Information processing system and information processing method

Abstract

To enable a manager to accurately recognize information effective for improving an organization without spending as much effort as possible in the field of improving the organization. [Solution] The information processing system has the following functions: using the functions of language model 4, to conduct specific interviews with members of an organization to elicit the organization's challenges and solutions to those challenges; a function to extract problem-solution pairs, which are combinations of problem answers that mention the challenges and solution answers that mention the solutions, from the results of the specific interviews; a function to classify each of the problem-solution pairs based on the specific interviews conducted with multiple members into one of multiple problem categories; and a function to provide information based on the problem-solution pairs belonging to each problem category to the administrator for each problem category.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system for improving an organization and an information processing method by the information processing system. [Background technology]

[0002] Conventionally, technologies for supporting organizational improvement have been proposed for companies, associations, and other organizations. For example, Patent Document 1 describes the following technology. Specifically, the organizational improvement activity support device described in Patent Document 1 acquires a measure suitability level, which quantitatively indicates the degree of suitability for the characteristics and improvement theme of the target organization, a measure agreement level, which quantitatively indicates the degree of support for the measure among members of the target organization, and a measure activity level, which quantitatively indicates the degree of implementation of the measure in the target organization. Based on these, the device calculates an effect point, which quantitatively indicates the degree of effectiveness of organizational improvement activities in the target organization, and presents information on at least the activity status of the target organization to facilitators and / or members of the target organization based on the effect point. The technology described in Patent Document 1 makes it possible to improve the continuity of organizational improvement activities without the need for on-site expert intervention. Patent Document 2 also describes the following technology. Specifically, an information processing device 3 stores organizational status information regarding the status of the organization and presentation information, which is information to be presented to members of the organization. The information processing device 3 uses the organizational status information to determine and transmit the presentation information to be presented to members of the organization from the presentation information. According to the technology of Patent Document 2, it is possible to use organizational status information to appropriately present information to members of an organization in order to improve the organization. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-139323 [Patent Document 2] Japanese Patent Publication No. 2023-171503 Summary of the Invention [Problem to be solved by the invention]

[0004] As suggested in Patent Documents 1 and 2, in the field of organizational improvement, there is a need to enable managers to accurately recognize information that is effective for improving their organizations with as little effort as possible.

[0005] The present disclosure has been made to solve such problems, and aims to enable managers in the field of organizational improvement to accurately recognize information that is effective for improving organizations with as little effort as possible. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, the present disclosure has the following configuration: An information processing system comprising: an information processing unit that uses a language model function to conduct specific interviews with members of an organization to elicit the organization's problems and solutions to those problems; a function of the information processing unit that extracts problem-solution pairs that are combinations of problem answers that mention the problems and solution answers that mention the solutions from the results of the specific interviews; a function of the information processing unit that classifies each of the problem-solution pairs based on the specific interviews conducted with a plurality of members into one of a plurality of problem categories; and a function of the information processing unit that provides, for each problem category, information based on the problem-solution pairs that belong to the problem category to a manager. [Effects of the Invention]

[0007] According to the present disclosure configured as described above, organizational issues perceived by employees and their solutions are elicited through interviews using the language model function. The combinations of issues perceived by employees and their solutions are information that is directly or indirectly useful for organizational improvement, and are therefore effective information for organizational improvement. According to the present disclosure, multiple issue-related pairs are classified into multiple issue categories, and information based on the issue-related pairs for each category is provided to the manager. This allows the manager to accurately recognize information based on "organizational issues perceived by employees and their solutions," information effective for organizational improvement, organized by category. Moreover, according to the present disclosure, the interviews are conducted mechanically using a language model, thereby reducing the effort required to provide information to the manager compared to interviews conducted manually. In other words, the present disclosure enables managers to accurately recognize information effective for organizational improvement in the field of organizational improvement with minimal effort. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a control system according to an embodiment. [Figure 2] 2 is a block diagram illustrating an example of a functional configuration of an information processing server, an employee terminal, and a manager terminal according to an embodiment. FIG. [Figure 3] FIG. 10 is a diagram showing an example of an interview screen. [Figure 4] 10 is a flowchart showing an information processing method by an employee terminal and an information processing server. [Figure 5] 10 is a flowchart illustrating an information processing method by an employee terminal and a language model server. [Figure 6] FIG. 10 is a diagram showing an example of an interview screen. [Figure 7] FIG. 10 is a diagram showing an example of the contents of interview result information. [Figure 8] FIG. 10 is a diagram showing the hierarchical structure of task categories. [Figure 9] FIG. 10 is a diagram used to explain processing by an information processing server. [Figure 10] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 11] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 12] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 13] This is a diagram used to explain the second selection task section. [Figure 14] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 15] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 16] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 17] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 18] This is a diagram used to explain the task matrix. [Figure 19] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 20] FIG. 10 is a diagram illustrating an example of a main management screen. [Figure 21] FIG. 1 illustrates an example of the configuration of an information processing system. DETAILED DESCRIPTION OF THE INVENTION

[0009] A first embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a diagram showing an example of the configuration of a control system 1 (information processing system) according to this embodiment. As shown in FIG. 1, the control system 1 includes an information processing server 2 (information processing system, server, computer), an employee terminal 3E (information processing system, terminal, computer), and a manager terminal 3R (information processing system, terminal, computer). The information processing server 2, the employee terminal 3E, and the manager terminal 3R can all be connected to a network N including the Internet, a telephone network, and other communication networks. A language model server 4 is connected to the network N. In the following description, a database will be referred to as a "DB," and a user interface will be referred to as a "UI."

[0010] The information processing server 2 has the function of providing services related to organizational improvement support and other services. Hereinafter, the services provided by the information processing server 2 are referred to as the "service." In this embodiment, the organization is assumed to be a single company, and this company is referred to as the "target company." In this embodiment, the target company (a concept that also includes individuals belonging to the target company) is assumed to use the service. In this embodiment, a "manager" refers to a person in a position to plan and implement organizational improvements. For example, a group leader, department head, or executive of the target company corresponds to a manager. However, the term "manager" does not refer only to individuals in a specific position. The term "manager" broadly encompasses anyone who can access the main management screen 30, described below. In this embodiment, an employee (member) refers to anyone who belongs to the target company but is not a manager. However, the term "employee" does not refer only to individuals in a specific position. The term "employee" broadly encompasses anyone who can participate in the specific interview, described below. Hereinafter, employees and managers are collectively referred to as "users." Note that the entity using the service is a single company for simplicity's sake; it goes without saying that the service can be used by multiple organizations.

[0011] In FIG. 1 and FIG. 2 described below, the information processing server 2 is represented by a single block. However, this does not mean that the information processing server 2 is composed of a single device. The information processing server 2 may be composed of a virtual server. The information processing server 2 may also be composed of a plurality of devices. In this configuration, the devices constituting the information processing server 2 may include a web server, a web application server, or a database server. In this configuration, the information processing server 2 may also be composed of a plurality of server devices whose load is distributed by a load balancer. When the information processing server 2 is composed of a plurality of devices, each of the information processing units of the plurality of devices, or a combination of the plurality of information processing units, functions as an "information processing unit."

[0012] The employee terminal 3E is a terminal used by an employee. However, the employee terminal 3E is a convenient reference to a terminal used by an employee, and does not mean a terminal used exclusively by an employee. The employee terminal 3E may be of any type. For example, a tablet computer (including so-called smartphones), a desktop computer, or a notebook computer can function as the employee terminal 3E. The administrator terminal 3R is a terminal used by an administrator. However, the administrator terminal 3R is a convenient reference to a terminal used by an administrator, and does not mean a terminal used exclusively by an administrator. The administrator terminal 3R may be of any type.

[0013] The language model server 4 is a server equipped with a language model 5. The language model 5 according to this embodiment is a so-called large-scale language model (LLM). The provider of the language model 5, the type of the language model 5, and the machine learning method of the language model 5 are not limited. The language model 5 may be a publicly available non-commercial model or a publicly available commercial model (e.g., GPT-4, GPT-4o, or BERT). The language model 5 may also be a local LLM. The language model 5 may be fine-tuned for use in the present service or for other reasons. The language model server 4 has a function of receiving a prompt (question sentence) from an external device, generating a response sentence to the prompt using the function of the language model 5, and transmitting the response sentence to the external device. The information processing server 2 is appropriately authorized to use the language model server 4.

[0014] Fig. 2 is a block diagram showing an example of the functional configuration of the information processing server 2, employee terminal 3E, and manager terminal 3R. As shown in Fig. 2, the information processing server 2 has, as its functional configuration, a server information processing unit 10 (information processing unit), a server communication unit 11 (communication unit), and a server storage unit 12 (storage unit). The employee terminal 3E has, as its functional configuration, a terminal information processing unit 13E (information processing unit), a terminal communication unit 14E (communication unit), a terminal display unit 15E (display unit), a terminal input unit 16E (input unit), a voice input unit 17E (voice input unit), a voice output unit 18E (voice output unit), and a terminal storage unit 19E (storage unit). The administrator terminal 3R has a functional configuration including a terminal information processing unit 13R (information processing unit), a terminal communication unit 14R (communication unit), a terminal display unit 15R (display unit), a terminal input unit 16R (terminal input unit), an audio input unit 17R (audio input unit), an audio output unit 18R (audio output unit), and a terminal memory unit 19R (memory unit).

[0015] The server information processing unit 10 comprises a processing device including a processor and a primary storage device. The server information processing unit 10 executes processing by having the processing device read out a program stored in the storage area of ​​the server storage unit 12 (or another storage area) into the primary storage device and execute it. In other words, the server information processing unit 10 executes processing through cooperation between hardware and software. The server communication unit 11 comprises a communication device including a communication control device and a network interface. The server communication unit 11 communicates with external devices via the communication device under the control of the server information processing unit 10. Hereinafter, it is assumed that communication by the information processing server 2 is appropriately executed by the server communication unit 11, and a description of the communication will be omitted. The server storage unit 12 stores data in non-volatile memory. The non-volatile memory is, for example, a hard disk drive (or other magnetic storage device), ROM, or flash memory.

[0016] The server storage unit 12 stores a user management DB 20. The user management DB 20 stores information about each user (including employees and managers) in association with a user ID (identification information).

[0017] The terminal information processing unit 13E of the employee terminal 3E includes a processing device including a processor and a primary storage device. The terminal information processing unit 13E executes processing by having the processing device read a program stored in the storage area of ​​the terminal storage unit 19E (or another storage area) into the primary storage device and execute it. In other words, the terminal information processing unit 13E executes processing through cooperation between hardware and software. The terminal communication unit 14E includes a communication device including a communication control device and a network interface. The terminal communication unit 14E communicates with external devices via the communication device under the control of the terminal information processing unit 13E. The terminal display unit 15E includes a liquid crystal panel, an organic EL panel, or other display device. The terminal display unit 15E displays images on the display device under the control of the terminal information processing unit 13E. The terminal input unit 16E detects input to the input device and outputs the detection result to the terminal information processing unit 13E. The input device is, for example, a keyboard, a mouse, a touch panel, or a camera. The voice input unit 17E includes a microphone and a signal processing circuit. The audio input unit 17E has a function of outputting an audio signal based on audio picked up by the microphone to the terminal information processing unit 13E. The terminal information processing unit 13E has a function of performing analog / digital conversion processing including sampling, quantization, and encoding processing, and other necessary signal processing on the audio signal input from the audio input unit 17E to generate audio data, and stores the audio data in the terminal storage unit 19E. The audio output unit 18E has a speaker and a signal processing circuit. The audio output unit 18E inputs an audio signal from the terminal information processing unit 13E, drives the speaker based on the input audio signal, and causes the speaker to emit audio based on the audio signal. The terminal storage unit 19E stores data in a non-volatile memory.

[0018] The terminal information processing unit 13R, terminal communication unit 14R, terminal display unit 15R, terminal input unit 16R, audio input unit 17R, audio output unit 18R, and terminal storage unit 19R of the manager terminal 3R each have the same hardware configuration and the same "functions based on the hardware configuration" as the terminal information processing unit 13E, terminal communication unit 14E, terminal display unit 15E, terminal input unit 16E, audio input unit 17E, audio output unit 18E, and terminal storage unit 19E of the employee terminal 3E. In the following, it is assumed that communication between the employee terminal 3E and the manager terminal 3R is appropriately performed by the terminal communication units 14E and 14R, and a description of the communication will be omitted.

[0019] As shown in FIG. 2, a dedicated application AP (hereinafter referred to as the "dedicated application AP") is installed on the employee terminal 3E and the manager terminal 3R. The dedicated application AP is dedicated software that implements functions such as providing various screens related to the service, transmitting and receiving various information related to the service to and from the information processing server 2, and executing other processes related to the service. Unless otherwise specified in the following description, the terminal information processing units 13E and 13R basically execute processes using the functions of the dedicated application AP (including the terminal's OS, web applications that the dedicated application AP can use, and other programs that can cooperate with the dedicated application AP). Furthermore, even if not otherwise specified in the following description, the terminal information processing units 13E and 13R execute the following processes as needed. That is, the terminal information processing units 13E and 13R communicate with the server information processing unit 10 (which may be an information processing unit of another external device; the same applies below) as needed to obtain information required for processing. In particular, when displaying various screens, the terminal information processing units 13E and 13R obtain information required for displaying the screens from the server information processing unit 10. The server information processing unit 10 refers to the user management DB 20, the investigation event management DB 21 (described later), and other databases, and transmits necessary information to the terminal information processing units 13E and 13R. The terminal information processing units 13E and 13R also communicate with the server information processing unit 10 as needed to request the execution of processing and obtain the processing results. In the following, the display of various screens on the terminal display units 15E and 15R by the terminal information processing units 13E and 13R using the functions of the dedicated application AP and other programs may be expressed simply as "the terminal information processing units 13E and 13R display a screen."

[0020] Next, the operation of the control system 1 will be described. The following explanation assumes the following regarding the target company: The target company holds survey events from time to time. In these survey events, specific interviews (described below) are conducted with employees, and various information based on the results of the specific interviews is provided to the manager. The server storage unit 12 of the information processing server 2 stores a survey event management DB 21 for managing various information related to each survey event. In the following explanation, when the survey event management DB 21 is simply mentioned, it means the survey event management DB 21 corresponding to the current survey event, unless otherwise specified.

[0021] <Scene of an employee dealing with a specific interview> First, one of the employees will be referred to as a "notable employee," and the operation of the control system 1 in a scene where the notable employee leaves for a specific interview will be described.

[0022] When a survey event is held, each employee of the target company is notified in a predetermined manner that they need to answer a specific interview. In response to this notification, the target employee launches the dedicated application AP on their employee terminal 3E and logs in to the service. When logging in, the server information processing unit 10 works with the terminal information processing unit 13E to perform authentication. The server information processing unit 10 acquires the target employee's user ID during authentication. The server information processing unit 10 can acquire information about the target employee from the user management DB 20 using the target employee's user ID. Even if not specifically described below, the server information processing unit 10 acquires information about the target employee from the user management DB 20 as needed. The above also applies when an administrator logs in to the service. In other words, a state is established in which the server information processing unit 10 can acquire information about the administrator from the user management DB 20 in response to the administrator's login.

[0023] After logging in to the service, the target employee performs a predetermined operation to instruct the display of the interview screen 22. In response to this instruction, the terminal information processing unit 13E displays the interview screen 22 on the terminal display unit 15E. FIG. 3 shows an example of the interview screen 22 in its initial state. Note that a series of interviews realized via the interview screen 22 corresponds to a "specific interview." As shown in FIG. 3, a character image 23 representing the interviewer is displayed on the left side of the interview screen 22. A message window 24 is displayed to the right of the character image 23. The message window 24 is a display area in which messages exchanged between the target employee and the AI ​​interviewer are displayed in chronological order. The AI ​​interviewer is a convenient representation of the entity that functions as the interviewer in the specific interview through the function of the language model 5. Hereinafter, the exchange of messages between the employee and the AI ​​interviewer in the specific interview may be referred to as a "dialogue."

[0024] An example of the operation of the control system 1 in a specific interview will be described below using a flowchart. Figure 4 is a flowchart showing an example of the operation of the control system 1. The flowchart FA shows an information processing method by the employee terminal 3E, and the flowchart FB shows an information processing method by the information processing server 2.

[0025] As shown in flowchart FA, after displaying the interview screen 22, the terminal information processing unit 13E executes interview processing (step SA1). The interview processing is processing in which the terminal information processing unit 13E uses the functions of the language model 5 to conduct a specific interview with an employee (a target employee in this example). The specific interview is conducted with the aim of obtaining answers to at least the following questions: Employees' thoughts on the challenges facing prominent companies and solutions to those challenges In this embodiment, the term "issue" broadly encompasses any matter that requires efforts to be made to solve it. The term "issue" includes, for example, problems that need to be solved in an organization or themes that a company needs to address. Furthermore, a "solution" broadly encompasses methods and means for achieving a desired result for a problem. A solution can also be referred to as a "measure."

[0026] 5 is a diagram showing details of interview processing by the terminal information processing unit 13E together with processing by the language model server 4. In FIG. 5, flowchart FC shows the information processing method by the employee terminal 3E, and flowchart FD shows the information processing method by the language model server 4. In the interview processing as shown in flowchart FC, first, the terminal information processing unit 13E generates an initial prompt (step SC1). The initial prompt is a prompt requesting the generation of the first question (hereinafter referred to as the "initial question") to be presented to the employee (the employee of interest in this example) in the specific interview. The initial prompt describes the following items: Information that employees will be interviewed to find out what they think are the challenges facing the organization and how they can solve them. - Information requesting the generation of the first questions to be asked of the employee of interest to achieve this purpose. However, the information to be written in the initial prompt is not limited to the information exemplified above. Any information that can contribute to improving the quality of a specific interview may be written in the initial prompt. For example, the terminal information processing unit 13E may write the following information in the initial prompt: ·Points to note when generating questions Sample initial questions ·Terms that should not be included in questions Results of specific past employee interviews Attribute information of featured employees In this embodiment, "attribute information" refers to information that includes attribute values ​​of various attributes. Employee attribute information includes, for example, name, gender, age, years of employment, and career history before and after joining the company. Note that the information described in the prompt is not limited to the example information, and this also applies to prompts other than the initial prompt.

[0027] The terminal information processing unit 13E generates the initial prompt, for example, in the following manner. A template for the initial prompt is prepared in advance, and the terminal information processing unit 13E processes the template based on the information to be written in the initial prompt to generate the initial prompt. The terminal information processing unit 13E requests the language model server 4 to generate an initial prompt, and acquires (generates) an initial prompt as a response sentence to the request. The initial prompt includes information necessary for generating the initial prompt. However, it goes without saying that the method for generating the initial prompt is not limited to the exemplified method, and the method for generating the initial prompt can also be applied to other prompt generation methods.

[0028] After step SC1, the terminal information processing unit 13E transmits the generated initial prompt to the language model server 4 (step SC2). As shown in flowchart FD, the language model server 4 receives the initial prompt and generates a response sentence based on the initial prompt using the language model 5 (step SD1). The response sentence includes an "initial question" that reflects the purpose of the specific interview and other matters described in the initial prompt. The language model server 4 transmits the generated response sentence to the terminal information processing unit 13E (step SD2). The terminal information processing unit 13E receives and acquires the response sentence (step SC3).

[0029] In the following description, when the terminal information processing unit 13E performs processing using the functions of the language model 5, even if not otherwise specified, the terminal information processing unit 13E generates a prompt, transmits it to the language model server 4, and obtains a response sentence from the server. The above points also apply to information processing units other than the terminal information processing unit 13E.

[0030] After acquiring the response sentence, the terminal information processing unit 13E controls the voice output unit 18E to voice output the wording indicated by the initial question based on the initial question of the response sentence (step SC4). The terminal information processing unit 13E voice outputs the initial question using voice synthesis technology or other technology. At this time, the terminal information processing unit 13E makes the character image 23 appear to be speaking in accordance with the voice output of the question. In synchronization with the voice output of the initial question, the terminal information processing unit 13E displays a message MS1 corresponding to the initial question in the message window 24 (step SC5). Figure 6 (A) shows the message MS1 displayed in the message window 24. Hereinafter, the questions posed to the employee in the specific interview will be referred to as "interview questions."

[0031] The target employee, having heard the audio output of the initial question, orally responds to the initial question (step SC6). Hereinafter, the response given by the employee to the interview question in the specific interview is referred to as the "interview response." The spoken voice is collected by the microphone of the audio input unit 17E, and the audio data is stored in the device storage unit 19E. The device information processing unit 13E converts the audio data into text data (hereinafter referred to as "interview response data") containing text (wording) corresponding to the interview response (step SC7). Next, the device information processing unit 13E displays a message MS2 corresponding to the interview response in the message window 24 based on the interview response data (step SC8). (B) of FIG. 6 shows the message MS2 displayed in the message window 24. Next, the terminal information processing unit 13E writes the interview question based on the response sentence acquired in step SC3 and the interview response based on the interview response data generated in step SC7 in the interview log according to the format (step SC9). An interview log is log data that records the interview questions and answers exchanged between an employee and an AI interviewer in chronological order, along with accompanying information (e.g., date and time) during a specific interview.

[0032] Next, the terminal information processing unit 13E generates a prompt requesting the generation of a second question by at least reflecting the dialogue so far (step SC10). The prompt for the second or subsequent questions includes the interview log (i.e., the interview questions and interview answers exchanged so far) and also includes information requesting the generation of questions by further reflecting the dialogue so far. Furthermore, the prompt for the second or subsequent questions includes information requesting that, if the question recorded in the response sentence is the "final question" in the specific interview, that information be included in the response sentence. After generating the prompt, the terminal information processing unit 13E sends the generated prompt to the language model server 4 (step SC11). Thereafter, the second, third, ..., and final interview questions are provided to the noted employee in the same manner as the first question, and the noted employee provides interview answers to the second, third, ..., and final interview questions. The terminal information processing unit 13E writes information in the interview log each time the noted employee provides an interview answer to an interview question.

[0033] For example, in a specific interview, the following dialogue takes place between the employee of interest and the AI ​​interviewer: The following example is a simplified example. <Beginning of specific interview> [AI Interviewer] What do you think are the challenges facing your company or organization? [Featured Employee] Labor shortages. [AI Interviewer] When do you specifically feel a labor shortage? [Featured Employee] When multiple projects are underway simultaneously, resources run out and deadlines become tight. [AI Interviewer] How do you think this can be resolved? [Featured Employee] I think hiring contract workers is counterproductive. I think it would be better to hire full-time employees with specialized skills. [AI Interviewer] Thank you. Are there any other challenges you're aware of? [Featured Employee] Well... [AI Interviewer] This is my last question. What ideas do you have for solving the problem you just mentioned? [Featured Employee] For example, I think it would be good to have a way to check how busy each department is. [AI Interviewer] This concludes the interview. Thank you for your hard work. <End of specific interview>

[0034] As described above, the terminal information processing unit 13E (information processing unit) has the function of using the language model 5 to conduct a specific interview with members of an organization to elicit the organization's challenges and solutions to those challenges. Here, the specific interview is conducted in a dialogue format, so the burden on the employee of interest is low. Also, because the interviewer is not human, the employee can respond to the specific interview without feeling nervous, and is more likely to speak his or her true feelings without worrying about personal relationships with the interviewer. Furthermore, because the interviewer is not human, anonymity of the employee's comments can be ensured, and the assurance of anonymity makes it easier for the employee to speak his or her true feelings. These are the details of the interview processing.

[0035] As shown in the flowchart FA of FIG. 4, once the interview process in step SA1 is complete, the terminal information processing unit 13E executes the interview log analysis process (step SA2). The interview log analysis process analyzes the interview log and extracts "combinations of problem answers and solution answers" for each issue raised by the employee from the interview answers given by the employee in a specific interview. A problem answer is an interview answer that mentions a problem, and a solution answer is an interview answer that mentions a solution. Hereinafter, a combination of a problem answer (problem) and a solution answer (solution) corresponding to one problem will be referred to as a "problem-solution pair." In the interview log analysis process, multiple "problem-solution pairs" may be extracted.

[0036] The terminal information processing unit 13E executes the extraction process in the following manner: That is, the terminal information processing unit 13E generates a prompt in which the following information is described. Interview log. ·Information requesting extraction of problem-solving pairs from interview logs. - Information indicating that problem-solving pairs should be extracted by reflecting the chronological order of interview questions and answers in a specific interview, as well as the content of the interview questions and answers. The terminal information processing unit 13E transmits a prompt to the language model server 4 and receives a response sentence from the server 4. The terminal information processing unit 13E acquires (extracts) problem-solving pairs based on the response sentence.

[0037] However, the method for extracting problem-solving pairs is not limited to the exemplified method. For example, the following method may be used. That is, in a specific interview, the terminal information processing unit 13E, using the functions of the language model 5, divides the interview into a part for hearing about the problem and a part for hearing about the solution for each problem. Then, for one problem, the terminal information processing unit 13E extracts, as a problem-solving pair, a combination of "the problem answer spoken by the noted employee in the part for hearing about the problem" and "the question and answer spoken by the noted employee in the part for hearing about the solution." The above method may be used.

[0038] In this embodiment, the problem answers and solution answers that make up the problem-solving pairs are the answers (comments) provided by the employees themselves. However, the problem answers and solution answers may be sentences that summarize the answers provided by the employees, or sentences that modify the answers provided by the employees without changing the gist of them. In this case, the terminal information processing unit 13E (or another information processing unit) summarizes or modifies the problem answers using the functions of the language model 5. The terminal information processing unit 13E may also be configured to have the target employee review each of the extracted problem-solving pairs and correct them as necessary. In this configuration, the terminal information processing unit 13E displays, for example, a screen on the terminal display unit 15E that displays each of the problem-solving pairs in an editable state. This concludes the details of step SA2.

[0039] As described above, the terminal information processing unit 13E (information processing unit) has a function of extracting problem-solution pairs, which are combinations of problem answers that mention the problem and solution answers that mention the solution, from the results of a specific interview.

[0040] After step SA2, the server information processing unit 10 generates interview result information (step SA3). FIG. 7 is a diagram showing the contents of the interview result information. As shown in FIG. 7, the interview result information includes the user ID of the employee who underwent the specific interview, an interview ID which is identification information for the specific interview, an interview log related to the specific interview, and extracted information. The extracted information includes each of the problem-solving pairs extracted in the interview log analysis process of step SA2. Note that in the problem-improvement pairs, type information indicating that the answer is a problem answer is associated with the problem answer, and type information indicating that the answer is a solution answer is associated with the solution answer.

[0041] After step SA3, the terminal information processing unit 13E transmits the interview result information to the server information processing unit 10 (step SA4). As shown in flowchart FB, the server information processing unit 10 receives and acquires the interview result information (step SB1). Next, the server information processing unit 10 registers the received interview result information in the survey event management DB 21 in an appropriate manner (step SB2). The above is the operation of the control system 1 in the <scene in which an employee handles a specific interview>.

[0042] In the survey event according to this embodiment, all employees are required to respond to the specific interview. Ideally, the interview result information for all employees will eventually be registered in the survey event management DB 21. However, it is possible that some employees may not respond to the specific interview due to certain circumstances.

[0043] <Scene for executing the provision information generation process> After the deadline for the period during which an employee is to conduct a specific interview in a survey event has passed, the server information processing unit 10 executes a process for generating information to be provided. The process for generating information to be provided is a process for generating information to be provided based on the survey event management DB 21. Information to be provided is a general term for information provided to the manager based on the results of the specific interview in the survey event. The information to be provided also includes information that forms the basis of various screens provided to the manager. The process for generating information to be provided includes a first generation process, a second generation process, and a third generation process. Below, the operation of the server information processing unit 10 will be described for each of the first generation process, the second generation process, and the third generation process.

[0044] First generation process First, the first generation process will be described. In this embodiment, multiple divisions are defined for the assignment. Hereinafter, each of the multiple divisions defined for the assignment will be referred to as a "task division." The assignment divisions are hierarchically organized into four levels. Figure 8 is a diagram showing the assignment divisions together with their hierarchical structure. As shown in Figure 8, the assignment divisions are hierarchically organized into four levels, from level 0 to level 4. The assignment division in level 0 is a convenient definition of the single assignment division located at the top level. Hereinafter, the assignment division in level 0 will be referred to as a "basic assignment division." Furthermore, each assignment division belonging to the first level will be referred to as the first division, each assignment division belonging to the second level will be referred to as the second division, and each assignment division belonging to the third level will be referred to as the third division. Each third division is assigned a third division ID, which is identification information for identifying the third division.

[0045] In the first generation process, the server information processing unit 10 classifies (assigns) each of the problem-solving pairs extracted in the survey event (each of the problem-solving pairs based on specific interviews conducted with multiple members) into one of multiple third categories. Note that there may be a third category into which no problem-solving pairs are classified. Below, we will explain how the server information processing unit 10 classifies one of the problem-solving pairs, "problem-solving pair PA1," into one of the third categories.

[0046] When classifying the problem-solving pair PA1, the server information processing unit 10 first generates a prompt in which the following information is described. · Contents of problem-solving pair PA1 (= contents of the problem answer and solution answer that make up problem-solving pair PA1). - Content information for each of the third categories. - Information requesting that the problem-solving pair PA1 be classified into one of the third categories based on the content of the problem-solving pair PA1 and the category content information of each of the third categories, and that the third category ID of the third category into which it has been classified be responded to. In addition, the division content information of one third division includes, in addition to the third division ID of the one third division, information that is useful for determining whether a problem-solving pair should be classified into the one third division. In this embodiment, the division content information of one third division includes at least the content, definition, and meaning of the one third division. However, the information described in the prompt is not limited to the exemplified information. For example, the server information processing unit 10 may describe in the prompt the division content information of each of the first and second divisions along with information indicating the hierarchical structure of the problem divisions.

[0047] The server information processing unit 10 sends the generated prompt to the language model server 4 and obtains a response sentence from the server. The response sentence includes the third category ID of the third category into which the problem-solving pair PA1 is classified. The server information processing unit 10 recognizes the third category ID into which the problem-solving pair PA1 is classified based on the response sentence. This creates a state in which the problem-solving pair PA1 is classified into one of the third categories. The above is the classification method for the problem-solving pair PA1. As described above, the server information processing unit 10 classifies each of the problem-solving pairs extracted in the survey event into one of multiple third categories. As a result, a state in which all problem-solving pairs are classified into one of the third categories is created.

[0048] After all problem-solving pairs have been classified, the server information processing unit 10 executes an intra-division analysis process for each third division. Note that there may be third divisions into which no problem-solving pairs are classified, but the server information processing unit 10 does not execute an intra-division analysis process for such third divisions. Below, the third division to be processed is referred to as "third division KB1," and the intra-division analysis process executed by the server information processing unit 10 for third division KB1 will be described.

[0049] FIG. 9 is a diagram used to explain the intra-category analysis process related to the third category KB1. In the intra-category analysis process, the server information processing unit 10 refers to the investigation event management DB 21 and acquires each of the problem-solving pairs belonging to the third category KB1. In this example, as indicated by the symbol SY1 in FIG. 9, the server information processing unit 10 acquires 10 problem-solving pairs PA1 to PA10 as problem-solving pairs belonging to the third category KB1. Next, the server information processing unit 10 groups each of the acquired problem-solving pairs PA1 to PA10 based on the similarity of the content of the problem answers. Hereinafter, the groups generated by grouping will be referred to as "problem groups." The process related to grouping will be described in detail below.

[0050] The server information processing unit 10 includes each of the problem-solving pairs PA1 to PA10 and generates a prompt requesting that the problem-solving pairs be grouped according to the similarity in the content of the problem answers. The server information processing unit 10 then sends the prompt to the language model server 4 and obtains a response sentence. The server information processing unit 10 groups the problem-solving pairs based on the response sentence. The server information processing unit 10 assigns a task group ID, which serves as identification information, to each task group generated by the grouping. In this example, as shown by symbol SY2 in Figure 9, the server information processing unit 10 groups the problem-solving pairs PA1 to PA10 into three task groups KG1 to KG3. The above is the details of the grouping process.

[0051] After dividing the tasks into task groups, the server information processing unit 10 generates a summary (hereinafter referred to as a "task group summary") for each task group based on each of the task answers belonging to that task group. The following describes in detail the process by which the server information processing unit 10 generates a task group summary for task group KG1, one of the task groups in this example. The server information processing unit 10 generates a prompt that includes each of the task answers belonging to task group KG1 and requests that a summary be generated for each of the task answers. The server information processing unit 10 then sends the prompt to the language model server 4 and receives a response. The server information processing unit 10 obtains (generates) a task group summary from the response. The above is the detailed process for generating a task group summary for task group KG1. As indicated by reference symbol SY3 in FIG. 9, in this example, the server information processing unit 10 generates a task group summary for each of task groups KG1 to KG3.

[0052] In the following explanation, the task corresponding to one task group will be referred to as the "main task." In other words, the task answers belonging to one task group have similarities, but the totality of the task answers belonging to one task group corresponds to the "main task." The task group summary of one task group indicates the content of the main task of that task group. Multiple main tasks can belong to one third section. In this example, as shown in Figure 9, three main tasks belong to the third section KB1: the main task related to task group KG1, the main task related to task group KG2, and the main task related to task group KG3.

[0053] After generating a task group summary for each task group, the server information processing unit 10 executes the following process for each task group. That is, the server information processing unit 10 groups each of the solution answers belonging to the task group based on the similarity of their contents. Hereinafter, the groups generated by grouping are referred to as "solution groups." The process related to grouping will be described in detail below.

[0054] The server information processing unit 10 generates a prompt that includes each of the solution answers and requests that the solution answers be grouped based on the similarity of the content of each answer. The server information processing unit 10 then sends the prompt to the language model server 4 and receives a response sentence. The server information processing unit 10 groups the solution answers based on the content of the response sentence. The server information processing unit 10 assigns a solution group ID, which serves as identification information, to each solution group generated by the grouping. The above is a detailed description of the grouping process. As shown by reference character SY4 in FIG. 9, in this example, the server information processing unit 10 generates a task group summary for each of the task groups KG1 to KG3. In this example, as shown by reference character SY4 in FIG. 9, the server information processing unit 10 generates two solution groups SG1 and SG2 for the task group KG1, two solution groups SG3 and SG4 for the task group KG2, and two solution groups SG5 for the task group KG2.

[0055] After dividing the solutions into solution groups, the server information processing unit 10 generates a summary (hereinafter referred to as a "solution group summary") for each solution group SG1 to SG5 based on each of the solution answers belonging to the group. The following describes in detail the processing of the server information processing unit 10 when generating a solution group summary for solution group SG1. The server information processing unit 10 generates a prompt that includes each of the solution answers belonging to solution group SG1 and requests that a summary be generated for each of the solution answers. The server information processing unit 10 then sends the prompt to the language model server 4 and obtains a response. The server information processing unit 10 obtains (generates) a solution group summary from the response. The above is the detailed processing related to the generation of a solution group summary for solution group SG1. As indicated by reference symbol SY5 in FIG. 9, in this example, the server information processing unit 10 generates a solution group summary for each of solution groups SG1 to SG5.

[0056] Furthermore, the server information processing unit 10 uses the function of the language model 5 to generate, for each task group KG1 to KG3, an AI solution sentence that indicates, in text, a solution for improving the task (main task) corresponding to the task group based on the task answers belonging to the task group. Hereinafter, a solution corresponding to the AI ​​solution sentence will be referred to as an "AI solution." Below, the processing of the server information processing unit 10 when generating an AI solution sentence for task group KG1 will be described in detail. That is, the server information processing unit 10 generates a prompt that includes each task answer belonging to task group KG1 and requests the generation of a solution for solving the task indicated by the task answer. The server information processing unit 10 sends the prompt to the language model server 4 and obtains a response sentence from the server. The server information processing unit 10 obtains (generates) an AI solution from the response sentence. Note that the server information processing unit 10 may write a task group summary sentence in the prompt instead of or in addition to the task answer. The server information processing unit 10 may also write a solution answer belonging to task group KG1 in the prompt.

[0057] In the following explanation, a solution corresponding to one solution group is referred to as an "employee-proposed solution." In other words, the solution answers belonging to one solution group have similarities, but the totality of the solution answers belonging to one solution group corresponds to an "employee-proposed solution." The solution group summary for one solution group indicates the content of the employee-proposed solution for that solution group. Furthermore, the employee-proposed solutions and the AI ​​solutions are collectively referred to as the "main solutions."

[0058] The above is the intra-division analysis process. As described above, the server information processing unit 10 executes the intra-division analysis process for each of the third divisions. As a result, main problems and main solutions are generated for each of the third divisions (excluding third divisions to which no problem-solution pairs belong).

[0059] As described above, the server information processing unit 10 (information processing unit) has a function of classifying each problem-solving pair based on specific interviews conducted with multiple members into one of multiple problem categories. The server information processing unit 10 (information processing unit) also has a function of classifying each problem-solving pair into one of the lowest-level problem categories. The server information processing unit 10 (information processing unit) also has a function of grouping, for each problem category, the problem-solving pairs belonging to the problem category into one or more problem groups based on the problem answers, and for each problem group, grouping the solution answers belonging to the problem group into one or more solution groups. The server information processing unit 10 (information processing unit) also has a function of generating, for each problem group, a summary of the problem answers belonging to the problem group, using the function of the language model 5, and generating, for each solution group, a summary of the solution answers belonging to the solution group. The server information processing unit 10 (information processing unit) also has a function of generating, for each problem group, an AI solution based on the problem answers belonging to the problem group, using the function of the language model 5. This concludes the description of the first generation process.

[0060] Second generation process Next, the second generation process will be described. In the second generation process, the server information processing unit 10 executes the following process. That is, the server information processing unit 10 derives the task change tendency, task response priority, importance score, and urgency score for each main task (task group).

[0061] The problem change trend for a major problem is information indicating whether the major problem is improving, has not changed, or is worsening relative to similar major problems in past survey events. The server information processing unit 10 derives the problem change trend for each major problem using the functions of the language model 5. When deriving the problem change trend for a major problem, the server information processing unit 10 writes information about the major problem, information about similar major problems in past survey events, and other necessary information in a prompt sent to the language model server 4.

[0062] The issue response priority for a major issue refers to the priority with which the corresponding action should be taken for that major issue. In this embodiment, the issue response priority takes one of three levels: "High," which indicates the highest priority; "Low," which indicates the lowest priority; and "Medium," which is intermediate between "High" and "Low." This also applies to the solution response priority, which will be described later. The server information processing unit 10 derives the issue response priority for each major issue using the functions of the language model 5.

[0063] The importance score for a major issue is information that indicates the importance of that major issue by a numerical value (score). The importance of a major issue refers to the degree to which that major issue is important to the organization. In this embodiment, the importance score ranges from 0 to 100 points (points are a convenient unit). The same applies to the urgency score, feasibility score, and impact score described below. The server information processing unit 10 derives an importance score for each major issue using the functions of the language model 5. The importance score corresponds to the issue evaluation level that takes into account an evaluation of the issue's importance, which is a "predetermined indicator for the issue."

[0064] The urgency score for a major issue is information that indicates the urgency of that major issue using a numerical value (score). The urgency of a major issue refers to the degree of urgency for the organization to address that major issue. The server information processing unit 10 derives an urgency score for each major issue using the functions of the language model 5. The urgency score corresponds to the issue evaluation level that takes into account an evaluation of the urgency of the issue, which is a "predetermined indicator for the issue."

[0065] Furthermore, in the second generation process, the server information processing unit 10 executes the following process: That is, the server information processing unit 10 derives a solution response priority, a feasibility score, and an impact score for each of the main solutions (employee-proposed solutions and AI solutions).

[0066] The solution response priority for one main solution means the priority with which a corresponding action should be taken for that one main solution. The server information processing unit 10 derives the solution response priority for each main solution using the function of the language model 5.

[0067] The feasibility score for one main solution is information that indicates the feasibility of that one main solution by a numerical value (score). The feasibility of a one main solution means the degree of ease of realizing that one main solution for an organization. The server information processing unit 10 derives a feasibility score for each main solution using the functions of the language model 5. The feasibility score corresponds to the solution evaluation level that takes into account an evaluation of the solution's feasibility, which is a "predetermined indicator for the solution."

[0068] The impact score for one main solution is information that indicates the impact of that one main solution using a numerical value (score). Impact refers to the degree of influence (impact) on business operations when the main solution is adopted. The server information processing unit 10 derives an impact score for each main solution using the functions of the language model 5. The impact score corresponds to the solution evaluation level that takes into account an evaluation of the impact of the solution, which is a "predetermined indicator for the solution."

[0069] As described above, the server information processing unit 10 has the function of deriving an importance score (degree of overestimation) and an urgency score (degree of problem evaluation) for each problem group. The server information processing unit 10 also has the function of deriving a feasibility score (degree of solution evaluation) and an impact score (degree of solution evaluation) for each solution group. The server information processing unit 10 (information processing unit) also has the function of classifying each problem-solution pair into one of the third categories (lowest-level problem categories). This concludes the description of the second generation process.

[0070] Third generation process Next, the third generation process will be explained. In the third generation process, the server information processing unit 10 executes the following process. That is, the server information processing unit 10 uses the function of the language model 5 to generate a summary sentence based on each of the task answers belonging to the basic task category. Note that a task answer belonging to one category means a task answer that belongs to each of the third categories subordinate to that one category (however, if that one category is a third category, then that one category itself). This also applies to problem-solution pairs and solution answers. Therefore, a task answer belonging to a basic task category means all task answers. Hereinafter, a summary sentence based on each of the task answers belonging to the basic task category will be referred to as a "basic task summary sentence."

[0071] Furthermore, in the third generation process, the server information processing unit 10 executes the following process: For each of the first sections, the server information processing unit 10 uses the function of the language model 5 to generate a summary based on each of the assignment answers belonging to the first section.

[0072] Furthermore, in the third generation process, the server information processing unit 10 executes the following process. That is, for each of the second segments, the server information processing unit 10 generates a summary based on each of the assignment answers belonging to the second segment using the function of the language model 5. This concludes the description of the third generation process.

[0073] The server information processing unit 10 registers the processing results of the first generation process, the second process, and the third generation process (including the various types of generated information) in the investigation event management DB 21 in an appropriate manner.

[0074] <Scenes in which the Administrator uses this Service> Next, an example of the operation of the control system 1 in a scenario where an administrator uses the present service will be described. Below, one of the administrators will be referred to as the "noted administrator," and an example of the operation of the control system 1 will be described assuming that this noted administrator performs various tasks. Even if not otherwise specified, when the terminal information processing unit 13R displays various screens, the server information processing unit 10 provides the terminal information processing unit 13R with information necessary for displaying the screens. In particular, the server information processing unit 10 can obtain information necessary for displaying the screens from the investigation event management DB 21 and provide it to the terminal information processing unit 13R.

[0075] The administrator launches the dedicated application AP on his / her administrator terminal 3R and logs in to the service. After logging in, the administrator performs a predetermined operation to instruct the display of the main management screen 30. In response to this instruction, the terminal information processing unit 13R cooperates with the server information processing unit 10 to display the main management screen 30 on the terminal display unit 15R. FIG. 10 is a diagram showing an example of the main management screen 30 in its initial state. As shown in FIG. 10, the top of the main management screen 30 displays the number of people who were the subject of a specific interview (number of subjects), the number of people who actually underwent the specific interview (number of respondents), the ratio of the number of respondents to the number of subjects (response rate), and the period during which the specific interview was conducted (response period). The main management screen 30 also displays the number of main issues and the number of main solutions.

[0076] As shown in FIG. 10 , a graph display area 31 is provided on the left side of the main management screen 30. In the initial state of the main management screen 30, a basic graph 32 is displayed in this area. The basic graph 32 is a sunburst graph that displays all task divisions from level 0 to level 3 in a hierarchical structure. In other words, the basic graph 32 is a sunburst graph that displays task divisions according to a hierarchical structure with the basic task division at level 0 as the root. The angular size of each task division's sector in the sunburst graph corresponds to the number of major tasks belonging to the task division. The basic graph 32 and the first and second graphs 33 and 34 described below are composed of sunburst graphs, which visually show the hierarchical structure of the task divisions and indicate the number of major tasks belonging to each task division. Hereinafter, the basic graph 32, first graph 33, and second graph 34 displayed in the graph display area 31 are collectively referred to as "hierarchical graphs." By referring to the hierarchical graph, the focused manager can accurately grasp the distribution of major tasks while being aware of the hierarchical structure of the task divisions.

[0077] On the main management screen 30, a route summary display area 35 is formed to the right of the graph display area 31. The route summary display area 35 displays a summary corresponding to the issue category located at the root of the hierarchical graph (basic graph 32 in FIG. 10) displayed in the graph display area 31. Therefore, on the main management screen 30 in FIG. 10, the route summary display area 35 displays a basic issue summary corresponding to the basic issue category. By referring to the basic issue summary, the featured manager can recognize the overall issues of the featured company.

[0078] On the main management screen 30, a changeover switch 36 is provided below a route summary display area 35, and a matrix display area 37 is formed below the changeover switch 36. The changeover switch 36 is a switch for switching the diagram displayed in the matrix display area 37 between a problem matrix 38 corresponding to the problem and a solution matrix 39 corresponding to the solution. The default is the problem matrix 38, and the problem matrix 38 is displayed in Figure 10. The problem matrix 38 and the solution matrix 39 will be described later.

[0079] Each sector of the first and second divisions of the basic graph 32 is selectable. Hereinafter, the sector of the first division in the hierarchical graph will be simply referred to as the "first division." The same applies to the second and third divisions. When one of the first divisions in the basic graph 32 is selected, the terminal information processing unit 13R displays a first graph 33 consisting of a sunburst graph with the selected first division as its root in the graph display area 31, instead of the basic graph 32. Furthermore, the terminal information processing unit 13R displays a summary corresponding to the selected first division in the route summary display area 35, instead of the basic task summary. Figure 11 shows the main management screen 30 when the noted manager selects the first division "Human Resources" (reference symbol D1 in Figure 10) of the basic graph 32 in Figure 10. The graph display area 31 of the main management screen 30 shown in Figure 11 displays a first graph 33 consisting of a sunburst graph with the first division "Human Resources" selected by the noted manager as its root. Furthermore, the route summary display area 35 displays a summary corresponding to the first division "Human Resources."

[0080] The second section of the first graph 33 is selectable. When one of the second sections is selected in the first graph 33 (or the basic graph 32), the terminal information processing unit 13R displays a second graph 34 consisting of a sunburst graph with the selected second section as its root in the graph display area 31, in place of the first graph 33. Furthermore, the terminal information processing unit 13R displays a summary corresponding to the selected second section in the route summary display area 35. FIG. 12 is a diagram showing the main management screen 30 when the noted administrator selects the second section “Hiring” (symbol D2 in FIG. 11) of the first graph 33 in FIG. 11. As shown in FIG. 12, the graph display area 31 of the main management screen 30 displays the second graph 34 consisting of a sunburst graph with the second section “Hiring” selected by the noted administrator as its root. Furthermore, the route summary display area 35 displays a summary corresponding to the second section “Hiring.” Hereinafter, the main management screen 30 on which the second graph 34 is displayed will be referred to as the “second management screen 40.” The second segment of the route of the second graph 34 (= the second segment selected by the administrator) is called the "selected second segment."

[0081] As shown in FIG. 12, the terminal information processing unit 13R displays a lower area 41 at the bottom of the second management screen 40. The lower area 41 displays an issue block 42 for each of the main issues (issue groups) belonging to the selected second issue category. FIG. 13 is a diagram used to explain the selected second issue category "Adoption." As shown in FIG. 13, four third sections Q1 to Q4 belong to the selected second issue category "Adoption" (see also the second graph 34 in FIG. 12 for this point). Furthermore, seven main issues R1 to R7 belong to the four third sections Q1 to Q4 in the manner shown in FIG. 13. Focusing on the third section Q1, the main issues R1 and R2 belong to the third section Q1. Furthermore, 18 main solutions S1 to S18 belong to the main issues R1 to R7 in the manner shown in FIG. 13. Focusing on the main issue R1, the main solutions S1 to S3 belong to the main issue R1. Of these, the main solutions S1 and S2 are employee-proposed solutions, and the main solution S3 is an AI solution. Based on the above, the lower area 41 of Fig. 12 displays seven task blocks 42 corresponding to the main tasks R1 to R7 (however, only some of them are displayed in Fig. 12).

[0082] Below, we will focus on the task block 42-1 in Figure 12 and explain the display contents of the task block 42. The task block 42-1 is a block that corresponds to the main task R1 in Figure 13. As shown in Figure 12, the task block 42-1 displays a task status selection object 43. The task status selection object 43 is an object for setting the status of the main task R1 that corresponds to the task block 42-1. The status values ​​available are a value that indicates that the main task will be addressed, and a value that indicates that the main task will not be addressed. The concerned manager can use this object to set the status of the main task R1. The task block 42-1 also displays information indicating the first, second, or third division to which the main task R1 belongs.

[0083] The task block 42-1 also displays task change trend information 44, which indicates the task change trend. By referring to the information 44, the focused manager can understand the task change trend of the major task R1, and can use this as a reference when working on the major task R1, for example. The task block 42-1 also displays task response priority information 45, which indicates the task response priority. By referring to the information 45, the focused manager can understand the task response priority of the major task R1, and can use this as a reference when deciding the priority of working on the major tasks, for example. The task block 42-1 displays importance information 46, which indicates the importance score, and urgency information 47, which indicates the urgency score. The importance information 46 and urgency information 47 are configured as barometers that indicate the degree of score.

[0084] The task block 42-1 displays the task group summary (symbol 48) for the main task R1. The task group summary is a summary that summarizes the task answers of the task group corresponding to the main task R1 (see Figure 9). By referring to the task group summary in the task block 42-1, the focused manager can accurately grasp the content and gist of the main task R1.

[0085] The information displayed in the task block 42-1 corresponds to "information based on the task-solving pair." In other words, the terminal information processing unit 13R (information processing unit) has a function to provide the administrator with information based on the task-solving pair belonging to each task category. The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with a summary of the task answers for each task group.

[0086] As shown in FIG. 12, the assignment block 42-1 has selectable buttons, namely, an assignment answer details button 50, a re-interview button 51, and a solution confirmation button 52.

[0087] When the assignment answer details button 50 of the assignment block 42-1 is selected, the terminal information processing unit 13R pops up an assignment answer details screen 53 that displays a list of assignment answers belonging to the assignment group corresponding to the main assignment R1. The assignment answers belonging to the assignment group corresponding to the main assignment R1 are the assignment answers used to generate the assignment group summary sentence corresponding to the main assignment R1. Figure 14 shows the assignment answer details screen 53 popped up. As shown in Figure 14, the assignment answer details screen 53 displays an assignment answer block 54 for each assignment answer. The corresponding assignment answer is displayed in the assignment answer block 54. In addition, a dialogue confirmation button 55 is displayed in the assignment answer block.

[0088] When the dialogue confirmation button 55 is selected, the terminal information processing unit 13R pops up a dialogue content screen 56 that displays the content of the dialogue in which the corresponding task answer was spoken. FIG. 15 shows the dialogue content screen 56 popped up. As shown in FIG. 15, the dialogue content screen 56 displays the dialogue that took place in the specific interview in which the corresponding task answer was spoken. By referring to the dialogue content screen 56, the administrator of interest can recognize the process that led to the task answer and the interview question that corresponds to the task answer.

[0089] As described above, the terminal information processing unit 13R (information processing unit) has a function to provide the administrator with information based on the problem-solving pairs belonging to each problem category. The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with information based on the problem answers belonging to each problem group. The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with the problem answers belonging to each problem group.

[0090] Referring to FIG. 12, when the re-interview button 51 (first user interface) of task block 42-1 is selected, the terminal information processing unit 13R pops up a re-interview screen 57. FIG. 16 is a diagram showing the re-interview screen 57 popped up. As shown in FIG. 16, the re-interview screen 57 has a request input field 58 (second user interface) in which requests can be entered when re-interviewing the employee. Requests are a concept that broadly includes the main points / key points of the re-interview, things the employee wants to hear in the re-interview, the theme of the re-interview, and other matters that should be reflected in the re-interview. The re-interview screen 57 has an interview execution button 59.

[0091] When the noted manager inputs requests in the request input field 58 and selects the interview execution button 59, a notification is sent to each employee terminal 3E of the employee who provided an answer to the issue corresponding to the main issue R1. When the employee responds to the notification, the terminal information processing unit 13E uses the function of the language model 5 to conduct a re-interview with the employee to ask more detailed questions about the issue. In the re-interview, the terminal information processing unit 13E (AI interviewer) reflects the requests entered in the request input field 58 and conducts the re-interview. To achieve this, the terminal information processing unit 13E writes the requests in a prompt in an appropriate format and sends it to the language model server 4. In response to a request from the noted manager, the terminal information processing unit 13R displays a screen on the terminal display unit 15R showing information based on the results of the re-interview and provides the information to the noted manager.

[0092] The re-interview button 51 corresponds to a first user interface for specifying the task group to be re-interviewed. As described above, the terminal information processing unit 13R (information processing unit) has a function for providing the re-interview button 51 (first user interface) that allows the user to specify one of the task groups. The terminal information processing unit 13R (information processing unit) has a function for providing a request input field 58 (second user interface) that allows the user to input requests for the re-interview. The terminal information processing unit 13E (information processing unit) has a function for, using the function of the language model 5, conducting a re-interview with the member corresponding to the task answer belonging to the task group specified by the re-interview button 51, reflecting the requests entered in the request input field 58 (second user interface). The terminal information processing unit 13R has a function for providing information based on the results of the re-interview to the manager. With this configuration, the manager can conduct a re-interview with the employee corresponding to the key task to hear more details about the key task in accordance with the requests set by the manager. In particular, the manager does not need to conduct the re-interview himself / herself, thereby reducing the manager's workload.

[0093] 12, when the solution confirmation button 52 (FIG. 12) of the task block 42-1 is selected, the terminal information processing unit 13R expands the solution related area 60 below the task block 42-1. FIG. 17 is a diagram showing the expanded solution related area 60. As shown in FIG. 17, the solution related area 60 has a solution block 61 for each of the main solutions S1 to S3 (see FIG. 13) that correspond to (belong to) the main task R1.

[0094] Below, we will first focus on the solution block 61-1 and explain the display contents of the solution block 61 related to the employee-proposed solution. The solution block 61-1 is the solution block 61 corresponding to the main solution S1 (see Figure 13). A solution status selection object 62 is displayed in the solution block 61-1. The solution status selection object 62 is an object for setting the status of the main solution S1 corresponding to the solution block 61-1. As status values, a value indicating that the solution will be addressed and a value indicating that the solution will not be adopted are prepared. The focusing manager can use this object to set the status of the main solution.

[0095] The solution block 61-1 displays a mark MK indicating whether the corresponding main solution is an employee-proposed solution or an AI solution. The solution block 61-1 also displays solution response priority information 63 indicating the solution response priority. By referring to the information 63, the focused manager can accurately grasp the solution response priority of the main solution S1. The solution block 61-1 also displays feasibility information 64 indicating the feasibility score and impact information 65 indicating the impact score. The feasibility information 64 and impact information 65 are configured as barometers indicating the degree of the score.

[0096] The solution block 61-1 displays the solution group summary (reference numeral 66) of the main solution S1. The solution group summary is a summary of the solution answers of the solution group corresponding to the main solution S1 (see Figure 9). By referring to the solution group summary in the solution block 61-1, the focused manager can accurately grasp the content and gist of the main solution S1.

[0097] The solution block 61-1 has a solution answer details button 67. When the solution answer details button 67 is selected, the terminal information processing unit 13R pops up a solution answer details screen (not shown) displaying a list of solution answers belonging to the solution group corresponding to the main solution S1. The solution answers belonging to each solution group corresponding to the main solution S1 are the solution answers used to generate the solution group summary corresponding to the main solution S1. By referring to the solution answer details screen, the featured manager can recognize the specific content of the solution answer corresponding to the main solution S1. Note that, like the issue answer details screen, the solution answer details screen has a UI for checking the content of the dialogue of the specific interview in which the solution answer was given for each solution answer. The featured manager can use this UI to check the corresponding dialogue for the desired solution answer. Note that the solution answer details button 67 is displayed only in solution blocks 61 corresponding to employee-provided solutions and is not displayed in solution blocks 61 corresponding to AI solutions.

[0098] Next, focusing on the solution block 61-3 in Figure 17, the display contents of the solution block 61 related to the AI ​​solution will be explained. The solution block 61-3 is the solution block 61 corresponding to the main solution S3 (see Figure 13). As with the solution block 61-1, the solution block 61-3 displays a solution status selection object 62, a mark MK, solution response priority information 63, feasibility information 64, and impact information 65. The solution block 61-3 also displays the AI ​​solution text (reference number 68) of the main solution S3. By referring to the AI ​​solution text, the focused manager can accurately grasp the content and gist of the main solution S3.

[0099] By referring to the solution-related area 60 corresponding to the primary issue R1, the focused manager can check various information regarding the primary solutions S1 to S3 corresponding to the primary issue R1 and accurately understand the contents of the primary solutions S1 to S3. In particular, the primary solutions S1 and S2 are solutions that reflect the honest opinions of employees actually working at the focused company, and by referring to such primary solutions S1 and S2, the focused manager can obtain highly effective solutions. Furthermore, the primary solution S3 is a solution generated by the function of the language model 5, and by referring to such primary solution S3, the focused manager can consider solutions to the primary issue R1 from various perspectives and multiple angles.

[0100] The information contained in the solution block 61 and the information derived and provided from the block correspond to "information based on the problem-solving pair" and "information based on the solution answer belonging to the solution group." As described above, the terminal information processing unit 13R (information processing unit) has a function to provide the administrator with information based on the problem-solving pair belonging to the problem category for each problem category. The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with information based on the solution answer belonging to the solution group for each solution group. The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with a summary of the solution answer for each solution group. The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with an AI solution.

[0101] As described above, the matrix display area 37 displays the problem matrix 38 (third user interface) or the solution matrix 39 (fourth user interface). In FIG. 10, the problem matrix 38 is displayed in the matrix display area 37. As shown in FIG. 10, the problem matrix 38 is a diagram configured as an Eisenhower matrix. As shown in FIG. 10, the problem matrix 38 is divided into four main areas AR1 to AR4 by a main vertical axis and a main horizontal axis. Each of the four main areas AR1 to AR4 is further divided into four sub-areas by a sub-vertical axis and a sub-horizontal axis. In other words, the problem matrix 38 is divided into eight cells CE by the main vertical axis, main horizontal axis, sub-vertical axis, and sub-horizontal axis.

[0102] The main vertical axis and sub-vertical axis indicate the urgency of the main issue, while the main horizontal axis and sub-horizontal axis indicate the importance of the main issue. Based on this, the qualitative meaning of the four main areas can be explained as follows: Main area AR1, which corresponds to the first quadrant in the upper right, means "important and urgent," Main area AR2, which corresponds to the second quadrant, means "not important but urgent," Main area AR3, which corresponds to the third quadrant, means "neither important nor urgent," and Main area AR4, which corresponds to the fourth quadrant, means "important but not urgent." Furthermore, within a single main area, sub-areas located on the right side indicate greater importance than sub-areas located on the left side, and sub-areas located higher indicate greater urgency than sub-areas located lower.

[0103] As described above, the task matrix 38 has eight cells CE. Each cell CE defines a range of importance scores and a range of urgency scores that define the major tasks that should belong to that cell. Specifically, as shown in FIG. 18, the upper-right cell CE1 defines "75pt<Importance Score≦100pt, and 75pt<Urgency Score≦100pt." The lower-left cell CE2 defines "0pt≦Importance Score≦25pt, and 0pt≦Urgency Score≦25pt." Each cell CE in the task matrix 38 displays the number of major tasks that have the importance score and urgency score corresponding to that cell CE, among the major tasks belonging to the task category at the root of the hierarchical graph that is displayed at the same time. For example, referring to FIG. 10, the number "5" is displayed in the upper-right cell CE1. This means that of the major tasks (=all major tasks) belonging to the basic task category of the root of the basic graph 32, which is displayed at the same time, there are "five" major tasks with "75pt<Importance score≦100pt and 75pt<Urgency score≦100pt." Also, for example, referring to FIG. 11, the number "2" is displayed in cell CE1. This means that of the major tasks belonging to the first category "Human Resources" of the root of the first graph 33, which is displayed at the same time, there are "two" major tasks with "75pt<Importance score≦100pt and 75pt<Urgency score≦100pt."

[0104] Any cell CE can be selected in the task matrix 38. The focused manager can select one cell CE taking into consideration importance and urgency. When one cell CE is selected by the focused manager, the terminal information processing unit 13R displays a selected cell correspondence graph 70 in the graph display area 31. The selected cell correspondence graph 70 is a sunburst graph that hierarchically shows task classifications at the first, second, and third levels for the main tasks belonging to the selected cell CE. Furthermore, the terminal information processing unit 13R forms a lower area 41 and displays task blocks 42 for each of the main tasks belonging to the selected cell CE.

[0105] FIG. 19 is a diagram showing the main management screen 30 displayed by the terminal information processing unit 13R when cell CE1 is selected on the main management screen 30 of FIG. 10. The selected cell correspondence graph 70 in FIG. 19 is a sunburst graph corresponding to each of the major tasks belonging to cell CE1. By referring to the selected cell correspondence graph 70, the administrator in question can accurately grasp the hierarchical structure of the cell CE that he or she has selected. In addition, the lower area 41 in FIG. 19 displays task blocks 42 for each of the major tasks belonging to cell CE1. The administrator in charge can use the task blocks 42 to obtain information about the major tasks and perform various processes.

[0106] The cells CE of the task matrix 38 correspond to multiple target categories divided according to task evaluation levels (importance scores and urgency scores in this embodiment). As described above, the terminal information processing unit 13R (information processing unit) has a function to provide the task matrix 38 (third user interface) that allows a user to specify one of multiple cells CE (target categories) divided according to importance scores and urgency scores (task evaluation levels). The terminal information processing unit 13R (information processing unit) also has a function to provide the administrator with information based on task answers belonging to the cell CE (target category) specified in the task matrix (third user interface).

[0107] Referring to FIG. 10, the main management screen 30 is provided with a selector switch 36. As described above, the administrator can use the selector switch 36 to switch the diagram from the issue matrix 38 to the solution matrix 39. FIG. 20 is a diagram showing the main management screen 30 displayed by the terminal information processing unit 13R when the solution matrix 39 (fourth user interface) is selected with the selector switch 36. Hereinafter, the state in which the solution matrix 39 is selected with the selector switch 36 is referred to as the "solution selection state." As shown in FIG. 20, in the solution selection state, the solution matrix 39 is displayed in the matrix display area 37. The solution matrix 39 is an Eisenhower matrix with feasibility as the main horizontal axis and impact as the main vertical axis. The main area formed by the main vertical axis and the main horizontal axis is provided with a sub-horizontal axis indicating feasibility and a sub-vertical axis indicating impact, respectively. As a result, eight cells CE are formed in the solution matrix.

[0108] In each cell CE of the solution matrix 39, a feasibility score range and an impact score range are defined, defining the main solutions belonging to each cell CE, in a similar manner to the problem matrix 38. A cell CE of the solution matrix 39 displays the number of main solutions corresponding to the feasibility score and impact score of that cell CE. Each cell CE of the solution matrix 39 is selectable. When a cell CE is selected, the terminal information processing unit 13R forms a lower area 41 and displays solution blocks 61 for each of the main solutions belonging to that cell CE in the lower area 41. By referring to the lower area 41, the administrator in question can grasp the status of the main solutions and obtain various information from the perspective of the main solutions.

[0109] As described above, the terminal information processing unit 13R has a function of providing a solution matrix (fourth user interface) that allows a user to specify one of a plurality of cells CE (target categories) divided according to the feasibility score and the impact score (solution evaluation level). The terminal information processing unit 13R has a function of providing the administrator with information based on the solution answers that belong to the cell CE specified in the solution matrix (fourth user interface).

[0110] As described above, the information processing system according to this embodiment has the following functions. A function in which the terminal information processing unit 13E (information processing unit) uses the function of the language model 5 to conduct a specific interview with employees (members) of the target company (organization) to find out about the organization's challenges and solutions to those challenges. A function in which the server information processing unit 10 (information processing unit) extracts problem-solution pairs, which are combinations of problem answers that mention the problem and solution answers that mention the solution, from the results of the specific interview. A function in which the server information processing unit 10 (information processing unit) classifies each of the problem-solving pairs based on specific interviews conducted with multiple employees into one of multiple problem categories. A function in which the terminal information processing unit 13R (information processing unit) provides the administrator with information based on the problem-solving pairs belonging to each problem category for each problem category.

[0111] According to this configuration, through interviews using the language model 5, organizational issues perceived by employees and their solutions are elicited. The combinations of issues perceived by employees and their solutions are information that is directly or indirectly useful for organizational improvement, and thus is effective information for organizational improvement. According to the above configuration, multiple issue-related pairs are classified into multiple issue categories, and information based on the issue-related pairs for each category is provided to the manager. This allows the manager to accurately recognize information based on information effective for organizational improvement, such as "organizational issues perceived by employees and their solutions," organized by category. Moreover, according to the present disclosure, the interviews are conducted mechanically using the language model 5, thereby reducing the effort required to provide information to the manager compared to interviews conducted manually. In other words, according to the present disclosure, it is possible to enable managers to accurately recognize information effective for organizational improvement in the field of organizational improvement with as little effort as possible.

[0112] Although one embodiment of the present invention has been described above, the above embodiment merely illustrates one example of a specific embodiment of the present invention, and the technical scope of the present invention should not be construed as being limited thereby. In other words, the present invention can be embodied in various forms without departing from the gist or main features thereof. Below, variations of the above embodiment are presented. The following variations may be combined when possible.

[0113] <First Modification> The information processing system may be configured to have the following functions. A function in which the server information processing unit 10 (information processing unit) uses the function of the language model 5 to generate, for each problem category, a summary sentence of the problem answer and a summary sentence of the solution answer of the problem-solving pair belonging to the problem category. A function in which the terminal information processing unit 13R provides the administrator with a summary of the problem answer and a summary of the solution answer for each problem category. According to this configuration, the administrator can grasp the content and gist of the problem answers belonging to each problem category, as well as the content and gist of the solutions belonging to each problem category.

[0114] <Second Modification> The information processing system may be configured to have the following functions. A function in which the terminal information processing unit 13R (information processing unit) provides the administrator with the problem answers and solution answers of each problem-solving pair belonging to the problem category for each problem category. According to this configuration, the administrator can check each of the problem answers and solution answers that belong to each problem category.

[0115] <Other variations> In the above embodiment, the size of the angle of the sector of each problem category in the hierarchical graph was based on the number of main problems (main problems based on problem-solving pairs) belonging to the problem category. In this regard, the size of the angle of the sector of each problem category may also be based on the number of problem-solving pairs belonging to the problem category. In the above embodiment, the issue evaluation levels used in the issue matrix 38 were the importance score and the urgency score. In this regard, the issue evaluation levels used in the issue matrix 38 may be either the importance score or the urgency score, or may be issue evaluation levels corresponding to different indicators. The same applies to the solution matrix 39. The type of hierarchical graph does not have to be a sunburst graph, and the types of the problem matrix 38 and solution matrix 39 do not have to be Eisenhower matrices. In the above embodiment, the task categories are determined in advance. In this regard, the server information processing unit 10 (or another information processing unit) may be configured to generate task categories using the function of the language model 5. In the above embodiment, the task categories are hierarchical, but the task categories may not be hierarchical.

[0116] In the above embodiment, the company corresponds to the "organization," the employees correspond to the "members," and the managers of the target company correspond to the "manager." However, the organizations, members, and managers are not limited to the examples given in the above embodiment. · Specific interviews may be conducted via text-based chat rather than audio. In the above embodiment, information is provided by displaying the screen, but the information may be provided by a method other than displaying the screen. For example, the information may be provided by "provision of a file via email, communication tools, or other means," or "printing out a document containing the information." In the above embodiment, the entity using the service is a single company, but this is for the sake of simplicity, and the service can naturally be used by multiple organizations. In the above embodiment, a configuration may be adopted in which a browser executes some or all of the processing executed by the dedicated application AP. In the above embodiment, a part or all of the data stored in the server storage unit 12 may be stored in an external device accessible by the server information processing unit 10 (for example, a database server connected to the network N). The functional blocks shown in the above embodiments can be realized by any hardware or by a combination of any hardware and any software. In other words, these functional blocks are not limited to specific hardware.

[0117] The embodiments may also include the provision of a program executed by a computer in the information processing server 2, the employee terminal 3E, or the manager terminal 3R. The embodiments may also include the provision of a recording medium on which the program is recorded in a computer-readable manner. The recording medium may be a magnetic or optical recording medium or a semiconductor memory device. Specific examples include portable or fixed recording media such as flexible disks, hard disk drives (HDDs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray (registered trademark) discs, magneto-optical disks, flash memories, and card-type recording media.

[0118] Furthermore, in the above-described embodiment, a device having a certain function is not limited to the device exemplified as a device having that function. For example, let us focus on the "function of classifying problem-solving pairs into one of multiple problem categories" (referred to as the first function) and the "function of providing information based on the problem-solving pairs to the administrator for each problem category" (referred to as the second function). In the above-described embodiment, as shown in FIG. 21A, the server information processing unit 10 of the information processing server 2 has the first function, and the terminal information processing unit 13R of the administrator terminal 3R has the second function. In this configuration, the combination of the information processing server 2 and the administrator terminal 3R functions as an "information processing system." Furthermore, the server information processing unit 10 and the terminal information processing unit 13R each function as an "information processing unit." On the other hand, as shown in FIG. 21B, the terminal information processing unit 13R of the administrator terminal 3R may have the first and second functions. In this configuration, the administrator terminal 3R functions as an "information processing system," and the terminal information processing unit 13R functions as an "information processing unit." 21(C), the server information processing unit 10 may have the first and second functions. In this configuration, the information processing server 2 functions as an "information processing system," and the server information processing unit 10 functions as an "information processing unit." When the information processing units of multiple devices (e.g., the server information processing unit 10 and the terminal information processing unit 13R) each function as an "information processing unit," the functions provided in each information processing unit are not limited. A single function may also be realized by multiple information processing units. An information processing unit that realizes a certain function may be an information processing unit of a device other than the information processing server 2, the employee terminal 3E, and the manager terminal 3R. [Explanation of symbols]

[0119] 1. Control system (information processing system) 2. Information processing server (information processing system) 3E Employee terminal (information processing system) 3R Administrator terminal (information processing system) 10 Server information processing unit (information processing unit) 13E Terminal information processing unit (information processing unit) 13R Terminal information processing unit (information processing unit)

Claims

1. a function of the information processing unit to conduct a specific interview with members of an organization by using the function of the language model to elicit issues of the organization and solutions to the issues; a function of the information processing unit extracting problem-solution pairs, which are combinations of problem answers that mention a problem and solution answers that mention a solution, from the results of the specific interview; The information processing unit has a function of classifying each of the problem-solving pairs based on the specific interviews conducted with a plurality of members into one of a plurality of problem categories; The information processing unit has a function of providing, for each problem category, information based on the problem-solving pairs belonging to the problem category to an administrator. An information processing system comprising:

2. a function of the information processing unit to generate, for each problem category, a summary of the problem answer of the problem-solving pair belonging to the problem category or a summary of the solution answer, using the function of the language model; The information processing unit has a function of providing the administrator with a summary of the problem answer or a summary of the solution answer for each problem category.

2. The information processing system according to claim 1, wherein:

3. The information processing unit has a function of providing the problem answer or the solution answer of each of the problem-solving pairs belonging to the problem category to the administrator for each of the problem categories.

2. The information processing system according to claim 1, wherein:

4. The information processing unit has a function of grouping, for each problem category, the problem-solving pairs belonging to the problem category into one or more problem groups based on the problem answers, and grouping, for each problem group, the solution answers belonging to the problem group into one or more solution groups; The information processing unit has a function of providing, for each problem group, information based on the problem answers belonging to the problem group to the administrator, and also providing, for each solution group, information based on the solution answers belonging to the solution group to the administrator.

2. The information processing system according to claim 1, wherein:

5. a function of the information processing unit to generate, for each of the problem groups, a summary of the problem answers belonging to the problem group, and to generate, for each of the solution groups, a summary of the solution answers belonging to the solution group, by using the function of the language model; The information processing unit has a function of providing the administrator with a summary of the problem answers for each problem group, and providing the administrator with a summary of the solution answers for each solution group.

5. The information processing system according to claim 4.

6. The information processing unit uses the function of the language model to generate, for each problem group, an AI solution sentence that indicates a solution for improving the problem corresponding to the problem group as a sentence based on the problem answers belonging to the problem group; The information processing unit has a function of providing the AI ​​solution document to the administrator.

5. The information processing system according to claim 4.

7. The information processing unit has a function of providing the problem answers belonging to the problem group to the administrator for each problem group, and providing the solution answers belonging to the solution group to the administrator for each solution group.

5. The information processing system according to claim 4.

8. a function of the information processing unit to provide a first user interface that allows a user to specify one of the task groups; a function of the information processing unit to provide a second user interface that allows the user to input requests for a re-interview; a function of the information processing unit to use the language model function to conduct a re-interview with the member who belongs to the assignment group specified in the first user interface and corresponds to the assignment answer, while reflecting the requests input to the second user interface; The information processing unit has a function of providing information based on the result of the re-interview to the administrator.

5. The information processing system according to claim 4.

9. The information processing unit has a function of deriving an assignment evaluation level for each assignment group, the evaluation level taking into account an evaluation of a predetermined index related to the assignment; a function of the information processing unit to provide a third user interface that allows the user to specify one of a plurality of target categories divided according to the assignment evaluation level; The information processing unit has a function of providing the administrator with information based on the assignment answers that belong to the target category specified in the third user interface.

5. The information processing system according to claim 4.

10. The indicators related to the issues include at least one of an indicator indicating the importance of the issue and an indicator indicating the urgency of the issue.

10. The information processing system according to claim 9.

11. the information processing unit deriving, for each of the solution groups, a solution evaluation level that takes into account an evaluation of a predetermined index related to the solution; a function of the information processing unit providing a fourth user interface that allows the user to specify one of a plurality of target categories divided according to the solution evaluation level; the information processing unit has a function of providing the administrator with information based on the solution answer that belongs to the target category specified in the fourth user interface.

5. The information processing system according to claim 4.

12. The indicators related to the solution include at least one of an indicator indicating the feasibility of the solution and an indicator indicating the impact of the solution.

12. The information processing system according to claim 11.

13. The plurality of problem categories are hierarchically organized, The information processing unit has a function of classifying each of the problem-solving pairs into one of the problem categories at the lowest level.

2. The information processing system according to claim 1, wherein:

14. The information processing unit has a function of displaying, on a display unit, a graph showing the hierarchical structure of the problem categories and the number of the problem-solving pairs belonging to the problem categories.

14. The information processing system according to claim 13.

15. The information processing unit has a function of grouping the problem-solving pairs belonging to the problem category according to the similarity of the content of the problem answers; The information processing unit has a function of displaying on a display unit a graph showing the hierarchical structure of the task divisions and the number of main tasks corresponding to the groups belonging to the task divisions.

14. The information processing system according to claim 13.

16. The graph is a sunburst graph 16. The information processing system according to claim 14 or 15.

17. an information processing unit of the information processing system conducting a specific interview with members of an organization using a function of the language model to elicit issues of the organization and solutions to the issues; The information processing unit extracts problem-solution pairs, which are combinations of problem answers that mention a problem and solution answers that mention a solution, from the results of the specific interviews; a step in which the information processing unit classifies each of the problem-solving pairs based on the specific interviews conducted with a plurality of members into one of a plurality of problem categories; and a step in which the information processing unit provides, for each problem category, information based on the problem-solving pairs belonging to the problem category to an administrator.

1. An information processing method comprising:

Images