Solution generation device and solution generation method

Abstract

To provide a solution generation device for generating a sentence describing a solution even to a new problem and a new technical element.SOLUTION: The solution generation device for obtaining a solution to a problem by a language model includes an input part 3 for inputting a plurality of combinations of problems and technical elements for solving the problems from a problem database 1 and a technical element database 2, and generates instruction information to the language model for each combination of the problem and the technical element input by the input part. This device is provided with a generation part 4 for inputting instruction information to a language model, setting a diversity parameter 8 for instructing the diversity of a solution to be obtained by the language model to the language model, and instructing the language model to generate the sentence of the solution, and an output part 5 for outputting the solution obtained by the language model with a problem and a technical element input by an input part as items.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a solution generation device and a solution generation method for generating solutions. [Background technology]

[0002] There is a technique for generating candidate answer sentences that serve as answers to new questions submitted by users, based on a question and answer database.

[0003] For example, Patent Document 1 describes a system that includes a processor and a storage device, and that stores a question and answer database that associates and saves past question sentences with past answer sentences corresponding to the past question sentences. When a user inputs an item word group and a new question sentence selected by a user from an item candidate word group generated based on the past question sentences and new question sentences stored in the question and answer database, the processor generates question information including the item word group based on the item word group and the new question sentence, calculates a similarity between each of the past question sentences stored in the question and answer database and the question information, extracts past question sentences similar to the question information from the question and answer database based on the similarity, and extracts past answer sentences associated with the past question sentences similar to the extracted question information from the question and answer database to set them as first answer candidate sentences. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2023-091791 Summary of the Invention [Problem to be solved by the invention]

[0005] In use cases (such as generating solution ideas) where multiple questions about new issues or new technological elements are input, such as generating solution ideas that respond to changes in technological elements in response to changes in social trends, it is difficult to apply the above-mentioned prior art that extracts similar questions from an answer database.

[0006] An object of the present invention is to provide a solution generation device and a solution generation method that can generate documents describing solutions even for new problems and new technical elements. [Means for solving the problem]

[0007] In order to solve the above problems, the solution generating device of the present invention comprises: A solution generation device that finds solutions to problems using a language model, comprising: an input unit for inputting a problem and a plurality of combinations of technical elements for solving the problem from a problem database and a technical element database; a generation unit that generates instruction information for a language model for each combination of the problem and the technical element input by the input unit, inputs the instruction information into the language model, sets a diversity parameter instructing the diversity of solutions sought by the language model in the language model, and instructs the language model to generate a sentence of the solution; an output unit that outputs a solution obtained by the language model using the problem and technical elements input by the input unit as items; Equipped with I did so. [Effects of the Invention]

[0008] According to the present invention, it is possible to generate text describing solutions even for new problems and new technical elements. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a functional block diagram showing the overall configuration of a solution generation device according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a specific hardware configuration of the solution generation device. [Figure 3] FIG. 2 is a diagram showing the data structure of assignments stored in an assignment database. [Figure 4] FIG. 2 is a diagram showing a data structure of a technology element stored in a technology element database. [Figure 5] FIG. 10 is a diagram illustrating the task selection process in the task / technology selection unit. [Figure 6] FIG. 10 is a diagram illustrating the selection process of a technology element in the problem / technology selection unit. [Figure 7] FIG. 10 is a diagram showing additional viewpoint information. [Figure 8] FIG. 10 is a diagram illustrating a diversity parameter setting process in a setting unit. [Figure 9] FIG. 10 is a diagram illustrating an example of setting values ​​of diversity parameters Temperature and Top_p. [Figure 10] 10 is a flowchart illustrating a solution document generation process executed by a generation unit. [Figure 11] FIG. 10 is a diagram showing an example of a display of a solution notified to a solution display unit. [Figure 12] FIG. 10 is a diagram showing a display example of an additional viewpoint processing area for inputting an additional viewpoint. [Figure 13] 10 is a flowchart illustrating a solution document generation process executed by a generation unit that adds an additional viewpoint and digs deeper; DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0011] FIG. 1 is a functional block diagram showing the overall configuration of a solution generation device according to an embodiment. The solution generation device is composed of a problem database 1 (problem DB), a technical element database 2 (technical element DB), an input unit 3, a generation unit 4, an output unit 5, a solution display unit 6, a setting unit 7 that sets diversity parameters 8, and a large-scale language model unit 9.

[0012] Issue Database 1, which will be described in more detail later, stores a list of issues to be resolved. Examples of issues include long-term social issues such as global warming, management issues facing the organization to which the user belongs, development issues for the services and products that the organization provides, and mid-term business plans for companies. It also includes megatrends, which are changes that have a major impact on people's lives, such as the economic impact of climate change and resource shortages.

[0013] The technology element database 2 (technology element DB) stores a list of technology elements that contribute to problem solving. Here, technology elements refer to technologies owned by users involved in the solution study, new technologies that are expected to be put into practical use in the near future, etc.

[0014] The input unit 3 is composed of a problem / technology selection unit 31, a solution selection unit 32, and an additional viewpoint input unit 33. Then, problem / technology elements that will be the basis for generating prompts for the generation AI that constitutes the large-scale language model unit 9 (described later) are selected, and these are used as input information for the generation unit 4 together with additional viewpoints for in-depth consideration.

[0015] The problem / technology selection unit 31 selects, based on user instructions, from the problems and technology elements stored in the problem database 1 and the technology element database 2, problems and technology elements to be considered in the study of solutions.

[0016] The solution selection unit 32 selects a solution to be explored from the solutions output to the solution display unit 6 by the output unit 5 based on a user instruction. Based on a user instruction, the additional viewpoint input unit 33 inputs additional viewpoints to be considered in the solution to be explored selected by the solution selection unit 32. The solution selection unit 32 and the additional viewpoint input unit 33 can be collectively called an exploration processing unit.

[0017] The generation unit 4 generates prompts (answer instruction information) that are input information to be given to the large-scale language model unit 9 based on the information input by the input unit 3. At this time, for the multiple tasks and technical elements selected by the task / technology selection unit 31, one-to-one combinations of tasks and technical elements are found, and a prompt is generated for each combination. Note that a "prompt" is used as an example of "instruction information."

[0018] Furthermore, the generation unit 4 generates a prompt from the additional perspective input by the additional perspective input unit 33 and the problem and technology corresponding to the solution for which the additional perspective was input. The generation unit 4 then inputs the generated prompt to the large-scale language model unit 9, instructs it to generate a sentence describing the solution based on the diversity parameter 8, and outputs the obtained solution to the output unit 5.

[0019] The output unit 5 notifies the solution display unit 6 of the solution text obtained from the generation unit 4 to present to the user. At this time, as will be described in detail later, the output unit 5 outputs solutions in a table format for 1:1 combinations of problems and technical elements, with the multiple problems and technical elements selected by the problem / technology selection unit 31 as items.

[0020] The solution display unit 6 displays solutions for each combination of problem and technology in a table format, and also displays the displayed solutions so that the user can select them. The solution selection unit 32 selects the solution selected by the user. The solution display unit 6 also displays a text box window for inputting an additional viewpoint using the additional viewpoint input unit 33, superimposed on the solution displayed in the table format.

[0021] The setting unit 7 has a diversity setting selection unit 71 and sets a diversity parameter 8, which is setting information for the large-scale language model unit 9. The diversity parameter 8 is a parameter indicating the diversity of the output of the large-scale language model unit 9. High diversity in the output of the large-scale language model unit 9 means that the large-scale language model unit 9 is in a state where it outputs noise and errors, but it is possible to expect the seeds of new ideas and unexpected output. For example, the diversity parameter 8 is represented by Temperature and Top_p in GPT (registered trademark, Generative Pre-trained Transformer), which is a type of large-scale language model (LLM). GPT is a registered trademark of OpenAI Opco LLC.

[0022] Although details will be described later, the diversity setting selection unit 71 of the setting unit 7 allows the user to select from a plurality of mode settings, namely, "divergence mode," "discussion mode," and "convergence mode," for the diversity (creativity) of the large-scale language model unit 9. Then, the setting unit 7 sets Temperature and Top_p according to the mode setting selected by the user, and notifies the generation unit 4 of these as diversity parameters 8.

[0023] The mode settings are not limited to the "divergence mode," "discussion mode," and "convergence mode." The diversity setting selection unit 71 selects at least two of the "divergence mode," "discussion mode," and "convergence mode."

[0024] The large-scale language model unit 9 provides the generation unit 4 with a natural-text response as a solution in response to the input of natural-text generated by the generation unit 4 from a combination of a problem and a technology or a combination of a problem, a technology, and an additional perspective. At this time, the large-scale language model unit 9 generates a sentence describing a solution with diversity corresponding to the diversity parameter 8 input from the generation unit 4.

[0025] As described above, the solution generation device of the embodiment is a solution generation device that finds solutions to problems using a large-scale language model, and includes: an input unit 3 that inputs problems and multiple combinations of technical elements that solve the problems from a problem database 1 and a technical element database 2; a generation unit 4 that generates a prompt for each combination of problem and technical element input by the input unit 3, inputs the prompt to a language model, sets a diversity parameter 8 indicative of the diversity of solutions found by the language model in the language model, and instructs the language model to generate sentences of solutions; and an output unit 5 that outputs the solutions found by the language model using the problem and technical elements input by the input unit 3 as items. The language model is generated by deep learning. Examples of the language model include a large-scale language model, a small-scale language model, and a multimodal language model.

[0026] Next, an example of a specific hardware configuration of the solution generation device will be explained with reference to FIG. Specifically, the solution generation device of the embodiment is realized by a computer 200 shown in the hardware configuration diagram of Fig. 2. The computer 200 has a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, a RAM 203, an HDD (Hard Disk Drive) 204, an input / output I / F (Interface) 205, a communication I / F 206, and a media I / F 207. The HDD 204 may be an SSD (Solid State Drive).

[0027] The CPU 201 operates based on programs stored in the ROM 202 or the HDD 204, and controls each unit of the computer 200. The ROM 202 stores a boot program executed by the CPU 201 when the computer 200 starts up, programs related to the hardware of the computer 200, and the like.

[0028] The CPU 201 controls an input device 210 such as a mouse or keyboard, and an output device 211 such as a display or printer, via an input / output I / F 205. The CPU 201 acquires data from the input device 210 via the input / output I / F 205, and outputs generated data to the output device 211. Note that a GPU (Graphics Processing Unit) or the like may be used as a processor together with the CPU 201.

[0029] The HDD 204 stores programs executed by the CPU 201 and data used by the programs. The communication I / F 206 receives data from other devices via a communication network (e.g., NW (Network) 220) and outputs the data to the CPU 201, and also transmits data generated by the CPU 201 to other devices via the communication network.

[0030] The media I / F 207 reads a program or data stored in the recording medium 212 and outputs it to the CPU 201 via the RAM 203. The CPU 201 loads a program related to a target process from the recording medium 212 onto the RAM 203 via the media I / F 207, and executes the loaded program. The recording medium 212 is an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto Optical Disk), a magnetic recording medium, a semiconductor memory, or the like.

[0031] For example, when the computer 200 or the like functions as the solution generation device of the embodiment, the CPU 201 of the computer 200 executes a program loaded on the RAM 203 to realize the functions of each processing unit of the solution generation device.

[0032] The CPU 201 reads and executes a program related to the target processing from the recording medium 212. Alternatively, the CPU 201 may read a program related to the target processing from another device via a communication network (NW 220).

[0033] In detail, the problem database 1 and the technical element database 2 are stored in the HDD 204. The solution display unit 6 is realized by the output device 211. The large-scale language model unit 9, the generation unit 4, the output unit 5, and the setting unit 7 realize their functions by the CPU 201 executing a program. Also, the input unit 3 realizes its function by the CPU 201 controlling the input device 210 and the output device 211 by executing a program.

[0034] The solution generation device may not only realize its functions by the computer 200 (information processing device) shown in FIG. 2, but also provide the functions of the solution generation device as a cloud computing service.

[0035] In more detail, a problem database 1 and a technical element database 2 are set up on the cloud, and the functions of a large-scale language model unit 9, a generation unit 4, an output unit 5, a setting unit 7, and an input unit 3 are realized by a cloud virtualization server. The output unit 5 on the cloud displays solutions on the display unit of a user terminal connected to the cloud as a solution display unit 6, and the input unit 3 and setting unit 7 on the cloud control the user terminal to make a selection.

[0036] The configuration and operation of the solution generation device will be explained in more detail below.

[0037] FIG. 3 is a diagram showing the data structure of the problem to be solved 11 recorded in the problem database 1 (FIG. 1). Task 11 consists of the task ID, the task name to be solved, and the task summary (description of the task content and trend) for each task to be solved.

[0038] Problem 11 is registered in advance in problem database 1 before a solution to the problem is found by large-scale language model unit 9. At this time, the outline of the problem may be found by inputting the name of the problem to be solved into large-scale language model unit 9. This makes it easy to register problem 11.

[0039] Figure 4 is a diagram showing the data structure of the technical elements 21 for solving problems recorded in the technical element database 2 (Figure 1). The technical elements 21 are composed of the ID, name, and summary of the technical element (description of the technical content and progress) for each technical element.

[0040] The technical elements 21 are registered in advance in the technical element database 2 before a solution to the problem is found by the large-scale language model unit 9. At this time, the outline of the technical element may be found by inputting the name of the technical element into the large-scale language model unit 9. This makes it easy to register the technical elements 21.

[0041] Figure 5 is a diagram explaining the problem selection process in the problem / technology selection unit 31 (Figure 1) of the solution generation device, and shows the problem selection information 311. The problem / technology selection unit 31 reads out the problems 11 explained in Figure 3 from the problem database 1, and for each problem to be solved registered in the problem 11, provides a selection item for setting whether or not to select the problem as a problem for which a solution is sought by the large-scale language model unit 9, and generates the problem selection information 311.

[0042] Then, the problem / technology selection unit 31 displays the problem selection information 311 shown in Fig. 5, and selects the problem for which the user has marked the selection item with an X as the problem to be solved. The generation unit 4 generates a prompt for the large-scale language model unit 9 based on the selected problem. In detail, the problem / technology selection unit 31 regards the problem to be solved corresponding to the position tapped by the user on the screen of the displayed problem selection information 311 as the selected problem, and displays an X in the selection item to indicate that it has been selected as the problem to be solved.

[0043] Fig. 6 is a diagram for explaining the selection process of technological elements in the problem / technology selection unit 31 (Fig. 1) of the solution generation device, and shows the selection information 312 of technological elements. The problem / technology selection unit 31 reads out the technological elements 21 explained in Fig. 4 from the technological element database 2, and for each technological element registered in the technological elements 21, provides a selection item for setting whether or not to select it as a technological element when the large-scale language model unit 9 finds a solution, and generates the selection information 312 of technological elements.

[0044] The problem / technology selection unit 31 then displays the technology element selection information 312 shown in Fig. 6 and selects the technology element for which the user has marked the selection item with an X as the technology element that solves the problem. The generation unit 4 generates a prompt for the large-scale language model unit 9 based on the selected technology element. In detail, the problem / technology selection unit 31 selects the technology element corresponding to the position tapped by the user on the screen of the displayed technology element selection information 312 as the selected technology element, and displays an X in the selection item to indicate that it has been selected as the technology element that solves the problem.

[0045] Figure 7 shows the additional perspective information 331 of the additional perspective input unit 33 (Figure 1) of the solution generation device. As will be described in detail later, the additional perspective input unit 33 records, as an additional perspective, an explanatory text entered by the user in a text box displayed superimposed on the solution in the solution display unit 6 in the additional perspective information 331. The generation unit 4 generates a prompt for the large-scale language model unit 9 based on the input additional information.

[0046] Fig. 8 is a diagram showing the process of setting the diversity parameters 8 in the setting unit 7 of the solution generation device. The diversity parameters should include at least a first parameter indicating the appearance probability distribution of words and a second parameter indicating the threshold of the top cumulative probability when selecting words to appear. In the following, a case will be explained in which the diversity parameters 8 are represented by Temperature and Top_p in GPT. In the following explanation, the first parameter is Temperature, the second parameter is Top_p, and words are tokens.

[0047] As shown in Figure 8, the diversity setting selection unit 71 displays mode setting buttons for "divergence mode," "discussion mode," and "convergence mode," which are diversity selection buttons with preset values ​​for the diversity parameters Temperature and Top_p, as well as a mode setting button for "custom mode," which allows the user to set any diversity parameter. It also displays the set values ​​for the diversity parameters Temperature and Top_p. In Figure 8, "divergence mode" has been selected by the user, and the set values ​​for the diversity parameters at that time, "Temperature: 1.0" and "Top_p: 1.0," are displayed.

[0048] FIG. 9 is a diagram showing an example of the set values ​​of Temperature and Top_p of the diversity parameter 8 in the mode settings of "divergence mode," "discussion mode," and "convergence mode."

[0049] Temperature is a parameter used to calculate the probability distribution when selecting tokens in sentence generation in the large-scale language model unit 9 (GPT). When the Temperature is set high, the probability of occurrence of tokens with a low probability of being selected as the next token is calculated to be high, and when the Temperature is set low, the probability of occurrence of tokens with a high probability of being selected as the next token is calculated to be high. Therefore, setting the Temperature high has the characteristic of increasing the diversity of the generated sentences. On the other hand, setting the Temperature low has the characteristic of increasing the consistency of the generated sentences, and setting the Temperature to 0 results in the token with the highest probability of being selected as the next token always being selected.

[0050] Top_p is the threshold value for the top cumulative probability when selecting tokens from the token occurrence probability distribution during sentence generation in the large-scale language model unit 9 (GPT). For example, if Top_p is set to 0.9, only tokens that make up the top 90% probability will be considered as selection candidates. Therefore, setting Top_p higher will generate a solution sentence from a wider and more diverse set of token candidates. Setting Top_p lower will generate a solution sentence from a more consistent and more confident set of token candidates.

[0051] Next, the solution document generation process executed by the generation unit 4 will be explained with reference to the flowchart of FIG. The flowchart in FIG. 10 shows the process of finding solutions for each combination of the problem to be solved selected in FIG. 4 and the technical elements selected in FIG.

[0052] In step S101, the generating unit 4 reads the diversity parameter 8 set by the setting unit . In step S102, the generation unit 4 reads the first problem among the items selected by the problem / technology selection unit 31 in the list of problems to be solved. In step S103, the generation unit 4 reads the first technological element of the item selected by the problem / technology selection unit 31 in the list of technological elements that solve the problem.

[0053] In step S104, the generation unit 4 generates a prompt to be input to the large-scale language model unit 9 from the read problem and technical elements, and notifies the large-scale language model unit 9 of the generated prompt and the read diversity parameters 8, instructing it to create a sentence describing a solution.The generation unit 4 then obtains the sentence describing the solution created by the large-scale language model unit 9 and notifies the output unit 5.

[0054] For example, the generator 4 generates the following prompt (instruction sentence): You are an expert in forced ideation in design thinking workshops. Under the following conditions, you will generate a solution to the specified "problem to be solved" using "technical elements that contribute to the solution."

[0055] Issue to be solved: Aging society Summary of the issue: The proportion of people aged 65 and over in Japan's total population was 7.1% in 1970, but will increase to 37.7% in 2050. Technological element that contributes to the solution: AI technology Technology Overview: AI technology has improved significantly with the emergence of large-scale language models that can communicate with users in natural language.

[0056] The large-scale language model unit 9 generates, for example, the following sentence in response to the above instruction, that is, the prompt starting with "You have improved..." and ending with "...": "An autonomous vehicle designed specifically for the elderly. This vehicle is equipped with AI that takes into account the specific issues faced by the elderly (decreased reaction speed, impaired eyesight, hearing, etc.) and provides safe driving support."

[0057] In step S105, the generation unit 4 checks whether the loaded technical element is the last item in the list of technical elements that solve the problem selected by the problem / technology selection unit 31. If it is the last item (Yes in S105), the process proceeds to step S107, and if it is not the last item (No in S105), the process proceeds to step S106.

[0058] In step S106, the generation unit 4 reads the next technological element in the list of technological elements that solve the problem, after the item selected by the problem / technology selection unit 31, and returns to step S104.

[0059] In step S107, the generation unit 4 checks whether the loaded problem is the last item in the list of problems to be solved selected by the problem / technology selection unit 31. If it is the last item (Yes in S107), the process ends, and if it is not the last item (No in S105), the process proceeds to step S108.

[0060] In step S108, the generation unit 4 reads the next problem in the list of problems to be solved after the item selected by the problem / technology selection unit 31, and returns to step S103.

[0061] FIG. 11 is a diagram showing an example of the display of the solution 51 that the generation unit 4 finds according to the flowchart of FIG. 10 and notifies the solution display unit 6 by the output unit 5. The solution 51 is output in a table format that can be viewed at a glance, with the horizontal axis displaying the selected problem to be solved and the vertical axis displaying the selected technical elements. Then, the text of the solution (solution) generated by the large-scale language model unit 9 by combining the selected problem to be solved and the technical elements is displayed. 11 ~Solution 33 ) is displayed. 11 will display the message described above: "An autonomous vehicle designed specifically for the elderly. This vehicle is equipped with AI that takes into account the specific problems faced by the elderly (decreased reaction speed, reduced eyesight and hearing, etc.) and provides safe driving support."

[0062] In FIG. 11, a case is described in which a solution is proposed to solve the problem to be solved using one technical element, but it is also possible to propose solutions to solve the problem to be solved using each combination of selected technical elements.

[0063] In other words, if the technological elements of "AI technology," "EV popularization," and "IoT" are selected, a solution may be proposed that combines each of the technological elements of "AI technology," "EV popularization," "IoT," "AI technology + EV popularization," "EV popularization + IoT," "IoT + AI technology," and "AI technology + EV popularization + IoT" with the problem to be solved.

[0064] The solution generation device described above makes it possible to automatically generate text describing a solution that combines the problem to be solved with technical elements that have the potential to solve that problem, and depending on the progress phase of the discussion meeting where multiple users are discussing solutions, it is possible to generate more diverse solutions, for example, when multiple ideas are being widely considered in the early stages of the discussion meeting, and to generate more consistent solutions in the later stages of the discussion meeting, thereby making it possible to propose solutions that are appropriate to the progress of the discussion.

[0065] Next, a process of digging deeper into a solution by combining a predetermined problem to be solved and a technical element will be described with reference to Fig. 12. Fig. 12 shows the solution indicated by the user as the solution to be digged deeper in the display of the solution 51 notified to the solution display unit 6 described in Fig. 11. 11 10 is a diagram showing a display example of an additional viewpoint processing area 332 for inputting an additional viewpoint regarding the object.

[0066] The additional viewpoint processing area 332 allows the user to select solutions to be explored further, for example, solutions 11 When the area is tapped, it is displayed as a pop-up window. The additional viewpoint processing area 332 is made up of a text box for inputting additional viewpoints for digging deeper into the solution, an area for displaying additional viewpoints registered in the additional viewpoint information 331, and the digged-out solution.

[0067] As will be described in detail later, the solution selection unit 32 of the input unit 3 selects a solution to be explored further from the solutions output by the output unit 5 to the solution display unit 6 based on a user instruction. Then, the issues and technical elements corresponding to the selected solution are determined. The additional perspective input unit 33 of the input unit 3 displays an additional perspective processing area 332 and inputs additional perspectives to be considered in the solution to be explored further that is selected by the solution selection unit 32. The additional perspective input unit 33 additionally registers the input additional perspective in the additional perspective information 331.

[0068] The generation unit 4 then generates a prompt to be input to the large-scale language model unit 9 from the problem and technical elements corresponding to the solution selected by the solution selection unit 32 and the additional perspective input by the additional perspective input unit 33, and notifies the large-scale language model unit 9 of the generated prompt to instruct it to create a sentence describing the solution. The generation unit 4 then acquires the sentence describing the in-depth solution created by the large-scale language model unit 9 and notifies the output unit 5. The output unit 5 displays the notified sentence as an "in-depth solution" in the additional perspective processing area 332.

[0069] Next, the solution document generation process executed by the generator 4 for digging deeper by adding additional viewpoints will be explained with reference to the flowchart of FIG. In step S131, the generating unit 4 reads the diversity parameter 8 set by the setting unit .

[0070] In step S132, the generation unit 4 causes the solution selection unit 32 to select, from the solutions 51 in the solution display unit 6, the solution designated by the user as the solution to be explored in depth. In step S133, the generation unit 4 refers to the additional viewpoint information 331 (FIG. 7) and reads from the additional viewpoint information 331 the additional viewpoint input by the additional viewpoint input unit 33 into the additional viewpoint processing area 332 described with reference to FIG.

[0071] In step S134, the generation unit 4 reads the problem corresponding to the solution to be explored selected by the solution selection unit 32. In step S135, the generation unit 4 reads the technical elements corresponding to the solution to be explored selected by the solution selection unit 32.

[0072] In step S136, the generation unit 4 generates a prompt to be input to the large-scale language model unit 9 from the additional perspective read in step S133, the problem read in step S134, and the technical elements read in step S135, and notifies the large-scale language model unit 9 of the generated prompt and the read diversity parameters 8, instructing it to create a sentence describing a solution.The generation unit 4 then obtains the sentence describing the solution created by the large-scale language model unit 9, and displays it as an "in-depth solution" in the additional perspective processing area 332.

[0073] For example, the generator 4 generates the following prompt (instruction sentence): You are an expert in forced ideation in design thinking workshops. You have generated a "solution" for a given "problem to be solved" using "technical elements that contribute to the solution." Using "additional perspectives" added by the user, you are asked to propose a new, more advanced "solution."

[0074] Issue to be solved: Aging society Summary of the issue: The proportion of people aged 65 and over in Japan's total population was 7.1% in 1970, but will increase to 37.7% in 2050. Technological element that contributes to the solution: AI technology Technology Overview: AI technology has improved significantly with the emergence of large-scale language models that can communicate with users in natural language. Solution: A self-driving car specifically designed for the elderly. This car is equipped with AI that takes into account the specific challenges faced by the elderly (slower reaction times, impaired eyesight, hearing, etc.) and provides safe driving support. Additional perspective 1: Targeting the automotive industry. Additional point 2: Support functions will be configured by obtaining individual user problems (such as vision, hearing, and muscle weakness) from the hospital database. Security technology will be applied to connections with external databases.

[0075] The large-scale language model unit 9 generates, for example, the following sentence in response to the above directive. Development of an individually tailored self-driving car using AI technology. This car will obtain individual problems such as poor eyesight, hearing, or muscle strength from a hospital database and provide driving support based on that. For example, for a user with poor eyesight, the vehicle will recognize the surrounding situation and provide driving information via voice. For a user with poor muscle strength, the vehicle will provide support tailored to the user's condition, such as automatically performing driving operations. This system will provide new business opportunities for the automotive industry and solve mobility problems in an aging society. Furthermore, the latest security technology will be applied to the handling of personal information, and privacy will be thoroughly protected.

[0076] In this way, the user can select a solution they want to develop from the text describing the solutions generated by the solution generation device, add perspectives to consider, and regenerate the solution, allowing the user to improve the solution through confirmation and addition of perspectives, thereby realizing the brushing up of solutions through collaboration between large-scale language models (generative AI) and humans.

[0077] Furthermore, the present invention is not limited to the above-described embodiments, and includes various modifications. The above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. [Explanation of symbols]

[0078] 1. Issue database 2. Technology Element Database 3 Input section 31 Issues and Technology Selection Department 32 Solution Selection Section 33 Additional viewpoint input section 4 Generation part 5 Output section 6 Solution display area 7. Settings 71 Diversity setting selection section 8 Diversity parameters 9 Large-scale language model section

Claims

1. A solution generation device that finds solutions to problems using a language model, comprising: an input unit for inputting a problem and a plurality of combinations of technical elements for solving the problem from a problem database and a technical element database; a generation unit that generates instruction information for a language model for each combination of the problem and the technical element input by the input unit, inputs the instruction information into the language model, sets a diversity parameter instructing the diversity of solutions sought by the language model in the language model, and instructs the language model to generate a sentence of the solution; an output unit that outputs a solution obtained by the language model using the problem and technical elements input by the input unit as items; A solution generator comprising:

2. 2. The solution generator of claim 1, The diversity parameter is a first parameter indicating a word occurrence probability distribution; a second parameter indicating a threshold value of a top cumulative probability for selecting words to appear; Solution generator.

3. 3. The solution generator according to claim 2, The first parameter is a temperature that indicates a probability distribution of token appearances, The second parameter is Top_p, which indicates a threshold value of the top cumulative probability when selecting a token to appear. Solution generator.

4. 2. The solution generator of claim 1, a setting unit that sets the diversity parameters in accordance with a plurality of preset diversity mode settings; Solution generator.

5. 5. The solution generator according to claim 4, The mode is: Includes mode settings for divergence mode, discussion mode, and convergence mode; When the divergence mode is input, the setting unit sets the first parameter value and the second parameter value to be higher than the first parameter value and the second parameter value in the discussion mode, When the discussion mode is entered, the setting unit sets the first parameter value and the second parameter value to be higher than the first parameter value and the second parameter value in the convergence mode. Solution generator.

6. 2. The solution generator of claim 1, a solution selection unit that selects a solution to be explored; an additional viewpoint input unit for inputting an additional viewpoint when digging deeper; The generation unit generating instruction information for the language model from the problem and technical elements corresponding to the solution selected by the solution selection unit and the additional viewpoint input by the additional viewpoint input unit, inputting the instruction information to the language model, and setting a diversity parameter in the language model to instruct the language model to generate a sentence of the solution; The output unit The language model outputs the problem, technical elements, and solutions obtained from additional perspectives. Solution generator.

7. 2. The solution generator of claim 1, The output unit outputting said solutions in a tabular format; Solution generator.

8. 2. The solution generator of claim 1, The instruction information is a prompt. Solution generator.

9. A solution generation method for finding a solution to a problem using a language model, comprising: inputting a plurality of combinations of problems and technical elements that solve the problems from a problem database and a technical element database; generating instruction information for a language model for each combination of an input problem and a technical element; a step of setting the instruction information and a diversity parameter indicating the diversity of solutions sought by the language model in the language model, and instructing the language model to generate sentences of solutions; a step of outputting a solution obtained by the language model using the problem and the technical element as items; Solution generation methods, including:

10. The solution generation method according to claim 9, further comprising: Selecting a solution to explore further; A step of inputting additional perspectives when digging deeper; A step of reading the problem and technical elements corresponding to the selected in-depth solution; generating instruction information for the language model from the read problem and technical elements and the input additional viewpoint; a step of setting the instruction information and a diversity parameter indicating the diversity of solutions sought by the language model in the language model, and instructing the language model to generate sentences of solutions; outputting the solution obtained by the language model as an in-depth solution; Solution generation methods, including:

Images