Information processing device, information processing method, and information processing program

Abstract

To provide an information processor, an information processing method, and an information processing program that can deliver information that is likely to interest a user.SOLUTION: An information processor according to the present application includes a learning unit and a generation unit. The learning unit receives delivery information as input and learns a model, which is trained as a dataset of delivery information delivered to a user in first service and an interest of the user on the delivered information estimated on the basis of behavior of the user related to the delivered information in second service, that outputs an improvement plan for the delivery information that the user is interested in. The generation unit inputs the delivery information received from a delivery source into the model, and generates improvement information on the basis of an improvement proposal output from the model.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, various techniques for providing information to users have been proposed. For example, a technique has been proposed in which a category in which a user is interested is identified and advertisements related to the identified category are delivered. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-099631 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology has room for further improvement in terms of delivering information that is more likely to interest users.

[0005] The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can deliver information that is likely to interest users. [Means for solving the problem]

[0006] The information processing device according to the present application includes a learning unit and a generating unit. The learning unit trains a model that uses, as a data set, distribution information distributed to a user via a first service and the user's interest in the distribution information estimated based on the user's behavior related to the distribution information via a second service, and that receives the distribution information as input and outputs improvement suggestions for the distribution information in which the user is interested. The generating unit inputs the distribution information received from a distribution source to the model and generates improvement information based on the improvement suggestions output from the model. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to deliver information that is likely to interest users. [Brief explanation of the drawings]

[0008] [Figure 1A] FIG. 1A is a diagram showing a process executed by an information processing apparatus according to an embodiment. [Figure 1B] FIG. 1B is a diagram showing a process executed by the information processing apparatus according to the embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of user information. [Figure 5] FIG. 5 is a diagram illustrating an example of model information. [Figure 6] FIG. 6 is a flowchart illustrating the processing procedure of the interest estimation process executed by the information processing device according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating the processing procedure of the improvement information generation processing executed by the information processing apparatus according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] (Embodiment) First, a process executed by an information processing device according to an embodiment will be described with reference to FIGS. 1A and 1B. FIGS. 1A and 1B are diagrams showing a process executed by an information processing device according to an embodiment. FIG. 1A describes a user interest estimation process, and FIG. 1B describes a distribution information generation process. FIGS. 1A and 1B show an example of the operation of an information processing system S including an information processing device 1 according to an embodiment. In the following description, the first service is a dialogue service through a chatbot, but is not limited to this and may be any service that delivers information from AI (Artificial Intelligence) to a user. The second service is a service different from the first service, such as a search service, shopping service, or auction service. The second service may be any service that provides predetermined information as a result of an action taken by a user.

[0011] As shown in FIGS. 1A and 1B, an information processing system S according to the embodiment includes an information processing device 1, a client terminal 50, a user terminal 100, and a log server 200.

[0012] First, a user interest estimation process will be described with reference to Fig. 1A. The information processing system S shown in Fig. 1A identifies related actions related to related words performed by the user in a second service based on related words related to distribution information distributed to the user in a first service, and estimates the user's interest in the distribution information based on the identified related actions.

[0013] Specifically, first, the requester terminal 50 receives a request for distribution of distribution information to a user in response to an operation by the requester (step S1). The distribution request includes the distribution information. The distribution information is, for example, advertising content.

[0014] Next, the information processing device 1 distributes the received distribution information to the user terminal 100 (step S2). In FIG. 1A, in the interactive service that is the first service, when a user inputs "Tell me about sales information" to the official account of AA Shop via the user terminal 100, the chatbot distributes the distribution information in response. Note that the distribution information is not limited to information that is distributed in response to a user's action, but may also be distributed spontaneously from the chatbot via a push notification.

[0015] Next, the information processing device 1 acquires an action log of the user terminal 100 of the user from the log server 200 (step S3). The action log is a history of actions in the second service, such as search actions, purchasing actions, and the like.

[0016] Next, the information processing device 1 identifies related actions performed by the user in the second service based on related words related to the distribution information, based on the acquired behavior log (step S4). The related words are, for example, words included in the distribution information (e.g., "ultimate pants" or "pants made of new material") or words associated with words included in the distribution information (e.g., "AA shop new pants"). For example, the information processing device 1 identifies related actions as performed when a search is performed by entering related words in a search query in the search service, which is the second service. Furthermore, the information processing device 1 identifies these actions as related actions when a user searches for, browses, or purchases a product related to the related words in the shopping service, which is the second service.

[0017] Next, the information processing device 1 estimates interest in the distributed information based on the related behavior (step S5). For example, the information processing device 1 estimates that the user is interested in the distributed information if the user performs the related behavior within a predetermined period from the time the distributed information is distributed (from the time the user views the information). Furthermore, the information processing device 1 estimates that the shorter the period from the time the distributed information is distributed (from the time the user views the information) to the time the user performs the related behavior, the stronger the degree of interest in the distributed information.

[0018] Next, when the information processing device 1 estimates that the user has an interest in the distribution information, it counts the distribution information as a conversion (CV) (step S6). Furthermore, when the information processing device 1 estimates that the user has an interest in the distribution information, the information processing device 1 may target the user for retargeting of the distribution information. For example, when the information processing device 1 searches for information about the tour content, venue, etc. based on tour information distributed on an artist's account, the information processing device 1 estimates that the user has an interest in the tour content and targets the user for retargeting. Furthermore, when the information processing device 1 searches for information about the current movie based on movie information distributed on the movie's official account, the information processing device 1 targets the user for retargeting and delivers the next movie to the user.

[0019] In this way, the information processing device 1 according to the embodiment can estimate the user's interests with high accuracy by identifying and determining related behaviors in the second service based on the distribution information distributed in the first service.

[0020] Next, the process of generating distribution information will be described with reference to Fig. 1B. In Fig. 1B, the process of generating distribution information is performed using the processing result of the interest estimation process performed in Fig. 1A.

[0021] 1B trains a model using data sets of distribution information distributed to a user in a first service and user interests in the distribution information estimated based on the user's actions related to the distribution information in a second service, inputs distribution information received from a distributor (requester) to the model, and generates improvement information based on an improvement plan output from the model.The information processing system S then generates (improves) the distribution information based on the generated improvement information.

[0022] Specifically, as shown in FIG. 1B, the information processing device 1 learns a model based on the distribution information that has been completely distributed and the interest estimation result of the distribution information (step S1). The model learns a dataset of distribution information distributed to a user in a first service and a user's interest in the distribution information estimated based on the user's behavior related to the distribution information (related behavior) in a second service. The model is a natural language processing model such as LLM (Large Language Models), and can output text, images, audio, etc.

[0023] Next, the information processing device 1 receives new distribution information from the requester terminal 50 (step S2). For example, the information processing device 1 may receive the distribution information included in a distribution request, or may receive the distribution information as a request for improving the distribution information.

[0024] Next, the information processing device 1 inputs the received distribution information into a model and outputs improvement proposals for the distribution information from the model (step S3). For example, the information processing device 1 outputs improvement proposals for the wording of words included in the distribution information and character format (font, size, position, etc.) in text format. The information processing device 1 also outputs improvement proposals for the display mode (color, size, etc.) of images included in the distribution information in text format.

[0025] Next, the information processing device 1 generates improvement information based on the improvement proposal (step S4) and provides it to the client terminal 50 (step S5). The improvement information is, for example, information in which the improvement proposal is itemized in text format. The improvement information may also be distribution information that reflects the improvement proposal.

[0026] In this way, the information processing device 1 according to the embodiment can make a model learn distribution information that is estimated to be of interest, thereby suggesting improvements to distribution information that is likely to interest the user. That is, the information processing device 1 according to the embodiment can deliver distribution information that is likely to interest the user.

[0027] Next, a configuration example of an information processing system S according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing system S according to an embodiment. As shown in Fig. 2, in the information processing system S according to an embodiment, an information processing device 1, a plurality of client terminals 50, a plurality of user terminals 100, and a log server 200 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0028] The information processing device 1 is a server device that executes an information processing method according to the embodiment. The information processing device 1 cooperates with a plurality of client terminals 50 and a plurality of user terminals 100, and provides API (Application Programming Interface) services for various applications (hereinafter referred to as apps) and various data to the plurality of client terminals 50 and the plurality of user terminals 100, and is realized by a server device, a cloud system, or the like.

[0029] Furthermore, the information processing device 1 may be an information processing device that provides some kind of online web service to a plurality of client terminals 50 and a plurality of user terminals 100. For example, the information processing device 1 may provide services such as internet connection, search services, SNS (Social Networking Service), electronic commerce (EC), electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route searches, route guidance, line information, operation information, and weather forecasts as web services. In practice, the information processing device 1 may cooperate with various servers that provide the above-mentioned web services and act as an intermediary for the web services or may be responsible for processing the web services.

[0030] The requester terminal 50 is a terminal device owned by a requester who requests distribution. The requester terminal 50 can be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The requester terminal 50 transmits various types of information to the information processing device 1 or the like, and receives information provided by the information processing device 1 or the like.

[0031] The user terminal 100 is a terminal device owned by a user who is the destination of distribution information. The user terminal 100 can be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The user terminal 100 transmits various types of information to the information processing device 1 or the like, and receives information provided by the information processing device 1 or the like.

[0032] The log server 200 is a server device that stores various log data of users and provides the log data to the information processing device 1. The log server 200 is not limited to a server device, and may be realized by a cloud system or the like.

[0033] Next, an example of the configuration of the information processing device 1 will be described with reference to FIG.

[0034] Fig. 3 is a diagram showing an example of the configuration of an information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes a reception unit 31, a distribution unit 32, an identification unit 33, an estimation unit 34, a learning unit 35, a generation unit 36, and a provision unit 37. The storage unit 4 stores user information 41 and model information 42.

[0035] The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 is connected to a network by wire or wirelessly.

[0036] The control unit 3 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a work area. The control unit 3 is also a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0037] The storage unit 4 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0038] The user information 41 is information about the user.

[0039] Fig. 4 is a diagram showing an example of user information 41. As shown in Fig. 4, the user information 41 includes items such as "user ID," "attribute information," "behavioral information," "acquired benefits," and "donation information."

[0040] "User ID" is identification information that identifies a user. "Attribute information" is information about a user's attributes. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavioral information" is information about the user's behavior history, including the history of various behaviors such as search behavior, purchasing behavior, and visiting behavior.

[0041] The model information 42 is information about a model that receives distribution information as input and outputs an improvement plan for the input distribution information.

[0042] Fig. 5 is a diagram showing an example of the model information 42. As shown in Fig. 5, the model information 42 includes items such as "model ID" and "model information".

[0043] The "model ID" is identification information for identifying a model. The "model information" is information related to the model, and includes, for example, input parameters and coefficients of the model. A model may be generated for each user attribute, for example.

[0044] Next, each function of the control unit 3 of the information processing device 1 (receiving unit 31, distribution unit 32, identification unit 33, estimation unit 34, learning unit 35, generation unit 36, and provision unit 37) will be described.

[0045] The receiving unit 31 receives various types of information. For example, the receiving unit 31 receives a distribution request for distribution information from the requester terminal 50. The distribution request includes the distribution information. The distribution information is, for example, advertising content.

[0046] The delivery unit 32 delivers the delivery information received by the reception unit 31 to the user terminal 100. For example, when a request for delivery information is received from the user terminal 100 in the interactive service that is the first service, the delivery unit 32 delivers the delivery information in response to the request. Note that the delivery information is not limited to information that is delivered in response to a user's action, and may be delivered spontaneously by a push notification.

[0047] The identification unit 33 identifies related behaviors performed by the user in the second service based on related words related to the distribution information. Specifically, the identification unit 33 acquires the user's behavior log from the log server 200 and identifies related behaviors based on the behavior log. The related words are, for example, words included in the distribution information or words associated with words included in the distribution information. For example, the identification unit 33 identifies related behaviors as performed when a search is performed by inputting related words into a search query in a search service, which is the second service. Furthermore, the identification unit 33 identifies these behaviors as related behaviors when a product related to the related words is searched for, viewed, or purchased in a shopping service, which is the second service.

[0048] The estimation unit 34 estimates an interest in the distribution information based on the related behavior identified by the identification unit 33. For example, the estimation unit 34 estimates that a user is interested in the distribution information if the user performs the related behavior within a predetermined period from the time the distribution information is distributed (from the time the user views the information). Furthermore, the estimation unit 34 estimates that the shorter the period from the time the distribution information is distributed (from the time the user views the information) to the performance of the related behavior, the stronger the degree of interest in the distribution information. When the estimation unit 34 estimates that a user is interested in the distribution information, it counts this as a conversion (CV) of the distribution information. Furthermore, when the estimation unit 34 estimates that a user is interested in the distribution information, the user may be a target for retargeting the distribution information.

[0049] The learning unit 35 learns a model using the distribution information for which distribution has been completed and the interest estimation result of the distribution information estimation unit 34. The model is trained using, as a data set, the distribution information distributed to the user in the first service and the user's interest in the distribution information estimated based on the behavior (related behavior) performed by the user in relation to the distribution information in the second service. The model is a natural language processing model such as LLM (Large Language Models), and is capable of outputting text, images, audio, etc.

[0050] The generation unit 36 ​​inputs distribution information received from the distribution source into the model, and generates improvement information based on the improvement proposal output from the model. The generation unit 36 ​​inputs distribution information newly received from the client terminal 50 into the model, and outputs an improvement proposal for the distribution information from the model (step S3). For example, the generation unit 36 ​​outputs, in text format, improvement proposals for the wording of words included in the distribution information and character format (font, size, position, etc.). The generation unit 36 ​​also outputs, in text format, improvement proposals for the display mode (color, size, etc.) of images included in the distribution information. The generation unit 36 ​​generates the improvement information based on the improvement proposal output from the model. The improvement information is, for example, information in which the improvement proposals are itemized in text format. The improvement information may also be distribution information that reflects the improvement proposals.

[0051] The providing unit 37 provides the improvement information generated by the generating unit 36 ​​to the requester terminal 50. This allows the requester to improve the distribution information that is likely to interest users. The providing unit 37 may also improve the distribution information based on the improvement information and distribute it to the user terminal 100, or provide the improved distribution information to the requester terminal 50.

[0052] Next, a processing procedure of processing executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 6 and Fig. 7. Fig. 6 is a flowchart showing the processing procedure of interest estimation processing executed by the information processing device 1 according to the embodiment. Fig. 7 is a flowchart showing the processing procedure of improvement information generation processing executed by the information processing device 1 according to the embodiment.

[0053] 6, the control unit 3 first distributes the distribution information received from the requester terminal 50 to the user terminal 100 (step S101). Note that the control unit 3 may distribute distribution information that has been improved based on the improvement information.

[0054] Next, the control unit 3 acquires the user's action log from the log server 200 after the distribution information is distributed (step S102).

[0055] Next, the control unit 3 identifies related actions performed based on related words related to the distribution information, based on the acquired action log (step S103).

[0056] Next, the control unit 3 estimates the user's interest in the distribution information based on the identified related behavior (step S104).

[0057] Next, when the control unit 3 determines that the user is interested in the distribution information, it counts the conversion for the distribution information (step S105) and ends the process.

[0058] Next, as shown in Fig. 7, the control unit 3 learns a model based on the distribution information distributed to the user and the interest estimation result in step 104 in Fig. 6 (step S201). This model is a model that receives the distribution information as an input and outputs an improvement plan for the distribution information.

[0059] Next, the control unit 3 receives new distribution information from the requester terminal 50 (step S202).

[0060] Next, the control unit 3 inputs the received distribution information into the model, and outputs an improvement proposal for the distribution information from the model (step S203).

[0061] Next, the control unit 3 generates improvement information based on the improvement plan output from the model (step S204).

[0062] Next, the control unit 3 provides the generated improvement information to the client terminal 50 (step S205), and ends the process. Note that the control unit 3 may improve the distribution information based on the improvement information and distribute it to the user.

[0063] 〔others〕 Furthermore, among the processes described in the above embodiments, some of the processes described as being performed automatically can also be performed manually. Alternatively, all or some of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0064] Furthermore, the components of each device shown in the figure are conceptual functional components and do 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.

[0065] 3 may be held in a storage server or the like, rather than being held by each device. In this case, each device obtains various pieces of information by accessing the storage server.

[0066] [Hardware configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 8. Fig. 8 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090.

[0067] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, or the like.

[0068] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, scanner, etc., and is realized by a USB, etc.

[0069] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0070] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0071] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0072] For example, when the computer 1000 functions as the information processing device 1, the arithmetic unit 1030 of the computer 1000 executes a program loaded onto the primary storage device 1040, thereby realizing the functions of the control unit 3.

[0073] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes a receiving unit 31, an identifying unit 33, and an estimating unit 34. The receiving unit 31 receives distribution information distributed to a user in a first service. The identifying unit 33 identifies related behaviors performed by the user in a second service based on related words related to the distribution information. The estimating unit 34 estimates the user's interest in the distribution information based on the identified related behaviors. This configuration enables highly accurate estimation of the user's interest.

[0074] The information processing device 1 according to the embodiment also includes a learning unit 35 and a generation unit 36. The learning unit 35 learns a model that uses, as a data set, distribution information distributed to a user in a first service and a user's interest in distribution information estimated based on the user's behavior related to the distribution information in a second service. The learning unit 35 inputs the distribution information and trains the model that outputs improvement suggestions for distribution information that interest the user. The generation unit 36 ​​inputs distribution information received from a distribution source to the model and generates improvement information based on the improvement suggestions output from the model. This makes it possible to propose improvements to distribution information that is likely to interest users. In other words, the information processing device 1 according to the embodiment can deliver distribution information that is likely to interest users.

[0075] 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 implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0076] 〔others〕 Furthermore, among the processes described in the above embodiments, 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 using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0077] Furthermore, the components of each device shown in the figure are conceptual functional components and do 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.

[0078] Furthermore, the processes described in the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the process contents.

[0079] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, the control unit 3 can be read as control means or a control circuit. [Explanation of symbols]

[0080] 1. Information processing equipment 2. Communications Department 3. Control Unit 4 Storage section 31 Reception 32 Distribution Department 33 Specific part 34 Estimation part 35 Learning Department 36 Generation part 37 Providing Department 41 User Information 42 Model Information 50 Client terminal 100 user terminals 200 Log Server S Information Processing System

Claims

1. a learning unit that learns a model that is trained using, as a data set, distribution information distributed to a user in a first service and an estimated result that the user will be interested in the distribution information based on an action taken by the user in relation to the distribution information in a second service, and that receives the distribution information as an input and outputs an improvement plan for improving the distribution information to make the distribution information more likely to interest the user; a generation unit that inputs distribution information received from a distribution source into the model and generates improvement information based on the improvement plan output from the model; an identification unit that identifies a related behavior performed by the user in the second service based on a related word related to the distribution information; an estimation unit that estimates the user's interest in the distribution information based on the identified related behavior; Equipped with The learning unit The model is trained using the distribution information and the estimation result of the estimation unit as a data set. Information processing device.

2. a providing unit that provides the improvement information generated by the generating unit to the distribution source. The information processing device according to claim 1 .

3. The improvement information provided by the providing unit is This is information that lists the improvement proposals. The information processing device according to claim 2 .

4. The improvement information provided by the providing unit is The distribution information is improved based on the improvement proposal. The information processing device according to claim 2 .

5. The estimation unit If the related behavior is performed within a predetermined period after the distribution information is distributed to the user, it is estimated that the user is interested in the distribution information. The information processing device according to claim 4 .

6. the first service is an interactive service through a chatbot, The second service is a service that provides predetermined information as a result of an action taken by the user. The information processing device according to claim 1 .

7. The related behavior is: Search behavior or purchasing behavior on the second service The information processing device according to claim 4 .

8. The related words are: The word is included in the distribution information. The information processing device according to claim 4 .

9. The related words are: The word is associated with the word included in the distribution information. The information processing device according to claim 4 .

10. 1. A computer-implemented information processing method, comprising: a learning process for learning a model that is trained using, as a data set, distribution information distributed to a user in a first service and an estimated result of the user's interest in the distribution information based on the user's behavior in relation to the distribution information in a second service, the model inputting the distribution information and outputting an improvement plan for improving the distribution information to make the distribution information more likely to interest the user; a generation step of inputting distribution information received from a distribution source into the model and generating improvement information based on the improvement plan output from the model; an identifying step of identifying related behaviors performed by the user on the second service based on related words related to the distribution information; an estimation step of estimating the user's interest in the distribution information based on the identified related behavior; Including, The learning step includes: The model is trained using the distribution information and the estimation result of the estimation step as a data set. Information processing methods.

11. a learning procedure for learning a model that is trained using, as a data set, distribution information distributed to a user in a first service and an estimated result of the user's interest in the distribution information based on an action taken by the user in relation to the distribution information in a second service, the model inputting the distribution information and outputting an improvement proposal for improving the distribution information to distribution information that is likely to interest the user; a generation step of inputting distribution information received from a distribution source into the model and generating improvement information based on the improvement plan output from the model; an identification step of identifying related behaviors performed by the user on the second service based on related words related to the distribution information; an estimation step of estimating the user's interest in the distribution information based on the identified related behavior; on the computer, The learning procedure includes: The model is trained using the distribution information and the estimation results of the estimation procedure as a data set. Information processing program.

Images