Highly influential user search device, highly influential user search method, and program

Abstract

The purpose of the present disclosure is to efficiently collect, from among the vast amount of data on the web, data from posts that will help improve services.　Therefore, the present disclosure provides a highly influential user search device (3) that searches for data of posts by highly influential users from among data of posts on the web, the highly influential user search device (3) comprising: an input unit (31) that inputs data of a prescribed post relating to a prescribed service on the web; a post analysis unit (34) that implements an analysis on the basis of the data of the prescribed post to estimate at least one from among data of a service usage history of a user with regards to the prescribed service, data of the influential power of the user with regards to the prescribed service, and data of a billing status of the user with regards to the prescribed service; a score calculation unit (35) that totals a score on the basis of the estimated result and identifies a user having a high score of a prescribed value or higher; and an output unit (38) that outputs data of a specific post by the user with the high score.

Description

[Technical Field]

[0001] The present disclosure relates to a method for collecting information based on user characteristics from the Web, such as a social networking service (SNS). This paper relates to a technology for extracting posts from a website. [Background technology]

[0002] In recent years, the importance of marketing using social media has increased for services. Social media is a great way to monitor the development of services, as a huge number of reviews and reactions are posted about them. However, from the huge volume of posts, it is difficult to obtain information on users who have a large impact on the service, such as sales, influence on SNS, and long-term use. Therefore, in the past, users were asked to provide feedback through online surveys, etc. For example, as shown in Figure 11, in the case of paid services, a small number of high-paying users account for a high proportion of the sales amount (see Non-Patent Document 1). Figure 11 is a diagram showing the proportion of the number of users (left) and the proportion of the amount (right) by the amount charged. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Mitsubishi Research Institute, Inc., "Survey Results on Smartphone Games," March 24, 2016, pp. 1-48 <https: / / www.caa.go.jp / policies / policy / consumer_policy / policy_coordination / internet_committee / pdf / 160324shiryo1-1.pdf> Summary of the Invention [Problem to be solved by the invention]

[0004] However, when collecting and summarizing user opinions through web surveys, etc., Furthermore, it is difficult to collect opinions that are of high importance to society. This creates a problem in that it is not possible to obtain the reactions of users who do not participate in the event.

[0005] The present invention has been made to solve the above-mentioned problems, and aims to efficiently collect posting data that is useful for improving services from the vast amount of data on the web. [Means for solving the problem]

[0006] In order to solve the above problem, the invention of claim 1 is a highly influential user search device for searching for data on posts made by highly influential users from data on posts made on the web, the highly influential user search device comprising an input unit for inputting data on predetermined posts relating to a predetermined service on the web, and a device for retrieving data on the user's service usage history relating to the predetermined service, data on the user's influence relating to the predetermined service, and data on the user's billing status relating to the predetermined service based on the data on the predetermined posts. Ta The system includes a post analysis unit that performs an analysis to estimate the posts, a score calculation unit that adds up the scores based on the estimated results and identifies users with high scores equal to or greater than a predetermined value, and an output unit that outputs data on specific posts by the users with high scores. The post analysis unit estimates the user's service usage history by acquiring the oldest post that is believed to indicate the user's use of the predetermined service. It is a high-impact user search device. [Effects of the Invention]

[0007] As described above, the present invention has the effect of making it possible to efficiently collect posted data useful for improving services from among the vast amount of data on the web. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram of a communication system. [Figure 2]FIG. 2 is an electrical hardware configuration diagram of a highly influential user search device. [Figure 3] FIG. 2 is a diagram illustrating an electrical hardware configuration of a communication terminal. [Figure 4] FIG. 2 is a functional configuration diagram of a highly influential user search device. [Figure 5] 10 is a flowchart showing a search process for a highly influential user. [Figure 6] FIG. 10 shows an example of the oldest tweets using the service. [Figure 7] FIG. 10 is a diagram showing an example of a tweet with high impressions. [Figure 8] FIG. 10 is a diagram showing an example of a post that indicates a billing status. [Figure 9] FIG. 10 is a diagram showing a product price list for service A. [Figure 10] FIG. 10 is a diagram showing an example of a displayed post. [Figure 11] This figure shows the ratio of the number of users (left) and the ratio of the amount (right) based on the amount charged. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0010] [System configuration of the embodiment] First, an outline of the configuration of a communication system according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a schematic diagram of a communication system according to an embodiment of the present invention.

[0011] 1, a communication system 1 of this embodiment is constructed by a highly influential user search device 3 and a communication terminal 5. The communication terminal 5 is managed and used by an analyst a.

[0012] Furthermore, the highly influential user search device 3 and the communication terminal 5 can communicate with each other via a communication network 100 such as the Internet. The communication network 100 may be connected wirelessly or by wire.

[0013] The highly influential user search device 3 is configured by one or more computers. When the highly influential user search device 3 is configured by multiple computers, it may be referred to as a "highly influential user search device" or a "highly influential user search system."

[0014] The highly influential user search device 3 focuses on the influence of users and extracts the opinions of highly influential users by scoring three indices (attributes): the user's service usage history (usage history), the user's communication ability, and the user's service billing status. Note that the number of indices is not limited to three. Other indices such as gender and age may also be taken into consideration.

[0015] The communication terminal 5 is a computer, and Fig. 1 shows a laptop computer as an example. In Fig. 1, analyst A operates the communication terminal 5. Note that the highly influential user search device 3 may perform processing alone without using the communication terminal 5.

[0016] [Hardware configuration] <Hardware configuration of high-impact user search device> Next, the electrical hardware configuration of the highly influential user search device 3 will be described with reference to Fig. 2. Fig. 2 is a diagram showing the electrical hardware configuration of the highly influential user search device.

[0017] As shown in FIG. 2 , the highly influential user search device 3 is a computer that includes a CPU (Central Processing Unit) 301, a ROM (Read Only Memory) 302, a RAM (Random Access Memory) 303, a Solid State Drive (SSD) 304, an external device connection I / F (Interface) 305, a network I / F 306, a media I / F 309, and a bus line 310. It is equipped with:

[0018] Of these, the CPU 301 controls the overall operation of the highly influential user search device 3. The ROM 302 stores programs such as an IPL (Initial Program Loader) used to drive the CPU 301. The RAM 303 is used as a work area for the CPU 301.

[0019] The SSD 304 reads or writes various data under the control of the CPU 301. Note that instead of the SDD 304, a HDD (Hard Disk Drive) may be used.

[0020] The external device connection I / F 305 is an interface for connecting various external devices, such as a display, a speaker, a keyboard, a mouse, a USB (Universal Serial Bus) memory, and a printer.

[0021] The network I / F 306 is an interface for performing data communication via the communication network 100 .

[0022] The media I / F 309 controls reading and writing (storing) of data from and to a recording medium 309m such as a flash memory, etc. The recording medium 309m includes a DVD (Digital Versatile Disc) and a Blu-ray Disc (registered trademark).

[0023] The bus line 310 is an address bus, a data bus, etc. for electrically connecting the components such as the CPU 301 shown in FIG.

[0024] <Hardware configuration of communication terminal> Next, the electrical hardware configuration of the communication terminal 5 will be described with reference to Fig. 3. Fig. 3 is a diagram showing the electrical hardware configuration of the communication terminal.

[0025] As shown in FIG. 3, the communication terminal 5 is a computer that includes a CPU 501, a ROM 502, a RAM 503, an SSD 504, an external device connection I / F (Interface) 505, a network The computer 500 includes a network I / F 506 , a display 507 , a pointing device 508 , a media I / F 509 , and a bus line 510 .

[0026] Of these, the CPU 501 controls the overall operation of the communication terminal 5. The ROM 502 stores programs such as IPL used to drive the CPU 501. The RAM 503 is used as a work area for the CPU 501.

[0027] The SSD 504 reads or writes various data under the control of the CPU 501. Note that instead of the SSD 504, an HDD (Hard Disk Drive) may be used.

[0028] The external device connection I / F 505 is an interface for connecting various external devices, such as a display, a speaker, a keyboard, a mouse, a USB memory, and a printer.

[0029] The network I / F 506 is an interface for performing data communication via the communication network 100 .

[0030] The display 507 is a type of display means such as a liquid crystal display or organic EL (Electro Luminescence) display that displays various images.

[0031] The pointing device 508 is a type of input means for selecting and executing various instructions, selecting a processing target, moving a cursor, etc. If analyst A uses a keyboard, the function of the pointing device 508 may be turned off.

[0032] The media I / F 509 controls reading and writing (storing) of data from and to a recording medium 509m such as a flash memory, etc. The recording medium 509m includes DVDs, Blu-ray Discs (registered trademarks), etc.

[0033] The bus line 510 is an address bus, a data bus, or the like for electrically connecting the components such as the CPU 501 shown in FIG.

[0034] [Functional configuration of the high-influence user search device] Next, the functional configuration of the highly influential user search device will be described with reference to Fig. 4. Fig. 4 is a functional configuration diagram of the highly influential user search device in the embodiment of the present invention.

[0035] 4, the highly influential user search device 3 includes an input unit 31, an input processing unit 32, a post analysis unit 34, a score calculation unit 35, an analysis unit 36, an output processing unit 37, and an output unit 38. Each of these units is a function realized by an instruction from the CPU 301 in FIG. 2 based on a program.

[0036] Furthermore, a posted information DB (Data Base) 33 is constructed in the RAM 303 or HD 304 in FIG. It has been done.

[0037] <Posting information DB> The post information DB 33 manages data such as the date of the post, the text, and the impressions obtained from the post data.

[0038] <Each function configuration> Next, each functional configuration of the highly influential user search device will be described with reference to FIGS.

[0039] The input unit 31 receives input of data posted by an unspecified number of users relating to a predetermined service from the analyst a via the communication terminal 5 and the network I / F 306.

[0040] The input processing unit 32 processes the data input by the input unit 31 so that it can be easily processed later.

[0041] The post analysis unit 34 performs analysis based on the data of a specified post to estimate data on the user's service usage history for a specified service, data on the user's influence for the specified service, and data on the user's billing status for the specified service.

[0042] The score calculation unit 35 calculates the score S based on the results estimated by the post analysis unit 34. The system calculates the scores and identifies users with high scores equal to or greater than a predetermined value.

[0043] The analysis unit 36 ​​communicates with an external server or the like via the communication network 100 from the input unit 31, thereby calculating and adjusting the constants α, β, and γ, which will be described later.

[0044] The output processing unit 37 acquires the analysis data (data of specific posts by high-scoring users) from the analysis unit 36, and creates analysis result data that can be viewed by analyst a.

[0045] The output unit 38 outputs the analysis result data. Examples of the output method include sending the output result data to the communication terminal 5, displaying it, or printing it.

[0046] [Processing or Operation of the Embodiment] Next, the processing or operation of this embodiment will be described in detail with reference to Figures 5 to 10. Figure 5 is a flowchart showing the search process for highly influential users. Here, an example will be described in which analyst A collects user reviews of service A, a predetermined service developed by his company.

[0047] STEP 1: As shown in FIG. 5, first, the input unit 31 receives an input from the communication terminal 5 by the analyst a. Alternatively, the input unit 31 may directly acquire the data of the SNS post by the name of the service. The input processing unit 32 searches for the data of posts on the SNS by the name of the service. The date, text, and impression of the post are then obtained, and this information is stored in the post information DB 33.

[0048] For example, the input unit 31 may search Twitter for an example of post data under the name of service A. and retrieve the data of the specified post.

[0049] STEP 2: The post analysis unit 34 analyzes whether a user is likely to be using a predetermined service. The data of the oldest posts is searched (obtained) and normalized to estimate the user's service usage history.

[0050] For example, as shown in Fig. 6, the post analysis unit 34 searches the user's past tweets to find the oldest tweet that is thought to be from service A, and estimates the service usage history. Fig. 6 is a diagram showing an example of the oldest tweet from a user using a service.

[0051] STEP 3: The post analysis unit 34 analyzes the posts of a user for a predetermined period from the present to the past (for example, one month). From the data of posts (minutes), a certain number of tweets with impressions (number of times) above a threshold are extracted (obtained), and these impressions are summed and normalized to estimate the user's influence.

[0052] For example, as shown in FIG. 7, the post analysis unit 34 analyzes the user's posts from the past month up to the present. The 10 most popular tweets are extracted and the number of impressions is calculated to estimate the influence of the user. Figure 7 shows examples of tweets with high impressions.

[0053] STEP 4: The post analysis unit 34 analyzes any posts from a predetermined period (for example, one month) from the present to the past. We search (obtain) posts that reveal the user's payment status and estimate the user's payment status, including normalization. The payment status is estimated by extracting words that represent the in-service payment system (e.g., "paid plan," "xx coins," "xx gacha series," etc.).

[0054] For example, as shown in FIGS. 8 and 9, the post analysis unit 34 analyzes user posts from the past month up to the present. We search for posts that give an indication of the user's billing status and estimate the amount using (Equation 1).

[0055]

number

[0056] Further explanation will be given below.

[0057] STEP 5: The score calculation unit 35 sums up the scores using (Equation 2) and calculates high scores equal to or greater than a predetermined value. The user (specific user) is identified. Note that (Equation 2) is an example.

[0058]

number

[0059] Furthermore, the score calculation unit 35 normalizes Σ(R+L) in the following procedure.

[0060] The score calculation unit 35 randomly selects 30 or more examples from posts that mention the service, and creates a t-distribution of impressions. The standard deviation of Σ(R+L) is derived from the distribution. In this embodiment, a method using t distribution for normalization is used. However, other methods may be used.

[0061] The score calculation unit 35 estimates the user's service usage history (see STEP 2), It is also possible to calculate the score using at least one of the results of the estimation of the impact (see STEP 3) and the estimation of the user's billing status (see STEP 4). For example, when analyzing a service related to a new product that has just been released, the importance of the usage history of this service (see STEP 2) is low. Therefore, it may be excluded from the impact score.

[0062] STEP 6: The analysis unit 36 ​​receives the data from the input unit 31 via the communication network 100 from an external server. etc., to calculate and adjust the constants α, β, and γ.

[0063] For example, if service A has just been released and long-term users are not important, the analysis unit 36 ​​adjusts the constant α to be smaller. On the other hand, if the company wants to focus on public relations activities and therefore place importance on the opinions of influencers, the analysis unit 36 ​​adjusts the constant β to be larger.

[0064] STEP 7: The output processing unit 37 receives the analysis data (specific inputs of high-scoring users) from the analysis unit 36. The output unit 38 outputs the analysis result data including the posts of high-scoring users, as shown in FIG.

[0065] [Effects of the embodiment] As described above, according to this embodiment, by using (Equation 2) to estimate user attributes from data posted on the web, such as SNS, it is possible to efficiently collect posts that are useful for improving services from a huge amount of data. For example, by incorporating the opinions of users who have a high impact on the service, it is possible to efficiently collect highly important opinions. It is also possible to obtain responses from users who do not voluntarily participate in surveys. Furthermore, when using influencers to release a new application, it is possible to select the most suitable users by searching existing similar games.

[0066] 〔supplement〕 The present invention is not limited to the above-described embodiment, and may have the following configurations or processes (operations). (1) The highly influential user search device 3 can be realized by a computer and a program, but this program can also be recorded on a (non-transitory) recording medium or provided via the communication network 100. (2) In the communication between the highly influential user search device 3 and the communication terminal 5, other devices (servers, routers, etc.) may relay data. For example, for the sake of simplicity, this specification describes that the input unit 31 of the highly influential user search device 3 transmits data to the communication terminal 5, but this transmission process also includes cases where other devices relay data. (4) In the above embodiment, a notebook computer is shown as an example of the communication terminal 5, but this is not limited to this and may be, for example, a desktop computer, a tablet terminal, a smartphone, a smartwatch, a car navigation device, a refrigerator, a microwave oven, etc. (5) Each CPU 301, 501 may be a single CPU or may be multiple CPUs. (6) At least a part of the processing performed by the post analysis unit 34 or the analysis unit 36 ​​may use a neural network. [Explanation of symbols]

[0067] 1. Communication Systems 3 High-impact user search device 5. Communication terminals 31 Input section 32 Input processing section 33 Posted Information DB (Example of Posted Information Management Section) 34 Post Analysis Department 35 Score Calculation Section 36 Analysis Department 37 Output Processing Section 38 Output section

Claims

1. A highly influential user search device that searches for data posted by highly influential users from data posted on the web, an input unit for inputting predetermined posting data related to the predetermined service on the web; a post analysis unit that performs analysis based on predetermined post data to estimate data on the user's service usage history regarding the predetermined service, data on the user's influence regarding the predetermined service, and data on the user's billing status regarding the predetermined service; a score calculation unit that sums up scores based on the estimated results and identifies users with high scores equal to or greater than a predetermined value; an output unit that outputs data of specific posts by the high-scoring users; and The post analysis unit estimates the user's service usage history by acquiring the oldest post that is thought to indicate that the user is using the specified service.

2. A highly influential user search device that searches for data posted by highly influential users from data posted on the web, an input unit for inputting predetermined posting data related to the predetermined service on the web; a post analysis unit that performs analysis based on predetermined post data to estimate data on the user's service usage history regarding the predetermined service, data on the user's influence regarding the predetermined service, and data on the user's billing status regarding the predetermined service; a score calculation unit that sums up scores based on the estimated results and identifies users with high scores equal to or greater than a predetermined value; an output unit that outputs data of specific posts by the high-scoring users; and The post analysis unit estimates the user's billing status by acquiring post data that reveals the user's billing status for a predetermined period from the present to the past.

3. The highly influential user search device of claim 1 or 2, wherein the post analysis unit normalizes data on the user's service usage history for the specified service, data on the user's influence for the specified service, and data on the user's billing status for the specified service.

4. The highly influential user search device of any one of claims 1 to 3, wherein the post analysis unit obtains a predetermined number of tweets with impressions above a threshold from the user's posts for a predetermined period from the present to the past, and estimates the influence of the user by summing up the impressions.

5. A search method for highly influential users executed by a highly influential user search device that searches for data of posts by highly influential users from data of posts on the web, comprising: an input process for inputting predetermined posting data related to the predetermined service on the web; a post analysis process for performing an analysis based on data of a predetermined post to estimate data on the user's service usage history for the predetermined service, data on the user's influence on the predetermined service, and data on the user's billing status for the predetermined service; a score calculation process for summing up scores based on the estimated results and identifying users with high scores equal to or greater than a predetermined value; an output process for outputting data of specific posts by the high-scoring users; Run The post analysis process is a highly influential user search method that includes a process of estimating the user's service usage history by obtaining the oldest post that is thought to indicate the user's use of the specified service.

6. A search method for highly influential users executed by a highly influential user search device that searches for data of posts by highly influential users from data of posts on the web, comprising: an input process for inputting predetermined posting data related to the predetermined service on the web; a post analysis process for performing an analysis based on data of a predetermined post to estimate data on the user's service usage history for the predetermined service, data on the user's influence on the predetermined service, and data on the user's billing status for the predetermined service; a score calculation process for summing up scores based on the estimated results and identifying users with high scores equal to or greater than a predetermined value; an output process for outputting data of specific posts by the high-scoring users; Run The post analysis process is a highly influential user search method that includes a process of estimating the user's billing status by obtaining post data that reveals the user's billing status for a predetermined period from the present to the past.

7. A program causing a computer to execute the method according to claim 5.

Images