JP7540987B2 - 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.

In recent years, with the rapid spread of the Internet, technology that allows companies to develop various campaigns by targeting users who match the conditions specified by the company has become widespread. For example, a technology has been proposed that identifies the subjects of each user's interest or concern by analyzing each user's query log (see, for example, Patent Document 1).

JP 2021-149694 A

However, conventional technology does not take into account, for example, how each user's interests and concerns change.

The present invention has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can provide content related to the transitions in the interests and concerns of each user.

In order to solve the above-mentioned problems and achieve the object, the information processing device according to the present invention includes an acquisition unit that acquires a behavioral history of a user who has taken a predetermined action, a calculation unit that calculates an interest score for each action by quantifying the interest of the user in a specific target from each piece of divided data obtained by dividing the behavioral history acquired by the acquisition unit into a predetermined period, and a provision unit that provides score information indicating the fluctuation of the interest score for each action calculated by the calculation unit.

The present invention makes it possible to provide content related to the transitions in each user's interests and concerns.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. FIG. 3 is a diagram illustrating an example of information stored in a user information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of information stored in a model storage unit according to the embodiment. FIG. 5 is a diagram showing an example of a screen for receiving input of generation conditions. FIG. 6 is a diagram showing an example of a screen for receiving input of generation conditions. FIG. 7 is a flowchart illustrating an example of a processing procedure of a model generation process according to the embodiment. FIG. 8 is a flowchart illustrating an example of a processing procedure of the score information providing process according to the embodiment. FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

Below, the information processing device, information processing method, and information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to these embodiments.

[Embodiment]
[1. Information Processing]
First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing method is executed by, for example, an information processing device 10 shown in Fig. 1.

As shown in FIG. 1, the information processing device 10 according to the embodiment is an information processing device that cooperates with a portal site and calculates an interest score related to the interests of each user U using the behavioral history of each user U who uses the portal site.

For example, the information processing device 10 provides score information, which is content related to changes in interest scores, to the business operator terminal 500. For example, the business operator terminal 500 is a terminal device owned by each business operator, such as a company or a sole proprietor, and implements various campaigns for customers of each business operator according to the score information.

The user terminal 50 is a terminal device owned by a user U who uses the portal site. Examples of the user terminal 50 include a smartphone, a tablet terminal, a personal computer, and a wearable terminal.

In the example shown in FIG. 1, the portal site includes a search log server 101 that provides a search service and a shopping server 102 that operates a shopping site. In addition to the above, the portal site may also include servers that provide a variety of other services, such as a news site, a social networking site, and a real estate site.

By the way, for example, if a business operator were to run an individual campaign for customers who purchased one of its products, it would need to properly understand how the interests of each customer change after purchasing the product.

As a more specific example, if information is available on the timing at which customers who have purchased a single-lens reflex camera become interested in single-lens lenses, a campaign for single-lens lenses can be run at such timing, making the campaign more efficient.

On the other hand, for example, businesses often do not have sufficient knowledge about information related to these changes in interests, leaving room for improvement in terms of making campaigns more efficient or increasing customer satisfaction.

In response to this, the information processing device 10 according to the embodiment divides the portal site behavior history of a user U who has taken a predetermined action into predetermined time periods, and calculates and provides an interest score that quantifies interest from each divided behavior history.

Note that, in the following, a case will be described in which the action is the purchase of a specific item on a portal site, but the action may also be, for example, viewing a specific item on a portal site, adding it to a cart, or the user U actually visiting a store. Note that in this case, for example, the information processing device 10 may use the location information of the user terminal 50 to recognize that the user U has visited a store.

For example, when user U uses a portal site via user terminal 50 (step S01), the portal site accumulates the usage history of user U. Then, information processing device 10 acquires the usage history of each user U from the servers operating each portal site (in the example of FIG. 1, search log server 101 and shopping server 102) (step S02).

The information processing device 10 generates a model using the search log of the user U who took a predetermined action from the acquired usage history (step S03). The example shown in the figure illustrates the case of generating a model for a man in his 30s who purchased a single-lens reflex camera.

The model here is a model that learns how the interests of a man in his 30s who has purchased a single-lens reflex camera change after the purchase. For example, in the model learning stage, the information processing device 10 first identifies a user U who has purchased a single-lens reflex camera from the usage history of the shopping server 102, and divides the search log from the purchase of the single-lens reflex camera as the starting point t0 up to a predetermined period tn into n parts.

Then, for example, the information processing device 10 generates a model by machine learning using the divided search log and the elapsed time period. For example, in the above example, a model is generated for each purchased item x demographic attribute, and the generated model is stored in the model storage unit of the information processing device 10. Note that, although a case where a model is generated using a search log has been described here, this is not limited to this, and for example, a model may be generated using an access log to news or information media, a posting history to SNS, or a browsing history.

Then, the information processing device 10 uses the model to calculate an interest score for each elapsed period, for example, based on conditions specified by the business operator terminal 500 (step S04). For example, conditions such as "purchased item," "male in his 30s," and "product for which a campaign is planned (for example, a single-lens lens or other company product)" can be specified by the business operator terminal 500, and the information processing device 10 calculates an interest score for each elapsed period based on these conditions.

Next, the information processing device 10 generates score information regarding the interest score for each elapsed period (step S05) and provides the generated score information to the business terminal 500 (step S06).

This allows businesses to know the trends in interest scores, making it easier for them to know when and for which demographics they should target campaigns.

In this way, in the information processing device 10 according to the embodiment, for example, the usage history of the portal site is divided into time periods, and an interest score is calculated from the usage history for each divided period.

As a result, the information processing device 10 according to the embodiment can provide content related to the transitions in the interests and concerns of each user U. Note that, in the above example, a case where a model is generated for each demographic attribute has been described, but a model may also be generated for each of a predetermined common attribute of user U, such as place of residence (prefecture/city/town/mesh) or occupation. This makes it possible to provide content related to the transitions in interest scores for each of such common attributes.

2. Example of the configuration of an information processing device
Next, a configuration example of the information processing device 10 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing device 10 according to the embodiment. As shown in Fig. 2, the information processing device 10 has a communication unit 110, a control unit 120, and a storage unit 130.

The communication unit 110 is realized, for example, by a NIC (Network Interface Card) or the like. The communication unit 110 transmits and receives information to and from an external device via a network such as various wireless communication networks, such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or a wireless LAN (Local Area Network), or various wired communication networks.

The storage unit 130 is realized, for example, by a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 130 also has a user information storage unit 131 and a model storage unit 132.

The user information storage unit 131 is a storage unit that stores information about a user U who uses the portal site. FIG. 3 is a diagram showing an example of information stored in the user information storage unit 131 according to the embodiment.

As shown in FIG. 3, for example, the user information storage unit 131 stores information on items such as "user ID," "demographic attributes," "purchase history," and "search history" in association with each other.

"User ID" is an identifier for identifying each user. "Demographic attributes" is information regarding the demographic attributes of user U identified by the corresponding user ID. Note that demographic attributes here may include demographic attributes of each user U, such as age, gender, residential area, educational background, family structure, place of employment, annual income, etc.

"Purchase history" is information about the purchase history of products purchased on the portal site by user U, who is identified by the corresponding user ID. For example, "purchase history" stores information about the purchased products, the purchase date and time, the store where the purchase was made, etc.

"Search history" is information about the search history (search log) performed on the portal site by a user U identified by the corresponding user ID. For example, "search history" stores information about the search query entered by user U and the date and time of the search.

Returning to the explanation of FIG. 2, the model storage unit 132 will be described. The model storage unit 132 is a storage unit that stores a model for calculating the transition of the interest score. FIG. 4 is a diagram showing an example of information stored in the model storage unit 132 according to an embodiment.

As shown in FIG. 4, for example, the model storage unit 132 stores information on items such as "purchased item," "attribute type," and "score model" in association with each other. "Purchased item" is an identifier for identifying an item purchased by user U. Note that the purchased item may be information for identifying the category, price range, or grade of the corresponding item. "Attribute type" is an identifier for identifying the demographic attribute that is the subject of the model.

The "score model" is a model for calculating the interest score of user U for the corresponding "purchased item" and "attribute type." The example shown in the figure indicates that models for the attribute types identified by "D1-1" and "D2-1" respectively for the purchased item identified by "UI001" are stored in the "score model."

Returning to the explanation of FIG. 2, the control unit 120 will be described. The control unit 120 is, for example, a controller, and is realized by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., executing various programs stored in a storage device inside the information processing device 10 using the RAM as a working area.

As shown in FIG. 2, the control unit 120 has an acquisition unit 121, a generation unit 122, a reception unit 123, a calculation unit 124, and a provision unit 125. The acquisition unit 121 acquires the behavior history of a user U who has taken a predetermined action.

In this embodiment, the acquisition unit 121 acquires the portal site usage history of a user U who has purchased a product on the portal site, and stores the history in the user information storage unit 131. For example, the acquisition unit 121 acquires a search log from the search log server 101, and acquires a purchase history from the shopping server 102.

The acquisition unit 121 may acquire search logs of all users U, for example, the search log of a user U who has purchased a specific item.

The generation unit 122 generates a model for calculating an interest score that quantifies the interest of a user U who has taken a predetermined action. For example, in the model learning stage, the generation unit 122 generates split data by dividing the usage history of the portal site after the user U purchased a product by the elapsed period (for example, one month).

Next, the generation unit 122 performs machine learning by associating information for each elapsed period with each piece of split data, thereby generating a model that learns the relationship between the elapsed period and the search log, i.e., the relationship between the elapsed period and the interests of user U.

For example, the generation unit 122 generates a model for each purchased item and demographic attribute, and stores the generated model in the model storage unit 132.

The reception unit 123 receives, for example, the conditions for generating score information from the business operator terminal 500, and passes information on the received conditions for generating score information to the calculation unit 124. Specific examples of the conditions for generating score information will be described later with reference to FIG. 5 and FIG. 6.

The calculation unit 124 calculates an interest score for each action by quantifying the interest of the user U in a specific target from each of the divided data obtained by dividing the behavioral history acquired by the acquisition unit 121 into predetermined periods.

The calculation unit 124 calculates an interest score using the model stored in the model storage unit 132 according to the generation conditions specified by the business operator terminal 500 received from the reception unit 123, and passes the interest score to the provision unit 125.

The providing unit 125 provides the business operator terminal 500 with score information indicating the change in the interest score calculated by the calculating unit 124. Here, a series of processes of the receiving unit 123, the calculating unit 124, and the providing unit 125 will be described with reference to Figs. 5 and 6.

Figures 5 and 6 are diagrams showing examples of screens that accept input of generation conditions. For example, the information processing device 10 provides a UI as shown in Figure 5 and accepts the generation conditions of score information from the business operator terminal 500.

The example shown in FIG. 5 shows a case where generation conditions for items such as "purchased item," "demographic attribute," and "target product" are accepted. "Purchased item" indicates the name of the item purchased by user U, and "demographic attribute" indicates the demographic attribute for which score information is to be generated.

The "target item" indicates the item for which the interest score is calculated. In the example shown in the figure, the purchased item is a single-lens reflex camera, the demographic attributes are 30s and male, and the target item is a single-lens lens.

That is, in this case, the change in the interest score for a single-lens reflex camera of a man in his 30s who purchased the camera is provided to the business operator terminal 500 as score information. For example, the reception unit 123 receives the conditions for generating score information via a UI such as that shown in FIG. 5, and the calculation unit 124 calculates the interest score for the target item of the specified demographic attribute for each period using a model according to the generation conditions.

The providing unit 125 then provides the business operator terminal 500 with score information indicating the change in interest score for each period calculated by the calculation unit 124. The example of score information shown in the figure indicates that interest in single-lens lenses is highest at time t11, and the business operator can efficiently implement a campaign related to single-lens lenses by running the campaign at time t11.

For example, if there is no model corresponding to the purchased item, the interest score may be calculated using a model of another similar purchased item, or the interest score may be calculated using a model of a higher-level category corresponding to the purchased item.

Purchased items may be classified into product categories, or may be subdivided into categories such as product manufacturer, price range, and grade. In other words, for example, even for single-lens reflex cameras, models may be generated for each manufacturer, price range, and grade, and an interest score may then be calculated.

In this case, for example, the business operator terminal 500 can specify different generation conditions to check the difference in interest score trends depending on the manufacturer, price range, and grade. In other words, by checking the difference in interest score trends between a competitor's product and the company's own product, it is possible to receive information that is useful not only for the efficiency of campaigns but also for product development. In this case, multiple score information may be provided by superimposing them on the same graph.

The example in FIG. 6 shows a case where "psychographic attributes" are received instead of the target item. Here, "psychographic attributes" are psychological attributes such as hobbies, preferences, lifestyle, etc., and in the following, "psychographic attributes" are assumed to indicate hobbies. Note that psychographic attributes may be derived, for example, from the usage history of the portal site, or the results of a survey conducted on user U may be used.

In the example shown in the figure, "car" is selected as the "psychographic attribute." In other words, in this case, information on the change in interest score of a car-loving man in his 30s who purchased a single-lens reflex camera is provided as score information.

In this way, for example, by further limiting "psychographic attributes" and generating and providing score information, it becomes possible to implement appropriate campaigns according to psychographic attributes.

3. Processing Procedure
Next, a process procedure executed by the information processing device 10 according to the embodiment will be described with reference to Fig. 7 and Fig. 8. Fig. 7 is a flowchart showing an example of a process procedure of a model generation process according to the embodiment. Fig. 8 is a flowchart showing an example of a process procedure of a score information provision process according to the embodiment.

As shown in FIG. 7, for example, the information processing device 10 acquires the usage history of a portal site of a user U who has taken a predetermined action (step S101). Next, the information processing device 10 calculates an interest score from each of the usage histories for each period (step S102).

Next, the information processing device 10 updates the model using the interest scores for each period (step S103). Then, the information processing device 10 ends the model generation process.

Next, as shown in FIG. 8, the information processing device 10 accepts the conditions for generating score information (step S111). Next, the information processing device 10 calculates the interest score for each elapsed period using a model according to the generation conditions (step S112).

Next, the information processing device 10 provides score information regarding the change in the interest score for each elapsed period (step S113). Then, the information processing device 10 ends the score information provision process.

4. Modifications
In the above embodiment, the transition of the interest score after the user U purchases a product is provided as score information, but the present invention is not limited to this. A series of transitions of the interest score before and after the product purchase may be provided as score information.

In the above embodiment, a case has been described in which information relating to a series of changes in the interest score is provided as score information, but the present invention is not limited to this. For example, information relating to the period when the interest score is highest and the period when the interest score is lowest may be provided as score information. Also, for example, interest scores corresponding to multiple demographic attributes may be automatically calculated using a model corresponding to multiple demographic attributes, and information indicating characteristic changes in the interest score due to, for example, age differences or regional differences may be provided as score information.

For example, for each demographic attribute, if there is a change in the trend of interest scores at the age of 50, then there may be a change in the trend of interest scores between urban and rural areas, and the analysis results may be provided as score information.

In the above-described embodiment, for example, a case has been described in which the interest score is calculated from a search log related to a user U who has purchased one item, but this is not limited to this. For example, the interest score may be calculated using a search log related to a user U who has purchased multiple items. In this case, for example, the information processing device 10 can provide score information related to a user U who has purchased product A and product B.

In the above embodiment, a case has been described in which information regarding changes in interest scores is provided as score information, but this is not limited to this. For example, the calculation unit 124 may calculate a vector indicating the characteristics of interests for each elapsed period, and the provision unit 125 may provide information regarding changes in the vector as score information. Note that the vector here refers to data obtained by reducing search logs to N-dimensional (e.g., 128-dimensional) data. Even in this case, the business operator can grasp the trends in the interests of user U from the changes in the vector.

5. Effects
The information processing device 10 according to the embodiment described above includes an acquisition unit 121 that acquires a behavioral history of a user U who has taken a predetermined action, a calculation unit 124 that calculates an interest score for each action by quantifying the user's interest in a specific target from each piece of divided data obtained by dividing the behavioral history acquired by the acquisition unit 121 for each predetermined period, and a provision unit 125 that provides score information indicating the fluctuation of the interest score for each action calculated by the calculation unit 124. Therefore, the information processing device 10 according to the embodiment can provide content related to the transition of the interests and concerns of each user.

The calculation unit 124 according to the embodiment described above calculates an interest score for each item from the behavioral history of a user who has purchased a specific item. Therefore, according to the information processing device 10 according to the embodiment, it is possible to provide content related to the changes in the interests of a user U who has purchased a specific item.

The calculation unit 124 according to the embodiment described above calculates an interest score for a product designated by a business as a specific target. Therefore, the information processing device 10 according to the embodiment can provide content related to the changes in the interest of the user U in products desired by the business.

The acquisition unit 121 according to the embodiment described above acquires a search history on a portal site as a behavior history, and the calculation unit 124 calculates an interest score from the search history. Therefore, according to the information processing device 10 according to the embodiment, it is possible to accurately calculate an interest score.

The acquisition unit 121 according to the embodiment described above acquires information related to the demographic attributes of the user by linking it to the behavioral history, and the calculation unit 124 calculates an interest score for each demographic attribute. Therefore, according to the information processing device 10 according to the embodiment, it is possible to provide content related to changes in the interests of the user U according to the demographic attributes.

The providing unit 125 according to the embodiment described above provides information on the time series changes in the interest score as score information. Therefore, according to the information processing device 10 according to the embodiment, it is possible to provide content that allows the user U to easily grasp the time series changes in the interest score.

The calculation unit 124 according to the embodiment described above calculates a vector indicating the characteristics of interests for each period from the behavioral history of the user U, and the provision unit 125 provides information on the fluctuation of the vector as score information. Therefore, according to the information processing device 10 according to the embodiment, it is possible to grasp the trends in the interests of the user U from the change in the vector.

6. Hardware Configuration
The information processing device 10 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each component. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, and programs that depend on the hardware of the computer 1000, etc.

HDD 1400 stores programs executed by CPU 1100 and data used by such programs. Communication interface 1500 receives data from other devices via network (communication network) N and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via network N.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 9, the output devices and input devices are collectively referred to as "input/output devices") via the input/output interface 1600. The CPU 1100 acquires data from the input devices via the input/output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input/output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

For example, when the computer 1000 functions as the information processing device 10 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 120. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the disclosure section of the invention.

[7. Other]
Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

The above-described embodiments and variations can be combined as appropriate to the extent that they do not cause inconsistencies in the processing content.

The above-mentioned "section, module, unit" can be read as "means" or "circuit." For example, an acquisition unit can be read as an acquisition means or an acquisition circuit.

10 Information processing device 50 User terminal 101 Search log server 102 Shopping server 110 Communication unit 120 Control unit 121 Acquisition unit 122 Generation unit 123 Reception unit 124 Calculation unit 125 Provision unit 130 Storage unit 131 User information storage unit 132 Model storage unit 500 Business operator terminal

Claims (9)

an acquisition unit that acquires a behavior history of a user who has taken a predetermined action in the online shopping mall ;
a calculation unit that calculates an interest score by quantifying an interest of the user in a specific target specified from each of divided data obtained by dividing the behavior history acquired by the acquisition unit for each predetermined period;
a providing unit that provides score information indicating a change in the interest score calculated by the calculating unit. The calculation unit is
The information processing apparatus according to claim 1 , wherein the interest score is calculated for each of the items from the behavior history of the user who has purchased a predetermined item as the predetermined action . The calculation unit is
The information processing device according to claim 1 , further comprising: a processor configured to calculate the interest score for a product designated by a business operator as the specific target. The acquisition unit is
A search history on a portal site is acquired as the behavior history,
The calculation unit is
The information processing device according to claim 1 , 2 or 3 , wherein the interest score is calculated from the search history. The acquisition unit is
Acquire information on demographic attributes of the user by linking it to the behavioral history;
The calculation unit is
5. The information processing device according to claim 1, further comprising: a processor configured to calculate the interest score for each of the demographic attributes. The providing unit is
6. The information processing device according to claim 1, wherein the score information is information relating to a time series change in the interest score. The calculation unit is
Calculating a vector indicating an interest characteristic for each of the time periods from the behavioral history of the user;
The providing unit is
7. The information processing device according to claim 1, wherein information relating to a variation in the vector is provided as the score information. 1. A computer-implemented information processing method, comprising:
An acquisition step of acquiring a behavior history of a user who has taken a predetermined action in the online shopping mall ;
a calculation step of calculating an interest score by quantifying the interest of the user in a specific target specified from each of divided data obtained by dividing the behavioral history acquired by the acquisition step for each predetermined period;
and a providing step of providing score information indicating a change in the interest score calculated by the calculating step. An acquisition step for acquiring a behavior history of a user who has taken a predetermined action in the online shopping mall ;
a calculation step of calculating an interest score by quantifying an interest of the user in a specific target specified from each of divided data obtained by dividing the behavior history acquired by the acquisition step for each predetermined period;
and a providing step of providing score information indicating a change in the interest score calculated by the calculating step.

Images