JP4924866B2 - Information processing apparatus, information processing method, and program - Google Patents

Description

  The present invention relates to an information processing device, an information processing method, and a program, and more particularly, to an information processing device, an information processing method, and a program that can extract high-quality preference information that accompanies user preferences, for example. .

  Conventionally, in a video recorder that processes EPG (Electronic Program Guide) data, for example, an exclusion keyword that is set to be excluded in advance from EPG data of a program for which the user has started recording or reserved recording, etc. In some cases, the process of extracting keywords from the remaining keywords was performed.

  FIG. 1 is a flowchart for explaining conventional keyword extraction processing.

  The keyword extraction process is performed, for example, when the user makes a program recording or recording reservation.

  In step S11, the video recorder excludes the excluded keyword from the EPG data of the program for which the user has started recording the program or reserved the recording using the exclusion dictionary, and proceeds to step S12. In the exclusion dictionary, keywords that are estimated not to accompany the user's preference are registered as exclusion keywords.

  In step S12, the video recorder extracts keywords from the remaining EPG data from which the excluded keywords are excluded by, for example, a character type separation method which is one of morpheme analysis methods, and ends the processing.

  The extracted keyword is stored as preference information representing the user's preference, and is used, for example, to select a program recommended to the user or a program to be automatically recorded.

  Here, the character type separation method is a method of extracting keywords from title information and detailed information in EPG data, for example, according to the following rules.

  When extracting a keyword from title information in EPG data, the title information is selected from (1) Kanji, Hiragana, Katakana, any one-byte alphabet, (2) Half-width character, (3) Symbol. Each character string composed of any one of the above is separated, and a character string of two or more characters is extracted as a keyword.

  When extracting a keyword from the detailed information in the EPG data, first, an external character that is a character other than a character registered as a character that can be used by the video recorder included in the detailed information is replaced with a space (blank). Next, the detailed information is separated for each character type, and only a character string of three or more characters is extracted as a keyword. In this case, when the character type is Kanji, only a character string of 3 to 5 characters is extracted as a keyword. When the character type is hiragana, even if it is a character string of three or more characters, it is not extracted as a keyword.

In addition, as a technique for acquiring preference information, Patent Document 1 discloses (1) information on how many times a user has viewed a series of programs that are broadcast multiple times as a series. (2) Based on information on how many times of the programs broadcasted multiple times, (3) information on whether or not to watch continuously, the user's preference for the series programs On the other hand, for a non-series program, (1) information on how many times the program has been viewed in a predetermined period, (2) information on the genre of the program, and (3) information on all or one of the times of viewing the program A method for calculating the user's preference for the non-series program based on the section is also disclosed.
Japanese Patent Laid-Open No. 2003-46458

  By the way, since the exclusion keyword used in the conventional keyword extraction process as described above is registered in advance in the exclusion dictionary by the design side, the design side's subjectivity is inevitably included, and it is adapted to all users. An exclusion dictionary cannot be prepared. For example, a keyword that has a preference for a certain user is not registered, or a keyword that does not have a preference for a certain user is registered.

  Also, since the number of excluded keywords registered in the exclusion dictionary is finite, keywords that are not originally accompanied by user preferences may be acquired as preference information without being excluded from the EPG data. It was.

  Therefore, for example, as a user's preference information, a keyword A with the user's preference and keywords B and C without the user's preference may be acquired. In this case, the keyword A is described. In the EPG data program X and the EPG data program Y in which the keywords B and C are described, it is estimated that the program Y in which two keywords are hit is a program that matches the user's preference, As a result, a program Y that does not match the user's preference is recommended.

  In addition, in the method disclosed in Patent Document 1, the degree of preference is calculated from the title, genre, and broadcast frame. However, for detailed information describing program performers and the like, The degree is not calculated.

  Therefore, it is possible to calculate the user's preference for a program such as a monthly drama with a fixed broadcast frame (drama broadcast every 21:00 on Monday), a program of a genre with a large number of views, etc. For example, it is not possible to calculate the user's preference for a program in which a favorite actor (program performer) appears.

  This invention is made | formed in view of such a condition, and enables it to extract the high quality preference information suitable for a user's preference.

In the information processing apparatus according to one aspect of the present invention , a predetermined user operation is performed on a predetermined series program among a plurality of series programs representing each program of the same series broadcast in a plurality of broadcast times. Corresponding to the keyword acquisition means for acquiring at least one keyword from the EPG data of the predetermined series program, and a first set composed of the keyword acquired from the EPG data of the predetermined series program Storage control means for storing in the storage unit in association with broadcast times of the predetermined series program, and a second set associated with broadcast times prior to the predetermined series program stored in the storage unit In the case where the first set is stored in the storage unit, the reading unit that reads the second set from the storage unit, and the read Based on a set of 2, from the first in the set obtained from the EPG data of the predetermined series program, a keyword selection means for selecting a keyword for learning to be used for learning the user's preferences, selection Preference learning means for learning preference information representing the user's preference based on the selected learning keyword, and the keyword selection means includes a plurality of sets corresponding to each set stored in the storage unit. Based on the second set associated with the broadcast times immediately preceding the predetermined series program, the keywords included in the second set are matched with the second set. The learning keyword to be selected, or among the plurality of broadcast times corresponding to each set stored in the storage unit, in each broadcast time before the predetermined series program Based on the plurality of the second set of attached response, from among the first set, which is information processing apparatus for selecting a keyword for the learning common to a set of a plurality of the second.

Wherein the learning-use keyword, those associating the preference level indicating the degree of user's preference for the keyword for the learning, further it can be provided a preference information storage means for storing as the preference information, the preference learning the unit, when a keyword for the learning is stored in the preference information storage unit, updates the preference degree of the keyword for the learning, the keyword for the learning is not stored in the preference information storage unit In this case, it is possible to perform the learning in which the preference information storage unit stores, as new preference information, an association between the learning keyword and the preference level set to a predetermined value.

In the keyword acquisition unit, further, in response to the user operation that has been determined in advance against the non-series program representing different programs and series of programs is performed, the non-series program from the EPG data, at least one of When the keyword is acquired and the preference learning unit stores the keyword acquired from the EPG data of the non-series program as the learning keyword, and the learning keyword is stored in the preference information storage unit, updating the preference degree of the keyword for the learning, if the keywords for the learning is not stored in the preference information storage unit, and keywords for the learning, and the degree of preference is a predetermined value It is also possible to perform the learning in which the preference information storage means stores the information associating as the new preference information.

Based on the preference information, recommendation of a program, or processing means for performing at least one of the reservation of recording of the program may be further provided.

An information processing method according to an aspect of the present invention is an information processing method of an information processing device that learns user preferences, and includes a plurality of programs representing the same series of programs broadcast by a plurality of broadcast times by the information processing device. A keyword acquisition step of acquiring at least one keyword from the EPG data of the predetermined series program in response to a predetermined user operation being performed on the predetermined series program among the series programs of a first set constituted by the keyword acquired from the EPG data of the predetermined series program, a storage control step of storing in the storage unit in association with episode said predetermined series program, in the storage unit When the second set associated with the broadcast times before the predetermined series program is stored, the first set is stored in the storage unit. In response to this, the reading step of reading the second set from the storage unit, and the first set obtained from the EPG data of the predetermined series program based on the read second set from among the set, and a keyword selection step of selecting a learning-use keyword to be used for learning the preferences of the user, based on the keywords for the learning that has been selected, the learning of the taste information representing the taste of the user look including the preference learning step of performing, the keyword selection step, among a plurality of broadcast times corresponding to the respective set already stored in the storage unit, associated with the immediately preceding episode of the predetermined series program Based on the second set, the learning keyword that matches the keyword included in the second set is selected from the first set, or the previous keyword is selected. Of the plurality of broadcast times corresponding to each set stored in the storage unit, the first set is based on the plurality of second sets associated with each broadcast time before the predetermined series program. An information processing method for selecting the learning keyword common to a plurality of the second sets from the set .
The program of one aspect of the present invention corresponds to a predetermined user operation being performed on a predetermined series program among a plurality of series programs representing each program of the same series broadcast in a plurality of broadcast times. Then, a keyword acquisition step of acquiring at least one keyword from the EPG data of the predetermined series program, and a first set composed of the keywords acquired from the EPG data of the predetermined series program , A storage control step for storing in a storage unit in association with broadcast times of a predetermined series program, and a second set associated with broadcast times prior to the predetermined series program are stored in the storage unit. A read step of reading the second set from the storage unit in response to the storage of the first set in the storage unit; The on the basis of the second set, from among the first in the set obtained from the EPG data of the predetermined series program, keyword selection for selecting a keyword for learning to be used for learning the user's preferences a method, based on the keywords for the learning that has been selected, viewing including the preference learning step of performing learning of taste information representing taste of a user, the keyword selection step, each set already stored in the storage unit Among the plurality of broadcast times, the second set corresponding to the broadcast times immediately before the predetermined series program is changed to the second set from the first set. The learning keyword that matches the included keyword is selected, or the predetermined series number is selected from a plurality of broadcast times corresponding to each set stored in the storage unit. Based on the plurality of the second set associated with each episode earlier than, from among the first set, to select the keywords for the learning common to a set of a plurality of the second A program for causing a computer to execute processing.

In one aspect of the present invention, in response to a predetermined user operation being performed on a predetermined series program among a plurality of series programs representing each program of the same series broadcast in a plurality of broadcast times. Then , at least one keyword is acquired from the EPG data of the predetermined series program, and a first set composed of the keywords acquired from the EPG data of the predetermined series program is the predetermined series program When the second set associated with the broadcast times before the predetermined series program is stored in the storage unit in association with the broadcast times, and the storage unit stores the second set In response to storing one set, the second set is read from the storage unit, and based on the read second set, EPG data of the predetermined series program From the first of the set is al acquired, it is selected keywords for learning to be used for learning the preferences of the user, based on the keywords for the learning that has been selected, the preference information indicating a preference of the user Learning is done.
Of the plurality of broadcast times corresponding to each set stored in the storage unit, the first set is based on the second set associated with the broadcast time immediately before the predetermined series program. From the set, the learning keyword that matches the keyword included in the second set is selected, or among a plurality of broadcast times respectively corresponding to each set stored in the storage unit, Based on the plurality of second sets associated with each broadcast time before the predetermined series program, the learning set common to the plurality of second sets from the first set Keywords are selected.

  ADVANTAGE OF THE INVENTION According to this invention, the preference information showing a user's preference with a high quality accompanying a user's preference can be extracted.

Embodiments of the present invention will be described below .

  Next, embodiments of the present invention will be described with reference to the drawings.

  FIG. 2 is a diagram showing a configuration example of a video recorder system to which the present invention is applied.

  The video recorder system of FIG. 2 includes a video recorder 11, an antenna 12, a remote controller 13, and a television receiver 14. The video recorder 11 includes a tuner 31, an EPG data acquisition unit 32, an EPG data storage unit 33, a keyword extraction unit 34, a preference learning unit 35, a preference information storage unit 36, a light receiving unit 37, an operation unit 38, an input / output interface 39, a recording A reservation processing unit 40, a program recording unit 41, a recorded program storage unit 42, a reservation information storage unit 43, and a display control unit 44 are included.

  The antenna 12 receives a digital television broadcast wave (including EPG data) such as a ground wave or a satellite wave, and supplies an RF (Radio Frequency) signal to the tuner 31.

  The remote controller 13 emits an operation signal corresponding to the operation of the remote controller 13 by the user to the video recorder 11 by infrared rays or the like.

  The television receiver 14 displays a predetermined screen according to the control by the display control unit 44. The television receiver 14 displays a recording reservation screen used for setting a recording reservation.

  A tuner 31 constituting the video recorder 11 acquires an audio signal and a video signal of a program broadcast on a predetermined channel (frequency band) from an RF signal supplied from the antenna 12, and the acquired audio signal and video signal are acquired. This is supplied to the program recording unit 41. Further, the tuner 31 acquires a channel signal for broadcasting a program from the RF signal supplied from the antenna 12, and supplies the acquired signal to the EPG data acquisition unit 32.

  The EPG data acquisition unit 32 acquires EPG data from the signal supplied from the tuner 31 and stores (stores) the acquired EPG data in the EPG data storage unit 33.

  The EPG data storage unit 33 stores the EPG data supplied from the EPG data acquisition unit 32. The EPG data stored in the EPG data storage unit 33 includes text data representing the title information and detailed information of each program.

  The keyword extraction unit 34 acquires (reads) the EPG data of the program from the EPG data storage unit 33 when, for example, the recording of the program or the recording reservation is performed by the recording reservation processing unit 40, and from the acquired EPG data. Extract keywords. The extracted keyword is supplied to the preference learning unit 35.

  If the keyword supplied from the keyword extraction unit 34 is not yet registered in the preference information storage unit 36, the preference learning unit 35 registers the unregistered keyword supplied from the keyword extraction unit 34 in the preference information storage unit 36. At the same time, a default preference value is registered as the preference level representing the degree of user preference for the keyword.

  In addition, when the keyword supplied from the keyword extraction unit 34 is already registered in the preference information storage unit 36, the preference learning unit 35 updates the preference level of the keyword registered in the preference information storage unit 36. Thus, in the preference learning unit 35, updating the preference degree according to the frequency with which the same keyword is extracted is performed as learning of the user's preference.

  The preference information storage unit 36 stores the keyword supplied from the preference learning unit 35 and the preference level corresponding to the keyword as preference information representing the user's preference.

  The light receiving unit 37 receives the operation signal emitted from the remote controller 13 and supplies it to the input / output interface 39.

  The operation unit 38 includes a power button, a channel button, and the like provided on the housing surface of the video recorder 11, and supplies an operation signal corresponding to an operation by the user to the input / output interface 39.

  The input / output interface 39 supplies the operation signal supplied from the light receiving unit 37 or the operation unit 38 to the recording reservation processing unit 40.

  The recording reservation processing unit 40 performs various processes using the EPG data acquired from the EPG data storage unit 33 and the preference information acquired from the preference information storage unit 36 according to the operation signal supplied from the input / output interface 39. Do.

  Specifically, the recording reservation processing unit 40, when instructed to start recording a predetermined program, controls the program recording unit 41 to start recording the program. Further, the recording reservation processing unit 40 generates reservation information representing the recording reservation contents of the program based on the EPG data acquired from the EPG data storage unit 33 when the recording reservation of the predetermined program is instructed. Then, the generated reservation information is stored in the reservation information storage unit 43.

  Furthermore, the recording reservation processing unit 40 controls the display control unit 44 to display information on a program recommended to the user on the television receiver 14.

  The program recording unit 41 records the designated program according to the control by the recording reservation processing unit 40. That is, the program recording unit 41 acquires the audio signal and video signal of the designated program supplied from the tuner 31 and stores the acquired audio signal and video signal in the recorded program storage unit 42 as program data of a predetermined format. Remember me.

  The recorded program storage unit 42 stores the program data supplied from the program recording unit 41.

  The reservation information storage unit 43 stores the reservation information supplied from the recording reservation processing unit 40.

  The display control unit 44 causes the television receiver 14 to display program information recommended to the user in accordance with control by the recording reservation processing unit 40.

  FIG. 3 is a diagram illustrating a detailed configuration example of the keyword extraction unit 34 of FIG.

  As shown in FIG. 3, the keyword extraction unit 34 includes a keyword acquisition unit 71, a program determination unit 72, a switch 73, a keyword selection unit 74, and a keyword storage unit 75.

  The keyword acquisition unit 71 acquires EPG data of a recorded program or a program for which recording reservation has been set (hereinafter referred to as a program of interest as appropriate) from the EPG data storage unit 33, and from the acquired EPG data, for example, The keyword is acquired (extracted) using the character type separation method. The keyword acquisition unit 71 supplies the acquired keyword to the switch 73.

  The program determination unit 72 determines whether the program of interest is a series program based on the EPG data acquired from the EPG data storage unit 33, and supplies the determination result to the switch 73. The EPG data includes information indicating that the program is a series program. Here, the series program is a program of every system that is broadcast at a fixed cycle such as a certain time zone every day, a certain time zone every week, and the like.

  The switch 73 supplies the keyword supplied from the keyword acquisition unit 71 to the keyword selection unit 74 or the preference learning unit 35 based on the determination result supplied from the program determination unit 72.

  For example, when it is determined that the program of interest is a series program, the switch 73 supplies the keyword supplied from the keyword acquisition unit 71 to the keyword selection unit 74. On the other hand, when it is determined that the program of interest is not a series program, the switch 73 supplies the preference learning unit 35 with the keyword supplied from the keyword acquisition unit 71.

  The keyword selection unit 74 stores the keyword of the series program supplied from the switch 73 in the keyword storage unit 75. In addition, the keyword selection unit 74 stores, in the keyword storage unit 75, the keyword (the keyword of the previous broadcast times) acquired from the EPG data of the broadcast program before the target program of the series program including the program of interest. If it is, the keyword that matches the keyword of the previous broadcast time is selected from the keywords acquired from the EPG data of the program of interest (keyword of the program of interest). The keyword selection unit 74 supplies the selected keyword to the preference learning unit 35 as a matching keyword.

  The keyword storage unit 75 stores the keyword acquired by the keyword acquisition unit 71 from the EPG data of the series program.

  FIG. 4 is a diagram illustrating an example of a preference information list stored in the preference information storage unit 36 of FIG.

  The left column of the preference information list in FIG. 4 is a column in which keywords are registered. The right column is a column in which the degree of preference of each keyword registered in the left column is registered. The keyword and the preference level are associated with each other and registered in each field. It can be said that a keyword having a higher preference degree is a keyword accompanied by a user's preference.

  Based on such a preference information list, for example, the recording reservation processing unit 40 recommends a program that matches the user's preference.

  Next, the preference learning process performed by the keyword extraction unit 34 and the preference learning unit 35 will be described with reference to the flowchart of FIG.

  This process is performed, for example, when the user records a program or schedules recording.

  In step S31, the keyword extraction unit 34 obtains EPG data of the program of interest from the EPG data storage unit 33 using the program recorded by the user as the program of interest, and performs keyword extraction processing based on the acquired EPG data. Do.

  The keywords are extracted by the keyword extraction process performed here, and the extracted keywords are supplied to the preference learning unit 35. For example, a keyword extracted from EPG data of an attention program (non-series program) that is not a series program, or a part of keywords extracted from EPG data of an attention program that is a series program is a keyword extraction unit 34. To the preference learning unit 35. Details of the keyword extraction processing will be described later with reference to the flowchart of FIG.

  In step S <b> 32, the preference learning unit 35 determines whether the keyword supplied from the keyword extraction unit 34 is already registered in the preference information storage unit 36.

  In step S32, when the preference learning unit 35 determines that the keyword supplied from the keyword extraction unit 34 is not yet registered in the preference information storage unit 36, the preference learning unit 35 proceeds to step S33, and the keyword supplied from the keyword extraction unit 34. Is registered in the preference information storage unit 36, and a default preference value is registered as the preference level of the keyword. Thereafter, the process is terminated.

  On the other hand, if the preference learning unit 35 determines in step S32 that the keyword supplied from the keyword extraction unit 34 has already been registered in the preference information storage unit 36, the process proceeds to step S34 and is registered in the preference information storage unit 36. The preference degree of the keyword being updated is updated, and the process is terminated.

  Next, the keyword extraction process performed in step S31 of FIG. 5 will be described with reference to the flowchart of FIG.

  In step S51, the keyword acquisition unit 71 of the keyword extraction unit 34 acquires EPG data of the program of interest from the EPG data storage unit 33, and acquires keywords from the acquired EPG data using, for example, a character type separation method. The keyword acquisition unit 71 supplies the acquired keyword to the switch 73, and the process proceeds to step S52.

  In step S52, the program determination unit 72 acquires EPG data of the program of interest from the EPG data storage unit 33, and determines whether the program of interest is a series program based on the acquired EPG data. As described above, when the program of interest is a series program, information indicating that is included in the EPG data.

  If it is determined in step S52 that the program of interest is not a series program, the process proceeds to step S53, and the switch 73 supplies the keyword supplied from the keyword acquisition unit 71 to the preference learning unit 35. Thereafter, the process returns to step S31 in FIG. 5, and the subsequent processing is performed.

  On the other hand, when it is determined in step S52 that the program of interest is a series program, the process proceeds to step S54, and the keyword selection unit 74 stores the keyword supplied from the switch 73 in the keyword storage unit 75. When it is determined in step S52 that the program of interest is a series program, the keyword acquired by the keyword acquisition unit 71 is supplied to the keyword selection unit 74 via the switch 73.

  In step S55, the keyword selection unit 74 determines whether or not the keyword of the program of the broadcast times before the program of interest is stored in the keyword storage unit 75, and if it is determined that it is not stored, FIG. The process returns to step S31. At this time, since the keyword is not supplied to the preference learning unit 35, the processing in FIG.

  On the other hand, in step S55, when the keyword selection unit 74 determines that the keyword of the previous broadcast program is stored in the keyword storage unit 75, the process proceeds to step S56, and the previous keyword among the keywords of the program of interest is stored. Select a keyword that matches the keyword of the broadcast program.

  In step S57, the keyword selection unit 74 supplies the keyword selected in step S56 as a matching keyword to the preference learning unit 35, and then returns to step S31 in FIG. 5 to perform subsequent processing.

  As for the keywords extracted from the EPG data of the series program through the above processing, only the keywords that match the keywords of the previous broadcast program are used for learning the preference information. Information is obtained, and as a result, the quality of the recommendation of a program performed based on such high quality preference information is also improved.

  Further, since it is difficult to select a keyword that does not accompany the user's preference as a matching keyword, it is possible to suppress wasteful use of the storage capacity of the preference information storage unit 36 as compared to the case where such a keyword is also stored. Can do.

  Furthermore, since keywords are acquired without using an exclusion dictionary and handled as keywords with user preference, even if keywords are excluded if keywords are extracted using an exclusion dictionary, Without excluding the keyword, it can be reliably handled as a keyword accompanied by the user's preference.

  In addition, after removing an exclusion keyword using an exclusion dictionary, it can also be made to extract a keyword by performing the above process for the remaining keyword contained in EPG data.

  FIG. 7 is a diagram for explaining a program to be compared with a keyword.

  As shown in FIG. 7, programs of the first episode, the second episode, the third episode, the fourth episode, and the sixth episode that are programs of the same series are recorded, for example, and only the program of the fifth episode is recorded. Otherwise, when the second episode program is selected as the program of interest, the second episode program keyword (the keyword extracted from the EPG data of the program) is compared with the first episode program keyword. The matching keywords are used for updating the user's preference information.

  When the third episode program is selected as the program of interest, the keywords of the third episode program are compared with the keywords of the second episode program, and when the fourth episode program is selected as the program of interest. The keyword of the fourth episode program and the keyword of the third episode program are compared. When the sixth episode program is selected as the program of interest, the keyword of the sixth episode program is compared with the keyword of the fourth episode program.

  In other words, the keyword of the program of interest is compared with the keyword of the program of the broadcast program immediately before the program of interest among the programs whose keywords can be compared.

  In addition to the keyword of one program of the previous broadcast time, the keywords of the target program are compared with the keywords of a plurality of programs before the target program, and are common to all the programs to be compared. Only included keywords may be selected as matching keywords.

  In the above, it is assumed that learning of preference information and the like is performed by using the recording of a program or the recording reservation by the user as a trigger. Processing may be started at the timing.

  Moreover, as a display of the screen which recommends to the user the program selected based on the preference information obtained as described above, for example, it is estimated that it matches the user's preference in the displayed program guide or program list. It is possible to adopt a display in which a star mark or the like is added to the program column to be displayed or the column is blinked.

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

  FIG. 8 is a block diagram showing an example of the configuration of a personal computer that executes the above-described series of processing by a program.

  A CPU (Central Processing Unit) 201 executes various processes according to a program stored in a ROM (Read Only Memory) 202 or a storage unit 208. A RAM (Random Access Memory) 203 appropriately stores programs executed by the CPU 201 and data. The CPU 201, ROM 202, and RAM 203 are connected to each other via a bus 204.

  An input / output interface 205 is also connected to the CPU 201 via the bus 204. Connected to the input / output interface 205 are an input unit 206 made up of a keyboard, mouse, microphone, and the like, and an output unit 207 made up of a display, a speaker, and the like. The CPU 201 executes various processes in response to commands input from the input unit 206. Then, the CPU 201 outputs the processing result to the output unit 207.

  A storage unit 208 connected to the input / output interface 205 includes, for example, a hard disk, and stores programs executed by the CPU 201 and various data. The communication unit 209 communicates with an external device via a network such as the Internet or a local area network.

  The drive 210 connected to the input / output interface 205 drives a removable medium 211 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and drives the programs and data recorded therein. Get etc. The acquired program and data are transferred to and stored in the storage unit 208 as necessary.

  As shown in FIG. 8, a program recording medium that stores a program that is installed in a computer and can be executed by the computer includes a magnetic disk (including a flexible disk), an optical disk (CD-ROM (Compact Disc-Read Only). Memory, DVD (Digital Versatile Disc), a magneto-optical disk, a removable medium 211 that is a package medium made of a semiconductor memory, a ROM 202 in which a program is temporarily or permanently stored, or a storage unit 208 It is comprised by the hard disk etc. which comprise. The program is stored in the program recording medium using a wired or wireless communication medium such as a local area network, the Internet, or digital satellite broadcasting via a communication unit 209 that is an interface such as a router or a modem as necessary. Done.

  In the present specification, the steps for describing a program are not only processes performed in time series in the order described, but also processes that are executed in parallel or individually even if they are not necessarily processed in time series. Is also included.

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

It is a flowchart explaining the conventional keyword extraction process. It is a block diagram which shows the structural example of the video recorder system to which this invention is applied. It is a block diagram which shows the detailed structural example of the keyword extraction part of FIG. It is a figure which shows the example of the preference information list memorize | stored in the preference information storage part of FIG. It is a flowchart explaining a preference learning process. It is a flowchart explaining the detail of the keyword extraction process performed in FIG.5 S31. It is a figure which shows the example of the program used as comparison object. And FIG. 16 is a block diagram illustrating a configuration example of a personal computer.

Explanation of symbols

  11 Video recorder, 32 EPG data acquisition unit, 33 EPG data storage unit, 34 Keyword extraction unit, 35 Preference learning unit, 36 Preference information storage unit, 71 Keyword acquisition unit, 72 Program determination unit, 73 Switch, 74 Keyword selection unit, 75 Keyword storage

Claims (6)

In response to a predetermined user operation being performed on a predetermined series program among a plurality of series programs representing each program of the same series broadcast in a plurality of broadcast times, the predetermined series program Keyword acquisition means for acquiring at least one keyword from EPG data;
Storage control means for storing a first set composed of the keywords acquired from EPG data of the predetermined series program in a storage unit in association with broadcast times of the predetermined series program ;
In the case where the second set associated with the broadcast times before the predetermined series program is stored in the storage unit, the first set is stored in the storage unit. Reading means for reading the second set from the storage unit;
Based on the read second set, a learning keyword to be used when learning user preferences is selected from the first set acquired from EPG data of the predetermined series program. Keyword selection means;
Based on the selected keyword for the learning, and a preference learning means for performing learning of the taste information representing the taste of the user,
The keyword selection means includes
Of the plurality of broadcast times respectively corresponding to each set stored in the storage unit, based on the second set associated with the broadcast time immediately before the predetermined series program, the first set The learning keyword that matches the keyword included in the second set is selected,
Or, based on a plurality of the second set associated with each broadcast times prior to the predetermined series program among a plurality of broadcast times respectively corresponding to each set stored in the storage unit, The learning keyword common to the plurality of second sets is selected from the first set.
Information processing apparatus. Wherein the learning-use keyword, those associating the preference level indicating the degree of user's preference for the keyword for the learning, further comprising a preference information storage means for storing as the preference information,
The preference learning means is:
When the learning keyword is stored in the preference information storage means, the preference level of the learning keyword is updated,
When the learning keyword is not stored in the preference information storage unit, the learning keyword is associated with the preference level set to a predetermined value as new preference information. The information processing apparatus according to claim 1, wherein the learning is stored in the preference information storage unit. The keyword acquiring means further, in response to the user operation that has been determined in advance against the non-series program representing different programs and series of programs is performed, the from the EPG data of the non series program, at least one of Get keywords,
The preference learning means uses a keyword acquired from the EPG data of the non-series program as the learning keyword,
When the learning keyword is stored in the preference information storage means, the preference level of the learning keyword is updated,
When the learning keyword is not stored in the preference information storage unit, the learning keyword is associated with the preference level set to a predetermined value as new preference information. The information processing apparatus according to claim 2, wherein the learning is stored in the preference information storage unit. The information processing apparatus according to claim 1, further comprising a processing unit that performs at least one of program recommendation and program recording reservation based on the preference information. In an information processing method of an information processing apparatus for learning user preferences,
According to the information processing apparatus,
In response to a predetermined user operation being performed on a predetermined series program among a plurality of series programs representing each program of the same series broadcast in a plurality of broadcast times, the predetermined series program A keyword acquisition step of acquiring at least one keyword from the EPG data;
A storage control step of storing a first set of the keywords acquired from the EPG data of the predetermined series program in a storage unit in association with the broadcast times of the predetermined series program ;
In the case where the second set associated with the broadcast times before the predetermined series program is stored in the storage unit, the first set is stored in the storage unit. A reading step of reading out the second set from the storage unit;
Based on the read second set, a learning keyword to be used when learning user preferences is selected from the first set acquired from EPG data of the predetermined series program. A keyword selection step;
Based on the selected keyword for the learning, it viewed contains a preference learning step of performing learning of taste information representing taste of a user,
The keyword selection step includes:
Of the plurality of broadcast times respectively corresponding to each set stored in the storage unit, based on the second set associated with the broadcast time immediately before the predetermined series program, the first set The learning keyword that matches the keyword included in the second set is selected,
Or, based on a plurality of the second set associated with each broadcast times prior to the predetermined series program among a plurality of broadcast times respectively corresponding to each set stored in the storage unit, The learning keyword common to the plurality of second sets is selected from the first set.
Information processing method. In response to a predetermined user operation being performed on a predetermined series program among a plurality of series programs representing each program of the same series broadcast in a plurality of broadcast times, the predetermined series program A keyword acquisition step of acquiring at least one keyword from the EPG data;
A storage control step of storing a first set of the keywords acquired from the EPG data of the predetermined series program in a storage unit in association with the broadcast times of the predetermined series program ;
In the case where the second set associated with the broadcast times before the predetermined series program is stored in the storage unit, the first set is stored in the storage unit. A reading step of reading out the second set from the storage unit;
Based on the read second set, a learning keyword to be used when learning user preferences is selected from the first set acquired from EPG data of the predetermined series program. A keyword selection step;
Based on the selected keyword for the learning, it viewed contains a preference learning step of performing learning of taste information representing taste of a user,
The keyword selection step includes:
Of the plurality of broadcast times respectively corresponding to each set stored in the storage unit, based on the second set associated with the broadcast time immediately before the predetermined series program, the first set The learning keyword that matches the keyword included in the second set is selected,
Or, based on a plurality of the second set associated with each broadcast times prior to the predetermined series program among a plurality of broadcast times respectively corresponding to each set stored in the storage unit, The learning keyword common to the plurality of second sets is selected from the first set.
Program for executing the processing to the computer.

Images