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

Abstract

Properly monetize using generative AI. [Solution] The information processing device according to the present application includes an acquisition unit and a provision unit. The acquisition unit acquires user histories from multiple domains. The provision unit provides a generation AI with user information, including history in response to a user question, from the history acquired by the acquisition unit.

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] 2. Description of the Related Art Conventionally, there is known a technique for charging for conversions when they occur via the Internet. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-177525 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional technology has not established a standard mechanism for monetization using generative AI, making it impossible to properly monetize using generative AI.

[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 appropriately perform monetization using generation AI. [Means for solving the problem]

[0006] The information processing device of the present application is characterized by having an acquisition unit that acquires user history from multiple domains, and a provision unit that provides history acquired by the acquisition unit that responds to the user's questions as user information to a generation AI. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to achieve an effect of appropriately monetizing using the generation AI. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of a generation AI server according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a user information storage unit according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of an advertisement information storage unit according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a conversion information storage unit according to the embodiment. [Figure 9] FIG. 9 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 10] FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

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

[0010] (Embodiment) [1. Information Processing System Configuration] An information processing system 1 shown in Fig. 1 will be described. As shown in Fig. 1, the information processing system 1 includes a terminal device 10, a generation AI server 50, and an information processing device 100. The terminal device 10, the generation AI server 50, and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication. Fig. 1 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment.

[0011] The terminal device 10 is an information processing device used by a user who asks a question. For example, it is used by a user who asks a question during a search and desires an answer that will be useful for the search. The terminal device 10 may be any device that can implement the processing in the embodiment. The terminal device 10 may also be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. FIG. 2 shows a case where the terminal device 10 is a smartphone.

[0012] The terminal device 10 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 4G to 5G (Generations) or LTE (Long Term Evolution). The terminal device 10 may have a screen such as a liquid crystal display with a touch panel function, and may accept various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by a user's finger or stylus. In FIG. 2, the terminal device 10 is used by a user U1.

[0013] The generation AI server 50 is an information processing device that manages the generation AI (provides a platform for the generation AI) and may be any device capable of implementing the processes described in the embodiments. The generation AI server 50 generates answer content by, for example, inputting information provided by the information processing device 100 into the generation AI, and provides the answer content to the information processing device 100. The answer content includes at least an answer to the user's question and an advertisement selected from predetermined candidates as candidates for advertisements to be provided along with the answer (for example, the top advertisement among advertisements listed in a predetermined order). The answer content is information indicating the answer to the user's question and the candidate selected from the advertisement candidates, and need not be content actually displayed on the terminal device 10. Therefore, the content actually displayed on the terminal device 10 may be generated by the information processing device 100 based on information regarding the answer to the user's question and information regarding the candidate selected from the advertisement candidates.

[0014] Generative AI is, for example, a sentence generation model trained on data published on the Internet. An example is a GPT (Generative Pre-trained Transformer) model that generates answers to questions. Such models generate answers to questions from data published on the Internet. Since new data is published on the Internet every day, the answers generated by the model are updated daily. In other words, even if the same question is asked, different answers will be generated depending on the time of the question, as the data referenced when the model generates the answer will differ. In addition, since the model can provide detailed answers to questions in a wide range of fields, users ask the model a wide variety of questions.

[0015] The information processing device 100 is an information processing device intended to appropriately perform monetization using a generation AI, and may be any device capable of implementing the processing described in the embodiments. For example, when the information processing device 100 receives a question from a user, the information processing device 100 provides information (input information to be input to the generation AI) to the generation AI server 50 to generate answer content including an answer to the user's question. The input information to the generation AI includes, for example, at least text information about the question, advertisement candidate information regarding advertisement candidates, user information about the user, and a prompt instructing the generation AI to perform information processing using various information. The information processing device 100 also provides, for example, answer content (output information output from the generation AI) provided by the generation AI server 50 to the user. Furthermore, the information processing device 100 determines, for example, a fee to be requested from the advertiser of the selected advertisement (advertisement included in the answer content) in response to a user's operation on the advertisement selected as an advertisement to be provided along with the answer (advertisement included in the answer content). For example, the fee is the fee incurred when a user clicks on the advertisement and a conversion occurs. In other words, the fee charged to the advertiser is an affiliate-like performance fee. Furthermore, the information processing device 100 determines the cost for using the generation AI (the amount charged to the provider of the generation AI, etc.) based on, for example, the volume of the question text (e.g., the number of texts, etc.). In other words, the charge to the provider of the generation AI, etc. (e.g., the administrator of the generation AI server 50, etc.) is a pay-per-use charge. Note that the charge may be based on the volume of all text, including the prompt text, rather than being limited to the question text. For this reason, the prompt may be generated so that the text is shorter based on the history of selections made by the user.

[0016] 1 shows a case where the generation AI server 50 and the information processing device 100 are separate devices, but the generation AI server 50 and the information processing device 100 may be integrated. Therefore, the information processing device 100 may provide a platform for the generation AI.

[0017] [2. An example of information processing] In searches using conventional queries, advertisers can be charged for conversions from ads displayed alongside search results, but in searches using generative AI, a standard monetization mechanism has not been established, making it impossible to properly monetize using generative AI. This application was made in light of the above, and aims to properly monetize using generative AI.

[0018] In a query-based search, the display order of search results is determined based on factors such as bit amount (bid amount) and user click-through rate. In contrast, in a search using generative AI, rules for determining the display order of search results are predefined, and the display order may be determined based on those rules, or the display order may be determined based on learning. In this case, for example, data indicating what type of people purchased what items may be used as training data. While typical generative AI performs supervised learning that emphasizes fairness using data from the Internet, if data from a specific service can be used as training data, it becomes possible to perform learning using data that is not known to typical generative AI. Note that when display order is determined based on learning, there are cases where even negative monetization results in a win. However, because monetization, such as displaying results higher according to bit amount, is also important, rules based on bit amount may also be added.

[0019] In this way, the display order may be determined using multiple rules for differentiating display. When determining the display order based on learning, for example, advertisements for products that users are likely to buy (or want) may be displayed in a predetermined slot on the UI screen, and advertisements for products based on the bit rate may be displayed in a separate advertising slot (sponsor slot). While overly prominent advertising slots on the UI screen may be detrimental to the service, displaying advertisements for products users are likely to want can attract users who perceive value. For example, if the advertisement is related to e-commerce (EC), an advertisement about inventory may be displayed; if it is related to gourmet food, an advertisement about hotel reservations may be displayed; and if it is related to recruitment, an advertisement about job openings may be displayed. This makes it possible to encourage action by appropriately presenting inventory, reservations, job openings, etc., depending on the user's inquiry to the AI. Furthermore, by presenting multiple values, such as for a surprise, and allowing the user to select, advertisements for products based on the selected value may be displayed.

[0020] Furthermore, a user's history may include different service histories across multiple domains. When generating answers for a user using a generation AI, if the history from all such domains is used as input information, it is possible to generate and select content that suits the user, but the amount of information can be large, which can place a heavy burden on the system. Furthermore, since the cost of the generation AI is calculated based on the amount of text entered, the cost increases as the amount of information increases. For this reason, it is thought that the burden can be reduced by selecting the history corresponding to the question from the history obtained from multiple domains and inputting only the selected history as user information.

[0021] FIG. 2 is a diagram illustrating an example of information processing in the information processing system 1 according to the embodiment. When user U1 asks a question, the information processing device 100 accepts the question from user U1 (step S101). For example, the information processing device 100 accepts the question in text form from user U1. The information processing device 100 provides information (input information to be input to the generation AI) to the generation AI server 50 to generate answer content including an answer to the question for user U1 (step S102). For example, the information processing device 100 provides, as input information to the generation AI, advertisement candidate information regarding advertisement candidates for selecting an advertisement to be provided to user U1 along with the answer, text information of the question accepted from user U1, user information regarding user U1, and information regarding a prompt that instructs the generation AI to perform information processing using various information. The prompt is an instruction document that instructs what information processing to perform using various information, such as an instruction document such as, "Please select an advertisement appropriate for user U1." By such an instruction document, an advertisement to be included in the answer content is selected from the user information of user U1, advertisement candidate information, and text information of the question. Also, by an instruction document such as, for example, "Please generate an answer to the question including the content of the selected advertisement," an answer to be included in the answer content is generated from the user information of user U1, advertisement candidate information, and text information of the question. Note that the prompt may be predetermined or may be generated by the information processing device 100. For example, the prompt may be generated according to the user information of user U1, the question received from user U1, advertisement candidate information, etc.

[0022] The prompt also includes an instruction document that instructs the generation AI on what information to use from the input information to execute information processing. For example, the prompt may include an instruction document that instructs the generation AI on whether to use all of the candidate advertisement information for advertisement selection, or on whether to narrow down the candidate advertisements based on user information. The prompt also includes an instruction document that instructs the generation AI on what information processing to execute using the input information to execute. For example, the prompt may include an instruction document that instructs the generation AI on how to use user information to select an advertisement. In this way, the prompt includes an instruction document that instructs the generation AI on what information to use from the input information to execute information processing and how to execute it.

[0023] When the generation AI server 50 acquires input information for the generation AI from the information processing device 100, it inputs the input information provided from the information processing device 100 to the generation AI (step S103). The generation AI generates answer content based on the input information (step S104). For example, the generation AI generates an answer to user U1's question based on the input information and generates answer content including the generated answer. Furthermore, for example, the generation AI selects an advertisement based on the input information and generates answer content including the selected advertisement. For example, the generation AI selects an advertisement based on the history of a domain frequently used by user U1 from user U1's domain history and generates answer content including the selected advertisement. Furthermore, for example, the generation AI selects an advertisement based on the history selected in response to user U1's question from user U1's domain history and generates answer content including the selected advertisement. In this case, for example, user U1's domain history is a domain history generated by linking user U1's log data from multiple domains and is used to generate a prompt for generating an answer to user U1's question. In this way, log data from multiple domains may be linked to generate a prompt for generating an answer for user U1 when user U1 asks a question. For example, even for the same user or question, a domain may be selected from multiple domains depending on the user's situation at the time, the question text, etc. Furthermore, for example, the generation AI may select an advertisement based on the generated answer to user U1's question and generate answer content including the selected advertisement. In this way, the generation AI generates answer content including an advertisement selected based on at least one of user information of user U1 and an answer generated as an answer to user U1's question. Furthermore, the generation AI may generate answer content that includes the answer generated as an answer to user U1's question in a predetermined frame (third frame) and an advertisement selected from candidate advertisements in a first frame. Furthermore, the generation AI may generate answer content that includes an advertisement selected from candidate advertisements in the first frame and an advertisement selected based on predetermined information such as a bid amount in a second frame.

[0024] The generation AI server 50 provides the information output from the generation AI to the information processing device 100 (step S105). For example, the generation AI server 50 provides answer content generated by the generation AI. When the information processing device 100 acquires the answer content from the generation AI server 50, it provides the answer content to the terminal device 10 (step S106). When the terminal device 10 receives the answer content from the information processing device 100, it displays the answer content.

[0025] At this time, a conversion occurs when the user U1 operates (for example, clicks or taps) an advertisement included in the answer content displayed on the terminal device 10. When a conversion occurs, the information processing device 100 stores which advertiser's advertisement the conversion occurred for. Then, the information processing device 100 determines the fee to the advertiser according to the number of conversions tallied during a predetermined period (step S107). For example, the information processing device 100 determines the fee to the advertiser so that the fee increases as the number of conversions increases. Then, the information processing device 100 charges the advertiser the determined fee. Furthermore, the information processing device 100 is not limited to charging the fee determined by tallying the number of conversions, and may charge each time a conversion occurs.

[0026] In the above embodiment, the information processing device 100 may determine the cost for using the generation AI according to the volume of question text received from user U1. For example, the information processing device 100 may determine the cost for using the generation AI so that the cost increases as the volume increases. The information processing device 100 may then perform processing to pay the determined cost to the provider of the generation AI, etc. Note that the determination of the cost for using the generation AI may be performed at any time, for example, in step S101. Furthermore, the information processing device 100 may determine the cost for using the generation AI according to the volume of question text received from user U1 during a predetermined period. By determining the cost for using the generation AI in this way and charging the advertiser based on conversions, it is possible to provide a service to user U1 free of charge.

[0027] In the above embodiment, the information processing device 100 determines the fee for using the generation AI based on the volume of the question text. However, if user U1 asks a further question in response to an answer included in the answer content provided to user U1, processing for payment of the fee for using the generation AI for the question in response to that answer may not be performed. That is, the information processing device 100 may determine the fee for using the generation AI only for the first question. Furthermore, an answer to be included in the answer content is generated based on a prompt. For this reason, the prompt may be a prompt that instructs the user to generate an answer that will prevent further questions from being asked in response to the answer, and the information processing device 100 may generate such a prompt and provide information regarding such a prompt. Furthermore, the prompt may be, for example, a prompt that instructs the user to generate an answer that encourages conversion, and the information processing device 100 may generate such a prompt and provide information regarding such a prompt. Furthermore, the prompt may be, for example, a prompt generated based on the history of a domain frequently used by user U1 from the domain history of user U1, and the information processing device 100 may generate such a prompt and provide information regarding such a prompt. Furthermore, the prompt may be, for example, a prompt generated based on a history selected in response to a question from user U1's domain history, and the information processing device 100 may generate such a prompt and provide information regarding such a prompt. Furthermore, the prompt may be, for example, a prompt instructing that the amount of advertising in the first slot be varied depending on the length of a question-and-answer exchange between user U1 and the generation AI, and the information processing device 100 may generate such a prompt and provide information regarding such a prompt. Furthermore, the prompt may be, for example, a prompt generated to shorten text based on a history selected in response to user U1, and the information processing device 100 may generate such a prompt and provide information regarding such a prompt.

[0028] In the above embodiment, an example has been described in which the information processing device 100 determines the cost to an advertiser and charges the advertiser, but the information processing device 100 may determine the cost to an advertising agency that has a predetermined relationship with the advertiser and charge the advertising agency. In the above embodiment, the information processing device 100 determines the cost based on conversion, but the information processing device 100 may determine the cost to the advertising agency based on customer referrals. In other words, the cost to the advertising agency may be determined based on the number of users referred to the advertising agency. Note that an advertising agency may have a predetermined relationship with multiple advertisers.

[0029] In the above embodiment, an example has been described in which the generation AI selects an advertisement from candidate advertisements and generates answer content, but the candidate advertisements may be used to generate information on conditions for listing the advertisement. The information processing device 100 may then obtain information on conditions for listing from the generation AI server 50, perform listing, and generate answer content.

[0030] [3. Configuration of terminal device] Next, the configuration of the terminal device 10 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Fig. 3, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0031] (Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC), etc. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100, etc., via the predetermined network N.

[0032] (Input section 12) The input unit 12 accepts various operations from the user. In FIG. 2, the input unit 12 accepts various operations from the user U1. For example, the input unit 12 may accept various operations from the user via a display screen using a touch panel function. The input unit 12 may also accept various operations from buttons provided on the terminal device 10 or a keyboard or mouse connected to the terminal device 10. For example, the input unit 12 accepts text operations for inputting a question.

[0033] (Output section 13) The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays answer content provided from the information processing device 100.

[0034] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device inside the terminal device 10 using a RAM (Random Access Memory) as a work area. For example, these various programs include application programs installed in the terminal device 10. For example, these various programs include an application program that displays answer content provided by the information processing device 100. The control unit 14 is also realized by an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0035] As shown in FIG. 3, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0036] (Receiving unit 141) The receiving unit 141 receives, for example, answer content provided from the information processing device 100. For example, the receiving unit 141 receives answer content including an answer generated by the generation AI as an answer to a user's question. Also, for example, the receiving unit 141 receives answer content including an advertisement selected by the generation AI as an advertisement to be provided to the user.

[0037] (Transmitter 142) The transmitting unit 142 transmits, for example, text information of a question input by the user to the terminal device 10. For example, the transmitting unit 142 transmits text information of a question input on a UI screen for the user to ask a first question. Furthermore, for example, the transmitting unit 142 transmits text information of a question input on a UI screen for the user to ask a further question in response to the provided answer content. Note that the transmitting unit 142 may also transmit user information of the user who asked the question.

[0038] [4. Configuration of the Generative AI Server] Next, the configuration of the generation AI server 50 according to the embodiment will be described with reference to Figure 4. Figure 4 is a diagram showing an example configuration of the generation AI server 50 according to the embodiment. As shown in Figure 4, the generation AI server 50 has a communication unit 51 and a control unit 52. The generation AI server 50 may also have an input unit (e.g., a keyboard or mouse) that accepts various operations from an administrator of the generation AI server 50, and a display unit (e.g., an LCD display) that displays various information.

[0039] (Communications Department 51) The communication unit 51 is realized by, for example, a NIC etc. The communication unit 51 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100 etc. via the network N.

[0040] (control unit 52) The control unit 52 is a controller, and is realized by, for example, a CPU or MPU executing various programs stored in a storage device inside the generation AI server 50 using RAM as a work area. The control unit 52 is also realized by, for example, an integrated circuit such as an ASIC or FPGA.

[0041] 4, the control unit 52 has a receiving unit 521, a generating unit 522, and a transmitting unit 523, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 52 is not limited to the configuration shown in FIG. 4, and may be any other configuration as long as it performs the information processing described below.

[0042] (Receiving unit 521) The receiving unit 521 receives, for example, information provided from the information processing device 100. For example, the receiving unit 521 receives text information of a question entered by a user. Also, for example, the receiving unit 521 receives advertisement candidate information for selecting an advertisement to be provided to the user (the user who asked the question). Also, for example, the receiving unit 521 receives user information of the user (the user who asked the question). Also, for example, the receiving unit 521 receives prompt information generated by the information processing device 100. In this way, the receiving unit 521 receives, for example, text information of a question, advertisement candidate information, user information, and prompt information. Note that all of this information is input to the generation AI.

[0043] (Generation unit 522) The generation unit 522 generates answer content by, for example, inputting information provided from the information processing device 100 into the generation AI. For example, the generation unit 522 generates an answer to be included in the answer content. For example, the generation unit 522 sets the answer output from the generation AI as the answer to be included in the answer content. Also, for example, the generation unit 522 selects an advertisement to be included in the answer content. For example, the generation unit 522 sets the advertisement output from the generation AI as the advertisement to be included in the answer content. For example, the generation unit 522 sets the advertisement output from the generation AI as the advertisement to be included in the first slot of the answer content. For example, the generation unit 522 may generate answer content that includes the advertisement output from the generation AI in the first slot and includes an advertisement selected based on predetermined information such as a bid amount in the second slot.

[0044] (Transmitter 523) The transmission unit 523 provides, for example, the answer content generated by the generation unit 522 to the information processing device 100. For example, the transmission unit 523 provides information output from the generation AI. For example, the transmission unit 523 provides information related to the answer output from the generation AI or information related to the advertisement output from the generation AI.

[0045] 5. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 5, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing device 100 may also have an input unit (e.g., a keyboard or a mouse) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display) that displays various information.

[0046] (Communication unit 110) The communication unit 110 is realized by, for example, a NIC. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the terminal device 10, the generation AI server 50, and the like via the network N.

[0047] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in Fig. 5, the storage unit 120 has a user information storage unit 121, an advertisement information storage unit 122, and a conversion information storage unit 123.

[0048] The user information storage unit 121 stores user information. For example, the user information storage unit 121 stores information indicating the user's attributes, hobbies, preferences, behavioral history, etc. FIG. 6 shows an example of the user information storage unit 121 according to the embodiment. The information stored in the user information storage unit 121 is used, for example, to generate answer content. As shown in FIG. 6, the user information storage unit 121 has items such as "user ID" and "user information."

[0049] "User ID" indicates identification information for identifying a user. "User information" indicates user information. In the example shown in FIG. 6, conceptual information such as "User information #1" and "User information #2" is stored in "User information," but in reality, information indicating the user's attributes such as age, gender, and place of residence, information indicating hobbies and preferences, information indicating behavioral history, etc. is stored.

[0050] The advertisement information storage unit 122 stores advertisement information. For example, the advertisement information storage unit 122 stores information indicating the advertiser, the advertisement category, the target user, and the like, as well as image data of the advertisement. The information stored in the advertisement information storage unit 122 is used, for example, to generate response content. Here, FIG. 7 shows an example of the advertisement information storage unit 122 according to the embodiment. As shown in FIG. 7, the advertisement information storage unit 122 has items such as "advertising ID," "advertiser," and "advertising information."

[0051] "Advertising ID" indicates identification information for identifying an advertisement. "Advertiser" indicates an advertiser. "Advertising Information" indicates advertising information. In the example shown in FIG. 7, conceptual information such as "Advertising Information #1" and "Advertising Information #2" is stored in "Advertising Information," but in reality, image data or the like is stored. Also, for example, a URL where the image data is located, or a file path name indicating the storage location, may be stored.

[0052] The conversion information storage unit 123 stores conversion information. For example, the conversion information storage unit 123 stores information indicating a user who has performed a conversion, an advertisement for which a conversion has been performed, etc. The information stored in the conversion information storage unit 123 is used, for example, to count the number of conversions or to determine fees for advertisers. FIG. 8 shows an example of the conversion information storage unit 123 according to the embodiment. As shown in FIG. 8, the conversion information storage unit 123 has items such as a "conversion ID," an "advertisement ID," a "user ID," and a "conversion date and time."

[0053] "Conversion ID" indicates identification information for identifying a conversion. "Advertising ID" indicates identification information for identifying an advertisement. "User ID" indicates identification information for identifying a user. "Conversion date and time" indicates the date and time of the conversion. In the example shown in Figure 8, conceptual information such as "Conversion date and time #1" and "Conversion date and time #2" is stored in "Conversion date and time," but in reality, information indicating the date and time is stored.

[0054] (control unit 130) The control unit 130 is a controller, and is realized by, for example, a CPU or an MPU executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also realized by, for example, an integrated circuit such as an ASIC or an FPGA.

[0055] 5, the control unit 130 has an acquisition unit 131, a generation unit 132, a provision unit 133, and a determination unit 134, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be any other configuration as long as it performs the information processing described below.

[0056] (Acquisition part 131) The acquiring unit 131 acquires various pieces of information from the storage unit 120. The acquiring unit 131 also stores the acquired various pieces of information in the storage unit 120.

[0057] The acquisition unit 131 acquires various pieces of information from an external information processing device. The acquisition unit 131 acquires various pieces of information from other information processing devices such as the terminal device 10.

[0058] The acquisition unit 131 receives a question from a user by, for example, acquiring text information of a question input by the user. For example, the acquisition unit 131 receives an initial question from a user by acquiring text information of a question input by the user on a UI screen for asking an initial question. Furthermore, for example, the acquisition unit 131 receives a further question from a user by acquiring text information of a question input by the user on a UI screen for asking a further question about answer content. Furthermore, for example, when a conversion occurs as a result of the user operating an advertisement included in the answer content, the acquisition unit 131 acquires information about the conversion that has occurred.

[0059] The acquisition unit 131 acquires, for example, a user history. For example, the acquisition unit 131 acquires the user history of a plurality of domains. For example, the acquisition unit 131 acquires the user history of a plurality of domains as user information.

[0060] (Generation unit 132) For example, when the generation unit 132 receives a question from a user via the acquisition unit 131 (acquires text information of the question), it causes the generation AI to generate answer content by inputting advertisement candidates, the question (text information of the question), user information, and prompt information to the generation AI. For example, the generation unit 132 provides the advertisement candidate information, the question sentence, the user information, and the prompt information to the generation AI server 50, which inputs the information to the generation AI to generate answer content. For example, the generation unit 132 generates an answer to be included in answer content to be provided to the user who asked the question. Also, for example, the generation unit 132 selects an advertisement to be included in answer content to be provided to the user who asked the question from advertisement candidates. Also, for example, the generation unit 132 causes the answer content generated by the generation AI to be provided to the information processing device 100.

[0061] (Provider 133) The providing unit 133, for example, provides answer content generated by the generation AI to the user by providing it to the terminal device 10. For example, the providing unit 133 provides information about the answer generated by the generation AI. For example, the providing unit 133 provides answer content including the answer generated by the generation AI. For example, the providing unit 133 provides answer content generated based on information about the answer generated by the generation AI. For example, the providing unit 133 obtains information about the answer from the generation AI server 50 and provides answer content generated based on the obtained information about the answer. Also, for example, the providing unit 133 provides information about an advertisement selected by the generation AI. For example, it provides answer content including the advertisement selected by the generation AI. For example, the providing unit 133 provides answer content generated based on information about the advertisement selected by the generation AI. For example, the providing unit 133 obtains information about the advertisement from the generation AI server 50 and provides answer content generated based on the obtained information about the advertisement.

[0062] The providing unit 133 provides, for example, the user history acquired by the acquiring unit 131 to the generation AI server 50. For example, the providing unit 133 provides, as user information, a history that satisfies a predetermined condition among the user history acquired by the acquiring unit 131. For example, the providing unit 133 provides, as user information, a history that corresponds to a user question among the user history acquired by the acquiring unit 131. Note that, for example, a history that satisfies a predetermined condition is a history selected as a history to be input to the generation AI. For example, a history that satisfies a predetermined condition is a history selected as a history for causing the generation AI to generate answer content. For example, a history that satisfies a predetermined condition is a history selected as a history for causing the generation AI to generate answer content including an answer to a question. For example, a history that satisfies a predetermined condition is a history selected as a history for causing the generation AI to generate answer content including an advertisement aimed at conversion. For example, a history that satisfies a predetermined condition is a history selected as a history for causing the generation AI to generate answer content that includes a predetermined advertisement in a first slot and an advertisement selected from candidate advertisements based on a bid amount in a second slot.

[0063] (Decision unit 134) The determination unit 134 determines the fee to the advertiser, for example, in accordance with a user's operation on an advertisement included in the answer content provided by the provision unit 133. For example, the determination unit 134 determines the fee to the advertiser in accordance with the number of conversions corresponding to the user's operation on an advertisement included in the answer content. Then, the determination unit 134 charges the fee determined in this manner to the advertiser, for example. Furthermore, the determination unit 134 determines the fee for using the generation AI in accordance with, for example, the volume of text indicated by the text information acquired by the acquisition unit 131. Then, the determination unit 134 may perform processing to pay the fee determined in this manner to the provider of the generation AI, for example.

[0064] [6. Information Processing Flow] Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the procedure of information processing by the information processing system 1 according to the embodiment.

[0065] As shown in FIG. 9, the information processing device 100 acquires text information of a question input by a user (step S201).

[0066] The information processing device 100 provides the acquired text information, advertisement candidate information, user information, and prompt information to the generation AI server 50, which inputs the information into the generation AI to generate answer content (step S202).

[0067] The information processing device 100 provides the answer content generated by the generation AI (that is, the answer content provided by the generation AI server 50) to the user (step S203).

[0068] The information processing device 100 determines the cost to the advertiser according to the number of conversions corresponding to the user's operations on the advertisement included in the provided response content (step S204).

[0069] [7. Effects] As described above, the information processing device 100 according to the embodiment includes the acquisition unit 131 and the provision unit 133. The acquisition unit 131 acquires user histories from multiple domains. The provision unit 133 provides, as user information to the generation AI, a history corresponding to a user question from among the histories acquired by the acquisition unit 131.

[0070] As a result, the information processing device 100 according to the embodiment can, for example, charge for conversions by including advertisements in the answer content output by the generation AI, thereby enabling appropriate monetization using the generation AI.

[0071] Furthermore, the providing unit 133 provides the history selected as the history to be input to the generation AI as user information to the generation AI.

[0072] As a result, the information processing apparatus 100 according to the embodiment can appropriately provide, for example, a history to be input to the generation AI as user information.

[0073] Furthermore, the providing unit 133 provides the history selected as the history for causing the generation AI to generate the answer content as user information to the generation AI.

[0074] As a result, the information processing device 100 according to the embodiment can appropriately provide, for example, a history for causing the generation AI to generate answer content as user information.

[0075] Furthermore, the providing unit 133 provides the generation AI with the history selected as the history for causing the generation AI to generate answer content including the answer to the question as user information.

[0076] As a result, the information processing device 100 according to the embodiment can appropriately provide, as user information, a history for causing the generation AI to generate answer content including an answer to a question, for example.

[0077] In addition, the providing unit 133 provides the generation AI with the history selected as user information for causing the generation AI to generate answer content including an advertisement aimed at conversion.

[0078] As a result, the information processing device 100 according to the embodiment can appropriately provide, as user information, a history for causing the generation AI to generate answer content including an advertisement aimed at conversion, for example.

[0079] In addition, the providing unit 133 provides the generation AI with the history selected as user information to generate answer content that includes an advertisement in the first slot and an advertisement selected from candidate advertisements based on the bid amount in the second slot.

[0080] As a result, the information processing device 100 according to the embodiment can appropriately provide, as user information, a history for allowing the generation AI to generate answer content that includes, for example, a predetermined advertisement in the first slot and an advertisement selected from candidate advertisements based on the bid amount in the second slot.

[0081] [8. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 configured as shown in Fig. 10. Fig. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0082] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0083] The HDD 1400 stores programs executed by the CPU 1100, data used by these programs, etc. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0084] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0085] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0086] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0087] [9. 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 a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0088] 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.

[0089] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0090] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0091] 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]

[0092] 1. Information Processing Systems 10 Terminal Equipment 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information processing device 110 Communications Department 120 Storage section 121 User information storage unit 122 Advertising information storage unit 123 Conversion information storage unit 130 control section 131 Acquisition Department 132 Generation part 133 Provision Department 134 Decision Section 141 Receiving unit 142 Transmitter N Network

Claims

1. an acquisition unit for acquiring user histories of multiple domains; a providing unit that provides a history corresponding to the user's question among the history acquired by the acquiring unit as user information to a generation AI; An information processing device comprising:

2. The providing unit The history selected as the history to be input to the generation AI is provided to the generation AI as the user information.

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

3. The providing unit The history selected as the history for generating the answer content by the generation AI is provided to the generation AI as the user information.

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

4. The providing unit The history selected as the history for causing the generation AI to generate the answer content including the answer to the question is provided to the generation AI as the user information.

4. The information processing apparatus according to claim 3,

5. The providing unit The history selected as the history for causing the generation AI to generate the answer content including the advertisement for the purpose of conversion is provided to the generation AI as the user information.

4. The information processing apparatus according to claim 3,

6. The providing unit The answer content includes the advertisement in a first slot, and an advertisement selected from advertisement candidates based on a bid amount in a second slot. The answer content includes a history of selection as a history for causing the generation AI to generate the answer content, and the history of selection is provided to the generation AI as the user information.

6. The information processing apparatus according to claim 5,

7. 1. A computer-implemented information processing method, comprising: an acquisition step of acquiring user histories of multiple domains; a providing step of providing a history corresponding to the user's question among the history acquired by the acquiring step to a generation AI as user information; An information processing method comprising:

8. The procedure to retrieve user history for multiple domains, a provision step of providing a history acquired by the acquisition step, the history corresponding to the user's question, to a generation AI as user information; An information processing program characterized by causing a computer to execute the above.

Images