System, computer device, and method

Abstract

To provide a system for specifying appropriate advertisement information.SOLUTION: A system includes at least one computer device. The system includes acquisition means which acquires advertisement information similar to an answer obtained by inputting a prompt to a language model, from a database that stores advertisement information relating to advertisements. The acquisition means acquires multiple pieces of advertisement information. The system may include selection means which selects, from among the acquired multiple pieces of advertisement information, one or more pieces of advertisement information similar to the prompt or a question input from a user terminal to generate a prompt.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a system, a computer device and a method. [Background technology]

[0002] In recent years, systems have been provided that use large-scale language models (LLMs) to perform natural language processing tasks such as question-answering, text summarization, and text generation. LLMs are natural language processing models trained using large amounts of text data. When using LLMs in a question-answering system, text is input into the LLM, which outputs an answer. The text input into the LLM is called a prompt. By using LLMs, users can easily obtain answers. However, depending on the content of the prompt, the LLM may not provide an appropriate answer.

[0003] For example, Patent Document 1 discloses an information processing device that enables answers to questions to be provided with increased accuracy. The information processing device described in Patent Document 1 includes a processing unit that selects a database corresponding to an input question from among a plurality of databases each storing different types of data based on the content of the question, generates a prompt to be input into a language model based on the selected database and the question, and generates an answer based on the prompt and the language model. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7441366 Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention can solve, for example, any of the following problems.

[0006] A first object of the present invention is to provide a system that generates a prompt by adding predetermined information when the input question does not contain predetermined information. A second object of the present invention is to provide a system that can identify appropriate advertising information. A third object of the present invention is to provide a system that can provide an answer with improved accuracy. A fourth object of the present invention is to provide a system that can provide new suggestions to users. A fifth object of the present invention is to provide a system that can determine whether an answer to an input question is appropriate. [Means for solving the problem]

[0007] The object of the present invention is to [1] A system including at least one computer device, the system including: a determination means for determining whether a question input from a user terminal includes predetermined information; and a first generation means for, when it is determined that the input question does not include the predetermined information, adding the predetermined information to the question and generating a prompt to be input to the language model; [2] The system according to [1], wherein the determining means determines whether the input question contains predetermined information by comparing the input question with a standard question phrase; [3] The system according to [1] or [2], wherein the input question is a request for a recommended action, and the predetermined information is information about a purpose to be achieved or a feeling to be obtained by performing the recommended action, or information about a situation or condition when performing the recommended action; [4] The system according to [3], further comprising: a requesting means for requesting a user terminal to input information about the purpose or the emotion, or the situation or the condition, when the determining means determines that the input question does not include, as predetermined information, the purpose or the emotion, or information about the situation or the condition; and a first generating means for generating a prompt to be input to the language model based on the question and the information about the purpose or the emotion, or the situation or the condition, acquired by input from the user terminal; [5] A method executed on at least one computer device, the method comprising: a determination step of determining whether a question input from a user terminal includes predetermined information; and a first generation step of adding the predetermined information to the question and generating a prompt to be input to the language model when it is determined that the input question does not include the predetermined information; [6] A computer device comprising: a determination means for determining whether a question input from a user terminal contains predetermined information; and a first generation means for, when it is determined that the input question does not contain the predetermined information, adding the predetermined information to the question and generating a prompt to be input to the language model; [7] A system including at least one computer device, the system including an acquisition means for acquiring, from a database in which advertising information related to advertisements is stored, advertising information similar to an answer acquired by inputting a prompt into a language model; [8] The system according to [7], wherein the acquisition means acquires a plurality of pieces of advertising information, and the system includes a selection means for selecting, from the acquired plurality of pieces of advertising information, one or more pieces of advertising information that are similar to a prompt or a question input from the user terminal to generate a prompt; [9] The system according to [8] or [9], further comprising: a calculation execution means for executing a vector operation on an answer obtained by inputting a prompt into a language model; and an acquisition means for acquiring advertising information in which a value obtained by executing the vector operation on the advertising information is close to a value obtained by the vector operation from the answer;

[10] A system including at least one computer device, the system including an acquisition means for acquiring, from a database in which advertising information related to advertisements is stored, advertising information similar to a prompt or a question input from a user terminal for generating a prompt for input into a language model;

[11] The system according to

[10] , wherein the acquisition means acquires a plurality of pieces of advertising information, and the system further comprises a selection means for selecting, from the acquired plurality of pieces of advertising information, one or more pieces of advertising information that are similar to the answer acquired by inputting the prompt into a language model;

[12] The system according to

[10] or

[11] , further comprising: a calculation execution means for executing a vector calculation on a question input from a user terminal or information relating to the question in order to generate a prompt; and an acquisition means for acquiring advertising information in which a value obtained by executing the vector calculation on the advertising information is approximate to a value obtained by the vector calculation from the question or information relating to the question;

[13] A method executed on at least one computer device, comprising: acquiring, from a database storing advertising information relating to advertisements, advertising information similar to an answer acquired by inputting a prompt into a language model;

[14] A method executed on at least one computer device, comprising: acquiring, from a database storing advertising information relating to advertisements, advertising information similar to a prompt or a question input from a user terminal for generating a prompt for input into a language model;

[15] A computer device comprising: an acquisition means for acquiring, from a database in which advertising information relating to advertisements is stored, a plurality of pieces of advertising information similar to an answer acquired by inputting a prompt into a language model;

[16] A computer device comprising: an acquisition means for acquiring, from a database in which advertising information relating to advertisements is stored, a plurality of pieces of advertising information similar to a prompt to be input into a language model or a question input from a user terminal to generate a prompt;

[17] A system including at least one computer device, the system including: an answer acquisition means for acquiring an answer from a language model based on a prompt; an acquisition means for acquiring or generating information about a facility or area from a database storing information about the facility or area when the prompt to be input to the language model includes facility preference information requesting a recommendation of a facility or area; and an answer editing means for editing the answer acquired from the language model based on the information acquired or generated by the acquisition means;

[18] A system including at least one computer device, the system including: an answer acquisition means for acquiring an answer from a language model based on a prompt; an acquisition means for acquiring or generating information about a facility or area corresponding to the answer from a database storing information about the facility or area when the answer acquired from the language model includes information about the facility or area; and an answer editing means for editing the answer acquired from the language model based on the information acquired or generated by the acquisition means;

[19] The system according to

[17] or

[18] , further comprising: a calculation execution means for executing a vector operation on a prompt or an answer obtained by inputting the prompt into a language model; and an acquisition means for acquiring information about a facility or area, the information about which is obtained by executing the vector operation on the information about the facility or area being close to a value obtained by the vector operation from the prompt or the answer;

[20] A method executed on at least one computer device, the method comprising: an answer acquisition step of acquiring an answer from a language model based on a prompt; an acquisition step of acquiring or generating information about a facility or area from a database storing information about the facility or area when the prompt to be input to the language model includes facility preference information requesting a recommendation of a facility or area; and an answer editing step of editing the answer acquired from the language model based on the information acquired or generated in the acquisition step;

[21] A method executed on at least one computer device, the method comprising: an answer acquisition step of acquiring an answer from a language model based on a prompt; an acquisition step of acquiring or generating information about a facility or area corresponding to the answer from a database storing information about the facility or area, if the answer acquired from the language model includes information about the facility or area; and an answer editing step of editing the answer acquired from the language model based on the information acquired or generated in the acquisition step;

[22] A computer device comprising: an answer acquisition means for acquiring an answer from a language model based on a prompt; an acquisition means for acquiring or generating information about a facility or area from a database that stores information about the facility or area when the prompt to be input to the language model includes facility preference information requesting a recommendation of a facility or area; and an answer editing means for editing the answer acquired from the language model based on the information acquired or generated by the acquisition means;

[23] A computer device comprising: answer acquisition means for acquiring an answer from a language model based on a prompt; acquisition means for acquiring or generating information about a facility or area corresponding to the answer from a database storing information about the facility or area when the answer acquired from the language model includes information about the facility or area; and answer editing means for editing the answer acquired from the language model based on the information acquired or generated by the acquisition means;

[24] A system including at least one computer device, the system including: an answer acquisition means for acquiring an answer from a language model based on a prompt; a proposal generation means for generating proposal information corresponding to the answer when the answer acquired from the language model includes action information that triggers the generation of proposal information suggesting an action to be taken by a user; and an answer editing means for editing the answer acquired from the language model based on the proposal information generated by the proposal generation means;

[25] A method executed on at least one computer device, the method comprising: an answer acquisition step of acquiring an answer from a language model based on a prompt; a proposal generation step of generating proposal information corresponding to the answer when the answer acquired from the language model includes action information that triggers the generation of proposal information suggesting an action to be taken by a user; and an answer editing step of editing the answer acquired from the language model based on the proposal information generated in the proposal generation step;

[26] A computer device comprising: answer acquisition means for acquiring an answer from a language model based on a prompt; proposal generation means for generating proposal information corresponding to the answer when the answer acquired from the language model includes action information that triggers the generation of proposal information suggesting an action to be taken by a user; and answer editing means for editing the answer acquired from the language model based on the proposal information generated by the proposal generation means;

[27] A system including at least one computer device, the system including a determination means for determining whether an answer obtained by inputting a prompt into a language model is appropriate as an answer to a question corresponding to the prompt, based on an example prompt and an example answer corresponding to the example prompt;

[28] The system according to

[26] , wherein the determination means determines that the answer is appropriate as an answer to the question corresponding to the prompt when the prompt includes facility preference information requesting a recommendation of a facility or area and the answer includes information about the facility or area;

[29] The system according to

[27] or

[28] , further comprising an operation execution means for executing vector operations on a prompt and an answer obtained by inputting the prompt into a language model, and wherein the determination means determines that the answer is appropriate as an answer to the question corresponding to the prompt when a value obtained by vector operation on the prompt is approximate to a value obtained by vector operation on the prompt, or when a value obtained by vector operation on an answer example corresponding to the prompt is approximate to a value obtained by vector operation on the answer;

[30] A method executed on at least one computer device, comprising a determining step of determining whether an answer obtained by inputting a prompt into a language model is appropriate as an answer to a question corresponding to the prompt, based on an example prompt and an example answer corresponding to the example prompt;

[31] A computer device including a determination means for determining whether an answer obtained by inputting a prompt into a language model is appropriate as an answer to a question corresponding to the prompt, based on an example prompt and an example answer corresponding to the example prompt; This can be solved by: [Effects of the Invention]

[0008] According to the present invention, it is possible to provide a system that generates a prompt by adding predetermined information when predetermined information is not included in an input question. According to the present invention, it is possible to provide a system that can identify appropriate advertising information. According to the present invention, it is possible to provide a system that can provide an answer with increased accuracy. According to the present invention, it is possible to provide a system that can provide new suggestions to a user. According to the present invention, it is possible to provide a system that can determine whether an answer to an input question is appropriate. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing a configuration of a system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing a hardware configuration of a user terminal according to an embodiment of the present invention. [Figure 3] FIG. 2 is a block diagram showing a hardware configuration of a server device according to an embodiment of the present invention. [Figure 4] FIG. 10 is a flowchart showing an output process according to an embodiment of the present invention. [Figure 5] FIG. 10 is a flowchart showing a question completion process according to an embodiment of the present invention. [Figure 6] FIG. 10 is a flowchart showing a confirmation information output process according to the embodiment of the present invention. [Figure 7] FIG. 10 is a flowchart showing a response acquisition process according to an embodiment of the present invention. [Figure 8] FIG. 10 is a flowchart showing an answer determination process according to an embodiment of the present invention. [Figure 9] FIG. 10 is a flowchart showing an answer complementing process according to an embodiment of the present invention. [Figure 10] FIG. 10 is a flowchart showing an advertisement specification process according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0010] The following describes embodiments of the present invention, but the present invention is not limited to the following embodiments as long as they do not violate the spirit of the present invention. The order of each process constituting the flowcharts described below is random as long as no contradictions or inconsistencies occur in the process content. Furthermore, it is possible to omit some of the processes constituting the flowcharts or add new processes to each process constituting the flowcharts as long as they do not violate the spirit of the present invention. Furthermore, the device that executes each process constituting the flowcharts can be changed to another device as long as it does not violate the spirit of the present invention. In this case, the process content can be changed so as not to cause contradictions or inconsistencies in the process content.

[0011] The system of the present invention is a system that provides a user with information to support the user's actions. In this embodiment, the user's actions are actions performed by the user for a predetermined purpose, and the user's actions may involve movement or may not involve movement. The purpose of the actions is not particularly limited, but examples include travel, business trips, going out, sightseeing, exercise, walking, shopping, resting, and evacuation. Furthermore, the information that supports the user's actions may be information corresponding to the purpose of the user's actions, information regarding means for achieving the purpose of the user's actions, or information derived from the purpose of the user's actions.

[0012] [System Configuration] FIG. 1 is a block diagram showing the configuration of an information processing system according to an embodiment of the present invention. The system 10 includes at least one computer device. The system 10 includes, for example, a user terminal 1 and a server device 2. The system 10 may also include a language model server 3 and an administrator terminal 4. The user terminal 1, the server device 2, the language model server 3, and the administrator terminal 4 are communicably connected to each other via a communication network 5. In the system 10, any one of the user terminal 1, the server device 2, and the language model server 3 can function as an information processing device. When any one of the devices functions as an information processing device, information is transmitted and received between the user terminal 1, the server device 2, and the language model server 3 as necessary.

[0013] The system 10 may include multiple user terminals 1, multiple server devices 2, and multiple administrator terminals 4. The server devices 2 may function in a distributed manner across multiple computer devices. For example, instead of the server devices 2, a distributed ledger technology such as a blockchain may be used.

[0014] [User device] The user terminal 1 is operated by a user of the system 10. The user operates the user terminal 1 to input a predetermined question to the system 10. The user terminal 1 is not particularly limited, but examples thereof include a conventional mobile phone, a tablet terminal, a smartphone, a laptop computer, a desktop computer, etc.

[0015] 2 is a block diagram showing the hardware configuration of a user terminal according to an embodiment of the present invention. The user terminal 1 includes a control unit 11, a RAM 12, a storage unit 13, an input unit 14, a display unit 15, and a communication interface 16, all of which are connected via a bus. The user terminal 1 may also include a GPS receiver.

[0016] The control unit 11 is composed of a CPU and a ROM. The control unit 11 executes programs stored in the storage unit 13 and controls the user terminal 1. The RAM 12 is a work area for the control unit 11. The storage unit 13 is a memory area for saving programs and data. In other words, the storage unit 13 functions as a recording medium that stores programs. The control unit 11 performs arithmetic processing based on the programs and data read from the RAM 12 and data input via the input unit 14.

[0017] The display unit 15 has a display screen. The control unit 11 outputs a video signal for displaying an image on the display screen according to the result of the arithmetic processing. Here, the display screen of the display unit 15 may be a touch panel equipped with a touch sensor. In this case, the touch panel functions as the input unit 14. The GPS receiver receives a GPS signal and identifies the location of the user terminal 1. The communication interface 16 can be connected to the communication network 5 wirelessly or via a cable, and can send and receive data to and from other computer devices via the communication network 5. Data received via the communication interface 16 is loaded into the RAM 12, and the control unit 11 performs arithmetic processing.

[0018] [Server device] 3 is a block diagram showing a hardware configuration of a server device according to an embodiment of the present invention. The server device 2 includes at least a control unit 21, a RAM 22, a storage unit 23, and a communication interface 24, which are connected to each other via an internal bus.

[0019] The control unit 21 is composed of a CPU and a ROM, and executes programs stored in the storage unit 23 to control the server device 2. The control unit 21 also has an internal timer that measures time. The RAM 22 is the work area of ​​the control unit 21. The storage unit 23 is a memory area for saving programs and data. In other words, the storage unit 23 functions as a recording medium that stores programs. The control unit 21 reads out the programs and data from the RAM 22, and performs program execution processing based on information received from the user terminal 1, etc.

[0020] The server device 2 generates a prompt to be input to the language model server 3 based on the question input from the user terminal 1. The server device 2 edits the answer based on the answer output from the language model server 3. The server device 2 also acquires advertisement information related to the advertisement based on the answer output from the language model server 3. The server device 2 stores various databases (DBs) for executing these processes in the storage unit 23. The content of each process and the various DBs will be described later.

[0021] [Language model server] The language model server 3 is a computer device that stores a language model for processing natural language. The hardware configuration of the language model server 3 can be appropriately adapted from the description of the hardware configuration of the server device 2. In this embodiment, the language model used is the LLM, but a language model other than the LLM may also be used as long as it can process natural language.

[0022] Note that the server device 2 may store a language model. When a language model is stored in the server device 2, the system 10 does not need to include the language model server 3. Alternatively, a small-scale language model that is smaller in scale than an LLM may be stored in the server device 2, and the LLM may be stored in the language model server 3. A small-scale language model is a natural language processing model trained based on less data than an LLM.

[0023] [Administrator's terminal] The administrator terminal 4 is operated by an administrator who manages the system 10. The administrator terminal 4 is not particularly limited, but examples thereof include conventional mobile phones, tablet terminals, smartphones, laptops, and desktop computers. The hardware configuration of the administrator terminal 4 can be appropriately adapted from the description of the hardware configuration of the user terminal 1.

[0024] In this embodiment, the program may be stored on a recording medium such as a CD-ROM. In this case, the program stored on the recording medium may be installed in the user terminal 1 or the server device 2 to execute the predetermined function. Alternatively, the program may be distributed from a computer device external to the system. In this case, the program distributed from the computer device external to the system may be installed in the user terminal 1 or the server device 2 to execute the predetermined function.

[0025] [Output Processing] The output processing of the system 10 according to this embodiment will be described. Fig. 4 is a diagram showing a flowchart of the output processing according to this embodiment. Details of each process included in the flowchart will be described later.

[0026] First, the user logs in to the system 10 by accessing the server device 2 from the user terminal 1 via a web browser. Alternatively, the user may log in to the system 10 by activating an application program (hereinafter referred to as a dedicated app) downloaded to the user terminal 1 and accessing the server device 2. When logging in to the system 10, the user may be required to input pre-registered user identification information (also referred to as a user ID) or an email address, and a password.

[0027] When a user logs in to the system 10, the user inputs a question by operating the user terminal 1. The server device 2 accepts input of question information related to the question (step S100).

[0028] Questions are input in natural language (text). Question information is text information related to a sentence, and includes letters, symbols, or numbers. A user can input a question using a keyboard, mouse, touch panel, voice input device, or the like. The content of the question is not particularly limited, but the question may, for example, be a request for a recommended action. For example, the question may be, "I want to know where I can spend time before departure," or "An earthquake occurred while I was out. What should I do?"

[0029] Next, the server device 2 generates one or more partial prompts from the question information (step S120). The partial prompts are generated by breaking down the question information. A known method can be used for the process of generating the partial prompts. For example, the partial prompts may be generated so that one thing is included in one sentence. The partial prompts can be considered to be part of the question.

[0030] Each partial prompt can be used as a prompt. In this embodiment, a prompt is text information to be input to a language model. The system 10 may combine multiple partial prompts and input them as a single prompt to the language model. An answer is obtained by inputting the prompt to the language model.

[0031] For example, if the question information is "Please tell me where you recommend in Tokyo before I board the Shinkansen at 11 o'clock," in step S120, the server device 2 generates a partial prompt "I will board the Shinkansen at 11 o'clock," and a partial prompt "Please tell me where you recommend in Tokyo."

[0032] Next, the server device 2 determines whether or not the question input from the user terminal 1 in step S100 contains predetermined information. If the question does not contain the predetermined information and there is missing information (also called missing elements), a question completion process is executed to complete the missing elements and generate a partial prompt (step S140). In step S140, a partial prompt may be generated regardless of whether or not there are missing elements. In step S140, at least one partial prompt is generated.

[0033] For example, in step S140, the partial prompt "Please tell me some recommended places in Tokyo" changes to the partial prompt "Please tell me some recommended places in Tokyo for sightseeing." Also, in step S140, the partial prompts "The questioner is currently in Shibuya," "The questioner is male," and "The questioner's hobby is visiting museums" are generated.

[0034] When a partial prompt with missing elements completed is generated in step S140, the server device 2 generates a prompt for input to the language model (step S160). In the system 10, multiple partial prompts are generated before the processing of step S160. In step S160, the server device 2 combines the multiple partial prompts generated in steps S120, S146, S148, and / or S149 to generate a single prompt. In other words, when the system 10 determines that the input question does not contain predetermined information, it can add the predetermined information to the question and generate a prompt for input to the language model.

[0035] For example, if partial prompts such as "I will be taking the Shinkansen at Shinagawa Station at 11 o'clock," "What are some recommended places in Tokyo for sightseeing?", "The questioner is a man," and "The questioner's hobby is visiting museums" are generated, the following prompts will be generated in step S160. "What places in Tokyo do you recommend for sightseeing? Please use the information below as a reference when answering. I'll be boarding the Shinkansen at Shinagawa Station at 11:00. The questioner is currently in Shibuya. The questioner is male. His hobby is visiting museums.

[0036] Next, an answer acquisition process is executed to acquire an answer based on the prompt generated in step S160 (step S180). For example, when step S180 is executed for the above prompt, the following answer is obtained: The facility information included in the answer is information about an actually existing facility. "We'll introduce you to some recommended sightseeing spots in Tokyo. Before boarding the Shinkansen from Shinagawa Station, you can enjoy places that are close to Shibuya and suit your tastes. A Art Museum: It has a wide range of exhibits from modern art to contemporary art. Museum B: Located in Ueno, this is a wonderful museum where you can experience Japanese history and culture. C Museum: A museum where you can learn about Tokyo's history and culture from the Edo period to the present day. I chose these museums to coincide with my hobby of visiting museums."

[0037] Next, an answer determination process is executed (step S200) to determine whether the answer acquired in step S180 is appropriate as an answer to the question corresponding to the prompt generated in step S160. If the answer is appropriate, an answer complement process is executed (step S220) to complement the answer acquired in step S180.

[0038] For example, the above answer is determined to be appropriate in response to the question, "Please tell me some recommended places in Tokyo before I board the Shinkansen at 11 o'clock." Furthermore, when the answer is complemented in step S220, the following sentence is obtained. "We'll introduce you to some recommended sightseeing spots in Tokyo. Before boarding the Shinkansen from Shinagawa Station, you can enjoy places that are close to Shibuya and suit your tastes. A Art Museum: It has a wide range of exhibits from modern art to contemporary art. From Shibuya, it takes about 20 minutes by train, and about 30 minutes to Shinagawa. The total journey time is about 1 hour. For transfer information, please see the following website: https: / / www.shinagawa-station.jp / Would you like to schedule Museum A from 10:00 to 11:00? Museum B: A wonderful museum where you can experience Japanese history and culture. It takes about 25 minutes by train from Shibuya and about 45 minutes to Shinagawa. The total journey time is 45 minutes. For transfer information, please see the following website: https....However, it seems that X station is crowded. Reservation tickets for the B Museum can be obtained from the following website: https: / / www.bmuseum.jp / I chose these museums to suit my hobby of visiting museums. I also took into consideration the travel time from Shibuya to Shinagawa, so you can enjoy both sightseeing and travel. Note that "Would you like to schedule Museum A from 10:00 to 11:00?" and "You can get reservation tickets for Museum B from the following website: https..." correspond to the action suggestion information described below.

[0039] In addition, an advertisement identification process is executed to identify advertisement information based on the question information entered in step S100 or the prompt generated in step S160, and / or the answer obtained in step S180 or the answer supplemented in step S220 (step S240).

[0040] For example, in response to the question "What are some recommended places in Tokyo where I can go before boarding the Shinkansen at 11 o'clock?", the following advertisements are identified for the answer completed in step S220. "D Coffee Shop: It has a relaxed and comfortable atmosphere. For more information, please visit: https…." "F Memorial Park: You can see buildings that recreate the streets of the Edo period. Opening hours are 9:00 AM to 4:00 PM. For more information, please see the following website: https..."

[0041] The answer complemented in step S220 and the advertising information identified in step S240 are output to the user terminal 1 (step S260). The output process is completed by the above-described processes of steps S100 to S260.

[0042] In step S260, the display mode in which the answer and advertisement information are output on the user terminal 1 is not particularly limited. For example, the answer is output in a chat format. The answer may be displayed as one response or as multiple responses. When multiple responses are displayed, for example, the answer generated based on the answer output from the language model, facility information about the facility or area information about the area, proposal information about the proposal, and advertisement information may each be displayed in a different speech bubble.

[0043] [Question completion processing] The question completion process in step S140 will now be described with reference to Fig. 5, which is a flowchart of the question completion process according to the embodiment of the present invention.

[0044] First, the server device 2 determines whether or not the question input from the user terminal 1 includes predetermined information (step S141). If the question does not include the predetermined information, when the question is input as a prompt to a language model, a desired answer cannot be obtained, or there is a high possibility that the desired answer cannot be obtained. In this embodiment, the predetermined information that is not included in the question is also referred to as a missing element. In other words, in step S141, the server device 2 determines whether or not the question information includes a missing element.

[0045] Here, "predetermined information" refers to information required to answer a question input from the user terminal 1 or to provide an appropriate answer. "Predetermined information" includes at least "command information" related to commands, and may also include "context information" related to context. "Predetermined information" may also include location information related to the user's location. "Predetermined information" may be a predetermined word or a predetermined phrase.

[0046] An instruction specifies whether a question requires an answer of "when," "where," "who," "what," "why," or "how." Instruction information specifies whether a question requires an answer of "when," "where," "who," "what," "why," or "how."

[0047] Context information is information necessary to obtain an appropriate answer from a question, and is information about the user's purpose for obtaining the appropriate answer, the purpose the user wants to achieve by obtaining the answer, the feelings the user wants to have by obtaining the answer, or the circumstances or conditions that are prerequisites for obtaining the appropriate answer. If the question requests an answer about an action to be recommended to the user, the context information is information about the purpose to be achieved or the feelings to be obtained by performing the recommended action, or the circumstances or conditions when performing the recommended action. Context information may also be information about time or location.

[0048] Purpose has the same meaning as the purpose of the above-mentioned action, such as sightseeing, exercise, or a walk. Emotion is the user's subjective feeling, such as excitement, nervousness, surprise, or happiness. Circumstances include how many people are traveling, the attributes of the users (for example, whether there are elderly people or young children), the weather, temperature, etc. Conditions include the means of transportation, the departure and arrival points, time constraints, and cost constraints.

[0049] In step S141, the server device 2 compares the input question with a standard question phrase to determine whether or not the input question contains predetermined information. More specifically, the server device 2 compares the question information received in step S100 or the partial prompt generated in step S120 with the standard phrases stored in the prompt definition DB to determine whether or not the input question contains predetermined information.

[0050] The prompt definition database stores fixed phrases in which predetermined information is defined as prompts or partial prompts. Each fixed phrase is associated with whether the predetermined information is command information, context information, or location information.

[0051] For example, the process of step S141 will be described when only "Todaiji Temple" or "What is Todaiji Temple?" is input as a question in step S100.

[0052] The server device 2 identifies a fixed phrase from the prompt definition DB. For example, the server device 2 identifies fixed phrases such as "How do I get to XX?", "How many minutes does it take to get to XX?", "Where is XX?", "What is XX?", and "Who built XX?". XX corresponds to a word representing a place, location, facility, or region. The server device 2 compares the identified fixed phrase with the question information or partial prompt.

[0053] If the input question is "Todaiji Temple," the server device 2 determines that the predetermined information is not included. If the input question is "What is Todaiji Temple?", the server device 2 determines that the predetermined information is included.

[0054] The method for determining whether predetermined information is included is not particularly limited. For example, the server device 2 may determine whether predetermined information is included based on the similarity between the question information or partial prompt and the fixed phrase. The similarity can be calculated, for example, using vector calculation, which will be described later. If the similarity is equal to or greater than a predetermined threshold or within a predetermined threshold range, the server device 2 can determine that the predetermined information is included. Alternatively, the server device 2 may perform vector calculation after excluding predetermined words, such as proper nouns, from the question information or partial prompt. If the absolute value of the difference between the value obtained by vector calculation of the question information or partial prompt and the value obtained by vector calculation of the fixed phrase is within a predetermined threshold range, the server device 2 can determine that the question information or partial prompt is similar to the fixed phrase. If the question information or partial prompt is not similar to any fixed phrase, the server device 2 may determine that the predetermined information is not included.

[0055] Furthermore, for example, the server device 2 may determine whether or not predetermined information is included by determining whether or not the question information or the partial prompt includes a predetermined phrase determined for each template. For example, if the template is information such as "How do I get to XX?", the server device 2 may determine whether or not the question information or the partial prompt includes a phrase such as "how to get there," "how to get there," or "directions."

[0056] In step S141, if the predetermined information is not included, the server device 2 identifies the content of the predetermined information based on the content associated with the predetermined information. For example, by comparing each of the partial prompts generated in step S120 with the fixed phrase, if the predetermined information corresponding to the command information is not included in any of the partial prompts, the server device 2 can determine that the question information does not include command information and that the predetermined information (missing element) is command information. Furthermore, for example, by comparing the question information with the fixed phrase, if the question information does not include the predetermined information corresponding to the command information, the server device 2 can determine that the question information does not include command information and that the predetermined information (missing element) is command information.

[0057] For example, determining whether the question information contains context information may be performed as follows: The server device 2 identifies a fixed phrase associated with the context information from the prompt definition DB. For example, the server device 2 identifies fixed phrases such as "What are some recommended places for sightseeing?", "Where can I buy souvenirs?", "I'm looking for a place to kill time?", and "Where can I go for a walk?". If the input question is "What are some tourist spots?", the server device 2 determines that the question contains context information and further identifies that the purpose is sightseeing. If the input question is "What are some recommended places in Tokyo?", the server device 2 determines that the question does not contain context information and further identifies that there is insufficient information regarding the purpose.

[0058] In step S141, the server device 2 may determine whether the question information or the partial prompt includes a word representing a place, a location, a facility, or a region. If the question information or the partial prompt includes such information, in step S141, the server device 2 may compare the question information or the partial prompt with a template including a place, a location, a facility, or a region.

[0059] If it is determined in step S141 that a missing element exists (YES in step S141), the server device 2 determines whether the missing element is command information (step S142).

[0060] If the missing element is command information (YES in step S142), the server device 2 outputs error information (step S143). This is because if command information is not included in the question information, no answer will be obtained even if the question information is entered as a prompt into the LLM. The error information may include instruction information that instructs the user who entered the question to enter a more specific question. The error information is output to the display screen of the user terminal 1. When a question is entered into the user terminal 1, the processing from step S100 is executed again.

[0061] If the missing element is not command information (NO in step S142), the server device 2 determines whether the missing element is context information (step S144). If the missing element is context information (YES in step S144), the server device 2 acquires the missing context information from the history DB, the attribute information DB, and / or the behavior information DB (step S145), and generates a partial prompt related to the context information (step S146). The process of step S145 is a process of acquiring the predetermined information that is determined not to be included from the history DB that stores the predetermined information when it is determined that the input question does not include predetermined information.

[0062] The history DB stores information acquired by the system 10. The information acquired by the system 10 is, for example, a history of question information, partial prompts, prompts, and / or answers. The partial prompts stored in the history DB are, for example, partial prompts generated in steps S120, S146, S148, and / or S149. The prompts stored in the history DB are, for example, prompts generated in S160. The answers are, for example, answers acquired in steps S183 or S185, answers edited in step S193, answers supplemented in S220, and / or answers output in S260. The information in the history DB may be stored in association with the user who asked the question. In the history DB, the question information, partial prompts, prompts, and / or answers may be stored in association with each other.

[0063] For example, if partial prompts such as "I'm taking the 11 o'clock Shinkansen" and "Please tell me some recommended places in Tokyo" are generated from the question information, the question does not include the departure date and time of the Shinkansen, the station where the Shinkansen will be boarded, the user's current location, the purpose for which the user wants to receive a place recommendation, etc. Therefore, this information is identified as missing context information.

[0064] In step S145, if the missing element is location information related to the current location, the server device 2 acquires the location information of the user terminal 1. The location information of the user terminal 1 may be acquired using the GPS function of the user terminal 1. In this case, in step S146, a partial prompt related to the user's current location is generated.

[0065] The method of acquiring the context information in step S145 is not particularly limited. For example, the server device 2 may compare the information included in the history DB with the question information or the partial prompt, and acquire the context information included in the information with a high degree of similarity. The degree of similarity can be calculated, for example, using a vector operation described below. Alternatively, the server device 2 may determine whether the question information or the partial prompt includes a predetermined wording, and acquire the context information associated with the predetermined wording.

[0066] The process of step S146 is a process of generating a partial prompt based on the predetermined information acquired in step S145 and the question. In step S146, if there are multiple missing elements of the context information, a partial prompt is generated for the context information corresponding to each missing element.

[0067] If the missing element is context information (YES in step S144), a confirmation information output process may be executed to request the user terminal to input the context information (step S147). By the process of step S147, the server device 2 may generate a partial prompt related to the context information in step S146 based on the context information input by the user. By the process of step S146, a prompt can be generated in step S160 based on the acquired context information and the question.

[0068] After the process of step S146, or if it is determined in step S141 that there are no missing elements (NO in step S141), the server device 2 refers to the attribute information DB and generates a partial prompt related to the user attribute information (step S148).

[0069] User attribute information is information relating to the attributes of a user. In the system 10, user attribute information of users who use the system 10 is registered in advance in the attribute information DB of the server device 2. Examples of user attributes include gender, age, occupation, hobbies, preferences, health status, family structure, etc. User attribute information is information set for each user.

[0070] For example, in step S148, partial prompts such as "The questioner is a 30-year-old man" and "The questioner's hobby is visiting museums" may be generated.

[0071] After the process of step S148, the server device 2 refers to the behavior information DB and generates a partial prompt related to the behavior information (step S149).

[0072] The behavioral information is information relating to the behavioral history of a user acquired by the system 10. The behavioral information is stored in the behavioral information DB of the server device 2. For example, the behavioral information includes information such as question information entered by the user, user response information to answers or advertisement information, and user behavioral history information. The response information is, for example, information relating to whether or not the URL of the suggested information included in the answer was selected. The user behavioral history information is, for example, information relating to the user's Internet browsing history and search history. The behavioral information is information stored for each user.

[0073] For example, in step S149, partial prompts such as "The questioner was browsing the homepage of Art Museum A three days ago," or "When facilities α, β, and γ were suggested to the questioner, the URL of facility β was selected" may be generated.

[0074] The question complementing process is completed by the processes of steps S141 to S149. Note that the processes of steps S144 to S147, S148, and S149 may be executed in reverse order. The process of step S147 may be omitted.

[0075] Before the process of step S148, it may be determined whether or not the question information or the partial prompt includes user attribute information, and if the user attribute information is not included, the process of step S148 may be executed.Similarly, before the process of step S149, it may be determined whether or not the question information or the partial prompt includes behavioral information, and if the behavioral information is not included, the process of step S149 may be executed.

[0076] In step S141, the determination of whether or not a missing element exists may be performed for each missing element. For example, the server device 2 may first determine whether or not a missing element corresponding to command information exists in the question information or partial prompt, then determine whether or not a missing element corresponding to context information exists, and then determine whether or not a missing element corresponding to user location information exists. Furthermore, the determination of whether or not a missing element exists corresponding to context information may be performed according to the importance of the context information. For example, context information related to a purpose may be set to be more important than context information related to an emotion.

[0077] Note that partial prompts may not be generated for all of the context information determined to be insufficient in step S146. For example, partial prompts may be generated for context information with higher importance depending on the importance of the context information. The importance of the context information may be set in advance or may vary depending on the question.

[0078] The partial prompt generation process in steps S146, S148, and / or S149 may utilize a language model (e.g., the language model server 3). To generate the prompt in step S160, the server device 2 may cause the language model to extract predetermined features according to the user's history. To extract the predetermined features, the server device 2 may request an answer from the language model two or more times.

[0079] For example, if the question information or partial prompt does not include predetermined information (e.g., context information related to a facility or area) (YES in step S144), the server device 2 identifies facility information or area information proposed to a user who previously input a question from the history DB. Then, the server device 2 requests the language model to extract predetermined features from the identified facility information or area information. The server device 2 can generate a partial prompt based on the features extracted from the language model. The predetermined features are features identified according to the user, such as the user's preferred area or type of facility.

[0080] For example, to request the language model to extract features, the server device 2 may generate a prompt such as "In the past, you have suggested X Art Museum, Y Museum, and Z Archive Center to the questioner. In order to suggest a new facility to the questioner, please extract features of the facility that the questioner prefers," and input the generated prompt to the language model. Then, the server device 2 can use the answer obtained from the language model as a partial prompt.

[0081] In addition, the process of extracting predetermined features may be performed when, as a result of comparing the template with the question information or partial prompt in step S141, the question information or partial prompt does not contain a predetermined phrase, and when predetermined information corresponding to the phrase can be identified from the user's past history.

[0082] [Confirmation information output process] Next, the confirmation information output process of step S147 will be described below. Fig. 6 is a diagram showing a flowchart of the confirmation information output process according to the embodiment of the present invention.

[0083] First, the server device 2 generates confirmation information (step S11). The confirmation information is information for requesting the user to input context information corresponding to the missing element. The server device 2 transmits the confirmation information to the user terminal 1 (step S12). The user terminal 1 receives the confirmation information (step S13). The processing of steps S11 to S13 is processing for requesting the user terminal 1 to input information regarding the purpose, emotion, or situation or condition when it is determined that the input question does not include information regarding the purpose, emotion, or situation or condition as predetermined information.

[0084] In step S13, confirmation information is output at the user terminal 1. In response to the output confirmation information, the user inputs the context information intended by the user into the user terminal 1 (step S14).

[0085] For example, if the question information is "Please tell me recommended places in Tokyo," confirmation information may be output such as "Are you looking for recommended places in Tokyo for sightseeing purposes?" or "For what purpose are you looking for recommended places in Tokyo?" The user terminal 1 may display options that the user can select as confirmation information. The user can input context information by selecting an option.

[0086] The context information input in step S14 is transmitted from the user terminal 1 to the server device 2 (step S15) and received by the server device 2 (step S16). The context information received in step S16 is used to generate a partial prompt in step S146. In this way, the server device 2 obtains information related to the purpose or emotion, or the situation or condition, based on the input from the user terminal. The confirmation information output process is completed by the processing of steps S11 to S16.

[0087] [Answer acquisition process] Next, the answer acquisition process of step S180 will be described below. Fig. 7 is a diagram showing a flowchart of the answer acquisition process according to the embodiment of the present invention.

[0088] First, the server device 2 determines whether or not desired facility information is present in the prompt generated in step S160 (step S181).

[0089] The facility preference information is information requesting recommendations for facilities or regions. A facility is a place where one can stay for a specified amount of time, and may be an artificially created location such as a building or park, or a natural object such as a mountain or the sea. A facility may also be a concrete facility that actually exists. A region is a place with a specified area. A region may be, for example, a city, ward, town, village, prefecture, country, etc.

[0090] The process of step S181 will be described. For example, the server device 2 can determine whether facility preference information is present in the prompt by determining whether the prompt includes a predetermined phrase. The predetermined phrase is, for example, a recommendation phrase and a phrase related to a facility or an area. Examples of recommendation phrases include phrases such as "recommended," "recommended," and "looking for." Examples of phrases related to an area or facility include phrases corresponding to information about a facility, an area, or a location.

[0091] Furthermore, for example, the server device 2 can determine whether facility preference information is present in a prompt by determining the similarity between the prompt and a fixed phrase. Fixed phrases are stored in the server device 2. The fixed phrases are stored as prompts or partial prompts for recommending facilities or areas. Fixed phrases are, for example, fixed questions such as "I'm looking for XX" or "Where would you recommend?" The server device 2 can perform vector calculations on the stored fixed phrases and the prompt to calculate the similarity. If the similarity is equal to or greater than a predetermined value, the server device 2 can determine that facility preference information is present in the prompt. Alternatively, the server device 2 can compare the value obtained from the calculated vector calculation between the fixed phrase and the prompt, and if the value is within a predetermined range, determine that facility preference information is present in the prompt.

[0092] If the prompt to be input to the language model does not include facility preference information (NO in step S181), the server device 2 inputs the prompt to the language model (step S183). In step S183, the server device 2 transmits the prompt to the language model server 3. The language model server 3 inputs the prompt to the language model and outputs an answer. When the answer is transmitted from the language model server 3 to the server device 2, the server device 2 acquires the answer from the language model based on the prompt (step S183).

[0093] If the prompt to be input to the language model includes desired facility information (YES in step S181), the server device 2 inputs the prompt to the language model (step S184) and acquires a response (step S185). The processes of steps S184 and S185 are similar to those of steps S182 and S183. Furthermore, the server device 2 refers to the specialized information DB based on the desired facility information and acquires facility information or area information that is highly similar (step S191). The server device 2 generates facility suggestion information based on the facility information or area information acquired in step S191 (step S192). The processes of steps S191 and S192 are processes of acquiring or generating information about facilities or areas (also referred to as facility suggestion information) from the specialized information DB.

[0094] Here, the specialized information DB is a database that stores information about facilities or areas. The specialized information DB is stored in the storage unit 23 of the server device 2. The specialized information DB is set by operating the administrator terminal 4. The specialized information DB may be linked to a predetermined search engine and may update the information in the database every predetermined period (for example, once a week).

[0095] The facility suggestion information is information about a facility or area suggested to the user, and is information acquired or generated in the response acquisition process. The facility suggestion information includes, for example, facility information, area information, etc. The facility suggestion information may be predetermined information to which information about the facility or area is added.

[0096] Facility information is information about a facility. The facility information includes, for example, information about the facility name, facility location, facility classification, facility usage fee, facility opening hours, and facility features. Area information is information about an area. The area information includes, for example, the area name, area location, area tourist attractions, and facility information about facilities in the area.

[0097] The following describes the process of acquiring information with a high degree of similarity by the server device 2 in step S191. Information with a high degree of similarity to the prompt can be acquired using a known method.

[0098] For example, the server device 2 performs vector calculation on the prompt generated in step S160 to vectorize the prompt. Furthermore, the facility information or area information stored in the specialized information DB is vectorized by performing vector calculation. The server device 2 uses the vectorized prompt and the vectorized information in the specialized information DB to acquire information that provides a value similar to the value obtained from the vectorized prompt. In other words, if the values ​​obtained from the vectorized sentences are similar between text A and text B, text A and text B are determined to have a high degree of similarity. Information with a high degree of similarity may be information in which the vectorized values ​​are similar.

[0099] In the present embodiment, "approximate" means, for example, that the absolute value of the difference between the values ​​is equal to or less than a predetermined threshold (or less than the predetermined threshold). The predetermined threshold can be set as appropriate.

[0100] Here, the text B that approximates the value obtained by vectorization may be one in which the difference between the value obtained by vector operation on text A and the value obtained by vector operation on text B is equal to or less than a predetermined value, or it may be one in which the top three (not limited to three, any values ​​will do) of multiple texts B that are closest to the value obtained by vector operation on text A are identified.

[0101] Alternatively, the server device 2 may calculate the similarity between the vectorized prompt and the vectorized information in the specialized information database. The similarity may be, for example, a cosine similarity. If the calculated similarity for a given piece of information is greater than a predetermined threshold, the information can be determined to have a high similarity to the prompt.

[0102] The server device 2 can calculate a vector of a sentence from the question information, prompt, partial prompt, and / or answer input from the user terminal 1. For example, the small-scale language model provided in the server device 2 can convert a sentence into a numerical vector. Converting a sentence into a numerical vector is also called vectorization. The method for performing vector calculations on a sentence is not particularly limited, and other known techniques may be applied. For example, words may be extracted from a sentence by morphological analysis, and the meanings of the words and the relationships between the words may be vectorized.

[0103] After the process of step S192, the server device 2 edits the answer acquired from the language model based on the facility proposal information generated in step S192 (step S193). Editing the answer based on predetermined information is a concept that includes adding predetermined information to the answer, deleting part of the answer and replacing it with predetermined information, and generating a new sentence based on the answer and the predetermined information.

[0104] Note that the answer editing process in step S193 and in S230 (described later) may be performed by the server device 2, or may utilize a language model (e.g., the language model server 3). For example, when the answer is edited by the server device 2 in step S193, predetermined information may be added to the answer acquired from the language model server 3 in step S185, or a portion of the information included in the answer may be deleted and the predetermined information may be added. For example, when the answer is edited using a language model in step S193, the server device 2 may request the language model to create a sentence that includes the predetermined information, based on the answer acquired from the language model server 3 in step S185. The predetermined information may be the information acquired in step S191 or the information generated in step S192.

[0105] For example, in step S193, the server device 2 determines whether the answer includes location information. Location information is information related to a location, and includes facility information and / or area information. If the answer includes location information, the server device 2 deletes the location information from the answer. In addition, the server device 2 adds the facility proposal information generated in step S192 to the answer. This allows the server device 2 to edit the answer based on the generated facility proposal information.

[0106] The processes of steps S181, S191, S192, and S193 may be executed as follows. For example, the processes of steps S182 and S183 are executed before step S181 is executed. After the answer is acquired in step S183, the server device 2 determines whether the answer acquired from the language model includes facility information or area information (step S181'). If the answer includes facility information or area information, the server device 2 acquires information about the facility or area corresponding to the answer from the specialized information DB (step S191'). Next, the server device 2 generates facility suggestion information based on the acquired facility information or area information (step S192'). The server device 2 edits the answer acquired from the language model based on the information generated in step S192' (step S193').

[0107] The facility information or area information corresponding to the answer in step S191' may be facility information or area information that is highly similar to the answer. Facility information or area information that is highly similar to the answer can be acquired in the same manner as facility information or area information that is highly similar to the prompt. In this case, the server device 2 performs vector calculations on the answer.

[0108] Note that the processing of steps S192 and S192' may be omitted. In this case, the facility information or area information acquired in steps S191 and S191' becomes facility suggestion information. That is, in steps S193 and S193', the answer acquired from the language model can be edited based on the facility information or area information acquired in steps S191 and S191'.

[0109] [Answer determination process] Next, a description will be given of the answer determination process in step S. Fig. 8 is a diagram showing a flowchart of the answer determination process according to the embodiment of the present invention.

[0110] First, the server device 2 determines whether the answer acquired in step S183 or step S193 is appropriate (step S201). If the answer is appropriate (YES in step S201), the answer determination process ends. If the answer is inappropriate (NO in step S201), answer error information is generated (step S202) and output (step S203). The answer error information output in step S203 is transmitted to and output from the user terminal 1. The answer determination process ends with the processing of steps S201 to S203.

[0111] The answer error information is information indicating that the answer acquired from the language model is not appropriate as an answer to the prompt or the question corresponding to the prompt. For example, as the answer error information, the user terminal 1 outputs information such as "We were unable to obtain the information you were looking for. Please enter your question again." When a question is entered into the user terminal 1, the process is executed again from step S100.

[0112] In step S201, the server device 2 determines whether the answer obtained by inputting the prompt into the language model is appropriate as an answer to the question corresponding to the prompt by referring to an answer definition DB in which prompt examples and answer examples corresponding to the prompt examples are stored.

[0113] The answer definition DB is stored in the storage unit 23. The answer definition DB may store, for example, example prompts and information required as answer examples for the prompts in association with each other, or may store example prompts and answer examples for the prompts in association with each other.

[0114] For example, in the answer definition DB, information about a facility or area is stored as required information in association with an example prompt that includes facility preference information, as an example answer to the example prompt. The server device 2 can refer to the answer definition DB and, when an answer to a prompt that includes facility preference information includes information about a facility or area, determine that the answer is appropriate as an answer to the question corresponding to the prompt.

[0115] Alternatively, the server device 2 may identify an example prompt that is highly similar to the prompt, and determine whether the answer is appropriate based on the similarity between the example answer corresponding to the example prompt and the output answer. For example, the server device 2 may determine that an answer is appropriate as an answer to the question corresponding to the example prompt if a value obtained by vector operation of an example answer corresponding to the example prompt is approximate to a value obtained by vector operation of the answer.

[0116] In this case, the server device 2 performs vector operations on the prompt and the answer acquired by inputting the prompt into the language model.

[0117] In addition, the determination of whether the value obtained by vector-operating an answer example corresponding to a prompt example that gives a value that is approximated by vector-operation to the value obtained by vector-operating the prompt is approximate to the value obtained by vector-operating the answer can be made not only by determining whether the value obtained by vector-operating an answer example corresponding to a prompt example that gives a value that is approximated by vector-operation to the value obtained by vector-operating the prompt is approximate to the value obtained by vector-operating the answer, but also by determining whether the value obtained by vector-operating a prompt example corresponding to an answer example that gives a value that is approximated by vector-operation to the value obtained by vector-operating the answer is approximate to the value obtained by vector-operating the prompt.

[0118] [Answer completion processing] Next, the answer complementing process in step S220 will be described below with reference to Fig. 9, which is a flowchart of the answer complementing process according to the embodiment of the present invention.

[0119] First, the server device 2 determines whether the answer acquired in step S183 or the answer edited in step S193 includes location information (step S221). If the answer includes location information (YES in step S221), the server device 2 calculates the staying time for each location based on the location information (step S222).

[0120] The staying time is an approximate length of time that a user stays in a predetermined location such as a facility or an area. The staying time may be included in the facility information or area information stored in the specialized information DB. The server device 2 determines the staying time by acquiring facility information or area information corresponding to the facility or area corresponding to the location information included in the response from the specialized information DB. Alternatively, if the staying time is not included in the facility information or area information, the server device 2 may calculate a predetermined time (e.g., 30 minutes) as the staying time.

[0121] Next, the server device 2 calculates the travel time based on the location information (step S223).

[0122] The travel time is an estimated time required to travel from one predetermined location to another. In this embodiment, the travel time may be an estimated time required to travel from a departure point to an arrival point via a location corresponding to the location information. The server device 2 stores a traffic information DB for calculating the travel time. The traffic information DB includes map information, information on public transportation timetables, road congestion status, delay information, past congestion status, etc. The traffic information DB may be updated with real-time status.

[0123] Next, the server device 2 calculates the consumed time based on the stay time calculated in step S222 and the travel time calculated in step S223 (step S224). The consumed time is the sum of the stay time and the travel time.

[0124] Once the consumed time is calculated, the server device 2 generates travel proposal information (step S225). The travel proposal information is information in which the stay time, travel time, and / or consumed time are added to the location information included in the response. The travel proposal information may include information on the means of transportation, transfers, and / or congestion status. The travel proposal information is output to the user terminal 1 as a response. The travel proposal information is included in the response.

[0125] Next, the server device 2 determines whether the question input in step S100 includes disposable time (step S226). Disposable time is the time during which a user can take action. For example, in the case of a question such as "Please tell me where I can kill time between 10:00 and 16:00," the disposable time is six hours from 10:00 to 16:00.

[0126] If the question input in step S100 includes disposable time (YES in step S226), the server device 2 extracts travel suggestion information that satisfies a predetermined condition (step S227). The predetermined condition is, for example, that the consumption time calculated in step S224 is shorter than the disposable time included in the question.

[0127] The processing of steps S221 to S227 is performed in the same way when the answer includes one piece of location information and when the answer includes two or more pieces of location information. For example, when the answer includes three pieces of location information, facility α, facility β, and facility γ, the processing of steps S221 to S227 is performed as follows. First, the server device 2 calculates the stay time at facility α, facility β, or facility γ to be 0.5 hours, 1 hour, and 2 hours, respectively. Next, the travel time from the departure point to the arrival point via facility α, facility β, or facility γ to be 2 hours, 1 hour, and 1 hour, respectively. Then, the server device 2 calculates the spent time at facility α, facility β, or facility γ to be 2.5 hours, 2 hours, and 3 hours, respectively.

[0128] If the disposable time included in the question is two hours, then in step S227, the server device 2 extracts facilities α and β as travel suggestion information.

[0129] The stay time, travel time, and consumption time may be calculated for one location or for multiple locations. For example, if the response includes location information for three locations, facility α, facility β, and facility γ, the server device 2 may identify facility α, facility β, and facility γ in order of proximity from the departure point. Alternatively, the server device 2 may identify two facilities from facility α, facility β, and facility γ and identify the order of proximity from the departure point. Next, the server device 2 may calculate the travel time from the departure point to the arrival point according to the identified order. The server device 2 can calculate the consumption time for each by adding the travel time and the stay time.

[0130] Returning to the description of the flowchart, if the answer does not include location information (NO in step S221), if the question entered in step S100 does not include disposable time (NO in step S226), or after extracting the travel suggestion information in step S227, the server device 2 determines whether or not the answer includes action information (step S228). If the answer includes action information (YES in step S228), the server device 2 references the action suggestion information associated with the action information and generates action suggestion information corresponding to the answer (step S229).

[0131] The action information is information that triggers the generation of action suggestion information that suggests an action to be taken by the user. The server device 2 stores the action information and the action suggestion information in association with each other. For example, the action suggestion information that suggests the user to register a schedule may be stored in association with the action information that is time and location information, or the action suggestion information that provides a URL of a site where detailed information about the facility or area can be viewed may be stored in association with the action information that is facility information or area information. The action information is, for example, a predetermined character string, a predetermined sentence, and / or a predetermined sentence type. The action information may also be set in association with the facility information or area information. For example, action information that indicates that a facility corresponding to the facility information is a facility that requires a reservation can be associated with the facility information in advance.

[0132] In addition, the presence of action information in the answer includes both cases where action information is present in the text included in the answer, and cases where action information is associated with facility information or area information included in the answer or travel suggestion information.

[0133] The determination of whether or not action information is present in the answer in step S228 can be performed as follows. For example, the server device 2 may determine that the action information is present if a word corresponding to the action information is present in the answer. Alternatively, the server device 2 may determine that the action information is present in the answer if the answer and the action information are similar. The determination of similarity can be made based on the value obtained by performing the above-mentioned vector calculation.

[0134] If the answer does not include action information (NO in step S228), or after generating the action suggestion information in step S229, the server device 2 edits the answer based on the movement suggestion information and / or action suggestion information (step S230). The answer complementation process ends with the processes in steps S221 to S230.

[0135] Note that editing the answer based on predetermined information has the same meaning as that explained in step S193. For example, in step S230, the server device 2 may add movement suggestion information for a location included in the answer so as to correspond to the location information. Also, for example, in step S230, the server device 2 may add action suggestion information generated from action information to the answer, in association with a sentence including the action information.

[0136] In step S229, the server device 2 may store the sentence as the action suggestion information, and the server device 2 may acquire the action suggestion information corresponding to the action information instead of generating the action suggestion information.

[0137] The order of the processes in steps S222 and S223 may be reversed. If the determination in both steps S221 and S228 is NO, the process in step S230 may be omitted.

[0138] [Advertisement specific processing] Next, the advertisement identification process in step S240 will be described below with reference to Fig. 10, which is a flowchart showing the advertisement identification process according to the embodiment of the present invention.

[0139] First, the server device 2 acquires, from the advertisement information DB, advertisement information similar to the answer acquired by inputting the prompt into the language model (step S241). In step S241, a plurality of advertisement information may be acquired. Next, the server device 2 selects, from the acquired plurality of advertisement information, one or more advertisement information similar to the prompt or the question input from the user terminal to generate the prompt (step S242). The advertisement information selected in step S242 is output together with the answer information in step S260. The system 10 may output an advertisement corresponding to the advertisement information acquired from the advertisement information DB as is, or may output an advertisement obtained by editing the advertisement information.

[0140] Here, the advertising information DB is a database that stores advertising information related to advertisements. The advertising information includes, for example, facility information and area information. The advertising information may be registered by operating the administrator terminal 4 or by operating a terminal operated by the advertising client. A usage fee may be charged to the advertising client in response to registering the advertising information in the advertising information DB. The advertising information DB stores information such as customer targets, advertiser information, product names, types, and features, and advertising copy for each advertisement. The information in the advertising information DB may be subjected to vector calculations in advance based on information included in the advertisement, such as customer targets, advertiser information, product names, types, and features, and advertising copy. Alternatively, the information included in the advertising information DB may be subjected to vector calculations each time based on information such as the advertisement text and images.

[0141] The processing of steps S241 and S242 will be described. In step S241, the server device 2 can acquire advertising information similar to the answer using a known method. In step S242, the server device 2 can select advertising information similar to the prompt or question using a known method. In steps S241 and S242, advertising information being similar to the answer, prompt, or question means that the advertising information is highly similar to the answer, prompt, or question. The answer used in step S141 may be the answer acquired in step S180 or the answer supplemented in step S220, and the prompt or question used in step S142 may be the prompt generated in step S160, a partial prompt, or question information input in step S100.

[0142] For example, steps S241 and S242 can use the same technique as step S191. The server device 2 performs vector calculations on the prompt generated in step S160, the partial prompt generated, or the question and answer entered in step S100, to vectorize the prompt, the partial prompt, or the question and answer. The advertisement information stored in the advertisement information DB has also been vectorized by performing vector calculations. In step S241, the server device 2 uses the vectorized answer and the vectorized advertisement information in the advertisement information DB to obtain advertisement information that provides a value approximate to the value obtained from the vectorized answer.

[0143] Then, in step S242, the server device 2 uses the vectorized prompt, vectorized partial prompt, or question and the vectorized advertising information acquired in step S241 to extract advertising information from which a value similar to that obtained from the vectorized prompt, partial prompt, or question can be obtained. Note that the generated prompt or the generated partial prompt is included in information related to the input question. The extraction method is not particularly limited, and for example, the server device 2 may extract advertising information from which a value similar to that obtained from the vectorized prompt, partial prompt, or question can be obtained, or may rank the advertising information from which a value similar to that obtained from the vectorized prompt, partial prompt, or question can be obtained, and a predetermined number (e.g., three) of the top advertising information may be extracted.

[0144] Alternatively, the server device 2 may calculate the similarity using the vectorized answer, prompt, partial prompt, or question and the vectorized advertisement information in the advertisement information DB. In step S241, advertisement information whose calculated similarity is greater than a predetermined threshold is acquired, and in step S242, a predetermined number of advertisement information items are extracted in descending order of similarity.

[0145] Steps S241 and S242 may be executed as follows. For example, in step S241, the server device 2 may acquire, from the advertisement information DB, advertisement information similar to a prompt to be input into the language model or a question input from the user terminal to generate the prompt. In addition, in step S242, the server device 2 may select, from the acquired plurality of pieces of advertisement information, one or more pieces of advertisement information similar to an answer acquired by inputting the prompt into the language model.

[0146] In the above advertisement identification process, multiple pieces of advertising information similar to the answer obtained by inputting a prompt into a language model are selected, and then advertising information similar to a prompt to be input into the language model or a question input from a user terminal to generate a prompt is selected, or multiple pieces of advertising information similar to a prompt to be input into a language model or a question input from a user terminal to generate a prompt are selected, and then advertising information similar to the answer obtained by inputting the prompt into a language model is selected, but one or more pieces of advertising information similar to the answer may be obtained and used as an advertisement, or one or more pieces of advertising information similar to the prompt or the question may be obtained and used as an advertisement. In other words, the process of step S242 may be omitted.

[0147] Note that, as long as the output process includes steps S100, S160, and S260, other steps may be omitted as appropriate. For example, the processes of steps S120, S140, S200, S220, and / or S240 may be omitted. If the process of step S120 is omitted, the server device 2 executes the processes of step S140 and subsequent steps for the question information received in step S100.

[0148] In the above, the information on which vector operations are performed to calculate similarity with various information may be stored in association with the values ​​on which the vector operations were performed in advance in various databases in which the information is stored (e.g., prompt definition database, history database, attribute information database, behavioral information database, specialized information database, answer definition database, advertising information database, etc.).

[0149] In this way, the system includes a determination unit that determines whether a question input from a user terminal contains predetermined information necessary as a prompt for input to a language model, and a first generation unit that, when it is determined that the input question does not contain the predetermined information, adds the predetermined information to the question and generates a prompt for input to the language model. Therefore, even if the question does not contain the predetermined information, a prompt with the predetermined information added can be generated. Furthermore, adding the predetermined information increases the amount of information in the prompt. Therefore, when the prompt is input to the LLM, a more appropriate answer is output as an answer to the question.

[0150] Furthermore, in this way, the input question requests a recommended action, the specified information is a purpose to be achieved or an emotion to be obtained by performing the recommended action, or information regarding the situation or conditions when performing the recommended action, and the system comprises a request means that, when the determination means determines that the input question does not include the purpose or the emotion, or information regarding the situation or the conditions, as the specified information, requests the user terminal to input the purpose or the emotion, or information regarding the situation or the conditions, and the first generation means generates a prompt to be input into the language model based on the purpose or the emotion, or information regarding the situation or the conditions obtained by input from the user terminal, and the question, thereby making it possible to generate a prompt that is in line with the user's intention.

[0151] Furthermore, by providing the system with an acquisition means for acquiring advertising information similar to an answer acquired by inputting a prompt into a language model from a database in which advertising information related to advertisements is stored, or an acquisition means for acquiring advertising information similar to a prompt to be input into the language model or a question input from a user terminal to generate a prompt from a database in which advertising information related to advertisements is stored, advertising information more suitable for the user who input the question can be identified. Furthermore, by providing the acquisition means for acquiring a plurality of pieces of advertising information, and the system with a selection means for selecting, from the acquired plurality of pieces of advertising information, one or more pieces of advertising information similar to the answer acquired by inputting the prompt into the language model, or a selection means for selecting, from the acquired plurality of pieces of advertising information, one or more pieces of advertising information similar to the prompt or the question input from the user terminal to generate a prompt, advertising information more suitable for the user who input the question can be identified.

[0152] Furthermore, by providing the system with an answer acquisition means for acquiring an answer from a language model based on a prompt, an acquisition means for acquiring or generating information about a facility or area from a database storing information about the facility or area when the prompt to be input to the language model includes facility preference information requesting a recommendation of a facility or area, and an answer editing means for editing the answer acquired from the language model based on the information acquired or generated by the acquisition means, it is possible to suggest information about actually existing facilities or areas while using the language model. Similarly, by providing the system with an answer acquisition means for acquiring an answer from a language model based on a prompt, and an acquisition means for acquiring or generating information about a facility or area corresponding to the answer from a database storing information about the facility or area when the answer acquired from the language model includes facility information about the facility or area, and an answer editing means for editing the answer acquired from the language model based on the information acquired or generated by the acquisition means, it is possible to suggest information about actually existing facilities or areas while using the language model.

[0153] In this way, the system is equipped with an answer acquisition means that acquires an answer from a language model based on a prompt, a proposal generation means that generates proposal information corresponding to the answer when the answer acquired from the language model includes action information to encourage the user to take action, and an answer editing means that edits the answer acquired from the language model based on the proposal information generated by the proposal generation means, thereby making it possible to make suggestions related to the answer to the user.

[0154] Furthermore, in this way, the system is equipped with a determination means for determining whether an answer obtained by inputting a prompt into a language model based on an example prompt and an example answer corresponding to the example prompt is appropriate as an answer to a question corresponding to the prompt, thereby making it possible to provide the user with an appropriate answer as an answer to a question.

[0155] 1 User terminal 2 Server device 3 Language model server 4 Administrator terminal 5 Communication network 10 System 11 control unit 12 RAM 13 storage unit 14 input unit 15 Display unit 16 Communication interface 21 control unit 22 RAM 23 storage unit 24 communication interface

Claims

1. 1. A system comprising at least one computer device, An acquisition means for acquiring advertising information similar to the answer acquired by inputting the prompt into the language model from a database in which advertising information related to the advertisement is stored. A system comprising:

2. The acquisition means acquires a plurality of pieces of advertising information, A selection means for selecting, from the acquired plurality of pieces of advertising information, one or more pieces of advertising information that are similar to a prompt or a question input from the user terminal for generating a prompt. The system of claim 1 , comprising:

3. A calculation execution means for executing a vector calculation on an answer obtained by inputting a prompt into a language model. Equipped with The system according to claim 1 or 2, wherein the acquisition means acquires advertising information in which a value obtained by performing a vector operation on the advertising information is close to a value obtained by performing a vector operation on the response.

4. 1. A system comprising at least one computer device, An acquisition means for acquiring, from a database in which advertisement information relating to advertisements is stored, advertisement information similar to a prompt to be input to the language model or a question input from a user terminal to generate a prompt. A system comprising:

5. The acquisition means acquires a plurality of pieces of advertising information, a selection means for selecting, from the plurality of pieces of acquired advertising information, one or more pieces of advertising information that are similar to the answer acquired by inputting the prompt into a language model; The system of claim 4 , comprising:

6. A calculation execution means for executing a vector calculation on a question input from a user terminal or information relating to the question in order to generate a prompt. Equipped with The system described in claim 4 or 5, wherein the acquisition means acquires advertising information such that a value obtained by performing a vector operation on the advertising information is close to a value obtained by vector operation from the question or information relating to the question.

7. 1. A method executed on at least one computer device, comprising: an acquisition step of acquiring, from a database in which advertising information relating to advertisements is stored, advertising information similar to the answer acquired by inputting the prompt into the language model; A method comprising:

8. 1. A method executed on at least one computer device, comprising: an acquisition step of acquiring, from a database in which advertisement information relating to advertisements is stored, advertisement information similar to a prompt to be input into the language model or a question input from the user terminal to generate the prompt; A method comprising:

9. An acquisition means for acquiring, from a database storing advertising information relating to advertisements, a plurality of pieces of advertising information similar to the answer acquired by inputting a prompt into a language model. A computer device comprising:

10. An acquisition means for acquiring, from a database in which advertisement information relating to advertisements is stored, a plurality of pieces of advertisement information similar to a prompt to be input to a language model or a question input from a user terminal to generate a prompt. A computer device comprising:

Images