Program, method, information processing apparatus, and system

Abstract

To solve the problem that the review or target setting of a task can not be suitably performed.SOLUTION: A program to be executed by a computer including a processor and a storage unit, the program causing the processor to execute: a measurement value acquisition step of acquiring a measurement value indicating an activity status in work of a predetermined group including a plurality of users in a predetermined period; and a prompt step of generating an evaluation result based on the measurement value, A first generating step of generating a first prompt including the measurement value acquired in the measurement value acquiring step, an evaluation acquiring step of acquiring a result of evaluation by inputting the first prompt generated in the first generating step to a generation AI, and an evaluation outputting step of outputting the result of evaluation acquired in the evaluation acquiring step.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present disclosure relates to a program, a method, an information processing device, and a system. [Background technology]

[0002] 2. Description of the Related Art Information processing services that support business operations are known. Patent Document 1 discloses a technique that proposes a business support device, a business support method, and a business support program that more accurately support those under management in an organization, thereby supporting the business of the organization. Patent Document 2 discloses a business support device, a business support method, and a business support program that more accurately support the people under management in an organization, thereby supporting the business of the organization. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-049850 [Patent Document 2] Japanese Patent Publication No. 2021-163147 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a problem in that reviewing work or setting goals is not being carried out properly. Therefore, the present disclosure has been made to solve the above-mentioned problems, and its purpose is to provide a technology for appropriately reviewing work or setting goals.

[0005] There is a problem in that it is not possible to obtain measurement indicators suitable for improving business operations and to propose improvement measures (actions). Therefore, the present disclosure has been made to solve the above problems, and its purpose is to: The objective is to provide a technology that acquires measurement indicators suitable for improvement and proposes improvement measures (actions). [Means for solving the problem]

[0006] A program to be executed by a computer having a processor and a memory unit, wherein the processor executes the following steps: a measurement value acquisition step in which the processor acquires measurement values ​​indicating the activity status of a predetermined group of users in their work over a predetermined period of time; a first generation step in which the processor generates a first prompt that includes the measurement values ​​acquired in the measurement value acquisition step, which is a prompt that generates an evaluation result based on the measurement values; an evaluation acquisition step in which the first prompt generated in the first generation step is input into a generation AI to acquire an evaluation result; and an evaluation output step in which the processor outputs the evaluation result acquired in the evaluation acquisition step. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to appropriately review work or set goals. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Figure 3] FIG. 2 is a block diagram showing the functional configuration of a user terminal 20. [Figure 4] FIG. 10 is a diagram showing the data structure of a user table 1012. [Figure 5] FIG. 10 is a diagram showing the data structure of a group table 1013. [Figure 6] FIG. 10 is a diagram showing the data structure of a log table 1014. [Figure 7] FIG. 10 is a diagram showing the data structure of an evaluation table 1015. [Figure 8] FIG. 10 is a diagram showing the data structure of a target table 1016. [Figure 9]10 is a flowchart showing the operation of a review process. [Figure 10] 10 is a flowchart showing the operation of an improvement proposal process. [Figure 11] This is an example screen showing the output contents of the presented measurement values ​​and improvement proposals. [Figure 12] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated description will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0010] <System 1 Configuration> The system 1 in the present disclosure is an information processing system that provides an information service that supports reviewing work. The system 1 includes an information processing device including a server 10, a user terminal 20, and a generating AI 50, all of which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. As shown in FIG. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG.

[0011] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the user terminal 20, and the generation AI 50, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0012] <Server 10 configuration> The server 10 is an information processing device that provides an information service that supports reviewing work. The server 10 includes a storage unit 101 and a control unit 104 .

[0013] <Configuration of the storage unit 101 of the server 10> The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a group table 1013 , a log table 1014 , an evaluation table 1015 , and a target table 1016 .

[0014] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. Application programs 1011 include applications such as a web browser application.

[0015] User table 1012 is a table that stores and manages information about member users (hereinafter, "users") who use the service. When a user registers to use the service, the user's information is stored in a new record in user table 1012. This allows the user to use the service according to the present disclosure. The user table 1012 is a table having the user ID as a primary key and columns of user ID, user name, user data, and group ID. FIG. 4 is a diagram showing the data structure of the user table 1012. As shown in FIG.

[0016] The user ID is an item that stores user identification information for identifying a user. The user identification information is an item that is set with a unique value for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name. The user data includes information specific to the individual user and attribute information relating to the user's characteristics and background. The user's unique information includes information unique to the user, such as the user's date of birth (age), sex, and the like. The user's attribute information includes information such as the user's educational history (highest level of education, major, graduation year), occupation, work history, interests, place of residence, and language. This may include information such as the technology stack used in the product being developed by the specified group, the type of product being developed by the specified group, the language being used in the product being developed by the specified group, the framework being used in the product being developed by the specified group, and other technology attributes, which will be described in the group attributes section below. The group ID is an item for storing group identification information for identifying a group.

[0017] The group table 1013 is a table for storing and managing information about groups (group information). The group table 1013 is a table having columns for group ID, group name, and group attribute. FIG. 5 is a diagram showing the data structure of the group table 1013.

[0018] The group ID is an item for storing group identification information for identifying a group. The group name is an item for storing the name of the group. Any character string can be set as the group name. The group attribute is an item for storing attribute information of a group. Specifically, the attribute information includes the following information: The attribute information may be acquired from an external task management system (GitHub) or the like, or may be acquired by user input. Team size and role of each member (developer, tester, designer, project manager, etc.) Technology stack Front-end technologies (e.g. HTML, CSS, JavaScript, React, Angular, Vue.js) Backend technologies (e.g. Node.js, Django, Flask, SpringBoot, Ruby on Rails) Database technology (e.g., MySQL (registered trademark), PostgreSQL, MongoDB, Redis) Infrastructure technologies (e.g., Docker, Kubernetes, AWS, Azure, GCP) Product Type Web applications ·Mobile applications (iOS, Android) Desktop application Embedded systems Game Development ·SaaS Products Data analysis tools AI / ML models Languages ​​and Frameworks ·Programming languages ​​(e.g. JavaScript, Python, Java, C#, C++, Ruby, PHP) Frameworks and libraries (e.g., React, Angular, Vue.js, Django, Flask, Spring, .NET) Test frameworks (e.g., Jest, Mocha, JUnit, RSpec) Build tools (e.g., Webpack, Gulp, Maven, Gradle) Other technical attributes Version control systems (e.g. Git, SVN) ·CI / CD tools (e.g. Jenkins, TravisCI, CircleCI, GitLabCI / CD) Project management tools (e.g., Jira, Trello, Asana, Monday.com) Communication tools (e.g., Slack, Microsoft Teams, Discord) · Design tools (e.g. Adobe XD, Figma, Sketch)

[0019] The log table 1014 is a table for storing and managing information (log information) related to the logs of groups or individual users. In the present disclosure, indicators indicating the user's work status (which may be the same as the indicators shown in the log data items below) are collected from task management systems or schedule management systems such as GitHub, Trello, Asana, and Google Calendar, and stored in the log table 1014. Note that the server 10 may be configured to accept and store log data from users. The server 10 according to the present disclosure may be configured to execute control to calculate index values ​​(measured values) of the log data according to the present disclosure based on various indicators indicating the user's work status collected from the task management system. The log table 1014 is a table having a log ID as a primary key and columns of log ID, user ID, group ID, log data, period, and improvement information. FIG. 6 is a diagram showing the data structure of the log table 1014. As shown in FIG.

[0020] The log ID is an item that stores log identification information for identifying a log. The log identification information is an item that has a unique value set for each piece of log information. The user ID is an item that stores user identification information for identifying a user. When storing information related to the log of an individual user, the user identification information is stored in this item. Multiple user identification information may be stored. The group ID is an item for storing group identification information for identifying a group. When storing information related to a group log, the group identification information is stored in this item. Multiple group identification information may be stored. The log data is an item for storing log information relating to the business activity status of a group or user. Specifically, the log information includes the following information: Lead time: The time it takes for a business task (also known as a ticket, issue, or task) to be completed. It can be used as an indicator of the efficiency of the development process over a given period of time. Cycle time: The time from when work actually starts to when it is completed. It can be used as an indicator of the time required for pure work in a given period. Number of Issues Created: The number of business tasks (issues) created within a given period. Pull Requests Created: The number of pull requests created within a given period. Merged pull requests: The number of pull requests that were merged in the given period. · Number of Commits: The number of commits in a given period. · Number of Reviews: The number of code reviews performed in a given period. Mean Time to Resolve (MTTR): The average time it takes for a bug to be fixed after it is reported. This can be used as an indicator of quality control and response speed over a given period of time. Deployment frequency: The number of deployments within a given period. This can be used as an indicator of the activity and stability of development over a given period. Code review time: The time it takes for a pull request to be merged after it has been created. This can be used as an indicator of the code quality control process over a given period of time. Mean Time to Resolution (MTTR): The average time it takes for a business task to be resolved after it is created. It can be used as an indicator of the speed at which problems are resolved over a given period of time. Work in progress (WIP): The number of work in progress for a given period. This can be used as an indicator of the team's workload for a given period. On-time delivery rate: The percentage of tasks completed within the scheduled delivery time within a given period. This can be used as an indicator of a team's ability to meet commitments over a given period. Meeting Time: The total time spent in meetings during the given period. Meetings: The number of meetings held during the given period. The period is an item for storing the target period of the log information. Specifically, the start date and time and the end date and time that specify the target period are stored. The improvement information is an item that stores information (improvement information) related to the improvement of the log information. The improvement information may include information (improvement flag) indicating that the log information is a measurement value that has room for improvement, and evaluation indexes indicating the degree of room for improvement, such as importance, priority, and rank. The improvement flag includes graded index values ​​related to the log information, such as importance, priority, and rank.

[0021] The evaluation table 1015 is a table for storing and managing information relating to evaluations (evaluation information). A plurality of pieces of evaluation information may be stored for a plurality of pieces of log information. The evaluation table 1015 is a table having an evaluation ID as a primary key, and columns of an evaluation ID, a log ID, evaluation data, and vote data. FIG. 7 is a diagram showing the data structure of the evaluation table 1015.

[0022] The rating ID is an item for storing rating identification information for identifying a rating, and a unique value is set for each rating information. The log ID is an item for storing log identification information for identifying a log. The evaluation data is an item for storing an evaluation of the log information identified based on the log identification information. Specifically, the evaluation data stores a character string indicating an evaluation of the log information. The voting data is an item that stores the number of votes for the evaluation information. Specifically, users belonging to a group can vote on whether the evaluation information is good or bad.

[0023] The target table 1016 is a table for storing and managing information relating to targets (target information). A plurality of target information may be stored for a plurality of pieces of log information. The target table 1016 is a table having the target ID as a primary key, and columns of the target ID, the log ID, and the target data. FIG. 8 is a diagram showing the data structure of the target table 1016.

[0024] The target ID is an item for storing target identification information for identifying a target. The target identification information is an item for which a unique value is set for each piece of target information. The log ID is an item for storing log identification information for identifying a log. The target data is an item for storing a target for the log information identified based on the log identification information. Specifically, the target data stores a character string indicating a target for the log information.

[0025] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0026] The user registration control unit 1041 performs processing to store information about users who wish to use the service according to the present disclosure in the user table 1012. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a predetermined input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers the user information in the user table 1012, the service provider may conduct a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or may be automatically set by the user registration control unit 1041.

[0027] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses a service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or tablet, a stationary personal computer (PC) or a laptop PC, or a wearable terminal such as a head mounted display (HMD) or a wristwatch terminal. The user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .

[0028] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012 .

[0029] The user ID 2011 is the user's account ID. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID 2011 includes information such as a session ID temporarily assigned by the server 10 to identify the user using the user terminal 20.

[0030] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server or the like operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0031] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

[0032] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .

[0033] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082 .

[0034] <Configuration of generated AI50> Generative AI50 is a type of AI (artificial intelligence) system that uses machine learning algorithms to generate new content. Generative AI50 can generate various types of content, including text, images, audio, and video. Examples of generative AI50 include OpenAI ChatGPT, OpenAI DALL-E, Anthropic Claude, Google Gemini, Midjourney, and Stable Diffusion.

[0035] <System 1 Operation> Each process of the system 1 will be explained below. FIG. 9 is a flowchart showing the operation of the review process. FIG. 10 is a flowchart showing the operation of the improvement suggestion process.

[0036] <Review process> The review process is a process that supports a team (group) or an individual in reviewing their work activities over a predetermined period and setting goals (actions) for the next period. This disclosure will explain information processing that supports work reviews, primarily in software development projects, known as KPT retrospectives. KPT retrospectives are a framework for organizing specific improvements and success stories in project and work reviews. KPT stands for Keep, Problem, and Try, and each consists of the following three elements. Note that this disclosure can be applied to any work review framework other than KPT. It can also be applied to work reviews other than software development projects. Keep: Record what went well and what you want to continue. This is important for maintaining successful methods and effective processes in the future. Problem: Identify problems and areas that need improvement. Clarify current issues and what did not go well, and use this as a basis for improvement for next time. Try: Suggest new ideas and things you want to try next time. This is the phase where you come up with specific action plans to solve problems and ideas for trying new approaches.

[0037] <Outline of retrospective processing> The retrospective process is a process of acquiring measurements related to the work activities of a team (group) or individual, generating a first prompt including instructions for acquiring evaluation results related to the work activities based on the measurements, acquiring evaluation results based on information output by inputting the first prompt into the generation AI 50, voting on the evaluation results, and acquiring goals using a second prompt including instructions for acquiring goals based on the evaluation results and voting results. In this disclosure, an instruction refers to text information such as a general-purpose format or template (prompt format, prompt template) used to generate a prompt. A prompt refers to text information created by including a measurement value or other specific information (individual information) in the instruction. By inputting the prompt into the generation AI 50, a desired output result can be obtained from the generation AI 50.

[0038] <Details of the retrospective process> The review process will be described in detail below.

[0039] <Measurement value acquisition steps> In step S101, the control unit 104 of the server 10 executes a measurement value acquisition step of acquiring a measurement value indicating the activity status of a predetermined group of users in a given period of time in the course of their work. The measurement value acquisition step executes a step of acquiring measurement values ​​consisting of one or more index values ​​indicating the activity status of the business. The measurement value acquisition step includes a step of acquiring measurement values ​​of business tasks for a predetermined period consisting of at least one index value of lead time, cycle time, throughput, average bug fix time, deployment frequency, code review time, average resolution time, number of ongoing business tasks, first-time resolution rate, and delivery deadline compliance rate.

[0040] Specifically, the user operates the input device 206 of the user terminal 20 to execute a browser application or the like, and opens the review page by inputting the URL of a web page (review page) for executing the review process. The control unit 204 of the user terminal 20 transmits a request including the user ID 2011 for opening the review page to the server 10.

[0041] Upon receiving the request, the server 10 generates a review page and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the review page on the display 2081 of the user terminal 20. The review page includes an input field for inputting group identification information indicating the group (team) to be reviewed. Note that if the review target is an individual, the review page may also include an input field for inputting user identification information. The user inputs group identification information (first group ID) into an input field by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the input first group ID to the server 10. The control unit 104 of the server 10 searches the group ID item in the log table 1014 based on the received first group ID, and acquires one or more pieces of log information (first log information) including log data. The log information includes information about the business activity status of a group or user.

[0042] When the subject of the review is an individual, the user inputs user identification information (first user ID) into an input field by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the input first user ID to the server 10. The control unit 104 of the server 10 searches the user ID item in the log table 1014 based on the received first user ID, and acquires one or more pieces of log information including log data.

[0043] <First generation step> Step S102 In the method, the control unit 104 of the server 10 executes a first generating step of generating a first prompt by including the measurement value acquired in the measurement value acquiring step in a first instruction for generating an evaluation result based on the measurement value. Specifically, the control unit 104 of the server 10 creates the first prompt by inserting the measurement value acquired in step S101 into the ${measurement value} portion of the first instruction shown below. For example, the following value is inserted as the value of ${measurement value}: The measurement values ​​may also include FourKeys indicators (indicators) that are performance measurement indicators for software development teams calculated based on measurement values ​​obtained from a task management system. In other words, the measurement values ​​include any indicator values ​​calculated by combining measurement values. [Measurement value] Lead time: 5 days Cycle time: 3 days Throughput: 10 tasks / week Average bug fix time: 2 hours Deployment frequency: 20 times / week Code review time: 1 day Average resolution time: 3 hours Number of ongoing tasks: 5 First-time resolution rate: 90% Delivery on time rate: 95% [Index value] #Lead time for changes -Evaluate the time it takes from commit to production -Indicators for understanding issues in the development process and system infrastructure Current value: 5 days (lead time) #Change failure rate of production failures caused by deployments Indicators of system quality and release process health Related values: Deployment frequency 20 times / week #Average repair time Mean time to repair production failures Incident response efficiency indicators Current value: 2 hours (average bug fix time) #Deployment Frequency - Metric showing the number of deployments to the production environment Assess your continuous delivery maturity Current value: 4 times / day (20 times / week)

[0044] The first generating step may generate the first prompt by including, in the first instruction, a firstA instruction for generating an evaluation result based on attribute information indicating an attribute of the group and the attribute information of the predetermined group. The first generating step may generate a first prompt by including, in the first instructions, firstB instructions for generating an evaluation result based on evaluation criteria for each of one or more index values. Specifically, the control unit 104 of the server 10 creates the first prompt by inserting the attribute information of the group or user whose input was accepted in step S101 into the ${attribute information} portion of the first instruction shown below. For example, the following value is inserted as the value of ${attribute information}: It should be noted that the control unit 104 of the server 10 does not necessarily need to include the first A instruction, the attribute information, and the first B instruction in the first prompt. [Attribute information] Team size: 10 people Roles of each member: 3 front-end developers, 3 back-end developers, 2 testers, 1 designer, 1 project manager Technology stack: Front-end technologies: HTML, CSS, JavaScript, React Backend technology: Node.js, Django Database technology: MySQL (registered trademark), MongoDB Infrastructure technology: Docker, AWS Product type: Web application Languages ​​and Frameworks: ·Programming languages: JavaScript, Python Frameworks / libraries: React, Django Testing framework: Jest, Mocha Build tools: Webpack, Maven Other technical attributes: Version control system: Git ·CI / CD tools: Jenkins, GitLab CI / CD Project management tool: Jira Communication tool: Slack Design tool: Figma

[0045] [1st instruction] Based on the following measurements, the evaluation results of work performance (evaluation results to be used in KPT reviews) are output. The evaluation results will be done according to the instructions below. 1. Output the evaluation results taking into account the following attribute information of the person being evaluated (Instruction 1A) ·Attribute information:${Attribute information} 2. Output the evaluation results based on each evaluation criterion (Instruction 1B) Lead time: the shorter the better Cycle time: the shorter the better Throughput: the higher the better Average bug fix time: the shorter the better Deployment frequency: The higher the better (but keep in mind the rate of bugs) Code review time: within a reasonable time frame (not too short, not too long) ·Average resolution time: the shorter the better Number of ongoing work tasks: The right number (not too many, not too few) First-time resolution rate: the higher the better On-time delivery rate: the higher the better #Measurements: ${measurement value} #Evaluation results

[0046] The control unit 104 of the server 10 executes a first similarity extraction step of acquiring a second measurement value indicating the activity status of the reference group in the work similar to the measurement value acquired in the measurement value acquisition step, and a second evaluation result associated with the second measurement value. The first generation step may generate a first prompt by including the second measurement value and the second evaluation result acquired in the first similarity extraction step in a first instruction. Specifically, the control unit 104 of the server 10 searches for log data items in the log table 1014 based on the log data (first log data) acquired in step S101, and acquires log information (second log information) having one or more log data similar to the first log data. The similarity is calculated by cosine similarity, the inverse of Euclidean distance, the inverse of Manhattan distance, the inverse of Manhattan distance, Jaccard coefficient, Pearson correlation coefficient, or a weighted sum of similarities or distances output from one or more arbitrary algorithms when the log data is regarded as an independent vector of each measurement value included in the log data.

[0047] The first similarity extraction step may acquire a second measurement value (comparison value) and a second evaluation result of a reference group having attribute information similar to the attribute information of the predetermined group. The control unit 104 of the server 10 may acquire the second log information by taking into consideration the attribute information of the group. Specifically, when calculating the similarity of one or more pieces of second log information similar to the first log data, the control unit 104 of the server 10 takes into consideration the similarity of the group attribute of the group or the user data of the user (corresponding to the attribute information of the user) associated with the second log information. For example, the similarity of a group or user having attribute information similar to the attribute information of the group or user whose input was accepted in step S101 is calculated to be high, and the similarity of a group or user having dissimilar attribute information is calculated to be low. When each attribute information included in the attribute information is considered as an independent vector, the similarity can be calculated using cosine similarity, the inverse of Euclidean distance, the inverse of Manhattan distance, the inverse of Manhattan distance, Jaccard coefficient, Pearson correlation coefficient, or a weighted sum of similarities or distances output from one or more arbitrary algorithms. The similarity of the second log information is calculated by, for example, a weighted sum of the similarity based on the log data and the similarity based on the attribute information.

[0048] The control unit 104 of the server 10 acquires, as second log information, one or more log data whose similarity is equal to or greater than a predetermined value, or log information having a predetermined number of log data in descending order of similarity. The control unit 104 of the server 10 includes in the first instruction log data (measurement values) included in the second log information and evaluation data (evaluation information) that can be acquired by searching the item of the log ID in the evaluation table 1015 based on the log ID of the second log information. In other words, the first instruction may include log information (stored in the log table 1014) accumulated in past retrospective processing by this group or another group and the evaluation results for the log information (stored in the evaluation table 1015). For example, the first instruction includes the content of the following first instruction C. ${Measurement value example 1}, ${Evaluation result example 1}, ${Measurement value example 2}, and ${Evaluation result example 2} are each inserted with the log data items of one or more acquired second log information and the evaluation data items of the second evaluation result.

[0049] [1st C instruction] 3. Evaluation results are output based on the following past measurement value examples: ##Past evaluation example 1 ${Measurement value example 1} ${Evaluation result example 1} ##Past evaluation example 2 ${Measurement value example 2} ${Evaluation result example 2}

[0050] The first similarity extraction step may include a step of acquiring a second target associated with the second measurement value, and the first generation step may generate a first prompt by including the second target acquired in the first similarity extraction step in the first instruction. The control unit 104 of the server 10 includes goal data (goal information) that can be acquired by searching the log ID item in the goal table 1016 based on the log ID of the second log information. In other words, the first instruction may include log information (stored in the log table 1014) accumulated in past review processes by this group or another group and the goal for that log information (stored in the goal table 1016). For example, the first instruction includes the following content of the first D instruction: ${Measurement value example 1} and ${Target example 2} are inserted with the log data of one or more acquired second log information items and the target data items of the second target, respectively.

[0051] [1st D instruction] 4. Output the evaluation results by referring to the target cases for the following measurement values ​​taken in the past. Past Goal Example 1 ${Measurement value example 1} ${Target Case 1} Past Goal Example 2 ${Measurement value example 2} ${Target Case 2}

[0052] The first instruction may include the first instruction in addition to (combined with) the first instruction C, or in place of the first instruction C. For example, the first instruction may include the content of the following first instruction E:

[0053] [1st E instruction] 3. The evaluation results are output based on the evaluation results and target cases for the following measurement values ​​that have been evaluated in the past. ##Past evaluation example 1 ${Measurement value example 1} ${Evaluation result example 1} ${Target Case 1} ##Past evaluation example 2 ${Measurement value example 2} ${Evaluation result example 2} ${Target Case 2}

[0054] <Steps to obtain an evaluation> In step S103, the control unit 104 of the server 10 executes an evaluation acquisition step of acquiring an evaluation result by inputting the first prompt generated in the first generation step into the generation AI. The control unit 104 of the server 10 executes an evaluation acquisition step of acquiring a predetermined evaluation result for a task of a predetermined group in a predetermined period. The evaluation acquisition step acquires an evaluation result for each of one or more index values. The evaluation acquisition step is a step of acquiring evaluation results including at least one of items to be continued or items to be improved. Specifically, the evaluation acquisition step is a step of acquiring evaluation results regarding Keep (things to be continued) and Problem (issues) in the KPT review. Specifically, the control unit 104 of the server 10 transmits a request including the created first prompt to the API endpoint (URL) of the generation AI 50. The generation AI 50 outputs a response to the first prompt to the server 10. The response output by the generation AI 50 includes an evaluation result. Specifically, the generation AI 50 outputs the evaluation result described below. The evaluation result to be output is an evaluation result for the period (evaluation period) included in the log information related to the first log data acquired in step S101. Furthermore, when the first instruction includes a first B instruction, the response included by the generation AI 50 includes an evaluation result based on the evaluation criteria for each of one or more index values.

[0055] In this disclosure, an example in which the output result from the generation AI 50 is used as the evaluation result has been described as an example, but this is not limited to this. For example, a user according to this disclosure, a group member to be evaluated, or any other user may edit the output result from the generation AI 50 to create (modify, process) the evaluation result, and output the evaluation result. Such evaluation results are also included in the evaluation results obtained from the generation AI 50.

[0056] [Evaluation results] #Evaluation results ##Keep (things to continue) · Cycle time (3 days): Excellent Cycle times have been reduced by 30% compared to the previous period, and tasks are being processed efficiently. Average bug fix time (2 hours): Excellent Bug fix times have been reduced by 10% compared to the previous period, allowing us to respond more quickly. Deployment frequency (20 times / week): High frequency is good Code changes are occurring more frequently than in the previous period, and continuous improvements appear to be occurring. First-time resolution rate (90%): High We have seen the highest first-time resolution rate for bugs and issues in the past year, which suggests that we are solving problems effectively. · Delivery on time rate (95%): Excellent It seems that the delivery deadline is almost always met. ##Problem Throughput (10 tasks / week): Average As in the previous period, throughput is average and there is room for further improvement. Lead time (5 days): Good The lead time has increased by 1.5 hours compared to the previous period. There is a possibility that it can be shortened. #comprehensive evaluation The team maintains high performance across the board, with particular emphasis on cycle time, mean time to fix a bug, deployment frequency, first-time fix rate, and on-time delivery. Further improvements in throughput and lead times are expected to further improve overall performance. Also, there are fewer negative comments in the PR review!

[0057] The control unit 104 of the server 10 stores the log ID of the first log information acquired in step S101 and the acquired evaluation result in the log ID and evaluation data items of a new record in the evaluation table 1015.

[0058] In step S103, the control unit 104 of the server 10 executes an evaluation output step of outputting the evaluation result acquired in the evaluation acquisition step. Specifically, the control unit 104 of the server 10 transmits the acquired evaluation results to the user terminal 20. The control unit 204 of the user terminal 20 displays the received evaluation results on the display 2081 of the user terminal 20, etc. The evaluation results may be shared with all users belonging to the group related to the evaluation target using email, Slack, any other online tool, etc. Alternatively, the results may be output to a physical medium such as a whiteboard, sticky notes, or paper.

[0059] <First voting step> In step S104, the control unit 104 of the server 10 executes a vote receiving step of receiving votes from a plurality of users for the evaluation results output in the evaluation output step or processed information obtained by processing the evaluation results. Specifically, in step S103, users (team members) belonging to the group for which the evaluation results are output vote on the output evaluation results. For example, voting can be done by replying via email, by using a reaction such as a "Like" button in an online tool, or by other means such as "dot voting" using sticky notes or stickers on physical media such as whiteboards, sticky notes, or paper. When the voting target is a physical medium, a predetermined user inputs the voting results into an information processing terminal or the like, thereby capturing them as data. Voting may be performed for the entire evaluation result or for each of the multiple index values. In other words, voting results may be obtained for the entire evaluation result or for each of the multiple index values.

[0060] An example of the voting results is shown below. [Voting results] Keep Cycle time (3 days): Excellent 15 votes Average bug fix time (2 hours): Excellent 14 votes Deployment frequency (20 times / week): High frequency is good (12 votes) First-time resolution rate (90%): High (13 votes) Delivery on time rate (95%): Excellent 16 votes Problem Throughput (10 tasks / week): Average 10 votes Lead time (5 days): Good 8 votes

[0061] The control unit 104 of the server 10 stores the acquired voting results in the voting data item of the record in which the evaluation results were stored in step S103 in the evaluation table 1015. As a result, the log information, evaluation information, and voting results are stored in association with each other in the evaluation table 1015.

[0062] <Second generation step> In step S105, the control unit 104 of the server 10 executes a second generation step of generating a second prompt by including the measurement value acquired in the measurement value acquisition step and the evaluation result acquired in the evaluation acquisition step or processing information obtained by processing the evaluation result in the second instruction of generating a goal based on the measurement value and the evaluation result. Specifically, the control unit 104 of the server 10 creates the second prompt by inserting the evaluation result obtained in step S103 or the evaluation result edited by the user on the output result from the generation AI 50 (processed processing information) into the ${evaluation result} section of the second instruction shown below.

[0063] In the present disclosure, an example in which the second prompt is generated using the evaluation result output from the generation AI 50 in step S103 has been disclosed as an example, but this is not limiting. For example, instead of performing the information processing in steps S101 to S104 in the present disclosure, the evaluation work of the conventional KPT review may be performed manually, and only the information processing in steps S105 to S106 may be performed using the manually generated evaluation result. Similarly, it is possible to execute only the information processing related to steps S101 to S104, without executing the information processing of steps S105 to S106, and to manually perform the goal setting work of the conventional KPT review (corresponding to steps S105 to S106). In other words, it is not necessary to execute both the review processing (steps S101 to S104) and the goal setting processing (steps S105 to S106), and they can be executed separately and independently.

[0064] The second generating step may generate a second prompt by including, in the second instruction, a secondA instruction for generating a target based on attribute information indicating an attribute of the group and the attribute information of the predetermined group. The second generating step may generate a second prompt by including, in the second instructions, second instructions B for generating a goal based on evaluation criteria for each of the one or more index values. The second generating step may generate a second prompt by including, in the second instructions, secondC instructions for generating a goal based on the voting result and the votes received in the vote receiving step. It should be noted that the control unit 104 of the server 10 does not necessarily need to include the second A instruction, the second B instruction, the second C instruction, and the voting result in the second prompt.

[0065] [Second instruction] Based on the following evaluation results, output the goals (goals to be used in KPT retrospective). The goal is to output the following instructions: 1. Output the goal by taking into consideration the following attribute information of the person being evaluated (2A instruction) ·Attribute information:${Attribute information} 2. Output goals based on each evaluation criterion (2B instruction) Lead time: the shorter the better Cycle time: the shorter the better Throughput: the higher the better Average bug fix time: the shorter the better Deployment frequency: The higher the better (but keep in mind the rate of bugs) Code review time: within a reasonable time frame (not too short, not too long) ·Average resolution time: the shorter the better Number of ongoing work tasks: The right number (not too many, not too few) First-time resolution rate: the higher the better On-time delivery rate: the higher the better 3. Output the goal taking into account the following voting results on the evaluation results (2nd C instruction) ·Voting result:${Voting result} #Evaluation result: ${Evaluation result} #the goal:

[0066] The control unit 104 of the server 10 executes a second similar extraction step of acquiring a second measurement value (comparison value) indicating the activity status of the reference group in the work similar to the measurement value acquired in the measurement value acquisition step, and a second goal associated with the second measurement value. The second generation step may generate a second prompt by including the second evaluation result acquired in the second similar extraction step in the second instruction. Specifically, the control unit 104 of the server 10 searches for log data items in the log table 1014 based on the log data (first log data) acquired in step S101, and acquires log information (second log information) and target information (second target) having one or more pieces of log data similar to the first log data. The acquisition of the second log information and the second target is similar to the acquisition of the second log information and the second target in step S102.

[0067] The second similarity extraction step executes a step of acquiring a second measurement value (comparison value) of a reference group having attribute information similar to the attribute information of the predetermined group, and a second target. The control unit 104 of the server 10 may acquire the second log information and the second evaluation result in consideration of the attribute information of the group. The acquisition of the second log information and the second evaluation result is similar to the acquisition of the second log information and the second evaluation result in step S102.

[0068] For example, the second instruction includes the following content of the second D instruction: ${Measurement value example 1}, ${Target example 1}, ${Measurement value example 2}, and ${Target example 2} are filled with the log data items of one or more acquired second log information and the target data items of the second target, respectively.

[0069] [2nd D instruction] 4. Output the target based on the target examples for the following measurement values ​​taken in the past. Past Goal Example 1 ${Measurement value example 1} ${Target Case 1} Past Goal Example 2 ${Measurement value example 2} ${Target Case 2}

[0070] The second similarity extraction step may include a step of acquiring a second evaluation result associated with the second measurement value, and the second generation step may generate a second prompt by including the second measurement value acquired in the second similarity extraction step and the second goal in the second instruction. For example, the second instruction includes the following content of the second E instruction: ${Measurement value example 1}, ${Target example 1}, ${Measurement value example 2}, and ${Target example 2} are to be inserted with the items of log data of one or more pieces of acquired second log information and the items of target data of the second target, respectively.

[0071] [2nd E instruction] 5. Output the target based on the evaluation results of the following past measurement examples. ##Past evaluation example 1 ${Measurement value example 1} ${Evaluation result example 1} ##Past evaluation example 2 ${Measurement value example 2} ${Evaluation result example 2}

[0072] <Goal Acquisition Steps> In step S106, the control unit 104 of the server 10 executes a goal acquisition step of acquiring a goal by inputting the second prompt generated in the second generation step into the generation AI. The goal acquisition step executes a step of acquiring a goal for each of one or more index values. Specifically, the control unit 104 of the server 10 transmits a request including the created second prompt to the API endpoint (URL) of the generation AI 50. The generation AI 50 outputs a response to the second prompt to the server 10. The response output by the generation AI 50 includes a goal. Specifically, the generation AI 50 outputs the goals described below. The output goal is the evaluation result for the period (evaluation period) included in the log information related to the first log data acquired in step S101. Furthermore, when the second instruction includes a second B instruction, the response included by the generation AI 50 includes a goal based on the evaluation criteria for each of one or more index values.

[0073] In this disclosure, an example in which the output result from the generation AI 50 is used as a target has been described as an example, but this is not limited to this. For example, a user according to this disclosure, a group member to be evaluated, or any other user may edit the output result from the generation AI 50 to create (modify, modify) a target, and output the target. Such a target is also included in the target obtained from the generation AI 50.

[0074] 〔the goal〕 #the goal ##Try (Things you want to try) 1. Improved throughput Objective: Increase throughput to 20 tasks per week by implementing new agile methods and redesigning task management to maximize efficiency. 2. Shortening lead times Objective: To reduce lead time to three days or less, we will explore the introduction of process automation and efficiency tools to optimize work flow. 3.Other The average number of changed rows is the lowest in the past year. This is a very positive trend. To maintain a culture of making small changes frequently, continue to submit pull requests frequently before the changes become large. If large changes are necessary, try to break them down into stages. The development environment was slow to be established, resulting in a decline in work efficiency. Create scripts to automate the setup and updates of your development environment to speed up the process. Establish a process to regularly review your development environment and make any necessary updates or improvements quickly. 4. Overall There were many positive comments in this retrospective. Let's continue this positive atmosphere in the next retrospective. This energy will be a great driving force when we take on new challenges.

[0075] In step S106, the control unit 104 of the server 10 executes a target output step of outputting the target acquired in the target acquisition step. Specifically, the control unit 104 of the server 10 transmits the acquired goal to the user terminal 20. The control unit 204 of the user terminal 20 displays the received goal on the display 2081 of the user terminal 20, etc. Note that the goal may be shared with all users belonging to the group to be evaluated using email, Slack, or any other online tool. Alternatively, the goal may be output to a physical medium such as a whiteboard, sticky notes, or paper.

[0076] Based on the goals output in step S106, the user formulates goals (actions) for the next period of the development project. The user then performs the review process again when the next period ends. In this way, by repeatedly reviewing the work, the quality of the work, such as the development project, can be improved.

[0077] <Improvement proposal processing> The improvement proposal process is a process of acquiring measurement values ​​related to the work activities of a team (group) or individual, acquiring one or more measurement values ​​that have room for improvement among the measurement values, and acquiring predetermined measurement values ​​and improvement actions using a third prompt that includes instructions to associate each of the one or more measurement values ​​with a proposal for an improvement action, and presenting the measurement values ​​and improvement actions.

[0078] <Overview of improvement proposal processing> The improvement proposal process is a series of processes that acquires measurement values ​​related to the work activities of a team (group) or individual, generates a third prompt that includes instructions to acquire one or more measurement values ​​that have room for improvement from the measurement values ​​and to propose improvement actions in association with each of the one or more measurement values, acquires specified measurement values ​​and improvement actions based on the information output by inputting the third prompt into generation AI50, and presents the measurement values ​​and improvement actions. In addition, like the review process, the improvement proposal process may also be configured to acquire one or more measurement values ​​that have room for improvement for a team (group) or individual, and to take improvement action in association with each of the one or more measurement values.

[0079] <Details of improvement proposal processing>

[0080] The improvement suggestion process will be described in detail below.

[0081] <Measurement value acquisition steps> In step S301, the control unit 104 of the server 10 executes a measurement value acquisition step of acquiring a measurement value indicating the activity status of a predetermined group of users in a given period of time in the course of their work. Step S301 is the same as step S101. The log information to be acquired is the third log information.

[0082] <Third generation step> In step S302, the control unit 104 of the server 10 executes a third generation step of generating a third prompt, which is a prompt for acquiring predetermined measurement values ​​from among the measurement values ​​and includes the measurement values ​​acquired in the measurement value acquisition step. The third generation step generates a third prompt, which is a prompt for acquiring one or more measurement values ​​from among the measurement values ​​that have room for improvement (a prompt for acquiring one or more measurement values ​​from among the measurement values ​​that a predetermined group should focus on), and includes the measurement values ​​acquired in the measurement value acquisition step. Specifically, the control unit 104 of the server 10 creates the third prompt by inserting the measurement value acquired in step S301 into the ${measurement value} portion of the third instruction shown below. The value of ${measurement value} is the same as ${measurement value} in step S302 of the review process. Although the present disclosure discloses an example in which four measurement values ​​are output, other numbers may be used. Furthermore, the instruction may include instructions to output evaluation indices in association with each measurement value, which indicate the degree of room for improvement, such as importance, priority, and rank.

[0083] The third instruction includes the following instruction: - Instructions to obtain the index value that a specific group should focus on from multiple index values specifically, - Instructions to obtain indicator values ​​that can be improved - Instructions to obtain index values ​​with large improvements from the past -Instructions to obtain the index values ​​to be continued -Instructions to obtain index values ​​with potential for future growth

[0084] By inputting the third prompt into a large-scale language model, - The index value that a specific group should focus on from among multiple index values specifically, -Indicators with room for improvement -Indicator values ​​with large improvements from the past Indicators that should be continued -Indicator values ​​with great potential for future growth etc. can be obtained.

[0085] In this disclosure, for the sake of explanation, the review process and the improvement proposal process are described as different processes, but this is not limiting. For example, a series of processes including both the review process and the improvement proposal process may be realized as a configuration in which both processes can be executed in series or in parallel. Specifically, the first instruction in the review process may include an instruction related to the third instruction, and a prompt may be generated in which ${measurement value} represents a measurement value that can be commonly referenced in both the first and third instructions, and a measurement value and improvement proposal acquisition step S303 may be executed in the evaluation acquisition step S103. Similarly, a measurement value and improvement proposal presentation step S304 may be executed in the evaluation output step. An instruction that includes the first and third instructions may be called a thirteenth instruction, and a thirteenth prompt may be generated by including a measurement value in the thirteenth instruction (thirteenth generation step). In this case, the information obtained by inputting the 13th prompt into the large-scale language model includes both the output content (answer content) for the first instruction and the output content for the third instruction. The control unit 104 of the server 10 may be configured to execute step S103 and subsequent steps of the review process for the output content for the first instruction, and step S103 and subsequent steps of the improvement suggestion process for the output content for the third instruction. This allows the improvement proposal process to be included as part of the review process. This makes it possible to obtain one or more measurement values ​​that have room for improvement (one or more measurement values ​​that a specific group should focus on) from among the multiple measurement values ​​obtained along with the evaluation results. This reduces the number of instructions to the large-scale language model and processing time.

[0086] [Third instruction] Based on the measurements below, please output four measurements that have room for improvement. Associate each measurement with an evaluation index that indicates the degree of room for improvement, such as importance, priority, or rank. ${measurement value} #Measurements that could be improved

[0087] [Third instruction (first modified example)] Based on the following measurement values, please output the four measurement values ​​that show the greatest improvement from the past. Associate each measurement value with an evaluation index that indicates the degree of improvement, such as importance, priority, and rank. ${measurement value} #Measurements with large improvements from the past

[0088] [Third instruction (second modified example)] Based on the following measurements, please output four indicator values ​​that should be continued. Associate each measurement value with the reason why it should be continued. ${measurement value} #Continuous measurements

[0089] The thirteenth instruction is shown below. Note that instructions relating to the thirteenth instruction (first modified example) and the thirteenth instruction (second modified example) may be used, which are combinations of either the first instruction, the first-C instruction, or the first-D instruction with either the third instruction, the third instruction (first modified example), or the third instruction (second modified example). Also, instructions may be configured as including two or more of the first instruction, the first-C instruction, the first-D instruction, the third instruction, the third instruction (first modified example), and the third instruction (second modified example). [13th Instruction] Instruction 1: Based on the following measurements, the evaluation results of work performance (evaluation results to be used in KPT reviews) are output. The evaluation results will be done according to the instructions below. 1. Output the evaluation results taking into account the following attribute information of the person being evaluated (Instruction 1A) ·Attribute information:${Attribute information} 2. Output the evaluation results based on each evaluation criterion (Instruction 1B) Lead time: the shorter the better Cycle time: the shorter the better Throughput: the higher the better Average bug fix time: the shorter the better Deployment frequency: The higher the better (but keep in mind the rate of bugs) Code review time: within a reasonable time frame (not too short, not too long) ·Average resolution time: the shorter the better Number of ongoing work tasks: The right number (not too many, not too few) First-time resolution rate: the higher the better On-time delivery rate: the higher the better Instruction 2: Based on the measurements below, please output four measurements that have room for improvement. Associate each measurement with an evaluation index that indicates the degree of room for improvement, such as importance, priority, or rank. #Measurements: ${measurement value} #Evaluation results #Measurements that could be improved

[0090] In step S302, a third generating step generates a third prompt including a measurement value obtained by combining the plurality of measurement values ​​acquired in the measurement value acquiring step. The measurement values ​​may include FourKeys indicators (index values), which are performance measurement indicators of the software development team, calculated based on the measurement values ​​obtained from the task management system. In other words, the calculated measurement values ​​are calculated by combining the measurement values. In step S302, the third generation step generates a third prompt, which further includes one or more comparison values ​​(index values) indicating the activity status of the work of a reference group different from the predetermined group. The measurement value may include any index value that is set by the task management system. The measurement value may also include a measurement value that is a combination of any two or more measurement values ​​acquired from the task management system. Specifically, the measurement value may include a measurement value that is calculated by combining two or more measurement values. That is, the control unit 104 of the server 10 may generate the third prompt by including the index value in the third instruction. This makes it possible to identify index values ​​that have room for improvement based on the index values.

[0091] In step S302, the third generation step generates a third prompt that includes the measurement values ​​acquired in the measurement value acquisition step, which is a prompt that acquires one or more measurement values ​​that have room for improvement among the measurement values ​​and proposes improvement actions in association with each of the one or more measurement values. Specifically, the control unit 104 of the server 10 creates the 3A prompt by inserting the measurement value acquired in step S301 into the ${measurement value} portion of the 3A instruction shown below. The value of ${measurement value} is the same as ${measurement value} in step S302 of the review process.

[0092] [3rd A instruction] Based on the following measurements, output four measurements that have room for improvement. Associate each measurement with an evaluation index showing the importance, priority, rank, etc. that indicates the degree of room for improvement. Also, associate each measurement with an improvement action that should be taken. ${measurement value} #Measurements that could be improved

[0093] Specifically, the control unit 104 of the server 10 creates a 3B prompt by inserting the measurement value acquired in step S301 into the ${measurement value} portion of the 3B instruction shown below. The value of ${measurement value} is the same as the ${measurement value} in step S302 of the retrospective processing. The value of ${reference case} is inserted as the value of the log data acquired by searching the group ID in the log table 1014 based on the group ID of a reference group different from the target group in step S301. Note that the value of ${reference case} may include, in addition to the log data, information indicating activities such as improvement actions (improvement measures) taken by the reference group. An example of a reference case is shown below. [Reference example] #Improvement actions to increase deployment frequency: We established a continuous integration / delivery (CI / CD) pipeline, which included introducing automated tests, creating deployment automation scripts, and setting quality gates, and succeeded in streamlining the deployment process by 30%. #Improvement actions to shorten lead time: By introducing a Kanban board and setting WIP limits, they were able to visualize work and optimize parallel work. They also set size limits for pull requests and streamlined the review process, reducing lead time by 40%. #Improving code review efficiency: By formulating review guidelines and introducing an automated code review tool, review time was reduced by 50%. Furthermore, pair programming was partially introduced, resulting in early quality improvements. #Improvement actions for optimizing task management: By introducing a Scrum framework and streamlining daily stand-up meetings, we improved task progress management, promoted the division of tasks into smaller ones, promoted parallel work, and eliminated bottlenecks.

[0094] [3rd B instructions] Based on the following measurements, output four measurements that have room for improvement. Associate each measurement with an evaluation index showing the importance, priority, rank, etc. that indicates the degree of room for improvement. Also, associate each measurement with an improvement action that should be taken. ${measurement value} #Reference example ${Reference example} #Measurements that could be improved

[0095] <Steps for obtaining measurement values ​​and improvement proposals> In step S303, the control unit 104 of the server 10 executes a measurement value acquisition step of acquiring a predetermined measurement value by inputting the third prompt generated in the third generation step into the generation AI. Specifically, the control unit 104 of the server 10 sends a request including the created third prompt (which may be the 3A prompt or the 3B prompt) to the API endpoint (URL) of the generation AI 50. The generation AI 50 outputs a response to the third prompt (the 3A prompt or the 3B prompt) to the server 10. The response output by the generation AI 50 includes measurement values ​​that have room for improvement. Specifically, the generation AI 50 outputs the measurement values ​​that have room for improvement described below. The measurement values ​​that have room for improvement that are output are measurement values ​​that have room for improvement for the period (evaluation period) included in the log information related to the third log data acquired in step S301. If the third instruction includes an instruction to output an evaluation index that indicates the importance, priority, rank, etc. that indicate the degree of room for improvement in association with the measurement values, the response includes evaluation indexes that indicate the importance, priority, rank, etc. that indicate the degree of room for improvement for each of the measurement values ​​that have room for improvement. Furthermore, when the third instruction includes a third A instruction and a third B instruction, the response included in the generated AI 50 includes an improvement action to be performed for each of one or more measurement values ​​that have room for improvement. The control unit 104 of the server 10 stores the response obtained from the generation AI 50 in the improvement information item of the record of the log information related to the target measurement value in the log table 1014 (searched and identified by the log ID, log data, period, etc.). Note that the control unit 104 of the server 10 may store the measurement value and the improvement information in association with the measurement value in a table (not shown) or the like, instead of the log table 1014.

[0096] An example output of generated AI50 based on prompts 3, 3A, and 3B is shown below. [Measurements that could be improved (prompt 3)] #Measurement value 1: Throughput (10 tasks / week) ·Importance: A The current value is average, and there is a lot of room for improvement. ·Metrics that have a direct impact on improving team productivity #Measurement value 2: Lead time (5 days) ·Importance: B This is an increase of 1.5 hours compared to the previous period, and there is room for reduction. Key indicators that affect customer satisfaction #Measurement 3: Code review time (1 day) ·Importance: B - Timely, but there is room for improvement -A balance between maintaining quality and speed is required #Measurement 4: Number of ongoing work tasks (5) Importance: C The current state is adequate, but there is room for optimization. -Indicators that affect team work efficiency

[0097] [Measurements with room for improvement (prompt 3A)] #Measurement value 1: Throughput (10 tasks / week) ·Importance: A The current value is average, and there is a lot of room for improvement. ·Metrics that have a direct impact on improving team productivity Improvement actions: -Redesign task segmentation and prioritization - Strengthen progress management through daily stand-ups -Regular knowledge sharing within the team -Increase efficiency by introducing automation tools #Measurement value 2: Lead time (5 days) ·Importance: B This is an increase of 1.5 hours compared to the previous period, and there is room for reduction. Key indicators that affect customer satisfaction Improvement actions: -Identifying and improving bottleneck processes -Facilitating parallel work and process improvement -Improved efficiency of review system - CI / CD pipeline optimization #Measurement 3: Code review time (1 day) ·Importance: B - Timely, but there is room for improvement -A balance between maintaining quality and speed is required Improvement actions: -Establishment of review guidelines -Utilizing automated code review tools -Pilot implementation of pair programming -Small pull requests are encouraged #Measurement 4: Number of ongoing work tasks (5) ·Importance: C The current state is adequate, but there is room for optimization. -Indicators that affect team work efficiency Improvement actions: -Setting and operating WIP limits - Clarification of prioritization rules -Optimize task allocation - Conducting weekly backlog reviews

[0098] [Measurements that could be improved (prompt 3B)] #Measurement value 1: Throughput (10 tasks / week) ·Importance: A The current value is average, and there is a lot of room for improvement. ·Metrics that have a direct impact on improving team productivity Reference cases and improvement actions: - Team A Case Study: Achieving 15 tasks per week with automation → Test automation and CI / CD maintenance improve efficiency by 30% - Team B Case Study: Achieving 18 tasks / week by improving task division → Promoting parallel work by dividing tasks into smaller ones #Measurement value 2: Lead time (5 days) ·Importance: B This is an increase of 1.5 hours compared to the previous period, and there is room for reduction. Key indicators that affect customer satisfaction Reference cases and improvement actions: -C Team Case Study: Achieved reduction to 3 days →Improve reviews and introduce pair programming -D Team Case Study: Achieved reduction to 3.5 days → Use Kanban boards and WIP limits #Measurement 3: Code review time (1 day) ·Importance: B - Timely, but there is room for improvement -A balance between maintaining quality and speed is required Reference cases and improvement actions: -E Team Case Study: Achieved reduction to 0.5 days → Introduction of AI review tools and clarification of standards - Team F Case: Achieved reduction to 0.7 days →Pull request size limit and review priority setting #Measurement 4: Number of ongoing work tasks (5) ·Importance: C The current state is adequate, but there is room for optimization. -Indicators that affect team work efficiency Reference cases and improvement actions: -G Team Case Study: Achieving optimization in 3 tasks → Strict implementation of the Kanban system and daily review -H Team Case Study: Achieving stable operation with 4 tasks → Prioritize and establish weekly review

[0099] <Measurement value and improvement proposal presentation step> In step S304, the control unit 104 of the server 10 executes a measurement value output step of outputting the measurement value acquired in the measurement value acquisition step. Specifically, the control unit 104 of the server 10 transmits to the user terminal 20 information such as instructions to output the measurement values ​​that have room for improvement obtained in step S303, evaluation indicators that indicate the degree of room for improvement, importance, priority, rank, etc., and improvement actions. The control unit 204 of the user terminal 20 displays the received information on the display 2081 of the user terminal 20 or the like (measurement value / improvement proposal screen D1). The information may be shared with all users belonging to the group that is the target of the improvement proposal process using email, Slack, or any other online tool. Alternatively, the information may be output to a physical medium such as a whiteboard, sticky notes, or paper.

[0100] Figure 11 is an example screen showing the output contents of the presented measurement values ​​and improvement proposals. The measurement value and improvement proposal screen D1 includes an explanatory text D101 about the index values ​​that have room for improvement, a performance presentation field D102 showing the performance (evaluation) of the group that is the target of the improvement proposal process, improvement effects D103, and improvement actions D104. In this disclosure, the "number of pull requests created per person per day (hereinafter referred to as the presented index value)" will be described as an example of an index value (measurement value) to be improved. Note that in step S303, if multiple index values ​​are acquired, a measurement value and improvement proposal screen D1 is created for each of the multiple index values ​​and presented to the user. Alternatively, a measurement value and improvement proposal screen D1 may be created for statistical values ​​(median, average, maximum value, minimum value, etc.) of index values ​​related to some or all of the multiple index values ​​and presented to the user. The performance presentation column D102 shows the distribution of the entire market (companies that have adopted the information service described herein, all users) by classifying the target indicator value (number of pull requests per person per day) into four categories based on their ranking. Specifically, the categories are Elite (top 25% or more), High (top 50% or more, less than 25%), Medium (top 75% or more, less than 50%), and Low (top 100% or more, less than 75%), starting from the top of the triangle. Ranking may also be based on any score, such as standard deviation, instead of order. D102 shows that the group targeted for improvement proposal processing (your team) currently ranks low (top 100% or more, less than 75%) for the target indicator value. Additionally, for each of the Elite, High, Medium, and Low categories, the indicator value statistics (less than 200 lines, less than 400 lines, less than 800 lines, and less than 1600 lines) are displayed in association with each category. Furthermore, the group's target index value (1500 lines) is presented in comparison with the index values ​​of each category (less than 200 lines, less than 400 lines, less than 800 lines, and 1600 lines), allowing users to visually confirm the specific target value (less than 800 lines) and how much the group needs to improve its index value to move to a higher category (Medium).Users can visually confirm where (rank) the group's index value is positioned within the overall market, and how much improvement is required. The improvement effect D103 is a field that presents information indicating the improvement effect on the presentation target index value acquired in step S302. The improvement effect D103 presents to the user what benefits can be obtained by working to improve this index value. The improvement action D104 is a field that presents information indicating improvement measures (improvement actions) for the indicator values ​​to be presented in step S302. Specifically, it presents to the user improvement measures that the group or user should take. The improvement action D104 may also include information indicating the specific amount of improvement in the indicator value required to move (rank up) to a higher category among the multiple categories presented in D102 (reducing the granularity of the pull request to about half (750 lines)). This allows the user to confirm specific efforts toward the improvement action. Additionally, the order of presentation, presentation mode, etc. of multiple index values ​​(measured values) to be improved may be changed depending on the importance of the index value, such as the size of the improvement range of the index value, priority, etc. For example, index values ​​with high importance, priority, etc. may be presented preferentially on the measured value / improvement proposal screen D1.

[0101] The procedure for creating the measurement value and improvement proposal screen D1 is described below. The user operates the input device 206 of the user terminal 20 to select a measurement value to be presented on the measurement value and improvement proposal screen D1. The input device 206 of the user terminal 20 may present one or more types of measurement values ​​on the display 2081 of the user terminal 20 in a selectable manner based on the types of measurement values ​​stored in the log data items of one or more pieces of log information previously stored in the log table 1014. The user selects a predetermined type of measurement value by operating the input device 206 of the user terminal 20. In the present disclosure, the user selects a measurement value related to the "number of pull requests per person per day." The control unit 204 of the user terminal 20 transmits a request to the server 10 to create the measurement value and improvement proposal screen D1, including the type of measurement value (number of pull requests per person per day). Upon receiving the request, the control unit 104 of the server 10 searches the log data items in the log table 1014 based on the type of measurement value and acquires log information for all users. Note that the log information acquired by the control unit 104 of the server 10 does not need to be all log information, and log information for one or more users over a predetermined period may be acquired. The control unit 104 of the server 10 may acquire only part of the log information. The control unit 104 of the server 10 groups the log data by user ID and calculates statistical values ​​(median, average, maximum value, minimum value, etc.) for the measurement value for each user ID. The control unit 104 of the server 10 calculates a ranking (statistical distribution) based on the measurement value for each user ID. The control unit 104 of the server 10 compares the measurement value values ​​(1,500 rows) of the presentation target user with the statistical distribution to determine whether the presentation target user falls into one of the categories: Elite, High, Medium, or Low. The control unit 104 of the server 10 generates a score presentation field D102 indicating the position of the target user in association with the distribution of the measurement values ​​for each category (Elite, High, Medium, Low), and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received score presentation field D102 on the display 2081 of the user terminal 20. The control unit 104 of the server 10 searches the log data and user ID items in the log table 1014 based on the type of measurement value and the user ID of the user to whom the information is to be presented, and acquires the improvement information stored in association with the measurement value to be presented. The control unit 104 of the server 10 generates an improvement effect D103 and an improvement action D104 based on the acquired improvement information, and transmits them to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received improvement effect D103 and improvement action D104 on the display 2081 of the user terminal 20.

[0102] <Basic computer hardware configuration> 12 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main memory device 902, an auxiliary memory device 903, and a communication IF 991 (interface), which are electrically connected to one another by a communication bus 921.

[0103] The processor 901 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0104] The main memory device 902 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0105] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0106] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.

[0107] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0108] <Basic functional configuration of computer 90> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 12) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0109] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0110] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0111] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0112] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can allocate a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with the programs. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0113] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Typically, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0114] Note that the databases and masters in this disclosure may include any data structure in which information is structurally defined (such as a list, dictionary, associative array, or object). The data structure also includes data that can be considered as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

[0115] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0116] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0117] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, the program executing the following steps: a measurement value acquisition step (S101) in which the processor acquires measurement values ​​indicating the activity status of a predetermined group of users in their work over a predetermined period of time; a first generation step (S102) in which a first prompt is generated that includes the measurement values ​​acquired in the measurement value acquisition step, which is a prompt that generates an evaluation result based on the measurement values; an evaluation acquisition step (S103) in which the first prompt generated in the first generation step is input into a generation AI to acquire an evaluation result; and an evaluation output step (S103) in which the evaluation result acquired in the evaluation acquisition step is output. This makes it possible to obtain an evaluation result of the work activity status of a predetermined group of multiple users over a predetermined period of time. This allows for convenient review of work within the group.

[0118] (Appendix 2) 2. The program according to claim 1, wherein the evaluation acquisition step (S103) is a step of acquiring an evaluation result including at least one of an item to be continued or an item to be improved. This makes it possible to obtain an evaluation result for the business activity status of a predetermined group of multiple users over a predetermined period, taking into consideration the attribute information of the group. The review of work can be carried out appropriately by taking into consideration the attribute information of the group.

[0119] (Appendix 3) The program according to claim 1 or 2, wherein the first generation step (S102) is a step of generating a first prompt including an instruction to generate an evaluation result based on attribute information indicating the attributes of the group and attribute information of a specified group. This allows us to obtain an evaluation result of the business activity status of a given group of multiple users over a given period of time, taking into account the group's technology stack, product type, language, framework, and other technical attributes. Work reviews can be tailored to take into account the group's technology stack, product types, languages, frameworks, and other technical attributes.

[0120] (Appendix 4) The program of claim 3, wherein the attribute information includes at least one of a technology stack used in a product being developed by the specified group and a type of product being developed by the specified group. This allows the evaluation result of the work activity status of the group for a predetermined period to be acquired, taking into consideration one or more evaluation criteria of the index value. This allows for an appropriate review of work.

[0121] (Appendix 5) A program described in any of Appendices 1 to 4, wherein the measurement value acquisition step (S101) is a step of acquiring a measurement value consisting of one or more index values ​​that indicate the activity status in the business, and the first generation step (S102) is a step of generating a first prompt including instructions to generate an evaluation result based on evaluation criteria for each of the one or more index values. This allows you to obtain an evaluation result of the business activity status of the group over a specified period, taking into account evaluation criteria such as business task lead time, cycle time, throughput, average bug fix time, deployment frequency, code review time, average resolution time, number of ongoing business tasks, first-time resolution rate, and delivery deadline compliance rate, allowing you to conveniently review your business.

[0122] (Appendix 6) The program described in Appendix 5, wherein the measurement value acquisition step (S101) is a step of acquiring measurement values ​​of business tasks over a specified period, which consist of at least one index value of lead time, cycle time, throughput, average bug fix time, deployment frequency, code review time, average resolution time, number of ongoing business tasks, first-time resolution rate, and delivery date compliance rate. This allows for more appropriate evaluation results to be obtained for the business activity status of a specified group over a specified period, taking into account the measurement values ​​and evaluation results of other groups similar to the specified group that have been accumulated in past KPT reviews.

[0123] (Appendix 7) A program described in any of Appendices 1 to 6, wherein a processor executes a first similar extraction step (S102) to acquire a second measurement value (comparison value) indicating the activity status in the work of a reference group that is similar to the measurement value acquired in the measurement value acquisition step, and a second evaluation result associated with the second measurement value, and the first generation step (S102) is a step of generating a first prompt including the second measurement value and the second evaluation result acquired in the first similar extraction step. This allows the evaluation results of other groups similar to a given group to be acquired by taking into account the attribute information of the group, thereby enabling more suitable evaluation results to be acquired.

[0124] (Appendix 8) 8. The program according to claim 7, wherein the first similarity extraction step (S102) is a step of acquiring a second measurement value and a second evaluation result of a reference group having attribute information similar to the attribute information of the predetermined group. This allows for more appropriate evaluation results to be obtained for the business activity status of a specified group over a specified period, taking into account the measurement values, evaluation results, and goals of other groups similar to the specified group that have been accumulated in past KPT reviews.

[0125] (Appendix 9) A program described in Appendix 7 or 8, wherein the processor, in the first similar extraction step (S102), includes a step of acquiring a second target associated with a second measurement value, and in the first generation step (S102), generates a first prompt including the second target acquired in the first similar extraction step. This makes it possible to obtain a goal based on the business activity status of a predetermined group of users over a predetermined period of time. This allows for effective group work goal setting.

[0126] (Appendix 10) A program described in any of Appendices 1 to 9, in which a processor executes a second generation step (S105) of generating a second prompt that generates a goal based on a measurement value and an evaluation result, the second prompt including the measurement value acquired in the measurement value acquisition step and the evaluation result acquired in the evaluation acquisition step or processed information obtained by processing the evaluation result; a target acquisition step (S106) of acquiring a goal by inputting the second prompt generated in the second generation step into a generation AI; and a target output step (S106) of outputting the goal acquired in the target acquisition step. This makes it possible to obtain a goal based on the business activity status of a predetermined group of users over a predetermined period of time. This allows for effective group work goal setting.

[0127] (Appendix 11) A program to be executed by a computer having a processor and a memory unit, wherein the processor executes the following steps: a measurement value acquisition step (S101) for acquiring measurement values ​​indicating the activity status of a predetermined group of users in their work over a predetermined period of time; an evaluation acquisition step (S103) for acquiring predetermined evaluation results for the work of the predetermined group over a predetermined period of time; a second generation step (S105) for generating a second prompt that generates a goal based on the measurement values ​​and the evaluation results, the second prompt including the measurement values ​​acquired in the measurement value acquisition step and the evaluation results acquired in the evaluation acquisition step; a goal acquisition step (S106) for acquiring a goal by inputting the second prompt generated in the second generation step into a generation AI; and a goal output step (S106) for outputting the goal acquired in the goal acquisition step. This makes it possible to acquire a goal based on the business activity status of a predetermined group of multiple users during a predetermined period, taking into consideration the attribute information of the group. The goal can be set appropriately by taking into consideration the attribute information of the group.

[0128] (Appendix 12) The program according to appendix 10 or 11, wherein the second generation step (S105) is a step of generating a second prompt including an instruction to generate a goal based on attribute information indicating the attributes of the group and attribute information of a specified group. This allows for the acquisition of a goal based on the status of the work activities of the group in a predetermined period, taking into consideration one or more evaluation criteria for the index values, thereby enabling the setting of work goals in an appropriate manner.

[0129] (Appendix 13) A program described in any of Appendices 10 to 12, wherein the measurement value acquisition step (S101) is a step of acquiring a measurement value consisting of one or more index values ​​that indicate the activity status in the business, the second generation step (S105) is a step of generating a second prompt including instructions to generate a goal based on evaluation criteria for each of the one or more index values, and the goal acquisition step (S106) is a step of acquiring a goal for each of the one or more index values. This allows the group to acquire a goal based on the status of its work activities over a predetermined period, taking into account the results of voting on the evaluation results. This allows for the optimal setting of work goals.

[0130] (Appendix 14) A program as described in Appendix 10, wherein the processor executes a vote acceptance step (S104) in which votes are accepted from multiple users for the evaluation results output in the evaluation output step or processed information obtained by processing the evaluation results, and a second generation step (S105) is a step in which a second prompt is generated that includes instructions to generate a goal based on the voting results and the votes accepted in the vote acceptance step. This allows for obtaining more appropriate goals for a specific group by taking into account the measurement values ​​and goals of other groups similar to the specific group that have been accumulated in past KPT reviews.

[0131] (Appendix 15) A program described in any of Appendices 10 to 14, wherein a processor executes a second similar extraction step (S105) of acquiring a second measurement value indicating the activity status in the work of a reference group similar to the measurement value acquired in the measurement value acquisition step, and a second goal associated with the second measurement value, and the second generation step (S105) is a step of generating a second prompt including the second measurement value and the second goal acquired in the second similar extraction step. This allows for acquiring targets of other groups similar to a predetermined group, taking into account the attribute information of the group, and thus allows for acquiring more suitable targets.

[0132] (Appendix 16) 16. The program according to claim 15, wherein the second similar extraction step (S105) is a step of acquiring a second measurement value and a second target of a reference group having attribute information similar to the attribute information of the predetermined group. This allows for obtaining more appropriate goals for the business activity status of a specified group over a specified period of time, taking into account the measurement values, evaluation results, and goals of other groups similar to the specified group that have been accumulated in past KPT reviews.

[0133] (Appendix 17) A program described in Appendix 16, wherein the processor, in the second similar extraction step (S105), includes a step of obtaining a second evaluation result associated with the second measurement value, and in the second generation step (S105), generates a second prompt including the second evaluation result obtained in the second similar extraction step. This makes it possible to obtain an evaluation result of the work activity status of a predetermined group of multiple users over a predetermined period of time. This allows for convenient review of work within the group.

[0134] (Appendix 18) The program described in Appendix 1, wherein the first generation step (Appendix / S101, S302) is a step of generating a prompt as a first prompt to acquire one or more measurement values ​​that a specified group should focus on based on the measurement values, the evaluation acquisition step (Appendix / S303) is a step of acquiring one or more measurement values ​​that a specified group should focus on as an evaluation result by inputting the first prompt generated in the first generation step into a generation AI, and the evaluation output step (Appendix / S304) is a step of outputting the measurement values ​​acquired in the measurement value acquisition step as an evaluation result. This makes it possible to identify one or more measurement values ​​suitable for business improvement from among the multiple measurement values ​​acquired. Also, it is possible to present the identified measurement values. It is possible to identify one or more measurement values ​​that have room for improvement from among the multiple measurement values ​​acquired.

[0135] (Appendix 19) The program described in Appendix 18, wherein the first generation step (Appendix / S101, S302) is a step of generating a first prompt including the measurement values ​​acquired in the measurement value acquisition step, which is a prompt that acquires one or more measurement values ​​that a specific group should focus on and proposes improvement actions in association with each of the one or more measurement values. This allows the user to receive proposals for suitable improvement actions (improvement measures) to improve one or more measurement values ​​that have room for improvement for the specified group, based on the activity status of other company organizations and groups.

[0136] (Appendix 20) The program described in Appendix 19, wherein the first generation step (Appendix / S101, S302) is a step of generating a first prompt that further includes one or more comparison values ​​indicating the activity status in the work of a reference group different from the specified group. This allows the user to receive proposals for suitable improvement actions (improvement measures) to improve one or more measurement values ​​that have room for improvement for the specified group, based on the activity status of other company organizations and groups.

[0137] (Appendix 21) A computer-implemented method comprising a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of claims 1 to 20. This makes it possible to obtain an evaluation result of the work activity status of a predetermined group of multiple users over a predetermined period of time. This allows for convenient review of work within the group.

[0138] (Appendix 22) An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 20. This makes it possible to obtain an evaluation result of the work activity status of a predetermined group of multiple users over a predetermined period of time. This allows for convenient review of work within the group.

[0139] (Appendix 23) A system comprising means for performing all steps performed in any of the inventions according to any one of appendixes 1 to 20. This makes it possible to obtain an evaluation result of the work activity status of a predetermined group of multiple users over a predetermined period of time. This allows for convenient review of work within the group. [Explanation of symbols]

[0140] 1 System, 10 Server, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminal, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 50 Generation AI, 501 Memory Unit, 504 Control Unit, 506 Input Device, 508 Output Device

Claims

1. A program to be executed by a computer having a processor and a storage unit, the processor: a measurement value acquisition step of acquiring a measurement value indicating the activity status of a predetermined group of users in a predetermined period of time; a first generating step of generating a first prompt that generates an evaluation result based on the measurement value, the first prompt including the measurement value acquired in the measurement value acquiring step; an evaluation acquisition step of acquiring an evaluation result by inputting the first prompt generated in the first generation step into a generation AI; an evaluation output step of outputting the evaluation result acquired in the evaluation acquisition step; A program that executes.

2. The evaluation acquisition step is a step of acquiring an evaluation result including at least one of items to be continued or items to be improved. The program according to claim 1.

3. the first generating step is a step of generating the first prompt including an instruction to generate an evaluation result based on attribute information indicating an attribute of a group and the attribute information of the predetermined group; The program according to claim 1.

4. The attribute information includes at least one of a technology stack used in a product being developed by the predetermined group and a type of product being developed by the predetermined group; The program according to claim 3.

5. the measurement value acquisition step is a step of acquiring the measurement value consisting of one or more index values ​​indicating an activity status in the business, the first generating step is a step of generating the first prompt including an instruction to generate an evaluation result based on evaluation criteria for each of one or more index values; The program according to claim 1.

6. The measurement value acquisition step is a step of acquiring the measurement values ​​of the business tasks in the predetermined period, the measurement values ​​being composed of at least one index value of lead time, cycle time, throughput, average bug fix time, deployment frequency, code review time, average resolution time, number of ongoing business tasks, first-time resolution rate, and delivery deadline compliance rate. The program according to claim 5.

7. the processor: a first similarity extraction step of acquiring a second measurement value indicating an activity status in the work of a reference group similar to the measurement value acquired in the measurement value acquisition step, and a second evaluation result associated with the second measurement value; Run the first generation step is a step of generating the first prompt including the second measurement value and the second evaluation result acquired in the first similar extraction step; The program according to claim 1.

8. the first similarity extraction step is a step of acquiring the second measurement value and the second evaluation result of the reference group having attribute information similar to attribute information of the predetermined group; The program according to claim 7.

9. the processor: The first similarity extraction step includes a step of obtaining a second target associated with the second measurement value; the first generation step is a step of generating the first prompt including the second goal acquired in the first similar extraction step; The program according to claim 7.

10. the processor: a second generation step of generating a second prompt that generates a goal based on the measurement value and the evaluation result, the second prompt including the measurement value acquired in the measurement value acquisition step and the evaluation result acquired in the evaluation acquisition step or processed information obtained by processing the evaluation result; a goal acquisition step of acquiring a goal by inputting the second prompt generated in the second generation step into a generation AI; a target output step of outputting the target acquired in the target acquisition step; To execute The program according to claim 1.

11. A program to be executed by a computer having a processor and a storage unit, the processor: a measurement value acquisition step of acquiring a measurement value indicating the activity status of a predetermined group of users in a predetermined period of time; an evaluation acquisition step of acquiring a predetermined evaluation result for the work of the predetermined group during the predetermined period; a second prompt generation step of generating a goal based on the measurement value and the evaluation result, the second prompt including the measurement value acquired in the measurement value acquisition step and the evaluation result acquired in the evaluation acquisition step; a goal acquisition step of acquiring a goal by inputting the second prompt generated in the second generation step into a generation AI; a target output step of outputting the target acquired in the target acquisition step; A program that executes.

12. the second generating step is a step of generating the second prompt including an instruction to generate a goal based on attribute information indicating an attribute of a group and the attribute information of the predetermined group; The program according to claim 10.

13. the measurement value acquisition step is a step of acquiring the measurement value consisting of one or more index values ​​indicating an activity status in the business, the second generating step is a step of generating the second prompt including an instruction to generate a goal based on evaluation criteria for each of one or more index values; The target acquisition step is a step of acquiring a target for each of the one or more index values. The program according to claim 10.

14. the processor: a vote receiving step of receiving votes from a plurality of users for the evaluation result output in the evaluation output step or processed information obtained by processing the evaluation result; Run the second generating step is a step of generating the second prompt including an instruction to generate a goal based on a voting result and the vote received in the vote receiving step; The program according to claim 10.

15. the processor: a second similarity extraction step of acquiring a second measurement value indicating an activity status in the work of a reference group similar to the measurement value acquired in the measurement value acquisition step, and a second target associated with the second measurement value; Run the second generation step is a step of generating the second prompt including the second measurement value and the second target acquired in the second similar extraction step; The program according to claim 10.

16. the second similar extraction step is a step of acquiring the second measurement value and the second target of the reference group having attribute information similar to attribute information of the predetermined group; The program according to claim 15.

17. the processor: the second similarity extraction step includes a step of obtaining a second evaluation result associated with the second measurement value; the second generation step is a step of generating the second prompt including the second evaluation result acquired in the second similar extraction step; 17. The program of claim 16.

18. the first generating step is a step of generating, as the first prompt, a prompt for acquiring one or more measurement values ​​to be focused on by the predetermined group based on the measurement values; the evaluation acquisition step is a step of inputting the first prompt generated in the first generation step into the generation AI as the evaluation result, thereby acquiring one or more measurement values ​​to be focused on by the predetermined group; The evaluation output step is a step of outputting the measurement value acquired in the measurement value acquisition step as the evaluation result. The program according to claim 1.

19. the first generating step is a step of generating a prompt that acquires one or more measurement values ​​that the predetermined group should focus on and proposes an improvement action in association with each of the one or more measurement values, the first prompt including the measurement values ​​acquired in the measurement value acquiring step; 19. The program of claim 18.

20. the first generating step is a step of generating the first prompt further including one or more comparison values ​​indicating an activity status in a task of a reference group different from the predetermined group; 20. The program of claim 19.

21. A method implemented on a computer having a processor and a memory, wherein the processor performs all of the steps performed in any of the inventions according to claims 1 to 20.

22. 21. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in any one of the inventions according to claims 1 to 20.

23. A system comprising means for executing all steps performed in any one of the inventions according to claims 1 to 20.

Images