Device and method

Abstract

A device (1) comprises: an acquisition unit (11) that acquires feature information related to features of a user; and a generation unit (12) that, on the basis of the feature information acquired by the acquisition unit (11), generates a prompt for instructing a generative AI to generate analysis information for analyzing the user. The user may be a user of a commercial resource. The acquisition unit (11) may acquire feature information based on information related to a user of one commercial resource and information related to a user of a reference commercial resource. The generation unit (12) may generate the prompt further on the basis of the information related to the user. The generation unit (12) may generate the prompt further on the basis of the condition of the analysis information.

Description

Device and Method

[0001] One aspect of the present disclosure relates to a device and a method for generating a prompt for instructing an AI that generates analysis information for analyzing a user to generate the analysis information.

[0002] In Patent Document 1 below, a street information providing system configured to manage the acquired user characteristic information in association with an event log is disclosed.

[0003] Japanese Patent Application Laid-Open No. 2006-293880

[0004] In the above street information providing system, for example, it is not possible to generate analysis information for analyzing a user based on the acquired user characteristic information. Therefore, it is desired to generate information that can generate analysis information for analyzing a user.

[0005] The device according to one aspect of the present disclosure includes an acquisition unit that acquires characteristic information regarding the characteristics of a user, and a generation unit that generates a prompt for instructing an AI that generates analysis information for analyzing a user to generate the analysis information based on the characteristic information acquired by the acquisition unit.

[0006] In such an aspect, based on the acquired characteristic information, a prompt for instructing an AI that generates analysis information for analyzing a user to generate the analysis information is generated. That is, it is possible to generate information that can generate analysis information for analyzing a user.

[0007] According to one aspect of the present disclosure, it is possible to generate information that can generate analysis information for analyzing a user.

[0008] This figure shows an example of the functional configuration of the device according to the embodiment. This figure shows an example of a comparison information table. This figure shows an example of a system configuration including the device according to the embodiment. This figure shows a modified version of the system configuration of Figure 3. This figure shows an example of a prompt (1). This figure shows an example of a prompt (2). This figure shows an example of a prompt (3). This figure shows an example of a prompt (4). This figure shows another example of the type example of Figure 8. This figure shows an example of a prompt (5). This figure shows an example of a prompt (6). This figure shows an example of a prompt (7). This figure shows an example of analysis information. This figure shows an example of visualization data (1). This figure shows an example of visualization data (2). This figure shows an example of visualization data (3). This figure shows an example of visualization data (4). This flowchart shows an example of a process executed by the device according to the embodiment. This figure shows an example of the hardware configuration of the computer used in the device according to the embodiment.

[0009] The embodiments of this disclosure will be described in detail below with reference to the drawings. In the description of the drawings, the same elements will be denoted by the same reference numerals, and redundant descriptions will be omitted. Furthermore, the embodiments of this disclosure described below are specific examples of the present invention and are not limited to these embodiments unless otherwise stated to limit the present invention.

[0010] Device 1 is a computer that generates prompts to instruct an AI to generate analytical information for analyzing the user.

[0011] A user is a person or group of people who use any object (for example, a group of multiple people who use any object). A user may be a user of commercial resources. Commercial resources are any resources necessary for a company or business to operate. For example, commercial resources may be stores, goods, or services. In other words, a user may be a user of stores, goods, or services. In this embodiment, it is mainly assumed that the user is a user of a store, but it is not limited to this. In this embodiment, the user may be referred to as "user" or "customer" as appropriate.

[0012] Analytical information is information used to analyze users. For example, analytical information may include information used to analyze what attributes users have, what hobbies and preferences they have, what characteristics they possess, what behavioral tendencies they have, or what kind of image they project.

[0013] Generative AI is a technology that, in response to input from a prompt containing input information, generates content according to one or a combination of the instructions, context, questions, and output formats indicated by the prompt, and returns that content as response information. The prompt can also include input information, in which case the generative AI generates response information based on that input information. The generative AI may be a conversational AI that includes, for example, a Large Language Model (LLM) and a User Interface (UI) for interacting with the user, enabling text-based or voice-based chat with the user. Examples of such generative AI include tsuzumi®, ChatGPT, GPT®-3.5, GPT-4V, and PaLM2.

[0014] A prompt is information indicating instructions or questions to be entered by a user in an interactive system such as a conversation with a generating AI or a command-line interface (CLI). For example, a prompt may express in text the command to be executed by the generating AI, the task to be performed by the generating AI, the background / context that the generating AI should consider (e.g., role, conditions), the question that the generating AI should answer, and the output format of the response information from the generating AI. In addition, input information that will be the target of the command / task to be executed by the generating AI may be attached to the prompt. Such input information includes data files with filenames containing predetermined extensions, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data refers to data such as document data, table data, and graph data that can be processed by a default application program.

[0015] Device 1 may also have the function of RAG (Retrieval-Augmented Generation).

[0016] Figure 1 shows an example of the functional configuration of device 1. As shown in Figure 1, device 1 is composed of a storage unit 10, an acquisition unit 11 (acquisition unit), a generation unit 12 (generation unit), and an output unit 13.

[0017] Each functional block of Device 1 is intended to function within Device 1, but is not limited to this. For example, some of the functional blocks of Device 1 may function within a computer device separate from Device 1, connected to Device 1 via a network, while appropriately sending and receiving information with Device 1. Furthermore, some functional blocks of Device 1 may be omitted, multiple functional blocks may be integrated into a single functional block, or a single functional block may be broken down into multiple functional blocks.

[0018] The following describes the functions of the device 1 shown in Figure 1.

[0019] The storage unit 10 stores arbitrary information used in calculations in the device 1, as well as the results of calculations in the device 1. The information stored in the storage unit 10 may be referenced as appropriate by each function of the device 1. The information stored in the storage unit 10 may be pre-set information, information purchased in advance, or information acquired at any time by the acquisition unit 11 described later.

[0020] The acquisition unit 11 may acquire any information used in calculations in the device 1 from the storage unit 10 or from itself, or it may acquire (receive) information from other devices such as external devices via a network. The acquisition unit 11 may acquire any information in advance prior to any calculations in the device 1, or it may acquire information when it is needed, in accordance with the requirements of each function of the device 1. The acquisition unit 11 may store the acquired information in the storage unit 10, or it may output it to other functions of the device 1.

[0021] The acquisition unit 11 acquires characteristic information relating to the user's characteristics. The characteristic information is information relating to any characteristic of the user. For example, the characteristic information may be information indicating that there are many visitors (to the store targeted by the user) who like anime. The characteristic information may also be information from any perspective. For example, the characteristic information may be information for each attribute of the store targeted by the user. Store attributes may include, for example, the region where the store is located, the type of store (sushi restaurant, izakaya, yakitori restaurant, ramen shop, etc.).

[0022] The acquisition unit 11 may acquire multiple feature information. The acquisition unit 11 may acquire each of the multiple feature information at the same time, or at different times. In this embodiment, the multiple feature information is simply referred to as "feature information" as appropriate. When the multiple feature information is simply referred to as "feature information," the processing related to the feature information may be based on each of the multiple feature information, or it may be based on any part of the multiple feature information.

[0023] The acquisition unit 11 may acquire characteristic information based on specific user information, which is information about a user of a commercial resource, and standard user information, which is information about a standard user of a commercial resource. The acquisition unit 11 may acquire the specific user information and standard user information (at the same time or at different times), extract characteristic information based on the acquired specific user information and standard user information, and acquire the extracted characteristic information. Note that the extraction of characteristic information may be performed by another functional block of the device 1 (for example, an extraction unit not shown), and the acquisition unit 11 may acquire the characteristic information extracted by that functional block.

[0024] Specific user information is, for example, customer information of a single store, namely store A. In this embodiment, "customer information of store A" is used as an example of specific user information. Customer information of store A may include, for example, information such as age group, gender, place of residence, income group, occupation, purchasing behavior, visited facilities, and app usage.

[0025] The baseline user information is, for example, customer information of a store that serves as the model (baseline) for analysis. In this embodiment, as one specific example of baseline user information, customer information of a store that serves as the model for analysis is used as appropriate, and such customer information is simply referred to as the "model for analysis" as appropriate. The model for analysis may include, for example, information such as age group, gender, place of residence, income group, occupation, purchasing behavior, visited facilities, and app usage. The model for analysis may also be, for example, information obtained by aggregating and averaging customer information for a target region.

[0026] The extraction of feature information will be explained using comparative information that includes specific user information and standard user information for each perspective. Figure 2 shows an example of a comparative information table. In the comparative information table example shown in Figure 2, the perspective, "Label," corresponds to "Store A," which is customer information for Store A, and the model to be analyzed, "Analysis Target Model." For example, in the comparative information table example shown in Figure 2, regarding the perspective of age group, the customer information for Store A is "50 minors, 1000 people in their 20s, ..." (that is, the age group of users of Store A is 50 minors, 1000 people in their 20s, ...), and the analysis target model is "10% minors, 40% people in their 20s, ..." (that is, the age group of the analysis target model is 10% minors, 40% people in their 20s, ...). The extraction of feature information may be performed, for example, based on a comparison between the customer information of Store A included in the comparative information and the analysis target model included in the comparative information. As a concrete example of feature information extraction, one could set a threshold of 20% and extract (determine) customer information from store A that differs from the analysis model by 20% or more as feature information.

[0027] The acquisition unit 11 may acquire comparison information that has been previously stored by the storage unit 10, and may also acquire feature information extracted (by the acquisition unit 11 or other functional blocks of the device 1) based on the acquired comparison information.

[0028] Let's explain another specific example regarding the extraction of feature information. Suppose the customer information for store A consists of 50 minors, 1000 people in their 20s, 500 people in their 30s, 100 people in their 40s, 100 people in their 50s, and 100 people 60 and over. Also, suppose the analysis model consists of 10% minors, 40% in their 20s, 20% in their 30s, 10% in their 40s, 10% in their 50s, and 10% 60 and over. In this case, the number of minors is 50 out of the 1850 people listed in store A's customer information, which is 0.027... The threshold for 10% minors is 0.1 x 20%, which is 0.02 (if it is not included in 0.08 to 0.12, it is considered feature information). 0.027 is not included in 0.08 to 0.12, so it is extracted as feature information (it is a value smaller than the number obtained by subtracting the threshold from the data of the analysis model, so it has the feature "few minors").

[0029] The acquisition unit 11 may store the acquired feature information in the storage unit 10, or it may output it to the generation unit 12 and the output unit 13.

[0030] The generation unit 12 generates a prompt to instruct the generation AI to generate arbitrary information.

[0031] The generated AI may be stored in other devices connected to device 1 via a network, and configured to allow information exchange. Figure 3 shows an example of a system configuration including device 1. In the system configuration shown in Figure 3, the generated AI, LLM20, is stored in LLM server 2, which is connected to device 1 via a network. When needed, device 1 has LLM20 perform processing via the network, receives the execution results, and uses them.

[0032] The generated AI may be stored within device 1. Figure 4 shows a modified version of the system configuration in Figure 3. In the modified version shown in Figure 4, the generated AI, LLM20, is stored within device 1. When necessary, device 1 executes processing on the LLM20 stored within device 1 and uses the execution result.

[0033] The generation unit 12 may generate a prompt to instruct the generation AI to generate analysis information for analyzing the user, based on the feature information. The generation unit 12 may also generate a prompt to instruct the generation AI to generate analysis information for analyzing the user, based on the feature information acquired (input) by the acquisition unit 11 (hereinafter, the prompt will be simply referred to as "prompt" as appropriate).

[0034] The generation unit 12 may generate prompts based on further information about the user. User information may include, for example, information such as age group, gender, place of residence, income group, occupation, purchasing behavior, visited facilities, and app usage. In this embodiment, "based on further information about X" means based on X and any one or more pieces of information used when generating prompts, as described throughout the description of the generation unit 12 in this embodiment.

[0035] The generation unit 12 may generate prompts based on further conditions for the analysis information. The conditions for the analysis information (information related to them) may be stored in advance by the storage unit 10 or acquired by the acquisition unit 11.

[0036] Examples of the conditions for the analysis information include: • A document outlining the conditions for creating the presentation materials (PowerPoint presentation). • Predetermined information such as the number of slides in the presentation materials. • The structure of the presentation materials (for example, the title is "Customer Information for Store A," a brief description of the customer information, an image of a user model in the upper left corner corrected with characteristic information (a user's face photo (which can be an actual photo or a photo processed by a generating AI, etc.) is registered in advance as a model image and corrected), and on the right side, key phrases and the rationale for those key phrases for each aspect of the customer information). • Information for generating the content used in the presentation materials (for example, the user model image). • Instructions for generating marketing advice (for example, "Generate text to provide marketing advice based on customer information"). • Instructions for generating advertisements.

[0037] The generation unit 12 may generate prompts based on further conditions of the user persona to be included in the analysis information. The persona may be, for example, a typical customer profile of someone who uses commercial resources, or a fictional character that reflects the user's characteristics or tendencies.

[0038] Examples of user persona criteria to be included in the analysis include: • Instructions for generating an image of a user model whose name is Taro Yamada, age 25, gender male, residence in Tokyo, income between 3 million and 4 million yen, occupation related to IT, and hobbies of listening to music and watching anime. • Text: "Generate an image of a 20-something male who likes anime as a user model image." • Text: "Generate user profile information based on characteristic information."

[0039] The generation unit 12 may generate prompts based on further conditions for the visualization data to be included in the analysis information. Visualization data may include, for example, graphs, figures, or text that show statistical information.

[0040] The conditions for the visualization data to be included in the analysis information include, for example, the following: • Generation instructions that specify how gender should be represented by a pie chart and how age groups should be represented by a bar chart. • Generation instructions that specify how to include visualization data. • Information for generating the properties of the figure.

[0041] The generation unit 12 may generate prompts based on the conditions of the basis for the analysis information.

[0042] Examples of conditions for the basis of analytical information include: • Instructions for generating key phrases and their rationale for each perspective. • A sentence stating, "Please describe the rationale in 30 characters or less." • A sentence stating, "For customer information, please create 30-character descriptions for age group, gender, place of residence, income level, occupation, purchasing behavior, and visited facilities, and 50-character descriptions for the rationale of someone's love of anime." (Instructions to describe the rationale for characteristic information in detail (with a predetermined number of characters greater than the character limit for other items)).

[0043] The generation unit 12 may generate a prompt based on a plurality of feature information. The generation unit 12 may generate a prompt based on the plurality of feature information acquired by the acquisition unit 11.

[0044] The generation unit 12 may include information such as visualization data among the conditions of the analysis information based on the feature information.

[0045] For example, when gender, age, and place of residence are included in the feature information, the generation unit 12 may generate a prompt instructing to describe visualization data of gender, age, and residential distribution in the analysis information. Note that the visualization data may use information previously stored by the storage unit 10, or may instruct the generation AI to create a diagram based on the information.

[0046] Also, for example, when the app usage log and payment usage are included in the feature information, the generation unit 12 may generate a prompt instructing to describe visualization data such as the app usage log and the ranking of payment usage stores in the analysis information. Note that the visualization data may use information previously stored by the storage unit 10, or may instruct the generation AI to create a diagram based on the information.

[0047] Also, for example, the generation unit 12 may generate a prompt instructing to describe the reason for the analysis information in text or to describe the diagram serving as the basis. Further, the generation unit 12 may generate a prompt instructing to change the color of the data indicating the feature part (for example, the usage log of a specific app or payment information).

[0048] Hereinafter, specific examples will be described using FIGS. 5 to 17. FIGS. 5 to 12 show examples of prompts generated by the generation unit 12, and FIGS. 13 to 17 show examples of analysis information and visualization data generated by the generation AI based on the prompts generated by the generation unit 12.

[0049] Figure 5 shows an example of a prompt (1). The prompt example shown in Figure 5 includes the main instruction to the AI ​​that generates analysis information: "Create a presentation material for visitors to Store A." It also includes the text "Create it in one slide" as one of the conditions for the analysis information (presentation material), specifying the number of slides. It also includes the text "Store A customer information (... In particular, please include that there are a certain number of visitors who like anime" as one of the conditions for the analysis information, specifying what should be included in the analysis information based on the characteristic information that "there are a certain number of visitors who like anime." By having the generation AI process the prompt example shown in Figure 5, for example, a one-slide presentation material for visitors to Store A (a presentation material explaining visitors to Store A) can be created, which includes some or all of the customer information for Store A, and that there are a certain number of visitors who like anime.

[0050] Figure 6 shows an example prompt (part 2). The example prompt shown in Figure 6 includes the main instruction to the AI ​​that generates analytical information: "Create a diagram showing customer information for store A." It also includes text specifying the conditions for the visualization data (diagram) to be included in the analytical information: "Gender as a pie chart, age group as a bar graph, ..." and text specifying what should be included in the analytical information: "Customer information for store A (...), in particular, gender as a pie chart, age group as a bar graph, ...". By having the AI ​​generate the prompts shown in Figure 6 process them, for example, a diagram can be created showing customer information for store A, with gender represented by a pie chart, age group by a bar graph, ...

[0051] For example, if customer information (breakdown of visitors by age group) is ..., 20 years old 3%, 21 years old 4%, 22 years old 5%, 23 years old 5%, 24 years old 4%, 25 years old 4%, 26 years old 3%, 27 years old 3%, 28 years old 4%, 29 years old 3.6%, ... then 38.6% are in their 20s. If the age breakdown of visitors in their 20s in the model being analyzed is 30%, then 38.6% > 30 + threshold%, so 38.6% of those in their 20s becomes characteristic information (meaning that those in their 20s are particularly numerous). In this case, an example of a prompt generated by the generation unit 12 is shown in Figure 7. Figure 7 is a diagram showing an example of a prompt (number 3). In the example prompt shown in Figure 7, the role of the generator of the analysis information, various conditions for generating the analysis information, prompt input information, and prompt output format are defined. The prompt input information is based on characteristic information acquired by the acquisition unit 11 (for example, the characteristic that 38.6% are in their 20s as described above).

[0052] For example, Figure 8 shows an example of a prompt generated by the generation unit 12 when the key phrase is "The 'age group that constitutes characteristic information' is the most numerous" and the output is "The 'age group that constitutes characteristic information' accounts for the 'percentage of age groups that constitute characteristic information' of the total, making it the most numerous age group." Figure 8 is a diagram of prompt example (number 4). In the prompt example shown in Figure 8, the main generation instruction task, characteristic information (the characteristic that those in their 20s make up 38.6%), prompt input information, key phrases for each perspective, and type examples including their rationale (for example, perspective: age group, key phrase: "Those in their 20s are the most numerous", rationale: "Those in their 20s account for 38.6% of the total, making it the most numerous age group.") are defined. Figure 9 is a diagram showing another example of the type example in Figure 8. The type examples described above may be those generated by the generation AI.

[0053] This section describes an example of generating a prompt to instruct the generation of analysis information based on multiple feature information (e.g., anime lover, 20s, male). For example, the sentence "Generate an image of a 20-year-old male who likes anime as a user model image" is created and included in the prompt. Note that the sentence may be generated using generation AI (text generation). For example, Figure 10 shows an example prompt generated by the generation unit 12, which instructs "Generate a prompt to generate an image corresponding to the feature elements 'anime lover' and '20s male'." Figure 10 is a diagram showing prompt example (number 5). In the prompt example shown in Figure 10, the main generation instruction task, conditions for generating analysis information, input feature information, and an example of prompt output (including the above-mentioned "Generate a prompt to generate an image corresponding to the feature elements 'anime lover' and '20s male'") are defined.

[0054] Figure 11 shows an example of a prompt (number 6). The example prompt shown in Figure 11 defines system_prompt, which specifies the role of the generating AI, and assistant_prompt, which prompts the user to input customer information as text. A specific example of {age_text} in assistant_prompt is "Age distribution: 10s: 0.2%, 20s: 0.8%, 30s: 3.9%, 40s: 13.7%, 50s: 39.7%, 60s: 28.3%, 70s: 11.6%, 80s: 1.6%, 90s: 0.2%".

[0055] Figure 12 shows an example of a prompt (number 7). The prompt example shown in Figure 12 defines the main generation instruction "Instruction1", the output format "Output format" (defining the output format as CSV, specifying in detail the information to be stored in each column), the conditions "Points of view and Rules", and the checkpoint "Checkpoint".

[0056] Figure 13 shows an example of analytical information. As shown in the example of analytical information in Figure 13, the analytical information may consist of any of the following: a title ("Increase in customers at store A"), a summary of customer information ("Working in an IT-related occupation..."), information showing details of customer information (table of perspectives / key phrases / evidence in the lower right), and information about the user model (user model image (image of a man with headphones around his neck), user model profile information ("Name: Taro Yamada, Age: 25,...")).

[0057] Figure 14 shows an example of visualization data (part 1). The example of visualization data shown in Figure 14 is a pie chart showing the proportion of gender, which is basic information, among the customer information of store A. The visualization data may also be graphs or diagrams based on other basic information such as age or residential distribution.

[0058] Figure 15 shows an example of visualization data (part 2). The example of visualization data shown in Figure 15 is a pie chart showing the proportion of users of the analysis model by gender, which is basic information. By including both the visualization data of customer information for store A, as shown in Figure 14, and the visualization data of the analysis model, as shown in Figure 15, together in a single analysis, viewers can easily compare and contrast them, making the analysis more meaningful.

[0059] Figure 16 shows an example of visualization data (part 3). The visualization data example shown in Figure 16 is a bar graph showing the ranking of visited facilities, which is additional information for users of store A. The visualization data may also be graphs or figures based on other additional information such as app usage logs or rankings of stores where payments are made.

[0060] Figure 17 shows an example of visualization data (part 4). The example of visualization data shown in Figure 17 is a bar graph showing the ranking of visited facilities, which is additional information for the user of the model under analysis. By including both the visualization data of customer information for store A, as shown in Figure 16, and the visualization data of the model under analysis, as shown in Figure 17, together in a single piece of analysis information, viewers can easily compare and contrast them, making the analysis information more meaningful.

[0061] Furthermore, when the generation unit 12 issues instructions for generating visualization data, it may indicate in text which data is characteristic based on the characteristic information, change the color of characteristic parts of the graph, or include information that serves as the basis for indicating the characteristics.

[0062] The above explanation uses Figures 5 to 17 to illustrate specific examples.

[0063] Returning to Figure 1, the generation unit 12 may instruct the generation AI, LLM 20, to process the generated prompt, thereby generating analysis information, and as a result, acquire the analysis information generated by LLM 20. The generation unit 12 may store the acquired analysis information in the storage unit 10, or it may output it to other functions of the device 1.

[0064] The output unit 13 outputs (transmits) arbitrary information to other devices, such as external devices, via a network or the like. For example, the output unit 13 may output prompts generated by the generation unit 12, or analysis information acquired by the generation unit 12, to other devices.

[0065] Next, an example of the process performed by device 1 will be explained with reference to Figure 18. Figure 18 is a flowchart showing an example of the process (generation process) performed by device 1.

[0066] First, the acquisition unit 11 acquires information about a user of a commercial resource (specific user information) (step S1). Next, the acquisition unit 11 acquires information about a reference user of a commercial resource (reference user information) (step S2). Next, the acquisition unit 11 extracts feature information based on the specific user information acquired in step S1 and the reference user information acquired in step S2 (step S3). Next, the acquisition unit 11 acquires the feature information extracted in step S3 (step S4). Next, the generation unit 12 generates a prompt to instruct the generation AI to generate analysis information based on the feature information acquired in step S4 (step S5). Next, the generation unit 12 instructs the generation AI to generate analysis information based on the prompt generated in step S5 (step S6). Next, the output unit 13 outputs the analysis information generated based on the generation instruction made in step S6 (step S7). Note that the order of S1 and S2 may be reversed.

[0067] Next, the effects and advantages of the apparatus 1 according to this embodiment will be described.

[0068] The device 1 includes an acquisition unit 11 that acquires characteristic information relating to the user's characteristics, and a generation unit 12 that generates a prompt to instruct an AI to generate analysis information for analyzing the user based on the characteristic information acquired by the acquisition unit 11. With this configuration, a prompt is generated to instruct the AI ​​to generate analysis information for analyzing the user based on the acquired characteristic information. In other words, it is possible to generate information that can generate analysis information for analyzing the user.

[0069] In device 1, the user may be a user of commercial resources. This configuration allows for the generation of analytical information for analyzing users of commercial resources.

[0070] In the device 1, the acquisition unit 11 may acquire characteristic information based on information about a user of one commercial resource and information about a reference commercial resource user. This configuration makes it possible to acquire more accurate characteristic information based on information about a user of one commercial resource and information about a reference commercial resource user.

[0071] In the device 1, the generation unit 12 may generate prompts based on further information about the user. This configuration makes it possible to generate more accurate prompts based on further information about the user, thereby enabling the generation of analytical information that allows for a more accurate analysis of the user.

[0072] In the device 1, the generation unit 12 may generate prompts based on further conditions of the analysis information. This configuration makes it possible to generate more accurate prompts based on further conditions of the analysis information, thereby enabling the generation of analysis information that allows for a more accurate analysis of the user.

[0073] In the device 1, the generation unit 12 may generate prompts based on further conditions of the user persona to be included in the analysis information. This configuration makes it possible to generate more accurate prompts based on further conditions of the user persona to be included in the analysis information, thereby enabling the generation of analysis information that allows for a more accurate analysis of the user.

[0074] In the device 1, the generation unit 12 may generate prompts based on further conditions for the visualization data to be included in the analysis information. This configuration makes it possible to generate more accurate prompts based on further conditions for the visualization data to be included in the analysis information, thereby enabling the generation of analysis information that allows for a more accurate analysis of the user.

[0075] In the device 1, the generation unit 12 may generate prompts based on the conditions for the basis of the analysis information. This configuration makes it possible to generate more accurate prompts based on the conditions for the basis of the analysis information, thereby enabling the generation of analysis information that allows for a more accurate analysis of the user.

[0076] In the device 1, the generation unit 12 may generate prompts based on a plurality of feature information acquired by the acquisition unit 11. This configuration makes it possible to generate more accurate prompts based on a plurality of feature information, thereby generating analytical information that enables a more accurate analysis of the user.

[0077] A conventional challenge has been the uncertainty of what information should be included in prompts when creating materials for analyzing customer information about products, services, stores, etc., using generative AI. Device 1 makes it possible to create materials for analyzing customer information about products, services, stores, etc., using generative AI. Examples of generated content include presentation materials showing user personas (typical customer profiles of products and services), and image files such as graphs showing statistical information, as well as text information (visualization data). Device 1 makes it possible to create prompts for input into the generative AI.

[0078] The analytical information may include marketing advice, advertising creative images and text, or similar user expansion.

[0079] Device 1 can generate prompts that describe the structure of the analysis information (PowerPoint). Device 1 can also generate prompts that instruct the system to generate a user profile image from the characteristic information of a model user. Furthermore, Device 1 can generate prompts necessary for creating customer analysis information (presentation materials) using generation AI. Device 1 allows for easy creation of prompts. Device 1 can be described as a profiling system.

[0080] The apparatus 1 of this disclosure may have the following configuration.

[0081] [1] An apparatus comprising: an acquisition unit that acquires characteristic information relating to the characteristics of a user; and a generation unit that generates a prompt for instructing a generating AI to generate analysis information for analyzing the user based on the characteristic information acquired by the acquisition unit.

[0082] [2] The apparatus described in [1], wherein the user is a user of commercial resources.

[0083] [3] The apparatus according to [1] or [2], wherein the acquisition unit acquires characteristic information based on information relating to a user of one commercial resource and information relating to a user of a standard commercial resource.

[0084] [4] The apparatus according to any one of [1] to [3], wherein the generation unit generates the prompt based on further information about the user.

[0085] [5] The apparatus according to any one of [1] to [4], wherein the generation unit generates the prompt based on the conditions of the analysis information.

[0086] [6] The apparatus according to any one of [1] to [5], wherein the generation unit generates the prompt based on the conditions of the user persona to be included in the analysis information.

[0087] [7] The apparatus according to any one of [1] to [6], wherein the generation unit generates the prompt based on conditions for visualization data to be included in the analysis information.

[0088] [8] The apparatus according to any one of [1] to [7], wherein the generation unit generates the prompt based on the conditions of the basis of the analysis information.

[0089] [9] The apparatus according to any one of [1] to [8], wherein the generation unit generates the prompt based on a plurality of feature information acquired by the acquisition unit.

[0090]

[10] A method performed by a computer, comprising: an acquisition step of acquiring characteristic information relating to the characteristics of a user; and a generation step of generating a prompt to instruct a generating AI to generate analysis information for analyzing the user based on the characteristic information acquired in the acquisition step.

[0091] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0092] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0093] For example, Apparatus 1 in one embodiment of the present disclosure may function as a computer that processes the method of the present disclosure. Figure 19 is a diagram showing an example of the hardware configuration of Apparatus 1 according to one embodiment of the present disclosure. Physically, Apparatus 1 described above may be configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0094] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of device 1 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0095] Each function in device 1 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0096] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the acquisition unit 11, generation unit 12, and output unit 13 described above may be implemented by the processor 1001.

[0097] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the acquisition unit 11, the generation unit 12, and the output unit 13 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0098] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out a wireless communication method according to one embodiment of the present disclosure.

[0099] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., Compact Disc, Digital Multipurpose Disc, Blu-ray® Disc), a smart card, flash memory (e.g., a card, stick, key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0100] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the acquisition unit 11, generation unit 12 and output unit 13 described above may be implemented by the communication device 1004.

[0101] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0102] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0103] Furthermore, the device 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0104] The notification of information is not limited to the manner / embodiments described herein and may be carried out by other means.

[0105] Each aspect / embodiment described in this disclosure may be applied to at least one of the following systems: LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0106] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0107] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0108] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, by comparing with a predetermined value).

[0109] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0110] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0111] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0112] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0113] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0114] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

[0115] The terms “system” and “network” as used in this disclosure are interchangeable.

[0116] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0117] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure.

[0118] As used in this disclosure, the terms “determining” and “decision” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, search, inquiry (e.g., searching in tables, databases or other data structures), and ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and accessing (e.g., accessing data in memory). Furthermore, “determining” may include resolving, selecting, choosing, establishing, and comparing. In other words, "judgment" and "decision" can include considering that some action has been "judged" or "decided." Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0119] The terms “connected,” “coupled,” and any variations thereof mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0120] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0121] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0122] In the configuration of each of the above devices, "means" may be replaced with "part," "circuit," "device," etc.

[0123] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0124] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0125] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0126] 1...Device, 2...LLM server, 10...Storage unit, 11...Acquisition unit, 12...Generation unit, 13...Output unit, 20...LLM, 1001...Processor, 1002...Memory, 1003...Storage, 1004...Communication device, 1005...Input device, 1006...Output device, 1007...Bus.

Claims

1. An apparatus comprising: an acquisition unit that acquires characteristic information relating to the characteristics of a user; and a generation unit that generates a prompt to instruct a generating AI to generate analysis information for analyzing the user based on the characteristic information acquired by the acquisition unit.

2. The apparatus according to claim 1, wherein the user is a user of commercial resources.

3. The apparatus according to claim 1, wherein the acquisition unit acquires characteristic information based on information relating to a user of a commercial resource and information relating to a user of a standard commercial resource.

4. The apparatus according to claim 1, wherein the generation unit generates the prompt based on further information about the user.

5. The apparatus according to claim 1, wherein the generation unit generates the prompt based on the conditions of the analysis information.

6. The apparatus according to claim 1, wherein the generation unit generates the prompt based on the conditions of the user's persona to be included in the analysis information.

7. The apparatus according to claim 1, wherein the generation unit generates the prompt based on conditions for the visualization data to be included in the analysis information.

8. The apparatus according to claim 1, wherein the generation unit generates the prompt based on the conditions of the basis of the analysis information.

9. The apparatus according to claim 1, wherein the generation unit generates the prompt based on a plurality of feature information acquired by the acquisition unit.

10. A method performed by a computer, comprising: an acquisition step of acquiring characteristic information relating to the characteristics of a user; and a generation step of generating a prompt to instruct a generating AI to generate analysis information for analyzing the user based on the characteristic information acquired in the acquisition step.

Images