JP7679806B2 - Characteristic estimation device, characteristic estimation method, and program - Google Patents

Description

This disclosure relates to a characteristic estimation device, a characteristic estimation method, and a program.

There is a technology that analyzes the characteristics of a user's consumption behavior in a communication network such as the Internet and provides information according to the user's characteristics. For example, Patent Document 1 discloses a characteristics estimation server that estimates the characteristics of a user based on the user's questionnaire results and behavioral history.

The characteristic estimation server disclosed in Patent Document 1 classifies multiple target users who responded to a questionnaire into one of multiple predetermined characteristics based on the questionnaire results, and identifies teacher users whose behavioral history meets a predetermined standard. The characteristic estimation server then estimates the characteristics of the estimated user using a characteristic estimation model that uses behavioral information extracted from the behavioral history of the teacher users as explanatory variables and the characteristics of the teacher users as objective variables.

JP 2020-35409 A

However, in conventional technology, whether or not there are differences in consumption behavior between groups of users classified into the same characteristics is fluid. For example, the invention disclosed in Patent Document 1 identifies teacher users from target users classified based on survey results, so there is no guarantee that there are differences in consumption behavior characteristics between target users classified into different characteristics.

In view of the technical challenges described above, the present disclosure aims to estimate the characteristics of a user based on data representing the actual consumption behavior of the user.

In order to solve the above problem, a characteristic estimation device according to one aspect of the present disclosure includes a target extraction unit configured to extract a target user based on a web browsing history, a performance data acquisition unit configured to acquire consumption behavior performance data representing the performance of consumption behavior performed by the target user, a consumption behavior estimation unit configured to estimate purchase speed data representing the purchasing speed of the target user and listening degree data representing the listening degree of the target user based on the web browsing history and the consumption behavior performance data, and a characteristic determination unit configured to determine the consumption behavior characteristics of the target user based on the purchase speed data and the listening degree data.

According to one aspect of the present disclosure, it is possible to estimate a user's characteristics based on data representing the user's actual consumption behavior.

1 is a block diagram showing an example of an overall configuration of a consumption behavior characteristic estimation system. FIG. 2 is a block diagram showing an example of a hardware configuration of a computer. 2 is a block diagram showing an example of a functional configuration of a characteristic estimation device. FIG. 11 is a flowchart showing an example of a processing procedure of a characteristic estimation method. FIG. 13 is a conceptual diagram illustrating an example of a site classification master. FIG. 13 is a conceptual diagram illustrating an example of a web browsing history table. FIG. 13 is a conceptual diagram showing an example of a web browsing history to which site classification information has been added. FIG. 13 is a conceptual diagram illustrating an example of a subject master. FIG. 2 is a conceptual diagram illustrating an example of a customer master. FIG. 13 is a conceptual diagram illustrating an example of a web browsing history associated with subject information. FIG. 13 is a conceptual diagram illustrating an example of a contact medium table. FIG. 13 is a conceptual diagram illustrating an example of a product purchase record table. FIG. 13 is a conceptual diagram illustrating an example of a policy response record table. FIG. 13 is a conceptual diagram showing an example of purchase speed data and listening level data. FIG. 13 is a conceptual diagram showing an example of a purchasing speed score and a listening level score. FIG. 13 is a conceptual diagram illustrating an example of a characteristic determination rule. FIG. 13 is a conceptual diagram illustrating an example of a consumption behavior characteristic estimation result.

Each embodiment of the present disclosure will be described below with reference to the accompanying drawings. Note that in this specification and drawings, components having substantially the same functional configuration will be denoted by the same reference numerals, and redundant description will be omitted.

[Embodiment]
An embodiment of the present disclosure is a consumption behavior characteristic estimation system that estimates characteristics related to a user's consumption behavior (hereinafter also referred to as "consumption behavior characteristics"). The consumption behavior characteristic estimation system estimates a user's consumption behavior characteristics based on a web browsing history that represents a history of the user's web browsing and consumption behavior performance data that represents the performance of the user's consumption behavior. Note that a user for whom a consumption behavior characteristic is to be estimated is also referred to as a "target user."

In this embodiment, the target users are customers whose information is held by the entity (such as a company, organization, or individual) using the consumption behavior characteristic estimation system. However, the target users are not limited to customers of companies, etc., and any users can be the target users as long as their web browsing history and consumption behavior performance data can be obtained.

The consumer behavior characteristic estimation system estimates purchasing speed data representing the purchasing speed of the target user and listening level data representing the listening level of the target user based on the web browsing history and the consumer behavior performance data. The consumer behavior characteristic estimation system also determines the consumer behavior characteristics of the target user based on the purchasing speed data and listening level data estimated for the target user. Therefore, the consumer behavior characteristic estimation system can estimate the consumer behavior characteristics of the target user based on data representing the performance of the consumer behavior performed by the target user.

<Overall configuration of the consumer behavior characteristic estimation system>
The overall configuration of a consumption behavior characteristic estimating system in this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the overall configuration of a consumption behavior characteristic estimating system in this embodiment.

As shown in FIG. 1, the consumption behavior characteristic estimation system 1 in this embodiment includes a characteristic estimation device 10 and a user terminal 20. The characteristic estimation device 10 and the user terminal 20 are connected to each other so as to be able to communicate data with each other via a communication network N1 such as a LAN (Local Area Network) or the Internet.

The characteristic estimation device 10 is an information processing device such as a personal computer, a workstation, or a server that estimates the consumption behavior characteristics of a target user in response to a request from a user terminal 20. In response to a request from the user terminal 20, the characteristic estimation device 10 estimates the consumption behavior characteristics of the target user extracted from the web browsing history, and transmits the estimation result to the user terminal 20.

The user terminal 20 is an information processing terminal such as a personal computer, tablet terminal, or smartphone operated by a user of the consumption behavior characteristic estimation system 1. In response to the user's operation, the user terminal 20 transmits a request signal requesting estimation of a consumption behavior characteristic to the characteristic estimation device 10. The user terminal 20 also receives the estimation result from the characteristic estimation device 10 and outputs it to the user.

The overall configuration of the consumption behavior characteristic estimation system 1 shown in FIG. 1 is just one example, and various system configuration examples are possible depending on the application and purpose. For example, the characteristic estimation device 10 may be realized by multiple computers, or may be realized as a cloud computing service. In addition, for example, the consumption behavior characteristic estimation system 1 may be realized by a standalone information processing device that has the functions that the characteristic estimation device 10 and the user terminal 20 should each have.

<Hardware configuration of the consumer behavior characteristic estimation system>
The hardware configuration of the consumption behavior characteristic estimation system 1 in this embodiment will be described with reference to FIG.

<Computer hardware configuration>
The characteristic estimation device 10 and the user terminal 20 in this embodiment are realized by, for example, a computer. Fig. 2 is a block diagram showing an example of the hardware configuration of a computer 500 in this embodiment.

As shown in FIG. 2, the computer 500 has a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, a RAM (Random Access Memory) 503, a HDD (Hard Disk Drive) 504, an input device 505, a display device 506, a communication I/F (Interface) 507, and an external I/F 508. The CPU 501, the ROM 502, and the RAM 503 form a so-called computer. Each piece of hardware in the computer 500 is connected to each other via a bus line 509. Note that the input device 505 and the display device 506 may be connected to the external I/F 508 for use.

The CPU 501 is a computing device that reads programs and data from a storage device such as the ROM 502 or the HDD 504 onto the RAM 503 and executes processing to realize the overall control and functions of the computer 500.

ROM 502 is an example of a non-volatile semiconductor memory (storage device) that can retain programs and data even when the power is turned off. ROM 502 functions as a main storage device that stores various programs, data, etc. required for CPU 501 to execute various programs installed in HDD 504. Specifically, ROM 502 stores boot programs such as BIOS (Basic Input/Output System) and EFI (Extensible Firmware Interface) that are executed when computer 500 is started, as well as data such as OS (Operating System) settings and network settings.

RAM 503 is an example of a volatile semiconductor memory (storage device) from which programs and data are erased when the power is turned off. RAM 503 is, for example, a dynamic random access memory (DRAM) or a static random access memory (SRAM). RAM 503 provides a working area into which various programs installed in HDD 504 are expanded when executed by CPU 501.

HDD 504 is an example of a non-volatile storage device that stores programs and data. The programs and data stored in HDD 504 include an OS, which is basic software that controls the entire computer 500, and applications that provide various functions on the OS. Note that instead of HDD 504, computer 500 may use a storage device that uses flash memory as a storage medium (e.g., SSD: Solid State Drive, etc.).

The input device 505 includes a touch panel that the user uses to input various signals, operation keys or buttons, a keyboard or mouse, a microphone for inputting sound data such as voice, etc.

The display device 506 is composed of a display such as a liquid crystal or organic EL (Electro-Luminescence) display for displaying a screen, a speaker for outputting sound data such as voice, etc.

The communication I/F 507 is an interface that connects to a communication network and enables the computer 500 to perform data communication.

The external I/F 508 is an interface with external devices. Examples of external devices include a drive device 510.

The drive device 510 is a device for setting the recording medium 511. The recording medium 511 here includes media that record information optically, electrically, or magnetically, such as CD-ROMs, flexible disks, and magneto-optical disks. The recording medium 511 may also include semiconductor memory that records information electrically, such as ROM and flash memory. This allows the computer 500 to read and/or write to the recording medium 511 via the external I/F 508.

The various programs to be installed in the HDD 504 are installed, for example, by setting the distributed recording medium 511 in a drive device 510 connected to the external I/F 508 and reading the various programs recorded on the recording medium 511 by the drive device 510. Alternatively, the various programs to be installed in the HDD 504 may be installed by downloading them from a network different from the communication network via the communication I/F 507.

<Functional configuration of the characteristic estimation device>
The functional configuration of the characteristic estimation device 10 in this embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the functional configuration of the characteristic estimation device 10 in this embodiment.

As shown in FIG. 3, the characteristic estimation device 10 in this embodiment includes a site classification master storage unit 101, a web browsing history storage unit 102, a customer master storage unit 103, a subject master storage unit 104, a contact medium data storage unit 105, a product purchase data storage unit 106, a policy response data storage unit 107, a characteristic determination rule storage unit 108, a browsing history classification unit 111, a subject extraction unit 112, a performance data acquisition unit 113, a consumer behavior estimation unit 114, and a characteristic determination unit 115.

The site classification master storage unit 101, the web browsing history storage unit 102, the customer master storage unit 103, the subject master storage unit 104, the contact medium data storage unit 105, the product purchase data storage unit 106, the policy response data storage unit 107, and the characteristic determination rule storage unit 108 are realized by the RAM 503 or the HDD 504 shown in FIG. 2.

The browsing history classification unit 111, the target person extraction unit 112, the performance data acquisition unit 113, the consumption behavior estimation unit 114, and the characteristic determination unit 115 are realized by processing executed by the CPU 501 according to a program loaded onto the RAM 503 from the HDD 504 shown in FIG. 2.

The site classification master storage unit 101 stores site classification information. The site classification information is master data that associates a web page with a category of information posted on the web page. The site classification information is stored in the site classification master described below.

The web browsing history storage unit 102 stores web browsing history. Web browsing history is performance data that records website viewers in association with the web pages that the viewers viewed. The web browsing history is stored in a web browsing history table, which will be described later.

The web browsing history can be obtained from the access log of the web server. The characteristic estimation device 10 may periodically obtain the web browsing history from the web server at a predetermined time interval, or may obtain the web browsing history from the web server in response to a user request.

The customer master storage unit 103 stores customer information. The customer information is master data that represents information about customers of companies and the like that use the consumption behavior characteristic estimation system 1. The customer information is stored in the customer master, which will be described later.

The customer information can be obtained, for example, from a customer management system that manages information about customers. The characteristic estimation device 10 may periodically obtain customer information from the customer management system at a predetermined time interval, or may obtain customer information from the customer management system in response to a user request.

The subject master storage unit 104 stores subject information. The subject information is master data that represents information about subjects who responded to a market survey conducted over the Internet. The subject information is stored in the subject master, which will be described later.

The contact medium data storage unit 105 stores contact medium data. The contact medium data is performance data that records information about the media that subjects respond to in market research and that they come into contact with on a daily basis. The contact medium data is stored in a contact medium table, which will be described later.

The subject information and contact medium data can be acquired from a questionnaire server or the like for conducting market research. The characteristic estimation device 10 may acquire the subject information and contact medium data from the questionnaire server or the like periodically at a predetermined time interval, or may acquire the subject information and contact medium data from the questionnaire server or the like in response to a user request.

Product purchase data is stored in the product purchase data storage unit 106. The product purchase data is performance data that represents the history of a customer's purchase of a product or service. The product purchase data is stored in a product purchase performance table, which will be described later.

Product purchase data can be obtained, for example, from credit card payment history or purchase history on an EC (Electronic Commerce) site that sells products or services electronically. The characteristic estimation device 10 may obtain product purchase data periodically at a predetermined time interval, or may obtain product purchase data in response to a user request.

The policy response data storage unit 107 stores policy response data. The policy response data is performance data that indicates whether or not a customer responded to a sales promotion policy such as an advertisement or an incoming call. The policy response data is stored in a policy response performance table, which will be described later.

The policy response data can be obtained, for example, from a marketing system that implements sales promotion policies. The characteristic estimation device 10 may periodically obtain the policy response data from the marketing system at a predetermined time interval, or may obtain the policy response data from the marketing system in response to a user request.

The characteristic determination rule storage unit 108 stores characteristic determination rules. The characteristic determination rules are information representing rules for determining which of predetermined consumption behavior characteristics a target user falls under based on consumption behavior data estimated for the target user. The characteristic determination rules are determined in advance by a user of the consumption behavior characteristic estimation system 1. The characteristic determination rules are stored in a characteristic determination rule table, which will be described later.

The browsing history classification unit 111 identifies the category of the web pages recorded in each web browsing history by matching the web browsing history with the site classification master.

The subject extraction unit 112 matches the web browsing history with the subject master, thereby associating each web browsing history viewer with the subject of the market research. This allows the extraction of target users whose consumption behavior characteristics are to be estimated.

The performance data acquisition unit 113 acquires consumption behavior performance data related to the target user. In this embodiment, the consumption behavior performance data includes contact medium data, product purchase data, and policy response data.

The consumption behavior estimation unit 114 estimates consumption behavior data for the target user based on the web browsing history and consumption behavior performance data for the target user. In this embodiment, the consumption behavior data includes purchase speed data representing the purchasing speed of the target user, and listening attention data representing the listening attention degree of the target user, etc.

The characteristic determination unit 115 determines the consumption behavior characteristics of the target user based on the consumption behavior data about the target user. The consumption behavior characteristics are determined according to characteristic determination rules.

<Processing Procedure of the Consumption Behavior Characteristics Estimation System>
Next, a consumption behavior characteristic estimating method executed by the consumption behavior characteristic estimating system 1 in this embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of a processing procedure of the consumption behavior characteristic estimating method in this embodiment.

In step S1, the user terminal 20 transmits a request signal requesting estimation of a consumption behavior characteristic to the characteristic estimation device 10 in response to an operation by a user of the consumption behavior characteristic estimation system 1. The characteristic estimation device 10 receives the request signal from the user terminal 20 and activates the browsing history classification unit 111.

The browsing history classification unit 111 included in the characteristic estimation device 10 reads out the web browsing history from the web browsing history table stored in the web browsing history storage unit 102. Next, the browsing history classification unit 111 reads out the site classification information from the site classification master stored in the site classification master storage unit 101.

<Site Classification Master>
The site classification master in this embodiment will be described with reference to Fig. 5. Fig. 5 is a conceptual diagram showing an example of the site classification master in this embodiment.

As shown in FIG. 5, the site classification master in this embodiment has data items such as a URL (Uniform Resource Locator), a major item, and a medium item. The URL is information that indicates the location of a web page. The major item is information that indicates the category of the web page. The medium item is information that indicates a subcategory into which the major item is subdivided. The site classification master illustrated in FIG. 5 subdivides categories into two levels, major items and medium items, but the number of category levels can be set arbitrarily as needed.

<Web browsing history table>
The web browsing history table in this embodiment will be described with reference to Fig. 6. Fig. 6 is a conceptual diagram showing an example of the web browsing history table in this embodiment.

As shown in FIG. 6, the web browsing history table in this embodiment has data items such as history ID, cookie, access time (Time), URL, number of browsing times (Count), and source (Source). The history ID is identification information that identifies the browsing history. The cookie is identification information that is recorded in the information processing terminal used by the web browser. Therefore, the web browser can be identified by the cookie. The source is information that indicates the media that linked to the URL.

Then, the browsing history classification unit 111 compares the URLs included in the web browsing history with the URLs included in the site classification information. This identifies the category of the web pages recorded in each web browsing history. The URLs may be compared by full-text match or by prefix match. The URLs may also be compared by complete domain match or by partial domain match.

Figure 7 is a conceptual diagram showing an example of a web browsing history to which site classification information has been added. As shown in Figure 7, in the web browsing history, each URL is assigned with the major and minor items of the site classification master. This identifies the category of the web page indicated by each URL in the web browsing history. For example, it can be seen that the web page indicated by the URL "http://abc.com/456" is a web page that contains news about automobiles.

Returning to FIG. 4, in step S2, the subject extraction unit 112 included in the characteristic estimation device 10 reads out the web browsing history from the web browsing history table stored in the web browsing history storage unit 102. Next, the subject extraction unit 112 reads out the subject information from the subject master stored in the subject master storage unit 104.

<Subject Master>
The subject master in this embodiment will be described with reference to Fig. 8. Fig. 8 is a conceptual diagram showing an example of the subject master in this embodiment.

As shown in FIG. 8, the subject master in this embodiment has data items such as a survey ID, a cookie, an RMID, a WT_FPC, and a customer ID. The survey ID is identification information that identifies the market research results, and is an ID that is uniquely assigned to the subject of the market research. The customer ID is one of the customer IDs stored in the customer master. In other words, the subject master is associated with the customer master by the customer ID.

<Customer Master>
The customer master in this embodiment will be described with reference to Fig. 9. Fig. 9 is a conceptual diagram showing an example of the customer master in this embodiment.

As shown in FIG. 9, the customer master in this embodiment has the following data items: customer ID, name, contact information (email address, etc.), and phase. The customer ID is identification information that identifies the customer. The phase is information that classifies the customer's level of interest in a product into multiple stages. The phase is determined, for example, based on the results of market research on the customer or their response to sales promotion measures, and is registered, for example, in a customer management system.

In this embodiment, there are five phases: "Awareness - Interest", "Interest - Concern", "Interest - Desire", "Desire - Action", and "Action - Sharing". The types of phases are not limited to these, and may be more subdivided into six or more phases, or more condensed into four or less phases.

Awareness is a state in which a customer is aware of a product. Note that a product is not limited to a good or service, but may be a product in a broad sense, including a brand. Interest is a state in which a customer is interested in a product. Interest is a state in which a customer is interested in a product. Desire is a state in which a customer feels a desire to purchase the product. Action is a state in which a customer has taken action to purchase the product. Sharing is a state in which a customer has shared information about the product with others.

The subject extraction unit 112 matches the cookies included in the web browsing history with the cookies included in the subject information. Cookies are matched on a full-text basis. This associates viewers of each web browsing history with the subjects of the market research.

Figure 10 is a conceptual diagram showing an example of a web browsing history associated with subject information. As shown in Figure 10, each cookie in the web browsing history is associated with a survey ID and a customer ID from the subject master. This allows the customer ID corresponding to each cookie to be identified. For example, it can be seen that a user to whom a cookie "a3fWa" has been assigned is a customer identified by a customer ID "U0001".

The subject extraction unit 112 extracts the customer ID included in the subject information that can be associated with the web browsing history. Thereafter, the extracted customer ID is treated as the customer ID of the target user. In other words, the target user is a user whose customer ID can be identified from among users who browsed the web of a company or the like that uses the consumption behavior characteristic estimation system 1.

Returning to FIG. 4, in step S3, the performance data acquisition unit 113 included in the characteristic estimation device 10 reads contact medium data related to the target user from the contact medium table stored in the contact medium data storage unit 105. Next, the performance data acquisition unit 113 reads product purchase data related to the target user from the product purchase performance table stored in the product purchase data storage unit 106. Next, the performance data acquisition unit 113 reads policy response data related to the target user from the policy response performance table stored in the policy response data storage unit 107.

Then, the performance data acquisition unit 113 associates the contact medium data, product purchase data, and campaign response data for the same customer. In this way, consumption behavior performance data for the target user is acquired.

<Contact Media Table>
The contact medium table in this embodiment will be described with reference to Fig. 11. Fig. 11 is a conceptual diagram showing an example of the contact medium table in this embodiment.

As shown in FIG. 11, the contact medium table in this embodiment has data items such as a survey ID and contact frequency. The contact frequency is information that indicates the contact frequency for each medium (television, the Internet, newspapers, magazines, etc.). The survey ID is one of the survey IDs stored in the subject master. In other words, the contact medium table is associated with the subject master by the survey ID.

<Product purchase record table>
The product purchase record table in this embodiment will be described with reference to Fig. 12. Fig. 12 is a conceptual diagram showing an example of the product purchase record table in this embodiment.

As shown in FIG. 12, the product purchase history table in this embodiment has, as data items, the purchase date and time when the product (or service) was purchased, the customer ID, the purchased product, etc. The customer ID is one of the customer IDs stored in the customer master. In other words, the product purchase history table is associated with the customer master by the customer ID.

<Policy response performance table>
The policy response record table in this embodiment will be described with reference to Fig. 13. Fig. 13 is a conceptual diagram showing an example of the policy response record table in this embodiment.

As shown in FIG. 13, the policy response performance table in this embodiment has data items such as customer ID and whether or not there was a response for each phase. The customer ID is one of the customer IDs stored in the customer master. In other words, the policy response performance table is associated with the customer master by the customer ID.

The phases are the same as those in the customer master: "Awareness - Interest," "Interest - Concern," "Interest - Desire," "Desire - Action," and "Action - Sharing." The policy response performance table records whether or not the customer responded to the sales promotion policy in each phase.

Returning to FIG. 4, in step S4, the consumer behavior estimation unit 114 included in the characteristic estimation device 10 calculates the correct value of the purchasing speed data and the correct value of the listening level data based on the web browsing history and the consumer behavior performance data related to the target user. The correct value of the purchasing speed data and the correct value of the listening level data are calculated from the web browsing history and the consumer behavior performance data according to predetermined rules.

Next, the consumer behavior estimation unit 114 assigns the correct value of the purchasing speed data and the correct value of the listening level data to the web browsing history and the consumer behavior performance data. This generates learning data in which the web browsing history and the consumer behavior performance data are explanatory variables and the purchasing speed data or the listening level data is the objective variable. The consumer behavior estimation unit 114 estimates the purchasing speed data and the listening level data for the target user using a machine learning model trained using the learning data.

Specifically, the consumption behavior estimation unit 114 estimates purchasing speed data for the target user by performing multiple regression analysis on the learning data in which the correct answer value of purchasing speed data is assigned to the web browsing history and consumption behavior actual data. Also, the consumption behavior estimation unit 114 estimates listening degree data for the target user by performing multiple regression analysis on the learning data in which the correct answer value of listening degree data is assigned to the web browsing history and consumption behavior actual data.

Multiple regression analysis is an example of a machine learning model, and other machine learning models may be used. For example, purchase speed data and listening interest data for target users may be estimated using a decision tree or a neural network.

Figure 14 is a conceptual diagram showing an example of purchasing speed data and listening level data. As shown in Figure 14, purchasing speed data is data that indicates the purchasing speed of a target user for each phase. Purchasing speed is an index that indicates the time it takes to purchase a product in that phase.

In this embodiment, the purchasing velocity is an index obtained by converting the time taken from progressing to a particular phase until purchase into a numerical value between 0 and 1. A smaller purchasing velocity value indicates a faster purchasing velocity, and a larger purchasing velocity value indicates a slower purchasing velocity. Note that since a product may be purchased before progressing to a particular phase, the purchasing velocity may be a negative value. For example, if a product is purchased at the stage where the product is recognized, the purchasing velocity corresponding to the interest and subsequent phases will be a negative value.

As shown in FIG. 14, the listening level data is data that indicates the listening level of the target user for each phase. The listening level is a truth value that indicates whether or not there is a response to the policy. The listening level data is the same data as the policy response data.

Returning to FIG. 4, in step S5, the characteristic determination unit 115 included in the characteristic estimation device 10 calculates a purchasing velocity score from purchasing velocity data related to the target user. The purchasing velocity score is calculated by multiple regression analysis of the purchasing velocity data. Next, the characteristic determination unit 115 calculates a listening degree score from listening degree data related to the target user. The listening degree score is calculated by multiple regression analysis of the listening degree data.

Figure 15 is a conceptual diagram showing an example of a purchasing speed score and a listening level score. As shown in Figure 15, the purchasing speed score is an index that represents the overall purchasing speed of the target user regardless of the phase. Also, the listening level score is an index that represents the overall listening level of the target user regardless of the phase.

Returning to FIG. 4, in step S6, the characteristic determination unit 115 included in the characteristic estimation device 10 reads out the characteristic determination rules from the characteristic determination rule table stored in the characteristic determination rule storage unit 108. Then, the characteristic determination unit 115 identifies the consumption behavior characteristic that corresponds to the combination of the purchase speed score and the listening level score, thereby determining the consumption behavior characteristic of the target user.

Characteristic determination rule table
The characteristic determination rule table in this embodiment will be described with reference to Fig. 16. Fig. 16 is a conceptual diagram showing an example of the characteristic determination rule table in this embodiment.

As shown in FIG. 16, the characteristic determination rule table in this embodiment has consumption behavior characteristics, purchase speed scores, listening level scores, etc. as data items. The purchase speed scores and listening level scores are set within a score range, and are set so that a unique consumption behavior characteristic is determined for a certain combination of purchase speed scores and listening level scores. In other words, the characteristic determination rule is a rule that associates a combination of purchase speed scores and listening level scores with a consumption behavior characteristic.

The characteristic determination unit 115 outputs the estimated result of the consumption behavior characteristic for the target user. The characteristic estimation device 10 transmits the estimated result of the consumption behavior characteristic output by the characteristic determination unit 115 to the user terminal 20. The user terminal 20 receives the estimated result of the consumption behavior characteristic from the characteristic estimation device 10 and displays it on the display device 506 or the like.

Figure 17 is a conceptual diagram showing an example of a consumption behavior characteristic estimation result. As shown in Figure 17, the consumption behavior characteristic estimation result is information that lists consumption behavior characteristics estimated for each target user. The estimation result displayed by the user terminal 20 may be information that is obtained by processing the estimation result received from the characteristic estimation device 10. For example, the estimation result may be a list of target users who are estimated to have a consumption behavior characteristic specified by the user.

Effects of the embodiment
The consumer behavior characteristic estimation system in this embodiment estimates purchase speed data and listening level data for a target user based on the user's web browsing history and the user's consumption behavior performance, and estimates the consumer behavior characteristics of the target user based on the purchase speed data and listening level data. Therefore, the consumer behavior characteristic estimation system in this embodiment can estimate the consumer behavior characteristics of the target user based on performance data that represents the consumer behavior of the target user.

The consumer behavior characteristic estimation system in this embodiment estimates purchase speed data and listening level data used to determine consumer behavior characteristics based on web browsing history and consumer behavior performance data. In other words, the consumer behavior characteristic estimation system in this embodiment determines consumer behavior characteristics based on existing performance data. Therefore, there is no need to obtain new information about new target users. Therefore, the consumer behavior characteristic estimation system in this embodiment can estimate the consumer behavior characteristics of target users in real time.

For example, the invention disclosed in Patent Document 1 requires new survey results to be obtained in order to estimate the characteristics of new users. As a result, the invention disclosed in Patent Document 1 has a high inflow and outflow of unspecified users, making it difficult to apply to tasks that require real-time performance.

[supplement]
Each function of the above-described embodiments can be realized by one or more processing circuits. Here, the term "processing circuit" in this specification includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, and an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), a conventional circuit module, and other devices designed to execute each function described above.

Although the embodiments of the present invention have been described in detail above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

1 Consumer behavior characteristic estimation system 10 Characteristic estimation device 101 Site classification master storage unit 102 Web browsing history storage unit 103 Customer master storage unit 104 Subject master storage unit 105 Contact medium data storage unit 106 Product purchase data storage unit 107 Policy response data storage unit 108 Characteristic determination rule storage unit 111 Browsing history classification unit 112 Subject extraction unit 113 Performance data acquisition unit 114 Consumer behavior estimation unit 115 Characteristic determination unit 20 User terminal

Claims (5)

a target user extraction unit configured to extract target users based on web browsing histories;
a performance data acquisition unit configured to acquire consumer behavior performance data including at least one of product purchase data relating to the performance of the target user in purchasing a commodity and promotion response data indicating whether or not the target user has responded to a sales promotion campaign ;
a consumer behavior estimation unit configured to estimate, based on the web browsing history and the consumer behavior result data, purchase speed data representing the time it takes to make a purchase for each stage that classifies the degree of interest of the target user in a product , and listening level data representing the presence or absence of a reaction to the sales promotion measure for each stage ;
A characteristic determination unit configured to determine a consumption behavior characteristic of the target user based on the purchasing speed data and the listening level data;
A characteristic estimation device comprising: The characteristic estimation device according to claim 1 ,
the consumption behavior estimation unit is configured to estimate the purchasing speed data and the listening level data of the target user by multiple regression analysis of data in which a correct value of the purchasing speed data and a correct value of the listening level data are assigned to the web browsing history and the consumption behavior result data,
Characteristic estimation device. The characteristic estimation device according to claim 2 ,
The characteristic determination unit is configured to determine the consumption behavior characteristic of the target user according to a characteristic determination rule that associates a combination of a purchase speed score calculated from the purchase speed data and a listening degree score calculated from the listening degree data with the consumption behavior characteristic.
Characteristic estimation device. The computer
Extracting target users based on their web browsing history;
acquiring consumer behavior record data including at least one of product purchase data relating to the target user's record of purchasing a product and promotion response data indicating whether or not the target user has responded to a sales promotion campaign ;
a step of estimating, based on the web browsing history and the consumer behavior result data, purchase speed data representing the time it takes to make a purchase for each stage of the target user's interest in a product, and listening level data representing the presence or absence of a reaction to the sales promotion measures for each stage ;
determining consumption behavior characteristics of the target user based on the purchasing speed data and the listening level data;
A characteristic estimation method that performs On the computer,
Extracting target users based on their web browsing history;
A step of acquiring consumer behavior record data including at least one of product purchase data relating to the target user's record of purchasing a product and promotion response data indicating whether or not the target user has responded to a sales promotion campaign;
a step of estimating, based on the web browsing history and the consumer behavior result data, purchase speed data representing the time it takes to make a purchase for each stage of the target user's interest in a product, and listening level data representing the presence or absence of a reaction to the sales promotion measures for each stage ;
determining consumption behavior characteristics of the target user based on the purchasing speed data and the listening level data;
A program for executing the above.

Images