JP2019053621A - Information processor, information processing method, and information processing program - Google Patents

Abstract

To provide an information processor, an information processing method, and an information processing program capable of accurately predicting an index related to contents.SOLUTION: An information processor according to the present application includes: an accompanying information acquisition unit, a focused word information acquisition unit, and a prediction unit. The accompanying information acquisition unit acquires accompanying information accompanying contents. The focused word information acquisition unit acquires a focused word information indicating a focused word on a network. The prediction unit predicts an index related to the contents based on the accompanying information acquired by the accompanying information acquisition unit and the focused word information acquired by the focused word information acquisition unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

  2. Description of the Related Art Conventionally, a technique for predicting a box office performance such as distribution income for a movie has been proposed (see, for example, Patent Document 1). In such a prior art, the box office performance when an unreleased movie is released is predicted based on the performance data of other movies released in the past.

JP 2002-197233 A

  By the way, the prediction of the future box office performance of the movie as described above is important in conducting the marketing of the movie. Here, as an index that is desired to be predicted for content including a movie, an electronic book, and the like, there are the number of sales in the case of an electronic book in addition to the box office performance in the case of the movie. In addition, for example, an evaluation value indicating the degree of satisfaction with a user's content is also expected to be predicted as an index related to the content.

  However, with the above-described indexes related to contents, it may be difficult to predict with high accuracy only from past performance data as in the prior art. As described above, the prior art has room for improvement in terms of accurately predicting the index related to the content.

  The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of accurately predicting an index related to content.

  The information processing apparatus according to the present application includes an accompanying information acquisition unit, an attention word information acquisition unit, and a prediction unit. The accompanying information acquisition unit acquires accompanying information accompanying the content. The attention word information acquisition unit acquires attention word information indicating a word of interest on the network. The prediction unit predicts an index related to the content based on the accompanying information acquired by the accompanying information acquisition unit and the attention word information acquired by the attention word information acquisition unit.

  According to one aspect of the embodiment, it is possible to accurately predict an index related to content.

FIG. 1 is an explanatory diagram illustrating an example of information processing according to the first embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing system. FIG. 3 is a diagram illustrating a configuration example of the user terminal device. FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus. FIG. 5 is a diagram illustrating an example of the model information storage unit. FIG. 6 is a diagram illustrating an example of the accompanying information storage unit. FIG. 7 is a diagram illustrating an example of the attention word information storage unit. FIG. 8 is a flowchart showing a flow of information processing in the information processing apparatus. FIG. 9 is a diagram illustrating a configuration example of the information processing apparatus according to the second embodiment. FIG. 10A is a diagram (part 1) illustrating an example of an action history information storage unit. FIG. 10B is a diagram (part 2) illustrating an example of an action history information storage unit. FIG. 11 is a diagram illustrating an example of the user attribute information storage unit. FIG. 12 is a flowchart showing a flow of information processing in the information processing apparatus according to the second embodiment. FIG. 13 is a diagram illustrating an example of a hardware configuration of a computer that executes a program.

  Hereinafter, a mode for carrying out an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment.

(First embodiment)
[1. Information processing)
First, an example of information processing according to the first embodiment will be described with reference to FIG. FIG. 1 is an explanatory diagram illustrating an example of information processing according to the first embodiment. In the example illustrated in FIG. 1, information processing is performed by the information processing device 70.

  The information processing device 70 is connected to the content distribution device 50 and the focused word detection device 60 via a network such as the Internet, and is a server that transmits / receives various information to / from these devices. Various types of information includes content-accompanying information 51 and attention word information 61, which will be described later, and the information processing apparatus 70 performs processing for predicting, for example, an index related to the content based on such information.

  The information processing device 70, the content distribution device 50, and the attention word detection device 60 described above do not need to be a single processing device, but are realized by a plurality of processing devices such as a cloud system operating in cooperation. Also good. Further, in FIG. 1, the information processing device 70, the content distribution device 50, and the attention word detection device 60 are separate devices, but this is illustrative and not limited, and for example, the information processing device 70 distributes content. You may make it provide the apparatus 50 and the attention word detection apparatus 60. FIG.

  The contents include electronic books which are electronic books, for example, video contents (movie contents) such as movies and TV programs, games, etc., but are not limited to these, and other types of contents can be used. May be included. Further, the content is distributed and used by the content distribution device 50, for example, to the user terminal device 10 (see FIG. 2), but the distribution method is not limited to this.

  The index related to the content is information indicating the future popularity regarding the content, for example, and is an index indicating the possibility that the content will be hit in the future, in other words, the possibility of the popularity. Accordingly, the index related to the content includes, for example, “number of sales” and “sales amount” of the predicted content, “evaluation value” of the user's content, and the like.

  “Number of sales” is a value indicating, for example, the number of contents sold or the number of downloads. The “sales amount” is a value indicating, for example, the total sales amount of the content or the box office revenue when the content is a movie. The “evaluation value” is a value indicating a degree of satisfaction with the user's content, and is, for example, a score included in the user's review information.

  The information indicating the future popularity related to the content, which is an index related to the content, is not limited to the number of sales and the sales amount described above. In other words, the index (information indicating future popularity) may be anything that is predictable, such as an author or theme that may be hit in the future, related to the content. .

  By the way, the prediction of the index related to the content as described above is important for the future marketing of the content. Therefore, in the information processing apparatus 70 according to the present embodiment, it is possible to accurately predict the index related to the content.

  More specifically, the information processing apparatus 70 acquires the accompanying information 51 accompanying the content from the content distribution apparatus 50 (step S1). Here, for convenience of understanding, the accompanying information 51 will be described by taking the case where the content is an electronic book as an example.

  The accompanying information 51 is, for example, information indicating a word used in a sentence in a book (hereinafter may be referred to as “used word”), a book author name, and the like. Note that information indicating the rank of use frequency may be associated with the information on the use word. The rank of the frequency of use is, for example, extracted from the words in the book using various techniques such as morphological analysis, the words excluding particles and pronouns are counted, and the number of times the extracted words are used is counted. Although it can calculate by arranging in order with the largest number of times of use, it is not limited to this.

  In FIG. 1, the used word and the author name are shown as the accompanying information 51, but these are merely examples and are not limited. That is, the accompanying information 51 may include various information included in the content such as the content category, the theme, the selling price of the electronic book as the content, and the number of pages, in addition to or instead of the word used. . Hereinafter, in the accompanying information 51, the word used, the author name, the category, the theme, and the like may be referred to as “keyword”.

  Next, the information processing apparatus 70 acquires attention word information 61 indicating a word of interest on the network from the attention word detection apparatus 60 (step S2).

  The attention word detection device 60 accesses, for example, a search site or a news site, and detects the attention word information 61. The detection of the attention word information 61 will be described later.

  Here, the attention word information 61 is information indicating a word whose degree of attention is increasing on a network such as the Internet. In other words, the attention word information 61 indicates a word that is currently interested or interested in many users. Information. In the example of FIG. 1, the attention word information 61 includes information such as “weather”, “popular actor name: YY”, “word AA”, “author name: XX”, and the like.

  Then, the information processing apparatus 70 predicts an index related to the content based on the accompanying information 51 and the attention word information 61 (step S3). The prediction of the index is performed by calculating the index. In calculating the index, for example, a model obtained by regression analysis can be used, which will be described later.

  In the example of FIG. 1, “word AA” and “author name XX” of the accompanying information 51 of the content are included in the attention word information 61. That is, a keyword such as “word AA” included in the content is included in the attention word information 61 indicating words that are currently interesting to many users.

  Thus, when the accompanying information 51 of the content is included in the attention word information 61 in which the user is interested or interested at the present time, it is estimated that the content is likely to hit in the future. Therefore, in the case of FIG. 1, in the present embodiment, the index related to the content is set to a value indicating that the possibility of a hit in the future is relatively high.

  As described above, according to the present embodiment, by using the accompanying information 51 of the content and the attention word information 61 in which the user is interested or interested in the current time, it is possible to accurately calculate an index related to the content.

[2. Information processing system 1]
FIG. 2 is a diagram illustrating a configuration example of the information processing system 1. As illustrated in FIG. 2, the information processing system 1 according to the first embodiment includes a user terminal device 10, an information user terminal device 40, a content distribution device 50, an attention word detection device 60, and an information processing device 70. With.

  These various apparatuses are connected via a network N so that they can communicate with each other wirelessly or by wire. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

  The user terminal device 10 is a terminal device used by a user (not shown). The user terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a PDA (Personal Digital Assistant), a desktop PC (Personal Computer), a notebook PC, or the like. In FIG. 2, a plurality of user terminal devices 10 are shown, but the present invention is not limited to this, and one user terminal device 10 may be used.

[3. User terminal device 10]
FIG. 3 is a diagram illustrating a configuration example of the user terminal device 10. As illustrated in FIG. 3, the user terminal device 10 includes a communication unit 11, a display unit 12, an input unit 13, a control unit 20, and a storage unit 30.

[3.1. Communication unit 11]
The communication unit 11 is connected to the network N by wire or wireless, and can transmit and receive information to and from the content distribution device 50, the information processing device 70, and the like. For example, the communication unit 11 is realized by a NIC (Network Interface Card) or the like.

[3.2. Display unit 12]
The display unit 12 is a display device that displays various information including content such as an electronic book. For example, the display unit 12 is an LCD (Liquid Crystal Display) or an organic EL display. The display unit 12 may be a touch panel display.

[3.3. Input unit 13]
The input unit 13 is an input device that accepts various operations from the user. The input unit 13 includes, for example, buttons for inputting characters and numbers. When the display unit 12 is a touch panel display, a part of the display unit 12 functions as the input unit 13.

[3.4. Storage unit 30]
The storage unit 30 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 30 stores various programs, setting data, received content information, and the like.

[3.5. Control unit 20]
The control unit 20 is a controller, and includes, for example, a microcomputer having a central processing unit (CPU), a read only memory (ROM), a RAM, an input / output port, and various circuits. Further, the control unit 20 may be configured by hardware such as an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 20 includes a transmission unit 21, a reception unit 22, and a processing unit 23.

[3.6.1. Transmitter 21]
For example, the transmission unit 21 transmits a content (for example, electronic book or video content) acquisition request to the content distribution device 50 in accordance with a user operation received via the input unit 13.

  Further, for example, when the content is displayed on the display unit 12 and the user's operation on the content is received, the transmission unit 21 transmits a signal indicating the operation to the content distribution device 50. Note that the operations on the content include various operations such as an operation for advancing the page and a marker operation for attaching a marker to a specific position when the content is an electronic book. When the content is video content, various operations such as an operation for fast-forwarding or rewinding the video are included in the operation for the content.

[3.6.2. Receiver 22]
For example, the receiving unit 22 receives content information distributed from the content distribution device 50. The reception unit 22 can store the received content information in the storage unit 30.

[3.6.3. Processing unit 23]
The processing unit 23 controls the entire user terminal device 10 including the display unit 12 and the like. For example, the processing unit 23 can read content information received by the receiving unit 22 from the storage unit 30 and output the information to the display unit 12 for display.

[4. Information user terminal device 40]
Returning to the description of FIG. 2, the information user terminal device 40 is, for example, a terminal device of a person who uses information such as the index related to the content. Therefore, for example, the information processing apparatus 70 can provide information such as an index related to the predicted content to the information processing apparatus 70 via the network N.

  Accordingly, the information user can efficiently perform marketing such as a content sales strategy by using the index. The information user terminal device 40 is realized by, for example, a smartphone, a tablet terminal, a PDA, a desktop PC, a notebook PC, or the like.

[5. Content distribution device 50]
For example, the content distribution device 50 is a server that distributes various types of content corresponding to an acquisition request when a content acquisition request is received from the user terminal device 10. For example, when the content distribution device 50 is an electronic book distribution device, the content distribution device 50 distributes electronic book information as content. For example, when the content distribution device 50 is a video content distribution device, the content distribution device 50 distributes information on video content such as a movie as content.

  In addition, the content distribution device 50 can transmit the content accompanying information 51 to the information processing device 70 when receiving an acquisition request for the content accompanying information 51 (see FIG. 1) from the information processing device 70.

[6. Attention word detection device 60]
The attention word detection device 60 is a server that performs processing for detecting attention word information 61 (see FIG. 1) as described above. For example, the attention word detection device 60 accesses various sites such as a search site, a news site, a travel site, a shopping site, and a blog site provided from a web server (not shown), and collects information on each site. To do.

  Then, the attention word detection device 60 analyzes the collected information using various techniques such as morphological analysis, and detects (extracts) the attention word attracting attention in a predetermined period. The attention word is also called a so-called buzz word.

[7. Information processing apparatus 70]
FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus 70. As illustrated in FIG. 4, the information processing apparatus 70 includes a communication unit 71, a control unit 80, and a storage unit 90.

  As described above, the information processing apparatus 70 acquires the accompanying information 51 and the attention word information 61 of the content, and predicts the index related to the content based on the acquired accompanying information 51 and the attention word information 61. it can. Hereinafter, the configuration of the information processing apparatus 70 will be specifically described.

[7.1. Communication unit 71]
The communication unit 71 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from each device such as the content distribution device 50 and the attention word detection device 60. For example, the communication unit 71 is realized by a NIC or the like.

[7.2. Storage unit 90]
The storage unit 90 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 90 according to the present embodiment includes a model information storage unit 91, an accompanying information storage unit 92, and an attention word information storage unit 93.

[7.2.1. Model information storage unit 91]
The model information storage unit 91 stores model information for calculating the index related to the content. FIG. 5 is a diagram illustrating an example of the model information storage unit 91. For example, the model information storage unit 91 includes items such as “model ID” and “model information”.

“Model ID” indicates identification information for identifying a model. “Model information” indicates information on a model used for calculation of an index relating to content (hereinafter, sometimes simply referred to as “index”). In the example illustrated in FIG. 5, the model ID “M01” indicates that the model information is “MM”. Such “MM” includes specific model data (for example, a weight value set in ω _n to be described later) constituting the model.

  Here, an example of a model for calculating the index will be described. For example, the model is generated by the model generation unit 81 (see FIG. 4) of the control unit 80.

  For example, the model generation unit 81 generates a model by regression analysis using predetermined correct answer data. In the following, a case where the content is an electronic book and the index is the number of sales will be described as an example.

  For the electronic books sold in the past, the model generation unit 81 uses the actual number of sales (the number of sales copies as a result) as correct data (object variable), and the “sale price”, “number of pages”, “ Regression analysis can be performed using “category”, “theme”, “author name”, etc. as elements (explanatory variables).

  Further, the model generation unit 81 acquires accompanying information of an electronic book sold in the past from the content distribution device 50 and acquires attention word information from the attention word detection device 60 during a period in which the electronic book is sold. Good.

  Then, the model generation unit 81 uses the keyword information and the attention word information in the accompanying information to determine how often the keyword information is included in the attention word information (hereinafter, may be referred to as “keyword frequency”). Is calculated.

  The model generation unit 81 can perform a regression analysis using the calculated keyword frequency as an element. That is, the model generation unit 81 can use as an element a keyword frequency indicating how many keywords included in the electronic book are included in a word that has been noticed by the user during the period in which the electronic book is sold. .

  Specifically, the model generation unit 81 generates a regression equation such as the following equation (1).

Y = ω ₁ · x ₁ + ω ₂ · x ₂ + ω ₃ · x ₃ + ... + ω _n · x _n ... (1)

In the above formula (1), for example, correct data such as the actual number of sales of electronic books is input to “Y”. “X _{1 to} x _n ” includes, for example, variables (for example, sales price, number of pages, keyword, etc.) obtained by quantifying each of the sales price, the number of pages, the keyword frequency, etc. of the electronic book sold. Information obtained by quantifying the frequency and the like so that they can be compared with each other is input. In addition, n in Formula (1) shows arbitrary numbers.

The model generation unit 81 optimizes the value of “ω _n ” corresponding to each item by advancing learning using the above formula (1) (that is, calculating a sufficient number of samples recursively). . That is, the model generation unit 81 calculates, for example, a weight value “how much an element such as“ keyword frequency ”affects the index when calculating an index that represents the number of future sales for the electronic book. The value of “ω _n ” is obtained. The model generation unit 81 sets the obtained weight value and generates a model.

  Equation (2) below shows a model for calculating an index related to content. In the following equation (2), specific numerical values obtained by performing regression analysis on the equation (1) are substituted into the respective weight values ω.

Index related to content = ω ₁ · x ₁ + ω ₂ · x ₂ + ω ₃ · x ₃ + ... + ω _n · x _n (2)

The index related to the content is calculated by the prediction unit 84 (see FIG. 4) of the control unit 80. For example, the prediction unit 84 calculates an index (the number of sales in this case) related to the electronic book by inputting information on the electronic book to be predicted to “x ₁ ” to “x _n ” in the generated model. Can do. The calculated index may be the number of sales of the electronic book itself, or a score indicating the number of sales.

  The model described above is an example, and the model generated by the model generation unit 81 is not limited to the above example. In other words, the model generation unit 81 can appropriately generate a model different from the above example by combining known methods as long as it is a model that receives keyword frequency and the like and outputs a value indicating an index related to content. Good. For example, in the above example, an example is shown in which a model is generated by regression analysis, but the model generation unit 81 may generate a model by other statistical processing.

  In the above description, the keyword frequency, the sales price, and the like are specifically used as elements, but these are merely examples and are not limited. That is, of the information such as the keyword frequency and the sales price, any information may be used as an element, and further, other types of information may be used as an element. For example, the model generation unit 81 may use information (for example, information related to the contents of the electronic book) tagged to the content by the user or review information as an element.

  When the electronic book includes image information such as a cartoon, the model generation unit 81 analyzes the image information and extracts an object extracted based on the intersection of lines, corners, shading, color tone, etc. The feature of the image may be used as an element. The feature of the image does not necessarily need to be extracted based on the image analysis. For example, the feature of the image may be artificially determined and used as an element.

[7.2.2. Accompanying information storage unit 92]
The accompanying information storage unit 92 stores the accompanying information described above. FIG. 6 is a diagram illustrating an example of the accompanying information storage unit 92. For example, the accompanying information storage unit 92 includes items such as “accompanying information ID”, “information type”, and “information content”.

  The “accompanying information ID” indicates identification information for identifying the accompanying information. “Information type” indicates the type of information included in the accompanying information. “Information content” indicates the content of information included in the accompanying information.

  In the example illustrated in FIG. 6, the accompanying information ID “A1-01” indicates that the information type is “used word” and the information content is “word AA”. Information indicating the rank of the usage frequency of the word AA (here, “the first usage frequency”) may be associated with the information content.

  In the above description, the usage frequency of the used words is ranked. However, the present invention is not limited to this, and the used word (here, the word AA) is included in the number of times the used word is used and the number of all words included in the electronic book. ) May be used as frequency information.

  Further, as shown in FIG. 6, the accompanying information includes information such as an author, a category, a theme, a sales price, and the number of pages, but is not limited thereto. For example, other information such as a publisher and a release date is included. Types of information may be included.

  6 shows the accompanying information when the content is an electronic book, but the type of information may be different when the content is video content such as a movie. That is, the accompanying information of the video content may include various information such as performers, lines, directors, supervisions, categories, themes, and screening times. Note that the accompanying information of the video content described above is merely an example and is not limited.

[7.2.3. Attention word information storage unit 93]
The attention word information storage unit 93 stores the attention word information described above. FIG. 7 is a diagram illustrating an example of the attention word information storage unit 93. For example, the attention word information storage unit 93 includes items such as “attention word information ID”, “information source”, and “information content”.

  “Attention word information ID” indicates identification information for identifying attention word information. “Information source” indicates information such as a site where attention word information is detected. “Information content” indicates the content of the information included in the attention word information.

  In the example illustrated in FIG. 7, the attention word information ID “B1-01” indicates that the information source is “search site” and the information content is “weather”. Information indicating the ranking of the search frequency of “weather” that is the attention word (here, “first search frequency”) may be associated with the information content.

  In the above, the search frequency of the attention word is ranked. However, the present invention is not limited to this, and the ratio of “weather” as the attention word to the number of times the attention word is searched or the total number of words searched. Such information may be used as search frequency information.

  In the example shown in FIG. 7, the attention word information includes “popular actor name: YY”, “word AA”, “popular travel destination name: word BB”, “popular product name: word CC”, “author name”. : XX ". As described above, in the case where “word AA”, “word BB”, “word CC”, and “author name: XX” included in the accompanying information of the content are also included in the attention word information, the above-described index regarding the content May be calculated as a value indicating that the possibility of hitting is high.

[7.3. Control unit 80]
Returning to the description of FIG. 4, the control unit 80 is a controller, and includes, for example, a microcomputer having a CPU, a ROM, a RAM, an input / output port, and various circuits. The control unit 80 may be configured by hardware such as ASIC or FPGA, for example.

  The control unit 80 includes a model generation unit 81, an accompanying information acquisition unit 82, an attention word information acquisition unit 83, a prediction unit 84, and a provision unit 85.

[7.3.1. Model generation unit 81]
The model generation unit 81 generates the above model. For example, the model generation unit 81 generates a regression formula represented by the above formula (1), and performs a regression analysis on the generated regression formula, thereby obtaining a model for calculating an index related to the content represented by the above formula (2). Generate. Then, the model generation unit 81 causes the model information storage unit 91 to store information on the generated model.

[7.3.2. Accompanying information acquisition unit 82]
The accompanying information acquisition unit 82 acquires accompanying information accompanying the content from the content distribution device 50. For example, the accompanying information acquisition unit 82 includes information such as a use word included in the content, an author name when the content is an electronic book, and a performer name and a director name when the content is video content such as a movie. Can be acquired as a keyword.

  Further, for example, the accompanying information acquisition unit 82 can acquire information such as a selling price and the number of pages when the content is an electronic book, a screening time when the content is video content such as a movie, and the like as the accompanying information. Then, the accompanying information acquisition unit 82 causes the accompanying information storage unit 92 to store the acquired various accompanying information.

[7.3.3. Attention word information acquisition unit 83]
The attention word information acquisition unit 83 acquires attention word information indicating a word of interest on the network from the attention word detection device 60. Then, the attention word information acquisition unit 83 causes the attention word information storage unit 93 to store the acquired attention word information.

[7.3.4. Prediction unit 84]
The prediction unit 84 predicts an index related to the content based on the accompanying information and the attention word information. For example, the prediction unit 84 predicts information indicating future popularity regarding the content as an index regarding the content. Specifically, the prediction unit 84 reads accompanying information from the accompanying information storage unit 92 and reads attention word information from the attention word information storage unit 93. Further, the prediction unit 84 calculates the frequency at which the keyword information included in the accompanying information is included in the attention word information, that is, the keyword frequency.

Then, the prediction unit 84 reads the model information from the model information storage unit 91, and includes “x ₁ ” to “x _n ” of the read model (see Expression (2)) in the keyword frequency and the accompanying information. By inputting information such as a selling price, an index related to the electronic book can be calculated.

[7.3.5. Providing unit 85]
The providing unit 85 provides information indicating an index related to the content predicted (calculated) by the prediction unit 84 to the information user terminal device 40. Thereby, although not shown in the figure, index information about the content is displayed on the display unit of the information user terminal device 40, and the information user can check and use the index.

[8. Processing flow of information processing apparatus 70]
Next, an information processing procedure in the information processing apparatus 70 will be described. FIG. 8 is a flowchart showing the flow of information processing in the information processing apparatus 70.

  As illustrated in FIG. 8, the control unit 80 of the information processing device 70 generates a model (step S10). Next, the control unit 80 acquires the accompanying information of the content (Step S11), and acquires attention word information (Step S12).

  In the example illustrated in FIG. 8, the control unit 80 acquires the attention word information after acquiring the accompanying information of the content. However, the control unit 80 is not limited thereto, and acquires the attention word information and the accompanying information in this order. Alternatively, attention word information and accompanying information may be acquired simultaneously.

  Next, the control unit 80 predicts (calculates) an index related to the content based on the generated model, attention word information, and accompanying information (step S13). And the control part 80 provides the information user's terminal device 40 with the information of the parameter | index regarding the estimated content (step S14).

(Second Embodiment)
[9. Information Processing Device 70 According to Second Embodiment]
Next, a second embodiment will be described. When using a content, a user may have different behavior for content when the content is interesting or interested and behavior when the content is not interesting or not interested.

  For example, when the content is video content such as a movie, the content action is an operation of rewinding or fast-forwarding the video content, but is not limited thereto.

  That is, for example, when an operation of rewinding the video content is performed, it can be estimated that the user feels that the video content is interesting and wants to view it again. Therefore, it can be said that such video content is highly likely to be hit in the future.

  On the other hand, for example, when an operation for fast-forwarding video content is performed, it can be estimated that the user feels the video content is not interesting and wants to skip the video scene. Therefore, it can be said that such video content is unlikely to be hit in the future.

  Therefore, in the second embodiment, an index related to content indicating the possibility that the content will be hit in the future is predicted using information on the action history of the user's content. Thereby, in 2nd Embodiment, the parameter | index regarding a content can be estimated more accurately. The description that the user feels interesting in the above-described rewinding operation is an example and is not limited.

  Further, in the second embodiment, by using user attribute information, it is possible to predict an index related to content with higher accuracy. That is, age information is one of user attribute information. Therefore, for example, when the content of young users with a high percentage of young people tends to lead to future hits, the content can be obtained by using information on the user's age (an example of user attribute information). It is possible to predict the index regarding the accuracy with higher accuracy. Note that the tendency to lead to hits described above is an example and is not limited.

  FIG. 9 is a diagram illustrating a configuration example of the information processing apparatus 70 according to the second embodiment. In the following, the same components as those in the first embodiment described above are denoted by the same reference numerals and description thereof is omitted.

  As illustrated in FIG. 9, the control unit 80 of the information processing apparatus 70 according to the second embodiment further includes a history information acquisition unit 86 and a user attribute information acquisition unit 87. The storage unit 90 further includes an action history information storage unit 94 and a user attribute information storage unit 95.

[9.1.1. Action history information storage unit 94]
The action history information storage unit 94 stores action history information for the user's content. Here, a user's action history changes with kinds of contents. Therefore, FIG. 10A shows an example of the action history information storage unit 94 when the content is an electronic book, and FIG. 10B shows an example of the action history information storage unit 94 when the content is video content.

  First, FIG. 10A will be described. For example, the action history information storage unit 94 includes items such as “action history information ID”, “information type”, and “information content”. “Behavior history information ID” indicates identification information for identifying the behavior history information. “Information type” indicates the type of information included in the action history information. “Information content” indicates the content of information included in the action history information.

  In the example illustrated in FIG. 10A, the action history information ID “C1-01” indicates that the information type is “number of markers” and the information content is “20 places”. Note that, in the case of an electronic book, the user can perform a marker operation for attaching a marker to a specific position in the book, and here, it is shown that there are 20 markers.

  For example, as the number of markers increases, it can be estimated that the user has performed more marker operations because he / she feels that the electronic book is more interesting, and thus it can be said that there is a higher possibility that the electronic book will be hit in the future. In addition, in this specification, description of the action presumed that the user feels interesting or not interesting is merely an example and is not limited.

  The action history information ID “C2-01” indicates that the information type is “marker position” and the information content is “page 15, line 3, page 18, line 6,...”. For example, when the marker positions are gathered in the first half of the book, the user can estimate that the first half of the electronic book is interesting and the second half is not interesting, so that the electronic book It can be said that the possibility of a hit is low.

  The action history information ID “C3-01” indicates that the information type is “marker word” and the information content is “word AA, word FF,...”. For example, when the word AA with the marker is included in the above-described attention word information 61, the word that the user feels interesting matches the attention word that has been noticed on the network. It can be said that there is a high possibility of a hit in the future.

  The action history information ID “C4-01” indicates that the information type is “bookmark position” and the information content is “120th page”. In the case of an electronic book, the user can perform an operation of placing a bookmark at a specific position in the book, and here, the position where the bookmark is placed is the 120th page.

  The action history information ID “C5-01” indicates that the information type is “reading stop position” (that is, the position where the user stopped reading halfway), and the information content is “150th page”. Yes. For example, when the “bookmark position” and “reading stop position” described above are at the same position for a predetermined period, it can be estimated that the user stopped reading because he / she felt uninteresting on the way, so It can be said that there is a low possibility of a hit.

  The action history information ID “C6-01” indicates that the information type is “reading speed” and the information content is “1.5 pages / minute”. For example, it can be estimated that the faster the reading speed is, the more the user feels that the electronic book is being read, and that the electronic book is likely to hit in the future.

  The action history information ID “C7-01” indicates that the information type is “reading frequency” and the information content is “twice / day”. For example, it can be estimated that the more frequently the reading is performed, the more the user feels that the electronic book is more interesting, and thus it is more likely that the electronic book will be hit in the future.

  The action history information ID “C8-01” indicates that the information type is “one reading amount” and the information content is “20 pages”. For example, it can be estimated that the greater the amount of reading at one time, the more the user feels that the electronic book is being read, and that the electronic book is likely to hit in the future.

  In this way, by analyzing the user's action history on the electronic book, it is possible to predict the possibility that the electronic book will be hit in the future, in other words, an index related to the electronic book.

  Next, with reference to FIG. 10B, action history information when the content is video content will be described.

  In the example shown in FIG. 10B, the action history information ID “D1-01” has the information type “stop position” and the information content “40 minutes, 52 minutes,... , 52 minutes, ...). If the user performs an operation to stop the video when he / she finds it interesting, for example, when the stop position is gathered in the first half of the video content, the user feels the first half of the video content interesting, It can be estimated that the latter half is not interesting, so it is unlikely that the video content will be hit in the future.

  The action history information ID “D2-01” indicates that the information type is “stop frequency” and the information content is “5 times”. For example, it can be estimated that the more the stop frequency is, the more the user feels that the video content is more interesting and the more stop operations are performed, and thus the higher the possibility that the video content will be hit in the future.

  The action history information ID “D3-01” indicates that the information type is “fast forward position” and the information content is “20 minutes”. For example, it can be presumed that the user felt that the video scene in the vicinity of 20 minutes from the start of the video was not interesting and performed a fast-forward operation, and thus the video content is unlikely to hit in the future.

  The action history information ID “D4-01” indicates that the information type is “rewind position” and the information content is “35 minutes, 60 minutes,...”. For example, it can be presumed that the user performed a rewinding operation by feeling that the video scenes in the vicinity of 35 minutes and 60 minutes from the start of the video were interesting, and it can be said that the video content is likely to hit in the future.

  The action history information ID “D5-01” indicates that the information type is “viewing frequency” and the information content is “twice / day”. For example, it can be estimated that the more the viewing frequency is, the more the user feels that the video content is more interesting, and the higher the possibility that the video content will be hit in the future.

  The action history information ID “D6-01” indicates that the information type is “one viewing time” and the information content is “30 minutes”. For example, it can be estimated that the longer the viewing time for one time, the more the user feels that the video content is interesting and continues to watch, and thus the possibility that the video content will be hit in the future is high.

  The action history information ID “D7-01” indicates that the information type is “viewing screen” and the information content is “full screen display”. Note that the display size of the video content on the user terminal device 10 (see FIG. 3) can be switched between “standard screen display” and “full screen display” larger than the standard screen display. Indicates that the display is selected. Therefore, for example, it can be estimated that the larger the display size is, the more the user feels that the video content is more interesting, and thus it is more likely that the video content will be hit in the future.

  The action history information ID “D8-01” indicates that the information type is “volume” and the information content is “large”. For example, it can be estimated that the higher the volume is, the more the user feels that the video content is being viewed and the viewer is watching the video content.

  The action history information ID “D9-01” indicates that the information type is “time to return” and the information content is “60 minutes”. In the user terminal device 10 that displays video content, for example, the video is stopped by the user's stop operation, and then the stopped video is returned (restarted) by the user's return operation. Therefore, for example, it can be estimated that the shorter the time until return is, the more the user feels that the video content is more interesting, and therefore the possibility that the video content will be hit in the future is high.

  As described above, by analyzing the user's behavior history with respect to the video content, it is possible to predict the possibility that the video content will be hit in the future, in other words, an index related to the video content.

[9.1.2. User attribute information storage unit 95]
Returning to the description of FIG. 9, the user attribute information storage unit 95 stores attribute information of the user who uses the content. FIG. 11 is a diagram illustrating an example of the user attribute information storage unit 95. For example, the user attribute information storage unit 95 includes items such as “user ID”, “age”, “sex”, and “residence”.

  “User ID” indicates identification information for identifying a user. “Age” indicates information on the user's age, “Gender” indicates information on the user's gender, and “Residence” indicates information on the user's residence.

  In the example illustrated in FIG. 11, the user information ID “U001” indicates that the age is “21”, the gender is “female”, and the residence is “Tokyo”. The user information ID “U002” indicates that the age is “62”, the gender is “male”, and the residence is “Osaka Prefecture”.

  Here, for example, if it is assumed that the content tends to lead to a future hit when the percentage of young women who live in Tokyo tends to be a future hit, the user attribute information such as the user information ID “U001” It is possible to predict the possibility that the content will be hit in the future, in other words, an index related to the content.

[9.2.1. Model Generation Unit 81 According to Second Embodiment]
Returning to the description of FIG. 9, the model generation unit 81 according to the second embodiment further uses the action history information and user attribute information related to the content distributed in the past with respect to the model of the first embodiment to The regression equation shown in (1) is generated. And the model production | generation part 81 produces | generates the model for calculating the parameter | index regarding the content shown by said Formula (2) by carrying out regression analysis of the produced | generated regression formula. That is, in the second embodiment, action history information and user attribute information may be used as model elements.

[9.2.2. History information acquisition unit 86]
The history information acquisition unit 86 acquires action history information for the user's content from the content distribution device 50. The history information acquisition unit 86 may acquire action history information from the user terminal device 10. Then, the history information acquisition unit 86 stores the acquired behavior history information in the behavior history information storage unit 94.

[9.2.3. User attribute information acquisition unit 87]
The user attribute information acquisition unit 87 acquires user attribute information from the content distribution device 50. Note that the user attribute information acquisition unit 87 may acquire user attribute information from the user terminal device 10. Then, the user attribute information acquisition unit 87 causes the user attribute information storage unit 95 to store the acquired user attribute information.

[9.2.4. Prediction unit 84]
The prediction unit 84 predicts an index related to content based on the accompanying information, attention word information, action history information, and user attribute information. For example, the prediction unit 84 reads the accompanying information from the accompanying information storage unit 92 and the attention word information from the attention word information storage unit 93. The prediction unit 84 reads the behavior history information from the behavior history information storage unit 94 and reads the user attribute information from the user attribute information storage unit 95.

Then, the prediction unit 84 reads out model information from the model information storage unit 91, and “x ₁ ” to “x _n ” of the read model (see Expression (2)) includes action history information and user attribute information. By inputting such information, it is possible to calculate an index related to the content to be predicted.

  As described above, the prediction unit 84 according to the second embodiment can calculate the index related to the content more accurately by using the action history information and the user attribute information.

[10. Processing Flow of Information Processing Device 70 According to Second Embodiment]
Next, an information processing procedure in the information processing apparatus 70 according to the second embodiment will be described. FIG. 12 is a flowchart showing a flow of information processing in the information processing apparatus 70 according to the second embodiment.

  As illustrated in FIG. 12, the control unit 80 of the information processing device 70 acquires the action history information for the user's content after performing the above-described processing from step S10 to S12 (step S12a). Next, the control unit 80 acquires user attribute information of the user who uses the content (step S12b). In addition, the acquisition order of each information shown in FIG. 12 is an illustration to the last, and is not limited.

  Next, the control unit 80 predicts (calculates) an index related to the content based on the generated model, attention word information and accompanying information, action history information, and user attribute information (step S13). Then, the control unit 80 proceeds to step S14 and provides the information user terminal device 40 with index information related to the predicted content.

  In the above description, the index related to the content is predicted using the action history information and the user attribute information. However, the present invention is not limited to this, and any one of the information may be used.

[11. effect〕
The information processing apparatus 70 includes an accompanying information acquisition unit 82, an attention word information acquisition unit 83, and a prediction unit 84. The accompanying information acquisition unit 82 acquires accompanying information accompanying the content. The attention word information acquisition unit 83 acquires attention word information indicating a word to be noticed on the network. The prediction unit 84 predicts an index related to the content based on the accompanying information acquired by the accompanying information acquisition unit 82 and the attention word information acquired by the attention word information acquisition unit 83.

  Thereby, the index regarding the content can be accurately calculated by using the accompanying information of the content and, for example, the attention word information that the user is interested in at the present time.

  Further, the accompanying information acquisition unit 82 acquires keyword information included in the content as accompanying information, and the prediction unit 84 calculates an index related to the content based on the frequency (keyword frequency) that the keyword information is included in the attention word information. Predict. Thereby, the index regarding the content can be calculated more accurately.

  In addition, the prediction unit 84 predicts information indicating future popularity regarding the content as an index regarding the content. As a result, for example, it is possible to predict (calculate) various pieces of information such as the number of sales of content used for marketing such as a content sales strategy as an index related to the content.

  The information processing apparatus 70 further includes a history information acquisition unit 86 that acquires action history information indicating an action history for the user's content. The prediction unit 84 predicts an index related to content based on the action history information acquired by the history information acquisition unit 86. Thereby, the index regarding the content can be predicted with higher accuracy.

  The content includes an electronic book, and the history information acquisition unit 86 acquires an action history of the user with respect to the electronic book as action history information. Thereby, even if a content is an electronic book, the parameter | index regarding the electronic book which is a content can be estimated more accurately.

  The content includes video content, and the history information acquisition unit 86 acquires the action history of the user with respect to the video content as action history information. As a result, even if the content is a video content such as a movie name, an index related to the video content as the content can be predicted more accurately.

  The information processing apparatus 70 further includes a user attribute information acquisition unit 87 that acquires user attribute information of a user who uses the content. The prediction unit 84 predicts an index related to content based on the user attribute information acquired by the user attribute information acquisition unit 87. Thereby, the index regarding the content can be predicted with higher accuracy.

[12. Hardware configuration)
The information processing apparatus 70 in the above-described embodiment is realized when the computer 100 having a configuration as illustrated in FIG. 13 executes a program, for example.

  FIG. 13 is a diagram illustrating an example of a hardware configuration of a computer that executes a program. A computer 100 includes a central processing unit (CPU) 101, a random access memory (RAM) 102, a read only memory (ROM) 103, a hard disk drive (HDD) 104, a communication interface (I / F) 105, an input / output interface (I). / F) 106 and a media interface (I / F) 107.

  The CPU 101 operates based on a program stored in the ROM 103 or the HDD 104 and controls each unit. The ROM 103 stores a boot program executed by the CPU 101 when the computer 100 is started up, a program depending on the hardware of the computer 100, and the like.

  The HDD 104 stores data used by programs executed by the CPU 101. The communication interface 105 corresponds to the communication unit 71, receives data from other devices via the network N, sends the data to the CPU 101, and transmits data generated by the CPU 101 to other devices via the network N.

  The CPU 101 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 106. The CPU 101 acquires data from the input device via the input / output interface 106. Further, the CPU 101 outputs the generated data to the output device via the input / output interface 106.

  The media interface 107 reads a program or data stored in the recording medium 108 and provides it to the CPU 101 via the RAM 102. The CPU 101 loads the program from the recording medium 108 onto the RAM 102 via the media interface 107, and executes the loaded program. The recording medium 108 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  When the computer 100 functions as the information processing apparatus 70, the CPU 101 of the computer 100 executes a program loaded on the RAM 102, thereby causing the model generation unit 81, the accompanying information acquisition unit 82, and the attention information acquisition unit 82 illustrated in FIGS. The functions of the word information acquisition unit 83, the prediction unit 84, the provision unit 85, the history information acquisition unit 86, and the user attribute information acquisition unit 87 are realized.

  The CPU 101 of the computer 100 reads these programs from the recording medium 108 and executes them, but as another example, these programs may be acquired from other devices via the network N.

  As described above, some of the first and second embodiments of the present application have been described in detail with reference to the drawings. However, these are exemplifications and are based on the knowledge of those skilled in the art including the aspects described in the disclosure line of the invention. The present invention can be implemented in other forms with various modifications and improvements.

[13. Others]
Of the processes described in the first and second embodiments, all or a part of the processes described as being automatically performed can be performed manually, or can be performed manually. All or a part of the processing described as “1” can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the first and second embodiments described above can be appropriately combined within a range in which processing contents are not contradictory.

  Moreover, the above-mentioned “section (module, unit)” can be read as “means”, “circuit”, and the like. For example, the accompanying information acquisition unit 82 can be read as accompanying information acquisition means or an accompanying information acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Information processing system 70 Information processing apparatus 82 Accompanying information acquisition part 83 Attention word information acquisition part 84 Prediction part 86 History information acquisition part 87 User attribute information acquisition part

Claims (9)

An accompanying information acquisition unit for acquiring accompanying information accompanying the content;
An attention word information acquisition unit for acquiring attention word information indicating a word of interest on the network;
A prediction unit that predicts an index related to the content based on the accompanying information acquired by the accompanying information acquisition unit and the attention word information acquired by the attention word information acquisition unit. Processing equipment. The accompanying information acquisition unit
Obtaining keyword information included in the content as the accompanying information;
The prediction unit
The information processing apparatus according to claim 1, wherein an index related to the content is predicted based on a frequency with which the keyword information is included in the attention word information. The prediction unit
The information processing apparatus according to claim 1, wherein information indicating future popularity regarding the content is predicted as an index regarding the content. A history information acquisition unit that acquires behavior history information indicating a behavior history of the user with respect to the content;
The prediction unit
The information processing apparatus according to claim 1, wherein an index related to the content is predicted based on the action history information acquired by the history information acquisition unit. The content includes an electronic book,
The history information acquisition unit
The information processing apparatus according to claim 4, wherein an action history of the user with respect to the electronic book is acquired as the action history information. The content includes video content,
The history information acquisition unit
The information processing apparatus according to claim 4, wherein an action history of the user with respect to the video content is acquired as the action history information. A user attribute information acquisition unit that acquires user attribute information of a user who uses the content;
The prediction unit
The information processing apparatus according to claim 1, wherein an index related to the content is predicted based on the user attribute information acquired by the user attribute information acquisition unit. An information processing method executed by a computer,
An accompanying information acquisition step of acquiring accompanying information accompanying the content;
Attention word information acquisition step of acquiring attention word information indicating a word to be noticed on the network;
A prediction step of predicting an index related to the content based on the accompanying information acquired by the accompanying information acquisition step and the attention word information acquired by the attention word information acquisition step. Processing method. Accompanying information acquisition procedure for acquiring accompanying information accompanying content;
Attention word information acquisition procedure for acquiring attention word information indicating a word of interest on the network;
A computer is caused to execute a prediction procedure for predicting an index related to the content based on the accompanying information acquired by the accompanying information acquisition procedure and the attention word information acquired by the attention word information acquisition procedure. Information processing program.

Images