Information processing apparatus, information processing method, and information processing program

Abstract

To provide an information processing device, an information processing method, and an information processing program capable of improving selectivity of an advertisement in a chat room of a group chat.SOLUTION: An information processing apparatus includes a first selection unit, a second selection unit, and an output unit. The first selection section selects an advertisement to be displayed in a first area on a group chat screen on the basis of information regarding a plurality of users participating in a group chat. The second selection section selects an advertisement to be displayed in a second area of the group chat screen on the basis of a history of conversations between the users in the group chat. The output unit outputs the advertisement selected by the first selection unit and the advertisement selected by the second selection unit.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, there have been known techniques for providing advertisements via a network. For example, Patent Document 1 proposes a technique for forming a chat group including a user and at least one of a staff member of a customer service establishment and a cast member belonging to the customer service establishment, and displaying advertisements in a chat room of the chat group. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2024-027355 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-described conventional technology has a problem in that it is limited to displaying advertisements about reservations at a store in a chat group that includes the store's staff or cast members.

[0005] The present application 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 improve the selectivity of advertisements in group chat chat rooms. [Means for solving the problem]

[0006] The information processing device according to the present application includes a first selection unit, a second selection unit, and an output unit. The first selection unit selects an advertisement to be displayed in a first area on the group chat screen based on information about multiple users participating in the group chat. The second selection unit selects an advertisement to be displayed in a second area on the group chat screen based on a conversation history between users in the group chat. The output unit outputs the advertisement selected by the first selection unit and the advertisement selected by the second selection unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to improve the selectivity of advertisements in chat rooms of group chats. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an 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 a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of an advertisement information table stored in the advertisement information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a chat setting information table stored in the chat setting information storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a conversation history table stored in the conversation history storage unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a group chat screen displayed on a terminal device, including a first advertisement and a second advertisement output by an output unit in a processing unit of the information processing device according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of the first advertisement and the second advertisement that are output by the output unit in the processing unit of the information processing device according to the embodiment and displayed in a carousel format. [Figure 10] FIG. 10 is a diagram showing an example of a group chat screen displayed on a terminal device, which includes a first advertisement, a second advertisement, and grounds information output by an output unit in a processing unit of the information processing device according to the embodiment. [Figure 11] FIG. 11 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 12] FIG. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing 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 respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [1. An example of information processing] FIG. 1 is a diagram showing an example of information processing according to an embodiment, and in this embodiment, an information processing method is executed by an information processing device.

[0011] As shown in FIG. 1, the information processing device 1 includes terminal devices 21, 22, . . . , 2 m are communicably connected to the terminal devices 21, 22, . . . , 2 m The information processing device 1 transmits and receives information to and from the terminal devices 21, 22, . . . , 2. mThe terminal devices 21, 22, . . . , 2 provide online services including chat services for sending and receiving messages between users. m Users U1, U2, , U m Provided to.

[0012] The terminal device 21 is used by the user U1, the terminal device 22 is used by the user U2, and the terminal device 2 m is user U m It is used by users U1, U2,...,U m are participants in the same chat group, and terminal devices 21, 22, . . . , 2 m has an instant messenger application installed for group chat, which is chatting in a chat group.

[0013] Instant messengers can send and receive messages in group chats, one-to-one chats, one-to-many chats, etc. Messages sent and received through instant messengers include, for example, text, stamps, and captured images.

[0014] In the following, terminal devices 21, 22, . . . , 2 m When each of these is not individually distinguished, it may be referred to as terminal device 2, and users U1, U2, . . . , U m When referring to each of these without distinguishing them individually, they may be referred to as a user U. The terminal device 2 is, for example, a smartphone, a tablet PC (Personal Computer), or a notebook PC.

[0015] User U1,U2,...,U m are terminal devices 21, 22, . . . , 2 m The users U1, U2, . . . , U m are terminal devices 21, 22, . . . , 2 m, and transmits a group chat message to the information processing device 1 via a network (not shown) (steps S11, S12, . . . S1 m ).

[0016] The information processing device 1 includes terminal devices 21, 22, . . . , 2 m The group chat message is then sent to the terminal device 2 of the user U other than the user U who sent the message via a network (not shown) (steps S21, S22, . . . S2 m ) Terminal devices 21, 22,..., 2 m receives a chat message, which is a group chat message, sent from the information processing device 1, and displays the received chat message.

[0017] In the example shown in FIG. 1(a), the terminal device 21 stores chat messages CTM1 and CTM4 from user U1, chat message CTM2 from user U2, and chat message CTM3 from user U3. m The chat message CTM3 is displayed. The name of the chat group is Group A.

[0018] Next, the information processing device 1 receives a group chat request from multiple users U1, U2, . . . , U m Based on the information, an advertisement to be displayed in a first area on the group chat screen, which is a screen for the group chat, is selected (step S3).

[0019] In the process of step S3, the information processing device 1 selects a plurality of users U1, U2, . . . , U m and multiple users U1, U2, . m and the content of a chat message posted by any one of the users, a first advertisement to be displayed in the first area is selected.

[0020] Multiple users U1, U2,..., U mThe information is, for example, given by multiple users U1, U2, . m The behavioral history is, for example, attribute information indicating the attributes of each user U and behavioral history. The attributes of user U include, for example, demographic attributes and psychographic attributes. Demographic attributes are demographic attributes of user U. Psychographic attributes are attributes indicating, for example, user U's interests, values, lifestyle, personality, etc. The behavioral history is, for example, the online behavioral history of each user U, but may also include the offline behavioral history of each user U.

[0021] In the process of step S3, the information processing device 1 receives a plurality of users U1, U2, . . . , U m Based on the attribute information of multiple users U1, U2, . m Estimate the persona of group A, which is a group of

[0022] For example, the information processing device 1 is connected to a plurality of users U1, U2, . . . , U m Based on the attribute information of multiple users U1, U2, . m The common characteristics of multiple users U1, U2,..., U are determined as the persona of group A. m The common feature is, for example, that multiple users U1, U2, . m Examples of common attributes, interests, or patterns of behavior include, but are not limited to, common attributes, interests, or patterns of behavior.

[0023] Common attributes include, but are not limited to, age, gender, family, occupation, etc. Common interests include, but are not limited to, car enthusiasts, shopping enthusiasts, and travel enthusiasts. Common behavioral patterns include, but are not limited to, traveling at least once a month, eating out on weekday nights at least three times a week, and going shopping every weekend.

[0024] In the example shown in FIG. 1(a), the information processing device 1 is mThe first ad is selected based on the most recent chat message CTM4 among the chat messages CTM1, CTM2, CTM3, and CTM4 and the persona of group A. The most recent chat message CTM4 contains the string "Got it! We'll be staying at a hotel around Osaka Station on July 10th!"

[0025] For example, the information processing device 1 extracts the words "7 / 10," "Around Osaka Station," and "Hotel" from the chat message CTM4 as information on a specific date, a specific area, and a location type using natural language processing technology, regular expressions, etc. The information processing device 1 can also extract the information on a specific date, a specific area, and a location type from the chat message CTM4 using generative AI (Artificial Intelligence) such as Large Language Models (LLM).

[0026] The information processing device 1 acquires a hotel list, which is a list of hotels in a specific area where accommodation is available on a specific date, from an internal database or an external database, based on information such as a specific date, a specific area, and a location type. The information processing device 1 also acquires attribute information (e.g., location, price range, facilities, services, room type, and user reviews) of the hotels included in the hotel list from the internal database or an external database.

[0027] The information processing device 1 selects a first advertisement based on the attribute information of each hotel included in the hotel list and the persona of group A. For example, the information processing device 1 receives as input information information including the attribute information of each hotel included in the hotel list and the persona of group A, and causes the first learning model to output a score indicating the probability that the advertisement will be selected.

[0028] The information processing device 1 selects a predetermined number N1 of advertisements as first advertisements in descending order of score based on the scores of each advertisement output from the first learning model. The first learning model is, for example, a logistic regression model, a neural network model, or the like, but is not limited to such examples.

[0029] In the above example, the information processing device 1 narrows down the locations indicated by location type using the chat message CTM4, but it is also possible to narrow down the locations indicated by location type using the chat message CTM1, etc. Furthermore, the information processing device 1 can also select a first advertisement based on the persona of the group without using the chat message CTM4.

[0030] In addition, the information processing device 1 is configured to process the group chat data of users U1, U2, . . . , U m Based on the conversation history between the users, a second advertisement is selected to be displayed in a second area on the group chat screen (step S4). The second area is an area different from the first area.

[0031] The information processing device 1 is, for example, a plurality of users U1, U2, . . . , U m The second advertisement to be displayed in the second area can be selected based on the content of a chat message posted by one of the users U and the history of conversations between the users U in the chat room of the group chat before the chat message was posted.

[0032] Multiple users U1, U2,..., U m The chat message posted by any user U among the above is the latest chat message posted in the chat room of the group chat, but is not limited to this example.

[0033] The information processing device 1 is connected to users U1, U2, . . . , U mInformation including the history of conversation between the two users can be input as input information to the generation AI, and the generation AI can be made to generate advertising condition information indicating second advertising conditions, which are conditions for advertisements to be displayed in the second area.

[0034] The second advertising conditions are conditions for selecting a second advertisement to be provided to a group. For example, the second advertising conditions include conditions specifying the type of target of the advertisement (e.g., the type of service or product to be advertised), the target demographic (e.g., age, gender, occupation, interests), the type of advertisement format (e.g., video advertisement, banner advertisement, native advertisement), etc.

[0035] The type of service may be, for example, an accommodation service such as a hotel, or a food and beverage service or catering service provided by a restaurant, but is not limited to these examples. If the type of target of the advertisement is a hotel, the second advertising condition may include conditions such as the date of use, area, and number of people. If the type of target of the advertisement is a restaurant, the second advertising condition may include conditions such as the date and time of use, the type of restaurant, area, and number of people.

[0036] An example of a generative AI is a text generation AI, which is a large-scale language model trained to predict and output the next token from an input token sequence, such as a transformer-based model or an RNN (Recurrent Neural Network)-based model.

[0037] Examples of the transformer-based model include, but are not limited to, a generative pre-trained transformer (GPT), etc. Examples of the RNN-based model include, but are not limited to, a receptance weighted key value (RWKV).

[0038] The generation AI may be a language model that has been trained (for example, fine-tuned) specifically for generating answer information. The generation AI is disposed in an external information processing device, and the information processing device 1 uses the generation AI via an API (Application Programming Interface), but the generation AI may also be disposed within the information processing device 1.

[0039] The information processing device 1 is, for example, a m The generation AI is input with information including the conversation history between the two users and instruction information, which is the string "Please specify the conditions for the advertisement to be proposed to the user group having the given conversation." as input information, and the generation AI is caused to generate advertising condition information indicating second advertising conditions, which are the conditions for the advertisement to be displayed in the second area.

[0040] The instruction information may include information showing examples of linking examples of conversation history with examples of conditions for the advertisement to be proposed, thereby enabling the generation AI to generate advertising condition information with high accuracy. Furthermore, the generation AI may be a generation AI that has been trained by fine-tuning or the like using a dataset of the conversation histories and advertising condition information of multiple users U, and in this case, the input information input to the generation AI may not include instruction information.

[0041] The information processing device 1 can also input information including information on multiple users U (e.g., attribute information and behavior history) and a conversation history between the users U as input information to the generation AI, and cause the generation AI to generate advertising condition information. For example, the information processing device 1 inputs information including information on multiple users U, a conversation history between the users U, and instruction information to the generation AI as input information, and cause the generation AI to generate advertising condition information.

[0042] In this case, the instruction information is, for example, a character string "Please specify the conditions of the advertisement to be proposed to a group of multiple users who each have a given attribute and are having a given conversation," but is not limited to this example. In this case, the instruction information may also include information indicating examples of combinations of information about multiple users U and their conversation histories linked to examples of conditions for the advertisement to be proposed.

[0043] The information processing device 1 also stores information on a plurality of users U and a plurality of users U1, U2, . . . , U m It is also possible to input information into the generation AI including the content of a chat message posted by one of the users U and the history of conversations between the users U in the chat room of the group chat before the chat message was posted, and have the generation AI generate advertising condition information.

[0044] For example, the information processing device 1 inputs information including information on multiple users U, the contents of chat messages posted by the users U, the history of conversations between the users U in the chat room of the group chat before the chat messages were posted, and instruction information into the generation AI as input information, and causes the generation AI to generate advertising condition information.

[0045] In this case, the instruction information is, for example, a string such as "Please specify the conditions for the advertisement to be proposed to a group of multiple users who each have given attributes and are having a given conversation. The conditions for the advertisement to be proposed should be to place the most weight on the most recent message.", but is not limited to such an example.

[0046] In this case, the instruction information may also include information showing examples of combinations of information of multiple users U, conversation history, and latest messages, and examples of conditions for advertisements to be proposed. The latest message is the latest chat message among the multiple chat messages included in the input information.

[0047] The information processing device 1 selects a second advertisement to be displayed in the second area based on the advertisement condition information generated as described above. For example, when the advertisement condition information generated as described above includes information about accommodation services (e.g., information about the accommodation date and time, accommodation area, etc.), the information processing device 1 acquires a hotel list, which is a list of hotels in the accommodation area that are available for accommodation on the accommodation date and time, from an internal database or an external database based on the information about the accommodation services. In addition, the information processing device 1 acquires attribute information of the hotels included in the hotel list (e.g., location, price range, facilities, services, room type, customer reviews, etc.) from an internal database or an external database.

[0048] The information processing device 1 selects the first advertisement based on the attribute information of each hotel included in the hotel list and the persona of group A. For example, the information processing device 1 uses a second learning model that outputs a score indicating the probability that the advertisement will be selected, using information including the attribute information of each hotel included in the hotel list and information included in the advertisement condition information generated as described above (information such as the target demographic and the type of advertisement format), and causes the second learning model to output a score for each advertisement.

[0049] The information processing device 1 selects a predetermined number N2 of advertisements as second advertisements in descending order of score based on the scores of each advertisement output from the second learning model. The second learning model is, for example, a logistic regression model, a neural network model, or the like, but is not limited to such examples.

[0050] In addition, the information processing device 1 inputs information including information instructing the generation of the basis for the second advertising condition indicated in the advertising condition information as input information to the generation AI, and causes the generation AI to generate basis information, which is information indicating the basis for the second advertising condition indicated in the advertising condition information and is information to be displayed on the group chat screen.

[0051] For example, the information processing device 1 can cause the generation AI to generate basis information, which is information indicating the basis for the second advertisement condition indicated in the advertisement condition information, by further including information such as a character string "Please also output a sentence indicating the basis for specifying the advertisement condition" in the above-mentioned instruction information. By causing the generation AI to output the basis information, the information processing device 1 can increase the accuracy of the second advertisement condition specified by the generation AI.

[0052] The basis information is, for example, information such as the character string "I'm looking for a hotel near Osaka Station" or the character string "I'm excited about a trip to Okinawa", but is not limited to these examples.

[0053] Next, the information processing device 1 transmits the first advertisement selected in step S3 and the second advertisement selected in step S4 to the terminal devices 21, 22, . . . , 2 m (Steps S51, S52, . . . 5 m ) As a result, the terminal devices 21, 22, . . . , 2 m In step S3, the first advertisement selected in step S3 and the second advertisement selected in step S4 are displayed in the chat room of group A.

[0054] In the example shown in Figure 1(b), Advertisement CTA1, Advertisement CTA2, Advertisement CTM_A1, and Advertisement CTM_A2 are first advertisements, and Advertisement CTA3 and Advertisement CTM_A3 are second advertisements. Advertisements CTA1 and CTM_A1 are advertisements for AAA Hotels, Advertisements CTA2 and CTM_A2 are advertisements for DDD Hotels, and Advertisements CTA3 and CTM_A3 are advertisements for CCC Hotels.

[0055] The area where advertisements CTA1, CTA2, CTM_A1, and CTM_A2 are displayed is the first area, and the area where advertisements CTA3 and CTM_A3 are displayed is the second area, but the present invention is not limited to this example.

[0056] Ad CTM_A1, Ad CTM_A2, and Ad CTM_A3 are text ads in the form of messages, and are displayed in the same way as chat messages on the group chat screen. Ad CTA1, Ad CTA2, and Ad CTA3 are banner ads containing images, text, and links, and are sometimes called card ads because they are displayed in a carousel format.

[0057] 1B, the second advertisement selected by the information processing device 1 and provided to the terminal device 2 also includes an advertisement CTA 4 (not shown) outside the display area of ​​the terminal device 2.

[0058] The first and second areas are arranged in a direction (horizontal direction in FIG. 1(b)) perpendicular to the arrangement direction of chat messages on the group chat screen (vertical direction in FIG. 1(b)). In the area including the first and second areas, advertisements CTA1 and CTA2, which are first advertisements, and advertisements CTA3 and CTA4, which are second advertisements, are displayed in a carousel format.

[0059] The carousel display is performed in response to a specific operation (for example, a flick operation or a scroll operation) performed by the user U on the terminal device 2, but may also be performed automatically. The carousel display of the first advertisements, ie, advertisements CTA1 and CTA2, and the second advertisements, ie, advertisements CTA3 and CTA4, is performed by moving the first and second areas in the arrangement direction.

[0060] Furthermore, the information processing device 1 performs steps S51, S52, . . . 5 m The basis information generated in the terminal devices 21, 22, . . . , 2 m The information processing device 1 can also output the second advertisement to the terminal devices 21, 22, . . . , 2 m After outputting the basis information to the terminal device 21, 22, . . . , 2 m Output to.

[0061] As a result, the terminal devices 21, 22, . . . , 2 mIn the example, after or before the second advertisement is displayed in the chat room of the chat group, the basis information is displayed in the chat room of the chat group. m This allows the user to easily understand the reason why the second advertisement was displayed, and the information processing device 1 can improve the advertising effectiveness of the advertisement.

[0062] In this way, the information processing device 1 selects an advertisement to be displayed in a first area on the group chat screen as a first advertisement based on information about multiple users U participating in the group chat, and selects an advertisement to be displayed in a second area on the group chat screen as a second advertisement based on the history of conversations in the group chat between users U. This allows the information processing device 1 to improve the selectivity of advertisements in the chat room of the group chat.

[0063] The information processing device 1 and the terminal devices 21-2 perform the above-described processing. m The configuration of the information processing system including the above will be described in detail.

[0064] [2. Information Processing System Configuration] 2 is a diagram showing an example of the configuration of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 100 according to an embodiment includes an information processing device 1 and a plurality of terminal devices 21, 22, . . . , 2 n For example, n is an integer equal to or greater than the above-mentioned m.

[0065] A plurality of terminal devices 21, 22, . . . , 2 n are different users U1, U2, . n Terminal devices 21, 22,...,2 used by n Examples of the device include a laptop computer, a desktop computer, a smartphone, a tablet computer, and a wearable device, such as, but not limited to, smart glasses or a smart watch.

[0066] Information processing device 1 and terminal devices 21, 22, . . . , 2 n are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG.

[0067] The network N includes, for example, a WAN (Wide Area Network) such as the Internet and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

[0068] The terminal device 2 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0069] 3. Configuration of Information Processing Device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0070] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 via the network N.

[0071] [3.2. Storage section 11] The storage unit 11 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. The storage unit 11 has a user information storage unit 20, an advertisement information storage unit 21, a chat setting information storage unit 22, and a conversation history storage unit 23.

[0072] [3.2.1. User information storage unit 20] The user information storage unit 20 stores user information including information about the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment. As shown in Fig. 4, the user information table stored in the user information storage unit 20 includes items such as "user ID," "user name," and "user information."

[0073] "User ID" is identification information that identifies user U, and is information assigned to each user U. "User name" is the name of user U corresponding to the "user ID." "User information" is the attribute information and behavioral history of user U corresponding to the "user ID."

[0074] The attribute information of user U includes, for example, psychographic attribute information, demographic attribute information, etc. Demographic attributes include, for example, gender, age, place of residence, and occupation, while psychographic attributes include interests such as travel, clothing, cars, and religion, lifestyle, thoughts, and ideological tendencies.

[0075] The behavioral history of user U is the behavioral history of user U in online services and offline behavioral history of user U. The behavioral history of user U in online services includes information such as search history, browsing history, posting history, and purchase history.

[0076] The search history includes information on search queries used in past searches by the user U and content viewed by the user U from among the search results. Information on search queries includes, for example, search keywords and search phrases.

[0077] The browsing history includes, for example, information indicating the content that the user U has viewed on the online service, the posting history includes, for example, information indicating the content (e.g., reviews, comments, etc.) that the user U has posted in the past on the online service, and the purchase history includes information on the items of transactions that the user U has made in the past.

[0078] The offline behavioral history of user U may be, for example, user U's offline movement history, user U's usage history at physical stores (including product and service purchase history), etc., but is not limited to such examples.

[0079] 3.2.2. Advertising Information Storage Unit 21 The advertisement information storage unit 21 stores information related to various advertisements. Fig. 5 is a diagram showing an example of an advertisement information table stored in the advertisement information storage unit 21 of the information processing device 1 according to the embodiment. As shown in Fig. 5, the advertisement information table stored in the advertisement information storage unit 21 includes items such as "advertisement ID" and "advertisement information."

[0080] The "advertising ID" is an identifier that identifies an advertisement and is information assigned to each advertisement. The "advertising information" is various information related to the advertisement associated with the "advertising ID," and includes information such as the advertisement, the type of advertisement format, information on the target demographic, information on the target of the advertisement, and attribute information for each advertisement.

[0081] Types of advertising formats include, but are not limited to, banner ads, listing ads, native ads, social media ads, and video ads. Target demographic information is information such as attribute information of users U who are the target recipients of the advertisement. Information on the target of the advertisement is, for example, information indicating the type of service that is the subject of the advertisement or the type of product that is the subject of the advertisement.

[0082] The attribute information for an advertisement may include, for example, location, price range, facilities, services, room type, and word-of-mouth reviews if the service being advertised is a hotel accommodation service, and may include, for example, location, price range, cuisine, services, seating type (e.g., table or tatami room), and word-of-mouth reviews if the service being advertised is a hotel accommodation service, but is not limited to these examples.

[0083] 5, the advertisement information table also includes information such as the advertisement effect target of the advertisement (for example, information on the index used to calculate the advertisement effect) associated with the "advertising ID," information on the advertisement distribution period, and information on the index unit price (for example, CPA (Cost Per Action)). Furthermore, the advertisement information storage unit 21 is not limited to the above and can store various types of information according to the purpose.

[0084] 3.2.3. Chat Setting Information Storage Unit 22 The chat setting information storage unit 22 stores various setting information for the chat service. Fig. 6 is a diagram showing an example of a chat setting information table stored in the chat setting information storage unit 22 of the information processing device 1 according to the embodiment. As shown in Fig. 6, the chat setting information table stored in the chat setting information storage unit 22 includes items such as "group ID," "group name," and "participating user ID."

[0085] The "group ID" is an identifier for identifying a chat group, and is information assigned to each chat group. The "group name" is information indicating the name of the chat group associated with the "group ID."

[0086] The "participating user ID" includes the user ID of each user U participating in the chat group associated with the "group ID." Although not shown, the chat setting information table shown in FIG. 6 also includes setting information other than chat groups, such as setting information for one-to-one chats and one-to-many chats.

[0087] [3.2.4. Conversation History Storage Unit 23] The conversation history storage unit 23 stores various conversation histories in the chat service. Fig. 7 is a diagram showing an example of a conversation history table stored in the conversation history storage unit 23 of the information processing device 1 according to the embodiment. As shown in Fig. 7, the conversation history table stored in the conversation history storage unit 23 includes items such as "message ID," "user ID," "group ID," "date and time," and "message."

[0088] "Message ID" is an identifier that identifies a chat message and is information assigned to each chat message. "User ID" is the user ID of the user U who posted the chat message corresponding to the "Message ID." "Group ID" is the group ID of the chat group corresponding to the chat room in which the chat message corresponding to the "Message ID" was posted.

[0089] "Date and time" is information indicating the date and time when the chat message corresponding to the "Message ID" was posted. "Message" is the chat message corresponding to the "Message ID." Although not shown, the chat setting information table shown in FIG. 7 also includes conversation history other than that of chat groups, such as conversation history of one-to-one chats and conversation history of one-to-many chats.

[0090] [3.3. Processing Unit 12] The processing unit 12 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 examples of information processing programs) stored in a storage device inside the information processing device 1 using RAM or the like as a working area.

[0091] The processing unit 12 is a controller, and may be realized by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU).

[0092] 3, the processing unit 12 has a receiving unit 30, an acquiring unit 31, a determining unit 32, a first selecting unit 33, an identifying unit 34, a second selecting unit 35, an output unit 36, and an allocating unit 37, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration that performs the information processing described below.

[0093] 3.3.1. Reception unit 30 The reception unit 30 receives various requests and information from the terminal device 2 via the communication unit 10.

[0094] For example, the requests received by the receiving unit 30 include a posting request including a chat message posted by the user U, a request to acquire a chat message posted by the user U, and the like, but are not limited to these examples.

[0095] The posting request includes information such as the user ID of the poster, user U, the group ID of the chat group to which the posting is to be made, the chat message, etc. When the reception unit 30 receives a posting request, it updates the conversation history table stored in the conversation history storage unit 23 based on the received posting request.

[0096] The reception unit 30 can receive a posting request including a chat message posted by a user U as an evaluation of an advertisement. The evaluation of an advertisement may be, for example, a negative evaluation such as information such as the character string "A better hotel would be nice" or a positive evaluation such as information such as the character string "This hotel is nice," but is not limited to such examples. For example, the evaluation of an advertisement may be performed by selecting a positive evaluation button or a negative evaluation button displayed at a position corresponding to the advertisement.

[0097] [3.3.2. Acquisition part 31] The acquisition unit 31 acquires various pieces of information from an external information processing device or the terminal device 2 via the communication unit 10, and stores the acquired information in the storage unit 11.

[0098] For example, the acquisition unit 31 acquires user information, which is information about the user U, from an external information processing device or terminal device 2 or the like via the communication unit 10, and adds the acquired user information to the user information table in the user information storage unit 20. In addition, the acquisition unit 31 acquires advertising information, which is information about advertisements, from the like via the communication unit 10, and adds the acquired advertising information to the advertising information table in the advertising information storage unit 21.

[0099] Furthermore, the acquisition unit 31 acquires user information, advertisement information, chat setting information, conversation history, and the like from the storage unit 11.

[0100] 3.3.3. Determination unit 32 The determination unit 32 makes various determinations. For example, the determination unit 32 determines, for each chat group, one or more of the size of at least one of the first and second areas, the advertisement display mode (posting mode), and the advertisement output frequency (posting frequency) based on the number of users U participating in the group chat. The advertisement display mode is the mode in which advertisements are posted in the chat room of the group chat, and is, for example, a text advertisement, a banner advertisement, a pop-up advertisement, etc., but is not limited to these examples.

[0101] For example, if the number of users U participating in the group chat is equal to or greater than a threshold, the determination unit 32 sets the advertisement display format to text advertisements and banner advertisements, and if not, sets the advertisement display format to banner advertisements and does not use text advertisements. Furthermore, the determination unit 32 can increase the size of the area or increase the advertisement output frequency as the number of users U participating in the group chat increases, or can perform the reverse process.

[0102] In addition, the determination unit 32 can also determine, for each chat group, one or more of the size of at least one of the first area and the second area, the display mode of the advertisement, and the frequency of advertisement output, based on the number of chat messages per short period of time.

[0103] For example, if the number of chat messages per short period is equal to or greater than a threshold, the determination unit 32 sets the advertisement display mode to text advertisements and banner advertisements, and if not, sets the advertisement display mode to banner advertisements and does not use text advertisements. Furthermore, the determination unit 32 can increase the size of the area or increase the advertisement output frequency as the number of chat messages per short period increases, or can perform the reverse process.

[0104] In addition, the determination unit 32 can also determine, for each chat group, one or more of the size of at least one of the first area and the second area, the display mode of the advertisement, and the frequency of advertisement output, based on the number of users U participating in the group chat and the number of users U participating in the group chat.

[0105] The determination unit 32 can also determine, for each chat group, one or more of the size of at least one of the first and second areas, the advertisement display mode, and the advertisement output frequency, based on the proportion of premium members participating in the group chat. A premium member is, for example, a member who can enjoy specific benefits in a service operated or sponsored by an administrator that provides a chat service, and a user U can become a premium member by, for example, paying a fixed monthly fee.

[0106] For example, if the percentage of premium members participating in the group chat is less than a threshold, the determination unit 32 sets the advertisement display mode to text advertisements and banner advertisements, and if not, sets the advertisement display mode to banner advertisements and does not use text advertisements. Furthermore, the determination unit 32 can increase the size of the area or increase the advertisement output frequency as the percentage of premium members participating in the group chat decreases, or can perform the reverse process.

[0107] In addition, the determination unit 32 can also stop the selection of the second advertisement by the second selection unit 35 when one or more of the number of users U participating in the group chat, the number of chat messages per short period of time, and the percentage of premium members participating in the group chat satisfy predetermined conditions.

[0108] The predetermined conditions are, for example, a condition that the number of users U participating in the group chat is below a threshold, a condition that the number of chat messages per short period of time is below a threshold, and a condition that the proportion of premium members participating in the group chat is above a threshold, but are not limited to such examples.

[0109] [3.3.4. First selection unit 33] The first selection unit 33 selects, as a first advertisement, an advertisement to be displayed in a first area on the screen of the group chat, based on information of a plurality of users U participating in the group chat.

[0110] For example, the first selection unit 33 selects the first advertisement to be displayed in the first area based on information about multiple users U participating in a group chat and the content of a chat message posted by any one of the multiple users U.

[0111] The information about user U is, for example, attribute information indicating the attributes of user U and behavioral history. The attributes of user U are, for example, demographic attributes and psychographic attributes. Demographic attributes are demographic attributes of user U. Psychographic attributes are, for example, attributes indicating user U's interests, values, lifestyle, personality, etc. The behavioral history is, for example, the online behavioral history of each user U, but may also include the offline behavioral history of each user U.

[0112] The first selection unit 33 estimates personas of a chat group to which multiple users U belong, based on attribute information of the multiple users U. The personas of a chat group are, for example, a group of three boys who love traveling to Osaka, a group of four girls who love Hokkaido, a volunteer group who are enthusiastic about contributing to society, a group of people who love a particular game, etc., but are not limited to these examples.

[0113] For example, the first selection unit 33 determines a characteristic common to the multiple users U as the persona of the group based on the attribute information of the multiple users U. The characteristic common to the multiple users U is, for example, an attribute, interest, or behavioral pattern common to the multiple users U, but is not limited to such examples.

[0114] Common attributes include, but are not limited to, age, gender, family, occupation, etc. Common interests include, but are not limited to, car enthusiasts, shopping enthusiasts, and travel enthusiasts. Common behavioral patterns include, but are not limited to, traveling at least once a month, eating out on weekday nights at least three times a week, and going shopping every weekend.

[0115] The first selection unit 33 can, for example, input information about multiple users U belonging to a group and instruction information instructing the generation AI to determine the persona of the group from the information about the multiple users U, and have the generation AI determine the persona of the group. In this case, the instruction information can be, for example, a character string such as "Based on the information about the given users, please determine the persona of the group of these users," but is not limited to such an example.

[0116] The instruction information may include information showing examples that link examples of information of multiple users U with examples of personas of the group, thereby enabling the generation AI to accurately estimate the persona of the group. The generation AI may also be a generation AI that has been trained by fine-tuning or the like using a dataset of information of multiple users U and the personas of the group, in which case the input information input to the generation AI may not include instruction information.

[0117] In the example shown in FIG. 8, which will be described later, the first selection unit 33 selects, for example, users U1, U2, U m The first ad is selected based on the most recent chat message CTM4 among the chat messages CTM1, CTM2, CTM3, and CTM4 and the persona of group A. The most recent chat message CTM4 contains the string "Got it! We'll be staying at a hotel around Osaka Station on July 10th!"

[0118] For example, the first selection unit 33 extracts the words "7 / 10," "around Osaka Station," and "hotel" from the chat message CTM4 as information on a specific date, a specific area, and a location type using natural language processing technology, regular expressions, etc. The first selection unit 33 can also extract the information on a specific date, a specific area, and a location type from the chat message CTM4 using a generation AI such as a large-scale language model.

[0119] For example, the first selection unit 33 can input the chat message CTM4 and instruction information instructing the generation AI to extract a specific date, a specific area, and a location type from the chat message CTM4, and have the generation AI extract the specific date, the specific area, and the location type. In this case, the instruction information can be, for example, a string such as "Please extract the date, the area, and the location type from the given message," but is not limited to this example.

[0120] The instruction information may include information showing examples of messages linked to examples of dates, areas, and location types, which allows the generation AI to accurately estimate the persona of the group. The generation AI may also be a generation AI trained by fine tuning using a data set of messages, dates, areas, and location types, in which case the input information input to the generation AI does not need to include instruction information.

[0121] The first selection unit 33 acquires a hotel list, which is a list of hotels in a specific area that are available for accommodation on a specific date, from an internal database or an external database, based on information such as a specific date, a specific area, and a location type. The first selection unit 33 also acquires attribute information (e.g., location, price range, facilities, services, room type, and reviews) of the hotels included in the hotel list from the internal database or an external database.

[0122] The first selection unit 33 selects a first advertisement based on the attribute information of each hotel included in the hotel list and the persona of the group. For example, the first selection unit 33 receives information including the attribute information of the hotels included in the hotel list and the persona of the group as input information, and uses a first learning model that outputs a score indicating the probability that the advertisement will be selected, and causes the first learning model to output a score for each advertisement.

[0123] The first selection unit 33 selects a predetermined number N1 of advertisements as first advertisements in descending order of score based on the scores of each advertisement output from the first learning model. The first learning model is, for example, a logistic regression model, a neural network model, or the like, but is not limited to such examples.

[0124] In the above example, the first selection unit 33 narrows down the locations indicated by the location type using the chat message CTM4, but it is also possible to narrow down the locations indicated by the location type using the chat message CTM1, etc. Furthermore, the first selection unit 33 can also select the first advertisement based on the persona of the group without using the chat message CTM4.

[0125] Furthermore, the first selection unit 33 reselects the first advertisement based on a plurality of chat messages posted by a plurality of users U as evaluations of the advertisement. For example, the first selection unit 33 reselects the first advertisement when a preset ratio (e.g., more than 50% or 2 / 3 or more) of the chat messages posted by a plurality of users U as evaluations of the advertisement are negative evaluations.

[0126] The first selection unit 33 determines whether a chat message is a negative evaluation, for example, by whether the chat message contains a term included in a negative term list that lists negative terms, but it can also make the determination using, for example, a generation AI.

[0127] For example, the first selection unit 33 inputs information including multiple chat messages posted by multiple users U as evaluations of the advertisement and instruction information instructing the generation AI to determine whether or not the advertisement should be reselected as input information, thereby causing the generation AI to output information indicating the determination result of whether or not the advertisement should be reselected.

[0128] [3.3.5. Specification part 34] The identification unit 34 performs various identifications. For example, the identification unit 34 identifies a chat message posted by the user U in a chat room other than the chat room of the group chat and the recipient of the notification of the chat message.

[0129] For example, user U1 is participating in group chats for groups A and B, and user U is participating in the group chat for group B. m+1 ,U m+2 In this case, the identification unit 34 identifies the chat message posted by the user U1 in the chat room of the group chat of the group B and the user U1 who is the recipient of the notification of the chat message. m+1 ,U m+2 Identify the following.

[0130] Furthermore, the identification unit 34 identifies other chat rooms in which the user U participates, based on a chat message posted by the user U in the chat room of the group chat. For example, assume that the user U1 participates in the group chat of groups A, B, and C. Based on the chat message posted by the user U1 in the chat room of group A, the identification unit 34 identifies other chat rooms in which a chat message related to the chat message posted by the user U1 has been posted as related chat rooms from among the chat rooms of groups B and C.

[0131] For example, the identification unit 34 has a list of related terms that lists terms that are related to each other, and can identify as related chat rooms other chat rooms in which user U1 participates and in which chat messages containing terms related to terms contained in a chat message posted by user U1 in a chat room of group A have been posted.

[0132] For example, the identification unit 34 can identify, as a related chat room, another chat room in which a chat message was posted by user U1 immediately before the posting of a chat message by user U1 in the chat room of group A.

[0133] The identification unit 34 can also use the generation AI to identify related chat rooms. For example, the identification unit 34 can input information including chat messages of other chat rooms in which the user U participates and instruction information instructing the generation AI to identify related chat rooms, and cause the generation AI to output information indicating the related chat rooms.

[0134] The instruction information includes, for example, information indicating a condition that other chat rooms in which chat messages related to a chat message by a user U1 in a chat room of group A are posted by the same user U1 are identified as related chat rooms. The instruction information also includes, for example, information indicating a condition that other chat rooms in which chat messages related to a chat message by a user U1 in a chat room of group A are posted by the same user U1 are identified as related chat rooms. m The definition information includes, but is not limited to, definition information that defines a chat room in which a topic (such as a topic) is posted as a related chat room.

[0135] In addition, the instruction information may include information showing examples that link examples of chat messages in a certain chat room with examples of chat messages in related chat rooms, which allows the generation AI to accurately identify related chat rooms.

[0136] [3.3.6. Second selection unit 35] The second selection unit 35 selects, as the second advertisement, an advertisement to be displayed in the second area on the group chat screen, based on the conversation history between users U in the group chat.

[0137] For example, the second selection unit 35 selects the second advertisement based on the content of a chat message posted by one of multiple users U and the history of conversations between users U in a group chat before the chat message was posted.

[0138] The chat message posted by any one of the multiple users U is the latest chat message posted in the chat room of the group chat, but is not limited to this example. Note that the second advertisement is selected by the second selection unit 35 from a group of advertisements that are candidates for selection of the first advertisement by the first selection unit 33, but is not limited to this example. For example, the second advertisement may be selected from a group of advertisements other than the group of advertisements that are candidates for selection of the first advertisement by the first selection unit 33.

[0139] The second selection unit 35 includes a generation processing unit 40 that causes a generation AI to generate advertising condition information indicating the conditions of the advertisement to be displayed in the second area, and a selection processing unit 41 that selects the second advertisement based on the advertising condition information generated by the generation processing unit 40.

[0140] [3.3.6.1. Generation Processing Unit 40] The generation processing unit 40 causes the generation AI to generate advertising condition information indicating the conditions for the advertisement to be displayed in the second area. For example, the generation processing unit 40 inputs information including a conversation history between users U as input information to the generation AI, and causes the generation AI to generate advertising condition information indicating second advertising conditions, which are the conditions for the advertisement to be displayed in the second area.

[0141] The second advertising conditions are conditions for selecting a second advertisement to be provided to a group. For example, the second advertising conditions include conditions specifying the type of target of the advertisement (e.g., the type of service or product to be advertised), the target demographic (e.g., age, gender, occupation, interests), the type of advertisement format (e.g., video advertisement, banner advertisement, native advertisement), etc.

[0142] The type of service may be, for example, an accommodation service such as a hotel, or a food and beverage service or catering service provided by a restaurant, but is not limited to these examples. If the type of target of the advertisement is a hotel, the second advertising condition may include conditions such as the date of use, area, and number of people. If the type of target of the advertisement is a restaurant, the second advertising condition may include conditions such as the date and time of use, the type of restaurant, area, and number of people.

[0143] The generation AI is, for example, a text generation AI. The text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input token sequence, such as a transformer-based model or an RNN-based model. An example of a transformer-based model is, but is not limited to, GPT. An example of an RNN-based model is, but is not limited to, RWKV.

[0144] The generation AI may be a language model that has been trained (for example, fine-tuned) specifically for generating answer information. The generation AI may be located in an external information processing device, and the generation processing unit 40 uses the generation AI via an API, but the generation AI may also be located within the information processing device 1.

[0145] The generation processing unit 40 inputs information including, for example, the conversation history between users U and instruction information, which is the string "Please specify the conditions of the advertisement to be proposed to the user group having the given conversation," as input information to the generation AI, and causes the generation AI to generate advertising condition information indicating second advertising conditions, which are the conditions of the advertisement to be displayed in the second area.

[0146] The instruction information may include information showing examples of linking examples of conversation history with examples of conditions for the advertisement to be proposed, thereby enabling the generation AI to generate advertising condition information with high accuracy. Furthermore, the generation AI may be a generation AI that has been trained by fine-tuning or the like using a dataset of the conversation histories and advertising condition information of multiple users U, and in this case, the input information input to the generation AI may not include instruction information.

[0147] The generation processing unit 40 can also input information including information on multiple users U and a conversation history between the users U as input information to the generation AI, and cause the generation AI to generate advertising condition information indicating the conditions for the advertisement to be displayed in the second area. The information on the users U is, for example, attribute information and behavioral history. For example, the generation processing unit 40 inputs information including information on multiple users U, a conversation history between the users U, and instruction information as input information to the generation AI, and cause the generation AI to generate advertising condition information.

[0148] In this case, the instruction information is, for example, a character string "Please specify the conditions of the advertisement to be proposed to a group of multiple users who each have a given attribute and are having a given conversation," but is not limited to this example. In this case, the instruction information may also include information indicating examples of combinations of information about multiple users U and their conversation histories linked to examples of conditions for the advertisement to be proposed.

[0149] In addition, the generation processing unit 40 can input information including information on multiple users U, the content of a chat message posted by any one of the multiple users U, and the history of conversations between users U in the chat room of the group chat before the chat message was posted, as input information to the generation AI, and cause the generation AI to generate advertising condition information.

[0150] For example, the generation processing unit 40 inputs information including information on multiple users U, the contents of chat messages posted by the users U, the history of conversations between users U in the chat room of the group chat before the chat messages were posted, and instruction information into the generation AI as input information, and causes the generation AI to generate advertising condition information.

[0151] In this case, the instruction information is, for example, a string such as "Please specify the conditions for the advertisement to be proposed to a group of multiple users who each have given attributes and are having a given conversation. The conditions for the advertisement to be proposed should be to place the most weight on the most recent message.", but is not limited to such an example.

[0152] In this case, the instruction information may also include information showing examples of combinations of information of multiple users U, conversation history, and latest messages, and examples of conditions for advertisements to be proposed. The latest message is the latest chat message among the multiple chat messages included in the input information.

[0153] In addition, the generation processing unit 40 inputs information including information instructing the generation of the basis for the second advertising condition indicated in the advertising condition information as input information to the generation AI, and causes the generation AI to generate basis information, which is information indicating the basis for the second advertising condition indicated in the advertising condition information and is information to be displayed on the group chat screen.

[0154] For example, the generation processing unit 40 can cause the generation AI to generate information indicating the basis for the second advertisement conditions indicated in the advertisement condition information by further including information such as a character string "Please also output a sentence indicating the basis for specifying the advertisement conditions" in the instruction information. By causing the generation AI to output information indicating the basis for specifying the second advertisement conditions, the generation processing unit 40 can increase the accuracy of the second advertisement conditions specified by the generation AI.

[0155] The basis information is, for example, information such as the character string "I'm looking for a hotel near Osaka Station" or the character string "I'm excited about a trip to Okinawa", but is not limited to these examples.

[0156] The basis information may include information indicating a summary of the conversation history used to select the second advertisement. In this case, the basis information generated by the generation processing unit 40 includes the character string "The above advertisement is being displayed for the following reason."

[0157] [3.3.6.2. Selection Processing Unit 41] The selection processing unit 41 selects a second advertisement based on the advertisement condition information generated by the generation processing unit 40.

[0158] For example, if the advertising condition information generated as described above includes information about accommodation services (such as information about the accommodation date and time and the accommodation area), the selection processing unit 41 acquires a hotel list, which is a list of hotels in the accommodation area that are available for accommodation on the accommodation date and time, from an internal database or an external database based on the information about the accommodation services.The selection processing unit 41 also acquires attribute information of the hotels included in the hotel list (such as location, price range, facilities, services, room type, and user reviews) from an internal database or an external database.

[0159] The selection processing unit 41 selects the first advertisement based on the attribute information of each hotel included in the hotel list and the persona of group A. For example, the selection processing unit 41 uses information including the attribute information of the hotels included in the hotel list and information included in the advertisement condition information generated as described above (information such as the target demographic and the type of advertisement format), and causes the second learning model to output a score indicating the probability that the advertisement will be selected.

[0160] The selection processing unit 41 selects a predetermined number N2 of advertisements as second advertisements in descending order of score based on the scores of each advertisement output from the second learning model. The second learning model is, for example, a logistic regression model, a neural network model, or the like, but is not limited to such examples.

[0161] The second selection unit 35 reselects the second advertisement based on a plurality of chat messages posted as evaluations of the second advertisement by a plurality of users U. The second selection unit 35 determines whether or not a chat message is a negative evaluation, for example, by whether or not the chat message contains a term included in a negative term list that lists negative terms, but the determination can also be made using, for example, a generation AI.

[0162] For example, the second selection unit 35 inputs information including multiple chat messages posted by multiple users U as evaluations of the advertisement and instruction information instructing the generation AI to determine whether or not the advertisement should be reselected as input information, thereby causing the generation AI to output information indicating the determination result of whether or not the advertisement should be reselected.

[0163] Furthermore, the second selection unit 35 can select the second advertisement to be displayed in the second area based on the conversation history between users and the chat message and notification recipient identified by the identification unit 34.

[0164] For example, the second selection unit 35 narrows down the type and content of the second advertisement based on the chat message identified by the identification unit 34. For example, the second selection unit 35 identifies information such as a specific date, a specific area, and a location type based on the chat message identified by the identification unit 34.

[0165] For example, the second selection unit 35 uses natural language processing technology, regular expressions, etc. to extract information such as a specific date, a specific area, and a location type from the most recent message posted in a chat room and chat messages in related chat rooms identified by the identification unit 34. The second selection unit 35 can also change the priority of the advertisements to be selected based on the notification recipients identified by the identification unit 34.

[0166] [3.3.7. Output section 36] The output unit 36 ​​outputs the first advertisement selected by the first selection unit 33 and the second advertisement selected by the second selection unit 35.

[0167] For example, the output unit 36 ​​outputs the first advertisement selected by the first selection unit 33 and the second advertisement selected by the second selection unit 35 by transmitting them via the communication unit 10 to multiple terminal devices 2 of multiple users U belonging to the chat group.

[0168] The output unit 36 ​​can also output the basis information generated by the generation processing unit 40 of the second selection unit 35 to the terminal device 2. For example, the output unit 36 ​​outputs the first advertisement and the second advertisement to the multiple terminal devices 2 after outputting them to the multiple terminal devices 2 of the multiple users U who belong to the chat group or before they are displayed.

[0169] FIG. 8 is a diagram showing an example of a group chat screen displayed on the terminal device 2, including the first and second advertisements output by the output unit 36 ​​in the processing unit 12 of the information processing device 1 according to the embodiment.

[0170] As shown in FIG. 8, chat messages CTM1, CTM2, CTM3, CTM4, and CTM5 and advertisements CTA1, CTA2, and CTA3 are displayed on a group chat screen 50, which is a screen for group chat.

[0171] The chat messages CTM1 and CTM4 are chat messages posted by the user U1, the chat message CTM2 is a chat message posted by the user U2, and the chat message CTM3 is a chat message posted by the user U3. m This is a chat message posted by

[0172] Chat message CTM5 is a chat message generated by information processing device 1, and includes text advertisements CTM_A1, CTM_A2, and CTM_A3. Advertisements CTA1, CTA2, and CTA3 are banner advertisements that include images, text, and links, and are sometimes called card advertisements because they are displayed in a carousel format.

[0173] Advertisement CTA1, Advertisement CTA2, Advertisement CTM_A1, and Advertisement CTM_A2 are the first advertisements, and Advertisement CTA3 and Advertisement CTM_A3 are the second advertisements. Advertisement CTA1 and Advertisement CTM_A1 are advertisements for AAA Hotels, Advertisement CTA2 and Advertisement CTM_A2 are advertisements for DDD Hotels, and Advertisement CTA3 and Advertisement CTM_A3 are advertisements for CCC Hotels.

[0174] Advertisement CTM_A1 and Advertisement CTA1 are advertisements for the same AAA Hotel, and Advertisement CTA1 includes a description of the AAA Hotel, an image and the name of the AAA Hotel, and link information. By operating the terminal device 2 and selecting Advertisement CTA1, the user U can display the AAA Hotel's landing page on the terminal device 2.

[0175] Advertisement CTM_A2 and Advertisement CTA2 are advertisements for the same DDD Hotel, and Advertisement CTA2 includes a description of DDD Hotel, an image and the name of DDD Hotel, and link information. By operating terminal device 2 and selecting Advertisement CTA2, user U can display the landing page of DDD Hotel on terminal device 2.

[0176] Ad CTM_A3 and Ad CTA3 are both advertisements for the same CCC Hotel, with Ad CTA3 including a description of the CCC Hotel, and Ad CTA2 including an image and name of the CCC Hotel as well as link information. By operating terminal device 2 and selecting Ad CTA3, user U can display the CCC Hotel landing page on terminal device 2.

[0177] The second advertisement provided to the terminal device 2 by the output unit 36 ​​also includes an advertisement CTA 4 (not shown) outside the display area of ​​the terminal device 2. Fig. 9 is a diagram showing an example of the first advertisement and the second advertisement output by the output unit 36 ​​in the processing unit 12 of the information processing device 1 according to the embodiment and displayed in a carousel format.

[0178] In the example shown in FIG. 9, the first and second advertisements output by the output unit 36 ​​and displayed in a carousel include advertisements CTA1, CTA2, CTA3, and CTA4. Advertisements CTA1 and CTA2 are first advertisements and are initially displayed in the top position on the left and the second position, while advertisements CTA3 and CTA4 are second advertisements and are arranged in lower positions to the right of the first advertisement. Advertisement CTA4 is initially located outside the display area 51 of the terminal device 2. Note that the number of second advertisements arranged outside the display area 51 of the terminal device 2 in the initial state is not limited to one.

[0179] The advertisements CTA1, CTA2, CTA3, and CTA4 are displayed in a carousel, moving in the direction of arrangement in response to operations (for example, swiping or scrolling) by the user U. Furthermore, the advertisements CTA1, CTA2, CTA3, and CTA4 may be displayed in a carousel, rotating one by one at regular intervals after a predetermined period of time has elapsed since the initial display began.

[0180] In this way, the first area and the second area are arranged in a direction (horizontal direction in FIG. 8) perpendicular to the arrangement direction (vertical direction in FIG. 8) of chat messages on the group chat screen 50. In the area including the first area and the second area, the advertisements CTA1, CTA2, CTA3, and CTA4 are displayed in a carousel format.

[0181] Note that the advertisements CTM_A1, CTM_A2, and CTM_A3 are text advertisements in the form of messages, and are displayed in the same display format as chat messages on the group chat screen. Note that in the example shown in Figure 8, the advertisements CTM_A1, CTM_A2, and CTM_A3 do not include a link to a landing page, but they can include a link to a landing page.

[0182] Advertisements CTA1, CTA2, CTA3, and CTA4 are banner advertisements that include images, text, and links, and are also sometimes called card advertisements because they are displayed in a carousel format.

[0183] When the advertisements displayed in the display area 51 are changed by the carousel display, the output unit 36 ​​can output to the terminal device 2 a request to change the content of the chat message CTM5 so that the chat message CTM5 includes a text advertisement corresponding to the advertisement displayed in the display area 51. This makes it possible to prevent the content of the chat message CTM5 from including anything other than the text advertisement corresponding to the advertisement displayed in the display area 51.

[0184] FIG. 10 is a diagram showing an example of a group chat screen displayed on the terminal device 2, including the first advertisement, the second advertisement, and the grounds information output by the output unit 36 ​​in the processing unit 12 of the information processing device 1 according to the embodiment.

[0185] On the group chat screen 50 shown in FIG. 10, following advertisements CTM_A1, CTM_A2, CTM_A3, CTA1, CTA2, CTA3, and CTA4, a chat message CTM6 including grounds information is displayed.

[0186] The basis information included in chat message CTM6 is the character string "Since you were looking for a hotel near Osaka Station, we will provide you with the above sponsor information (+Ad)", which allows chat group user U to easily understand why advertisements CTM_A1, CTM_A2, CTM_A3, CTA1, CTA2, CTA3, and CTA4 are being displayed. Therefore, the information processing device 1 can enhance the advertising effectiveness of advertisements CTM_A1, CTM_A2, CTM_A3, CTA1, CTA2, CTA3, and CTA4.

[0187] [3.3.8. Allocation Unit 37] The allocation unit 37 allocates advertising fees for advertisements on the chat message screen as funds for the usage fee of the generation AI. This allows the information processing device 1 to provide a chat service using the generation AI without requiring the user U to pay the usage fee for the generation AI.

[0188] In addition, if the advertising fee for the advertisement on the chat message screen cannot be fully appropriated as the source of the usage fee for the generation AI, the allocation unit 37 can allocate the difference to the user U.

[0189] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 11 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0190] 11, the processing unit 12 of the information processing device 1 determines whether or not a posting request has been received (step S10). If the processing unit 12 determines that the posting request has been received (step S10: Yes), the processing unit 12 outputs the chat message included in the posting request to the terminal device 2 of the user U in the same group as the terminal device 2 that sent the posting request (step S11).

[0191] When the processing of step S11 is completed or when it is determined that a posting request has not been received (step S10: No), the processing unit 12 determines whether or not it is time to provide an advertisement (step S12). The advertisement providing timing is, for example, a timing when the processing unit 12 determines that an effective advertisement can be provided based on the content of the posted chat message, or a predetermined timing, but is not limited to such examples.

[0192] When the processing unit 12 determines that it is time to provide an advertisement (step S12: Yes), it selects an advertisement to be displayed in a first area on the group chat screen as a first advertisement based on information of multiple users U participating in the group chat (step S13).

[0193] Furthermore, the processing unit 12 selects an advertisement to be displayed in the second area on the screen of the group chat as a second advertisement based on the conversation history between the users U in the group chat (step S14). Furthermore, the processing unit 12 generates basis information that is information indicating the basis for the selection condition of the second advertisement (step S15).

[0194] Next, the processing unit 12 outputs the first advertisement selected in step S13, the second advertisement selected in step S14, and the basis information generated in step S15 to the terminal device 2 of each user U in the group chat (step S16).

[0195] When the processing of step S16 is completed or when it is determined that the timing to provide an advertisement has not come (step S12: No), the processing unit 12 determines whether the timing to end the operation has come (step S17). The processing unit 12 determines that the timing to end the operation has come when, for example, the power of the information processing device 1 is turned off.

[0196] If the processing unit 12 determines that the operation end time has not yet arrived (step S17: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S17: Yes), it terminates the processing shown in Figure 11.

[0197] [5. Modifications] In the above example, the generation AI is described as a text generation AI, but the generation AI is not limited to such an example and may be, for example, a multimodal generation AI. A multimodal generation AI is, for example, a generation AI that can generate text and images from text and images.

[0198] The second selection unit 35 can also use a multimodal generation AI to generate advertising condition information indicating second advertising conditions from a conversation history including images and stamps. Examples of the multimodal generation AI include, but are not limited to, GPT-4 Turbo with vision, Gemini, and CM3Leon (Chameleon Multimodal Model).

[0199] Furthermore, the generation processing unit 40 of the second selection unit 35 can also estimate the situation of a group in a chat room using a generation AI based on the history of conversations between a plurality of users U in the chat room.

[0200] The generation processing unit 40 inputs, for example, information including a conversation history between multiple users U in a chat room and instruction information instructing the generation AI to estimate the group situation as input information, and causes the generation AI to estimate the group situation in the chat room.

[0201] The instruction information includes, for example, the string "The given message history is the history of conversations between multiple users U in a chat room. Based on this conversation history, please estimate the situation of the group in the chat room. The situation is defined as follows." and situation definition information.

[0202] The instruction information may include information showing examples that link conversation examples with situation examples, thereby enabling the generation AI to accurately estimate the situation. The generation AI may also be a generation AI that has been trained by fine tuning or the like using a data set of conversations and situations of multiple users U, and in this case, the input information input to the generation AI may not include instruction information.

[0203] The generation processing unit 40 can also cause the generation AI to generate advertising condition information indicating the second advertising condition based on the estimated group situation. The group situation can be, but is not limited to, the type of topic of the group, the depth of the topic of the group, the atmosphere of the group, the hierarchical relationship of the user U in the group, the level of intimacy of the group, the level of humor, etc.

[0204] For example, the generation processing unit 40 inputs information including the group's situation and instruction information instructing the generation AI to generate advertising condition information indicating second advertising conditions as input information, and causes the generation AI to generate advertising condition information indicating the second advertising conditions, which are conditions for an advertisement to be displayed in the second area. The instruction information may be, for example, a string such as "Please specify the conditions for an advertisement to be proposed to a group of the given situation," but is not limited to such an example. The instruction information may also include definition information for the situation.

[0205] Furthermore, the output unit 36 ​​can provide the second advertisement to, for example, only some of the users U among the multiple users U belonging to the group, or can provide the advertisement in a different manner for each user U. For example, the output unit 36 ​​provides the second advertisement to only the top k users U in descending order of the number of chat messages posted in a chat room of a chat group. k is x% (x is, for example, 50) of the total number of users U in the group, but is not limited to this example.

[0206] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 12. Fig. 12 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0207] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0208] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0209] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0210] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 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.

[0211] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, the CPU 81 may obtain these programs from another device via the network N.

[0212] [7. Other] 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.

[0213] 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.

[0214] For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Furthermore, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0215] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0216] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a first selection unit 33, a second selection unit 35, and an output unit 36. The first selection unit 33 selects an advertisement to be displayed in a first area on the group chat screen based on information about multiple users U participating in the group chat. The second selection unit 35 selects an advertisement to be displayed in a second area on the group chat screen based on a conversation history between users U in the group chat. The output unit 36 ​​outputs the advertisement selected by the first selection unit 33 and the advertisement selected by the second selection unit 35. This enables the information processing device 1 to improve the selectability of advertisements in the chat room of the group chat.

[0217] The second selection unit 35 also includes a generation processing unit 40 that inputs information including the conversation history between users U as input information to the generation AI and causes the generation AI to generate advertising condition information indicating the conditions for advertisements to be displayed in the second area, and a selection processing unit 41 that selects advertisements to be displayed in the second area based on the advertising condition information generated by the generation processing unit 40. This allows the information processing device 1 to accurately select advertisements that meet the conditions indicated by the advertising condition information.

[0218] Furthermore, the generation processing unit 40 inputs information including information on multiple users U and a conversation history between the users U as input information to the generation AI, and causes the generation AI to generate advertisement condition information indicating the conditions of the advertisement to be displayed in the second area. This allows the information processing device 1 to accurately select an advertisement that meets the conditions indicated by the advertisement condition information.

[0219] Furthermore, the generation processing unit 40 inputs information including information instructing the generation of grounds for the conditions indicated in the advertising condition information as input information to the generation AI, causes the generation AI to generate grounds information that indicates the grounds for the conditions indicated in the advertising condition information and is information to be displayed on the group chat screen, and the output unit 36 ​​outputs the grounds information generated by the generation processing unit 40. In this way, the information processing device 1 allows the user U to easily understand the reason for selecting the advertisement to be displayed in the second area.

[0220] Furthermore, the second selection unit 35 selects an advertisement to be displayed in the second area based on the content of a chat message posted by one of the multiple users U and the history of conversations between the users U in the group chat before the chat message was posted. This enables the information processing device 1 to improve the selectivity of advertisements in the chat room of the group chat.

[0221] The information processing device 1 also includes an identification unit 34 that identifies chat messages posted by users U in chat rooms other than the chat room of the group chat, and a second selection unit 35 selects advertisements to be displayed in the second area based on the conversation history between users U and the chat messages identified by the identification unit 34. This enables the information processing device 1 to improve the selectivity of advertisements in the chat room of the group chat.

[0222] Furthermore, the identification unit 34 identifies other chat rooms based on chat messages posted by the user U in the chat room of the group chat. This enables the information processing device 1 to improve the selectivity of advertisements in the chat room of the group chat.

[0223] Furthermore, the first selection unit 33 selects an advertisement to be displayed in the first area based on information about multiple users U participating in the group chat and the content of a chat message posted by any one of the multiple users U. This enables the information processing device 1 to improve the selectivity of advertisements in the chat room of the group chat.

[0224] Furthermore, in the first and second areas, advertisements are displayed in the same display format as chat messages on the group chat screen, thereby allowing the information processing device 1 to display advertisements seamlessly in the chat room.

[0225] The first and second areas are arranged in a direction perpendicular to the arrangement direction of chat messages on the group chat screen, and advertisements are displayed in a carousel format in the area including the first and second areas, allowing the information processing device 1 to display advertisements in a conspicuous manner in the chat room.

[0226] Furthermore, the second selection unit 35 reselects an advertisement based on a plurality of chat messages posted as evaluations of the advertisement by a plurality of users U. This enables the information processing device 1 to improve the selectability of advertisements in the chat room of the group chat.

[0227] The information processing device 1 also includes an allocating unit 37 that allocates advertising fees for advertisements on the chat message screen as a source of usage fees for the generation AI, thereby enabling the information processing device 1 to easily absorb the costs associated with using the generation AI.

[0228] The information processing device 1 also includes a determination unit 32 that determines one or more of the size of at least one of the first area and the second area, the display mode of the advertisement, and the frequency of advertisement output, based on the number of users U participating in the group chat. This enables the information processing device 1 to improve the visibility of advertisements in the chat room of the group chat.

[0229] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, 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 been modified and improved in various ways based on the knowledge of those skilled in the art.

[0230] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0231] 1. Information processing equipment 2,21,22,···,2 m ,2 n terminal device 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Advertising information storage unit 22 Chat setting information storage unit 23 Conversation history memory section 30 Reception 31 Acquisition Department 32 Decision Section 33 First Selection Section 34 Specific part 35 Second Selection Section 36 Output section 37 Allocation Section 40 Generation processing section 41 Selection processing section 100 Information Processing Systems N Network

Claims

1. a first selection unit that selects an advertisement to be displayed in a first area on the screen of the group chat based on information of a plurality of users participating in the group chat; a second selection unit that selects an advertisement to be displayed in a second area on the screen of the group chat based on a history of conversations between the users in the group chat; an output unit that outputs the advertisement selected by the first selection unit and the advertisement selected by the second selection unit.

1. An information processing device comprising:

2. The second selection unit a generation processing unit that inputs information including a conversation history between the users as input information to a generation AI and causes the generation AI to generate advertisement condition information indicating conditions for the advertisement to be displayed in the second area; a selection processing unit that selects an advertisement to be displayed in the second area based on the advertisement condition information generated by the generation processing unit.

2. The information processing apparatus according to claim 1, wherein:

3. The generation processing unit Inputting information including information about the plurality of users and a conversation history between the users as input information to a generation AI, and causing the generation AI to generate advertisement condition information indicating conditions for an advertisement to be displayed in the second area.

3. The information processing apparatus according to claim 2, wherein:

4. The generation processing unit inputting information including information instructing the generation of grounds for the conditions indicated in the advertising condition information as input information to the generation AI, and causing the generation AI to generate grounds information that indicates the grounds for the conditions indicated in the advertising condition information and is information to be displayed on the screen of the group chat; The output unit outputting the basis information generated by the generation processing unit; 4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

5. The second selection unit An advertisement to be displayed in the second area is selected based on the content of a chat message posted by any one of the plurality of users and a history of conversations between the users in the group chat before the chat message is posted.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

6. an identification unit that identifies chat messages posted by the users in chat rooms other than the chat room of the group chat; The second selection unit An advertisement to be displayed in the second area is selected based on a history of conversations between the users and the chat messages identified by the identification unit.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

7. The identification unit Identifying the other chat rooms based on chat messages posted by the users in the chat rooms of the group chat.

7. The information processing apparatus according to claim 6,

8. The first selection unit An advertisement to be displayed in the first area is selected based on information of the plurality of users participating in the group chat and content of a chat message posted by any one of the plurality of users.

2. The information processing apparatus according to claim 1, wherein:

9. In the first area and the second area, the advertisement is displayed in the same display manner as the chat message on the group chat screen.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

10. The first area and the second area are arranged in a direction perpendicular to the direction in which chat messages are arranged on the group chat screen, and the advertisements are displayed in a carousel in an area including the first area and the second area.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

11. The second selection unit Reselecting the advertisement based on a plurality of chat messages posted by the plurality of users as evaluations of the advertisement.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

12. an allocating unit that allocates advertising fees for the advertisements on the chat message screen as a resource for the usage fee for the generation AI; 4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

13. a determination unit that determines one or more of a size of at least one of the first area and the second area, a display mode of the advertisement, and an output frequency of the advertisement based on the number of the users participating in the group chat; 4. The information processing device according to claim 1, wherein the information processing device is a computer.

14. 1. A computer-implemented information processing method, comprising: a first selection step of selecting an advertisement to be displayed in a first area on the screen of the group chat based on information of a plurality of users participating in the group chat; a second selection step of selecting an advertisement to be displayed in a second area on the screen of the group chat based on a history of conversations between the users in the group chat; an output step of outputting the advertisement selected in the first selection step and the advertisement selected in the second selection step. An information processing method comprising:

15. a first selection step of selecting an advertisement to be displayed in a first area on the screen of the group chat based on information of a plurality of users participating in the group chat; a second selection step of selecting an advertisement to be displayed in a second area on the screen of the group chat based on a history of conversations between the users in the group chat; an output step of outputting the advertisement selected by the first selection step and the advertisement selected by the second selection step. An information processing program characterized by:

Images