Systems, Computer Devices and Methods

Abstract

A system for reducing the number of times a language model outputs an answer is provided. [Solution] A system including at least one computer device. The system includes a first acquisition means for acquiring an answer from a language model based on a prompt, a storage means for storing the answer acquired by the first acquisition means in association with information on the prompt corresponding to the answer, a first generation means for generating or acquiring a prompt to be input to the language model or a provisional prompt for generating the prompt, and an identification means for identifying an answer corresponding to the information on the prompt from the storage means when the prompt or provisional prompt generated or acquired by the first generation means and information on the prompt that satisfies a predetermined condition are stored.

Description

[Technical field]

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

[0002] In recent years, the accuracy of generative AI capable of autonomously generating text and images has improved, and it is expected to be used in various fields. For example, a system has been provided that uses large-scale language models (LLMs) to perform natural language processing tasks such as question and answer, text summarization, and text generation (for example, Patent Document 1). An LLM is a natural language processing model trained using a large amount of text data. When using an LLM to perform a task such as question and answer, text is input into the LLM, and an answer is output from the LLM. The text input into the LLM is called a prompt.

[0003] However, it is difficult for users who are not familiar with language models to input prompts by themselves. Also, depending on the content of the prompt input to the language model, the language model may output an answer different from the answer the user wants. For this reason, inputting prompts requires skills that are dependent on the individual, and it is difficult for users who are not familiar with language models to use them. [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. A first problem of the present invention is to provide a system that can obtain an answer with a simple input by a user. A second problem of the present invention is to provide a system for reducing the number of times a language model outputs an answer. [Means for solving the problem]

[0006] The object of the present invention is to [1] A system including at least one computer device, the system including: a selection means for accepting selection of one or more options from a plurality of options corresponding to a plurality of keywords in response to an input from a user terminal operated by a user; and a first generation means for generating a prompt to be input into a language model so as to include a keyword corresponding to the option selected and accepted by the selection means, or for generating a provisional prompt for generating the prompt; [2] The system according to [1], further comprising: a prompt display unit configured to control the user terminal to display the prompt or the provisional prompt generated by the first generation unit; [3] The system according to [1] or [2], further comprising an option display means for controlling the user terminal to display options, a selection means for accepting a selection of one or more options from the options controlled to be displayed by the option display means, and when one option is selected from the multiple options by the selection means, the option display means controls to further display options corresponding to a keyword associated with the selected one option; [4] The system according to [3], wherein a keyword associated with a first option and a keyword associated with a second option among the displayed options are different; [5] The system according to any one of [2] to [4] above, wherein the prompt display means controls so as to display a keyword corresponding to an option selected by the selection means in a manner different from other text included in the generated prompt or provisional prompt; [6] The system according to any one of [1] to [5], further comprising an input means for accepting input of text information in response to an input from the user terminal, and a first generation means for generating the prompt or the provisional prompt based on a keyword corresponding to an option selected by a selection means and the text information input by the input means; [7] The system according to any one of [1] to [6], wherein the first generating means generates the prompt or the provisional prompt by embedding a keyword corresponding to the option selected by the selecting means into a preset template; [8] The system according to any one of [1] to [7], further comprising an answer acquisition means for acquiring an answer from a language model based on the prompt generated by the first generation means or a prompt generated from a provisional prompt; [9] The system according to any one of [1] to [7], further comprising: an information acquisition means for acquiring, in a language model, related information from a specialized information database in which predetermined information is stored, based on the prompt generated by the first generation means or a prompt generated from a provisional prompt; and an answer acquisition means for acquiring an answer from the language model using the information acquired by the information acquisition means and the prompt;

[10] The system according to any one of [1] to [7], further comprising: an information acquisition means for acquiring related information from a specialized information database in which predetermined information is stored, based on the generated provisional prompt or a keyword corresponding to an option whose selection has been accepted; a second generation means for generating a prompt, based on the information acquired by the information acquisition means and the provisional prompt or the keyword; and an answer acquisition means for acquiring an answer from a language model, based on the prompt generated by the second generation means;

[11] The system according to [9] or

[10] , further comprising an extraction means for extracting predetermined keywords by referring to a specialized information database using the language model, and a selection means for accepting a selection of an option from options corresponding to the keyword extracted by the extraction means;

[12] The system according to any one of [1] to

[11] , further comprising, in the user terminal, an option display means for controlling the display of options, wherein a selection means accepts a selection of one or more options from the options controlled to be displayed by the option display means, and the option display means controls to display at least two or more options in a list, and controls to change and display an area displaying each of the options according to information on the number of times the option has been selected by the selection means;

[13] A computer device comprising: a selection means for accepting selection of one or more options from a plurality of options corresponding to each of a plurality of keywords in response to an input from a user terminal operated by a user; and a first generation means for generating a prompt to be input into a language model so as to include a keyword corresponding to the option selected by the selection means, or for generating a provisional prompt for generating the prompt;

[14] A method executed on at least one computer device, the method comprising: a selection step of accepting selection of one or more options from a plurality of options corresponding to a plurality of keywords in response to an input from a user terminal operated by a user; and a first generation step of generating a prompt to be input into a language model, the prompt including a keyword corresponding to the option selected in the selection step, or generating a provisional prompt for generating the prompt;

[15] A system having at least one computer device, comprising: a first acquisition means for acquiring an answer from a language model based on a prompt; a storage means for storing the answer acquired by the first acquisition means in association with information on the prompt corresponding to the answer; a first generation means for generating or acquiring a prompt to be input to the language model or a provisional prompt for generating the prompt; and an identification means for identifying an answer corresponding to the information on the prompt from the storage means when the prompt or provisional prompt generated or acquired by the first generation means and information on a prompt that satisfies a predetermined condition are stored;

[16] The system according to

[15] , further comprising: a second acquisition means for acquiring an answer from a language model based on a prompt generated from the prompt or provisional prompt generated or acquired by the first generation means when information relating to the prompt that satisfies a predetermined condition is not stored;

[17] The system according to

[16] , further comprising a second generating means for generating a prompt by adding predetermined information to the provisional prompt, wherein the second acquiring means acquires answers from a language model based on the prompt generated by the second generating means, and the storage means stores at least a part of the answers acquired by the second acquiring means in association with information on the prompt corresponding to at least a part of the answers;

[18] The system according to any one of

[15] to

[17] above, further comprising: an information acquisition means for acquiring related information from a specialized information database in which predetermined information is stored based on a prompt; a first acquisition means for acquiring an answer from a language model using the related information and the prompt; an information update means for adding, replacing, and / or deleting predetermined information from the specialized information database; and a deletion means for deleting information relating to the answer and / or the prompt corresponding to the answer stored in the storage means in response to the addition, replacement, and / or deletion of the predetermined information by the information update means;

[19] A computer device comprising: a first acquisition means for acquiring an answer from a language model based on a prompt; a storage means for storing the answer acquired by the first acquisition means in association with information related to the prompt corresponding to the answer; a first generation means for generating or acquiring a prompt to be input to the language model or a provisional prompt for generating the prompt; and an identification means for identifying an answer corresponding to the information related to the prompt when the prompt or provisional prompt generated or acquired by the first generation means and information related to a prompt that satisfies a predetermined condition are stored in the storage means;

[20] A method executed on at least one computer device, the method comprising: a first acquisition step of acquiring an answer from a language model based on a prompt; a storage step of associating and storing the answer acquired in the first acquisition step with information on the prompt corresponding to the answer; a first generation step of generating or acquiring a prompt to be input to the language model or a provisional prompt for generating the prompt; and, when the prompt or provisional prompt generated or acquired by the first generation means and information on a prompt satisfying a predetermined condition are stored in the storage step, a specification step of specifying an answer corresponding to the information on the prompt; This can be solved by: Effect of the Invention

[0007] According to the present invention, it is possible to provide a system that can obtain an answer with a simple input by a user. According to the present invention, it is possible to provide a system for reducing the number of times that a language model outputs an answer. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a configuration of a system according to an embodiment of the present invention; [Diagram 2] 2 is a block diagram showing a hardware configuration of a user terminal according to an embodiment of the present invention; FIG. [Diagram 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. 11 is a flowchart showing a specialized information update process according to an embodiment of the present invention. [Diagram 5] FIG. 11 is a flowchart showing a keyword setting process according to the embodiment of the present invention. [Figure 6] FIG. 11 is a flowchart showing an output process according to the embodiment of the present invention. [Figure 7] FIG. 11 is a flowchart showing a response acquisition process according to an embodiment of the present invention. [Figure 8] FIG. 11 is a flowchart illustrating another example of the answer acquisition process according to the embodiment of the present invention. [Figure 9] FIG. 4 is a diagram showing an example of a display screen according to the embodiment of the present invention. [Figure 10] FIG. 4 is a diagram showing an example of a display screen according to the embodiment of the present invention. [Figure 11] FIG. 4 is a diagram showing an example of a display screen according to the embodiment of the present invention. [Figure 12] FIG. 4 is a diagram showing an example of a display screen according to the embodiment of the present invention. [Figure 13] FIG. 4 is a diagram showing an example of a display screen according to the embodiment of the present invention. [Figure 14] FIG. 11 is a flowchart showing a display order change process according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The following describes an embodiment of the present invention, but the present invention is not limited to the following embodiment, as long as it does not go against the spirit of the present invention. The order of each process constituting the flowchart described below is random as long as there is no contradiction or inconsistency in the process content, and it is also possible to omit a part of each process constituting the flowchart or add a new process to each process constituting the flowchart, as long as there is no contradiction or inconsistency in the process content. In addition, the device that executes each process constituting the flowchart can be changed to another device, as long as it does not go against the spirit of the present invention. In that case, the process content can be changed so that there is no contradiction or inconsistency in the process content.

[0010] The system according to the present invention can assist in searches to obtain answers regarding specific information. The specific information is not particularly limited, and the system according to the present invention can be applied in various fields. The following mainly describes the application of the system according to the present invention in the field of nursing care insurance.

[0011] [System configuration] FIG. 1 is a block diagram showing a configuration of a 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 include a language model server 3, a specialized information database 4, and an administrator terminal 5. The user terminal 1, the server device 2, the language model server 3, the specialized information database 4, and the administrator terminal 5 are communicably connected to each other via a communication network 6. In the system 10, any of the user terminal 1, the server device 2, and the language model server 3 can function as an information processing device. When any of the devices functions as an information processing device, information is transmitted and received between the user terminal 1, the server device 2, the language model server 3, and the specialized information database 4 as necessary.

[0012] The system 10 may include a plurality of user terminals 1, a plurality of server devices 2, a plurality of specialized information databases 4, and a plurality of administrator terminals 5. The server device 2 may function in a distributed manner across a plurality of computer devices. For example, instead of the server device 2, a distributed ledger technology such as a blockchain may be used.

[0013] [User device] The user terminal 1 is operated by a user of 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 notebook computer, and a desktop computer.

[0014] 2 is a block diagram showing a 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, which are all connected to each other via a bus.

[0015] 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 storage 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 the data inputted by the input unit 14.

[0016] 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 communication interface 16 can be connected to the communication network 6 wirelessly or via a wire, and can transmit and receive data to and from other computer devices via the communication network 6. Data received via the communication interface 16 is loaded into the RAM 12, and the control unit 11 performs arithmetic processing.

[0017] [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 a bus.

[0018] 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 a work area for the control unit 21. The storage unit 23 is a storage 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 or the language model server 3, etc.

[0019] [Language model server] The language model server 3 is a computer device in which a language model for processing natural language is stored. The hardware configuration of the language model server 3 may 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 be used as long as it can process natural language.

[0020] The server device 2 may store a language model. When a language model is stored in the server device 2, the system 10 may not include the language model server 3. Also, a small-scale language model smaller in scale than an LLM may be stored in the server device 2 or the language model server 3. The small-scale language model is a natural language processing model trained based on less data than an LLM.

[0021] [Specialized information database] The specialized information database 4 is a database in which predetermined information is stored. In this embodiment, the predetermined information stored in the specialized information database 4 is also referred to as specialized information. The specialized information database 4 is stored in a computer device. The specialized information database 4 may be stored in the server device 2 or in the language model server 3. The specialized information database 4 may be stored in a distributed manner in a plurality of computer devices. The specialized information database 4 may be constructed as a different database for each attribute of the predetermined information.

[0022] [Administrator terminal] The administrator terminal 5 is operated by an administrator who manages the system 10. The administrator terminal 5 is not particularly limited, but examples thereof include conventional mobile phones, tablet terminals, smartphones, notebook computers, and desktop computers. The hardware configuration of the administrator terminal 5 may be appropriately adapted from the description of the hardware configuration of the user terminal 1.

[0023] In this embodiment, the program may be stored in a recording medium such as a CD-ROM. In this case, the program stored in the recording medium may be installed in the user terminal 1, the server device 2, or the language model server 3 to execute a predetermined function. Alternatively, the program may be distributed from a computer device outside the system. In this case, the program distributed from a computer device outside the system may be installed in the user terminal 1, the server device 2, or the language model server 3 to execute a predetermined function.

[0024] [Professional information update processing] Next, a specialized information update process for storing specialized information in the specialized information database 4 will be described.

[0025] The specialized information stored in the specialized information database 4 is not particularly limited, but is preferably information related to the field in which the system 10 is used. For example, in the field of long-term care insurance, the specialized information may be information issued by the Ministry of Health, Labor and Welfare. The specialized information database 4 may be set for each department that uses the system 10. For example, information related to departments such as the general affairs department, human resources department, and accounting department may be stored in the specialized information database 4.

[0026] The specialized information stored in the specialized information database 4 is, for example, text information, image information, video information, sound information, etc. The specialized information stored in the specialized information database 4 may be stored in association with vectorized numerical information obtained by performing vector calculation. The specialized information database 4 may be a vector database.

[0027] Registration of specialized information in the specialized information database 4 may be performed in response to an operation on the administrator terminal 5. Fig. 4 is a diagram showing a flowchart of specialized information update processing according to the embodiment of the present invention.

[0028] First, the administrator accesses the server device 2 from the administrator terminal 5 via a web browser, thereby logging in to the system 10. Alternatively, the administrator may start an application program (hereinafter, referred to as a dedicated application) downloaded to the administrator terminal 5, and access the server device 2, thereby logging in to the system 10.

[0029] When a user of the system 10 logs in to the system, the user may be required to input a user ID, a password, and the like. The password may be set by the user. The password is stored in the system in association with the user ID. The user ID is identification information capable of identifying a user.

[0030] Next, the administrator terminal 5 accepts input of instruction information by an operation of the administrator (step S11). The instruction information is information for storing specialized information in the specialized information database 4. The instruction information includes specialized information and information on whether to add the specialized information to the specialized information database 4, replace the specialized information with specialized information already stored, or delete the specialized information from the specialized information database 4. The instruction information may also include information on the file name of the information, a comment when the information is displayed on the user terminal 1, and the like.

[0031] Next, the administrator terminal 5 transmits an update request to the server device 2 to request that the specialized information database 4 be updated (step S12). The update request includes instruction information. When the server device 2 receives the update request (step S13), it updates the specialized information in the specialized information database 4 (step S14). If the specialized information database 4 is stored in the server device 2, step S14 is executed in the server device 2. If the specialized information database 4 is stored in a computer device other than the server device 2, the server device 2 transmits the update request received in step S13 to the computer device in which the specialized information database 4 is stored. The processing of step S14 is executed in that computer device.

[0032] Here, updating of specialized information refers to a process of adding, replacing, and / or deleting predetermined information (specialized information) to the specialized information database. The specialized information may be stored in the specialized information database 4 in association with the file name of the information, a comment when the information is displayed on the user terminal 1, and the like. Information on the fact that the addition, replacement, and / or deletion of predetermined information has been performed in the specialized information database 4 may be stored in association with information on the execution date and time, the administrator who instructed the execution, the file name, the comment, and the like. The execution date and time may be any of the time when the instruction information is received in step S11, the time when the update request is sent in step S12, the time when the update request is received in step S13, and the time when the specialized information is updated in step S14.

[0033] After executing step S14, the server device 2 deletes the history information in response to the addition, replacement, and / or deletion of the specialized information in step S14 (step S15). The specialized information update process is completed by the above processes of steps S11 to S15.

[0034] The history information stores an answer acquired from a language model in association with information on a prompt corresponding to the answer. In this embodiment, the system 10 can acquire an answer from a language model based on a prompt. "Acquiring an answer from a language model" means that a prompt is input to the language model, and the language model outputs an answer. The system 10 also stores an answer acquired from the language model in association with information on a prompt corresponding to the answer. The information on the prompt is, for example, the prompt itself input to the language model, information on keywords and / or text information included in the prompt, information on the answer level included in the prompt, information on the output format of the answer included in the prompt, a provisional prompt used to generate the prompt, etc. The history information may also store attribute information on a user who inputted the prompt in association with information on the answer or prompt. The attribute information is, for example, a user's job title, years of service, gender, age, etc.

[0035] In this embodiment, a question or instruction input into a language model to obtain an answer from the language model is defined as a "prompt," and information generated in the process of generating a prompt based on input and / or selection at user terminal 1 is defined as a "temporary prompt."

[0036] The history information is stored, for example, in a database in the storage unit 23 of the server device 2. In step S15, the server device 2 can delete the answer stored in the database in the storage unit 23 and / or information related to the prompt corresponding to the answer.

[0037] Note that "deleting history information" in step S15 may mean completely erasing the information to be deleted from the database of the storage unit 23, or may mean setting a deletion flag on the information to be deleted. Information with a deletion flag set is excluded from the history information to be determined in step S61 or S71 described later.

[0038] In step S15, the history information to be deleted may be all history information stored in the database, or may be history information related to the specialized information updated in step S14. History information related to specialized information is, for example, history information associated with a prompt including the specialized information, history information associated with an answer including the specialized information, or history information associated with an answer that references the specialized information.

[0039] In the above, the processes of steps S11 and S12 are executed by the administrator terminal 5, but may be executed by the user terminal 1. Also, instead of the processes of steps S11 to S13, the process of step S14 may be executed in response to a predetermined condition being satisfied. For example, when addition, replacement and / or deletion of information is detected in a predetermined database, addition, replacement and / or deletion of information may be executed in the specialized information database 4 so as to correspond to the information.

[0040] [Keyword setting process] Next, a keyword setting process for setting keywords corresponding to options displayed on the user terminal 1 will be described.

[0041] In this embodiment, a keyword is text information indicating a predetermined content. A keyword may be one word or may include multiple words. The system 10 can operate the administrator terminal 5 to register keywords to be displayed as options on the user terminal 1 in the storage unit 23. When registering a keyword, it is also possible to set attributes such as major item, medium item, and small item for each keyword (two attributes of major item and small item may be used, and the number of attributes is not particularly limited. Also, attributes represented by numbers such as first item, second item, and third item may be used). For example, the major item, medium item, and small item may be a higher-level concept as a major item, a lower-level concept below a major item as a medium item, and a lower-level concept below a medium item as a small item.

[0042] Furthermore, among the words constituting the prompt, the upstream concept for identifying the contents of the prompt may be the major item, the downstream concept from the major item may be the medium item, and the downstream concept from the medium item may be the small item. For example, when "home care" or "home nursing" is a keyword of the major item, "problem", "fee", and "method" are keywords of the medium item and the small item. By registering attributes to keywords in this way, for example, multiple options of the major items are displayed on the user terminal 1, and when at least one of these options is selected, multiple options of the medium items are displayed. When at least one of the options of the displayed medium items is selected on the user terminal 1, multiple options of the small items are displayed, and it is possible to select at least one of these options.

[0043] Furthermore, when registering a keyword, the system 10 can register in the storage unit 23 a related keyword associated with each keyword. The system 10 can register a plurality of related keywords for one keyword. Furthermore, when registering this related keyword, the system 10 can register in the storage unit 23 a related keyword associated with this related keyword. In this case, a plurality of related keywords can be registered for one related keyword. By registering related keywords in this way, for example, a plurality of options are displayed on the user terminal 1, and when at least one of these options is selected, an option corresponding to the related keyword registered for the keyword corresponding to the selected option is displayed. Furthermore, when at least one of these options is selected, an option corresponding to the related keyword registered for the related keyword corresponding to the selected option is displayed.

[0044] 5 is a diagram showing a flowchart of a keyword setting process according to an embodiment of the present invention. First, an administrator logs in to the system 10 from the administrator terminal 5. The login to the system 10 is similar to the specialized information update process, and therefore will not be described.

[0045] Next, the administrator terminal 5 transmits a keyword setting request to the server device 2, requesting that a keyword be set by an operation by the administrator (step S21).

[0046] The keyword setting request transmitted in step S21 may include a prompt regarding what kind of keyword to set. For example, the prompt included in the keyword setting request is "Refer to the information stored in the specialized information database 4 regarding nursing care insurance, and set keywords for major, medium, and minor items. Please set the keywords for the medium items to correspond to the keywords for the major items and to subdivide each keyword. Please set the keywords for the minor items to correspond to the keywords for the medium items and to subdivide each keyword."

[0047] When the server device 2 receives the keyword setting request (step S22), it uses the language model to extract keyword information related to the keyword (step S23).

[0048] The process of step S23 will be described. In step S23, the server device 2 transmits a keyword setting request to the language model server 3. Upon receiving the keyword setting request, the language model server 3 refers to the specialized information database 4 to extract predetermined keywords.

[0049] The server device 2 stores the keyword information extracted in step S23 (step S24), and deletes the history information (step S25). Through the above processes of steps S21 to S25, the keyword setting process ends.

[0050] The keyword information includes text information indicating the keyword and information related to the keyword category. The information related to the keyword category includes information regarding which category the keyword belongs to and which keyword the keyword is associated with.

[0051] The history information in step S25 has the same meaning as the history information in step S15. The history information deleted in step S25 may be all history information stored in the database, or may be history information related to the keyword information stored in step S24. The history information related to the keyword information is, for example, history information associated with information related to the keyword corresponding to the keyword information, or history information associated with a prompt including the keyword corresponding to the keyword information.

[0052] The process of step S25 may be omitted. When the language model is stored in the server device 2, step S23 is executed in the server device 2.

[0053] Note that, in place of the above steps S21 to S23 or in addition to the above steps S21 to S23, the keyword setting process may be performed by inputting keyword information to the administrator terminal 5, thereby executing the process of step S24. For example, the administrator may input information about a keyword that he or she has created himself or herself to the administrator terminal 5, thereby allowing the administrator to set the keyword.

[0054] After the process of step S23, the extracted keyword information may be controlled to be displayed on the administrator terminal 5. The administrator can check the displayed keywords and change, add, and / or delete the keywords by operating the administrator terminal 5. The input keyword information may be transmitted from the administrator terminal 5 to the server device 2, thereby executing the processes from step S24 onwards.

[0055] [Output processing] Next, a description will be given of the output process in which a user displays a predetermined answer using the system 10. Fig. 6 is a diagram showing a flowchart of the output process according to the present embodiment.

[0056] First, the user logs in to the system 10 from the user terminal 1. The operation of logging in to the system 10 is the same as that of the administrator terminal 5 in the specialized information update process, and therefore will not be described here. It is preferable that the user registers attribute information related to the user in advance in the system 10 in association with the user ID.

[0057] When logging in to the system 10, the user terminal 1 displays a screen for inputting a question (step S31). In step S31, the system 10 controls the user terminal 1 to display options. At least one option is displayed on the display screen in step S31. One option corresponds to one keyword. A plurality of options may be displayed on the display screen in step S31. Each of the multiple options corresponds to a different keyword. Details of the display screen will be described later. The user terminal 1 accepts input of one option from the options displayed on the screen (step S32).

[0058] The user terminal 1 transmits the input information input in step S32 to the server device 2 (step S33). The input information in step S33 includes information related to the option selected in step S32. The server device 2 receives the input information (step S34). Step S34 is a process of accepting the selection of one or more options from a plurality of options corresponding to each of a plurality of keywords in response to the input from the user terminal 1.

[0059] The server device 2 identifies an option to be displayed next (step S35). In step S35, the server device 2 refers to a database in which keywords are stored to identify an option to be displayed next. Specifically, the server device 2 identifies a keyword associated with the keyword corresponding to the option accepted in step S34. The identified keyword is the keyword corresponding to the option to be displayed next.

[0060] Next, the server device 2 generates a provisional prompt to be displayed on the user terminal 1 from the information about the options received in step S34 (step S36). In step S36, the provisional prompt is generated to generate a prompt to be input to the language model so as to include a keyword corresponding to the option selected in step S32. The method of generating the provisional prompt in step S36 is not particularly limited.

[0061] In step S36, a method for generating a provisional prompt may be, for example, to embed a keyword corresponding to the option selected in step S32 into a preset template to generate the provisional prompt. The template may differ depending on the number of options selected and / or whether or not text information, which will be described later, has been input. That is, in step S34, a template to be referenced is specified depending on the number of options selected on the user terminal 1. The server device 2 can generate a provisional prompt by inserting a keyword corresponding to the option into a predetermined position in the template.

[0062] For example, examples of fixed phrases include "Tell me about (keyword corresponding to option 1) in the long-term care insurance system," and "Tell me about (keyword corresponding to option 2) in (keyword corresponding to option 1) in long-term care insurance." Option 1 is the option selected first, and option 2 is the option selected second.

[0063] Alternatively, as a method of generating the temporary prompt in step S36, a table may be set in advance in which temporary prompts are stored in association with keywords corresponding to the options. The server device 2 may refer to the table to identify the temporary prompt corresponding to the keyword.

[0064] The server device 2 transmits option information relating to the option identified in step S35 and the temporary prompt generated in step S36 to the user terminal 1 (step S37). The user terminal 1 receives the option information and the temporary prompt (step S38) and displays them on the screen (step S39). In step S39, the user terminal 1 is controlled to display the temporary prompt generated in step S36. The options displayed in step S39 are options corresponding to the keywords associated with the one option selected in step S32.

[0065] The processes of steps S32 to S39 are repeated any number of times depending on the content of the question the user wishes to ask. That is, the system 10 can accept the selection of one or more options from the options controlled to be displayed in steps S31 and S39. The number of times steps S32 to S39 are repeated is set in advance by the operation of the administrator terminal 5. It is preferable that the administrator sets keyword items depending on the number of times to be repeated.

[0066] When the repeated processing of steps S32 to S39 is completed and the user selects an option corresponding to the keyword he / she wishes to select, the user terminal 1 accepts input of text information by the user's operation (step S40). In step S40, it is preferable that a word is input as the text information. In step S40, information on the answer level and / or information on the output format of the answer may be accepted. The user terminal 1 transmits the input information input in step S40 to the server device 2 (step S41). The input information in step S41 includes information on the option selected in step S32 and the text information input in step S40. In addition, the input information in step S41 may include information on the answer level and / or information on the output format. The server device 2 receives the input information (step S42). Step S42 is a process of accepting input of text information in response to an input from the user terminal.

[0067] Next, the server device 2 generates a provisional prompt to be displayed on the user terminal 1 based on the keyword corresponding to the option selected in step S32 and the text information input in step S40 (step S43). The process of step S43 is executed in the same manner as the process of step S36.

[0068] The server device 2 transmits the temporary prompt generated in step S43 to the user terminal 1 (step S44). The user terminal 1 receives the temporary prompt (step S45) and displays the temporary prompt on the screen (step S46).

[0069] If the user checks the temporary prompt and determines that it expresses the question that the user wants to ask, the user operates the user terminal 1, and the user terminal 1 transmits an answer request to the server device 2 (step S47). The answer request includes information about the temporary prompt. The answer request may include information about keywords included in the temporary prompt, text information, and information about the user's attributes. When the server device 2 receives the answer request (step S48), an answer acquisition process is executed to acquire answer information about the answer (step S49).

[0070] When the server device 2 acquires the answer information in step S49, it transmits the answer information to the user terminal 1 (step S50). The user terminal 1 receives the answer information (step S51). The answer information transmitted in step S50 is answer information corresponding to the answer request transmitted from the user terminal 1 in step S47. The user terminal 1 displays an answer on the screen from the received answer information (step S52). The answer information acquired in step S49 and the answer information displayed in step S52 do not have to match. The answer information displayed in step S52 may be a part of the answer information acquired in step S49. The server device 2 stores the answer acquired in step S49 as history information in the storage unit 23 (step S53). The output process is completed by the above-mentioned processes of steps S31 to S53.

[0071] The history information in step S53 has the same meaning as the history information in step S15. Regarding step S53, storage of the history information may be executed only when answer information is acquired in step S70 or S91 described later. Also, in step S53, the server device 2 may store information related to a keyword corresponding to the option selected in the user terminal 1. The information related to the keyword may be stored in association with the date and time of selection. The server device 2 can calculate the number of times a given keyword has been selected in a given period of time.

[0072] After the process of step S52, input of evaluation information for evaluating the answer may be executed in response to an operation on the user terminal 1. The answer information transmitted in step S50 may include information requesting the user to evaluate the answer. In step S52, information for the user to evaluate the answer is displayed on the display screen. The evaluation information may be a step-by-step evaluation of whether the answer was satisfactory, or may be information that accepts comments on the answer as text information. The evaluation information is stored in the storage unit 23 of the server device 2. The evaluation information may be stored in the storage unit 23 of the server device 2 in association with history information corresponding to the evaluation information. The evaluation information can be controlled to be displayed on the administrator terminal 1.

[0073] The order of the processes of steps S35 and S36 may be reversed. Furthermore, the processes of steps S35 and S36 and / or step S43 may be executed in the user terminal 1. In this case, the processes of steps S33, S34, S37, and S38, and / or steps S41, S42, S44, and S45 may be omitted.

[0074] The provisional prompt displayed in step S39 may be a prompt. In this case, steps S40 to S46, and steps S63 to S85 described later are omitted. The system 10 may generate a prompt so as to include a keyword corresponding to the option selected in step S32. The provisional prompt displayed in step S46 may be a prompt. In this case, steps S63 to S85 described later are omitted. The system 10 may generate a prompt based on the keyword corresponding to the option selected in step S32 and the text information input in step S40.

[0075] [Answer acquisition process] Next, the answer acquisition process in step S49 will be described. Fig. 7 is a diagram showing a flowchart of the answer acquisition process according to the present embodiment. In the answer acquisition process shown in Fig. 7, the specialized information is acquired by the language model server 3.

[0076] First, the server device 2 determines whether or not information relating to the provisional prompt received in step S48 and a prompt that satisfies a predetermined condition is stored (step S61). As described above, information relating to the prompt is stored as history information in the server device 2. In step S61, the server device 2 compares the provisional prompt with information relating to the prompt included in the history information to determine whether or not information relating to the provisional prompt and a prompt that satisfies a predetermined condition is stored.

[0077] The "predetermined condition" in step S61 may be, for example, that the temporary prompt and the information about the prompt match or are similar. The information about the temporary prompt and the prompt to be compared may include the temporary prompt itself, keywords and / or text information contained in the temporary prompt, attributes of the user who input the options, the answer level, the output format, etc.

[0078] A match between the provisional prompt and the information relating to the prompt means that the above-mentioned comparison target is a complete match between the provisional prompt and the information relating to the prompt. A similarity between the provisional prompt and the information relating to the prompt means that the above-mentioned comparison target is similar between the provisional prompt and the information relating to the prompt. For example, if the comparison target is a keyword, the server device 2 may determine that they are similar if a predetermined threshold or more (e.g., two or more out of three) of keywords match. If the comparison target is the provisional prompt itself, the server device 2 may determine that they are similar if the vector similarity between the provisional prompt and the prompt is a predetermined threshold or more (e.g., 0.5 or more).

[0079] When the comparison targets are keywords and / or text information, the server device 2 may determine whether or not the order in which the keywords and / or text information are selected or input matches in addition to the contents of the keywords and / or text information. In other words, the server device 2 may determine whether or not the contents and / or order of the keywords and / or text information included in the provisional prompt match or are similar to those of the keywords and / or text information included in the prompt stored in the history information.

[0080] If information relating to the provisional prompt and a prompt that satisfies the predetermined condition is stored (YES in step S61), the server device 2 acquires answer information by identifying an answer corresponding to the information relating to the prompt from the history information (step S62).On the other hand, if information relating to the provisional prompt and a prompt that satisfies the predetermined condition is not stored (NO in step S61), the server device 2 generates a prompt from the provisional prompt (step S63).

[0081] In step S63, the server device 2 generates a prompt by adding predetermined information to the provisional prompt. The predetermined information is, for example, information on a keyword, an answer level, and / or an output format corresponding to an option not selected by the user in step S32 and / or step S40. Furthermore, the predetermined information is preferably information on a prompt that is not stored in the server device 2 as history information.

[0082] In step S63, the server device 2 identifies information about a prompt that is set in the system 10 and is not stored in the server device 2. The server device 2 then generates a temporary prompt by connecting the identified information to information of the same type as the identified information with a selective conjunction. Alternatively, the server device 2 generates a temporary prompt by replacing the identified information with information of the same type as the identified information in the temporary prompt. The server device 2 then generates a prompt by combining the temporary prompt received in step S48 with the generated temporary prompt.

[0083] In addition, information of the same type may be, for example, in the case of keywords, keywords of the same attribute; in the case of answer levels, information set as an answer level; and in the case of output formats, information set as an output format.

[0084] For example, when the temporary prompt received in step S48 is "Please tell me about keyword B of keyword A. Please output in output format X," the following process is executed in step S63. When output formats X, Y, and Z are set in the system 10, the information on the keyword and output format included in the temporary prompt is "keyword A, keyword B, and output format X," so the server device 2 adds information on output format Y and output format Z to the temporary prompt.

[0085] The server device 2 generates a prompt such as, for example, "Please tell me about keyword B of keyword A. Please output in output format X, Y, or Z." Or, the server device 2 generates a prompt such as, for example, "Please tell me about keyword B of keyword A. Please output in output format X. Please tell me about keyword B of keyword A. Please output in output format Y. Please tell me about keyword B of keyword A. Please output in output format Z."

[0086] The server device 2 transmits the prompt generated in step S63 to the language model server 3 (step S64). Upon receiving the prompt (step S65), the language model server 3 acquires specialized information as related information from the specialized information database 4 based on the prompt (step S66).

[0087] In step S66, the language model server 3 may use a known method for the process of acquiring related information from the specialized information database 4. For example, information including a keyword included in the prompt may be regarded as related information. The language model server 3 may acquire information including a keyword included in the prompt from the specialized information database 4. In addition, the language model server 3 may acquire information including a keyword corresponding to the option selected in step S32 from the specialized information database 4.

[0088] Alternatively, information having a vectorized value that is similar to the vectorized value of the prompt may be regarded as the related information. The language model server 3 can acquire the related information as follows. For example, the language model server 3 performs a vector operation on the prompt received in step S65 to vectorize the prompt. Furthermore, the specialized information stored in the specialized information database 4 is vectorized by performing a vector operation. The server device 2 acquires information that provides a value that is similar to the value obtained from the vectorized prompt, using the vectorized prompt and the vectorized information in the specialized information database 4. In other words, when the values ​​obtained from the vectorized sentence are similar between text A and text B, text A and text B are determined to be related. The related information may be that the vectorized values ​​are similar.

[0089] 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 is less than the predetermined threshold). The predetermined threshold can be set appropriately.

[0090] After acquiring the specialized information in step S66, the language model server 3 uses the specialized information and the prompt to output an answer from the language model (step S67). The language model server 3 transmits answer information related to the output answer to the server device 2 (step S68). The server device 2 receives the answer information (step S69) and acquires the answer information (step S70).

[0091] Next, the server device 2 associates the answer information with information on the prompt (step S71). In step S63, the server device 2 generates a prompt that causes multiple answers to be output in one answer. Therefore, in step S71, the server device 2 executes a process of associating at least a part of the acquired answer with information on the prompt corresponding to at least a part of the answer. For example, the server device 2 associates a first part included in the answer with information on the prompt corresponding to the first part, and associates a second part included in the answer with information on the prompt corresponding to the second part.

[0092] A known method can be used for the process of identifying which part of the answer acquired in step S70 is related to which keyword, answer level, and / or output format. For example, the system 10 may perform additional learning such as fine tuning on the language model regarding how to output the answer. Alternatively, the system 10 may generate a prompt in step S63 to include a provisional prompt that specifies the output.

[0093] The answer information and the information about the prompt associated in step S70 are stored as history information in step S53. That is, the system 10 can store multiple pieces of history information by outputting an answer from the language model once. The answer acquisition process is completed by the above steps S61 to S71.

[0094] Next, another example of the answer acquisition process in step S49 will be described. Fig. 8 is a diagram showing a flowchart of another example of the answer acquisition process according to the embodiment of the present invention. The answer acquisition process shown in Fig. 8 differs from the answer acquisition process shown in Fig. 7 in that specialized information is acquired by the server device 2.

[0095] First, the server device 2 determines whether information relating to the temporary prompt received in step S48 and a prompt that satisfies a predetermined condition is stored (step S81). If information relating to the temporary prompt and a prompt that satisfies the predetermined condition is stored (YES in step S81), the server device 2 acquires answer information by identifying an answer corresponding to the information relating to the prompt from the history information (step S82). The processing in steps S81 and S82 can be the same as that in steps S61 and S62, and therefore a description thereof will be omitted.

[0096] If information relating to the temporary prompt received in step S48 and a prompt that satisfies the predetermined condition is not stored (NO in step S81), the server device 2 generates a temporary prompt (step S83). The process of step S83 can be the same as the process of step S63, except that the "prompt" to be generated is a "temporary prompt."

[0097] The server device 2 acquires specialized information as related information from the specialized information database 4 based on the temporary prompt generated in step S83 or the keyword corresponding to the option selected in step S32 (step S84).

[0098] In step S84, a known method can be used for the process in which the server device 2 acquires related information from the specialized information database 4. For example, the process in step S84 can be the same as the process in which the language model server 3 acquires related information from the specialized information database 4 (step S66) described above, except that the "prompt" is replaced with a "temporary prompt" and the "language model server 3" is replaced with the "server device 2."

[0099] When the specialized information is acquired in step S84, the server device 2 generates a prompt based on the information acquired in step S84 and the keyword corresponding to the temporary prompt received in step S48 or the option selected in step S32 (step S85).

[0100] In step S85, the server device 2 can generate a prompt by adding the specialized information acquired in step S84 to the provisional prompt received in step S48. Also, in step S85, the server device 2 can generate a prompt to be input to the language model so as to include the keyword corresponding to the option selected in step S32 and the text information input in step S40.

[0101] The server device 2 transmits the prompt generated in step S85 to the language model server 3 (step S86). The language model server 3 receives the prompt (step S87). The language model server 3 outputs an answer by inputting the prompt into a language model (step S88). The language model server 3 transmits answer information related to the output answer to the server device 2 (step S89). The server device 2 receives the answer information (step S90) and acquires the answer information (step S91).

[0102] The server device 2 associates the answer information with information about the prompt (step S92). The process of step S92 can be the same as the process of step S71. After the processes of steps S81 to S92, the answer acquisition process ends.

[0103] In the above, a provisional prompt to be input to the language model is generated by the processing of steps S31 to S48, but the provisional prompt used in the answer acquisition process may be obtained by inputting it in another computer device. That is, instead of the processing of steps S31 to S48, the answer acquisition process may be executed by acquiring a provisional prompt inputted in another computer device.

[0104] Also, the process of step S63 or S83 may be omitted. In this case, the process of step S71 or S92 is also omitted. Furthermore, in this case, in the answer acquisition process shown in Fig. 7, the provisional prompt received in step S48 is used as the prompt. The prompt used in the answer acquisition process may be obtained from one input in another computer device.

[0105] The processes of steps S63 to S71 and S53, or steps S83 to S92 and S53, may be executed in response to an operation on the administrator terminal 5. For example, the above processes may be executed after the keyword setting process. At this time, answers corresponding to temporary prompts combining the set keywords are stored as history information. When answers corresponding to all combinations of the set keywords, answer levels, and output formats have been stored as history information, the processes of steps S63 to S71 or steps S83 to S92 may be omitted in the output process executed in response to an operation on the user terminal 1.

[0106] In the above answer acquisition process, related specialized information is acquired in step S66 or S84, but the process of step S66 or S84 may be omitted. When step S84 is omitted, the process of step S85 is also omitted. At this time, the provisional prompt displayed in step S39 or S46 may be input to the language model as a prompt. The system 10 can acquire an answer from the language model based on the prompt generated in step S36 or S43, or a prompt generated from the provisional prompt generated in step S36 or S43.

[0107] [Display screen explanation] Next, the display screen according to this embodiment will be described. Figures 9 to 13 are diagrams showing examples of the display screen according to this embodiment. Figure 9 shows a display screen 100a in step S31.

[0108] The display screen 100a is a screen for a user to input a question to the system 10. The display screen 100a has a first option display area 101, a second option display area 102, a third option display area 103, a free word input area 104, and a generated prompt display area 110. The display screen 100a may have an answer level selection area 105 and / or an output format selection area 106.

[0109] The first option display area 101 is an area for displaying the first option that the user first selects. It is preferable that the first option is always selected by the user. A plurality of first options 30, 31, 32, 33, 34 are displayed in the first option display area 101. Also, first options 30a to 30j are displayed so as to correspond to the first option 30. Each of the keywords corresponding to the first options 30a to 30j is associated with a keyword corresponding to the first option 30.

[0110] Similarly, first options 31a to 31d corresponding to first option 31, first options 32a to 32c corresponding to first option 32, and first options 33a to 33c corresponding to first option 33 are displayed.

[0111] In the present embodiment, among the multiple options displayed, the keyword associated with the first option is different from the keyword associated with the second option. That is, on the display screen 100a, the keyword associated with the keyword "home care" corresponding to the first option 30 is different from the keyword associated with the keyword "facility care" corresponding to the first option 31. Note that among the multiple options displayed, there may be options in which some or all of the keywords associated with the options overlap.

[0112] In this embodiment, each option is displayed in a manner that allows the corresponding keyword to be understood. In Figures 9, 10, and 12, text indicating the content of the keyword corresponding to the option is displayed in a rectangular frame.

[0113] The second option display area 102 is an area for displaying a second option that is selected second by the user. The third option display area 103 is an area for displaying a third option that is selected third by the user. On the display screen 100a, options corresponding to the second option display area 102 and the third option display area 103 are not displayed. The free word input area 104 is an area for the user to input text information (also called a free word) in step S40.

[0114] The answer level selection area 105 is an area for displaying options related to an answer level selected by the user. In the answer level selection area 105, level options 105a to 105d are displayed. The system 10 pre-sets level options in correspondence with keywords related to the answer levels. In addition, the system 10 may store a provisional prompt corresponding to the keywords related to the answer levels. The keywords related to the answer levels may be, for example, those related to the level of the answer, such as "easy to understand", "concise", "without using technical terms", "so that even an elementary school student can understand", "as if explaining from an expert", or those related to the expression of the answer, such as "in the polite form" or "in the polite form".

[0115] The output format selection area 106 is an area for displaying options related to an output format selected by the user. In the output format selection area 106, output format options 106a to 106d are displayed. The output format options 106a to 106d are options for the user to select an output format of the answer in step S40. The system 10 pre-sets output format options in correspondence with keywords related to the output format. In addition, the system 10 may store a temporary prompt corresponding to a keyword related to the output format. The keyword related to the output format may be, for example, a keyword related to the type of answer to be output, such as "item list", "table format", "FAQ format", or "unspecified", or may be a keyword related to the number of characters to be output, such as "within 300 characters".

[0116] The generated prompt display area 110 is an area for displaying the provisional prompt generated in step S36 or S43.

[0117] The display screen 100a may have icons 121 to 124. When the icon 121 is selected, the answer request in step S47 is sent to the server device 2. The temporary prompt displayed in the generated prompt display area 110 when the icon 121 is selected becomes the temporary prompt included in the answer request. When the icon 122 is selected, the content selected or displayed on the display screen 100a is erased. When the icon 123 is selected, the first option displayed in the first option display area 101 is erased.

[0118] 10 shows the display screen 100b in step S39 after the first option is selected. In the following explanation, the contents explained on the display screen 100a will be omitted to avoid duplication.

[0119] The display screen 100b is a display screen that is displayed after the first option 30a is selected on the display screen 100a. In the first option display area 101 on the display screen 100b, "Home care" corresponding to the selected first option 30a is displayed. In the second option display area 102 on the display screen 100b, the second options 40a to 40c are displayed. Moreover, the first option is not displayed on the display screen 100b.

[0120] The second options 40a to 40c each correspond to a keyword associated with the keyword "home care" corresponding to the first option 30a.

[0121] Also, the temporary prompt generated in step S36, "Tell me about home care under the nursing care insurance system," is displayed in generated prompt display area 110. As shown in Fig. 10, the temporary prompt displayed in generated prompt display area 110 displays "home care" in bold. In this embodiment, system 10 controls so that the keyword corresponding to the option selected in step S32 is displayed in a different form from other text included in the generated temporary prompt.

[0122] The different manner is preferably a manner in which the keyword is displayed more prominently than other text, for example, by making the keyword bold, blinking, changing the color of the keyword, changing the size of the keyword, etc.

[0123] In this embodiment, the system 10 may perform control so that the temporary prompt displayed in the generated prompt display area 110 cannot be edited from the user terminal 1. Alternatively, the system 10 may perform control so that the temporary prompt displayed in the generated prompt display area 110 can be edited from the user terminal 1. The processes from step S47 onwards are executed using the temporary prompt edited by operating the user terminal 1.

[0124] When icon 121 is selected on display screen 100b, an answer corresponding to the provisional prompt displayed in generated prompt display area 110 is output. Specifically, when icon 121 is selected, the processes from step S47 onwards are executed. Fig. 11 corresponds to display screen 100c at step S52 after the answer has been output, with the processes from steps S40 to S46 omitted from display screen 100b shown in Fig. 10.

[0125] The display screen 100c has a condition display area 130, a questionnaire input area 140, and an answer display area 150.

[0126] Information about conditions for outputting an answer is displayed in the condition display area 130. Conditions 131 and generation prompts 132 are displayed in the condition display area 130. The conditions 131 display options selected by the user and / or text information entered by the user.

[0127] The generation prompt 132 displays the prompt input to the language model to output an answer. Note that the prompt displayed in the generation prompt 132 does not have to match the prompt actually input to the language model. The prompt displayed in the generation prompt 132 may be the same as the provisional prompt displayed in the generation prompt display area 110.

[0128] The questionnaire input area 140 is an area for inputting evaluation information. The questionnaire input area 140 is provided with a satisfaction level input area 141 and a reason input area 142. The user can operate the user terminal 1 to input the satisfaction level of the answer in the satisfaction level input area 141. The user can also operate the user terminal 1 to input the reason for the evaluation in the reason input area 142.

[0129] At least a part of the answer information acquired in step S49 is displayed in the answer display area 150. Information capable of identifying the specialized information acquired from the specialized information database 4 and referenced when acquiring the answer may be displayed in the answer display area 150. The information capable of identifying the specialized information may be the specialized information itself, a URL to the specialized information, or a comment when the specialized information is displayed on the user terminal 1.

[0130] FIG. 12 shows the display screen 100d in step S46 after the first and second options have been selected and text information has been input.

[0131] The display screen 100d is a display screen that is displayed after the second option 40a is selected on the display screen 100b and "problem" is further input as a free word. In the first option display area 101 on the display screen 100d, "home care" corresponding to the selected first option 30a is displayed, and in the second option display area 102, "physical care" corresponding to the selected second option 40a is displayed. In addition, in the third option display area 103 on the display screen 100d, the third options 50a to 50f are displayed. In addition, the first option and the second option are not displayed on the display screen 100b.

[0132] The third options 50a to 50f each correspond to a keyword associated with the keyword "physical care" corresponding to the second option 40a.

[0133] Also, the generated prompt display area 110 displays the temporary prompt generated in step S43, "Tell me about the problems with physical care in home care under the nursing care insurance system." As shown in FIG. 12, the temporary prompt displayed in the generated prompt display area 110 displays "home care," "physical care," and "problems" in bold. In this embodiment, the system 10 controls so that the keyword and text information corresponding to the option selected in step S32 are displayed in a manner different from other text included in the generated temporary prompt. The different manner is preferably a manner in which the keyword and text information are displayed more prominently than other text as described above.

[0134] When icon 121 is selected on display screen 100d, an answer corresponding to the tentative prompt displayed in generated prompt display area 110 is output. Specifically, when icon 121 is selected, the processes from step S47 onwards are executed. FIG. 13 shows display screen 100e in step S52 after an answer request is sent from display screen 100d displayed in FIG. 12 and an answer is output. The components displayed on display screen 100e are the same as those on display screen 100c. An answer corresponding to the prompt displayed in generated prompt 132 is displayed in answer display area 150 of display screen 100e.

[0135] [Display order change process] Next, a description will be given of a display order change process for changing, in accordance with predetermined information, an area in which options are displayed on the user terminal 1. Fig. 14 is a diagram showing a flowchart of the display order change process according to the present embodiment.

[0136] The timing of execution of the display order change process is not particularly limited, and may be executed in response to a request from the administrator terminal 5, or may be executed every predetermined period (for example, one month). The display order change process may be executed for all options, or may be executed for options within a predetermined range. The options within the predetermined range include options associated with the same keyword (for example, the first options 30a to 30j), options displayed on the same display screen, etc.

[0137] First, the server device 2 identifies the number of times each option has been selected within a predetermined period for which the display order change process is executed (step S91). The predetermined period is not particularly limited, and may be, for example, one month, one week, one day, etc. The predetermined period may be the period from when the display order change process was last executed to when it is newly executed.

[0138] Next, the server device 2 changes the area in which each option is displayed according to the information on the specified number of times (step S92). The information on the number of times is, for example, the number of times the option was selected in a predetermined period. The server device 2 stores the changed display area in association with the option (step S93). The display order change process is completed by the above steps S91 to S93.

[0139] Changing the display area in step S93 is a concept that includes changing the display order on the same display screen, changing the options displayed on the first display screen to be displayed on the second display screen, causing the options displayed on the first display screen to be further displayed on the second display screen, and displaying further options.

[0140] For example, the position of the first option 30j may be changed to the position of the first option 30b on the display screen 100a by step S93. Also, for example, the positions of the first options 33a to 33c related to the first option 33 on the display screen 100a may be changed to a position above the first option 30 on the display screen 100a by step S93. Also, for example, the first option 30b may be further displayed above the other first options on the display screen 100a by step S93. Also, for example, the second option 40a displayed on the display screen 100b may be changed to be displayed on the display screen 100a by step S93. At this time, the second option 40a may be displayed near the first option 30a, and the first option 30a and the second option 40a may be selected by selecting the second option 40a on the display screen 100a.

[0141] Note that the display mode of the options may be controlled to be different depending on the information on the number of times specified in step S91. For example, the server device 2 may display the options that have been selected more frequently in a predetermined period in a more prominent manner than the other options. The server device 2 may also display the options that have been selected more frequently in a predetermined period in red, the options that have been selected in the middle order in blue, and the options that have been selected in the lower order in black. At this time, the server device 2 may or may not change the display area of ​​the options.

[0142] In this embodiment, the system 10 controls so as to display at least two or more options in a list (see FIGS. 9, 10, and 12). By the processes of steps S91 to S93, the system 10 can control so as to change and display the areas displaying each option in steps S31, S39, or S46 according to information on the number of times the option was selected in step S32.

[0143] In this embodiment, the system 10 controls the display screen to display the next option each time an option is selected, but it may also be controlled to display, for example, the first option, the second option, and the third option on a single display screen.

[0144] The system 10 may control the user terminal 1 to display search history information related to the search history searched by the user operating the user terminal 1. The search history information is stored by associating a keyword corresponding to a selected option, input text information, information on an answer level, information on an output format, a user ID, and / or a search date and time with each other. The search history information may be displayed in a list on the user terminal 1. Also, by selecting one piece of search history information by operating the user terminal 1, the keyword or the like corresponding to the search history information may be displayed in a selected state on the display screen 100a.

[0145] The system 10 may control the user terminal 1 to display a screen for selecting the specialized information database 4 and / or the language model server 3 before step S31. The system 10 may display a search screen, such as a portal site, before step S31. The user can select the specialized information database 4 and / or the language model server 3 to be used to output an answer in the system 10. In addition, the system 10 may be configured to search and extract a specific specialized information database 4 and / or language model server 3 in the screen for selecting the specialized information database 4 and / or the language model server 3 in response to an operation of the user terminal 1. In addition, the system 10 may control the user terminal 1 to display a list of selectable specific specialized information databases 4 and / or language model servers 3.

[0146] On the display screen of the user terminal 1, the specialized information database 4 is displayed in a manner that allows the information stored in the specialized information database 4 to be understood. For example, attributes of the information stored in the specialized information database 4 may be displayed. For example, information attributes such as "nursing care insurance field," "personnel recruitment information," "accounting information," "customer service," etc. are displayed on the user terminal 1. By selecting an attribute of the information about which the user wants to ask a question, the selected specialized information database 4 and / or language model server 3 are used to execute output processing and answer output processing.

[0147] It is not necessary to provide the process of receiving the input of text information in step S40. If the process of receiving the input of text information is not provided, the processes of steps S40 to S46 are omitted. Alternatively, options regarding the answer level and / or the output format are input, and the processes of steps S40 to S46 are executed. In this case, the free word input area 104 is not displayed on the display screen 100. At this time, the user is limited to inputting only the options displayed on the display screen 100. This allows the system 10 to limit the questions input to the language model to only keywords intended by the administrator who manages the options, and to restrict the language model from outputting answers to unrelated matters. In this way, the system can provide answers to the user by limiting the content of the question input by the user.

[0148] In this embodiment, the system 10 stores evaluation information. The administrator can display the evaluation information on the administrator terminal 5 and review the template phrases for generating temporary prompts for answers with low evaluations. The administrator can also consider problems and areas for improvement based on the evaluation information.

[0149] In the above, the system 10 has been described as supporting a search for obtaining an answer related to specific information. However, the process of supporting the generation of a prompt by selecting an option in the system 10 is not limited to a search, and can be used to support the generation of a prompt for a language model to output various kinds of information. For example, the system 10 can be used to generate a prompt for a language model to summarize or proofread a sentence, or to generate a prompt for a language model to generate a sentence or an image. The sentence or image generated based on the language model may be, for example, a document such as a proposal document, an analysis report for marketing, or a program code.

[0150] In this way, the system includes at least one computer device, a selection means for accepting a selection of one or more options from a plurality of options corresponding to each of a plurality of keywords in response to an input from a user terminal operated by a user, and a first generation means for generating a prompt to be input to a language model so as to include a keyword corresponding to the option selected by the selection means, or a provisional prompt for generating the prompt, thereby making it possible to assist a user in inputting a prompt to be input to a language model. Furthermore, by preparing options corresponding to keywords in advance, it is possible to reduce the burden on the user when generating a prompt. Furthermore, a user can obtain an output from a language model with a simple input. For example, a user can obtain an answer to a question from a language model by inputting an option.

[0151] In addition, since the system includes a prompt display means for controlling the display of the prompt or provisional prompt generated by the first generating means in the user terminal, the user can check the prompt or provisional prompt generated based on the selected option. If the prompt or provisional prompt is different from the one intended, the user can reselect an option.

[0152] Also, in this way, the system includes an option display means for controlling the user terminal to display options, the selection means accepts the selection of one or more options from the options controlled to be displayed by the option display means, and when one option is selected from the multiple options by the selection means, the option display means controls to further display an option corresponding to a keyword associated with the selected one option, thereby making it possible to provide more detailed information about the content of a question that the user asks the language model. Also, in this way, among the multiple options displayed, the keyword associated with a first option and the keyword associated with a second option are different, so that the option intended by the user can be displayed.

[0153] Furthermore, by controlling the prompt display means to display the keyword corresponding to the option selected by the selection means in a manner different from other text contained in the generated prompt or provisional prompt, the user can confirm that the keyword selected by the user is included in the prompt or provisional prompt.

[0154] In this way, the system includes an input means for accepting input of text information in response to input from the user terminal, and the first generation means generates the prompt or the provisional prompt based on keywords corresponding to the options selected and accepted by the selection means and the text information input and accepted by the input means, thereby allowing the user to flexibly input questions they wish to ask in addition to input based on preset options.

[0155] Furthermore, in this way, the first generation means generates the prompt or the provisional prompt by embedding keywords corresponding to the options selected by the selection means into a preset template text, thereby reducing the processing burden on the computer device in generating the prompt or provisional prompt.

[0156] In addition, in this way, the system is provided with an answer acquisition means for acquiring an answer from a language model based on the prompt generated by the first generation means or a prompt generated from a provisional prompt, thereby making it possible to output an answer from the language model.

[0157] In addition, in this way, the system includes an information acquisition means for acquiring related information from a specialized information database in which predetermined information is stored, based on the prompt generated by the first generation means or a prompt generated from a provisional prompt in the language model, and an answer acquisition means for acquiring an answer from the language model using the information acquired by the information acquisition means and the prompt, so that an answer based on the predetermined information can be output from the language model. In addition, in this way, the system includes an information acquisition means for acquiring related information from a specialized information database in which predetermined information is stored, based on the generated provisional prompt or a keyword corresponding to an option whose selection has been accepted, a second generation means for generating a prompt based on the information acquired by the information acquisition means and the provisional prompt or the keyword, and an answer acquisition means for acquiring an answer from the language model based on the prompt generated by the second generation means, so that an answer based on the predetermined information can be output from the language model. This makes it possible to acquire an answer including information updated since the learning of the language model was completed.

[0158] In this way, the system is equipped with an extraction means that extracts specific keywords by having the language model refer to a specialized information database, and the selection means accepts a selection of an option from options corresponding to the keywords extracted by the extraction means, thereby reducing the burden on the administrator to set keywords.

[0159] Also, in this way, the system includes option display means for controlling the user terminal to display options, the selection means accepts the selection of one or more options from the options controlled to be displayed by the option display means, and the option display means controls to display at least two or more options in a list, and the area displaying each option is controlled to be changed and displayed according to information related to the number of times the option was selected by the selection means, so that the area displaying the options can be changed according to the selection history of the option. Also, options that are frequently selected during a search can be changed to be displayed in an area that is easy for the user to select.

[0160] In this way, the system includes at least one computer device, a first acquisition means for acquiring an answer from a language model based on a prompt, a storage means for storing the answer acquired by the first acquisition means in association with information on the prompt corresponding to the answer, a first generation means for generating or acquiring a prompt to be input to the language model or a provisional prompt for generating the prompt, and an identification means for identifying an answer corresponding to the information on the prompt from the storage means when the prompt or provisional prompt generated or acquired by the generation means and information on a prompt satisfying a predetermined condition are stored, thereby reducing the number of times an answer is output from the language model. Also, by reducing the number of times the language model is used, the response to output an answer can be made faster. Also, by reducing the number of times the language model is used, the usage fee for using the language model can be reduced.

[0161] In addition, in this way, when the system is provided with a second acquisition means for acquiring an answer from a language model based on a prompt generated from the prompt or provisional prompt generated or acquired by the first generation means and information regarding a prompt that satisfies a specified condition is not stored, the system can output an answer to the user even if the answer is not stored in the system.

[0162] Furthermore, in this way, the system includes a second generating means for generating a prompt by adding predetermined information to the provisional prompt, the second acquiring means acquires an answer from a language model based on the prompt generated by the second generating means, and the storage means stores at least a part of the answer acquired by the second acquiring means in association with information on the prompt corresponding to at least a part of the answer, thereby dividing the answer output from the language model and storing the divided answers as answers corresponding to multiple questions. This allows the system to store multiple answers by outputting one answer, thereby reducing the number of times answers are output from the language model.

[0163] In this way, the system is equipped with an information acquisition means for acquiring related information from a specialized information database in which specified information is stored based on a prompt, and a first acquisition means for acquiring an answer from a language model using the related information and the prompt, and is equipped with an information update means for adding, replacing, and / or deleting specified information from the specialized information database, and a deletion means for deleting information relating to the answer stored in the storage means and / or the prompt corresponding to the answer in response to the addition, replacement, and / or deletion of specified information by the information update means, thereby making it possible to prevent answers output based on past specified information from being provided to the user.

[0164] 1 User terminal 2 Server device 3 Language model server 4 Specialized information database 5 Administrator terminal 6 Communication Network 10 System 11 control section 12 RAM 13 storage section 14 input section 15 Display unit 16 Communication interface 21 control unit 22 RAM 23 storage unit 24 communication interface 101 1st choice display area 102 2nd choice display area 103 Third option display area 104 Free word input area 105 Answer level selection area 105a~105d Level options 106 Output format selection area 106a~106d Output format options 110 Generation prompt display area 121~124 Icons 130 Condition Display Area 131 Conditions 132 Generation Prompts 140 Questionnaire input area 141 Satisfaction level input area 142 Reason input area 150 Answer display area

Claims

1. A system comprising at least one computing device, an information acquisition means for acquiring related information from a specialized information database in which predetermined information is stored, based on the prompt; a first acquiring means for acquiring an answer from a language model based on the related information and the prompt; a storage means for storing the answer acquired by the first acquisition means and information on the prompt corresponding to the answer in association with each other; a first generating means for generating or obtaining a prompt for input to a language model or a provisional prompt for generating the prompt; a determination means for determining, when a prompt or provisional prompt generated or acquired by the first generation means and information about a prompt that satisfies a predetermined condition are stored, an answer corresponding to the information about the prompt from the storage means; An information updating means for adding, replacing, and / or deleting predetermined information from the specialized information database; a deletion means for deleting information on the answer and / or the prompt corresponding to the answer stored in the storage means in response to the addition, replacement, and / or deletion of the predetermined information by the information update means; A system comprising:

2. a second acquisition means for acquiring an answer from a language model based on a prompt generated from the prompt or provisional prompt when information about the prompt or provisional prompt generated or acquired by the first generation means and a prompt that satisfies a predetermined condition is not stored; The system of claim 1 , comprising:

3. a second generating means for generating a prompt by adding predetermined information to the provisional prompt; Equipped with a second obtaining means for obtaining an answer from the language model based on the prompt generated by the second generating means; the storage means stores at least a part of the answers acquired by the second acquisition means in association with information on the prompts corresponding to the at least a part of the answers; The system of claim 2.

4. An information acquisition means for acquiring related information from a specialized information database in which predetermined information is stored based on a prompt; a first acquiring means for acquiring an answer from a language model based on the related information and the prompt; a storage means for storing the answer acquired by the first acquisition means and information on the prompt corresponding to the answer in association with each other; a first generating means for generating or obtaining a prompt for input to a language model or a provisional prompt for generating the prompt; a determination means for determining an answer corresponding to information on a prompt when the prompt or provisional prompt generated or acquired by the first generation means and information on the prompt that satisfies a predetermined condition are stored in the storage means; An information updating means for adding, replacing, and / or deleting predetermined information from the specialized information database; a deletion means for deleting information on the answer and / or the prompt corresponding to the answer stored in the storage means in response to the addition, replacement, and / or deletion of the predetermined information by the information update means; A computer device comprising:

5. A method executed on at least one computing device, comprising: an information acquisition step of acquiring related information from a specialized information database in which predetermined information is stored based on the prompt; a first acquisition step of acquiring an answer from a language model based on the related information and the prompt; a storage step of storing the answer acquired in the first acquisition step in association with information on the prompt corresponding to the answer; a first generation step of generating or obtaining a prompt for input to a language model or a provisional prompt for generating said prompt; a step of identifying an answer corresponding to the information on the prompt when the information on the prompt or provisional prompt generated or acquired in the first generating step and the prompt satisfying a predetermined condition are stored in the storing step; an information updating step of adding, replacing, and / or deleting predetermined information from the specialized information database; a deletion step of deleting information related to the answer and / or the prompt corresponding to the answer stored in the storage step in response to the addition, replacement, and / or deletion of the predetermined information by the information update step; The method comprising:

Images