 by vector matching, that is, programs ranked in the top five among similar recommended programs are listed as similar recommended programs. / 2 19: 00-21: 00 4ch "Professional Baseball Broadcasting", 2nd place 4/1 16: 00-17: 00 6ch "Drama B (re)", 3rd place, 4/4 19: 30-20 : 00 6ch "World Travel Discovery", 4th, 4/2 21: 00-23: 00 8ch "Wednesday Western Theater", 5th, 4/4 23: 00-23: 30 2ch "Pop Studio" , Extracted as a similar recommended program. The priority of programs recommended by all vector matching, that is, similar recommended programs, is basically 90 as set in the column 311, but is multiplied by the matching coefficient according to the ranking (step S484). The value multiplied by the matching coefficient is the priority of each program. As a matching coefficient, for example, the first place is 1.0, the second place is 0.9, the third place is 0.8, the fourth place is 0.7, and the fifth place is 0.6.

  Therefore, the priority of “4/2 19: 00-21: 00 4ch“ Professional Baseball ”” which is the first place is 90 (= 90 × 1.0), and “4/1 16: 00-17: 00 6ch “Drama B (re)” has a priority of 81 (= 90 × 0.9), which is 3rd, 4/4 19: 30-20: 00 6ch “World Travel Discovery” ”Is 72 (= 90 × 0.8), 4th place, 4/2 21: 00-23: 00 8ch“ Wednesday Western Theater ”is 63 (= 90 × 0.7) ), 4/4 23: 00-23: 30 2ch "Pop Studio" has a priority of 54 (90x0.6).

  Therefore, in the case of the priority by algorithm set in the column 311 of FIG. 52 and the standard recommended program and the similar recommended program shown in the columns 312 to 315, the recommended program determining unit 302 prioritizes each program. For example, a display screen as shown in FIG. 53 is generated in descending order. That is, in FIG. 53, tabs 321 to 323 are displayed from the top, and “4/4 (night)”, “4/5 (morning)”, and “4/5 (daytime)” are displayed for each tab. Each tab shows a recommended program on the night of April 4th, a recommended program on the morning of April 5th, and a recommended program on the afternoon of April 5th. Yes. In each tab, the recommended programs belonging to the time zone are displayed up to four programs with high priority, and the 4/4 (night) tab has a column in FIG. 52 at the top. From 312 “4/4 19: 00-20: 00 10ch“ Mystery Case Book ”” is shown, and below that column 314 “4/4 19: 00-20: 00 4ch“ Talent A exciting TV ”” 52, “4/4 19: 30-20: 00 6ch“ World trip discovery ”” from column 315 in FIG. 52, and “4/4 19: 00-20: 00 8ch “What Variety” is selected and displayed, and is displayed from the top in order of priority. Similarly, recommended programs are displayed for the other tabs.

  Further, as shown in FIG. 53, each of the recommended program display areas 321a to 321d on the tab 321 displays priority information of each recommended program when the pointer or the like is moved to that position. That is, for example, when the pointer is moved to the display area 321a, priority 100 is displayed, when the pointer is moved to the display area 321b, priority 80 is displayed, and when the pointer is moved to the display area 321b, priority 72 is displayed. When the pointer is moved to the display area 321b, the priority 60 is displayed. This display allows the user to examine the program to be reserved for recording while recognizing the priority of the recommended program.

  In the above example, it is assumed that the priority is set in advance and stored in the initial registration storage unit 301, and then the priority does not change. For example, the user can freely set the priority. Or learning may be performed according to the acceptance status of each algorithm.

  54 and 55 show the configurations of the recommendation server 13 and the recording / playback apparatus 14 that allow the user to freely set the priority, or learn according to the acceptance status of each algorithm. Yes. The configurations described with reference to FIGS. 50 and 4 are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

  Here, the configuration of the recommendation server 13 in FIG. 54 is different from the configuration of the recommendation server 13 in FIG. 50 in that a priority setting unit 331 is newly provided. The priority setting unit 331 generates a screen for setting priority according to a request from the recording / playback device 14 and supplies the screen to the recording / playback device 14. Also, upon receiving notification that the priority setting process has been completed, the priority setting unit 331 reads the operation log list 82 of the recording / playback device 14, reads the priority setting information, and the initial registration storage unit 301. Change the priority setting. Furthermore, the priority setting unit 331 periodically reads the operation log list 82 of the recording / playback device 14, reads the acceptance status of each recommended program by algorithm, and changes the priority setting of the initial registration storage unit 301. , Learn the priority according to the acceptance situation.

  Also, the recording setting unit 341 in FIG. 55 requests the recommendation server 13 for a priority setting screen, acquires it, and displays it on the display unit 90 or a television receiver (not shown). Further, in the recording setting unit 341, the operation input unit 81 changes the display of the priority according to the operation signal. Further, when the priority setting is completed, the recommendation server 13 is notified, the operation log list 82 in the priority setting is read, and the priority setting contents are reflected.

  Next, priority setting processing in the recommendation server 13 in FIG. 54 and the recording / playback apparatus 14 in FIG. 55 will be described with reference to the flowchart in FIG.

  In step S501, the recording setting unit 341 determines whether or not the priority setting is requested by operating the operation input unit 81, and the process is repeated until the priority setting is requested. When it is determined in step S501 that priority setting has been instructed, in step S502, the recording setting unit 341 notifies the recommendation server 13 that priority setting has been instructed.

  In step S521, the priority setting unit 331 of the recommendation server 13 determines whether or not a priority setting instruction is notified, and repeats the processing until a priority setting instruction is notified. In step S521, for example, when the priority setting is notified by the process of step S502, it is determined that the priority setting is notified, and the process proceeds to step S522.

  In step S522, the priority setting unit 331 generates a priority setting screen and notifies the recording / playback apparatus 14 of the priority setting screen.

  In step S503, the recording setting unit 341 determines whether or not a priority setting screen is supplied, and repeats the process until it is transmitted. When the priority setting screen is transmitted by the process of step S522, it is determined that the priority setting screen has been transmitted, and the process proceeds to step S504.

  In step S504, the recording setting unit 341 displays the transmitted priority setting screen as shown in FIG. 57, for example. In FIG. 57, tabs 341 to 343 are provided as setting screens, and “priority”, “keyword”, and “personalization” are displayed on each tab, and any of the tabs 341 to 343 is displayed. By selecting, “priority”, “keyword”, and “personalization” can be set.

  In this case, it is a priority setting, and from the top, "Time zone", "Favorite genre", "Favorite performer", and "Fit to taste" are displayed. As priority currently set, “100”, “60”, “80”, and “90” are shown from the top, and the time zone priority of the standard recommended program corresponding to “time zone” is 100. The priority of the genre of the standard recommended program corresponding to “favorite genre” is 60, and the priority of the performer of the standard recommended program corresponding to “favorite performer” is 80 , It is shown that the priority of the similar recommended program corresponding to “preferred to taste” is 90, respectively. In addition, when the button labeled “UP” provided on the right side of each column is pressed, the value is incremented by 1. When the button labeled “DOWN” is pressed, the value is decremented by 1. Furthermore, when a button labeled “Delete” is pressed, the priority setting is deleted, and the priority is substantially zero.

  Furthermore, “learning function” is displayed below, and the on / off of the learning function to be described later is switched by pressing the buttons 361 and 362 at the time of “ON” and “OFF” next to the “learning function”. Can do. In the bottom row, a button 351 indicating “Done” is displayed, and is pressed by the user when the operation is completed.

  The recording setting unit 341 determines whether or not the priority setting has been changed. For example, one of the buttons “UP”, “DOWN”, and “Delete” illustrated in FIG. When pressed by operating the unit 81, it is determined that the setting has been changed. In step S506, the recording setting unit 341 reflects the change in the priority setting, and the display unit 90 or the television set is reflected. Display on the receiver. That is, when the button displayed as UP is pressed, the priority is incremented by one, when the button displayed as DOWN is pressed, the priority is decremented by one, and further, the button displayed as erase is pressed. And the priority setting is deleted. If it is determined in step S505 that the priority setting has not been changed, the process of step S506 is skipped.

  In step S507, the recording setting unit 341 determines whether or not the priority setting is completed by pressing the button 351 displayed as “complete” shown in FIG. 57, and it is determined that the setting is not completed. If so, the process returns to step S504. That is, the processes in steps S504 to S507 are repeated until the button 351 displayed as “complete” is pressed. If it is determined in step S507 that the button 351 displayed as “complete” has been pressed and it is determined that the priority setting has been completed, in step S508, the recording setting unit 341 determines the end of the setting to the recommended server. 13 is notified.

  In step S523, the priority setting unit 331 determines whether or not the completion of the priority setting is notified, and repeats the process until the completion is notified. In step S523, for example, when the completion of the priority setting process is notified by the process in step S508, the process proceeds to step S524.

  In step S524, the operation log acquisition unit 46 reads the operation log list 82 of the recording / playback device 14, acquires the priority information whose settings have been changed by the series of processing in steps S504 to S507, and saves the history as an operation history. Stored in the unit 47.

  In step S525, the priority setting unit 331 changes the priority stored in the initial registration storage unit 301 based on the operation history stored in the history storage unit 47.

  With the above processing, the priority can be changed by the user, so that the priority according to the user's preference can be set, and as a result, the program recommendation display screen with the priority according to the user's preference. Therefore, it is possible to make a recommended program more suitable for the user's preference when making a recording reservation.

  Next, priority learning processing by the recommendation server 13 in FIG. 54 will be described with reference to the flowchart in FIG. This priority learning process is a process that is performed when the learning function is turned on by pressing the learning function ON button 361 as shown in FIG. 57, for example.

  In step S541, the priority setting unit 331 determines whether or not the recording reservation is completed, and repeats the process until the recording reservation is completed. If it is determined that the recording reservation has been completed, the process proceeds to step S542.

  In step S542, the operation log acquisition unit 46 reads the operation log list 82 of the recording / playback apparatus 13, and causes the history storage unit 47 to store an operation history corresponding to the read operation log list.

  In step S543, the priority setting unit 331 determines whether or not a program recommended in the time zone (standard recommended program) has been reserved based on the operation history of the history storage unit 47. For example, the priority setting unit 331 has been reserved. In this case, in step S544, the priority of the time zone algorithm of the standard recommended program is incremented by one. On the other hand, if the program recommended in the time zone (standard recommended program) is not reserved, the priority of the time zone algorithm of the standard recommended program is decremented by 1 in step S545.

  Furthermore, in step S546, the priority setting unit 331 determines whether or not a program recommended by a genre (standard recommended program) is reserved based on the operation history of the history storage unit 47. For example, the priority setting unit 331 is reserved. In step S547, the priority of the genre algorithm of the standard recommended program is incremented by 1. Conversely, if the program recommended by genre (standard recommended program) is not reserved, the priority of the algorithm of the standard recommended program genre is decremented by 1 in step S548.

  In step S549, the priority setting unit 331 determines whether the program recommended by the performer (standard recommended program) is reserved based on the operation history of the history storage unit 47, for example, reserved. If so, in step S550, the priority of the algorithm of the performer of the standard recommended program is incremented by one. On the other hand, if the program recommended by the performer (standard recommended program) is not reserved, the priority of the performer algorithm of the standard recommended program is decremented by 1 in step S551.

  Furthermore, in step S552, the priority setting unit 331 determines whether or not a similar recommended program has been reserved based on the operation history of the history storage unit 47. For example, if it has been reserved, the priority setting unit 331 determines in step S553. The priority of the similar recommended program is incremented by one. On the other hand, when the similar recommended program is not reserved, the priority of the algorithm of the similar recommended program is decremented by 1 in step S554, and the process returns to step S541.

  With the above processing, when the recommended program is reserved for recording for the time zone, genre, performer, and similar type recommended program algorithm of the standard recommended program, the priority is increased by 1 and conversely reserved. If it is not done, the priority for each algorithm can be learned by lowering by one.

  The series of processes described above can be executed by hardware, but can also be executed by software. When a series of processes is executed by software, a program constituting the software may execute various functions by installing a computer incorporated in dedicated hardware or various programs. For example, it is installed from a recording medium in a general-purpose personal computer or the like.

  59 shows a case where the electrical internal configuration of the recommendation server 13 shown in FIG. 3, FIG. 28, FIG. 30, FIG. 33, FIG. 36, FIG. 38, FIG. 1 shows a configuration of an embodiment of a personal computer. The CPU 501 of the personal computer controls the overall operation of the personal computer. Further, when a command is input from the input unit 506 such as a keyboard or a mouse from the user via the bus 504 and the input / output interface 505, the CPU 501 stores the instruction in a ROM (Read Only Memory) 502 correspondingly. Run the program. Alternatively, the CPU 501 reads a program read from the magnetic disk 521, the optical disk 522, the magneto-optical disk 523, or the semiconductor memory 524 connected to the drive 510 and installed in the storage unit 508 into a RAM (Random Access Memory) 503. To load and execute. As a result, the function of the recommendation server 13 shown in FIG. 3, FIG. 28, FIG. 30, FIG. 33, FIG. 36, FIG. 38, FIG. Further, the CPU 501 controls the communication unit 509 to communicate with the outside and exchange data.

  As shown in FIG. 59, the recording medium on which the program is recorded is distributed to provide the program to the user separately from the computer. The magnetic disk 521 (including the flexible disk) on which the program is recorded is distributed. By a package medium composed of an optical disk 522 (including CD-ROM (Compact Disc-Read Only Memory), DVD (Digital Versatile Disk)), a magneto-optical disk 523 (including MD (Mini-Disc)), or a semiconductor memory 524 In addition to being configured, it is configured by a ROM 502 on which a program is recorded, a hard disk included in the storage unit 508, and the like provided to the user in a state of being incorporated in a computer in advance.

  In this specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series in the order described, but of course, it is not necessarily performed in time series. Or the process performed separately is included.

  Further, in this specification, the system represents the entire apparatus constituted by a plurality of apparatuses.

It is a figure which shows the delivery system to which this invention is applied. It is a block diagram which shows the structure of the delivery server of FIG. It is a block diagram which shows the structure of the recommendation server of FIG. It is a block diagram which shows the structure of the video recording / reproducing apparatus of FIG. It is a flowchart explaining the recording reservation process by the delivery system of FIG. It is a figure explaining EPG data. It is a figure explaining a program vector. It is a flowchart explaining an EPG display process. It is a flowchart explaining a setting information change process. It is a figure explaining a setting screen. It is a figure explaining a setting screen. It is a figure explaining EPG. It is a figure explaining a setting screen. It is a figure explaining a setting screen. It is a figure explaining a setting screen. It is a figure which shows the screen displayed when the program for recording reservation is selected. It is a flowchart explaining a recommendation program display screen production | generation process. It is a flowchart explaining the recommendation program number determination process according to algorithm. It is a flowchart explaining a standard system recommended program determination process. It is a flowchart explaining a similar system recommended program determination process. It is a figure explaining a recommendation program. It is a figure which shows the example of the display screen of a recommendation program. It is a figure which shows the example of the display screen of a recommendation program. It is a figure which shows the example of the display screen of a recommendation program. It is a figure which shows the example of the display screen of a recommendation program. It is a figure which shows the example of the display screen of a recommendation program. It is a figure which shows the example of the display screen of a recommendation program. It is a block diagram which shows the other structure of a recommendation server. It is a flowchart explaining the recommendation program number determination process according to algorithm by the recommendation server of FIG. It is a block diagram which shows the further other structure of a recommendation server. It is a flowchart explaining a recommendation program display screen production | generation process. It is a figure which shows the other example of the display screen of a recommendation program. It is a block diagram which shows the other structure of a recommendation server. It is a block diagram which shows the other structure of a video recording / reproducing apparatus. It is a flowchart explaining the recording confirmation process by the recommendation server of FIG. 33 and the recording / reproducing apparatus of FIG. It is a block diagram which shows the other structure of a recommendation server. 37 is a flowchart for explaining algorithm-specific recommended program number determination processing by the recommendation server in FIG. 36. It is a block diagram which shows the other structure of a recommendation server. It is a block diagram which shows the other structure of a video recording / reproducing apparatus. It is a flowchart explaining the recommended program display process by the recommendation server of FIG. 33 and the video recording / reproducing apparatus of FIG. It is a figure explaining a common recommendation program. It is a block diagram which shows the other structure of a recommendation server. 43 is a flowchart for describing recommended program display screen generation processing by the recommendation server of FIG. 42. 43 is a flowchart for describing standard recommended program determination processing by the recommendation server of FIG. 42. 43 is a flowchart for describing similar recommended program determination processing by the recommendation server of FIG. 42. 43 is a flowchart for describing algorithm-specific recommended program number determination processing by the recommendation server of FIG. It is a block diagram which shows the other structure of a recommendation server. It is a flowchart explaining the recording reservation process by the recommendation server of FIG. It is a flowchart explaining the recommendation program display screen generation process by the recommendation server of FIG. It is a block diagram which shows the other structure of a recommendation server. 51 is a flowchart for explaining recommended program display screen generation processing by the recommendation server of FIG. 50. It is a figure explaining the setting of a priority. It is a figure which shows the example of the display screen of a recommendation program. It is a block diagram which shows the other structure of a recommendation server. It is a block diagram which shows the other structure of a video recording / reproducing apparatus. 56 is a flowchart for explaining priority setting processing by the recommendation server in FIG. 54 and the recording / playback apparatus in FIG. 55. It is a figure which shows the example of the display screen of a recommendation program. FIG. 55 is a flowchart for describing priority learning processing by the recommendation server of FIG. 54. FIG. It is a figure explaining a recording medium.

Explanation of symbols

DESCRIPTION OF SYMBOLS 11 Network, 12, 12-1 thru | or 12-n Distribution server, 13 Recommendation server, 14, 14-1 thru | or 14-n Recording / reproducing apparatus, 21 Data acquisition part, 22 Metadata extraction part, 23 Program vector production | generation part, 24 Data storage unit, 25 data transmission unit, 26 metadata DB, 27 streaming data DB, 41 data acquisition unit, 42 program vector extraction unit, 43 similar program recommendation unit, 44 operation input unit, 45 initial registration storage unit, 46 operation Log acquisition unit, 47 history storage unit, 48 acceptance rate calculation unit, 49 recommended program determination unit, 50 recommendation information output unit, 51 recommended program list, 81 operation input unit, 82 operation log list, 83 recording setting unit, 84 recording reservation List, 85 recording control section, 86 data input section, 87 recording / playback processing section, 88 recommended program display image acquisition section, 8 9 recommended program display image, 90 display unit, 201 recommended program determining unit, 211 recommended program determining unit, 231 recommended program determining unit, 241 recording setting unit, 251 recommended program determining unit, 261 recommended program determining unit, 271 recording setting unit, 281 Recommended Program Determination Unit, 282 Acceptance Rate Calculation Unit, 291 Acceptance Rate Calculation Unit, 292 Recommended Program Determination Unit, 301 Initial Registration Storage Unit, 302 Recommended Program Determination Unit, 331 Priority Determination Unit

Claims (4)

Metadata acquisition means for acquiring metadata of a plurality of programs;
For each of the plurality of algorithms, an operation history acquisition means for acquiring an operation history indicating whether or not a program that has been recommended so far is accepted and reserved for recording ;
Program number determining means for determining the number of the programs recommended by each of the plurality of algorithms from the operation history;
Extracting means for extracting the program by a plurality of algorithms based on the metadata of the plurality of programs and the number of the programs recommended by each of the plurality of algorithms;
An information processing apparatus comprising: recommendation means for recommending the program extracted by the extraction means . A metadata acquisition step for acquiring metadata of a plurality of programs;
For each of the plurality of algorithms, an operation history acquisition step for acquiring an operation history indicating whether any of the programs recommended so far is accepted and reserved for recording ;
A program number determination step for determining the number of the programs recommended by each of the plurality of algorithms from the operation history;
An extracting step of extracting the program by a plurality of algorithms based on the metadata of the plurality of programs and the number of the programs recommended by each of the plurality of algorithms;
A recommendation step of recommending the program extracted in the processing of the extraction step. For each of the plurality of algorithms, a program that determines the number of programs recommended by each of the plurality of algorithms from an operation history indicating which programs have been accepted and reserved for recording among the programs recommended so far. A number determination step;
An extracting step of extracting the program by a plurality of algorithms based on the metadata of the plurality of programs and the number of the programs recommended by each of the plurality of algorithms;
A recording medium on which a computer-readable program is recorded for executing a recommendation step of recommending the program extracted in the extraction step . For each of the plurality of algorithms, a program that determines the number of programs recommended by each of the plurality of algorithms from an operation history indicating which programs have been accepted and reserved for recording among the programs recommended so far. A number determination step;
An extracting step of extracting the program by a plurality of algorithms based on the metadata of the plurality of programs and the number of the programs recommended by each of the plurality of algorithms;
A program causing a computer to execute a recommendation step of recommending the program extracted in the extraction step .

Images