JP7249316B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program for detecting interest in an object.

Conventionally, there is known a device that detects keywords that are hot topics on the Internet by totaling keywords searched on the Internet and calculating a burst value that indicates the increase value of the keywords per unit time ( For example, see Patent Document 1).
By detecting such topical keywords, it becomes possible to determine what keywords many users are currently interested in. keywords can be used.

WO2008/087728

However, when companies, etc. use celebrities, etc. to increase the effect of attracting customers, even if celebrities, etc. are selected based on keywords that are hot topics on the Internet, there are times when the effect of attracting customers cannot be sufficiently obtained. . In other words, even if a keyword is searched by many users, it is unclear whether each user has a strong interest in the keyword. It is also possible that the number of interested users is small. For example, if there are many users who search for celebrities only for reasons such as high search volume and topicality, it may not be possible to obtain a sufficient effect of attracting customers even if the celebrities are used to attract customers. be. That is, in the case of improving the effect of attracting customers as described above, the number of people who are interested in the keyword target is not enough, and the number of people who enthusiastically support the target is not sufficient. To do so, it is necessary to detect the degree of enthusiasm that indicates how enthusiastically the target is supported.

An object of the present invention is to provide an information processing device, an information processing method, and an information processing program for detecting a user's enthusiasm for an object.

An information processing apparatus according to the present invention includes an action history acquisition unit that acquires a user's action history with respect to a target, and extracts from the action history an action with respect to the target that consumes at least one of time and money as a target-related action, and an enthusiasm determination unit that determines a degree of enthusiasm indicating a degree of enthusiasm of the user for the object based on the object-related behavior.

If a user enthusiastically supports an object, the user will waste a lot of time on that object and invest a lot of money on that object. The present invention determines the object-related behavior for the object that involves the consumption (time cost and monetary cost) as described above from the user's action history, and based on the object-related behavior, measures the user's enthusiasm for the object. judge. This makes it possible to appropriately determine the user's enthusiasm for the target.

Schematic diagram showing an information processing system according to an embodiment of the present invention. 1 is a block diagram showing a schematic configuration of a server device according to an embodiment; FIG. FIG. 2 is a block diagram showing a configuration example of a user terminal according to the embodiment; 4 is a flowchart showing an information processing method according to the embodiment; The figure which shows the pattern example by which a target person is extracted by the enthusiasm determination part of this embodiment. The figure which shows an example of the imaged target enthusiasm information of this embodiment.

An embodiment according to the present invention will be described below.
[Overview of information processing system]
FIG. 1 is a schematic diagram showing an information processing system of this embodiment.
As shown in FIG. 1, the information processing system of this embodiment includes a server device 10, which is an information processing device, and a plurality of user terminals 20 connected to the server device 10 via the Internet.
In this embodiment, the server device 10 acquires the user's action history from the user terminal 20 owned by the user, and detects the target that each user enthusiastically supports based on these action histories.

Such an information processing system can be used, for example, when a distributor who provides creations such as articles created by creators scouts popular creators (targets). In other words, such distributors need to determine which creators to scout in order to create creators who can create creations that are frequently purchased by users.
Conventionally, distributors have scouted creators who are frequently searched on the Internet, creators who are often viewed on video viewing sites, and the like. However, even if the number of searches on the Internet or the number of views on a video site is large, it is not always the case that the user will purchase the creation created by the creator. In other words, even if the number of searches is large, there are many users who are slightly interested in the creator. Such users watch creators' creations and browse videos if they are free of charge, but not many users are willing to pay money to purchase creations.
On the other hand, users who purchase creators' creations with a high probability are often so-called "core fans" who continue to be passionate about creators, and determine whether users enthusiastically support creators. It is important to.
Therefore, the server device 10 of the present embodiment acquires the action history of the target person such as a creator from the user's user terminal 20, and determines the user's enthusiasm for the target person based on this action history.

We will now further discuss the "enthusiasm" referred to herein. The degree of enthusiasm is a parameter indicating how much passion the user has for the target person and how much he/she supports the target, and is a parameter different from the general degree of interest.
In other words, the number of users who are interested in the target is calculated based on, for example, the number of searches on the Internet, the number of views on video sites, comments posted on SNS (Social Networking Service), and the like. Users who searched for the subject as a keyword, watched videos related to the subject, or posted comments on the subject may become so-called "core fans" who enthusiastically support the subject. , As mentioned above, there are quite a few users (so-called “niwaka fans”) who are temporarily interested simply because of the large number of searches in the world and the fact that it is a hot topic. This includes users who have just searched or watched videos so as not to miss the topic.
According to the knowledge of the inventor of the present application, when a target person is scouted based on the degree of interest and content produced by the target person is sold, the content produced by the target person whose interest level is higher than a predetermined value is sold. Even if there is, the sales result corresponding to the degree of interest cannot be obtained. This is because users with a high degree of interest include "core fans" who frequently purchase services related to the subject, and other users who do not purchase frequently. This is because it is difficult to detect these ratios only with the number of comments posted on SNS. Therefore, in the present application, the degree of enthusiasm (fan degree) as described above is used as a parameter different from the degree of interest.
Hereinafter, each configuration of such an information processing system will be described with a particular focus on the server device 10 .

[Configuration of server device 10]
FIG. 2 is a block diagram showing a schematic configuration of the server device 10. As shown in FIG.
The server device 10 is composed of a general computer, and as shown in FIG. 2, it has various units that constitute a computer, such as a communication unit 11, a recording unit 12, a processor 13, and the like. Note that the number of computers constituting the server device 10 is not particularly limited. For example, the server device 10 may be configured by one computer, or a cloud server constructed by connecting a plurality of computers via a network may be used as the server device 10 .
The communication unit 11 is connected to the Internet and communicates with each device such as the user terminal 20 via the Internet.

The recording unit 12 records various information and information processing programs for controlling the server device 10 .
The recording unit 12 also includes a user information recording unit 121 that records user information about a user, an analysis target information recording unit 122 that records analysis target information about a target person such as a creator, and the like. Here, an example in which the user information recording unit 121 and the analysis target information recording unit 122 are provided in the recording unit 12 of the server device 10 is shown, but other than that, the recording unit 12 is connected to the server device 10 via a network so as to be communicable. Various databases such as the user information recording unit 121 and the analysis target information recording unit 122 may be provided in a data server or cloud storage.

[User Information Recorded in User Information Recording Unit 121 of Recording Unit 12]
The user information recording unit 121 is a database that records user information including various information about general users.
The user who is the target of this user information may be, for example, a user using a search service by a portal site or the like, or a user using an SNS. It may be a user using an information distribution service or the like. User information may also be generated by integrating information on users using a plurality of services.
In the present embodiment, the server device 10 acquires various types of information about the user from the user terminal of the user who uses such various services, and records the information in the user database as user information.

Specifically, the user information includes a user ID, user attribute information, home range information, action history information, and the like.
The user ID is information for identifying a user, and may be information automatically assigned by the server device 10, or may be an account name arbitrarily set by the user.
The user attribute information records various information about the user, such as the user's gender, occupation, and hobbies.

Home range information is information indicating a user's home range, and a predetermined distance range centered on bases frequently visited by the user, such as the user's whereabouts or workplace, is set. The base of the user may be a point registered by the user, or may be a base determined by the server apparatus 10 based on the movement history of the user, which will be described later. Also, the range of the home range may be set to a user's movement area based on the user's movement history (position history), or may be set to a predetermined distance range centering on the base. When setting a distance range centered on a base, the user's frequently used means of transportation (walking, bicycle, car, etc.) may be determined based on the movement history, and the distance range corresponding to the relevant means of transportation may be set. Based on the history, the distance range may be the average distance traveled by the user centering on the base.

The action history information includes action history detected by various sensors mounted on the user terminal 20 and various applications installed on the user terminal 20 in addition to the user's action history on the Internet.

The action history on the Internet includes, for example, search history, browsing history, purchase history, transmission history, and the like.
The search history is history information indicating search keywords and search dates and times used in search processing performed by the user on the Internet.
The browsing history is history information that records the website browsed by the user on the Internet and the browsing date and time, and may further include the creator or operator of the target website.

The purchase history is history information indicating products and services purchased by the user at online shops and auction sites, transaction amounts, transaction dates and times, and the like. Further, the purchase history includes not only the history of the establishment of a sales contract, but also the purchase attempt history when the user tried to purchase a predetermined product but was unable to purchase it. For example, tickets for live performances of popular artists may only be purchased by users who have made reservations in advance (reservation sales), or may only be purchased by a predetermined number of users on a first-come, first-served basis (first-come-first-served basis). In the present embodiment, when the user made a reservation in the reservation sale but was unable to make a reservation, or when the user tried to purchase in the first-come-first-served sale but was not able to make a purchase because it was out of the first-come-first-served order, As the trial information, the product for which the purchase was attempted, the target person (artist, etc.) related to the product, the date and time of the trial purchase action, and the like are recorded.

The transmission history is history information indicating the user's public profile information to SNS or the like, the transmission or update of public content such as a blog or homepage created by the user, and the date and time of transmission or update. The posted information includes, for example, user's public profile information on SNS. The public content included in the transmission history may be a copy of the public content generated by the user, or may be a link destination of the public content.
Note that, in the present embodiment, outgoing content is content having content greater than or equal to a preset volume (the number of characters in a text sentence, etc.), and means content different from posted information such as tweets composed of short sentences. are doing.

Examples of action history information detected by various sensors and various applications of the user terminal 20 include location history, application execution history, and the like.
The location history is information indicating the user's location and the date and time when the user was located at that location using a location detection sensor such as a GPS device installed in the user terminal 20 .
The application execution history is the execution history of various applications executed by the user on the user terminal 20 . This application execution history may include the name of the application that was executed and the date and time of execution, as well as various information acquired by the application.
For example, in the execution history (payment history) of a payment application that executes payment and settlement using electronic money, the product to be paid, the amount of the payment, the store where the payment was made, and the like may be recorded.
Also, in the content browsing history for browsing content such as news, the browsed content and the browsing date and time of the content may be recorded.

[Target Information Recorded in Analysis Target Information Recording Unit 122 of Recording Unit 12]
The analysis target information recording unit 122 records target information related to the analysis target.
In this embodiment, the analysis target is a person (target person). The selection of the target person is not particularly limited. For example, the target person may be registered by the administrator of the server device 10, extracted from keywords searched by search processing on the Internet, or may be selected from the user's action history. A target person detected based on this may be targeted. In this embodiment, for example, a target person is selected in advance by an administrator of the server apparatus 10, and an example in which target information of the selected target person is recorded is shown.
This target information includes, for example, target ID, name information, target attribute information, activity schedule information, and the like.
The target ID is information for identifying target information.
The name information is information such as the real name and common name of the target person.
Target attribute information is information indicating various types of information about a target person, and can be obtained, for example, from content related to the target person published on the Internet, public profiles on SNSs published by the target person himself/herself or related parties, and the like. . Examples of information included in the target attribute information include, for example, the target person's occupation, activity field, activity area, activity history, and the like. Image information of a person (a photograph of the person's face, a moving image of the person in action, etc.) may be included.
The activity schedule information is the activity schedule of the target person, and records, for example, the date and time and place of the event in which the target person participates. The activity schedule information can be obtained, for example, from content related to the target person published on the Internet, or posted information posted on SNS by the target person or related parties. Alternatively, the date and time and place of the event for the target person may be acquired from a ticket sales server that sells participation tickets to the event.

[Functional Configuration of Processor 13]
The processor 13 is composed of an arithmetic circuit such as a CPU and a recording circuit such as a RAM. The processor 13 expands the information processing program recorded in the recording unit 12 into the RAM, and executes various processes in cooperation with the program expanded into the RAM.
Then, by reading and executing the information processing program, the processor 13, as shown in FIG. 134 and an image generator 135 .

The user information acquisition unit 131 also functions as an action history acquisition unit of the present invention, and acquires user information including user action history information from the user terminal 20 .
The home range detection unit 132 detects the user's base and the user's home range based on the user's action history information.

The enthusiasm determination unit 133 determines (calculates) the user's enthusiasm for the target person based on the user information.
The statistical processing unit 134 statistically processes the degree of enthusiasm of each user for each target person.
The image generator 135 generates image data representing statistical processing results.
A detailed description of each functional configuration of the processor 13 will be given later.

[Configuration of User Terminal 20]
FIG. 3 is a block diagram showing a configuration example of the user terminal 20. As shown in FIG.
The user terminal 20 is a terminal device owned by a user, and is configured by a computer such as a smart phone, a tablet terminal, or a personal computer, for example. The user terminal 20 has a basic configuration of a general computer. That is, the user terminal 20 includes an input operation section 21, a display 22, a terminal communication section 23, a sensor section 24, a terminal recording section 25, a terminal processor 26, and the like.

The input operation unit 21 is an input device that receives user's input operations. The input operation unit 21 may be composed of, for example, a keyboard, a mouse, or the like, or may be composed of a touch panel integrated with the display 22 .
The display 22 is a display screen for displaying various image information.
The terminal communication unit 23 is a device that communicates with an external device. As the terminal communication unit 23, a plurality of communication devices corresponding to each of a plurality of communication standards may be provided. As the plurality of communication devices, for example, the terminal communication unit 23 includes a wireless LAN communication device that performs communication by Wi-Fi (registered trademark), a mobile communication device that uses a communication telephone line standard, Bluetooth (registered trademark), infrared communication, etc. , NFC (registered trademark), etc., can be exemplified.

The sensor unit 24 includes various sensors. Sensors included in the sensor unit 24 include, for example, a position detection sensor 241 such as a GPS device that detects the position of the user terminal 20 (that is, the position of the user), and a motion sensor that detects the attitude and acceleration of the user terminal 20. 242 can be exemplified. In addition, the sensor unit 24 may include a microphone that detects sound, a direction sensor that detects direction, an image sensor that captures images such as still images and moving images, and the like.

Various application software (programs) for providing various services and controlling the user terminal 20 and various data are recorded in the terminal recording unit 25 .
Various types of data include user action history information. As described above, the user's action history information includes, for example, the action history detected by various sensors and various applications, and the user's action history on the Internet.

As the action history detected by various sensors, for example, a movement history (position history) including the position detected by the position detection sensor 241 and the date and time when the position was detected can be exemplified. In addition, a motion history indicating motion data detected by the motion sensor and the date and time when the motion data was detected may be included. Also, the means of transportation of the user determined based on the movement history and the motion history may be associated with the movement history. The means of transportation can be detected by using a known technique. For example, the vertical vibration of the user terminal recorded in the motion history and the position and movement speed of the user based on the movement history can be used to determine whether the user is traveling by train. , whether it is movement by car or on foot, etc., can be determined.
As described above, execution histories of various applications include execution histories of applications such as payment histories and content viewing histories.
As the behavior history on the Internet, various behaviors on the Internet performed by the user terminal 20, such as search history, browsing history, purchase history, and transmission history, are recorded.
In this embodiment, an example in which each piece of action history information is recorded in the terminal recording unit 25 of the user terminal 20 is shown, but for example, only a part of the user's action history may be recorded. For example, an action history on the Internet may be immediately transmitted to the server device 10 and recorded as user information when a user performs a predetermined action on the Internet.

The terminal processor 26 is composed of an arithmetic circuit such as a CPU and a recording circuit such as a RAM. The terminal processor 26 expands the information processing program recorded in the terminal recording unit 25 into the RAM, and executes various processes in cooperation with the program expanded into the RAM.
For example, the terminal processor 26 executes a predetermined application (program) based on user operations and preset schedule information, records various information such as action history in the terminal recording unit 25, and or send.

[Information processing method]
Next, an information processing method in the information processing system will be described, centering on the processing of the server device 10. FIG.
In this example, it is assumed that the user ID and user attributes of the user information recorded in the user information recording unit 121 are registered in advance. User information is registered, for example, by accessing a predetermined registration site provided by the server device 10 from the user terminal 20, or by executing a predetermined application provided by the administrator of the server device 10 on the user terminal 20. be able to.

FIG. 4 is a flow chart showing the information processing method of this embodiment.
The user information acquisition unit 131 of the server device 10 first acquires action history information from the user terminal 20, and updates the user information in the user information recording unit 121 (step S1: action history acquisition step).
Specifically, in step S1, the server device 10 acquires a user ID specifying a user and action history information, and records (updates) the acquired action history information in the user information specified by the user ID. The execution timing of step S1 is, for example, the timing when an action such as search processing on the Internet is performed, the timing when payment processing using a payment application at a store is performed, or the like when the user performs a predetermined action. It can be timing. Alternatively, it may be implemented by being transmitted from the user terminal 20 at a preset cycle (for example, at a predetermined time, on weekends, at the end of the month, etc.).

Next, the home range detection unit 132 detects the user's home range (step S2). In this embodiment, the home range detection unit 132 detects the user's home range based on the user's behavior information.
For example, the home range detection unit 132 detects a position where the user has not moved for a predetermined time from the user's movement history, and if the position is substantially the same for a plurality of days, the user's position at the position is detected. Detect as a base. Also, the home range detection unit 132 sets a predetermined distance range centered on the user's base as the user's home range. Note that this distance range may be appropriately set based on the usual moving distance centered on the user's base. For example, the user's average moving distance centered on the base may be set as the predetermined distance range as the home range. Alternatively, the means of transportation that the user usually uses may be detected based on the movement history and motion history of the user, and the home range may be set based on the distance range preset for each means of transportation.
Alternatively, the home range detection unit 132 may set a movement area around the base of the user based on the user's movement history. In this case, the home range is not a circular range centered on the base of the user, but an area where the user actually moves frequently can be set as the home range.

Next, the enthusiasm determination unit 133 performs an enthusiasm determination process (enthusiasm determination step) for determining the user's enthusiasm for the target person based on the action history information of each user.
In this enthusiasm level determination process, first, the enthusiasm level determination unit 133 extracts, from the user's action history information, a target-related behavior that is a behavior that the user enthusiastically supports for a target person, and This target person is extracted (step S3).
In step S3, the enthusiasm determination unit 133 extracts, from the user's action history, a person supported by the user by spending at least one of time and money as a target person. We extract behaviors that do as object-related behaviors.

FIG. 5 is a diagram showing a pattern example in which a target person is extracted by the enthusiasm determination unit 133. As shown in FIG.
Pattern A in FIG. 5 is a pattern in which a public content including a keyword or an image indicating a target person is transmitted by a user, and is determined based on the transmission history of the user.
For example, compared to creating and transmitting short sentences such as so-called tweets, users spend more time creating information about their own public profile information on SNS, etc., and content posted by users themselves, such as blogs and websites. spend
Therefore, the enthusiasm determination unit 133 identifies public content published on the Internet by the user based on the transmission history, analyzes the public content by a technique such as morphological analysis or image analysis, and analyzes the public content. Extract the target person included in . At this time, it is more preferable to specify the target person used together with positive keywords such as "fan", "like", and "enjoyable".
Further, when the target person is extracted, the enthusiasm determination unit 133 extracts the transmission behavior of disclosing the public content in the transmission history as the target-related behavior of the user.

Pattern B in FIG. 5 is a pattern in which the user purchases a service related to the target person, and is determined based on the user's purchase history on the Internet and the application execution history of the user terminal 20 .
The purchase history of this embodiment includes the purchase history of services such as products at online shops, auction sites, and the like on the Internet. Also, the application execution history includes a history of payment using the payment application, that is, a history including the store where the user purchased the product or other service, the purchased product or other service, and the date and time of purchase.

For example, if a history of purchasing services related to a target person (for example, tickets for a live concert in which the target person appears or goods such as goods) is recorded as a purchase history or payment history, It means that you spent money on things that you do.
Therefore, the enthusiasm determination unit 133 analyzes the service purchased by the user based on the purchase history and payment history, and determines whether or not the service is related to the target person.
Analysis of purchased services may, for example, refer to information on the Internet regarding purchased services. As described above, the target attribute information of the target information includes the activity history of the target person, and may include services related to the target person. It can be easily determined whether the service is a service related to the target person. In addition, if the service related to the target person is the right to participate in an event that the target person holds or appears (participates in) (for example, tickets for live concerts, etc.), the activity schedule of the target information related to the target person The date and time and location of the event are recorded. Therefore, even in this case, it can be easily determined from the target information whether or not the service purchased by the user is related to the target person.
Therefore, the enthusiasm determination unit 133 identifies the service purchased by the user based on the purchase history included in the purchase history and the payment history included in the application execution history, analyzes the service, and identifies the service purchased. Extract the corresponding target person. In addition, when the target person is extracted, the enthusiasm determination unit 133 extracts the purchase behavior of the service in the purchase history or the payment history as the target-related behavior of the user.

In pattern C of FIG. 5, determination is made based on the target person and target-related behavior based on the purchase attempt history.
In this embodiment, the purchase history includes a purchase attempt history. This purchase attempt history is, for example, a history indicating that the user has tried to purchase a service such as a live concert ticket that is sold on a first-come, first-served basis or by lottery. Note that when the user can purchase the service, it is recorded as a normal purchase history. Therefore, the purchase trial history is recorded when a purchase is attempted but cannot be purchased due to being out of the first-come-first-served basis or lottery. Such a purchase attempt history is useful for measuring the user's enthusiasm for the target person.
Therefore, in the present embodiment, the enthusiasm determination unit 133 further identifies, based on the purchase attempt history, the service for which the user attempted to purchase, in the same manner as the purchase history, analyzes the service, and analyzes the service for which the user attempted to purchase. Extract a target person corresponding to . In addition, when the target person is extracted, the enthusiasm determination unit 133 extracts the purchase attempt behavior of the service in the purchase attempt history as the target-related behavior of the user.

Pattern D in FIG. 5 is a pattern for detecting the behavior of the user following the behavior of the target person, and is determined based on the movement history of the user, for example.
In other words, when the user is an enthusiastic fan of the target person, the user may follow the movement of the target person in order to meet the target person (so-called "chasing"). Such movement of the user following the movement of the target person is movement that is not necessary in the normal life of the user, and means that the user spends time with the target person. The movement of the target person is recorded, for example, in the date and place recorded in the activity schedule included in the activity schedule information of the target information. Therefore, the enthusiasm determination unit 133 can identify the target person that the user is following based on the movement history of the user and the activity schedule information of the target information. Further, when the target person is specified, the enthusiasm determination unit 133 extracts the movement behavior following the target person in the movement history as the target-related behavior of the user.

Even if the movement of the target person is not followed, the movement following the position of an object related to the target person may be determined as the target-related behavior.
For example, this corresponds to a case where the user's movement history includes movement to an exhibition where the target person's works are exhibited, or to a movie theater showing a movie in which the target person appears. In this case, by recording, in the activity schedule of the target information, the period and place of the exhibition of the work created by the target person, the movie theater where the target person's appearance movie is shown, the broadcasting period, etc., the enthusiasm determination unit 133 can identify whether the user's movement history includes movement following movement of objects related to the target person, and the target person that the user supports.

Then, the enthusiasm determination unit 133 calculates, based on the action history of each user, the degree of enthusiasm indicating how passionately the user supports the target person (step S4). .
In this step S4, the enthusiasm determination unit 133 uses a weight value based on the number of object-related behaviors included in the user's behavior history and a weight value based on a combination of a plurality of object-related behaviors to determine the degree of enthusiasm. Calculate Y.

For example, a basic value X _i is given to the object-related behavior corresponding to each pattern i (where i is one of A to D), and the pattern A first weight value K _in for i is set.

Also, different correction values α _iZ are set according to the contents of the patterns A to D, respectively. Here, the suffix Z is information indicating the content of the object-related behavior of each pattern, and differs for each pattern.
For example, in pattern A, the correction value α _AV is set according to the average volume V of the public content (the number of text characters and the number of images). That is, the correction value α _AV is set such that the degree of enthusiasm Y increases as the amount of content related to the target person increases.
In pattern B, a correction value α _BM is set according to the average amount M of purchased services. That is, the correction value α _BM is set such that the higher the average amount M, the higher the degree of enthusiasm Y.
In pattern C, the correction value α _CE is set according to the timing of the trial purchase. That is, the closer the average E of the difference between the sale date and reservation start date and time of the right to participate in the event held or participated in by the target person and the trial purchase date and time, the larger the correction value α _CE .
In pattern D, the correction value α _DR is set according to the average distance R from the user's location, workplace, or other base frequently used by the user or from the action area to the destination of the movement following the movement of the target person. . In other words, in order to move to an event venue far from the user's base, it is necessary to spend more time and money, and the correction value α _DR is increased for such movement.

Furthermore, a second weight value L _ij is set for a combination i×j (where i and j are any of A to D) of related object-related actions.
An example of a combination of object-related behaviors is a combination of a pattern C object-related behavior and a related pattern D object-related behavior.
This means that a user who tried to purchase the right to participate in an event in which the target person participates (for example, a ticket for a live concert), but was unable to purchase the right to participate, can purchase an event such as an event venue on the day of the event. This is the case when moving to the vicinity of the venue. In other words, there are users who cannot participate in the event because they do not have participation rights, but who move to the event site to enjoy the atmosphere of the event site, the voice of the target person leaking from the event site, the cheers of the audience, and the like. If there is no passionate support for the target person, such actions are rarely taken, and it can be determined that the above-described user has a very high degree of enthusiasm for the target person. In this embodiment, when there is a combination including pattern C and pattern D as described above, the second weight value _LCD is set to be larger than the combination of other patterns. That is, in the present embodiment, the second weight value _LCD is the maximum value among all the second weight values _Lij .

It should be noted that the above second weight value L _CD is an example, and the second weight value L _ij is individually set for each of the other combinations i×j.
For example, if multiple trial purchase behaviors (object-related behaviors) for the same event according to pattern C and purchase behaviors (object-related behaviors) for the same event according to pattern B are specified, participation rights at various stores are identified. It can be regarded as an action in which a purchase is attempted and participation rights are purchased as a result. In this case, for example, there is a possibility that the user supports the target person more than when there is only pattern B of the target-related behavior and there is no pattern C of the target-related behavior, so the degree of enthusiasm Y is increased. A second weight value L _BC for
Also, the second weight value L _ij may not be set for all combinations i×j. That is, there may be a second weight value L _ij such that L _ij =0.

Then, the enthusiasm determination unit 133 determines the basic value X _i corresponding to each target-related action for each target person extracted in step S3, the first weight value K _in corresponding to the number of extracted target-related actions, Using the correction value α _iZ according to the content of each object-related behavior and the second weight value L _ij according to the combination i×j of the related object-related behaviors, the enthusiasm Calculate Y. Note that Z indicates a set of Z={A, B, C, D}.

Formula (1) is an example, and the enthusiasm Y may be calculated by an arbitrary function Y=f(X _i , _Kin , α _iZ , L _ij ).

Thereafter, the statistical processing unit 134 statistically processes the enthusiasm Y for a plurality of target persons calculated for each user, and calculates target enthusiasm information indicating the relationship between the enthusiasm Y and the number of users for each target person. (Generate) (step S5). This target enthusiasm information is information indicating how many users with each enthusiasm level Y exist for the target person, and is obtained by dividing the number of users for each enthusiasm level Y or the enthusiasm level Y into a plurality of range groups. This is statistical information about the number of users belonging to each group in each case.
The statistical processing unit 134 generates target enthusiasm information for each target person.
Further, the image generation unit 135 converts the target enthusiasm information generated in step S5 into an image as image information (step S6).
FIG. 6 is a diagram showing an example of the target enthusiasm information imaged in step S6.
For example, as shown in FIG. 6, the image generator 135 visualizes the target enthusiasm level information on a two-axis graph in which the horizontal axis is the enthusiasm level Y and the vertical axis is the number of users.

Furthermore, the statistical processing unit 134 counts the number of users whose enthusiasm is equal to or higher than a predetermined first threshold value Y _th (see FIG. 6) for each target person, and counts the number of users whose enthusiasm is equal to or higher than the first threshold. A target person whose number is equal to or greater than the second threshold is extracted as a high-enthusiasm target (step S7).
In other words, in the present embodiment, the server device 10 allows a distributor who wants to scout a target person as a business partner, such as a distributor who distributes and sells creations provided by a target person such as a creator, to select a target person with a high profit rate. It should be properly extracted. The target person extracted in step S7 indicates that many users are supporting with high passion, and by scouting such a target person, the distributor can obtain a high profit. .

[Action and effect of the present embodiment]
The server device 10 of the present embodiment includes a recording unit 12 and a processor 13. The processor 13 reads an information processing program stored in the recording unit 12 to obtain a user information acquisition unit 131 and an enthusiasm determination unit 133. function as The user information acquisition unit 131 functions as an action history acquisition unit and acquires the user's action history with respect to the target person. The enthusiasm determination unit extracts the user's behavior toward the target person that consumes at least one of time and money as object-related behavior from the behavior history, and determines the user's enthusiasm Y for the target person based on the target-related behavior. .

Thereby, the degree of enthusiasm Y for the target person of each user can be determined. In other words, the number of search processes and the number of views of video sites alone do not show how passionately a user supports a target person. Enthusiasm based on time and money spent on By determining the degree of enthusiasm in this way, it is possible to accurately determine whether or not the user has a high probability of purchasing the service related to the target person.
Therefore, for example, when a distributor that distributes distribution content scouts a creator of content that can be purchased by many users, it is possible to appropriately determine the target person.

In this embodiment, the enthusiasm determination unit 133 extracts the behavior of the user following the behavior of the target person as the target-related behavior. Specifically, the enthusiasm determination unit 133 extracts the movement of the user following the movement of the target person as the target-related behavior.
When such a movement that follows the movement of the target person of the user is detected, it is highly likely that the user passionately supports the target person. In the present embodiment, since such movement behavior is extracted as the target-related behavior of pattern D, the user's enthusiasm Y for the target person can be calculated with high accuracy.

In this embodiment, the enthusiasm determination unit 133 extracts the purchase of a service related to the target person, which is included in the purchase history regarding the purchase of the service, as the target-related behavior.
If a user purchases a service related to a target person, the user is likely to endorse that target person. Also, if the user has purchased a service related to the target person multiple times or if the user has purchased an expensive service, the user is more likely to support the target person. Since the enthusiasm determination unit 133 of the present embodiment extracts such purchase behavior as the target-related behavior of pattern B, the enthusiasm Y for the target person of the user can be accurately calculated.

In this embodiment, the purchase history includes purchase attempt history of attempts to purchase services.
Even if the user has not purchased the service associated with the target person, the user is likely to endorse the target person if he/she attempts to purchase the service. In particular, in services where the number of sales of concert tickets is limited, sales are often performed on a first-come, first-served basis or by lottery, and even core fans may not be able to purchase the concert tickets. On the other hand, in the present embodiment, the enthusiasm determination unit 133 extracts the purchase trial behavior as the pattern C object-related behavior based on the purchase trial history. As a result, even if a user who has a high degree of enthusiasm for the target person cannot obtain a service related to the target person, the user will not be determined to have a low degree of enthusiasm. Enthusiasm Y can be calculated with high accuracy.

In this embodiment, the user information acquisition unit 131 acquires, as an action history, a transmission history of public content created by the user to the Internet. Then, the enthusiasm determination unit 133 extracts the transmission behavior of the public content including the keyword or image indicating the target person as the target-related behavior.
As described above, the public content in the present embodiment can be a public profile on SNS, a blog, a homepage, etc. Unlike so-called tweets and short sentences posted information, content created by the user spending a certain amount of time. point to In such public content, describing content about a target person indicates that the user has spent time on the target person, and there is a high possibility that the user will support the target person. Therefore, by extracting the transmission behavior of such public content as the target-related behavior, the user's enthusiasm Y for the target person can be calculated with high accuracy.

In this embodiment, the enthusiasm determination unit 133 uses the basic value X _i set for each object-related action and the first weight value K _in according to the number n of extracted object-related actions, Enthusiasm Y is calculated.
The more times a user performs a predetermined action for a target person, the more likely the user is passionately supporting the target person. For example, when a user publishes public profile information including a target person, participates in events held by the target person, and purchases products related to the target person, the user is more enthusiastic than a user who simply purchases products related to the target person. likely to support the target person. In this embodiment, an appropriate degree of enthusiasm Y can be calculated by correcting the basic value X _i with the first weight value K _in according to the number of such object-related actions.

In the present embodiment, the enthusiasm determination unit 133 determines enthusiasm using a basic value Xi set for each object-related behavior and a second weight value _Lij corresponding to a combination of extracted related object-related behaviors. degree Y is calculated.
If a user takes multiple actions related to a given behavior towards a target person, it is highly likely that the user is passionately supporting that target person. For example, when a user participates in an event held by a target person and purchases a product related to the target person at the event, the user is more enthusiastic than a user who simply participates in the event held by the target person. There is a high possibility that the target person is supported by In this embodiment, an appropriate degree of enthusiasm Y can be calculated by correcting the basic value X _i with the second weight value L _ij according to such a combination of related object-related behaviors.

Enthusiasm level determination unit 133 determines whether the user attempted to purchase the right to participate in the event, but failed to purchase the right to participate, and moved to the event venue on the date of the event. and are extracted as object-related behaviors, a second weight value _LCD is set that is greater than the second weight value L _ij for combinations of other object-related behaviors.
In other words, as in pattern C, when it is detected that the user tried to purchase the right to participate in the event but was unable to purchase it, the user usually gives up on participating in the event, even though the user cannot participate in the event. It is highly probable that the user passionately supports the target person by moving to the event venue. Therefore, the degree of enthusiasm Y can be calculated appropriately by setting the second weight value _LCD for the combination of object-related behaviors of patterns C and D as the maximum value among all the second weight values _Lij .

In this embodiment, the enthusiasm determination unit 133 corrects the basic value X _i using the correction value α _iZ according to the content of the extracted object-related behavior.
For example, even object-related behaviors of the same pattern may consume different amounts of time and money, and if these are set to the same reference value, an appropriate degree of enthusiasm cannot be calculated. On the other hand, in the present embodiment, by correcting the basic value X _i with the correction value α _iZ according to the content of the object-related behavior, it is possible to calculate a more appropriate degree of enthusiasm Y.

For example, in this embodiment, the processor 13 functions as a home range detection unit 132 that detects the user's home range. Then, when the user's movement behavior following the movement of the target person is extracted as the target-related behavior of pattern D, the enthusiasm determination unit 133 determines the correction value based on the average distance R between the movement destination and the home range in the target-related behavior. The α _DR is used to correct the base value X _D .
For example, a user residing in Tokyo travels to participate in an event held overseas such as in Europe, compared to a user residing in Tokyo traveling to participate in an event held in Tokyo. If you do, spend a lot of time and money on travel. Normally, such a long-distance movement is usually hesitant, and when such movement is detected, there is a high possibility that the user is passionately supporting the target person. In the present embodiment, it is possible to appropriately set the correction value _αDR according to the degree of burden that such movement following the movement of the target person imposes on the user. Enthusiasm Y can be calculated appropriately.

In this embodiment, the processor 13 further functions as a statistical processing section 134 . This statistical processing unit 134 statistically processes the degree of enthusiasm Y determined for a target person for a plurality of users. Then, regarding the target person, target enthusiasm information indicating the number of users for each level of enthusiasm Y is generated.
That is, the statistical processing unit 134 can visualize the enthusiasm distribution of users who support each target person. As a result, for example, a company that wants to scout a target person as a business partner can easily determine how many users with a high degree of enthusiasm Y exist for the target person, and support which target person should be scouted. It can be performed.

The statistical processing unit 134 generates target enthusiasm information for each of a plurality of target persons, and selects a target person for whom the number of users corresponding to the enthusiasm Y that is equal to or greater than the first threshold _Yth is equal to or greater than the second threshold. Extract as target.
As a result, a trader who wants to scout a target person as a business partner can automatically extract a target person to be scouted without having to analyze the results of statistical processing by themselves.

[Modification]
It should be noted that the present invention is not limited to the above-described embodiments, and includes modifications shown below within the scope of achieving the object of the present invention.

[Modification 1]
In the above embodiment, an example of acquiring user information from the user terminal 20 in step S1 is shown, but the present invention is not limited to this. For example, user information may be acquired from other service servers such as an SNS server that provides SNS and a search server that provides search services.
In this case, user association processing is performed to associate user information held by various service servers. The user association processing is performed, for example, by the user terminal 20, and is performed to associate a user account relating to a first service provided by the administrator of the server device 10 with a user account relating to a second service provided by another service server. By performing the operation, the information of the associated user account is transmitted from the user terminal 20 to the server device 10 . As a result, the server device 10 can acquire the user information specified by the user account related to the second service from the service server that provides the second service, and register it in the user information of the user information recording unit 121 . . Therefore, even if the action history is not directly acquired from the user terminal 20, it is possible to acquire the user's action history information and the like from the service server of another service used by the user.

[Modification 2]
In the above embodiment, an example is shown in which the administrator of the server apparatus 10 selects a target person in advance and records the target information of the target person in the analysis target information recording unit, but the present invention is not limited to this. For example, processor 13 may function as a target selector.
In this case, the target selection unit may, for example, crawl content on the Internet and select a person included as a keyword in a predetermined number or more of content as a target person. As a result, it is possible to timely detect a target person who is being talked about on the Internet, and to select a target person in a wider range than when selecting a target person manually.

Alternatively, the target selection unit may select the target person based on the user's action history. For example, a text sentence of the public profile information of the user's transmission history may be subjected to analysis processing such as morphological analysis, and keywords used with positive expressions such as "fan" may be extracted as the target person. Alternatively, the target person may be extracted by searching the Internet for information based on the user's purchase history, payment history, and movement history. For example, when a user purchases a service such as a product, the target person may be extracted by referring to web content published by the provider of the service. In addition, when the user moves to an event site based on the user's movement history, the target person who appears in the event may be extracted by referring to the web content related to the event held at the event site.

[Modification 3]
In the above embodiment, the user's moving behavior following the movement of the target person is detected as the target-related behavior of pattern D as the user's behavior following the target behavior, but the present invention is not limited to this.
For example, it is possible to detect behaviors such as a fan of an artist imitating a target person's behavior, such as changing the artist's hairstyle to the same hairstyle or purchasing an accessory that the artist loves. These may be detected, for example, from posted information posted on SNS, or may be detected from purchase history or payment history.

In the above embodiment, an example of setting the second weight value L _ij according to the combination of patterns i×j has been described. A value D _ij may be set.
For example, even though the target-related behavior of purchasing the right to participate in the event is specified in pattern B, if there is no moving behavior of pattern D of moving to the event site on the date of the event, the right to participate is transferred to another person. In such a case, the subtraction value _DBD may be set.

[Modification 4]
In the above embodiment, an example in which the target is a person was shown, but the target is not limited to this, and may be a specific product or the like. For example, cosmetic products sold by a predetermined cosmetics company may be targeted. However, in this case, the behavior of the user following the target behavior cannot be detected.

DESCRIPTION OF SYMBOLS 10... Server apparatus, 11... Communication part, 12... Recording part, 13... Processor, 121... User information recording part, 122... Analysis object information recording part, 131... User information acquisition part, 132... Home range detection part, 133... Enthusiasm level determination unit 134 Statistical processing unit 135 Image generation unit.

Claims (14)

an action history acquisition unit that acquires an action history of a user's target;
Enthusiasm degree for determining a degree of enthusiasm indicating a degree of enthusiasm of the user for the object based on the object-related behavior, extracting behavior toward the object that consumes at least one of time and money as object-related behavior from the behavior history a determination unit;
with
The enthusiasm determination unit determines the enthusiasm using a basic value set for each of the object-related actions and a second weight value according to a combination of the other object-related actions related to the target-related action. An information processing device that calculates degrees . the subject is a person,
The enthusiasm determination unit extracts the behavior of the user following the behavior of the target as the target-related behavior.
The information processing device according to claim 1 . The action history includes a movement history regarding movement of the user,
The enthusiasm determination unit extracts the movement of the user following the movement of the target as the object-related behavior, as the behavior of the user following the behavior of the target.
The information processing apparatus according to claim 2. The action history includes a purchase history regarding the purchase of services,
The enthusiasm determination unit extracts the purchase of the service related to the target, which is included in the purchase history, as the target-related behavior.
The information processing device according to claim 1 . The purchase history includes a purchase attempt history of attempts to purchase the service,
The information processing apparatus according to claim 4. the action history includes a transmission history of public content created by the user on the Internet;
The enthusiasm determination unit extracts transmission of the public content containing a keyword indicating the target or an image indicating the target as the target-related behavior.
The information processing device according to claim 1 . The enthusiasm determination unit calculates the enthusiasm using the basic value, the second weight value, and a first weight value according to the number of the extracted object-related behaviors.
The information processing apparatus according to any one of claims 1 to 6. the subject is a person,
The action history includes a movement history regarding movement of the user and a purchase attempt history of attempting to purchase a right to participate in an event in which the target participates,
The enthusiasm determination unit follows the purchase attempt indicating that the user attempted to purchase the participation right but was unable to purchase the participation right, and the movement of the target, which are included in the purchase attempt history. When the movement of the user to the vicinity of the venue of the event is extracted as the object-related behavior, the degree of enthusiasm is determined using the second weight value that is larger than the combination of the other object-related behaviors. to calculate
The information processing device according to claim 1 . The enthusiasm determination unit corrects the basic value using a correction value according to the content of the extracted object-related behavior.
The information processing apparatus according to any one of claims 1 to 8 . Further comprising a home range detection unit that detects the user's home range,
The enthusiasm determination unit extracts the movement of the user following the movement of the target as the target-related behavior, and uses the correction value based on the distance between the destination and the home range in the target-related behavior, correcting the base value;
The information processing apparatus according to claim 9 . Statistically processing the degree of enthusiasm determined for the target for the plurality of users, and generating target enthusiasm information indicating the relationship between the degree of enthusiasm for the target and the number of users corresponding to the degree of enthusiasm Further comprising a statistical processing unit that generates
The information processing apparatus according to any one of claims 1 to 10 . The statistical processing unit generates the target enthusiasm information for each of the plurality of targets, and selects the target for which the number of users corresponding to the enthusiasm level equal to or greater than a first threshold is equal to or greater than a second threshold as high enthusiasm. Extract as a degree target,
The information processing device according to claim 11 . An information processing method for processing information by a computer,
The computer includes an action history acquisition unit and an enthusiasm determination unit,
an action history acquisition step in which the action history acquisition unit acquires an action history of the user's target;
The enthusiasm determination unit extracts from the action history a behavior toward the object that consumes at least one of time and money as object-related behavior, and indicates the user's degree of enthusiasm toward the object based on the object-related behavior. Enthusiasm degree determination step for determining the degree of enthusiasm , and
In the enthusiasm determination step, the enthusiasm is determined using a basic value set for each object-related action and a second weight value according to a combination of the other object-related actions related to the object-related action. Information processing method for calculating degrees . A computer-readable and executable information processing program,
An information processing program that causes the computer to function as the information processing apparatus according to any one of claims 1 to 12 .

Images