JP6069245B2 - Information processing apparatus, information processing apparatus control method, and program - Google Patents

Description

  The present invention relates to an information processing apparatus, a control method for the information processing apparatus, and a program.

  In recent years, systems and services that recommend programs to users based on program metadata including information such as program genres have been proposed. This learns the user's preference for the program based on the user's program viewing history, and recommends a program that matches the user's preference based on the learning result.

  In Patent Document 1, a numerical value indicating a user's preference degree for a topic extracted from an electronic program guide (EPG) with reference to the viewing history calculated by the first calculation unit, and a calculation by the second calculation unit A program recommendation device for presenting a user with a topic recommended to the user and a recommended program corresponding to the topic using a numerical value indicating the degree of preference of the user based on the electronic program guide (EPG) and the viewing history. It is disclosed.

  Non-Patent Document 1 shows that if it is a variety program or music program, it is selected by the performer that the user likes, or if it is a travel program, it is analyzed in the region where it appears, or the part that is not known only by the genre of the program A technique for recommending a television program that covers the above is also disclosed.

International Publication No. 2011/067808

Mynavi News News Top Enterprise Net Trends, “Interview: Proposing a New TV Life Unique to PCs (1) – Automatic Program Recommendation on iEPG”, [online], October 2003, [January 27, 2014 Search], Internet <URL: http://news.mynavi.jp/news/2003/10/14/06.html>

  However, in the above conventional technique, it is not recommended to recommend a program in a state that reflects both the preference (interest) recognized by the user and the preference (interest) learned based on the user's viewing history. It wasn't. Therefore, for example, a program description for a soccer broadcast may include a favorite team name or a player name belonging to the team. Then, even if it is a fan of a player who belongs to the team, the variety program or talk program in which the player appears does not belong to the preference (degree of interest) learned based on the user's viewing history. There is a problem that even if it belongs to the preference (degree of interest) recognized by the user, it is not recommended for the user.

  Further, in the program recommendation device described in Patent Document 1, the user recommends a program corresponding to a topic having a high degree of user preference by referring to the user's viewing history in any calculation unit. Although the user's preference can be handled with the automatically learned interest degree, there is a problem that the user's own preference and the user's manually set interest degree cannot be handled.

  In addition, with the technology described in Non-Patent Document 1, it is possible to pinpoint a program that is particularly recommended for users, but the method of recommendation is not flexible, and the user's preference and interest level There is a problem that it is not possible to present a recommended program that flexibly responds to fluctuations.

  Therefore, the present invention has been made in view of the above-described conventional problems, and by combining the degree of interest with respect to the content genre and the degree of interest with respect to the character string (word, word) of the content, it is possible to flexibly meet the user's preference. An object of the present invention is to provide an information processing apparatus capable of recommending corresponding content, a method for controlling the information processing apparatus, and a program.

In order to solve the above-described problem, the information processing apparatus according to the first aspect of the present invention includes a genre interest degree setting unit that sets a genre interest degree in advance for each genre, which is a classification based on the content, and a user's viewing history. a string interestingness estimation means for estimating the degree of interest of the user for the character string obtained by analyzing a degree of interest of the user estimated by the character string interestingness estimation means, wherein the genre degree of interest set Decide what proportion of content with the genre interest level recommended for all content with respect to the recommendation level obtained by conversion using the genre interest level set by means And a threshold value setting means for setting a threshold value for doing so.

An information processing apparatus according to a second aspect of the present invention is the information processing apparatus according to the first aspect, wherein the degree of interest of the user with respect to the character string is based on a viewing history reflecting the user's preference. wherein the interest degree der Rukoto for string produced by machine learning.

Furthermore, the information processing apparatus according to the present invention described in claim 3 is the information processing apparatus according to claim 1 or 2, wherein the user's degree of interest in the character string includes an interest degree in the character string and the character string. It is estimated that it is estimated by normalizing at least a non-linear area | region among the relationship with this order | rank .

An information processing apparatus according to a fourth aspect of the present invention is the information processing apparatus according to any one of the first to third aspects , wherein the threshold setting means sets the obtained recommendation level. The method further includes means for estimating a recommended ratio of content belonging to a genre for which a predetermined genre interest degree is set based on the set threshold to the content of all genres .

And in order to solve the said subject, the control method of the information processing apparatus in this invention of Claim 5 sets the genre interest degree beforehand for every genre which is a classification | category based on the content content, The genre interest degree setting process When a string interestingness estimating step of estimating the degree of interest of the user with respect to the resulting string by analyzing the viewing history of the user, the interest degree of the user estimated by the character string interestingness estimating step The content set with the genre interest level is in any ratio with respect to the recommended level obtained by converting the genre interest level set in the genre interest level setting step . And a threshold value setting step for setting a threshold value for determining whether to be recommended.

In order to solve the above problem, the program according to the present invention described in claim 6 sets a genre interest degree in advance for each genre, which is a classification based on the content content, in the computer of the information processing apparatus. and setting process, and the string interestingness estimate processing for estimating the degree of interest of the user with respect to the resulting string by analyzing the viewing history of the user, interests of the user estimated by the character string interestingness estimation process The ratio of the content set with the genre interest level to all the content with respect to the recommendation level obtained by converting the degree using the genre interest level set by the genre interest level setting process And a threshold value setting process for setting a threshold value for determining whether or not it is recommended.

  According to the present invention, information processing that can recommend content flexibly corresponding to a user's preference by combining the interest level with respect to the genre of the content and the interest level with respect to the character string (word, word) of the content. Apparatus, information processing apparatus control method, and program are obtained.

It is a figure which shows the structure of the whole information processing system containing the information processing apparatus in embodiment of this invention. It is a schematic block diagram explaining the whole structure of the information processing apparatus in embodiment of this invention. It is a schematic block diagram explaining the whole structure of the web server in embodiment of this invention. It is a functional block diagram of an information processor in an embodiment of the present invention. It is a figure explaining the setting of the interest degree for every genre of content in the information processing apparatus in the embodiment of the present invention. It is a figure which shows the relationship between the interest degree with respect to the character string produced by the machine learning based on viewing history in the information processing apparatus in embodiment of this invention, and an order | rank. It is the figure which normalized the relationship between the degree of interest with respect to the character string created by the machine learning created in FIG. It is a functional block diagram explaining the recommendation degree calculation algorithm of the information processing apparatus in the embodiment of the present invention. It is a flowchart explaining operation | movement of the information processing apparatus in embodiment of this invention. In the information processing apparatus according to the embodiment of the present invention, the discrete value of the degree of interest for each genre of content, and the normalized relationship between the degree of interest and rank for the character string created by machine learning based on the viewing history, It is a figure which shows the relationship between the interest degree and recommendation degree with respect to the normalized character string when it calculates. In the information processing apparatus according to the embodiment of the present invention, the discrete value of the degree of interest for each genre of content, and the normalized relationship between the degree of interest and rank for the character string created by machine learning based on the viewing history, It is a figure explaining the state when a threshold value is set with respect to the relationship between the degree of interest and the recommendation degree with respect to the normalized character string when calculated. It is a functional block diagram explaining the recommendation degree reverse calculation algorithm of the information processing apparatus in the embodiment of the present invention. In the information processing apparatus according to the embodiment of the present invention, the discrete value of the degree of interest for each genre of content, and the normalized relationship between the degree of interest and rank for the character string created by machine learning based on the viewing history, It is a figure explaining the state at the time of calculating backward from the threshold value set with respect to the relationship between the interest degree and recommendation degree with respect to the normalized character string when it calculates. In the information processing apparatus according to the embodiment of the present invention, the real value of the degree of interest for each genre of content and the normalized relationship between the degree of interest and the ranking for the character string created by machine learning based on the viewing history, It is a figure which shows the relationship between the interest degree and recommendation degree with respect to the normalized character string when it calculates.

  Next, embodiments for carrying out the present invention will be described in detail with reference to the drawings. In addition, in each figure, the same code | symbol is attached | subjected to the part which is the same or it corresponds, The duplication description is simplified thru | or abbreviate | omitted suitably. Briefly explaining the contents of the present invention, a setting means for setting the estimated interest level by combining the setting interest degree preset for each content genre and the estimated interest degree estimated by viewing the content, and the composition. A generating means for generating a recommendation level of content belonging to a genre of interest level and a threshold value for determining a recommended ratio of content belonging to a genre having an arbitrary set interest level in all genres are generated. In addition, by including setting means for setting the recommendation level, it is possible to recommend content that flexibly corresponds to the user's preference.

  That is, the estimated value of the degree of interest learned automatically is converted by a non-linear expression corresponding to the degree of interest for each genre of content set by the user. The purpose of this conversion is to control the distribution of the estimated values of the degree of interest learned automatically. And, what percentage of content with the genre interest level recommended for all genre content compared to the case of generating an average recommendation level for the genre interest level? In order to determine the threshold value, a threshold value is provided. In short, a threshold value is provided to determine how much weight (gradient) is added and a recommendation level is generated for each degree of interest in a genre.

  First, the configuration of the entire information processing system including the information processing apparatus according to the embodiment of the present invention will be described. FIG. 1 is a diagram illustrating a configuration of an entire information processing system including an information processing apparatus according to an embodiment of the present invention. Referring to FIG. 1, an information processing system 10 including an information processing apparatus according to an embodiment of the present invention includes an information processing apparatus 200 exemplifying a personal computer (hereinafter also referred to as a PC), which is widely used by the public such as the Internet. Is connected to the Web server 400 via the connectable network 300. Further, the PC 200 can receive broadcast waves transmitted from the broadcasting station 100 and contents transmitted from the Web server 400. Of course, the information processing apparatus 200 includes a mobile information terminal such as a smartphone (not shown) in addition to the PC.

  The Web server 400 is connected to the PC 200 and a smartphone (not shown) via a network 300 such as the Internet. Then, in response to an access request for connecting to an arbitrary Web page issued from the PC 200 or a smartphone (not shown), the Web page provided from the Web server 400 specified by a URL (Uniform Resource Locator) is browsed. It becomes possible. In FIG. 1, only the PC 200 is connected to the network 300 such as the Internet, but the number of information processing apparatuses is not limited to one, and it goes without saying that a plurality of information processing apparatuses are connected.

  Next, the overall configuration of the information processing apparatus according to the embodiment of the present invention will be described. FIG. 2 is a schematic block diagram illustrating the overall configuration of the information processing apparatus according to the embodiment of the present invention. The PC 200 includes a TV tuner unit 201, a network connection unit 205, a CPU (Central Processing Unit) 206, a ROM (Read Only Memory) 202, a RAM (Random Access Memory) 203, an HDD (Hard Disk Drive) 204, , A display unit 207, an input unit 208, and a power supply unit 209.

  The TV tuner unit 201 receives and demodulates terrestrial digital, BS (Broadcasting Satellite), and CS (Communications Satellite) broadcasts transmitted from the broadcast station 100 (FIG. 1) from an antenna. The network connection unit 205 is connected to a network 300 represented by the Internet and serves as an interface with the network 300. The CPU 206 controls the operation of the entire PC 200, loads a control program stored in the ROM 202, and develops various data obtained by the operation of the PC 200 in the RAM 203. The HDD 204 stores application software programs of the PC 200, records TV programs received by the TV tuner unit 201, and contents transmitted from the Web server 400 (hereinafter collectively referred to as contents). To do.

  The display unit 207 is a display screen composed of an LCD (Liquid Crystal Display) or the like. The display unit 207 receives a result of an application software program executed by the PC 200, a TV program received by the TV tuner unit 201, and the Web server 400. The content is displayed. The input unit 208 is for a user to give an instruction to the PC 200 such as a keyboard, a mouse, and a touch panel. The power supply unit 209 supplies AC (Alternative Current: AC) or DC (Direct Current: DC) power to the PC 200.

  Next, the overall configuration of the Web server in the embodiment of the present invention will be described. FIG. 3 is a schematic block diagram illustrating the overall configuration of the Web server according to the embodiment of the present invention. The Web server 400 includes a network connection unit 403, a CPU 404, a ROM 401, a database unit 402, a display unit 405, an operation unit 406, and a power supply unit 407.

  The network connection unit 403 is connected to a network 300 (FIG. 1) represented by the Internet, and serves as an interface with the network 300. The CPU 404 controls the overall operation of the Web server 400. The CPU 404 loads a control program stored in the ROM 401 and develops various data obtained by the operation of the CPU 404 in the database unit 402, as will be described later. The content that matches the user's preference is transmitted. The display unit 405 is a display screen configured by an LCD or the like, and displays a storage status of data stored in the database unit 402 by the Web server 400. The operation unit 406 is for a maintenance person of the Web server 400 to give an instruction to the Web server 400 such as a keyboard, a mouse, and a touch panel. The power supply unit 407 supplies AC or DC power to the Web server 400.

  Next, functional blocks of the information processing apparatus according to the embodiment of the present invention will be described. FIG. 4 is a functional block diagram of the information processing apparatus according to the embodiment of the present invention.

  In FIG. 4, the PC 200 is demodulated by a plurality of tuner units 210, 211, 212, and 213 that receive broadcast waves transmitted from the broadcast station 100 (FIG. 1) and the tuner units 210, 211, 212, and 213. A content recording / playback unit 214 that records and plays back TV programs and content sent from the Web server 400, and an electronic program guide (EPG) that is transmitted using a gap between radio waves transmitted from the broadcasting station 100 And an EPG information management unit 217 for displaying a television program and content on a display 221 such as a liquid crystal (LCD). Of course, the number of tuner sections is not limited to four.

  The display 221 displays a live TV program screen, a recorded TV program playback screen, a list of recorded TV programs, and content received from the Web server 400. However, the program table of the program broadcast in the past, the program currently broadcast, or the program scheduled to be broadcast in the future, acquired by the EPG information management unit 217 described later is also displayed. It is also possible to display a TV program and a Facebook (registered trademark) screen side by side, or display the Facebook screen in the background of the TV screen.

  Further, the PC 200 is received by the network connection processing unit 220 for connecting to the Web server 400 via the network 300 (FIG. 1) available to the public such as the Internet, and the tuner units 210, 211, 212, and 213. Is transmitted from the EPG information management unit 217 and the moving image information acquisition recording unit 219 that acquires and records character strings (words, words) based on the user's viewing history of the TV program and the content acquired from the Web server 400. Interest in character strings (words, words) created by machine learning based on the degree of interest for each genre of content set through the electronic program guide and the interest information acquisition unit 218 and the viewing history of the received user Analyze the recommended degree by performing a predetermined operation between the normalized degree and rank The video analysis processing unit 216, a moving image display processing unit 215 that displays the recommended degree analyzed by the video analysis processing unit 216 on the display 221, and a remote controller 222 that remotely controls the operation of the PC 200 are configured. .

  Next, setting of the degree of interest for each genre of content in the information processing apparatus according to the embodiment of the present invention will be described. FIG. 5 is a diagram illustrating setting of the degree of interest for each genre of content in the information processing apparatus according to the embodiment of the present invention.

  As shown in FIG. 5, the user of the PC 200 can set a program genre 501 and an interest level 502 for each program genre for television programs received via the tuner units 210, 211, 212, and 213. . The program genre 501 is classified into 12 genres such as news / report, sports, information / wide show, drama, music, variety, movie, animation / special effects, documentary / cultural, theater / performance, hobby / education, welfare. This genre classification follows the genre classification defined by ARIB (Association of Radio Industries and Business), but any other genre classification can be used. In addition, the degree of interest 502 can be set in five stages from not interested (0) to interested (4).

  In the example of FIG. 5, news / report coverage is interest level 1, sports is not interested (0), information / wide show is interest level 1, drama is interest level 2, music is interested (4), variety is interest level 2. , The interest level is 3 for movies, the interest level is 3 for animation and special effects, the interest level is 2 for documentary / cultural education, the interest level is 3 for theater / performance, the interest level is 1 for hobbies / education, and the interest level is not interested (0). Has been. The degree of interest for each program genre may be set immediately after the user purchases the PC 200 or after the user purchases the PC 200 and views the content for a certain period. Then, the interest level for each program genre is set by the user using the input unit 208 of the PC 200 to the interest information acquisition unit 218 (FIG. 4) while the screen shown in FIG. 5 is displayed on the display unit 207. To do.

  Next, the relationship between the degree of interest and the ranking for the character string created by machine learning based on the viewing history in the information processing apparatus according to the embodiment of the present invention will be described. FIG. 6 is a diagram showing the relationship between the degree of interest and the ranking for the character string created by machine learning based on the viewing history in the information processing apparatus according to the embodiment of the present invention.

  As shown in FIG. 6, the degree of interest in the character string created by machine learning (machine learning) based on the viewing history reflecting the user's preference, in other words, the character string (word, word) included in the viewing history. The degree of interest for the character string (word, word) obtained by analyzing and evaluating is plotted on the vertical axis, and the rank is plotted on the horizontal axis. In FIG. 6, the ranking by machine learning is substantially covered when the degree of interest in the character string is an average value, but as the degree of interest in the character string becomes extremely large, the rank by machine learning decreases and becomes saturated. As the degree of interest in the character string becomes extremely small, the rank by machine learning increases and becomes saturated.

  Here, machine learning (machine learning) will be described briefly. In the present embodiment, an interest degree estimation algorithm based on a character string is used in a calculation process for generating a recommendation degree. The interest level estimation algorithm based on a character string estimates a user's interest level from character string information such as an outline of a program and a person's name acquired from an electronic program guide (EPG). This estimation is performed using known machine learning (machine learning) such as TF / IDF (Term Frequency Inverse Document Frequency), naive Bayes, vector space method, support vector machine, and the like. In the present embodiment, not only the nonlinear region (saturated region) but also the linear region (the degree of interest with respect to the character string is approximately the average value) of the relationship between the degree of interest and the ranking with respect to the character string illustrated in FIG. The degree of freedom of the number of recommendations is increased by recommending content using the non-saturated region in FIG.

  Next, what normalized the relationship between the degree of interest and the ranking for the character string created by the machine learning created in FIG. 6 will be described. FIG. 7 is a diagram in which the relationship between the degree of interest and the rank for the character string created by the machine learning created in FIG. 6 is normalized.

  In FIG. 7, when the non-linear curve in FIG. 6 is normalized in a linear format, as shown by a curve C in FIG. In the present embodiment, the curve C is calculated and converted so as to be close to the straight line D by performing normalization of (0, 1). If it does so, the interest degree with respect to a character string will be divided | segmented into about 9 to 1 by the point of the order 0.9. When approximated to the straight line D in this way, the length of the portion of the curve C exceeding the straight line D can easily match the number of programs in the whole.

  Next, the recommendation level calculation algorithm of the information processing apparatus in the embodiment of the present invention will be described. FIG. 8 is a functional block diagram for explaining the recommendation level calculation algorithm of the information processing apparatus according to the embodiment of the present invention.

  As shown in FIG. 8, the recommendation degree calculation algorithm 804 that is the object of this embodiment includes an electronic program guide (EPG) 801 for one week, the genre interest degree 802 described in FIG. 5, and a threshold value 803. As an input, a program list 806 with a recommendation level that is equal to or higher than a threshold is finally output. The EPG 801 for one week is a table in which information on each program of the television broadcast is stored by the EPG information management unit 217 (FIG. 4). The title, genre, broadcast date, broadcast station, and other text information are held for each program.

  The genre interest level 802 is an interest level explicitly set for each genre by the user as described in FIG. The degree of interest can be set in stages for each genre such as “drama”, “news / report”, and “variety”.

  The threshold value 803 is used to set a cut-off position (recommendation rate ratio) with respect to the recommendation level generated for each interest level with respect to the genre. It is a feature of this embodiment that the threshold value is correlated with the recommendation degree calculation algorithm 804. The recommendation degree calculation algorithm 804 is a main function of this embodiment, and the interest degree estimation algorithm 805 based on the character string described with reference to FIG. 7 is used in the calculation process of the recommendation degree calculation algorithm 804.

  The electronic program guide (EPG) 801 for one week is acquired by the EPG information management unit 217 (FIG. 4) and then stored in the RAM 203 (FIG. 2), and the genre interest level 802 and the threshold value 803 are input. After being input using the unit 208, it is stored in the HDD 204. An interest level estimation algorithm 805 and a recommendation level calculation algorithm 804 based on a character string are executed by the CPU 206, and a program list 806 with a recommendation level equal to or higher than a threshold is stored in the HDD 204 or the RAM 203.

  Next, the operation of the information processing apparatus in the embodiment of the present invention will be described. FIG. 9 is a flowchart for explaining the operation of the information processing apparatus according to the embodiment of the present invention.

  The recommendation degree calculation algorithm of the present embodiment is characterized in that it particularly has an interest degree normalization procedure and a non-linear transformation based on genre interest degree. In addition, threshold setting used for cut off is also a feature of this embodiment. The operation flow will be described below.

  In FIG. 9, first, in the processing of step (hereinafter referred to as “S”) 901, the degree of interest of a program by a character string is calculated. Specifically, as described with reference to FIG. 6, the relationship between the degree of interest and the ranking for the character string created by machine learning based on the viewing history is obtained. In the process of S902, it is determined whether or not the number of contents has been looped. If it is determined that the number of contents is not looped (S902: NO), the process waits until the number of contents is looped. If it is determined that the number of contents has been looped (S902: YES), the process proceeds to S903.

  In the process of S903, the interest level is normalized. Specifically, this is a process for normalizing the relationship between the degree of interest and the rank for the character string created by the machine learning created in FIG. 6 as described in FIG. In the normalization of the interest level, a conversion is performed such that the maximum value is 1, the average value is 0.5, and the minimum value is 0 with respect to the estimated value of the interest level of the program by the character string. For the accuracy of the subsequent calculations, first, the maximum value, the average value, and the minimum value are to use statistics for a certain period. For example, in the case of calculation using TF / IDF or naïve Bayes, the theoretical maximum / minimum cannot be defined, so that the statistic varies depending on the learning situation and the situation of the program guide. In order to optimally control according to the situation, it is desirable to use statistics over a certain period.

  Secondly, the normalized interest distribution is brought close to a uniform distribution using a non-linear transformation. This is because if the distribution is far from the uniform distribution, it becomes difficult to control the distribution by non-linear transformation using the genre interest degree.

  In the process of S904, it is determined whether or not the number of contents has been looped. If it is determined that the number of contents has not been looped (S904: NO), the process waits until the number of contents is looped. If it is determined that the number of contents has been looped (S904: YES), the process proceeds to S905.

  In the process of S905, non-linear conversion based on the genre interest is performed. The non-linear conversion based on the genre interest is an operation for converting the interest based on the normalized character string non-linearly as shown in FIG. Although both the input and output ranges from 0 to 1, the distribution is controlled by the degree of genre interest. An image of the conversion formula is shown in FIG. FIG. 10 normalizes the relationship between the discrete value of the degree of interest for each genre of content in the information processing apparatus according to the embodiment of the present invention and the degree of interest for the character string created by machine learning based on the viewing history. It is a figure which shows the relationship between the degree of interest and the recommendation degree with respect to the normalized character string when calculating a thing.

  The genre interest level is 1 to 3, and the greater the value, the more interested. In FIG. 10, it can be seen that the distribution moves in a direction in which the recommendation degree generated by the conversion formula of interest degree 3 is high and the recommendation degree generated by the conversion expression of interest degree 1 is low. In addition, the recommendation degree generated by the conversion formula of interest level 3 becomes higher if the interest level for the normalized character string becomes higher as much as possible, and the recommendation level generated by the conversion expression of interest level 1 The degree of recommendation is not high unless the degree of interest in the normalized character string is high. The recommendation level generated by the conversion formula of interest level 1 tends to be high for programs in which character strings (words, words) having a very high level of interest are written in the viewing history. Therefore, even if the content belongs to a genre with a low genre interest level, the recommendation level is high if the interest level for the normalized character string created by machine learning based on the viewing history for the derivative content related to the content is high. Since it becomes high, it becomes easy to become a recording target.

In order to control the distribution, even if the genre interest level is 1 (conversion formula of interest level 1), if the estimated interest level based on the normalized character string is sufficiently high, the recommendation level may be higher. it can. A plurality of such conversion expressions are assumed, such as a power and an arc shape passing through coordinate points (0, 0) and (1, 1). In any case, it is possible to give a similar effect. Thus, the interest level estimated value based on the character string is converted using the interest level with respect to the genre , and the order is reassigned. At that time, the degree of interest by the character string is normalized, and the recommendation degree is further increased or decreased according to the degree of interest set in the genre to which the program belongs.

  Returning to FIG. 9, in the processing of S <b> 906, it is determined whether or not the number of contents has been looped. If it is determined that the content is not looped (S906: NO), the process waits until the content is looped. If it is determined that the number of contents has been looped (S906: YES), the process proceeds to S907.

  In the processing of S907, sorting is performed according to the recommendation level. Specifically, as shown in FIG. 10, sorting is performed from a higher recommendation level to a lower recommendation level to generate a recommendation level. In the process of S908, a cut-off process using a threshold value is performed. An image of the threshold setting method is shown in FIG. FIG. 11 normalizes the relationship between the discrete value of the degree of interest for each genre of content and the degree of interest and rank for a character string created by machine learning based on the viewing history in the information processing apparatus according to the embodiment of the present invention. It is a figure explaining the state when a threshold value is set with respect to the relationship between the degree of interest and the recommendation degree with respect to the normalized character string when the one is calculated.

  When setting the threshold value so that the content corresponding to each degree of interest is recorded at an average ratio to the content of all genres, each of the cases where the degree of interest in the normalized character string is 0.5 What is necessary is just to set the value of the conversion formula in an interest degree to a threshold value. In this case, the thresholds are set as threshold 1, threshold 2, and threshold 3. Similarly, for example, when the threshold value is set so that the content corresponding to each degree of interest is recorded at a rate of 30% with respect to the content of all genres, the degree of interest in the normalized character string is 0. In the case of .7, the value of the conversion formula for each degree of interest may be set as a threshold value. In this case, the threshold values are set as a threshold value 1 ′, a threshold value 2 ′, and a threshold value 3 ′. After the cut-off by the threshold in the process of S908 is performed, the process is terminated.

  Here, how the meaning for the threshold value is presented to the user will be described briefly. Specifically, the threshold value is set to be a turn number in units of ten. For example, when the threshold value is 50, a program recorded as a screen image and a program not recorded are displayed in different colors. The user interface for informing the meaning of the threshold can take any form, such as displaying which program is not recorded and how many programs are recorded as a whole with a GUI (Graphical User Interface).

  Thus, in this embodiment, the estimated value of the degree of interest learned automatically is converted by a non-linear mathematical expression corresponding to the degree of interest for each genre of content set by the user. The purpose of this conversion is to control the distribution of the estimated values of the degree of interest learned automatically. And, in order to determine how much weight (slope) to generate the recommendation degree for each degree of interest in the genre, compared to the case of generating the average recommendation degree for the interest degree in the genre A threshold is set.

  Next, the system configuration of the recommended degree inverse calculation algorithm of the information processing apparatus according to the embodiment of the present invention will be described. FIG. 12 is a functional block diagram illustrating the recommended degree reverse calculation algorithm of the information processing apparatus according to the embodiment of this invention.

  In FIG. 8, the method of setting the threshold values discretely has been described. Applying the description so far, even if the user sets the threshold value as a continuous value, the ratio is recorded for each genre using the interest level conversion formula for each genre corresponding to the threshold value. Can be estimated. In the functional block diagram shown in FIG. 12, the genre interest 121 and the threshold 122 are input, and the estimated recording ratio 124 for each genre is presented using the recommended degree reverse calculation algorithm 123 which is an algorithm for performing the reverse calculation of the recommended level. Thus, the meaning of the set threshold value can be presented to the user.

  FIG. 13 shows an image of the algorithm for calculating the recommended degree. FIG. 13 normalizes the relationship between the discrete value of the degree of interest for each genre of content in the information processing apparatus according to the embodiment of the present invention and the degree of interest for the character string created by machine learning based on the viewing history. It is a figure explaining the state at the time of calculating backward from the threshold set with respect to the relationship between the degree of interest and the recommendation degree with respect to the normalized character string when the one is calculated.

  Arbitrary value set as a continuous value by the user for the recommendation level generated when computing the interest level for each genre of content and the normalized relationship between the level of interest and ranking for the character string And the intersection of the genre interest level 1 to 3 conversion formulas. Assume that the degrees of interest in the normalized character strings at the intersections are 0.4, 0.76, and 0.96, respectively. As a result, programs with a genre interest level of 3 are 60% for all genre programs, programs with a genre interest level of 2 are 24% for programs of all genres, and programs with a genre interest level of 1 are for all genres. It is estimated that 4% of the program is recorded.

  Moreover, in the said embodiment, it demonstrated on the assumption that a genre interest degree takes discrete values, such as 1, 2, and 3. The genre interest level can also be expressed as a real value. The conversion formula for each genre interest level may be expressed as a real number that changes according to the interest level.

Specifically, when a power is used, the power may be calculated from the genre interest degree as a real number. That is, when y = x ⁿ is used, n may be adjusted according to the degree of interest. In short, n is 1/2 according to the genre interest degree 3, n = 1 when the genre interest degree 2 is n, and n = 2 when the genre interest degree 1 is n according to the interest degree. A continuous value may be set.

  Also, when using an arc, the point of whether the center point is above and below and the radius of the arc may be calculated from the genre interest. In FIG. 14, the relationship between the real value of the degree of interest for each genre of content and the degree of interest for the character string created by machine learning based on the viewing history is normalized in the information processing apparatus according to the embodiment of the present invention. The relationship between the degree of interest and the recommendation degree for the normalized character string when the one is calculated. The area E in FIG. 14 is an area when the degree of interest for each genre of content is a real number.

  Further, in the above embodiment, the genre interest level is explicitly set by the user as shown in FIG. 5, but may be learned by a different method. For example, you may make it learn automatically. Although it has been explained in FIG. 14 that the genre interest level can be converted into a real number, an automatic learning value may be used as the genre interest level. This is particularly effective when the user's consciousness is different from the program guide expression. Furthermore, the recommendation level can be used for purposes other than recording purposes.

  Further, in the above embodiment, the interest level estimated value for the character string (word, word) is adopted as the normalized interest level. However, if it is possible to mount an appropriate determination means, image data and audio The degree of interest in data can be adopted as the normalized degree of interest. Furthermore, it is possible to acquire the degree of interest for each genre from a Web server.

  In the present embodiment, a television program is described as an example, but the present invention can be applied to other fields where a similar amount of information exists. For example, some contents such as VOD (Voice On Demand) and Web news, which are examples of YouTube (registered trademark), are classified into genres, and the degree of interest can be acquired in addition to the genre. If it can be evaluated, a recommendation degree can be generated. For example, text information related to the content is combined, and the degree of interest or preference is learned based on the operation history for the content. Then, the ranking and the score are assigned to the word-based learning of the text information, and it is only necessary to be normalized in the end. In addition, the degree of interest in the genre is set separately, and the degree of recommendation can be generated by converting the degree of interest in the genre using this normalized weight.

  As described above, according to the present invention, it is possible to make a recommendation that combines both an interest level for a genre and an estimated interest level for a character string. Even if the genre has a low interest level, the recommendation level is high when the interest level estimation value for the character string is particularly high. Also, by setting a threshold value, it can be presented in the form of an estimated value of the recording ratio of each genre.

  In addition, each operation | movement of each functional block which comprises the information processing apparatus (PC) 200 in embodiment of this invention shown in FIG. 9 can also be made to perform the program on a computer. That is, the processing is performed by the CPU 206 of the information processing apparatus 200 loading a program stored in a storage unit configured by the ROM 202, the RAM 203, and the like, and sequentially executing each processing step of the program.

  As described above, according to the present invention, the setting interest degree set in advance for each content genre and the estimated interest degree estimated by viewing the content are combined, and the combined interest is estimated by combining. Generating means for generating a recommendation degree of content belonging to the genre of the set interest degree with respect to the degree, and a threshold value for determining a recommended ratio of the content belonging to the genre having an arbitrary set interest degree in the content of all genres By including setting means for setting the generated recommendation level, it is possible to recommend content that flexibly corresponds to the user's preference.

  The present invention has been described above by the preferred embodiments of the present invention. While the invention has been described with reference to specific embodiments thereof, various modifications and changes can be made to these embodiments without departing from the broader spirit and scope of the invention as defined in the claims. is there.

DESCRIPTION OF SYMBOLS 10 Information processing system 100 Broadcasting station 121,802 Genre interest degree 122,803 Threshold value 123 Recommendation degree reverse calculation algorithm 124 Estimated recording ratio for every genre 200 Information processing apparatus (PC)
201 TV tuner 202, 401 ROM
203 RAM
204 HDD
205, 403 Network connection unit 206, 404 CPU
207, 405 Display unit 208 Input unit 209, 407 Power source unit 210, 211, 212, 213 Tuner unit 214 Content recording / playback unit 215 Video display processing unit 216 Video analysis processing unit 217 EPG information management unit 218 Interest information acquisition unit 219 Video information Acquisition recording unit 220 Network connection processing unit 221 Display 222 Remote control 300 Network 400 Web server 402 Database unit 406 Operation unit 501 Program genre 502 Interest 801 EPG for one week
804 Recommended degree calculation algorithm 805 Interest level estimation algorithm based on character string 806 Program list with recommended degree above threshold

Claims (6)

A genre interest level setting means for setting a genre interest level in advance for each genre, which is a classification based on the content of the content;
Character string interest degree estimating means for estimating the user's interest degree with respect to the character string obtained by analyzing the user's viewing history;
The genre interest with respect to the recommendation degree obtained by converting the interest degree of the user estimated by the character string interest degree estimation means using the genre interest degree set by the genre interest degree setting means. A threshold setting means for setting a threshold for determining the proportion of recommended content for all content;
An information processing apparatus comprising:   The information processing apparatus according to claim 1, wherein the degree of interest of the user with respect to the character string is an interest degree with respect to a character string created by machine learning based on a viewing history reflecting the user's preference. .   The degree of interest of the user for the character string is estimated by normalizing at least a non-linear region of the relationship between the degree of interest for the character string and the rank of the character string. 2. The information processing apparatus according to 2.   Based on the threshold set by the threshold setting means, the recommended ratio of the content belonging to the genre for which the predetermined genre interest is set to the content of all genres is estimated with respect to the obtained recommendation level. The information processing apparatus according to claim 1, further comprising means. A genre interest level setting step for setting a genre interest level in advance for each genre, which is a classification based on the content of the content;
A character string interest degree estimating step for estimating the user's interest degree with respect to the character string obtained by analyzing the user's viewing history;
The genre interest with respect to the recommendation degree obtained by converting the interest degree of the user estimated in the character string interest degree estimation step using the genre interest degree set in the genre interest degree setting step. And a threshold value setting step for setting a threshold value for determining at what ratio the set content is recommended for all contents. In the computer of the information processing device,
A genre interest level setting process for setting a genre interest level for each genre, which is a classification based on the content,
A character string interest estimation process for estimating the user's interest in the character string obtained by analyzing the user's viewing history;
The genre interest with respect to the recommendation degree obtained by converting the interest degree of the user estimated by the character string interest degree estimation process using the genre interest degree set by the genre interest degree setting process. A threshold setting process for setting a threshold value for determining what ratio is recommended for all contents,
A program for running

Images