Information provision device, information provision method, and recording medium

Abstract

This information provision device is provided with a user information acquisition unit, a query acquisition unit, and a display processing unit. The user information acquisition unit acquires information (user information) regarding a user on the basis of information obtained from a communication device used by the user. The query acquisition unit acquires a query for generative artificial intelligence (generative AI). The display processing unit displays, on a display, a generative AI output result based on the user information and the query that were acquired.

Description

Information providing device, information providing method, and recording medium

[0001] The present invention relates to an information providing device, an information providing method, and a recording medium.

[0002] Patent Document 1 below discloses an information processing device that performs processing according to an instruction sentence input by a user to a dialogue application. The information processing device described in Patent Document 1 has a configuration that creates a query sentence for a generation AI device based on the instruction sentence input to the dialogue application and template data for a query sentence to be passed to the generation AI device.

[0003] Patent No. 7370118

[0004] Generative AI can automatically generate various output information based on input information and present it to the user. However, users (especially those unfamiliar with generative AI) may have difficulty using generative AI to obtain the desired output results.

[0005] An information providing device according to one aspect of the present disclosure includes: a user information acquisition means for acquiring user information about a user based on information obtained from a communication device used by the user; a query acquisition means for acquiring a query for generative artificial intelligence (AI); and a display processing means for displaying an output result of the generative AI based on the query and the user information.

[0006] An information providing method according to another aspect of the present disclosure includes a computer acquiring user information about a user based on information obtained from a communication device used by the user, acquiring a query for generative artificial intelligence (AI), and displaying an output result of the generative AI based on the query and the user information.

[0007] In yet another aspect of the present disclosure, a recording medium records a program that, when executed by a computer, causes the computer to perform operations including: acquiring user information about the user based on information obtained from a communication device used by the user; acquiring a query for generative AI (generative artificial intelligence); and displaying an output result of the generative AI based on the query and the user information.

[0008] According to the present disclosure, a technique is provided for improving the accuracy of output results obtained from generative AI.

[0009] FIG. 1 is a diagram illustrating a first example of a functional configuration of an information providing device in the present disclosure. FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer that realizes the information providing device in the present disclosure. FIG. 3 is a flowchart illustrating a first example of processing executed by the information providing device in the present disclosure. FIG. 4 is a flowchart illustrating an example of processing by which a user information acquisition unit of the information providing device in the present disclosure acquires user information. FIG. 5 is a diagram schematically illustrating a flow in which user information is generated and acquired. FIG. 6 is a diagram illustrating an example of template data of a prompt given to a generation AI. FIG. 7 is a diagram illustrating a second example of a functional configuration of an information providing device in the present disclosure. FIG. 8 is a flowchart illustrating a second example of processing executed by the information providing device in the present disclosure. FIG. 9 is a diagram illustrating an example of template data of a prompt given to a generation AI.

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that in this disclosure, the drawings relate to one or more embodiments. Furthermore, in all drawings, similar components are given similar reference numerals, and descriptions thereof will be omitted as appropriate. Furthermore, unless otherwise specified, in each block diagram, each block represents a functional configuration, not a hardware configuration. Furthermore, when elements such as blocks in a diagram are linked by arrows, the direction of the arrows is merely intended to make the flow of information easier to understand. In this case, unless otherwise specified, the direction of the arrows does not limit the direction of communication (one-way communication / two-way communication).

[0011] In the following description, "acquisition" includes at least one of the following: a device going to retrieve data or information stored in another device or storage medium (active acquisition), and a device inputting data or information output from another device (passive acquisition). Examples of active acquisition include making a request or inquiry to another device and receiving a reply, and accessing and reading information from another device or storage medium. Examples of passive acquisition include receiving information that is distributed (or transmitted, push notification, etc.). Furthermore, "acquisition" may also mean selecting and acquiring data or information from received data or information, or selecting and receiving distributed data or information.

[0012] 1 is a diagram illustrating a first example of the functional configuration of an information providing device according to the present disclosure. The information providing device 10 illustrated in the diagram includes a user information acquiring unit 110, a query acquiring unit 120, and a display processing unit 130.

[0013] The user information acquisition unit 110 acquires information about a user (hereinafter also referred to as "user information") based on any information (hereinafter also referred to as "device information") obtained from a communication device used by the user (e.g., communication device 30 described below). "User information" includes at least information indicating the characteristics of the user. The query acquisition unit 120 acquires a query for the generation AI 20. The query is generated, for example, by a user's input operation on the communication device 30 (such as a keyboard input operation or a voice input operation). The display processing unit 130 displays the output result of the generation AI 20 based on the above-mentioned query and user information on a display (e.g., the display of the communication device 30 used by the user).

[0014] As an example, the information providing device 10 illustrated in this figure is a user's communication device. In this case, the user information acquisition unit 110 is configured to acquire user information pre-stored in a storage means of the user's communication device. Alternatively, the user information acquisition unit 110 is configured to acquire user information generated using any information (such as an application operation log) stored in the user's communication device. Furthermore, the query acquisition unit 120 is configured to acquire a query for the generation AI 20 via an input / output device of the user's communication device. Furthermore, the display processing unit 130 is configured to display the output results from the generation AI 20 on the display of the user's communication device.

[0015] As another example, the information providing device 10 is a server device that operates by communicating with users' communication devices. The user information acquiring unit 110 is configured to acquire user information of the corresponding user by referring to a database or the like that stores user information collected from each user's communication device. Alternatively, the user information acquiring unit 110 is configured to acquire (generate) user information based on any information (device information) collected from each user's communication device.

[0016] Furthermore, the generation AI 20 may be provided externally to the information providing device 10 as illustrated in this figure, or may be provided within the information providing device 10. Here, the generation AI 20 is realized, for example, by a neural network. The neural network includes multiple artificial neurons and has synapses connecting each neuron. Each synapse has a weight. When such a neural network receives an input, it performs calculations using the weights associated with each synapse and produces an output according to the input. A model representing the connection relationship between neurons and synapses is stored in a storage area such as a memory in the form of software, for example. The model representing the connection relationship between neurons and synapses may also be realized as a dedicated circuit. Similarly, the weights of each synapse are stored in a storage area such as a memory in the form of software. A dedicated circuit representing the weights of each synapse may also be implemented. Note that when the generation AI 20 is configured using multiple models, all of the models do not necessarily need to be stored in the same storage area (e.g., in the same memory). There are a variety of models using such neural networks, and the generative AI 20 may be realized by adopting or replacing a wide variety of models such as a Transformer, a convolutional neural network (CNN), or a recurrent neural network (RNN).

[0017] <Hardware Configuration Example> FIG. 2 is a diagram illustrating an example of the hardware configuration of a computer that realizes the information providing device 10 in the present disclosure.

[0018] The computer 1000 illustrated in this figure includes a bus 1010 , a processor 1020 , a memory 1030 , a storage device 1040 , an input / output interface 1050 , and a network interface 1060 .

[0019] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0020] The processor 1020 is a central processing unit (CPU) or a graphics processing unit (GPU).

[0021] The memory 1030 is a main storage device realized by a random access memory (RAM) or the like.

[0022] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read only memory (ROM), or the like. The storage device 1040 stores at least program modules that realize the functions of the information providing device 10 described above (the user information acquisition unit 110, the query acquisition unit 120, and the display processing unit 130). As an example of the present disclosure, the storage device 1040 may function as a device that stores the generation AI 20 and various modules related to the generation AI 20.

[0023] The processor 1020 loads a program module read from the storage device 1040 onto the memory 1030 and executes the program module, thereby realizing a function corresponding to the program module. For example, the processor 1020 reads a program module corresponding to the user information acquisition unit 110 onto the memory 1030 and executes the program module, thereby realizing the function of the user information acquisition unit 110 described in the present disclosure. Similarly, the processor 1020 reads a program module corresponding to the query acquisition unit 120 onto the memory 1030 and executes the program module, thereby realizing the function of the query acquisition unit 120 described in the present disclosure. Similarly, the processor 1020 reads a program module corresponding to the display processing unit 130 onto the memory 1030 and executes the program module, thereby realizing the function of the display processing unit 130 described in the present disclosure. The operation of the processor 1020 is common to each embodiment included in the present disclosure.

[0024] The above-described program modules may be recorded on a recording medium other than the storage device 1040. The recording medium on which the program modules are recorded may include any non-transitory, tangible medium usable by the computer 1000. The recording medium on which the program modules are recorded may have embedded therein program code that is readable by the computer 1000 (processor 1020).

[0025] The input / output interface 1050 is an interface for connecting the computer 1000 (information providing device 10) to various input / output devices.

[0026] The network interface 1060 is an interface for connecting the computer 1000 (information providing device 10) to a network. This network may be, for example, a local area network (LAN) or a wide area network (WAN). The network interface 1060 supports various wireless and wired communication standards and establishes communication between the computer 1000 (information providing device 10) and other devices (not shown) on the network. Although not limited thereto, "other devices" include a communication device 30 used by a user and a server device that is provided on a network with which the information providing device 10 can communicate and stores the generation AI 20 and various modules related to the generation AI 20.

[0027] The computer 1000 (information providing device 10) can also be connected to various devices (not shown) via the input / output interface 1050 or the network interface 1060. The "various devices" referred to here are not particularly limited, but include, for example, input devices such as operation buttons, keyboards, touch panels, mice, and microphones, and output devices such as displays, speakers, and printers. The computer 1000 (information providing device 10) accepts various inputs described in this disclosure via the input devices illustrated. The computer 1000 (information providing device 10) also outputs the output results of the generation AI 20 via the output devices illustrated.

[0028] Alternatively, each function of the information providing device 10 may be provided in a communication device used by a user. In this case, a program application that provides each function of the information providing device 10 is installed in the user's communication device. This allows the user's communication device to function as a device equivalent to the information providing device 10 described in this disclosure.

[0029] <Example of Operation of Information Providing Device> An example of operation of the information providing device according to the present disclosure will be described below with reference to the drawings.

[0030] FIG. 3 is a flowchart illustrating a first example of processing executed by the information providing device 10 in the present disclosure.

[0031] First, the query acquisition unit 120 acquires a query input by a user using a communication device (step S102). For example, the user inputs the query using an input device such as a keyboard or microphone provided on the communication device. The query acquisition unit 120 acquires the query input via the input device of the communication device 30.

[0032] When a query input via the communication device 30 is acquired, the user information acquisition unit 110 acquires user information related to the user of the communication device 30 (step S104). For example, if user information corresponding to the user of the communication device 30 is pre-stored in a predetermined storage area, such as the storage device 1040, the user information acquisition unit 110 identifies the user information of the target user based on, for example, information unique to the communication device, and reads the user information from the storage area. Furthermore, if the communication device 30 is equipped with each function of the information providing device 10, the user information acquisition unit 110 can acquire the user information from the storage area of ​​the communication device 30. Furthermore, the user information acquisition unit 110 may execute a process such as that illustrated in FIG. 4, which will be described later, in response to acquisition of the query, to acquire the user information of the target user.

[0033] The display processing unit 130 acquires the output result by the generation AI 20 based on the combination of the query acquired in the processing of step S102 and the user information acquired in the processing of step S104 (step S106).Then, the display processing unit 130 displays the output result by the generation AI 20 acquired in the processing of step S106 on the display of the communication device 30 (step S108).

[0034] According to the information providing device 10 of this embodiment, the output result of the generation AI 20 is obtained based on user information acquired based on device information used by the user and a query entered by the user. Here, as described above, the user information includes information indicating the user's characteristics, such as the user's hobbies and preferences. In other words, the information providing device 10 can control the generation AI 20 to provide output tailored to the user's characteristics.

[0035] Thus, according to the present disclosure, an information providing device 10 is provided that solves the problem that users (especially users unfamiliar with generation AI) have difficulty obtaining desired output results using generation AI. Also, according to the present disclosure, an information providing method executed by the information providing device 10 (computer), a program for realizing each function of the information providing device 10 (computer), and a computer-readable recording medium on which the program is recorded are provided.

[0036] In addition, in the present disclosure, user information including information about the user's characteristics is automatically generated based on information obtained from the device used by the user, which allows the output results from the generation AI 20 to be closer to the user's characteristics without the user being particularly aware of it.

[0037] A detailed example of the information providing device according to the present disclosure will be described below.

[0038] <Generation of User Information> As described above, user information is information indicating the characteristics of a user. Here, examples of information indicating the characteristics of a user include so-called psychographic attributes, such as the user's hobbies, preferences, habits, beliefs, and values. Another example of information indicating the characteristics of a user is the user's digital skills (level of digital skills). In the present disclosure, "user information" may include information indicating the user's psychographic attributes and / or information indicating the user's digital skills.

[0039] FIG. 4 is a flowchart illustrating an example of a process in which the user information acquisition unit of the information providing device according to the present disclosure acquires user information.

[0040] First, the user information acquisition unit 110 acquires device information from the communication device 30 used by the user (step S202). The "device information" acquired here is not particularly limited, but includes the model of the communication device 30, the types of applications installed on the communication device 30, the usage history of applications on the communication device 30, the operation time of the communication device 30, and location information of the communication device 30. Note that the user information acquisition unit 110 can acquire any information, including the types of information exemplified above, from the communication device 30 by, for example, using an Application Programming Interface (API) of an Operating System (OS) installed in the communication device 30.

[0041] The user information acquisition unit 110 acquires user information based on the acquired device information (step S204). For example, the user information acquisition unit 110 is configured to generate information indicating the user's psychographic attributes using information about applications installed in the communication device 30 (e.g., application type, usage history / usage frequency, etc.). As an example, the user information acquisition unit 110 generates a prompt for the generation AI 20 to infer psychographic attributes using information about the applications included in the device information acquired from the communication device 30. For example, the user information acquisition unit 110 generates a prompt with embedded context based on information about the applications included in the device information acquired from the communication device 30. The user information acquisition unit 110 then provides the generated prompt to the generation AI 20. As a result, the user information acquisition unit 110 can acquire the psychographic attribute estimation result output from the generation AI 20 as information indicating the user's psychographic attributes.

[0042] Note that the user information acquisition unit 110 may acquire information indicating the user's psychographic attributes without using the generation AI 20. For example, if there is another user with attributes similar to those of the target user and the psychographic attributes of the other user are known, the user information acquisition unit 110 may also acquire the psychographic attributes of the other user as the psychographic attributes of the target user. Furthermore, the user information acquisition unit 110 may acquire information indicating the user's psychographic attributes using, for example, the method described in Non-Patent Document 1.

[0043] Yusuke Ichikawa, Toru Kobayashi, "Proposal of an Attribute Estimation Method Focusing on the Power Law Distribution Tendency of User Web Access History," Transactions of Information Processing Society of Japan, Vol. 52, No. 3, pp. 1195-1203, (Mar. 2011)

[0044] As a variant, the user information acquisition unit 110 may be configured to generate (or update) the user's psychographic attributes using a history of input and output to the generation AI 20. For example, when the generation AI 20 is used for the first time, the user information acquisition unit 110 acquires information indicating the user's psychographic attributes from information about applications installed on the user's communication device 30, as exemplified above. Thereafter, when the user repeatedly interacts with the generation AI 20 using the communication device 30 several times, information about the interaction is accumulated in the communication device 30. The user information acquisition unit 110 acquires and analyzes information about the interaction history between the user and the generation AI 20 that is accumulated in this manner. The user information acquisition unit 110 can then acquire, as new information, information indicating the user's psychographic attributes determined based on the analysis results of information about the interaction history between the user and the generation AI 20. Alternatively, the user information acquisition unit 110 may update various parameter information related to the user's psychographic attributes that is stored in accordance with the user's psychographic attributes determined based on the analysis results of information related to the dialogue history between the user and the generation AI 20. With this configuration, the information indicating the user's characteristics (e.g., psychographic attributes) used by the information providing device 10 in the present disclosure can be made closer to the user's actual psychographic attributes.

[0045] Furthermore, by analyzing the dialogue history between the user and the generation AI 20, it is possible to capture changes in the user's characteristics (such as hobbies and preferences) over time. For example, the user information acquisition unit 110 can obtain information such as "The user was previously outdoorsy but has recently become interested in indoor activities" or "The user is concerned about his or her health and is trying to resume exercising" from the dialogue history information. As a result, the user information acquisition unit 110 can analyze the user to determine, for example, "The user is becoming health-conscious" and reflect the analysis results in the user's characteristics (psychographic attributes). For example, suppose the user's psychographic attributes before reflecting the analysis results were "hardworking, particular." In this case, the user information acquisition unit 110 can update the user's psychographic attributes to "hardworking, particular, health-conscious" by reflecting the analysis results exemplified above.

[0046] In analyzing the dialogue history with the generation AI 20, if the entire history is analyzed, there is a possibility that the analysis will result in an excessive amount of information. Therefore, the user information acquisition unit 110 may be configured to request the generation AI 20 to generate a summary of information related to the dialogue history. For example, if the dialogue history includes information spanning a relatively long period of time, the user information acquisition unit 110 requests the generation AI 20 to generate a summary for each predetermined unit (e.g., month or quarter). The user information acquisition unit 110 can then provide the output multiple time-series summaries and current psychographic attributes to the generation AI 20, thereby updating the psychographic attributes of the target user.

[0047] Then, the user information acquisition unit 110 stores the acquired user information in a predetermined storage area, such as the memory 1030 or the storage device 1040 (step S206). The user information stored in the storage area is read out in response to acquisition of a query by the query acquisition unit 120 (for example, the process of step S102 in FIG. 3).

[0048] A specific example of the process shown in the flowchart of Fig. 4 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an outline of the flow of generating and acquiring user information.

[0049] First, the user information acquisition unit 110 acquires device information from the user's communication device 30. In the example shown in the figure, the user information acquisition unit 110 acquires information such as the "model," "installed applications," "usage history of each application," and "operation time of the communication device" from the communication device 30 as device information.

[0050] Then, the user information acquisition unit 110 provides the generation AI 20 with a prompt that embeds a context based on the device information acquired from the communication device 30. In the example shown in the figure, the user information acquisition unit 110 generates a prompt that embeds a context based on information about the model of the communication device 30 used by the user and information about applications installed on the communication device 30. The generated prompt also includes instructions for inferring the user's psychographic attributes and instructions for inferring the user's digital skills.

[0051] In the example shown in this figure, the generation AI 20 infers the psychographic attribute of "hardworking and particular" based on the given prompt. The generation AI 20 also infers that the user's digital skills are relatively high based on the given prompt. The user information acquisition unit 110 then acquires the inference results of the generation AI 20 regarding the psychographic attributes and the inference results regarding the level of digital skills as user information from the generation AI 20. The user information acquisition unit 110 then stores the acquired user information in a specified storage area.

[0052] <Generation of prompt to be given to generation AI> In the present disclosure, the prompt to be given to the generation AI 20 is generated using the user information acquired by the user information acquisition unit 110 and the query acquired by the query acquisition unit 120. This may be executed by the information providing device 10, or may be executed by a device other than the information providing device 10 (for example, a server device not shown).

[0053] As an example, the information providing device 10 may have a function for generating a prompt using user information acquired by the user information acquiring unit 110 and a query acquired by the query acquiring unit 120. In this case, the information providing device 10 generates a prompt by embedding a context based on the query and user information into prompt template data, such as that shown in FIG. 6 . FIG. 6 is a diagram illustrating an example of prompt template data provided to the generation AI. In the example shown in this figure, the user information acquired by the user information acquiring unit 110 is incorporated into the {User Information} section. Also in the example shown in this figure, the query acquired by the query acquiring unit 120 is incorporated into the {Query} section. As a specific example, assume that the user information acquired by the user information acquiring unit 110 is "self-growth-oriented, information / technology enthusiast" and the query is "Please tell me a recipe for matsutake mushroom dishes." In this case, a prompt such as that shown in the following <<Prompt Example>> is generated as a prompt provided to the generation AI 20.

[0054] <<Example prompt>> You are an excellent butler. Please answer the master's question in a way that suits his characteristics. The master's question is, "Please tell me a recipe for matsutake mushroom dishes," and the master's characteristics are "self-improvement oriented, information / technology enthusiast."

[0055] As described above, information indicating user characteristics (such as psychographic attributes) acquired by the information providing device 10 of the present disclosure is reflected in the prompts provided to the generation AI 20. This allows the generation AI 20 to provide an output customized to the characteristics of the target user.

[0056] Second Embodiment <Functional Configuration Example> Fig. 7 is a diagram showing a second example of the functional configuration of an information providing device 10 according to the present disclosure. The information providing device 10 shown in this figure includes a prompt generation unit 140 in addition to the configuration shown in Fig. 1.

[0057] The prompt generation unit 140 generates a prompt for the generation AI 20 based on a query to the generation AI 20 and user information obtained based on the user's operation history of the communication device. The prompt generation unit 140 then inputs the generated prompt to the generation AI 20.

[0058] The prompt generation unit 140 may be configured to generate a prompt using a knowledge base prepared in advance. As an example, the information providing device 10 acquires information (hereinafter also referred to as “knowledge base selection information”) indicating a knowledge base to be used from various knowledge bases (e.g., a knowledge base about cooking recipes, a knowledge base about investment products) in response to an operation on the communication device 30. The various knowledge bases may be stored in the information providing device 10 or may be provided in another device (not shown) communicatively connected to the information providing device 10 (e.g., connected via the Internet). The prompt generation unit 140 then acquires additional information from the knowledge base selected based on the acquired knowledge base selection information. The prompt generation unit 140 then combines the acquired additional information with the query and user information to generate a prompt to be provided as input to the generation AI 20. Specifically, the prompt generation unit 140 incorporates the acquired additional information into the prompt as the context of the prompt provided as input to the generation AI 20.

[0059] The above-mentioned knowledge base may be, for example, the Internet to which an unspecified number of information processing devices are connected, or a closed network to which only specific information processing devices are connected. In this case, the prompt generation unit 140 is configured to extract characteristic words from the text entered in the query and obtain additional information related to the words from the Internet or the closed network.

[0060] The prompt generation unit 140 may narrow down the knowledge base to be searched depending on the content of the word. For example, when a word related to cooking is extracted, the prompt generation unit 140 acquires additional information from a knowledge base related to cooking.

[0061] The additional information obtained from the knowledge base is not limited to the information recorded in the knowledge base itself, but may be a summary of the obtained information.

[0062] FIG. 8 is a flowchart showing a second example of the process executed by the information providing device 10 in the present disclosure.

[0063] First, the query acquisition unit 120 acquires a query input by the user using the communication device 30 (step S302). For example, the user inputs the query using an input device such as a keyboard or microphone provided on the communication device 30. The query acquisition unit 120 acquires the query input via the input device of the communication device 30.

[0064] When a query input via the communication device 30 is acquired, the user information acquisition unit 110 acquires user information related to the user of the communication device 30 (step S304). For example, if user information corresponding to the user of the communication device 30 is pre-stored in a predetermined storage area, such as the storage device 1040, the user information acquisition unit 110 identifies the user information of the target user based on, for example, information unique to the communication device 30, and reads the user information from the storage area. Furthermore, if the communication device 30 is equipped with each function of the information providing device 10, the user information acquisition unit 110 can acquire the user information from the storage area of ​​the communication device 30. Furthermore, the user information acquisition unit 110 may execute the process illustrated in FIG. 4 in response to the acquisition of the query to acquire the user information of the target user.

[0065] When a query input via the communication device 30 is received, the prompt generator 140 obtains knowledge base selection information for selecting a knowledge base to be used (step S306).

[0066] As one example, the prompt generation unit 140 is configured to use information obtained by an operation of the communication device 30 as knowledge base selection information. As a specific example, assume that a user performs an operation to activate a function for searching for cooking recipes in a predetermined application installed on the communication device 30. In this case, the prompt generation unit 140 acquires information about the operation (the operation for activating the function for searching for cooking recipes) as knowledge base selection information. Based on the information acquired as the knowledge base selection information, the prompt generation unit 140 selects a knowledge base that stores information related to cooking recipes from various knowledge bases. As another specific example, assume that a user performs an operation to activate a function for checking the trends of investment products in a predetermined application installed on the communication device 30. Based on the information acquired as the knowledge base selection information, the prompt generation unit 140 acquires information about the operation (the operation for activating the function for checking the trends of investment products) as knowledge base selection information. Based on the information acquired as the knowledge base selection information, the prompt generation unit 140 selects a knowledge base that stores information related to investment products from various knowledge bases.

[0067] As another example, the prompt generation unit 140 may be configured to use the query information acquired in the process of step S302 as knowledge base selection information. As a specific example, suppose a query regarding a recipe for a dish using certain ingredients is acquired in the process of step S302. In this case, the prompt generation unit 140 selects, from various knowledge bases, a knowledge base that stores information related to the subject of the query (the recipe). As another specific example, suppose a query asking about recommended investment portfolios for saving for a home is acquired in the process of step S302. In this case, the prompt generation unit 140 selects, from various knowledge bases, a knowledge base that stores information related to the subject of the query (the investment product).

[0068] The prompt generator 140 then obtains additional information from the selected knowledge base (step S308).

[0069] As an example, assume that a knowledge base storing information related to "cooking recipes" is selected in step S306. In this case, the prompt generation unit 140 can identify additional information to be acquired from the selected knowledge base by using, for example, a keyword included in the query (e.g., a keyword indicating the purpose, such as "matsutake mushroom dishes").

[0070] As another example, suppose a knowledge base storing information related to "investment products" is selected in the processing of step S306. In this case, the prompt generation unit 140 can identify additional information to be acquired from the selected knowledge base, for example, using keywords included in the query (e.g., a keyword indicating a purpose, such as "housing finance"). The prompt generation unit 140 may also be configured to identify additional information to be acquired from the selected knowledge base by using, instead of or in addition to, information indicating user information (user characteristics). For example, suppose a knowledge base storing information related to "financial products," e.g., investment products, is selected in the processing of step S306. Furthermore, suppose the user information acquired in step S304 includes information indicating a user characteristic (psychographic attribute) of "risk-loving." In this case, the prompt generation unit 140 acquires information corresponding to "housing finance" from financial product knowledge in the knowledge base storing information about financial products. Such psychographic information regarding the user's attitude toward investment risk can be generated by the user information acquisition unit 110 based on an operation log of the communication device used by the user (for example, log information indicating a transaction history in a dedicated application or an information browsing history in a browser). Furthermore, when cooperation is obtained from a company that handles investment products, such as a securities company, the user information acquisition unit 110 may acquire, as user information, information indicating the user's characteristics provided by the company.

[0071] A more specific example is described below. For example, when text or audio information such as "Tell me an effective way to prepare funds for a home" is input as a query, the prompt generation unit 140 extracts "home financing" as a keyword from the input information. The prompt generation unit 140 then selects a knowledge base related to financial products. The prompt generation unit 140 then uses the selected knowledge base to identify knowledge related to financial products.

[0072] For example, suppose the prompt generation unit 140 is able to acquire the following information (1) to (5) from a knowledge base about financial products. (1) The higher the yield of a financial product, the higher the potential for generating profits in a short period of time. (2) Generally, the higher the yield, the higher the risk of loss. (3) Bonds have relatively low yields. (4) Stocks tend to have high yields. (5) Mr. A, a well-known investor, is an investor who tolerates relatively high risks and holds shares in Company X and Company Y. The yield last year was △△%. In this case, the prompt generation unit 140 can generate (acquire) the following information as additional information:

[0073] <<Example of additional information>> The higher the yield of a financial product, the greater the chance of earning a high profit in a short period of time, but generally, the higher the yield, the greater the risk of loss. Bonds tend to have relatively low yields, while stocks tend to have high yields. Mr. A, a well-known investor, is an investor who tolerates a relatively high level of risk and holds stocks in Company X and Company Y, with a yield of △△% last year.

[0074] Then, the prompt generation unit 140 generates a prompt to be provided to the generation AI 20 using the query obtained in the processing of step S302, the user information obtained in the processing of S304, and the additional information obtained in S308 (step S310).

[0075] For example, the prompt generation unit 140 completes the prompt to be provided to the generation AI 20 using prompt template data exemplified in FIG. 9. FIG. 9 is a diagram showing an example of prompt template data provided to the generation AI. In the example shown in this figure, user information acquired by the user information acquisition unit 110 is incorporated into the {User Information} section. Also in the example shown in this figure, a query acquired by the query acquisition unit 120 is incorporated into the {Query} section. Also, additional information acquired from the knowledge base by the prompt generation unit 140 is incorporated into the {Additional Information} section. As a specific example, assume that the user information acquired by the user information acquisition unit 110 is "self-growth oriented, information / technology enthusiast" and the query is "Please tell me a recipe for matsutake mushroom dishes." Also, suppose that additional information such as "The recommended matsutake dish is dobinmushi. The key to making dobinmushi is to use particularly good ingredients and take the time and effort to make the broth" is acquired from the knowledge base (knowledge base related to cooking recipes) selected by the prompt generation unit 140. In this case, the prompt generation unit 140 generates a prompt such as the one shown in <<Prompt example>> below as a prompt to be given to the generation AI 20.

[0076] <<Example prompt>> You are an excellent butler. Please answer the host's question in a way that suits his characteristics. The host's question is, "Please tell me a recipe for a matsutake dish," and the host's characteristics are "self-growth-oriented, information / technology enthusiast." == The recommended matsutake dish is dobinmushi. The key to making dobinmushi is to use particularly good ingredients and take the time and effort to extract the broth.

[0077] The prompt generation unit 140 inputs the generated prompt to the generation AI 20 (step S312). This results in an output result for the given prompt being obtained from the generation AI 20. The display processing unit 130 acquires the result output from the generation AI 20 in response to the processing of step S312 and displays the result on the display of the communication device 30 (step S314).

[0078] As described above, this embodiment includes the same configuration as the first embodiment, and therefore provides the same effects as those described in the first embodiment. In addition, the prompt generation unit 140 further incorporates additional information obtained from a knowledge base selected using the query and user information into the prompt provided to the generation AI 20. This allows more specialized information to be obtained from the generation AI 20 in a form tailored to the user's characteristics and presented to the user.

[0079] <Example of Display Control Process for Output Information> When displaying output information in response to a given prompt on a display of a target device (e.g., communication device 30), the display processing unit 130 may change the display mode of the output information based on information about the display of the output destination. For example, the display processing unit 130 can acquire information about the display connected to the output destination device by communicating with the output destination device. Although not particularly limited, "information about the display" in the present disclosure includes, for example, information indicating the size of the display, information about the aspect ratio of the display area of ​​the display, etc.

[0080] As an example, the display processing unit 130 may adjust the size of the display content (such as text, graphics, and graphs displayed based on the output information) on the output destination display depending on the size of the display. For example, the display processing unit 130 may execute control such that the larger the output destination display, the larger the displayed content. Similarly, the display processing unit 130 may execute control such that the smaller the output destination display, the smaller the displayed content. This can improve the visibility of the information displayed on the output destination display. In this case, an upper or lower limit may be set for the size of the displayed content. By setting an upper or lower limit for the size of the displayed content, it is possible to avoid problems such as the displayed content being displayed larger or smaller than necessary on the display, which could actually reduce visibility.

[0081] As another example, the display processing unit 130 may change the position of the display content on the output destination display, or may prevent a specific item in the display content from being displayed on the same screen.

[0082] As yet another example, the display processing unit 130 may be configured to change the display content depending on the processing capacity of the destination device (e.g., communication device 30). For example, the display processing unit 130 may reduce the amount of information displayed when the destination device has low processing capacity compared to when the destination device has high processing capacity. As a specific example, the display processing unit 130 may reduce the number of characters included in the display content by using a function to summarize text using natural language processing. Additionally, the display processing unit 130 may reduce the data size of drawings and graphs by lowering the resolution of the drawings and graphs or by limiting the number of colors used in the drawings and graphs. The display processing unit 130 may be configured to determine the "processing capacity of the destination device" by referencing a database (not shown) that pre-stores information regarding specifications such as the memory size of each device. Furthermore, the display processing unit 130 may be configured to communicate with the destination device and acquire information such as the operating status of the device's processor and the execution status of tasks as information for determining the "processing capacity of the destination device."

[0083] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0084] In addition, although the flowcharts used in the above description show a sequence of steps (processes), the order of steps executed in each embodiment is not limited to the sequence shown in the flowcharts. In each embodiment, the order of steps shown in the diagrams can be changed as long as it does not cause any problems in terms of the content.

[0085] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. 1. An information providing device comprising: user information acquiring means for acquiring user information about the user based on information obtained from a communication device used by the user; query acquiring means for acquiring a query for generative artificial intelligence (AI); and display processing means for displaying an output result of the generative AI based on the query and the user information. 2. The information providing device described in 1., further comprising prompt generating means for generating a prompt using the query and the user information and inputting the prompt to the generative AI. 3. The information providing device described in 2., wherein the prompt generating means acquires additional information from a knowledge base selected based on selection information indicating a knowledge base to be used, and generates the prompt by combining the additional information with the query and the user information. 4. The information providing device described in any one of 1. to 3., wherein the user information includes information indicating a psychographic attribute of the user. 5. The information providing device described in 4., wherein the user information acquisition means generates information regarding the psychographic attributes of the user using information regarding applications installed in the communication device. 6. The information providing device described in 5., wherein the user information acquisition means acquires information indicating the psychographic attributes of the user from the generation AI by providing the generation AI with a prompt generated based on information regarding applications installed in the communication device. 7. The information providing device described in 4., wherein the user information acquisition means generates information regarding the psychographic attributes of the user using a history of input and output of the generation AI. 8. The information providing device described in any one of 1. to 7., wherein the user information includes information indicating the user's digital skills.9. A method of providing information, comprising: a computer acquiring user information about a user based on information obtained from a communication device used by the user, acquiring a query for generative AI (generative artificial intelligence), and displaying an output result of the generative AI based on the query and the user information. 10. A program that, when executed by a computer, causes the computer to perform operations, including: acquiring user information about the user based on information obtained from a communication device used by the user, acquiring a query for generative AI (generative artificial intelligence), and displaying an output result of the generative AI based on the query and the user information.

[0086] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 8 that are subordinate to the above-mentioned Supplementary Note (information providing device) may also be subordinate to Supplementary Note 9 (information providing method) and Supplementary Note 10 (program) in the same subordinate relationship as Supplementary Note 2 to Supplementary Note 8. Furthermore, not limited to Supplementary Note 1, Supplementary Note 9, and Supplementary Note 10, some or all of the configurations described as Supplements may be subordinate to various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0087] This application claims priority based on Japanese Patent Application No. 2024-042823, filed March 18, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0088] REFERENCE SIGNS LIST 10 Information providing device 1000 Computer 1010 Bus 1020 Processor 1030 Memory 1040 Storage device 1050 Input / output interface 1060 Network interface 110 User information acquisition unit 120 Query acquisition unit 130 Display processing unit 140 Prompt generation unit 20 Generation AI 30 Communication device

Claims

1. An information providing device comprising: a user information acquisition means for acquiring user information about a user based on information obtained from a communication device used by the user; a query acquisition means for acquiring a query for generative artificial intelligence (AI); and a display processing means for displaying the output result of the generative AI based on the query and the user information.

2. The information providing device according to claim 1, further comprising prompt generating means for generating a prompt using the query and the user information and inputting the prompt to the generation AI.

3. The information providing device according to claim 2, wherein the prompt generating means obtains additional information from a knowledge base selected based on selection information indicating the knowledge base to be used, and generates the prompt by combining the additional information with the query and the user information.

4. The information providing device according to any one of claims 1 to 3, wherein the user information includes information indicating psychographic attributes of the user.

5. The information providing device according to claim 4, wherein the user information acquiring means generates information about the psychographic attributes of the user using information about applications installed in the communication device.

6. The information providing device of claim 5, wherein the user information acquisition means acquires information indicating the psychographic attributes of the user from the generation AI by providing the generation AI with a prompt generated based on information regarding applications installed on the communication device.

7. The information providing device according to claim 4, wherein the user information acquisition means generates information regarding the psychographic attributes of the user using a history of input and output of the generation AI.

8. An information providing device according to any one of claims 1 to 7, wherein the user information includes information indicating the digital skills of the user.

9. A method of providing information, comprising: a computer acquiring user information about a user based on information obtained from a communication device used by the user; acquiring a query for generative artificial intelligence (AI); and displaying an output result of the generative AI based on the query and the user information.

10. The information providing method of claim 9, further comprising the step of: generating a prompt using the query and the user information, and inputting the prompt to the generating AI.

11. The information providing method according to claim 10, further comprising the step of: said computer obtaining additional information from a knowledge base selected based on selection information indicating a knowledge base to be used; and generating said prompt by combining said additional information with said query and said user information.

12. The information providing method according to any one of claims 9 to 11, wherein the user information includes information indicating psychographic attributes of the user.

13. The information providing method according to claim 12, wherein the computer generates information about the psychographic attributes of the user using information about applications installed on the communication device.

14. The information provision method of claim 13, further comprising the step of: the computer obtaining information indicating the user's psychographic attributes from the generating AI by providing the generating AI with a prompt that is generated based on information about applications installed on the communication device.

15. The information provision method according to claim 12, further comprising the step of: generating information relating to the psychographic attributes of the user using a history of input and output of the generating AI.

16. An information providing method according to any one of claims 9 to 15, wherein the user information includes information indicating the digital skills of the user.

17. A computer-readable recording medium that records a program that, when executed by a computer, causes the computer to perform operations including: obtaining user information about the user based on information obtained from a communication device used by the user; obtaining a query for generative AI (generative artificial intelligence); and displaying the output result of the generative AI based on the query and the user information.

Images