Questionnaire creation assistance device, questionnaire creation assistance method, and recording medium
The question creation support device uses a generative model to identify and generate questions that accurately reflect survey respondents' needs, addressing the inefficiencies in existing systems and enhancing policy formulation.
Patent Information
- Application Number
- PCT/JP2025/001509
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-02-15
- Filing Date
- 2025-01-20
- Publication Date
- 2025-08-21
AI Technical Summary
Existing technologies lack the ability to efficiently create questions that accurately grasp the needs of survey respondents, requiring high skill and time, and existing systems do not adequately support the creation of high-quality questions for formulating effective policies.
A question creation support device utilizing a generative model, such as a Generative Pre-trained Transformer (GPT), to identify elements requiring investigation and generate questions based on user input, adjusting elements according to regional and department characteristics, and presenting questions to users for survey creation.
Enables efficient and accurate creation of questions that can more accurately grasp the needs of survey subjects, supporting the formulation of effective policies by understanding survey respondents' needs.
Smart Images

Figure JP2025001509_21082025_PF_FP_ABST
Abstract
Description
Question creation support device, question creation support method, and recording medium
[0001] The present invention relates to a question creation support device, a question creation support method, and a question creation support program.
[0002] Government agencies and other organizations create questions (questionnaires) to survey the needs of citizens and businesses, and use the responses to those questions from citizens and businesses to formulate measures (policies). Therefore, there is a need for technology that can support the efficient creation of such questions.
[0003] In relation to the above-mentioned technology, Patent Literature 1 discloses a survey system including a survey server with functions for operating, processing, storing, displaying, and managing all survey operations. This system includes a survey administrator terminal that can connect to the survey server via the Internet and that can create survey content and check survey results under the management of a survey administrator. This system also includes display means that can connect to the survey server via the Internet and retrieve and display survey content stored on the survey server, as well as means for inputting answers according to the survey content. This system also includes at least one survey terminal installed in a store, counter, service center, etc., where an unspecified number of users can easily participate.
[0004] JP 2009-015586 A
[0005] In order for government agencies and other organizations to formulate more effective policies, they need to more accurately understand the needs of citizens, businesses, and the like. To achieve this, it is important to include in the questions all of the things (elements) that should be asked of survey respondents regarding social issues and other problems, and to create questions in a way that is easy for survey respondents to understand. However, creating such high-quality questions requires high skill and is time-consuming. In other words, the challenge is to provide support for efficiently creating questions that can more accurately grasp the needs of survey respondents. The technology disclosed in Patent Document 1 cannot be said to be sufficient to solve this problem.
[0006] A primary object of the present invention is to support the efficient creation of questions that can more accurately grasp the needs of survey subjects.
[0007] A question creation support device according to one embodiment of the present invention comprises an element answer instruction means for inputting information representing a problem and element answer instruction information instructing a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model; a generation means for receiving information instructing a user to make adjustments to the elements answered from the first generation model and generating element information representing the adjusted elements; a question generation instruction means for inputting the element information and question generation instruction information instructing a user to generate questions for survey subjects regarding the element information into a second generation model; and a presentation means for presenting the questions generated by the second generation model to a user.
[0008] In another aspect of achieving the above object, a question creation support method according to one embodiment of the present invention includes, using an information processing device, inputting information representing a problem and element answer instruction information instructing a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model, accepting information instructing a user to make adjustments to the elements answered from the first generation model, generating element information representing the adjusted elements, inputting the element information and question generation instruction information instructing a user to generate questions for the survey subjects regarding the element information into a second generation model, and presenting the questions generated by the second generation model to a user.
[0009] In addition, in a further aspect of achieving the above-mentioned object, a question creation support program according to one embodiment of the present invention causes a computer to execute the following steps: an element answer instruction process that inputs information representing a problem and element answer instruction information that instructs a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model; a generation process that accepts information instructing a user to make adjustments to the elements answered from the first generation model and generates element information representing the adjusted elements; a question generation instruction process that inputs the element information and question generation instruction information that instructs a user to generate questions for survey subjects regarding the element information into a second generation model; and a presentation process that presents the questions generated by the second generation model to a user.
[0010] Furthermore, the present invention can also be realized by a computer-readable, non-volatile recording medium on which such a question creation support program (computer program) is stored.
[0011] The present invention can assist in efficiently creating questions that can more accurately grasp the needs of survey subjects.
[0012] 1 is a block diagram showing the configurations of question creation support devices 10 and 10A according to the present disclosure.
[0033] FIG. 1 is a diagram showing an example of assignment information 161, element answer instruction information 162, and regional characteristic information 163 input to a generation model 20 by a question creation support device 10 according to the present disclosure, and an answer element 166 from the generation model.
[0034] FIG. 1 is a diagram showing an example of element information 167 and question generation instruction information 168 input to a generation model 20 by a question creation support device 10 according to the present disclosure, and a question 169 generated by the generation model.
[0035] FIG. 1 is a flowchart showing the operation of a question creation support device 10 according to the present disclosure.
[0036] FIG. 1 is a diagram showing an example of assignment information 161 and element answer instruction information 162A input to a generation model 20 by a question creation support device 10A according to the present disclosure, and an answer element 166A from the generation model.
[0037] FIG. 1 is a diagram showing an example of element information 167 and question generation instruction information 168 input to a generation model 20 by a question creation support device 10A according to the present disclosure, regional characteristic information 163, and a question 169 generated by the generation model 20. Fig. 1 is a diagram showing an example of an input screen for element information 167 and question generation instruction information 168 displayed on a display screen 31 by a question creation support device 10A according to the present disclosure. Fig. 2 is a flowchart showing the operation of a question creation support device 10A according to the present disclosure. Fig. 3 is a block diagram showing the configuration of a question creation support device 40 according to the present disclosure. Fig. 4 is a flowchart showing the operation of a question creation support device 40 according to the present disclosure. Fig. 5 is a block diagram showing the configuration of an information processing device 900 that can realize a question creation support device according to the present disclosure.
[0013] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
[0014] 1 is a block diagram showing the configuration of a question creation support device 10 according to the present disclosure. The question creation support device 10 is a device that supports the creation of questions (questionnaires) that can more accurately grasp the needs of survey subjects, such as citizens and companies, in order to formulate effective measures to address issues in, for example, government agencies. Furthermore, at least a part of the question creation support device 10 may be a system built using cloud computing.
[0015] The question generation support device 10 is communicably connected to the generative model 20 and the terminal device 30 via a communication network such as the Internet.
[0016] The terminal device 30 is an information processing device such as a personal computer, a smartphone, or a tablet terminal, and is equipped with a display screen 31. The terminal device 30 inputs information input by a user through an input operation to the question creation support device 10, and displays information output from the question creation support device 10 on the display screen 31.
[0017] The generative model 20 is a learning model that constitutes generative AI (Artificial Intelligence) and is operated by an information processing device (not shown). The generative model 20 outputs an answer to an answer request input from the question creation support device 10 to the question creation support device 10. The generative model 20 may be included in the question creation support device 10.
[0018] Here we explain generative models in more detail. A generative model is an information analysis program that is trained, typically through machine learning or deep learning, to contextualize input data and produce output data that corresponds to the context of the input data.
[0019] More specifically, a generative model is a model (such as a large-scale language model) that learns the relationships between words in a sentence (including letters, symbols, and numbers) and the relationships between elements shown in a diagram or table, and generates related strings related to a target string from the target string. By using a generative model that has been trained on sentences and paragraphs from various contexts, it is possible to generate related strings with appropriate content related to the target string.
[0020] For example, a case where a generative model is used in question answering will be described. The generative model receives an input question such as "What kind of country is Japan?" as a target string. The generative model generates a string such as "Japan is an island country in the Northern Hemisphere..." as an answer to the question.
[0021] The method of training the generative model is not particularly limited, but as an example, the generative model may be trained to output at least one sentence that includes an input string.
[0022] As a specific example, a generative model is a Generative Pre-trained Transformer (GPT), which outputs a sentence containing an input string by predicting a string that is likely to follow the input string. Other generative models include a Text-to-Text Transfer Transformer (T5), a Bidirectional Encoder Representations from Transformers (BERT), a Robustly optimized BERT approach (RoBERTa), and an Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA).
[0023] Furthermore, the character strings generated by the generative model are not limited to natural languages. For example, the generative model may output an artificial language (such as program source code) in response to a character string input in a natural language. For example, the generative model may receive an input question such as, "How do I retrieve data containing a specific character string from a database?" as a target character string. The generative model may output program source code for performing database processing. Alternatively, the generative model may output a natural language corresponding to a character string input in an artificial language.
[0024] Furthermore, the content generated by a generative model is not limited to character strings. For example, the generative model may generate image data, video data, audio data, or other data formats corresponding to the input data.
[0025] The question creation support device 10 includes an element answer instruction unit 11, a generation unit 12, a question generation instruction unit 13, a presentation unit 14, an input / output control unit 15, and a memory unit 16. The element answer instruction unit 11, the generation unit 12, the question generation instruction unit 13, the presentation unit 14, and the input / output control unit 15 are examples of element answer instruction means, generation means, question generation instruction means, presentation means, and input / output control means, respectively.
[0026] The storage unit 16 is, for example, a storage device such as a RAM (Random Access Memory) 903 or a hard disk 904, which will be described later with reference to Fig. 11. The storage unit 16 stores assignment information 161, element answer instruction information 162, regional characteristic information 163, department characteristic information 164, priority information 165, answer elements 166 from the generation model, element information 167, question generation instruction information 168, and questions 169. Details of the above-mentioned information stored in the storage unit 16 will be described later.
[0027] The input / output control unit 15 receives information input by a user via an input operation on the terminal device 30 from the terminal device 30, and transmits information output from the question creation support device 10 to the terminal device 30. The input / output control unit 15 accepts the assignment information 161, the element answer instruction information 162, the area characteristic information 163, and the department characteristic information 164 from the terminal device 30, and stores the accepted information in the storage unit 16. The input / output control unit 15 may also accept information from the terminal device 30 instructing the acquisition of the assignment information 161, the element answer instruction information 162, the area characteristic information 163, and the department characteristic information 164 from an external device (not shown), and may acquire the assignment information 161, the element answer instruction information 162, the area characteristic information 163, and the department characteristic information 164 from the external device in accordance with the accepted information.
[0028] The issue information 161 is information that represents an issue, such as a social problem, that needs to be solved, and is created by a user, such as an employee of an administrative agency. The element answer instruction information 162 is information that instructs the generative model 20 to answer elements (items) related to the issue that are estimated to require investigation in order to solve the issue. The element answer instruction information 162 may include, for example, a prompt that instructs the generative model 20 to answer. The area characteristic information 163 is information that represents the characteristics of the area that has the issue and is the subject of investigation. The department characteristic information 164 is information that represents the characteristics of a department (organization) in, for example, an administrative agency that is responsible for solving the issue.
[0029] The element answer instruction unit 11 inputs task information 161 and element answer instruction information 162 to the generation model 20 in accordance with information instructing the operation of the question creation support device 10 input through an input operation by a user on the terminal device 30. The element answer instruction unit 11 also inputs at least one of regional characteristic information 163 and department characteristic information 164 to the generation model 20.
[0030] The generative model 20 generates an answer in accordance with the assignment information 161, element answer instruction information 162, regional characteristic information 163, and department characteristic information 164 input from the element answer instruction unit 11, and outputs the answer as an answer element 166 from the generative model. The answer element 166 from the generative model output from the generative model 20 is accepted by the input / output control unit 15, and the input / output control unit 15 stores the accepted answer element 166 from the generative model in the memory unit 16.
[0031] 2 is a diagram illustrating an example of task information 161, element answer instruction information 162, and regional characteristic information 163 input to the generation model 20 by the question creation support device 10 according to the present disclosure, and an example of answer elements 166 from the generation model. Note that in the example shown in FIG. 2, it is assumed that department characteristic information 164 is not input to the generation model 20.
[0032] 2 , the issue information 161 represents an issue (objective variable) of creating an attractive city for young people. The element answer instruction information 162 represents an answer regarding elements that need to be investigated in order to solve the issue represented by the issue information 161, and an answer regarding elements that are inconsistent with the regional characteristic information 163 (inconsistent elements). The regional characteristic information 163 represents the geographical conditions of the local government A, which is the subject of this survey, such as being located inland (i.e., having no coastline) and having a warm climate with an average annual temperature of 15°C and an average summer temperature of 29°C.
[0033] In the example shown in FIG. 2 , the answer elements 166 from the generative model represent six elements: (1) reasonable prices / rent, (2) availability of shopping centers / malls, (3) stable income, (4) career advancement, (5) abundant entertainment facilities, and (6) local events. For ease of explanation, two elements, (7) abundant winter sports environment and (8) attractive beaches, are listed as elements included in the answer elements 166 from the generative model. However, these elements are not actually output from the generative model 20 as elements included in the answer elements 166 from the generative model. This is because the element (7) abundant winter sports environment is inconsistent with the characteristic of a warm climate indicated by the regional characteristic information 163, and the element (8) attractive beaches is inconsistent with the characteristic of being located inland (no beach) indicated by the regional characteristic information 163. If the regional characteristic information 163 differs from the content shown in FIG. 2 , the answer elements 166 from the generative model may include the elements (7) abundant winter sports environment and (8) attractive beaches.
[0034] In addition, when department characteristic information 164 is input into the generation model 20 and the department characteristic information 164 indicates that the department responsible for solving the problem is not responsible for work related to entertainment facilities and local events, the generation model 20 excludes two elements, (5) improvement of entertainment facilities and (6) local events, from the elements included in the answer elements 166 from the generation model.
[0035] Furthermore, the area characteristic information 163 and the department characteristic information 164 may include priority information 165 that indicates the priority of investigation for each of a plurality of elements related to the area or department.
[0036] For example, the regional characteristic information 163 indicates that priority is given to the provision of shopping centers / malls and entertainment facilities by taking advantage of the region's characteristics as a tourist destination, and the element answer instruction information 162 indicates that the priority of elements is determined according to the priority criteria indicated by the regional characteristic information 163. In this case, the generative model 20 outputs answer elements 166 from the generative model that include increasing the priority of elements (2) the presence or absence of shopping centers / malls and (5) the provision of entertainment facilities in the example shown in Fig. 2. Furthermore, if the element answer instruction information 162 includes the provision of answering a predetermined number of elements starting from the element with the highest priority, the generative model 20 outputs answer elements 166 from the generative model that include only the predetermined number of elements (i.e., does not include elements with low priority).
[0037] Similarly, for example, the department characteristic information 164 indicates that the main task of the department is to implement measures to economically stabilize the lives of residents, and the element answer instruction information 162 indicates that the priority of elements is determined according to the priority criteria indicated by the department characteristic information 164. In this case, the generative model 20 outputs answer elements 166 from the generative model, including increasing the priority of elements (1) reasonable prices / rent and (4) stable income, in the example shown in FIG.
[0038] The generation unit 12 receives, from the terminal device 30 via the input / output control unit 15, information instructing adjustment of the answer element 166 from the generative model returned from the generative model 20, and generates element information 167 representing the adjusted element. The generation unit 12 stores the generated element information 167 in the storage unit 16.
[0039] The question generation instruction unit 13 inputs, to the generation model 20, the element information 167 generated by the generation unit 12 and question generation instruction information 168 that instructs the generation of questions for the survey subjects regarding the element information 167. However, the question generation instruction information 168 is input by a user's input operation on the terminal device 30, and is received from the terminal device 30 via the input / output control unit 15.
[0040] The generative model 20 generates an answer in accordance with the element information 167 and question generation instruction information 168 input from the question generation instruction unit 13 , and outputs the answer as a question 169 .
[0041] The presentation unit 14 presents the question 169 generated by the generative model 20 to the user by displaying it on the display screen 31 of the terminal device 30 via the input / output control unit 15 .
[0042] Figure 3 is a diagram showing an example of element information 167 and question generation instruction information 168 input to the generation model 20 by the question creation support device 10 of the present disclosure, and a question 169 output from the generation model 20.
[0043] In the example shown in Figure 3, the element information 167 includes six elements included in the answer elements 166 from the generative model illustrated in Figure 2, namely (1) reasonable prices / rent, (2) presence / absence of shopping centers / malls, (3) stable income, (4) career advancement, (5) abundant entertainment facilities, and (6) local events, as well as a new element, (9) abundant learning environment. This new element, (9) abundant learning environment, was added by a user who confirmed the answer elements 166 from the generative model and, based on his or her knowledge, as an element that needs to be investigated to solve the problem of creating an attractive city for young people. The new element, (9) abundant learning environment, is added to the element information 167 by the generation unit 12 in response to an instruction from the user. Furthermore, the question generation instruction information 168 indicates the generation of questions for a youth awareness survey regarding the elements indicated by the element information 167.
[0044] In the example shown in FIG. 3 , the questions 169 generated by the generative model 20 include questions such as, "Do you think current prices and rents are appropriate?" for the element (1) appropriate prices / rent. Question 169 includes questions such as, "Do you feel inconvenienced when purchasing daily necessities and food?" for the element (2) presence / absence of shopping centers / malls. Question 169 includes questions such as, "Are you satisfied with your current income?" for the element (3) stable income. Question 169 includes questions such as, "Are you provided with sufficient opportunities for career advancement?" for the element (4) career advancement. Question 169 includes questions such as, "Do you frequently use entertainment facilities?" for the item (5) abundance of entertainment facilities. Question 169 includes questions such as, "Do you want to actively participate in local events?" for the item (6) local events. Question 169 includes questions such as, "Do you think the learning environment is abundant?" for the element (6) abundance of learning environment.
[0045] When the question generation instruction information 168 includes information specifying the number of questions to be generated for each element, the generation model 20 generates the specified number of questions for each element in accordance with the question generation instruction information 168. When the element information 167 includes the priority of each element described above, and the question generation instruction information 168 includes information specifying the total number of questions to be generated, the generation model 20 generates a larger number of questions for an element with a higher priority, for example.
[0046] Next, the operation (processing) of the question creation support device 10 according to the present disclosure will be described in detail with reference to the flowchart of FIG.
[0047] The input / output control unit 15 receives the assignment information 161, element answer instruction information 162, and area characteristic information 163 from the terminal device 30, and stores the received assignment information 161, element answer instruction information 162, and area characteristic information 163 in the storage unit 16 (step S101). The element answer instruction unit 11 inputs the received assignment information 161, element answer instruction information 162, and area characteristic information 163 to the generative model 20 (step S102).
[0048] The generation unit 12 acquires the answer element 166 from the generative model 20 via the input / output control unit 15 (step S103). The generation unit 12 displays the answer element 166 from the generative model on the display screen 31 of the terminal device 30 via the input / output control unit 15 (step S104).
[0049] If the terminal device 30 does not receive information instructing adjustment of the answer element 166 from the generative model (No in step S105), the process proceeds to step S107. If the terminal device 30 receives information instructing adjustment of the answer element 166 from the generative model (Yes in step S105), the generator 12 adjusts the answer element 166 from the generative model in accordance with the received information (step S106). The generator 12 generates element information 167 from the answer element 166 from the generative model (step S107).
[0050] The question generation instruction unit 13 inputs the element information 167 and the question generation instruction information 168 received from the terminal device 30 to the generative model 20 (step S108). The presentation unit 14 displays the question 169 generated by the generative model 20 on the display screen 31 of the terminal device 30 via the input / output control unit 15 (step S109), and the entire process ends.
[0051] The question creation support device 10 according to the present disclosure can support the efficient creation of questions that can more accurately grasp the needs of survey subjects. This is because the question creation support device 10 obtains the questions 169 by having the generative model 20 answer elements that are estimated to need to be investigated to solve a problem, allowing the user to adjust the elements indicated by the answers, and then instructing the generative model 20 to generate questions 169 for the survey subjects regarding the adjusted elements.
[0052] The effects achieved by the question creation support device 10 according to the present disclosure will be described in detail below.
[0053] In order for government agencies and other organizations to formulate more effective policies, they need to more accurately understand the needs of citizens, businesses, and other stakeholders. To do this, it is important to include in the questions all the elements that should be asked of survey respondents regarding social issues and other problems, and to create questions written in a way that is easy for survey respondents to understand. However, creating such high-quality questions requires a high level of skill and is time-consuming. In other words, the challenge is to provide support for efficiently creating questions that can more accurately grasp the needs of survey respondents.
[0054] For such a problem, the question creation support device 10 according to the present disclosure inputs problem information 161 representing the problem and element answer instruction information 162 instructing the user to answer elements that are estimated to require investigation in order to solve the problem to the generative model 20. The question creation support device 10 receives information instructing the user to adjust an answer element 166 from the generative model answered by the generative model 20, and generates element information 167 representing the adjusted element. The question creation support device 10 inputs the element information 167 and question generation instruction information 168 instructing the user to generate a question for the survey subject regarding the element information 167 to the generative model 20. The question creation support device 10 then presents the question generated by the generative model 20 to the user. In other words, the question creation support device 10 uses the generation model 20 in two stages: the stage of identifying elements that are estimated to need to be investigated to solve the problem, and the stage of generating questions 169 using element information 167 in which the user's knowledge is added to the identified elements, and therefore can support the efficient creation of questions that can more accurately grasp the needs of the survey subjects.
[0055] The question creation support device 10 described above uses the same generative model 20 in the two stages described above, but may use, for example, a first generative model in the stage of identifying elements that are estimated to need to be investigated to solve the problem, and a second generative model different from the first generative model in the stage of generating questions 169 using the element information 167. In this case, the first generative model may be a small-scale generative model trained exclusively for identifying elements from a problem, and the second generative model may be a small-scale generative model trained exclusively for generating questions from elements.
[0056] Furthermore, the question creation support device 10 according to the present disclosure inputs at least one of regional characteristic information 163 representing the characteristics of the region having the problem and department characteristic information 164 representing the characteristics of the department responsible for solving the problem to the generative model 20. Then, the question creation support device 10 inputs element answer instruction information 162 representing an instruction to exclude elements that do not match at least one of the regional characteristic information 163 and the department characteristic information 164 to the generative model. In this way, the question creation support device 10 can support the more efficient creation of questions based on the characteristics of the region having the problem and the characteristics of the department responsible for solving the problem.
[0057] Furthermore, in the question creation support device 10 according to the present disclosure, the region characteristic information 163 and the department characteristic information 164 include information indicating the priority of a survey for each of a plurality of elements related to a region or a department. The element answer instruction information 162 indicates instructions to answer elements according to the priority. This allows the question creation support device 10 to generate questions 169 based on the priority of the elements, thereby supporting the efficient creation of questions that are in line with the activity policies of administrative agencies and the like that have set priorities.
[0058] Second Embodiment Next, a question creation support device 10A according to the present disclosure will be described. The configuration of the question creation support device 10A is similar to that of the above-described question creation support device 10, and therefore will be described with reference to the block diagram shown in FIG.
[0059] In the question creation support device 10A, components that have the same functions as those in the question creation support device 10 are assigned the same numbers as those in the question creation support device 10, and detailed descriptions thereof will be omitted. Note that components in the question creation support device 10A that have functions different from those in the question creation support device 10 are assigned numbers with "A" added to the end of the numbers assigned in the question creation support device 10.
[0060] In the question creation support device 10, when identifying elements that are estimated to require investigation in order to solve a problem, at least one of the regional characteristic information 163 and the department characteristic information 164 is input to the generative model 20. In contrast, the question creation support device 10A has a different configuration from the question creation support device 10 in that it adjusts elements answered from the generative model 20 using at least one of the regional characteristic information 163 and the department characteristic information 164 without using at least one of the regional characteristic information 163 and the department characteristic information 164.
[0061] The question creation support device 10A includes an element answer instruction unit 11A, a generation unit 12A, a question generation instruction unit 13, a presentation unit 14, an input / output control unit 15A, and a memory unit 16. The element answer instruction unit 11A, the generation unit 12A, the question generation instruction unit 13, the presentation unit 14, and the input / output control unit 15A are examples of element answer instruction means, generation means, question generation instruction means, presentation means, and input / output control means, respectively.
[0062] FIG. 5 is a diagram showing an example of assignment information 161 and element answer instruction information 162 input to the generative model 20 by the question creation support device 10A according to the present disclosure, and an example of an answer element 166A from the generative model.
[0063] 5, the element answer instruction information 162A indicates that an element that needs to be investigated is to be answered in order to solve the problem indicated by the problem information 161. In the question creation support device 10A, the regional characteristic information 163 is not input to the generative model 20 when identifying elements that are estimated to need to be investigated in order to solve the problem. Therefore, the element answer instruction information 162A does not include excluding from the answer elements that are inconsistent with the regional characteristic information 163 (inconsistent elements) and that are included in the element answer instruction information 162 illustrated in FIG.
[0064] The element answer instruction unit 11A inputs task information 161 and element answer instruction information 162A into the generation model 20 in accordance with information instructing the operation of the question creation support device 10 input via input operations by the user on the terminal device 30.
[0065] In the example shown in Figure 5, since regional characteristic information 163 is not input into the generative model 20, the answer element 166A from the generative model includes two elements: (7) a rich winter sports environment and (8) an attractive beach, which are not included in the answer element 166 from the generative model illustrated in Figure 2.
[0066] Figure 6 is a diagram showing an example of element information 167 and question generation instruction information 168 input to the generation model 20 by the question creation support device 10A of the present disclosure, regional characteristic information 163, and a question 169 output from the generation model 20.
[0067] The generation unit 12A receives information instructing the exclusion of inconsistent elements, which are elements answered from the generation model 20 and are inconsistent with at least one of the regional characteristic information 163 and the department characteristic information 164, from the element information 167, and excludes the inconsistent elements from the element information 167. For example, the generation unit 12A generates element information 167 by deleting two elements, (7) Good winter sports environment and (8) Attractive beaches, which are inconsistent with the regional characteristic information 163 illustrated in FIG. 6, from the elements included in the answer element 166A from the generation model illustrated in FIG. 5.
[0068] FIG. 7 is a diagram illustrating an example of an input screen for element information 167 and question generation instruction information 168 that is displayed on the display screen 31 by the question generation support device 10A according to the present disclosure.
[0069] The generation unit 12A presents to the user, via the input / output control unit 15A, a first element from the answer element 166A derived from the generation model that is inconsistent with at least one of the regional characteristic information 163 and the department characteristic information 164, in a display mode different from that of the second elements excluding the first element. More specifically, as illustrated in FIG. 7 , the generation unit 12A displays the two first elements, (7) a good winter sports environment and (8) an attractive beach, without check marks on the display screen 31. The generation unit 12A then displays the six second elements, (1) reasonable prices / rent, (2) availability of shopping centers / malls, (3) stable income, (4) career advancement, (5) good entertainment facilities, and (6) local events, with check marks on the display screen 31. When the user selects the "Automatic Questionnaire Creation" button on the screen shown in Fig. 7, the generation unit 12A generates element information 167 that includes the six second elements described above but does not include the two first elements. The question generation instruction unit 13 then inputs the generated element information 167 to the generation model 20, and obtains a question 169 such as that shown in Fig. 6 from the generation model 20 via the input / output control unit 15A.
[0070] The generation unit 12A may also receive, via the input / output control unit 15A, information instructing inclusion of one or more of the first elements described above in the element information 167, and generate element information 167 including the first elements instructed to be included in the element information 167. More specifically, the input / output control unit 15A receives information instructing instructing inclusion or exclusion of individual elements, input through an input operation by the user on the display screen 31 illustrated in FIG. 7 . For example, when the user checks the element (7) "Enhancement of Winter Sports Environment" on the display screen 31 illustrated in FIG. 7 , the generation unit 12A generates element information 167 including the element (7) "Enhancement of Winter Sports Environment" in addition to the six second elements described above. Furthermore, when the user unchecks the element (6) "Local Events" on the display screen 31 illustrated in FIG. 7 , the generation unit 12A generates element information 167 that does not include the element (6) "Local Events."
[0071] The generation unit 12A may also prevent a first element, among the answer elements 166A from the generation model, that is inconsistent with at least one of the regional characteristic information 163 and the department characteristic information 164, from being displayed on the display screen 31. In the example shown in Fig. 7, the question creation support device 10A can switch between a mode in which the first element is displayed on the display screen 31 and a mode in which it is not displayed, by turning on and off "display non-recommended items."
[0072] When the user selects the "Add Element" button on the display screen 31 illustrated in Fig. 7, the input / output control unit 15A receives information indicating the element to be added, input through an input operation by the user. For example, when the input / output control unit 15A receives information indicating that the element (9) "Enhancement of the Learning Environment" illustrated in Fig. 6 is to be added, the generation unit 12A generates element information 167 including the element (9) "Enhancement of the Learning Environment."
[0073] The question generation instruction unit 13 may generate question generation instruction information 168 indicating that a number of questions 169 equal to or smaller than the input maximum number is to be generated via the input / output control unit 15A, which allows the user to input the maximum number of questions 169 to be generated by the generation model 20. For example, in the case of the display screen 31 illustrated in Fig. 7 , the input / output control unit 15A receives, via an input operation by the user, information indicating that the maximum number of questions 169 to be generated is 30, and the question generation instruction unit 13 generates question generation instruction information 168 indicating that 30 or fewer questions 169 are to be generated.
[0074] The configuration and form of the input screen for the element information 167 and the question generation instruction information 168 that the question creation support device 10A displays on the display screen 31 are not limited to the configuration and form exemplified in Fig. 7. The input screen that the question creation support device 10A displays on the display screen 31 may not include at least some of the information exemplified in Fig. 7, or may include information different from the information exemplified in Fig. 7.
[0075] Next, the operation (processing) of the question creation support device 10A according to the present disclosure will be described in detail with reference to the flowchart of FIG.
[0076] The input / output control unit 15 receives the assignment information 161, the element answer instruction information 162A, and the regional characteristic information 163 from the terminal device 30, and stores the received assignment information 161, the element answer instruction information 162A, and the regional characteristic information 163 in the storage unit 16 (step S201). The element answer instruction unit 11 inputs the received assignment information 161 and the element answer instruction information 162 to the generative model 20 (step S202).
[0077] The generation unit 12A acquires answer elements 166A from the generation model 20 via the input / output control unit 15A (step S203). The generation unit 12A generates element information 167 by excluding inconsistent elements indicated by the regional characteristic information 163 from the answer elements 166A from the generation model (step S204). The generation unit 12A displays the element information 167 on the display screen 31 of the terminal device 30 via the input / output control unit 15A (step S205).
[0078] If the terminal device 30 does not receive information instructing adjustment of the element information 167 (No in step S206), the process proceeds to step S208. If the terminal device 30 receives information instructing adjustment of the element information 167 (Yes in step S206), the generation unit 12 adjusts the element information 167 in accordance with the received information (step S207).
[0079] The question generation instruction unit 13 inputs the element information 167 and the question generation instruction information 168 received from the terminal device 30 to the generative model 20 (step S208). The presentation unit 14 displays the question 169 generated by the generative model 20 on the display screen 31 of the terminal device 30 via the input / output control unit 15A (step S209), and the entire process ends.
[0080] The question creation support device 10A according to the present disclosure can support efficient creation of questions that can more accurately grasp the needs of survey subjects, for the reasons described above with respect to the question creation support device 10 in the description of the first embodiment.
[0081] Furthermore, the question creation support device 10A according to the present disclosure adjusts elements answered from the generative model 20 without using at least one of the region characteristic information 163 and the department characteristic information 164, using at least one of the region characteristic information 163 and the department characteristic information 164. The question creation support device 10A then provides a user interface that allows adjustment of elements included in the element information 167, as illustrated in Fig. 7, for example. This allows the question creation support device 10A to efficiently and flexibly support the creation of questions that can more accurately grasp the needs of survey subjects.
[0082] Furthermore, the question creation support device 10A according to the present disclosure presents to a user, via the input / output control unit 15A, first elements among the answer elements 166A from the generation model that are inconsistent with at least one of the region characteristic information 163 and the department characteristic information 164, in a display mode different from that of second elements excluding the first elements, as illustrated in FIG. 7 . The question creation support device 10A then receives, via the input / output control unit 15A, information instructing inclusion of one or more of the first elements in element information 167, and generates element information 167 including the first elements instructed to be included in the element information 167. This allows the question creation support device 10A to more efficiently and flexibly support the creation of questions that can more accurately grasp the needs of survey subjects.
[0083] Furthermore, the question creation support device 10A according to the present disclosure generates question creation instruction information 168 indicating that a number of questions 169 equal to or smaller than the input maximum number is to be generated via the input / output control unit 15A, which allows the user to input the maximum number of questions 169 to be generated by the generative model 20. This allows the question creation support device 10A to support the user in appropriately creating questions, taking into account the user's intention regarding the number of questions.
[0084] Furthermore, in the question creation support device 10A, as in the question creation support device 10, at least one of the regional characteristic information 163 and the department characteristic information 164 may be input to the generation model 20, and instead of the element answer instruction information 162A, the element answer instruction information 162 related to the question creation support device 10 may be input to the generation model 20.
[0085] 9 is a block diagram showing the configuration of a question creation support device 40 according to the present disclosure. The question creation support device 40 includes an element answer instruction unit 41, a generation unit 42, a question creation instruction unit 43, and a presentation unit 44. The element answer instruction unit 41, the generation unit 42, the question creation instruction unit 43, and the presentation unit 44 are examples of element answer instruction means, generation means, question creation instruction means, and presentation means, respectively.
[0086] The element answer instruction unit 41 inputs information 411 describing a problem and element answer instruction information 412 instructing the user to answer elements that are estimated to need to be investigated to solve the problem to the first generative model 51. The information 411 describing the problem is, for example, information similar to the problem information 161 related to the question creation support device 10 or the question creation support device 10A. The element answer instruction information 412 is, for example, information similar to the element answer instruction information 162 related to the question creation support device 10 or the element answer instruction information 162A related to the question creation support device 10A. The first generative model 51 is, for example, a generative model similar to the generative model 20 related to the question creation support device 10 or the question creation support device 10A. The element answer instruction unit 41 operates in the same manner as, for example, the element answer instruction unit 11 related to the question creation support device 10 or the element answer instruction unit 11A related to the question creation support device 10A.
[0087] The generation unit 42 receives information instructing adjustment of an element 421 answered from the first generative model 51, and generates element information 422 representing the adjusted element. The answered element 421 is, for example, an element similar to the answer element 166 from the generative model related to the question creation support device 10, or the answer element 166A from the generative model related to the question creation support device 10A. The element information 422 is, for example, information similar to the element information 167 related to the question creation support device 10 or the question creation support device 10A. The generation unit 42 operates in the same manner as, for example, the generation unit 12 related to the question creation support device 10, or the generation unit 12A related to the question creation support device 10A.
[0088] The question generation instruction unit 43 inputs the element information 167 and question generation instruction information 431 that instructs the second generation model 52 to generate questions for the survey subjects regarding the element information 167. The question generation instruction information 431 is, for example, information similar to the question generation instruction information 168 related to the question creation support device 10 or the question creation support device 10A. The second generation model 52 is, for example, a generation model similar to the generation model 20 related to the question creation support device 10 or the question creation support device 10A. The question generation instruction unit 43 operates in the same manner as the question generation instruction unit 13 related to the question creation support device 10 or the question creation support device 10A.
[0089] The presenting unit 44 presents to the user a question 441 generated by the second generative model 52. The question 441 is, for example, a question similar to the question 169 related to the question creation support device 10 or the question creation support device 10A. The presenting unit 44 operates in the same manner as the presenting unit 14 related to the question creation support device 10 or the question creation support device 10A.
[0090] Next, the operation (processing) of the question creation support device 40 according to the present disclosure will be described in detail with reference to the flowchart of FIG.
[0091] The element answer instruction unit 41 inputs information 411 representing the task and element answer instruction information 412 to the first generative model 51 (step S301). The generation unit 42 receives information instructing adjustment of an element 421 answered from the first generative model 51, and generates element information 422 representing the adjusted element (step S302).
[0092] The question generation instruction unit 43 inputs the element information 422 and question generation instruction information 431, which instructs the second generation model 52 to generate questions for the survey subjects regarding the element information 422, to the second generation model 52 (step S303). The presentation unit 44 presents the questions 441 generated by the second generation model 52 to the user (step S304), and the entire process ends.
[0093] The question creation support device 40 according to the present disclosure can support the efficient creation of questions that can more accurately grasp the needs of survey subjects. This is because the question creation support device 40 obtains the questions 441 by having the first generative model 51 answer elements that are estimated to need to be investigated to solve a problem, allowing the user to adjust the elements indicated by the answers, and then instructing the second generative model 52 to generate questions 441 for the survey subjects regarding the adjusted elements.
[0094] <Hardware Configuration Example> In each of the above-described embodiments, each unit in the question creation support device shown in Figures 1 and 9 can be realized by dedicated HW (Hardware) (electronic circuitry). In Figures 1 and 9, at least the following components can be considered as functional (processing) units (software modules) of a software program containing instructions executed by a processor: element answer instruction units 11, 11A, and 41; generation units 12, 12A, and 42; question creation instruction units 13 and 43; presentation units 14 and 44; input / output control units 15 and 15A; and a storage control function in the storage unit 16.
[0095] However, the division of the various components shown in these drawings is for the sake of convenience of explanation, and various configurations may be assumed for implementation. An example of the hardware environment in this case will be described with reference to FIG. 11.
[0096] Fig. 11 is a diagram illustrating an example of the configuration of an information processing device 900 (computer) capable of realizing the question creation support device according to the present disclosure. That is, Fig. 11 shows the configuration of a computer (information processing device) capable of realizing the question creation support device shown in Figs. 1 and 9, and represents a hardware environment capable of realizing each function in the above-described embodiment. However, each unit in the above-described question creation support device may be distributed among multiple information processing devices 900, or at least some of the functions may be provided in a server or the like that constitutes a cloud computing environment.
[0097] The information processing device 900 shown in Fig. 11 has the following components: a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a hard disk (storage device) 904, a communication interface 905, a bus 906 (communication line), a reader / writer 908 capable of reading and writing data stored in a recording medium 907 such as a CD-ROM (Compact Disc Read Only Memory), and an input / output interface 909 such as a monitor, speaker, keyboard, etc.
[0098] That is, the information processing device 900 having the above-described components is a general computer in which these components are connected via a bus 906. The information processing device 900 may have multiple CPUs 901, or may have a CPU 901 configured with multiple cores. The information processing device 900 may also not have some of the above-described components.
[0099] The present invention, explained using the above-mentioned embodiment as an example, supplies a computer program capable of realizing the following functions to the information processing device 900 shown in FIG. 11 . These functions are the functions of the configurations described above in the block diagrams ( FIGS. 1 and 9 ) or the flowcharts ( FIGS. 4 , 8 , and 10 ) referred to in the description of the embodiment. The present invention is then achieved by reading, interpreting, and executing the computer program into the CPU 901 of the hardware. The computer program supplied to the device may be stored in a readable / writable volatile memory (RAM 903) or a non-volatile storage device such as a ROM 902 or a hard disk 904.
[0100] In the above case, the method of supplying the computer program to the hardware can be a currently common procedure, such as installing the program in the device via a recording medium 907 such as a CD-ROM, or downloading the program from an external source via a communication line such as the Internet. In such a case, the present invention can be considered to be constituted by the code constituting the computer program or the recording medium 907 on which the code is stored.
[0101] The present invention has been described above using the above-described embodiments as exemplary examples. However, the present invention is not limited to the above-described embodiments. In other words, the present invention can be applied in various aspects that can be understood by a person skilled in the art within the scope of the present invention.
[0102] Note that part or all of the above-described embodiments can also be described as follows: However, the present invention, which has been exemplarily described using the above-described embodiments, is not limited to the following.
[0103] (Supplementary Note 1) A question creation support device comprising: an element answer instruction means for inputting information representing a problem and element answer instruction information instructing a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model; a generation means for receiving information instructing a user to make adjustments to the elements answered from the first generation model and generating element information representing the adjusted elements; a question generation instruction means for inputting the element information and question generation instruction information instructing a user to generate questions for survey subjects regarding the element information into a second generation model; and a presentation means for presenting the questions generated by the second generation model to a user.
[0104] (Supplementary Note 2) The question creation support device described in Supplementary Note 1, wherein the element answer instruction means inputs at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem into the first generation model, and the element answer instruction information indicates an instruction to exclude the elements that do not match at least one of the regional characteristic information and the department characteristic information.
[0105] (Supplementary Note 3) The question creation support device described in Supplementary Note 1, wherein the generation means receives information instructing the exclusion of inconsistent elements, which are the elements answered by the first generation model and are inconsistent with at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem, from the element information, and excludes the inconsistent elements from the element information.
[0106] (Appendix 4) The question creation support device described in Appendix 2, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the element answer instruction information represents an instruction to answer the elements according to the priority.
[0107] (Appendix 5) The question creation support device described in Appendix 3, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the question generation instruction information represents an instruction to generate the questions for the survey subjects related to the element information in accordance with the priority.
[0108] (Appendix 6) The question creation support device described in Appendix 3, wherein the generation means presents to the user via the input / output control means a first element among the elements answered from the first generation model that does not match at least one of the regional characteristic information and the department characteristic information in a display mode different from that of the second elements excluding the first element.
[0109] (Appendix 7) The question creation support device described in Appendix 6, wherein the generation means receives, via the input / output control means, information instructing inclusion of one or more first elements in the element information, and generates the element information including the first elements instructed to be included in the element information.
[0110] (Appendix 8) A question creation support device as described in any one of Appendices 1 to 6, wherein the question generation instruction means generates the question generation instruction information indicating that a number of questions equal to or smaller than the input maximum number will be generated via an input / output control means that allows a user to input the maximum number of questions to be generated by the second generation model.
[0111] (Supplementary Note 9) A question creation support method, using an information processing device, which inputs information representing a problem and element answer instruction information instructing a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model, receives information instructing a user to make adjustments to the elements answered from the first generation model, and generates element information representing the adjusted elements, inputs the element information and question generation instruction information instructing a user to generate questions for survey subjects regarding the element information into a second generation model, and presents the questions generated by the second generation model to a user.
[0112] (Appendix 10) A question creation support method as described in Appendix 9, wherein at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem is input into the first generation model, and the element answer instruction information indicates an instruction to exclude the elements that are inconsistent with at least one of the regional characteristic information and the department characteristic information.
[0113] (Appendix 11) A question creation support method as described in Appendix 9, which receives information instructing the exclusion of inconsistent elements, which are elements answered by the first generative model that are inconsistent with at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem, from the element information, and excludes the inconsistent elements from the element information.
[0114] (Appendix 12) A question creation support method as described in Appendix 10, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the element answer instruction information represents instructions to answer the elements according to the priority.
[0115] (Appendix 13) A question creation support method as described in Appendix 11, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the question generation instruction information represents an instruction to generate the questions for the survey subjects related to the element information in accordance with the priority.
[0116] (Appendix 14) A question creation support method as described in Appendix 11, in which a first element among the elements answered from the first generation model that does not match at least one of the regional characteristic information and the department characteristic information is presented to the user via an input / output control means in a display mode different from that of second elements excluding the first element.
[0117] (Appendix 15) A question creation support method as described in Appendix 14, which receives information instructing inclusion of one or more first elements in the element information via the input / output control means, and generates the element information including the first elements instructed to be included in the element information.
[0118] (Appendix 16) A question creation support method described in any one of Appendices 9 to 14, in which question generation instruction information indicating that a number of questions equal to or smaller than the input maximum number to be generated by the second generation model is generated via an input / output control means that allows a user to input the maximum number of questions to be generated by the second generation model is generated.
[0119] (Appendix 17) A question creation support program for causing a computer to execute the following steps: an element answer instruction process for inputting information representing a problem and element answer instruction information instructing a first generation model to answer elements that are estimated to require investigation in order to solve the problem; a generation process for receiving information instructing a second generation model to make adjustments to the answered elements and generating element information representing the adjusted elements; a question generation instruction process for inputting a second generation model with the element information and question generation instruction information instructing a second generation model to generate questions for survey subjects regarding the element information; and a presentation process for presenting the questions generated by the second generation model to a user.
[0120] (Appendix 18) A question creation support program as described in Appendix 17, wherein the element answer instruction process inputs at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem into the first generation model, and the element answer instruction information indicates an instruction to exclude the elements that are inconsistent with at least one of the regional characteristic information and the department characteristic information.
[0121] (Appendix 19) The question creation support program described in Appendix 17, wherein the generation process receives information instructing the exclusion of inconsistent elements, which are the elements answered by the first generation model that are inconsistent with at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem, from the element information, and excludes the inconsistent elements from the element information.
[0122] (Appendix 20) A question creation support program as described in Appendix 18, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the element answer instruction information represents instructions to answer the elements according to the priority.
[0123] (Appendix 21) A question creation support program as described in Appendix 19, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the question generation instruction information represents an instruction to generate the questions for the survey subjects regarding the element information in accordance with the priority.
[0124] (Appendix 22) The question creation support program described in Appendix 21, wherein the generation process presents to the user via an input / output control means a first element among the elements answered from the first generation model that does not match at least one of the regional characteristic information and the department characteristic information in a display mode different from that of the second elements excluding the first element.
[0125] (Appendix 23) The question creation support program described in Appendix 22, wherein the generation process receives, via the input / output control means, information instructing inclusion of one or more first elements in the element information, and generates the element information including the first elements instructed to be included in the element information.
[0126] (Supplementary Note 24) The question creation support program according to any one of Supplementary Note 17 to Supplementary Note 22, wherein the question generation instruction process generates, via input / output control means that allows a user to input a maximum number of questions to be generated by the second generative model, the question generation instruction information indicating that a number of questions equal to or smaller than the input maximum number is to be generated. This application claims priority based on Japanese Patent Application No. 2024-021154, filed on February 15, 2024, the disclosure of which is incorporated herein by reference in its entirety.
[0127] 10, 10A Question creation support device 11, 11A Element answer instruction unit 12, 12A Generation unit 13 Question creation instruction unit 14 Presentation unit 15, 15A Input / output control unit 16 Storage unit 161 Assignment information 162, 162A Element answer instruction information 163 Regional characteristic information 164 Department characteristic information 165 Priority information 166, 166A Answer element from generation model 167 Element information 168 Question creation instruction information 169 Question 20 Generation model 30 Terminal device 31 Display screen 40 Question creation support device 41 Element answer instruction unit 411 Information representing assignment 42 Generation unit 421 Answered element 422 Element information 43 Question creation instruction unit 431 Question creation instruction information 44 Presentation unit 441 Question 900 Information processing device 901 CPU 902 ROM 903 RAM 904 Hard disk (storage device) 905 Communication interface 906 Bus 907 Recording medium 908 Reader / writer 909 Input / output interface
Claims
1. A question creation support device comprising: an element answer instruction means for inputting information representing a problem and element answer instruction information instructing a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model; a generation means for receiving information instructing a user to make adjustments to the elements answered from the first generation model and generating element information representing the adjusted elements; a question generation instruction means for inputting the element information and question generation instruction information instructing a user to generate questions for survey subjects regarding the element information into a second generation model; and a presentation means for presenting the questions generated by the second generation model to a user.
2. The question creation support device described in claim 1, wherein the element answer instruction means inputs at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem into the first generation model, and the element answer instruction information indicates an instruction to exclude the elements that are inconsistent with at least one of the regional characteristic information and the department characteristic information.
3. The question creation support device described in claim 1, wherein the generation means receives information instructing the exclusion of inconsistent elements, which are elements answered by the first generation model that are inconsistent with at least one of regional characteristic information representing the characteristics of the region where the problem exists and department characteristic information representing the characteristics of the department responsible for solving the problem, from the element information, and excludes the inconsistent elements from the element information.
4. The question creation support device described in claim 2, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the element answer instruction information represents instructions to answer the elements according to the priority.
5. The question creation support device described in claim 3, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the question creation instruction information represents an instruction to generate the questions for the survey subjects related to the element information in accordance with the priority.
6. The question creation support device described in claim 3, wherein the generation means presents to the user via the input / output control means a first element among the elements answered by the first generation model that does not match at least one of the regional characteristic information and the department characteristic information in a display format different from that of the second elements excluding the first element.
7. The question creation support device described in claim 6, wherein the generation means receives, via the input / output control means, information instructing inclusion of one or more first elements in the element information, and generates the element information including the first elements instructed to be included in the element information.
8. A question creation support device as described in claim 1 or claim 2, wherein the question generation instruction means generates the question generation instruction information indicating that a number of questions equal to or smaller than the input maximum number will be generated via an input / output control means that allows a user to input the maximum number of questions to be generated by the second generation model.
9. A question creation support method using an information processing device: inputting information representing a problem and element answer instruction information instructing a user to answer elements that are estimated to require investigation in order to solve the problem into a first generation model; receiving information instructing a user to make adjustments to the elements answered from the first generation model, and generating element information representing the adjusted elements; inputting the element information and question generation instruction information instructing a user to generate questions for survey subjects regarding the element information into a second generation model; and presenting the questions generated by the second generation model to a user.
10. A question creation support method as described in claim 9, wherein at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem is input into the first generation model, and the element answer instruction information represents an instruction to exclude the elements that are inconsistent with at least one of the regional characteristic information and the department characteristic information.
11. A question creation support method as described in claim 9, which receives information instructing the exclusion of inconsistent elements, which are elements answered by the first generative model that are inconsistent with at least one of regional characteristic information representing the characteristics of the region where the problem exists and department characteristic information representing the characteristics of the department responsible for solving the problem, from the element information, and excludes the inconsistent elements from the element information.
12. A question creation support method as described in claim 10, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the element answer instruction information represents instructions to answer the elements according to the priority.
13. A question creation support method as described in claim 11, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the question creation instruction information represents an instruction to generate the questions for the survey subjects related to the element information in accordance with the priority.
14. A question creation support method as described in claim 11, wherein a first element among the elements answered by the first generation model that does not match at least one of the regional characteristic information and the department characteristic information is presented to the user via an input / output control means in a display mode different from that of second elements excluding the first element.
15. A question creation support method as described in claim 14, which receives information instructing inclusion of one or more first elements in the element information via the input / output control means, and generates the element information including the first elements instructed to be included in the element information.
16. A question creation support method as described in any one of claims 9 to 14, wherein the question creation instruction information indicating that a number of questions equal to or smaller than the input maximum number to be generated by the second generation model is generated via an input / output control means that allows a user to input the maximum number of questions to be generated by the second generation model is generated.
17. A recording medium having recorded thereon a question creation support program for causing a computer to execute the following steps: an element answer instruction process for inputting information representing a problem and element answer instruction information instructing a first generation model to answer elements that are estimated to require investigation in order to solve the problem; a generation process for receiving information instructing a second generation model to make adjustments to the elements answered from the first generation model and generating element information representing the adjusted elements; a question generation instruction process for inputting the element information and question generation instruction information instructing a second generation model to generate questions for survey subjects regarding the element information; and a presentation process for presenting the questions generated by the second generation model to a user.
18. The recording medium described in claim 17, wherein the element answer instruction process inputs at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem into the first generation model, and the element answer instruction information represents an instruction to exclude the elements that are inconsistent with at least one of the regional characteristic information and the department characteristic information.
19. The recording medium described in claim 17, wherein the generation process receives information instructing the exclusion of inconsistent elements, which are elements answered by the first generation model that are inconsistent with at least one of regional characteristic information representing the characteristics of the region having the problem and department characteristic information representing the characteristics of the department responsible for solving the problem, from the element information, and excludes the inconsistent elements from the element information.
20. The recording medium of claim 18, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the element answer instruction information represents an instruction to answer the elements according to the priority.
21. The recording medium described in claim 19, wherein the regional characteristic information and the department characteristic information include information representing the priority of the survey for each of the multiple elements related to the region or the department, and the question generation instruction information represents an instruction to generate the questions for the survey subjects regarding the element information in accordance with the priority.
22. The recording medium described in claim 21, wherein the generation process presents to the user via an input / output control means a first element among the elements returned from the first generation model that does not match at least one of the regional characteristic information and the department characteristic information in a display format different from that of second elements excluding the first element.
23. The recording medium according to claim 22, wherein the generation process receives, via the input / output control means, information instructing inclusion of one or more first elements in the element information, and generates the element information including the first elements instructed to be included in the element information.
24. A recording medium described in any one of claims 17 to 22, wherein the question generation instruction process generates, via an input / output control means that allows a user to input the maximum number of questions to be generated by the second generation model, question generation instruction information indicating that a number of questions equal to or smaller than the input maximum number will be generated.
Citation Information
Patent Citations
Unspecified large number of user target questionnaire system
JP2009015586A
Information processing method, program, and information processing system for supporting child consultation services
JP7368034B1