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

Abstract

To allow for more detailed analysis about a user.SOLUTION: An information processing device comprises an acquisition unit and a generation unit. The acquisition unit acquires user information of each user belonging to a prescribed user group. The generation unit generates an explanation content including a natural language explaining a user image of the prescribed user group by inputting an instruction sentence instructing the explanation of the user image of the prescribed user group on the basis of the user information into a model learned so as to generate an answer sentence to the input question sentence.SELECTED DRAWING: Figure 11

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] With the rapid spread of the Internet, for example, techniques related to analysis using various information on the Internet have been provided. For example, techniques have been provided that enable detailed analysis of users who have input search queries. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7135235 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques leave room for improvement in enabling more detailed analysis of users.

[0005] The present application has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can enable more detailed analysis of users. [Means for solving the problem]

[0006] The information processing device of the present application is characterized by having an acquisition unit that acquires user information of each user belonging to a specified user group, and a generation unit that generates explanation content including natural language that explains the user image of the specified user group by inputting an instruction sentence that instructs a model trained to generate an answer sentence to an input question sentence to explain the user image of the specified user group based on the user information. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide an effect of enabling more detailed analysis of the user. [Brief description 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. [Diagram 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Diagram 3] FIG. 3 is a diagram (1) showing an example of a UI screen according to the embodiment. [Figure 4] FIG. 4 is a diagram (2) showing an example of a UI screen according to the embodiment. [Diagram 5] FIG. 5 illustrates an example of a prompt for generating a title for a user image. [Figure 6] FIG. 6 illustrates an example of a prompt for generating an iconic image of a user figure. [Figure 7] FIG. 7 illustrates an example of a prompt for generating a summary of a user profile. [Figure 8] FIG. 8 is a diagram showing an example of a prompt for generating a characteristic worry of a user profile. [Figure 9] FIG. 9 is a diagram showing an example of a prompt for generating purchasing decision axes for a user profile. [Figure 10] FIG. 10 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of the configuration of an information processing device according to an embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of a user information storage unit according to the embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of a prompt information storage unit according to the embodiment. [Figure 14] FIG. 14 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 15] FIG. 15 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application 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 the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated explanations are omitted.

[0010] (Embodiment) [1. Configuration of information processing system] 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 and an information processing device 100. The terminal device 10 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 in a wired or wireless manner. 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 performs detailed analysis of users. The user, for example, performs product planning / improvement, marketing research, competitive research, etc. The terminal device 10 may be any device that can realize the processing in the embodiment. In addition, the terminal device 10 may 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 a tablet, and is a mobile terminal device capable of communicating with any server device via a wireless communication network such as 4G to 5G (Generation) or LTE (Long Term Evolution). The terminal device 10 has a screen such as a liquid crystal display having a touch panel function, and may receive various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by a user's finger or a stylus. In FIG. 2, the terminal device 10 is used by a user U1.

[0013] The information processing device 100 is an information processing device intended to enable detailed analysis of a user, and may be any device capable of implementing the processes in the embodiment. The information processing device 100 is implemented, for example, by a server device or a cloud system that provides a platform for performing detailed analysis of a user. For example, the information processing device 100 generates commentary content that explains a user image (persona) and provides information on the generated commentary content. The commentary content may include natural language. The commentary content is content that explains, for example, what characteristics the user image has, what worries the user image has, what products the user image is interested in, what criteria the user image uses to make purchases, and so on.

[0014] The information processing device 100 has a model. The model is, for example, a sentence generation model that is trained on data published on the Internet. For example, the model is a GPT (Generative Pre-trained Transformer) model that generates answers to questions. Such a model generates answers to questions from data published on the Internet. Since new data is published on the Internet every day, the answers provided by the model are updated every day. That is, even if a question of the same content is asked, different data is referenced when the model generates an answer depending on the time of the question, and therefore different answers are generated. In addition, since the model can provide detailed answers to questions in a wide range of fields, a wide variety of questions are asked of the model by users.

[0015] Although FIG. 1 illustrates a case in which the terminal device 10 and the information processing device 100 are separate devices, the terminal device 10 and the information processing device 100 may be integrated.

[0016] [2. An example of information processing] FIG. 2 is a diagram showing an example of information processing of the information processing system 1 according to the embodiment. FIG. 3 is a diagram showing an example of a UI screen according to the embodiment. The UI screen shown in FIG. 3 is a UI screen displayed on the terminal device 10, and information according to the operation of the user U1 is displayed on the screen G1. FIG. 2 will be described below with reference to FIG. 3 as appropriate. The user U1 inputs a search query by operating the terminal device 10 (step S11). In FIG. 3, the user U1 inputs "powdered milk" as a search query in a box B1 for inputting a search query. The user U1 also specifies a categorization axis (hereinafter, appropriately referred to as a "categorization axis") for dividing a user group by operating the terminal device 10 (step S12). The categorization axis is an axis prepared in advance for dividing a user group. For example, the categorization axis is an axis prepared in advance by an administrator who manages the information processing device 100, an administrator of a server device or a cloud system that provides a platform for performing detailed analysis on users, an administrator who provides the content of the screen G1, or the like. In FIG. 3, user U1 specifies a "marketing-oriented gender chronology" in box B2 for specifying a categorization axis. For example, user U1 specifies the "marketing-oriented gender chronology" by selecting the "marketing-oriented gender chronology" from among "age," "marketing-oriented gender chronology," "attribute area," "occupation," "family composition," "income," "behavioral history," "distance between nearest station and home," "shopping destination," "shopping purchasing tendency," "housing situation," and the like in box B2. Note that these options in box B2 are merely examples and need not be limiting. Also, the categorization axis may be specified by input rather than selection.

[0017] The information processing device 100 acquires information regarding the search query entered by the user U1 (step S101). In FIG. 3, since the user U1 has entered "powdered milk", the information processing device 100 acquires information that "powdered milk" has been entered in the search query. The information processing device 100 also acquires information regarding the categorization axis specified by the user U1 (step S102). In FIG. 3, since the user U1 has specified the "gender-chronology axis for marketing", the information processing device 100 acquires information that the "gender-chronology axis for marketing" has been specified as the categorization axis.

[0018] The information processing device 100 identifies a user group whose search history includes the search query input by the user U1 (step S103). In FIG. 3, the information processing device 100 identifies a user group whose search history includes "powdered milk". For example, the information processing device 100 identifies a user group whose search history includes "powdered milk" a predetermined number of times or more within a predetermined period. The information processing device 100 also divides the user group into groups according to a categorization axis specified by the user U1 (step S104). In FIG. 3, the information processing device 100 divides the user group into groups according to a "gender-age axis for marketing". For example, the information processing device 100 divides the user group into groups according to attributes such as gender and age in accordance with the "gender-age axis for marketing". Note that, when the user U1 specifies, for example, "behavior history" instead of the "gender-age axis for marketing" as the categorization axis, the information processing device 100 divides the user group into groups according to a specific behavior history. Furthermore, when the user U1 specifies, for example, "shopping purchasing tendency" as a categorization axis, the information processing device 100 divides the user group into groups based on the specific shopping purchasing tendency. In this way, the information processing device 100 performs categorization according to the categorization axis specified by the user U1.

[0019] The information processing device 100 generates user information for each category (step S105). For example, the information processing device 100 acquires user information of each user belonging to each category, and generates user information for each category. For example, the information processing device 100 generates user information for each category based on statistical processing of the user information of each user belonging to the category. At this time, the information processing device 100 may generate information indicating attributes of users belonging to the category, or may generate information indicating a word cloud of keywords included in the search history of users belonging to the category. In addition, the information processing device 100 may perform processing for displaying the generated user information arranged by category.

[0020] 3, the information processing device 100 performs a process for displaying, for example, information J11, which is information indicating attributes of users belonging to category K1, and information J21, which is information indicating attributes of users belonging to category K2, side by side. The information processing device 100 also performs a process for displaying, for example, information J12, which is information indicating characteristics of users belonging to category K1, and information J22, which is information indicating characteristics of users belonging to category K2, side by side. The information processing device 100 also performs a process for displaying, for example, information J13, which is information indicating interests / concerns of users belonging to category K1, and information J23, which is information indicating interests / concerns of users belonging to category K2, side by side.

[0021] Furthermore, the information processing device 100 performs processing for displaying, side by side, information J14, which is information indicating a word cloud of keywords included in the search history of a user belonging to category K1, and information J24, which is information indicating a word cloud of keywords included in the search history of a user belonging to category K2, for example. Furthermore, the information processing device 100 performs processing for displaying, side by side, information J15, which is information indicating a word cloud of keywords indicating brands of interest to a user belonging to category K1, and information J25, which is information indicating a word cloud of keywords indicating brands of interest to a user belonging to category K2, for example.

[0022] In order to grasp the user image of the category, the user U1 selects one of the categories by operating the terminal device 10 (step S13). The user image of the selected category is displayed on the terminal device 10. In FIG. 3, the user U1 selects the category K1. For example, the user U1 selects the category K1 by operating the information J16, which is information for displaying an explanation of the user image of the category K1. Hereinafter, the information processing device 100 causes a text generation model (generation AI) to generate an explanation of the user image of the category K1. Hereinafter, the generation AI that the information processing device 100 causes to generate an explanation of the user image is appropriately referred to as "model M1". The model M1 is a GPT model trained to generate an answer sentence to an input question sentence.

[0023] The information processing device 100 acquires information about the category selected by the user U1 (step S106). In FIG. 3, since the user U1 selected the category K1, the information processing device 100 acquires information that the category K1 was selected.

[0024] The information processing device 100 acquires user information of category K1. For example, the information processing device 100 acquires user information of each user belonging to category K1. Also, for example, the information processing device 100 may acquire user information of category K1 from the user information generated for each category in step S105.

[0025] The information processing device 100 uses the model M1 to generate explanation content explaining the user image of the category K1 (step S107). Here, the model M1 is a model that outputs explanation content explaining the user image of the category corresponding to the user information when it receives user information of a predetermined category and an instruction sentence (prompt) instructing to explain the user image of the category based on the user information. For example, when it receives user information of the category K1 and a prompt instructing to explain the user image of the category based on the user information, the model M1 outputs explanation content explaining the user image of the category K1.

[0026] The information processing device 100 uses the model M1 to generate information on, for example, the title, icon image, summary, characteristic worries, purchasing decision axis (for example, trends in product reviews charted to show which evaluations have high priority), and simulated interviews (user chat simulators including virtual personas). Note that these examples are merely examples, and the information generated by the information processing device 100 using the model M1 may not be limited to these examples. Furthermore, the information processing device 100 provides information on commentary content of the user profile of the category K1 generated using the model M1 (step S108). Moreover, an example of information generated by the information processing device 100 using the model M1 is the information displayed on the UI screen shown in FIG. 4.

[0027] FIG. 4 is a diagram showing an example of a UI screen according to the embodiment. The UI screen shown in FIG. 4 is a UI screen displayed on the terminal device 10, and the screen G2 displays information according to the operation of the user U1 on the screen G1. The UI screen shown in FIG. 4 is a screen showing details of a user image. The screen G2 displays information on a user image of a corresponding category according to the category selected by the user U1. For example, when the user U1 selects the category K1, the screen G2 displays information on the user image of the category K1, and when the user U1 selects the category K2, the screen G2 displays information on the user image of the category K2. Hereinafter, the generation of various information on the user image will be described with appropriate reference to FIG. 4.

[0028] The information processing device 100 generates information on the title of a user profile of the category K1 using the model M1. In FIG. 4, the information processing device 100 generates a title (information J1) such as "A new mother struggling with breastfeeding." FIG. 5 is a diagram showing an example of a prompt for generating a title of a user profile. Note that the prompt shown in FIG. 5 is an example of a prompt for generating a title of a user profile, and the prompt for generating a title of a user profile does not need to be limited to this example. The information processing device 100 generates a title (information J1) by inputting a prompt as shown in FIG. 5 into the model M1. The prompt shown in FIG. 5 includes information on "elements," "data," and "output contents," and a title is generated based on each piece of information.

[0029] Here, in the prompt shown in FIG. 5, "element" is information indicating the rule or format of the information to be output. For example, "element" is information instructing to generate the user image so that the lifestyle of the user image can be understood. For example, "element" is information instructing to output information on the user image that is closest to the category K1 when multiple user images are included. For example, "element" is information instructing to output information on the user image that is closest to the category K1 when multiple user images are included in the user image of category K1. "Data" is information prepared in advance. For example, information estimated as being of interest to all is input in "interests common to all". For example, the ratio of the gender of the target is input in "gender ratio". For example, the ratio of the age of the target is input in "age ratio". For example, the user attribute of the target is input in "user attribute". For example, information based on the browsing history in a knowledge search service such as a knowledge community site where knowledge and wisdom are shared on the Internet is input in "concerns". For example, information estimated as being of interest from the search history is input in "interesting keywords". Also, for example, in the "Brand of Interest" field, the brand name of the product in which the user is interested is entered.

[0030] The information processing device 100 generates information about an icon image of a user image of a category K1 using the model M1. In FIG. 4, the information processing device 100 generates an icon image (information J2). FIG. 6 is a diagram showing an example of a prompt for generating an icon image of a user image. Note that the prompt shown in FIG. 6 is an example of a prompt for generating an icon image of a user image, and the prompt for generating an icon image of a user image does not have to be limited to this example. The information processing device 100 generates an icon image (information J2) by inputting a prompt as shown in FIG. 6 into the model M1. Note that the icon image (information J2) is information generated using an image generation model based on information such as interest information, gender, and age.

[0031] The information processing device 100 generates information on the summary of the user profile of the category K1 by using the model M1. In FIG. 4, the information processing device 100 generates a summary (information J3). FIG. 7 is a diagram showing an example of a prompt for generating a summary of a user profile. The prompt shown in FIG. 7 is an example of a prompt for generating a summary of a user profile, and the prompt for generating a summary of a user profile may not be limited to this example. The information processing device 100 generates a summary (information J3) by inputting a prompt as shown in FIG. 7 to the model M1. The prompt shown in FIG. 7 is similar to the prompt shown in FIG. 5 regarding the title, but differs in that, for example, a long sentence (a large number of characters) is output in the output contents. The prompt shown in FIG. 7 includes information on "element", "data", and "output contents", and a summary is generated based on each information. The details of each information of the prompt are the same as those in FIG. 5, so a description thereof will be omitted.

[0032] The information processing device 100 generates information on characteristic worries of a user profile of the category K1 by using the model M1. In FIG. 4, the information processing device 100 generates characteristic worries (information J4). FIG. 8 is a diagram showing an example of a prompt for generating characteristic worries of a user profile. The prompt shown in FIG. 8 is an example of a prompt for generating characteristic worries of a user profile, and the prompt for generating characteristic worries of a user profile may not be limited to this example. The information processing device 100 generates characteristic worries (information J4) by inputting a prompt as shown in FIG. 8 into the model M1. The prompt shown in FIG. 8 includes, for example, information based on a browsing history in a knowledge search service and information instructing to summarize. For example, information instructing to express worries is included. Also, for example, information instructing to express worries with emphasis on highly related items based on a search history is included. The prompt shown in FIG. 8 includes information on "elements" and "worries / questions", and characteristic worries are generated based on each information.

[0033] The information processing device 100 generates information on the purchasing judgment axis of the user profile of the category K1 by using the model M1. In FIG. 4, the information processing device 100 generates the purchasing judgment axis (information J5). FIG. 9 is a diagram showing an example of a prompt for generating the purchasing judgment axis of the user profile. The prompt shown in FIG. 9 is an example of a prompt for generating the purchasing judgment axis of the user profile, and the prompt for generating the purchasing judgment axis of the user profile may not be limited to this example. The information processing device 100 generates the purchasing judgment axis (information J5) by inputting a prompt as shown in FIG. 9 into the model M1. The prompt shown in FIG. 9 includes, for example, information instructing to extract product reviews based on the browsing history and to score the extracted product reviews. The purchasing judgment axis (information J5) includes information such as price, delivery, quality, and after-sales support in addition to the product reviews. The prompt shown in FIG. 9 includes, for example, information instructing to extract price, delivery, quality, after-sales support, and to score the extracted price, delivery, quality, after-sales support, and the like. The prompt shown in Figure 9 includes information on "elements" and "product reviews," and purchasing decision criteria are generated based on each piece of information.

[0034] The information processing device 100 generates information on a pseudo interview of a user profile of the category K1 by using the model M1. In FIG. 4, the information processing device 100 generates a pseudo interview (information J6). The pseudo interview (information J6) includes bold characters, Ming type characters, and underlined characters. The bold characters (such as "ease of dissolving") are not in the search history and may not exist, while the Ming type characters (such as "allergic constitution" and "nutritional balance") are in the search history. The underlined characters (such as "baby" and "growth") are co-occurring keywords of "powdered milk" entered by the user U1 in the search query. The information processing device 100 generates the pseudo interview (information J6) by inputting a prompt for generating a pseudo interview of a user profile to the model M1. The prompt includes, for example, information instructing to generate an answer to a question as the user profile indicated by the summary, and information instructing to generate an answer to the question by estimating the summary, the question, and the answer of the user indicated by the summary. For example, text T2 is information estimated by model M1 as an answer to a question in text T1. Also, text T3 is information (choices of questions) estimated by model M1 as a further question to the answer in text T2. For example, the next question may be selected by model M1 from the choices in text T3.

[0035] In the above embodiment, the UI screen shown in Fig. 3 is an example and may not be limited to this example. For example, on the screen G1, other information may be displayed arranged by category, not limited to information indicating the attributes of the user, information indicating the characteristics of the user, information indicating the interests / concerns of the user, information indicating a word cloud of keywords included in the search history of the user, and information indicating a word cloud of keywords indicating a brand of interest to the user.

[0036] In the above embodiment, the UI screen shown in Fig. 4 is an example, and may not be limited to this example. For example, on the screen G2, other information may be generated and displayed by the model M1, not limited to information related to the title of the user image, an icon image, a summary, a characteristic concern, a purchase decision axis, and a simulated interview (a user chat simulator including a virtual persona).

[0037] 3. Configuration of terminal device Next, the configuration of the terminal device 10 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Fig. 10, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0038] (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.

[0039] (Input section 12) The input unit 12 accepts various operations from a user. In Fig. 2, the input unit 12 accepts various operations from a user U1. For example, the input unit 12 may accept various operations from a user via a display surface 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.

[0040] (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 content (for example, screen G1, screen G2, etc.) based on information received from the information processing device 100.

[0041] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by executing various programs stored in a storage device inside the terminal device 10 using a RAM (Random Access Memory) as a working area by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). For example, the various programs include application programs installed in the terminal device 10. For example, the various programs include application programs that display content based on information received from the information processing device 100. The control unit 14 is also realized by an integrated circuit, such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0042] As shown in FIG. 10, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0043] (Receiving unit 141) The receiving unit 141 receives information for displaying content based on information transmitted from the information processing device 100. For example, the receiving unit 141 receives information for displaying user information of each category generated based on a search query input by a user and a specified categorization axis. For example, the receiving unit 141 receives information for displaying information of category K1 and category K2 on the screen G1. Also, for example, the receiving unit 141 receives information for displaying various information of a user image generated based on user information and a model M1. For example, the receiving unit 141 receives information for displaying details of the user image such as the title (information J1) and summary (information J3) of the screen G2.

[0044] (Transmitter 142) The transmission unit 142 transmits user operation information. For example, the transmission unit 142 transmits user operation information for content based on information transmitted from the information processing device 100. For example, the transmission unit 142 transmits information related to a search query input by a user, information related to a specified categorization axis, and information related to a selected category. For example, the transmission unit 142 transmits information related to a search query input by a user and information related to a specified categorization axis in order to display the content of the screen G1. Also, for example, the transmission unit 142 transmits information related to a category selected by a user in order to display the content of the screen G2. For example, the transmission unit 142 transmits information related to a category selected by a user for the content of the screen G1.

[0045] 4. 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. 11. Fig. 11 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 11, 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 have an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0046] (Communication unit 110) The communication unit 110 is realized by, for example, a NIC etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the terminal device 10 etc. 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. 11, the storage unit 120 has a user information storage unit 121 and a prompt information storage unit 122.

[0048] The user information storage unit 121 stores user information. Here, Fig. 12 shows an example of the user information storage unit 121 according to the embodiment. As shown in Fig. 12, the user information storage unit 121 has items such as "user ID" and "user information". In addition, the "user information" further includes items such as "attribute information", "search history", and "browsing history".

[0049] "User ID" indicates identification information for identifying a user. "User information" indicates user information. User information includes information such as attribute information, search history, and browsing history. "Attribute information" indicates attribute information. In the example shown in FIG. 12, an example is shown in which conceptual information such as "attribute information #1" and "attribute information #2" is stored in "attribute information", but in reality, information such as gender and age is stored. "Search history" indicates search history. In the example shown in FIG. 12, an example is shown in which conceptual information such as "search history #1" and "search history #2" is stored in "search history", but in reality, information such as search date and time, number of searches, and keywords used in the search are stored. "Browse history" indicates browse history. In the example shown in FIG. 12, an example is shown in which conceptual information such as "browsing history #1" and "browsing history #2" is stored in "browsing history", but in reality, information such as browse date and time, number of searches, and keywords indicating the browsed target are stored.

[0050] The prompt information storage unit 122 stores information related to prompts. An example of the prompt information storage unit 122 according to the embodiment is shown in Fig. 13. As shown in Fig. 13, the prompt information storage unit 122 has items such as "prompt ID", "type", and "prompt".

[0051] "Prompt ID" indicates identification information for identifying a prompt. "Type" indicates the type of object for generating a user image (for example, title, icon image, summary, characteristic worries, purchasing decision criteria, mock interview, etc.). "Prompt" indicates a prompt. In the example shown in FIG. 13, conceptual information such as "Prompt #1" and "Prompt #2" is stored in "Prompt", but in reality, information such as sentences using natural language is stored. For example, information such as that shown in FIGS. 5 to 9 is stored. Furthermore, "Prompt" may have items such as "Element", "Data", "Output Content", "Worries / Questions", and "Product Reviews", and corresponding information may be stored therein.

[0052] (Control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU, an MPU, or the like, executing various programs stored in a storage device inside the information processing device 100 using a RAM as a working area. The control unit 130 is also realized, for example, by an integrated circuit such as an ASIC or an FPGA.

[0053] 11, the control unit 130 has an acquisition unit 131, an identification unit 132, a separation unit 133, a generation unit 134, and a provision unit 135, 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. 11, and may be other configurations as long as they perform the information processing described below.

[0054] (Acquisition part 131) The acquiring unit 131 acquires various types of information from the storage unit 120. In addition, the acquiring unit 131 stores the acquired various types of information in the storage unit 120.

[0055] 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.

[0056] The acquisition unit 131 acquires information related to a search query. For example, the acquisition unit 131 acquires information related to a search query input by a user. The acquisition unit 131 also acquires information related to a categorization axis. For example, the acquisition unit 131 acquires information related to a categorization axis specified by a user. The acquisition unit 131 also acquires information related to a category. For example, the acquisition unit 131 acquires information related to a category selected by a user. The acquisition unit 131 also acquires user information of each user belonging to a predetermined category (corresponding to a predetermined user group). The acquisition unit 131 also acquires user information of each user belonging to each category for each category.

[0057] (Specific Section 132) The identification unit 132 identifies a user group based on the information about the search query acquired by the acquisition unit 131. For example, the identification unit 132 identifies a user group whose search history includes a predetermined search query based on the information about the search query acquired by the acquisition unit 131. For example, the identification unit 132 identifies a user group whose search history includes a search query input by a user.

[0058] (Cutting section 133) The dividing unit 133 divides the user group based on the information on the categorization axis acquired by the acquisition unit 131. For example, the dividing unit 133 divides the user group by a predetermined categorization axis based on the information on the categorization axis acquired by the acquisition unit 131. For example, the dividing unit 133 divides the user group by a categorization axis designated by a user.

[0059] (Generation unit 134) The generation unit 134 generates user information of a predetermined category based on the user information of each user acquired by the acquisition unit 131. In addition, the generation unit 134 generates user information of each category based on the user information of each user acquired by the acquisition unit 131.

[0060] The generating unit 134 generates commentary content that explains the user image. For example, the generating unit 134 generates commentary content that explains the user image of a user who belongs to a predetermined category.

[0061] The generation unit 134 generates commentary content that explains the user image by using the model M1. For example, the generation unit 134 generates commentary content that explains the user image by inputting a prompt to the model M1 that instructs the model M1 to explain the user image of a user who belongs to a predetermined category based on user information. For example, the generation unit 134 generates commentary content that explains the user image by inputting user information of a predetermined category and a prompt to the model M1.

[0062] The generation unit 134 generates a title explaining the user image, for example, by inputting user information of a predetermined category and a prompt for generating a title (for example, FIG. 5, etc.) to the model M1 for generating a title. The generation unit 134 also generates an icon image explaining the user image, for example, by inputting user information of a predetermined category and a prompt for generating an icon image (for example, FIG. 6, etc.) to the model M1 for generating an icon image. The generation unit 134 also generates a summary explaining the user image, for example, by inputting user information of a predetermined category and a prompt for generating a summary (for example, FIG. 7, etc.) to the model M1 for generating a summary.

[0063] Similarly, the generation unit 134 generates a characteristic worry that explains a user image, for example, by inputting user information of a predetermined category and a prompt for generating a characteristic worry (e.g., FIG. 8, etc.) to the model M1 for generating a characteristic worry. Also, the generation unit 134 generates a purchase decision axis that explains a user image, for example, by inputting user information of a predetermined category and a prompt for generating a purchase decision axis (e.g., FIG. 9, etc.) to the model M1 for generating a purchase decision axis. Also, the generation unit 134 generates a pseudo interview that explains a user image, for example, by inputting user information of a predetermined category and a prompt for generating a pseudo interview to the model M1 for generating a pseudo interview.

[0064] (Provider 135) The providing unit 135 provides information on the commentary content generated by the generating unit 134. For example, the providing unit 135 provides information for displaying the commentary content generated by the generating unit 134. The providing unit 135 may provide information for displaying a part of the commentary content generated by the generating unit 134. For example, the providing unit 135 may provide information for displaying only a part of the information of the content of the screen G2 (for example, only the title). Upon receiving the information provided by the providing unit 135, the terminal device 10 displays the content based on the received information.

[0065] [5. 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. 14. Fig. 14 is a flowchart showing the procedure of information processing by the information processing system 1 according to the embodiment.

[0066] As shown in FIG. 14, the information processing device 100 acquires user information of each user who belongs to a predetermined category (step S201).

[0067] The information processing device 100 acquires a GPT model trained to generate an answer to an input question (step S202).

[0068] The information processing device 100 generates explanation content by inputting a prompt to instruct the user to explain a user image of a predetermined category based on the acquired user information to the acquired GPT model (step S203).

[0069] The information processing device 100 provides information about the generated commentary content (step S204).

[0070] 6. Effects As described above, the information processing device 100 according to the embodiment includes the acquisition unit 131 and the generation unit 134. The acquisition unit 131 acquires user information of each user belonging to a predetermined user group. The generation unit 134 generates explanation content including natural language explaining the user image of the predetermined user group by inputting an instruction sentence that instructs a model trained to generate an answer sentence to an input question sentence to explain the user image of the predetermined user group based on the user information.

[0071] As a result, the information processing device 100 according to the embodiment can generate commentary content that explains the user image of a predetermined user group, and therefore can perform detailed analysis of users belonging to the predetermined user group. For example, the information processing device 100 according to the embodiment can perform detailed analysis of users belonging to a predetermined user group, such as what characteristics the user image has, what worries the user image has, what products the user image is interested in, and what criteria the user image uses to make purchases.

[0072] Furthermore, the generation unit 134 generates guidance content by inputting user information of a predetermined user group, which is user information generated based on the user information acquired by the acquisition unit 131, and an instruction sentence into a model.

[0073] As a result, the information processing device 100 according to the embodiment can generate user information of a specific user group based on user information of users belonging to the specific user group, and generate commentary content based on that information, thereby making it possible to provide general-purpose commentary content regarding the user image of the specific user group.

[0074] In addition, the generation unit 134 generates information regarding the specified information corresponding to a specified user group by inputting an instruction sentence for generating the specified information to a model for generating the specified information of a user image.

[0075] As a result, the information processing device 100 according to the embodiment can generate explanatory content targeting specified information of the user image, thereby enabling detailed analysis of users belonging to a specified user group for each specified information of the user image.

[0076] Furthermore, the acquiring unit 131 acquires user information of each user belonging to a predetermined user group identified based on a predetermined search query.

[0077] As a result, the information processing device 100 according to the embodiment can identify a user group in accordance with the user's request and enable detailed analysis of users belonging to that user group, thereby promoting improvement of usability for users.

[0078] Moreover, the acquiring unit 131 acquires user information of each user belonging to a predetermined user group divided based on a predetermined axis.

[0079] As a result, the information processing device 100 according to the embodiment can divide user groups according to the user's requests and enable detailed analysis of users belonging to those user groups, thereby promoting improvement of usability for users.

[0080] The instruction sentence includes information indicating the rules or format of the output information of the model.

[0081] As a result, the information processing apparatus 100 according to the embodiment can specify the rules and format of information to be output in response to a user's request, thereby promoting improvement of usability for the user.

[0082] The instruction text includes information instructing that, when the user image of a predetermined user group includes a plurality of user images, the user image that is closest to the predetermined user group is to be explained.

[0083] As a result, the information processing device 100 according to the embodiment can generate explanatory content for a user image that is in line with a specified user group, thereby enabling a more detailed analysis of users belonging to a specified user group.

[0084] The instruction text includes information instructing that the lifestyles of users belonging to a predetermined user group are to be explained.

[0085] This enables the information processing device 100 according to the embodiment to perform a detailed analysis of the lifestyles of users belonging to a predetermined user group.

[0086] [7. Hardware Configuration] Moreover, the information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 having a configuration as shown in Fig. 15. Fig. 15 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, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0087] The CPU 1100 operates and controls each unit based on a program 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 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0088] The HDD 1400 stores programs executed by the CPU 1100, data used by such 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.

[0089] 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.

[0090] 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 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.

[0091] 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.

[0092] [8. 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 by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0093] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0094] Furthermore, the above-described embodiments can be appropriately combined as long as the processing contents are not contradictory.

[0095] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0096] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0097] 1. Information Processing Systems 10 Terminal Equipment 11 Communications Department 12 Input section 13 Output section 14 Control section 100 Information processing device 110 Communications Department 120 Storage section 121 User information storage unit 122 Prompt information storage unit 130 Control section 131 Acquisition Department 132 Specific part 133 Cutting section 134 Generation part 135 Provision Department 141 Receiving unit 142 Transmitter N Network

Claims

1. An acquisition unit that acquires user information of each user belonging to a predetermined user group; a generation unit that generates explanation content including natural language explaining the user image of the predetermined user group by inputting an instruction sentence that instructs the user to explain the user image of the predetermined user group based on the user information to a model trained to generate an answer sentence to an input question sentence; 13. An information processing device comprising:

2. The generation unit is The instruction text and user information of the predetermined user group, which is user information generated based on the user information acquired by the acquisition unit, are input to the model, thereby generating the commentary content.

2. The information processing apparatus according to claim 1,

3. The generation unit is The instruction sentence for generating predetermined information is input to the model for generating predetermined information of a user image, thereby generating information about the predetermined information corresponding to the predetermined user group.

2. The information processing apparatus according to claim 1,

4. The acquisition unit is Obtaining user information for each user belonging to the predetermined user group identified based on a predetermined search query 2. The information processing apparatus according to claim 1,

5. The acquisition unit is Acquire user information of each user belonging to the predetermined user group divided based on a predetermined axis.

2. The information processing apparatus according to claim 1,

6. The instruction sentence includes information indicating a rule or a format of the output information of the model.

2. The information processing apparatus according to claim 1,

7. The instruction sentence includes information instructing that, when the user image of the predetermined user group includes a plurality of user images, the user image closest to the predetermined user group is to be explained.

2. The information processing apparatus according to claim 1,

8. The instruction sentence includes information instructing that the lifestyle of the user belonging to the predetermined user group is to be explained.

2. The information processing apparatus according to claim 1,

9. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring user information of each user belonging to a predetermined user group; a generation step of generating explanation content including natural language explaining the user image of the predetermined user group by inputting an instruction sentence instructing to explain the user image of the predetermined user group based on the user information to a model trained to generate an answer sentence to an input question sentence; 13. An information processing method comprising:

10. An acquisition step of acquiring user information of each user belonging to a predetermined user group; a generation step of generating explanation content including natural language explaining the user image of the predetermined user group by inputting an instruction sentence instructing the model, which is trained to generate an answer sentence to an input question sentence, to explain the user image of the predetermined user group based on the user information; An information processing program characterized by causing a computer to execute the above.

Images