Program, information processing method and information processing device

Abstract

To provide technique capable of evaluating an influence of a content more accurately and generally.SOLUTION: A first keyword extraction unit 61 extracts first keywords included in first content information on the basis of first keyword information stored in a first keyword DB 200. On the basis of second keyword information stored in a second keyword DB 300, the first keyboard extraction unit extracts a second keyword corresponding to each of the first keywords extracted by the first keyword extraction unit 61. A second keyword extraction unit 64 extracts the first and second keywords included in second content information. An influence calculation unit 65 calculates an influence of the second keyword in the second content on the basis of a predetermined rule. An influence presentation unit 66 transmits result information related to the influence of the second keyword calculated by the influence calculation unit 65 to a service providing terminal 4.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to a program, an information processing method, and an information processing device. [Background technology]

[0002] In recent years, it has become known that television and other media content has a great influence, and is used, for example, to provide advertisements and the like. In this regard, for example, a system has been proposed that predicts which information actually led to a TV program leading to the purchase of a product by statistical processing of POS data and metadata (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2022-2066 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques including the technique described in the above-mentioned Patent Document 1 simply analyze information contained in one type of content and predict the purchasing effect of a TV program, and the prediction accuracy is insufficient.

[0005] The present disclosure has been made in light of the above circumstances, and aims to provide a technology that can evaluate the influence of content more accurately and generally.

[0006] In order to achieve the above object, a program according to one embodiment of the present disclosure comprises: Computer, A first information acquisition means for acquiring information related to a first content; A first term extraction means for extracting a predetermined word included in the first content as a first keyword; a term determination means for determining a word related to the first keyword as a second keyword; A second information acquisition means for acquiring information related to the second content; a second term extraction means for extracting the first keyword and the second keyword included in the second content; a first influence calculation means for calculating an influence of the first keyword or the second keyword in the second content; It is a program that functions as a

[0007] An information processing method and an information processing device according to an embodiment of the present disclosure are also provided as an information processing method or an information processing device corresponding to a program according to an embodiment of the present disclosure. Effect of the Invention

[0008] According to the present disclosure, it is possible to provide a technique capable of evaluating the influence of content more accurately and generally. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server constituting an information processing system according to an embodiment of the present disclosure. [Diagram 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a server and the like that configures an information processing system according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a conceptual diagram illustrating an example of information stored in a server constituting an information processing system according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 is an image diagram showing an example of information stored in a server constituting an information processing system according to an embodiment of the present disclosure, and is a diagram showing an example different from the example of FIG. 4. [Figure 6]FIG. 6 is an image diagram showing an example of information stored in a server constituting an information processing system according to an embodiment of the present disclosure, showing an example different from the examples of FIGS. 4 and 5. [Figure 7] 1 is an image diagram for explaining an example of a method for calculating influence in an information processing system according to an embodiment of the present disclosure. FIG. [Figure 8] 11 is a flowchart illustrating an example of the flow of an influence calculation process executed by a server constituting the information processing system according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] [Embodiment] <System configuration> FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present disclosure (hereinafter, referred to as "this system").

[0011] As shown in Fig. 1, the system includes a server 1, a first content device 2, a second content device 3, and a service providing terminal 4. The server 1, the first content device 2, the second content device 3, and the service providing terminal 4 are connected via a predetermined network N such as the Internet. However, the network N is not an essential component, and for example, NFC (Near Field Communication), Bluetooth (registered trademark), LAN (Local Area Network), etc. may be used. Note that hereinafter, when simply referring to "images", any image such as "moving images", "still images", and "stereoscopic images" is included.

[0012] The server 1 is an information processing device managed by an administrator of the system, etc. The server 1 is configured, for example, with a general-purpose PC (Personal Computer), etc. The server 1 executes various processes related to the influence calculation process described later.

[0013] The first content device 2 is an information processing device managed by an administrator of the first content. The first content device 2 is, for example, a general-purpose PC (Personal Computer). The first content device 2 manages various information related to the first content and transmits necessary information to the server 1 as appropriate. Here, the first content is, for example, content transmitted and received by television broadcasting (so-called television program, hereinafter referred to as "television program"). Television programs broadly include program content and commercials broadcasted by terrestrial broadcasting, satellite broadcasting, data broadcasting, cable television, IP broadcasting, Internet broadcasting, in-car broadcasting, in-flight broadcasting, etc. The first content also includes media such as radio, newspapers, and magazines, as well as content within the media, games, VOD, movies, outdoor advertisements, etc.

[0014] The second content device 3 is an information processing device managed by an administrator of the second content. The second content device 3 is, for example, a general-purpose PC (Personal Computer). The second content device 3 manages various information related to the second content and transmits necessary information to the server 1 as appropriate. Here, the second content is, for example, content provided by various network services such as YouTube (registered trademark), Niconico Video (registered trademark), TikTok (registered trademark), etc. (hereinafter, referred to as "video content").

[0015] The service providing terminal 4 is an information processing terminal used by a user who wishes to receive a service related to this system. The service providing terminal 4 is, for example, a general-purpose PC, a smartphone, a tablet, etc. The service providing terminal 4 receives various information transmitted from the server 1.

[0016] <Hardware configuration> FIG. 2 is a diagram showing an example of a hardware configuration of the server 1 constituting the present system.

[0017] As shown in FIG. 2, the server 1 includes a control unit 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a memory unit 18, a communication unit 19, and a drive 20.

[0018] The control unit 11 is configured with a microcomputer including a CPU, a GPU, a semiconductor memory, etc. The control unit 11 executes various processes according to a program recorded in a ROM 12 or a program loaded from a storage unit 18 to a RAM 13. The RAM 13 also stores information necessary for the control unit 11 to execute various processes as appropriate.

[0019] The control unit 11, ROM 12, and RAM 13 are connected to one another via a bus 14. An input / output interface 15 is also connected to this bus 14. An output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.

[0020] The output unit 16 is configured with various displays, speakers, etc. The output unit 16 outputs various images, sounds, etc.

[0021] The input unit 17 is configured with, for example, a keyboard, a mouse, etc. The input unit 17 accepts input of various information.

[0022] The storage unit 18 is configured with a hard disk drive (HDD), a solid state drive (SSD), etc., and stores various information. The storage unit 18 stores various programs and the like related to the provision of the present service.

[0023] The communication unit 19 controls communications between the device and other hardware devices via a network N including the Internet.

[0024] The drive 20 is provided as necessary. Removable media 31, which may be a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is appropriately mounted in the drive 20. Programs for executing various processes are stored in the removable media 31. The programs read from the removable media 31 by the drive 20 are installed in the storage unit 18 as necessary. Further, the removable medium 31 can store various information stored in the storage unit 18 in the same manner as the storage unit 18 .

[0025] The hardware configurations of the first content device 2, the second content device 3 and the service providing terminal 4 are basically the same as the hardware configuration of the server 1, and therefore will not be described here. The cooperation of such various hardware and software enables the execution of various processes, which will be described later.

[0026] FIG. 3 is a diagram illustrating an example of a functional configuration of a server constituting an information processing system according to an embodiment of the present disclosure. As shown in FIG. 3, the control unit 11 of the server 1 executes various programs and the like to cause a first content information acquisition unit 60, a first keyword extraction unit 61, a second keyword extraction unit 62, a second content information acquisition unit 63, a related word group extraction unit 64, an influence calculation unit 65, and an influence presentation unit 66 to function. In addition, a primary keyword DB 200, a secondary keyword DB 300, and a correlation coefficient DB 400 are stored in one area of ​​the storage unit 18. In the primary keyword DB 200, for example, information on words to be noted in the primary content (hereinafter referred to as "primary keywords") is stored in the form of a list, etc. The list indicating the primary keywords (hereinafter referred to as "primary keyword information") may be created independently by an administrator of the system, etc., or may be obtained via the Internet, etc. In the secondary keyword DB 300, for example, information on words (hereinafter referred to as "secondary keywords") that are highly related to a predetermined word is stored in the form of a list, etc. The list indicating the secondary keywords (hereinafter referred to as "secondary keyword information") may be created independently by an administrator of the system, etc., or may be obtained via the Internet, etc. In the correlation coefficient DB 400, for example, information on the correlation coefficients assigned to the primary and secondary keywords of interest is stored in the form of a list, etc. The correlation coefficients may be created by an administrator of the system, etc., based on the degree of relevance for each video keyword, or may be automatically calculated using various large-scale language models, etc.

[0027] The first content information acquisition unit 60 acquires information related to the first content. Specifically, the first content information acquisition section 60 acquires, via the communication section 19, information relating to the first content transmitted from the first content device 2 (hereinafter referred to as “first content information”). Here, the first content information includes, for example, moving images (image information, audio information) of any television program, commercial, or the like (first content).

[0028] The primary keyword extraction unit 61 extracts a predetermined word included in the primary content as a primary keyword. Specifically, the primary keyword extraction unit 61 extracts primary keywords included in the primary content information based on the primary keyword information stored in the primary keyword DB 200.

[0029] The secondary keyword extraction unit 62 determines words related to the primary keywords as secondary keywords. Specifically, the secondary keyword extraction unit 62 extracts secondary keywords corresponding to each of the primary keywords extracted by the primary keyword extraction unit 61 based on the secondary keyword information stored in the secondary keyword DB 300 .

[0030] The second content information acquisition unit 63 acquires information relating to the second content. Specifically, the second content information acquisition unit 63 acquires, via the communication unit 19, information relating to the second content transmitted from the second content device 3 (hereinafter referred to as “second content information”). Here, the second content information includes, for example, video images (image information, audio information, tag information, etc.) of video content provided by various network services.

[0031] The related word group extraction unit 64 extracts the first keyword and the second keyword contained in the second content. Specifically, the related word group extraction unit 64 extracts the first keyword extracted by the first keyword extraction unit 61 and the second keyword determined by the second keyword extraction unit 62 (hereinafter, the first keyword and the second keyword are collectively referred to as the "related word group").

[0032] The influence calculation unit 65 calculates the influence of the first keyword or the second keyword in the second content. Specifically, the influence calculation unit 65 calculates the influence of the related word group in the second content based on a predetermined rule. Note that an example of a method for calculating the influence by the influence calculation unit 65 will be described with reference to FIG. 6 and the like.

[0033] The influence presenting unit 66 presents the calculated influence of the first keyword or the second keyword. Specifically, the influence presentation unit 66 transmits information on the influence of the related word group calculated by the influence calculation unit 65 (hereinafter referred to as “result information”) to the service providing terminal 4. The service providing terminal 4 presents the obtained result information to the user.

[0034] FIG. 4 is a conceptual diagram illustrating an example of information stored in a server constituting an information processing system according to an embodiment of the present disclosure.

[0035] In the example of Fig. 4, the items "Program Name," "First Keyword," and "Second Keyword" are displayed. The program name is an example of a first content. In the example of Fig. 4, the words "cherry blossom viewing" and "sake" are extracted as first keywords from "TV Program Aa," and the words "building blocks" and "travel" are extracted as first keywords from "TV Program Bb." Then, the second keywords are extracted for each of the first keywords extracted in this way. Specifically, in the example of FIG. 4, the words "beer", "sake", and "banquet" are extracted as second keywords for the extracted first keyword "hanami". Similarly, in the example of FIG. 4, the words "brewery", "Niigata", "tasting", "sake", "kids", "3 years old", "playing at home", "gourmet", "hot spring", and "sake" are extracted as second keywords. In the example of FIG. 4, the combination of these first and second keywords is, for example, a related word group in this embodiment.

[0036] FIG. 5 is an image diagram showing an example of information stored in a server constituting an information processing system according to an embodiment of the present disclosure, and is a diagram showing an example different from the example of FIG.

[0037] In the example of FIG. 5, the following items are displayed: "Video No.", "Video ID," "Number of Plays," and "Words." The "video No." is, for example, a serial number given to a video content that is an example of the second content. The "video ID" is, for example, an ID given to each video content. The "number of plays" refers to the number of plays of each video content on the network service. In this embodiment, the number of plays is the most important factor for evaluating the influence of the second content. The "words" are words (hereinafter referred to as "video keywords") that are highly relevant to each of the second contents. In this embodiment, the video keywords are tags given to each of the second contents, and the influence of each video keyword is evaluated based on the number of views of each of the second contents. Specifically, in the example of Fig. 5, "Video Aaa" has been played 2000 times, and has been tagged with "Cherry Blossom Viewing", "Ueno Park", "Party", and "Beer". Similarly, the video content "Video Bbb" has been played 2000 times, and has been tagged with "Travel", "Europe", "Gourmet", and "Alcohol". In this system, information on the number of times each secondary content is played, as well as information on related video keywords, is compiled in a table and stored in a DB (not shown).

[0038] FIG. 6 is an image diagram showing an example of information stored in a server constituting an information processing system according to an embodiment of the present disclosure, and is a diagram showing an example different from the examples of FIG. 4 and FIG.

[0039] In the example of Figure 6, the following items are displayed: "Word No.", "Word Name," "Number of Views (Total)," "Likes (Total)," and "Word Influence." "Word No." is a serial number assigned to each video keyword. "Word name" refers to the name of the video keyword extracted from each video content. In the example of Figure 6, overlapping video keywords are displayed together. "Number of views (total)" refers to the total number of views of video content related to each video keyword. "Likes (total)" refers to the total number of likes set by each network service that provides each video content. "Word influence" refers to the influence of each video keyword in the second content. In the example of Figure 6, the value of "Number of views (total)" is taken as the influence of each video keyword. In the example of FIG. 6, the row of word No. 1 shows the word name "Hanami", the number of views (total) "2000", the likes (total) "150", and the word influence "2000". As shown in FIG. 5, the number of views of "Video Aaa" related to Hanami is 2000, and the influence of the word Hanami is 2000 is displayed together with other accompanying information. In contrast, for example, the row of word No. 4 shows the word name "Beer", the number of views (total) "3000", the likes (total) "200", and the word influence "3000". As shown in FIG. 5, the total number of views of "Video Aaa" and "Video Ddd" related to beer is 3000, so the influence of "Beer" is also 3000. In this way, in the example of FIG. 6, for video keywords related to multiple videos, the influence of each word itself can be estimated by adding up the number of views of each video content.

[0040] FIG. 7 is an image diagram for explaining an example of a method for calculating influence in an information processing system according to an embodiment of the present disclosure.

[0041] In the example of Figure 7, the video keywords for which influence is to be calculated and the correlation coefficient value for each video keyword are displayed in a table. Looking at Figure 7, as an example, in the row for "flower viewing," the correlation coefficient for banquet is displayed as "0.3," the correlation coefficient for beer is displayed as "0.1," the correlation coefficient for alcohol is displayed as "0.4," and the correlation coefficient for sake is displayed as "0.2." In the example of Figure 7, the influence of each word calculated in Figure 6 is multiplied by the correlation coefficient, and the calculated values ​​are added, so that the influence of the keyword displayed on the left side of Figure 7 can be calculated. In the example of cherry blossom viewing in Figure 7, the influence of cherry blossom viewing = influence of banquet (2000) x 0.3 + influence of beer (3000) x 0.1 + influence of alcohol (3000) x 0.4 + influence of sake (1000) x 0.2 = 2300. In this way, in the example of Figure 7, rather than simply calculating the influence of a word, the final influence of the keyword can be calculated by multiplying each related word by a coefficient called a correlation coefficient and calculating the total value. This allows the system to calculate a more comprehensive influence based on multiple contents rather than calculating the influence of a keyword in a single content. In the example of Fig. 7, the correlation coefficient of "Hanami" in the row of "Hanami" is displayed as "Not Applicable." This system may use either the influence of "Hanami" calculated by the method shown in Fig. 7 (e.g., 2300) or the influence of the word "Hanami" itself (e.g., 2000, see Fig. 6) without using the method shown in Fig. 7 as the influence of "Hanami."

[0042] FIG. 8 is a flowchart showing an example of the flow of influence calculation processing executed by a server configuring an information processing system according to an embodiment of the present disclosure.

[0043] In step S1, the first content information acquisition unit 60 of the server 1 acquires, via the communication unit 19, the first content information relating to the first content transmitted from the first content device 2.

[0044] In step S2, the primary keyword extraction unit 61 of the server 1 extracts primary keywords included in the primary content information based on the primary keyword information stored in the primary keyword DB 200.

[0045] In step S3, the secondary keyword extraction unit 62 of the server 1 extracts secondary keywords corresponding to each of the primary keywords extracted by the primary keyword extraction unit 61, based on the secondary keyword information stored in the secondary keyword DB 300.

[0046] In step S4, the second content information acquisition unit 63 of the server 1 acquires, via the communication unit 19, the second content information relating to the second content transmitted from the second content device 3.

[0047] In step S5, the related word group extraction unit 64 of the server 1 extracts the first keyword and the second keyword included in the second content information, that is, a related word group.

[0048] In step S6, the influence calculation unit 65 of the server 1 calculates the influence of the related word group in the second content based on a predetermined rule.

[0049] In step S7, the influence presentation unit 66 of the server 1 transmits result information on the influence of the related word group calculated by the influence calculation unit 65 to the service providing terminal 4. This ends the influence calculation process.

[0050] Although one embodiment of the present disclosure has been described above, the present disclosure is not limited to the above-described embodiment, and modifications and improvements within the scope that can achieve the object of the present disclosure are included in the present disclosure.

[0051] [Other embodiments] Here, we briefly supplement the background of this disclosure. As a method for estimating the influence of a television program, etc., the measurement of so-called viewer ratings and the measurement of the purchasing effect of advertisements are known, including the technology described in the above-mentioned Patent Document 1. However, these methods alone are not sufficient for estimating the influence of content. In particular, in recent years, the influence of various video contents has expanded, and there are cases where it is correlated with the influence of television programs. Therefore, in recent years, it is required to estimate the influence of each content, not limited to television programs, and it is desirable to consider the interactions that each content may have with each other. Furthermore, indices of video content, such as the number of plays and likes (high ratings), are suitable for expressing the degree of influence, since they are numerical values ​​that directly reflect the results of operations based on each user's motivation for viewing as the strength of interest. In light of this situation, the system according to the above-mentioned embodiment has been developed. This system measures the influence of various contents, not limited to television programs, and estimates the influence of each piece of content while taking into account the interactions that each piece of content has with others.

[0052] In the above embodiment, an example of the first content is a television program, and an example of the second content is a video content provided by a network service, but this is not limited thereto. For example, an example of the first content in the above embodiment may be a video content provided by a network service, and an example of the second content may be a television program. That is, the present system can adopt any type of content as the first content and the second content. In this case, the first content and the second content may be selected in consideration of the context of the release timing of the content.

[0053] In the above embodiment, the system is described as calculating the influence of the video keyword in the second content only based on the number of times the content is played, but this is not limited thereto. The system may calculate the influence based on a number of criteria including unique evaluation criteria for each network service, such as the number of times the content is played, the play time, recommendations (impressions), retweets, content ratings (likes, high ratings, low ratings, bookmarks, etc.), the number of comments, and changes in various indicators over time, by combining addition or multiplication of each numerical value, or by taking into consideration a predetermined criterion or comprehensively. In addition, the influence may be calculated not only based on an indicator for a single network service, but also by the total number of times the video is played for multiple network services. Furthermore, for example, the influence may be evaluated by comparing the changes in influence over time to determine the relationship between the changes in influence of the first keyword and the second keyword, and the leading or lagging of the influence.

[0054] Also, although not described in the above embodiment, the first content may include not only television programs that can be viewed in real time, but also content such as recordings or reruns of television programs, various catch-up broadcasts, etc.

[0055] In the above embodiment, the second content is described as a moving image, but is not limited thereto. The second content may be, for example, still images, text articles, sentences, audio content, or other content in various network services such as Instagram (registered trademark) and Twitter (registered trademark), or commercial materials in EC sites and SNS. It may also be NFT content, in which case the influence may be calculated based on the value of the NFT.

[0056] In the above-described embodiment, the method by which the system extracts keywords from various contents is merely an example and is not limited thereto. The system may extract keywords from contents by any method, such as tag information attached to various contents, audio analysis, video analysis, text analysis, etc. Furthermore, the system may extract keywords by using, for example, various large-scale language models, etc.

[0057] Also, although not explained in the above embodiment, this system has been used as an example of an application for estimating influence on purchasing, but is not limited to this. A content name or a person or character may be selected as the first keyword, and an alias or nickname may be selected as the second keyword, and the popularity of the content or the possibility of it being a hit, or a person's influence or popularity may be evaluated.

[0058] In the above embodiment, an arbitrary secondary keyword is extracted for a primary keyword, but this is not limited to this. For example, the secondary keyword may be extracted from a secondary content.

[0059] In the above embodiment, the first keyword and the second keyword are determined, and then the table shown in Fig. 7 is referred to, but this is not limited thereto. For example, the system may determine the second keyword by referring to the table shown in Fig. 7 that is prepared in advance.

[0060] In addition, although not described in the above embodiment, the present system may have a function of recommending a target primary keyword when the influence value calculated for the primary keyword is equal to or greater than a predetermined value.

[0061] In addition, although not explained in the above embodiment, the present system may have a function of recommending the target first keyword or second keyword when the influence value calculated for the second keyword is equal to or greater than a predetermined value.

[0062] In addition, although not explained in the above embodiment, the present system may have a function of recommending the target first keyword or second keyword when the value obtained by multiplying the influence calculated for each second keyword by the correlation coefficient is equal to or greater than a predetermined value, or when the value of the correlation coefficient is equal to or greater than a predetermined value.

[0063] In the above embodiment, the system calculates the influence of a keyword in the second content, but is not limited to this. For example, the system may have a function of calculating the influence of a keyword in the first content. In this case, for example, the system may calculate the influence of the keyword in the second content by taking into account the result of the influence calculated for the first content.

[0064] In addition, although not described in the above embodiment, the present system may have a function of changing the calculated influence of the first keyword or the second keyword depending on the degree of usage of the second content (usage situation, number of uses or number of clicks, time of usage, frequency of usage, etc.).

[0065] In the above embodiment, the system is described as multiplying the influence of each word by a correlation coefficient and adding the calculated values ​​to calculate the final influence of the keyword, but this is not limited to this. The calculation method of the influence shown in Fig. 7 is merely an example, and the administrator of the system can adopt any calculation method to calculate the influence of the keyword. The correlation coefficient values ​​of the respective words shown in FIG. 7 are also merely examples and are not limiting.

[0066] Also, although not explained in the above embodiment, the result of the influence of the first keyword or the second keyword calculated by this system, i.e., the result information, is obtained, for example, by a user who operates a retail store or an EC site, and is used for product selection, advertising presentation, etc. Furthermore, the system may have a function of linking the result information used in this manner to the purchase of goods, services, etc., and evaluating the effectiveness of keywords.

[0067] In the above embodiment, the correlation coefficient is defined between the first keyword and the second keyword, but this is not limited to this. For example, the system may define a correlation coefficient between the second keywords.

[0068] Although not described in the above embodiment, the method of defining the correlation coefficient in the present system is arbitrary. For example, the present system may use a value arbitrarily determined by an administrator of the present system as the correlation coefficient, or may determine the correlation coefficient according to a predetermined criterion.

[0069] Although not described in the above embodiment, the correlation coefficient in this system may be set as a normalized value or may be set as a non-normalized value. In addition, when a low-rated index is used as the influence degree of the second keyword, or when the keyword itself is a negative word, the correlation coefficient may take a negative value.

[0070] Furthermore, the above-described series of processes can be executed by hardware or software. In other words, the functional configurations in FIG. 3 and the like are merely examples and are not particularly limited. That is, it is sufficient that the information processing system is provided with a function capable of executing the above-mentioned series of processes as a whole, and the type of functional block used to realize this function is not limited to the example in Fig. 3, etc. Furthermore, the location of the functional block is not limited to the example in Fig. 3, etc., and may be arbitrary. Furthermore, one functional block may be configured as a single piece of hardware, may be configured as a single piece of software, or may be configured as a combination of both.

[0071] In addition, in this specification, the steps of describing the program to be recorded on the recording medium may be executed in parallel or individually, as well as in chronological order. Also, some of the steps described in the above embodiment may be omitted.

[0072] In addition, in this specification, the term "system" refers to an overall device that is composed of a plurality of devices or a plurality of means.

[0073] Furthermore, the number of different hardware components constituting this system and the number of users are optional, and the system may also include other hardware components. Furthermore, in this system, for example, some or all of the series of processes described above may be executed by another server or the like managed by a cloud or the like.

[0074] Furthermore, when the series of processes is executed by software, the programs constituting the software are installed into a computer or the like from a network or a recording medium.

[0075] The computer may be a computer that is built into dedicated hardware, or a computer that is capable of executing various functions by installing various programs. That is, for example, the various hardware in the above-described embodiment may be freely adopted as any computer, any mobile terminal such as a smartphone, etc. Furthermore, any combination of types and contents of various input units and various output units may be adopted.

[0076] Furthermore, the recording medium containing such a program may not only be constituted by a removable medium (not shown) provided separately from the device main body in order to provide the program to a user, etc., but may also be constituted by a recording medium that is provided to the user in a state in which it is pre-installed in the device main body.

[0077] Even when these other embodiments are adopted, the effects of the present embodiment are exhibited. In addition, the present embodiment can be appropriately combined with other embodiments, and other embodiments can be appropriately combined with each other.

[0078] To summarize the above, the program to which the present disclosure is applied can take various forms including the following configurations. Computer, A first information acquisition means for acquiring information related to a first content; A first term extraction means for extracting a predetermined word included in the first content as a first keyword; a term determination means for determining a word related to the first keyword as a second keyword; A second information acquisition means for acquiring information related to the second content; a second term extraction means for extracting the first keyword and the second keyword included in the second content; a first influence calculation means for calculating an influence of the first keyword or the second keyword in the second content; Any program that functions as such will suffice.

[0079] In addition, the first influence calculation means can calculate the influence of the first keyword by multiplying the influence calculated for each of the second keywords by a coefficient set in accordance with the second keyword and adding up each of the calculated values.

[0080] Furthermore, the first influence calculation means can recommend the target primary keyword when the influence calculated for each of the primary keywords is equal to or greater than a threshold value.

[0081] Furthermore, the first influence calculation means can recommend the target first keyword or the target second keyword when the influence calculated for each of the second keywords is equal to or greater than a threshold value.

[0082] In addition, the first influence calculation means can recommend the target first keyword or the second keyword when the value obtained by multiplying the influence calculated for each of the second keywords by the coefficient is greater than or equal to a threshold value, or when the coefficient is greater than or equal to a threshold value.

[0083] Moreover, the first influence calculation means can further function as a presentation means for presenting the calculated influence of the first keyword or the second keyword.

[0084] Moreover, the above-mentioned program can further function as a second influence calculation means for calculating an influence in the first content for each of the first keywords.

[0085] Furthermore, the first influence calculation means can calculate the influence of the first keywords in the second content by taking into account the influence of each of the first keywords in the first content.

[0086] In addition, the first influence calculation means can change the influence of the first keyword or the second keyword depending on the degree of usage of multiple contents included in the second content to which the first keyword or the second keyword is attached.

[0087] The degree of use may be determined based on the number of times the second content is used or the number of times it is clicked.

[0088] Furthermore, the first content or the second content may be a content that can be transmitted by broadcast or viewed via the Internet.

[0089] In addition, as another aspect of the present disclosure, 1. A computer-implemented information processing method, comprising: a first information acquisition step of acquiring information related to the first content; a first term extraction step of extracting a predetermined word included in the first content as a first keyword; a term determination step of determining a word related to the first keyword as a second keyword; a second information acquisition step of acquiring information related to the second content; a second term extraction step of extracting the first keyword and the second keyword included in the second content; a first influence calculation step of calculating an influence of the first keyword or the second keyword in the second content; The present invention may be an information processing method including the steps of:

[0090] In addition, as another aspect of the present disclosure, A first information acquisition means for acquiring information related to a first content; A first term extraction means for extracting a predetermined word included in the first content as a first keyword; a term determination means for determining a word related to the first keyword as a second keyword; A second information acquisition means for acquiring information related to the second content; a second term extraction means for extracting the first keyword and the second keyword included in the second content; a first influence calculation means for calculating an influence of the first keyword or the second keyword in the second content; The information processing device may include: [Explanation of symbols]

[0091] 1 Server 11 Control section 60 First content information acquisition unit 61 First Keyword Extraction Section 62 Second Keyword Extraction Section 63 Second content information acquisition unit 64 Related Word Group Extraction Unit 65 Influence Calculation Department 66 Influence presentation section 200 First Keyword DB 300 Second Keyword DB 400 Correlation Coefficient DB 2. First content device 3. Secondary content device 4 Service provision terminal

Claims

1. Computer, a first information acquisition means for acquiring information related to a first content; a first term extraction means for extracting a predetermined word included in the first content as a first keyword; a term determination means for determining a word related to the first keyword as a second keyword; A second information acquisition means for acquiring information related to the second content; a second term extraction means for extracting the first keyword and the second keyword included in the second content; a first influence calculation means for calculating an influence of the first keyword or the second keyword in the second content; A program that functions as a

2. the first influence calculation means multiplies the influence calculated for each of the second keywords by a coefficient set in accordance with the second keyword, and adds up the calculated values, thereby calculating the influence of the first keyword; The program according to claim 1.

3. the first influence calculation means recommends the target first keyword when the influence calculated for each of the first keywords is equal to or greater than a threshold value; The program according to claim 1.

4. the first influence calculation means recommends the target first keyword or the target second keyword when the influence calculated for each of the second keywords is equal to or greater than a threshold value; The program according to claim 1.

5. the first influence calculation means recommends the first keyword or the second keyword when a value obtained by multiplying the influence calculated for each of the second keywords by the coefficient is equal to or greater than a threshold value, or when the coefficient is equal to or greater than a threshold value; The program according to claim 2.

6. The first influence calculation means further functions as a presentation means for presenting the calculated influence of the first keyword or the second keyword. The program according to claim 1.

7. further functioning as a second influence calculation unit that calculates an influence in the first content for each of the first keywords; The program according to claim 1.

8. the first influence calculation means calculates the influence of the first keyword in the second content by taking into account the influence of the first keyword in the first content; The program according to claim 7.

9. the first influence calculation means changes the influence of the first keyword or the second keyword in accordance with a degree of use of a plurality of contents included in the second content to which the first keyword or the second keyword is attached; The program according to claim 1.

10. The degree of use is determined based on the number of times the second content is used or the number of times the second content is clicked. The program according to claim 9.

11. The first content or the second content is a content that can be transmitted by broadcast or viewed via the Internet.

11. The program according to claim 1.

12. 1. A computer-implemented information processing method, comprising: a first information acquisition step of acquiring information related to the first content; a first term extraction step of extracting a predetermined word included in the first content as a first keyword; a term determination step of determining a word related to the first keyword as a second keyword; a second information acquisition step of acquiring information related to the second content; a second term extraction step of extracting the first keyword and the second keyword included in the second content; a first influence calculation step of calculating an influence of the first keyword or the second keyword in the second content; An information processing method comprising:

13. a first information acquisition means for acquiring information related to a first content; a first term extraction means for extracting a predetermined word included in the first content as a first keyword; a term determination means for determining a word related to the first keyword as a second keyword; A second information acquisition means for acquiring information related to the second content; a second term extraction means for extracting the first keyword and the second keyword included in the second content; a first influence calculation means for calculating an influence of the first keyword or the second keyword in the second content; An information processing device comprising:

Images