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

Abstract

To distribute appropriate advertisements for users.SOLUTION: An information processing device 100 includes: an estimation unit 121 that estimates a user image of a user based on information of the user; a selection unit 122 that selects an advertisement based on the user image estimated by the estimation unit 121; a generation unit 123 that generates a sentence for a generation model so that the advertisement selected by the selection unit 122 is included in an answer; and an output unit 124 that outputs a sentence generated by the generation unit 123, to the generation model.SELECTED DRAWING: Figure 2

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, there are techniques for presenting answers to questions from users, and techniques for delivering advertisements related to questions from users. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6849982 [Patent Document 2] Japanese Patent Publication No. 2023-061663 Summary of the Invention [Problem to be solved by the invention]

[0004] In the conventional technology, it may not be possible to deliver an appropriate advertisement to a user. For example, in the conventional technology, advertisements related to keywords included in a sentence entered by a user or preset user attributes are delivered, and it may not be possible to deliver an advertisement to a user while taking into consideration the type of person the user is or the context. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems and achieve the objective, the information processing device is characterized by having an estimation unit that estimates a user image of a user based on information about the user, a selection unit that selects an advertisement based on the user image estimated by the estimation unit, a generation unit that generates a sentence for a generative model so that the advertisement selected by the selection unit is included in an answer, and an output unit that outputs the sentence generated by the generation unit to the generative model. [Effects of the Invention]

[0006] According to the present invention, it is possible to deliver advertisements appropriate to the user. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating an outline of the processing performed by the information processing device according to the embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of processing performed by the information processing apparatus according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of processing performed by the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of processing performed by the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of processing performed by the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of processing performed by the information processing device according to the embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of processing by the information processing device according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of a computer that executes an information processing program. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, with reference to the drawings, an information processing device, an information processing method, and an information processing program according to the present application will be described in detail. Note that the present invention is not limited to these embodiments. In addition, in the description of the drawings, the same parts are denoted by the same reference numerals, and duplicated explanations will be omitted.

[0009] [Introduction] First, an overview of the information processing device 100 will be described with reference to FIG. 1. FIG. 1 is a diagram illustrating an overview of the processing performed by the information processing device 100. Conventionally, generative models such as large-scale language models have been used to generate answers to questions from users. Also, there are technologies for delivering advertisements related to questions from users. However, with conventional technologies, there have been cases where it has not been possible to deliver advertisements appropriate to the user.

[0010] For example, when using conventional technology to deliver advertisements, advertisements related to keywords contained in a user's question or pre-set user attributes are simply delivered along with the answer to the user's question, and there was a problem in that it was not possible to select and deliver advertisements taking into account the type of person the user who asked the question or the context in which the user asked the question.

[0011] Therefore, the information processing device 100 according to this embodiment performs the following process. First, the information processing device 100 estimates the user profile of the user (FIG. 1(1)) who inputs a question (request) via an application, based on information about the user. Next, the information processing device 100 selects an advertisement (FIG. 1(2)) to be delivered based on the estimated user profile. Next, as shown in FIG. 1(3), the information processing device 100 generates a sentence for the generative model: "The user profile of the questioner is ~~~. Please answer the questioner including an advertisement. The question is as follows: '~~~~~~'" so that the selected advertisement is included in the answer from the generative model.

[0012] Then, the information processing device 100 outputs the generated sentence to the generative model. As a result, the information processing device 100 generates and outputs sentences to the generative model so as to respond including advertisements corresponding to the user's persona, thereby enabling delivery of advertisements appropriate for the user.

[0013] In other words, the information processing device 100 generates and outputs sentences for a generative model so that answers to user questions include advertisements that correspond to the estimated user persona, thereby providing the information the user is looking for as an answer and making it possible to deliver advertisements that the user wants or that the user has little psychological resistance to.

[0014] [Configuration of information processing device] Next, the configuration of the information processing device 100 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 2, the information processing device 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that these units may be held in a distributed manner in multiple devices. The processing of these units will be described below.

[0015] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and enables communication between an external device and the control unit 120 via a telecommunication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 110 enables communication between the external device and the control unit 120.

[0016] The storage unit 130 is realized by 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. Examples of information stored in the storage unit 130 include information about users, user profiles, information about advertisements, algorithms, learning data for machine learning, and learned models. Here, the information about users includes information such as a user ID, user attributes (age, gender, birthplace, place of residence, occupation, characteristic search keywords, etc.), personality (characteristics, values, worries, etc.), lifestyle (daily habits, consumption patterns, friendships, etc.), search history, browsing history, location information, conversational tendencies, conversation content, and context.

[0017] Here, the user profile is information that includes user attributes and indicates the characteristics of a user estimated from information about the user, and is a so-called persona. The user profile may also include a summary of conversations that the target user had over a predetermined period of time in the past. For example, the user profile of user A is "gender: male, age: 20, eats out with friends 3-5 times a month, is dissatisfied with the hassle of finding restaurants and making reservations, currently looking for a place to eat with user B." Here, the user profile may be stored as vector information. The user profile stored as vector information is updated as needed according to information about the user (for example, the content of conversations that the target user had).

[0018] Characteristic search keywords are search keywords of a specific user that are narrowed down based on information such as the number of searches, frequency of searches, and date and time of searches, such as the number of searches, frequency of searches, and recent search dates and times, in the user's search history. User attributes, personality, and lifestyle include not only those registered in advance, but also those inferred from conversation content (text entered on the application or content recognized by voice recognition). Context is information inferred from the context of the conversation, such as the flow of conversation.

[0019] As an example of context, if user A contacts a chat application and asks, "Have you decided on a restaurant for the weekend celebration?" and the next day user B contacts the chat application and says, "We're having yakiniku for the weekend celebration," it can be determined that "that" refers to the restaurant for the celebration based on the flow of the conversation. Note that the subject of context estimation is not limited to the content of the conversation, but includes all information about the user, such as search history, browsing history, and location information. Furthermore, the text and context of the conversation may be information that has been analyzed using natural language processing. Furthermore, information related to advertisements includes information such as advertisement IDs, advertisement types, budgets, periods, and targeting information (user attributes, keywords, conversational tendencies, context, etc.). Note that the information stored in the storage unit 130 is not limited to the above examples.

[0020] The control unit 120 is realized using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), or the like, and executes a processing program stored in a memory. As shown in Fig. 2, the control unit 120 has an estimation unit 121, a selection unit 122, a generation unit 123, and an output unit 124. Each unit of the control unit 120 will be described below.

[0021] The estimation unit 121 estimates a user image of a user based on information about the user. For example, the estimation unit 121 estimates the user image using one or more of the following information about the user: user attributes, search history, browsing history, location information, conversation content, conversation tendency, and context.

[0022] More specifically, the estimation unit 121 estimates the user profile of user A as "gender: male, age: 20s, occupation: university student, looking for a restaurant for a party, likes restaurant A" from the user attributes "gender: male, age: 20s, occupation: university student" and the context "looking for a restaurant for a party, likes restaurant A" as information about user A. Note that the user profile estimated by the estimation unit 121 is updated as needed according to information about the user (for example, the content of the conversation the target user had).

[0023] In addition, the estimation unit 121 estimates the user profile of user A as "gender: male, age: 30s, residence: Kanagawa" based on the user attributes "gender: male, age: 30s, residence: Kanagawa Prefecture, interested in tourist spots in Asakusa that can be visited by families" and the search history "Asakusa sightseeing family" as information about user A.

[0024] Furthermore, the estimation unit 121 estimates the user profile of user A as "gender: female, age: 20s, residence: Tokyo" from the user attributes "gender: female, age: 20s, residence: Tokyo", location information "Shibuya", browsing history "○○ popular cafes in Shibuya", and context "planning to go cafe hopping with friends".

[0025] Furthermore, the estimation unit 121 estimates a user image from information about the user using a model that has learned the relationship between information about the user and the user image. For example, the estimation unit 121 inputs information about the user into a learning model that takes information about the user as input and outputs a user image, and estimates the output result as the user image. For example, this model is stored in a server that processes information and is independently created by a business operator (Yahoo). Note that it is desirable to conceal input information, such as personal information, by performing learning so that the input information is not used as a new answer.

[0026] The selection unit 122 selects an advertisement based on the user image estimated by the estimation unit 121. For example, the selection unit 122 selects an advertisement that targets the user image estimated by the estimation unit 121 for advertisement delivery. For example, the selection unit 122 selects an advertisement that is posted targeting keywords corresponding to characteristic search keywords included in the user attributes of the user image estimated by the estimation unit 121. At this time, as an element for narrowing down the characteristic search keywords included in the user attributes of the user image, information such as the number of times, frequency, date and time searched by a certain user, such as search keywords searched by user A three or more times in the past week, can be used as appropriate.

[0027] More specifically, the selection unit 122 selects as an advertisement store A that targets the keyword "store A drinking party Shinjuku coupon" corresponding to the information on the characteristic search keywords "Shinjuku izakaya 5 or more people" and "store A coupon" of the user profile of user A estimated by the estimation unit 121.

[0028] As another example, the selection unit 122 compares the user image estimated by the estimation unit 121 with the targeting information of the advertisement, and selects an advertisement with a high degree of match between the user image and the targeting information of the advertisement.

[0029] More specifically, the selection unit 122 compares the information on the user profile of user A estimated by the estimation unit 121, "gender: male, age: 20s, occupation: university student, context: looking for a place to have a party, likes store A," with the targeting information of each advertisement, and selects store A with the highest matching rate (targeting information "university student, party, store A") as the advertisement. Note that the selection unit 122 may select the advertisement with the highest matching rate between the user profile and the targeting information of the advertisement, or may select a predetermined number of advertisements with the highest matching rate.

[0030] The generation unit 123 generates a sentence for the generative model so that the answer includes the advertisement selected by the selection unit 122. For example, the generation unit 123 generates a sentence including a sentence by the user, the user image estimated by the estimation unit 121, and the advertisement selected by the selection unit 122 as the sentence for the generative model.

[0031] More specifically, the generation unit 123 generates a sentence such as "User A's user image is '~~'. Please respond to User A including the selected advertisement A. The question is as follows: '~~~~~'" as a sentence for the generation model.

[0032] As another example, the generation unit 123 generates a sentence such as, as a sentence for the generation model, "Please answer the following questions based on the user image of user A. Also, please include the following advertisement sentence in your answer. The input from user A is as follows: "~~~~~" The user image of user A is as follows: "~~~~~" The advertisement is as follows: "~~~~~"."

[0033] At this time, the generation unit 123 can use any combination of advertisement information and user profile information (including user attributes) according to the purpose, such as "Please include in your response the keywords used in the selected advertisement as well as information on search keywords that are characteristic of the target user profile."

[0034] The output unit 124 outputs the sentences generated by the generation unit 123 to a generative model. For example, the output unit 124 outputs the sentences generated by the generation unit 123 to a trained large-scale language model that has been independently created by a business (Yahoo). It is desirable to keep input information, such as personal information, confidential by training the input information so that it will not be used as a new answer.

[0035] [Processing performed by information processing device] Next, an example of processing performed by the information processing device 100 according to the embodiment will be described with reference to Figures 3 to 7. Figures 3 to 7 are diagrams illustrating an example of processing performed by the information processing device 100 according to the embodiment.

[0036] First, as shown in Fig. 3, the information processing device 100 receives an input of a question from user A on an application, such as "Teach me how to write an XX report." Note that, although this example shows an example in which a question input from a user is received on an application used for communication, the information processing device 100 can receive an input of a question or request from a user in any format. For example, the information processing device 100 may receive an input of a question or request from a user in the form of voice recognition.

[0037] Next, the information processing device 100 estimates the user profile of user A who has received the input of the question. FIG. 4(1) is an example showing an exchange between user A and user B that took place on an application used for communication. As shown in FIG. 4(1), for example, an exchange such as "User A: Have you finished your report for XX seminar?", "User B: I still need it to advance to the next grade, so I need to put my all into finishing it. Let's have a party when I'm done," and "User A: That's great! By the way, store A that I went to the other day was great." is taking place between user A and user B on the application used for communication.

[0038] The estimation unit 121 of the information processing device 100 estimates the user profile of user A as "college student, looking for a place to have a party, likes store A" as shown in FIG. 4(2) from the context of the interaction on the application between user A and user B shown in FIG. 4(1) as information about the user.

[0039] Next, the selection unit 122 selects an advertisement that targets the advertisement delivery to the user image estimated by the estimation unit 121. More specifically, the selection unit 122 compares the information on the user image of user A estimated by the estimation unit 121, "college student, looking for a place to have a party, likes store A," with the targeting information of each advertisement, and selects an advertisement for store A that has a high degree of match between the user image and the targeting information of the advertisement (for example, store A's "targeting information: college student, party, store A").

[0040] Next, as shown in FIG. 5(1), the generation unit 123 generates a sentence including the question "Teach me how to write a XX report" from user A whose input has been accepted, the information on the user profile of user A "a college student, looking for a place to have a party, likes store A" estimated by the estimation unit 121, and the targeting information of the advertisement "store A" selected by the selection unit 122, as shown in FIG. 5(2). The sentence includes the question "Teach me how to write a XX report" from user A whose input has been accepted, the information on the user profile of user A "a college student, looking for a place to have a party, likes store A", and the targeting information of the advertisement "store A" selected by the selection unit 122.

[0041] At this time, the generation unit 123 may generate, as advertisement information, a sentence including content such as "Please answer by including the keyword in the advertisement and a search keyword characteristic of the user." Furthermore, the generation unit 123 may distribute coupon information targeted at the user profile of the questioner along with the answer. For example, the generation unit 123 distributes, along with the answer, a coupon targeted at the user profile of user A, the questioner, that is, "student."

[0042] Then, the output unit 124 outputs the sentences generated by the generation unit 123 to the generation model. For example, the output unit 124 outputs the sentences generated by the generation unit 123 to the large-scale language model, and the large-scale language model provides a response including the selected advertisement, such as "Here's how to write an XX report. · Organize the sections in the order of introduction, main body, conclusion, and references. · ~~~~~. · ~~~~~. · ~~~~~. By the way, I recommend Restaurant A for the after-party! Shall we make a reservation?" as shown in Fig. 6.

[0043] Furthermore, the question received by the information processing device 100 may be related to an image. For example, a case will be described in which a question such as "Show me a map of Tokyo Station" is input from user A on an application. The estimation unit 121 estimates the user profile of user A to be "hungry, frequently visits store A" based on user A's search history "Tokyo Station, lunch," current location information "○○, Marunouchi, Chiyoda-ku, Tokyo," past location information "△△, Marunouchi, Chiyoda-ku, Tokyo (address of store A)," and context "hungry."

[0044] Next, the selection unit 122 compares the information on the user profile of user A estimated by the estimation unit 121, "Looks hungry, frequently visits store A," with the targeting information of each advertisement, and selects an advertisement with a high degree of match between the user profile and the targeting information of the advertisement (for example, store A's "targeting information: frequent user of store A").

[0045] Next, the generation unit 123 generates a sentence including the question "Show me a map of Tokyo Station" from user A whose input has been accepted, the user image of user A "He looks hungry and frequently visits store A" estimated by the estimation unit 121, and the targeting information of the advertisement "Store A" selected by the selection unit 122, such as "User A's user image is 'He looks hungry and frequently visits store A'. Please respond to user A including the advertisement for store A. The question content is as follows: 'Show me a map of Tokyo Station'."

[0046] Then, the output unit 124 outputs the sentence generated by the generation unit 123 to the generation model. For example, the output unit 124 outputs the sentence to the large-scale language model. As a result, the large-scale language model provides a response including the selected advertisement A, such as "The map of the area around Tokyo Station is as follows. [Image] By the way, store A is currently distributing a coupon for XX. https: / / www.xxxxxxxx," as shown in FIG. 7.

[0047] As a result, the information processing device 100 generates and outputs sentences for the generative model that include advertisements that correspond to the user's persona, enabling delivery of advertisements appropriate to the user. In other words, it is possible to provide information desired by the user as an answer, while delivering advertisements that the user desires or that have little psychological resistance to the user.

[0048] 〔flowchart〕 Next, the flow of processing by the information processing device 100 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the flow of processing according to this embodiment.

[0049] First, the information processing device 100 receives advertisement information (step S101). For example, the information processing device 100 receives information such as an advertisement ID, an advertisement type, a budget, a period, and targeting information as the advertisement information, and stores the information in the storage unit 130.

[0050] Next, the information processing device 100 receives a question (request) from the user (step S102). For example, the information processing device 100 receives a question sentence input by the user on an application, and stores it in the storage unit 130.

[0051] Next, the estimation unit 121 estimates a user profile of the user based on the information about the user (step S103). For example, the estimation unit 121 estimates the user profile by using one or more pieces of information about the user stored in the storage unit 130 (user attributes, search history, browsing history, location information, conversation content, conversation tendency, and context).

[0052] Next, the selection unit 122 selects an advertisement based on the estimated user image (step S14). For example, the selection unit 122 selects an advertisement that targets the estimated user image for advertisement delivery.

[0053] Next, the generation unit 123 generates a sentence for the generative model so that the advertisement selected by the selection unit 122 is included in the answer (step S105). For example, the generation unit 123 generates a sentence including a sentence by the user, a user image, and an advertisement as the sentence for the generative model.

[0054] Then, the output unit 124 outputs the sentence generated by the generation unit 123 to the generative model (step S106). For example, the output unit 124 outputs the sentence generated by the generation unit 123 to a trained large-scale language model independently created by a business (Yahoo).

[0055] 〔effect〕 As described above, the information processing device 100 according to the embodiment includes an estimation unit 121 that estimates a user image of a user based on information about the user, a selection unit 122 that selects an advertisement based on the user image estimated by the estimation unit 121, a generation unit 123 that generates a sentence for a generative model so that the advertisement selected by the selection unit 122 is included in the answer, and an output unit 124 that outputs the sentence generated by the generation unit 123 to the generative model.

[0056] As a result, the information processing device 100 estimates a persona from the attributes of the user who accepted the question, selects an advertisement corresponding to the persona, and generates and outputs text for the generative model so that the advertisement is included in the answer to the question, thereby enabling the delivery of an appropriate advertisement according to the user.

[0057] Furthermore, the information processing device 100 generates and outputs sentences for the generative model so that the answer to the user's question includes an advertisement that corresponds to the estimated user's persona, thereby providing the information the user is looking for as an answer and making it possible to deliver advertisements that the user wants or that the user has little psychological resistance to.

[0058] The estimation unit 121 of the information processing device 100 according to the embodiment estimates a user image using one or more of user attributes, search history, browsing history, location information, conversation content, conversation tendency, and context as information about the user.

[0059] As a result, the information processing device 100 estimates a persona using information about the user who accepted the question, such as user attributes, search history, browsing history, location information, conversation content, conversation trends, and context information, selects an advertisement corresponding to the persona, and generates and outputs text for the generative model so that the advertisement is included in the answer to the question, thereby enabling the delivery of an appropriate advertisement tailored to the user.

[0060] The estimation unit 121 of the information processing device 100 according to the embodiment estimates a user image from information about the user using a model that has learned the relationship between information about the user and the user image. As a result, the information processing device 100 uses the model to estimate a persona from the attributes of a user who has accepted a question, selects an advertisement corresponding to the persona, and generates and outputs a sentence for the generative model so that the advertisement is included in the answer to the question, thereby enabling delivery of an appropriate advertisement tailored to the user.

[0061] The selection unit 122 of the information processing device 100 according to the embodiment selects an advertisement that targets the user image estimated by the estimation unit 121 for advertisement delivery. As a result, the information processing device 100 selects an advertisement that targets the persona estimated from the attributes of the user who accepted the question, and generates and outputs a sentence for the generative model so that the advertisement is included in the answer to the question, thereby enabling the delivery of an appropriate advertisement according to the user.

[0062] The generation unit 123 of the information processing device 100 according to the embodiment generates a sentence including a user's sentence, a user image, and an advertisement as a sentence for the generative model. As a result, the information processing device 100 generates and outputs a sentence including the user's sentence, a user image, and an advertisement for the generative model so that the advertisement is included in the answer to the question, thereby enabling delivery of an appropriate advertisement according to the user.

[0063] 〔program〕 It is also possible to create a program written in a computer-executable language that executes the processes executed by the information processing device 100 described in the above embodiment. In this case, the same effects as those of the above embodiment can be achieved by having a computer execute the program. Furthermore, such a program may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read and executed by a computer to achieve the same processes as those of the above embodiment.

[0064] Fig. 9 is a diagram showing an example of a computer that executes an information processing program. As shown in Fig. 9, the controller 200 includes a computer 1000, which includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0065] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0066] 9, the hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. The tables described in the above embodiments are stored in the hard disk drive 1090 or the memory 1010, for example.

[0067] The control program is stored in the hard disk drive 1090 as a program module in which instructions to be executed by the computer 1000 are written. Specifically, the hard disk drive 1090 stores a program module 1093 in which each process executed by the controller 2000 described in the above embodiment is written.

[0068] Furthermore, data used for information processing by the control program is stored as program data, for example, in the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 and program data 1094 stored in the hard disk drive 1090 into the RAM 1012 as necessary, and executes each of the above-described procedures.

[0069] The program module 1093 and program data 1094 related to the control program are not limited to being stored in the hard disk drive 1090, but may be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1041, etc. Alternatively, the program module 1093 and program data 1094 related to the control program may be stored in another computer connected via a network such as a LAN (Local Area Network) or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

[0070] 〔others〕 Although various embodiments have been described in detail herein with reference to the drawings, these embodiments are merely examples and are not intended to limit the present invention. In other words, the present invention makes it possible to learn, build, and update various multi-class classification models and estimate desired probabilities by changing the features used as input. The features described herein can be realized in various ways, including various modifications and improvements based on the knowledge of those skilled in the art.

[0071] Furthermore, the above-mentioned "module (-er suffix, -or suffix)" can be read as a unit, means, circuit, etc. For example, a communication module, a control module, and a storage module can be read as a communication unit, a control unit, and a storage unit, respectively. [Explanation of symbols]

[0072] 100 Information processing device 110 Communications Department 120 control section 121 Estimation Department 122 Selection section 123 Generation part 124 Output section 130 Storage section

Claims

1. an estimation unit that estimates a user image of the user based on information about the user; a selection unit that selects an advertisement based on the user image estimated by the estimation unit; a generation unit that generates a sentence for a generative model so that the advertisement selected by the selection unit is included in an answer; an output unit that outputs the sentence generated by the generation unit to the generative model; An information processing device comprising:

2. The information processing device according to claim 1, characterized in that the estimation unit estimates the user image using one or more of the following information about the user: user attributes, search history, browsing history, location information, conversation content, conversation tendencies, and context.

3. The information processing device according to claim 1 , wherein the estimation unit estimates the user image from information about the user using a model that has learned a relationship between information about the user and the user image.

4. The information processing device according to claim 1 , wherein the selection unit selects an advertisement that targets the user image estimated by the estimation unit for advertisement distribution.

5. The information processing device according to claim 1 , wherein the generation unit generates a sentence including the user's sentence, the user image, and the advertisement as the sentence for the generation model.

6. An information processing method executed by an information processing device, an estimation step of estimating a user profile of the user based on information about the user; a selection step of selecting an advertisement based on the user image estimated by the estimation step; a generation step of generating a sentence for a generative model so that the advertisement selected by the selection step is included in an answer; an output step of outputting the sentence generated in the generation step to the generative model; An information processing method comprising:

7. an estimation step of estimating a user image of the user based on information about the user; a selection step of selecting an advertisement based on the user image estimated by the estimation step; a generation step of generating a sentence for a generative model so that the advertisement selected by the selection step is included in an answer; an output step of outputting the sentence generated in the generation step to the generative model; An information processing program characterized by causing a computer to execute the above.

Images