Information processing methods, programs, and information processing systems

Abstract

This invention provides an information processing method, program, and information processing system that support system development by identifying requirements that are not limited in scope of application. [Solution] In an information processing system, the information processing method executed by the information processing device (server) includes a question provision step S102 which performs at least one of selecting a question and generating a question to obtain requirements; an answer acquisition step S108 which obtains an answer to a question; and output generation steps S110, S112 which generate the requirements from the answer using a trained model that is trained on at least text data, inputs information including the answer, and generates requirements estimated from the answer.

Description

Technical Field

[0001] The present invention relates to an information processing method, a program, and an information processing system.

Background Art

[0002] Patent Document 1 discloses a requirement definition determination support system that can significantly reduce oversight in the consideration of requirements in the development of systems and the like. In this system, items are recorded according to a requirement analysis template, and the content of question-and-answer sessions can be recorded and viewed, aiming to prevent omissions in requirement definitions.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the case of the above prior art, since items are recorded according to a template, the content may be limited to the scope assumed by the template, and there is room for improvement in this regard.

[0005] In consideration of the above facts, an object of the present invention is to support system development by identifying claim items with an unlimited scope of application.

Means for Solving the Problems

[0006] According to an information processing method according to one embodiment, the information processing method performed by the information processing device includes: a question provision step of performing at least one of selecting a question for obtaining requirements and generating the question; an answer acquisition step of obtaining an answer to the question; and an output generation step of generating the requirements from the answer using a trained model that has been trained on at least text data and generates requirements estimated from the answer when information including the answer is input.

[0007] According to a program of one embodiment, the information processing device is made to execute an information processing method that includes: a question provision step of performing at least one of selecting a question for obtaining requirements and generating the question; an answer acquisition step of obtaining an answer to the question; and an output generation step of generating the requirements from the answer using a trained model that has been trained on at least text data and generates requirements estimated from the answer when information including the answer is input.

[0008] According to an information processing system according to one embodiment, the information processing system executed by the information processing device includes: a question providing unit that performs at least one of selecting a question for obtaining requirements and generating the question; an answer obtaining unit that obtains an answer to the question; and an output generating unit that generates the requirements from the answer using a trained model that has been trained on at least text data and, upon input of information including the answer, generates requirements estimated from the answer. [Effects of the Invention]

[0009] According to one embodiment, system development can be supported by identifying requirements that are not limited in scope of application. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an example of the configuration of an information processing system according to the first embodiment. [Figure 2]This figure shows an example of the server hardware configuration according to the first embodiment. [Figure 3] This figure shows an example of the functional configuration of a server according to the first embodiment. [Figure 4] This figure shows an example of the processing flow of the information processing system according to the first embodiment. [Figure 5] This figure shows an example of a screen display in the information processing system according to the first embodiment. [Figure 6] This figure shows an example of a screen display in the information processing system according to the first embodiment. [Figure 7] This figure shows an example of a screen display in the information processing system according to the first embodiment. [Figure 8] This figure shows an example of the functional configuration of a server according to the second embodiment. [Figure 9] This figure shows an example of the processing flow of the information processing system according to the second embodiment. [Figure 10] This figure shows an example of a screen display in the information processing system according to the second embodiment. [Figure 11] This diagram conceptually illustrates a part of the processing of the information processing system according to the second embodiment. [Figure 12] This figure shows an example of the functional configuration of a server according to the third embodiment. [Figure 13] This figure shows a part of an example of the processing flow of the information processing system according to the third embodiment. [Figure 14] This figure shows another part of an example of the processing flow of the information processing system according to the third embodiment. [Figure 15] This diagram conceptually illustrates a part of the processing of the information processing system according to the third embodiment. [Modes for carrying out the invention]

[0011] (First Embodiment) Hereinafter, a first embodiment of the information processing system according to the present invention will be described with reference to FIGS. 1 to 7. In each figure, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for the convenience of explanation and may be different from the actual ratios.

[0012] (System Overview) First, the overview of the information processing system 10 according to this embodiment will be described. When a prompt as processing instruction information for instructing processing is input to a learned model such as a large language model in the information processing system 10 according to this embodiment, the learned model generates a processing result corresponding to the prompt and outputs the processing result. That is, when a prompt for creating a requirement definition as a requirement by the user U (see the prompt PT in FIG. 5) is input to the information processing system 10, processing is performed using the learned model based on the prompt, and a processing result is generated. Also, the information processing system 10 provides questions according to the prompt and generates a requirement definition from the answers of the user U to the questions. Note that the above-mentioned requirement definition is assumed to be what is required in system development and improvement using a computer, but is not limited to this, and may be what is required for other purposes such as the introduction or regulation of business processes, the formulation or change of compliance, etc. That is, the requirement definition in this embodiment is what organizes and clarifies the requirements for the system to be developed. Note that the prompt PT is not limited to being directly input by the user U, and may be automatically generated by the information processing system 10, or may be one using a previously prepared template.

[0013] (System Configuration) FIG. 1 is a diagram showing an example of the configuration of an information processing system 10 according to the present embodiment. As shown in FIG. 1, the information processing system 10 according to the present embodiment includes a server 12 as an information processing device and a plurality of user terminals 14 that are communicably connected to each other via a network N. The network N is, for example, a wired LAN (Local Area Network), a wireless LAN, the Internet, a public switched telephone network, a mobile data communication network, or a combination thereof.

[0014] The user terminal 14 is an example of an information processing device in which a user U, a manager M, and an operator OP each perform operations for inputting and displaying various information. The user terminal 14 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, a wearable device, or a combination thereof. As an example, the user U is an ordinary employee, the manager M is a management position, and the operator OP is a service provider that provides services related to the information processing system 10. The user U, the manager M, and the operator OP each have account information as user information associated with predetermined privilege information, and by logging in to the information processing system 10 using the account information, the information processing system 10 can acquire the account information and information related to the usage status in the account information (details will be described later).

[0015] The server 12 is an example of an information processing device that acquires information input from the user terminal 14, performs processing based on the information, and outputs the result. The server 12 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, or a combination thereof. The specific configuration and operation of the server 12 will be described later.

[0016] (Hardware Configuration) Figure 2 is a block diagram showing the hardware configuration of server 12. Server 12 comprises a processor 120, memory 122, storage 124, communication interface 126, input / output interface 128, output device 130, input device 132, and drive device 134, all of which are connected to each other via bus B in a manner that allows them to communicate with one another.

[0017] The processor 120 controls the configuration of the server 12 and realizes the functions of the server 12 by loading various programs stored in the storage 124 into the memory 122 and executing them. The programs executed by the processor 120 include, but are not limited to, the OS (Operating System) and the program 220 described later. By the processor 120 executing these programs, a part of the state visualization method according to this embodiment is realized. The processor 120 is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), or a combination thereof.

[0018] Memory 122 is, for example, ROM (Read Only Memory), RAM (Random Access Memory), or a combination thereof. ROM is, for example, PROM (Programmable ROM), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), or a combination thereof. RAM is, for example, DRAM (Dynamic RAM), SRAM (Static RAM), MRAM (Magnetoresistive RAM), or a combination thereof.

[0019] Storage 124 stores the OS, various programs described later, and various data. Storage 124 is, for example, flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), SCM (Storage Class Memories), or a combination of these.

[0020] The communication interface 126 is an interface for connecting the server 12 to external devices, including the user terminal 14 and the imaging device 16, via the network N, and for controlling communication. The communication interface 126 is, for example, an adapter compliant with Bluetooth®, Wi-Fi®, ZigBee®, Ethernet®, or optical communication (e.g., Fibre Channel).

[0021] The input / output interface 128 is an interface for connecting input devices 132 and output devices 130 to the server 12. Input devices 132 include, for example, a mouse, keyboard, touch panel, microphone, scanner, camera, various sensors, operation buttons, or a combination thereof. Output devices 130 include, for example, a display, projector, printer, speaker, vibrator, or a combination thereof.

[0022] The drive device 134 reads and writes data to the disk media 136. The drive device 134 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or a combination thereof. The disk media 109 is, for example, a CD (Compact Disc), a DVD (Digital Versatile Disc), an FD (Floppy Disk), an MO (Magneto-Optical disk), a BD (Blu-ray® Disc), or a combination thereof.

[0023] In this embodiment, the program may be written to memory 122 or storage 124 during the manufacturing stage of server 12, or it may be provided to server 12 via network N, or it may be provided to server 12 via a non-temporary, computer-readable recording medium such as disk media 136.

[0024] Furthermore, since the hardware configuration of the user terminal 14 is substantially the same as that of the server 12 described above, a detailed explanation will be omitted.

[0025] (Functional Configuration) Next, the functional configuration of server 12 will be described. Figure 3 shows an example of the functional configuration of server 12. When executing various programs, server 12 uses the above hardware resources to realize various functions. Server 12 has a communication unit 20, a storage unit 22, and a control unit 24 as the functional configuration that server 12 realizes. Each functional configuration is realized when the processor 120 reads and executes a program 220 stored in memory 122 or storage 124.

[0026] The communication unit 20 is implemented by the communication interface 126. The communication unit 20 sends and receives information with the user terminal 14 via the network N. The communication unit 20 receives information input from the user terminal 14. The communication unit 20 also sends information to the user terminal 14 and receives requests from user U from the user terminal 14.

[0027] The memory unit 22 is implemented by memory 122 and storage 124. The memory unit 22 stores the program 220, the trained model 222, the acquired information DB 224, the user information DB 226, the question DB 228, and the processing result DB 230.

[0028] The trained model 222 is composed of at least one trained machine learning model. One example of the machine learning models that make up this trained model 222 is a large-scale language model, which has been trained on a large amount of text data from articles, books, and websites on the internet. When text data is input as a prompt, it generates and outputs text data as a processing result corresponding to the prompt. In this embodiment, the large-scale language model in the trained model 222 generates a question in response to the prompt and generates a requirements definition, requirements document, requirements definition, and requirements document (details will be described later) estimated based on the answer to the question.

[0029] Furthermore, the trained model 222 has the function of generating an evaluation based on predetermined evaluation criteria and the rationale for that evaluation for the responses obtained from user U. Specifically, it analyzes the text data of the responses and evaluates them against evaluation criteria such as specificity, validity, consistency, and comprehensiveness. For example, it determines whether the response includes specific numbers or examples, whether it is technically and logically valid, whether it is consistent with past responses and requirements definitions, and whether it covers all the necessary information for the question. These evaluation results and their rationale are provided as feedback to user U, which can encourage them to revise their responses or provide additional information.

[0030] Furthermore, the trained model 222 analyzes the generated requirements definition and detects any missing information in at least one of the questions and answers. Specifically, it can analyze the content of the requirements in detail and identify areas where information is missing or details are lacking. If information deficiencies are detected, it generates prompts to obtain the information needed to resolve the deficiencies, and these prompts are used when the trained model 222 generates additional questions or improved answer examples (see the improved example IE in Figure 6 as an example).

[0031] Furthermore, the trained model 222 has the function of determining whether there are any inconsistencies between the multiple requirement definitions that have been generated. It analyzes whether there are any contradictions or discrepancies between the requirement definitions, and if an inconsistency is detected, it clarifies the details. If an inconsistency is determined to exist, it generates a prompt to obtain the information necessary to resolve the inconsistency, which is used when the question provider unit 242 provides additional questions to user U.

[0032] The acquired information DB224 is a database that stores information indicating prompts and responses entered by user U. The prompts and responses are in natural language, and as an example, the acquired information DB224 stores the prompts and responses linked to the account information at the time the prompts and responses were entered.

[0033] User Information DB226 is a database that stores various information about user U who has registered to use the information processing system 10. Examples of the various information stored include user identification information for unique identification, user preference information such as interest information, user history information including usage status such as past prompt input information and response input information, and user attribute information such as occupation, position, and authority.

[0034] The user information database is a database that stores questions presented to user U in order to obtain the request definition. The questions are written in natural language, and the user information database stores, for example, the question text linked to the account information at the time the question was provided. These questions can be categorized as follows, for example:

[0035] First, there are questions regarding the system's purpose. These include questions to clarify the main purpose of the new system, the business goals to be achieved through its implementation, and the current challenges and problems.

[0036] Next are questions about the user. These questions are used to understand who the target user is, what their technical skill level is, and what functions and services the user expects from the system.

[0037] Furthermore, questions regarding functional requirements include identifying the essential functions required for the system, the priority of each function, and whether there are any functions being considered for future addition.

[0038] Furthermore, there are questions regarding non-functional requirements. These include questions to confirm the system's performance requirements (e.g., response time, processing speed), availability and reliability requirements, and security and privacy requirements.

[0039] Questions regarding data include those that clarify the types and formats of data being handled, the data retention period and archiving requirements, and the requirements for data backup and restoration.

[0040] The user interface questions include those to confirm whether there are any requests regarding the user interface design, what the requirements are for multilingual support and accessibility, and whether the user intends to use it on mobile devices.

[0041] Questions regarding integration with other systems include questions to clarify whether integration with other systems or services is necessary, what the API and data sharing requirements are, and whether there are any integration requirements regarding authentication and authorization.

[0042] The section containing questions regarding technical constraints includes questions to confirm whether there are any specifications for the platform, language, or framework to be used, what the technical constraints and prerequisites are for system construction, and whether the use of existing hardware and software assets is necessary.

[0043] Questions related to project management include those that clarify development schedule and deadline requirements, budget and resource constraints, and who the stakeholders and related parties are.

[0044] The section on legal regulations and standards contains questions to confirm whether there are any laws or industry standards that must be followed, what regulations exist regarding data protection and privacy, and what compliance requirements exist.

[0045] Questions regarding operation and maintenance include those aimed at clarifying requirements for system operating hours and maintenance structures, requirements for handling failures and redundancy, and whether there are plans for regular maintenance and updates.

[0046] Finally, there are other questions. These questions are used to confirm any particular risks or challenges, any requests regarding future business development or scalability, and any matters that the user would like to convey to the development team. Through these questions, the user information database can systematically collect the information necessary for defining system development requirements from user U. This allows for clarification of requirements and streamlining the system development process. In addition to the specific examples of questions mentioned above, the user information database may also contain a variety of other questions necessary for defining system development requirements.

[0047] The Processing Results DB230 is a database that stores the results of various processes executed by Server 12, such as responses obtained from User U, generated requirement definitions, and their analysis results. Specifically, it stores requirement definitions generated using the trained model 222 in the output generation step, evaluation results and their rationale obtained from evaluation and rationale generation, information on missing or inconsistent information detected in the verification step, and additional questions and their answers (details will be described later). In addition, each processing result is linked to User U's account information and timestamp at the time the result was obtained and recorded in the Processing Results DB230. This makes it possible to track and analyze past processing results, contributing to updating requirement definitions and optimizing the system development process. Furthermore, the information stored in the Processing Results DB230 is used as basic data for decisions and processing in other processing steps, such as determining dependency and inconsistency of requirement definitions and setting standard requirement definitions. It also functions as a source of information to facilitate interaction with User U, such as issuing instructions to delete requirement definitions and generating questions for update confirmation.

[0048] The control unit 24 is realized when the processor 120 reads and executes the program 220 from the memory 122 (see Figure 2) and works in cooperation with other hardware components. The control unit 24 includes a question provision unit 242, an information acquisition unit 244 as an answer acquisition unit, an information processing unit 246 as an output generation unit, and an output unit 248.

[0049] The question provider unit 242 provides a question to user U (see question Q in Figure 5 as an example). Specifically, the question provider unit 242 performs at least one of the following: question selection and question generation. That is, in question selection, it selects an appropriate question for defining requirements in system development from the user information DB stored in the storage unit 22. In this question selection, as a specific example, the question provider unit 242 refers to user U's account information stored in the user information DB 226, the prompts entered, and the history in the acquired information DB 224, etc., to grasp at least one of the instructions and attributes from user U (e.g., job title, area of ​​expertise, past answer history). Next, it clarifies the issues in the current requirements definition and the need for additional information based on at least one of the grasped instructions and attributes. Based on this information, it prioritizes multiple questions stored in the user information DB based on the importance and urgency of the information to be collected. Specifically, questions related to items with missing information or items where inconsistencies have been detected are set to a higher priority. Additionally, questions that User U has already answered in the past may be excluded, while questions that have not yet been answered or questions that require further confirmation may be included in the selection process.

[0050] In selecting questions, the question provider unit 242 selects appropriate questions for defining requirements in system development from the user information DB stored in the storage unit 22. At this time, it refers to the user U's account information stored in the user information DB 226, the input prompts, and the history in the acquired information DB 224 to understand the instructions and attributes from user U (e.g., job title, area of ​​expertise, past answer history). Next, based on this information, it clarifies the issues in the current requirements definition and the need for additional information, and selects from the top questions based on the importance and urgency of the information to be collected from the multiple questions stored in the user information DB. Specifically, questions related to items with insufficient information or items where inconsistencies have been detected are given a higher priority. In addition, questions that user U has already answered in the past are excluded, and questions that have not yet been answered or that require reconfirmation are selected. In this embodiment, the selection process is performed on multiple questions stored in the user information DB, but it is not limited to this, and the selection process may also be performed on other information sources such as the processing result DB 230.

[0051] In generating questions, the question provider unit 242 generates new questions using the trained model 222. Based on instructions from user U, past answer history, attributes, etc., it clarifies the issues in the current requirements definition and the need for additional information. Based on this information, it automatically inputs analysis instructions (prompts) to the trained model 222 to analyze user U's needs, information deficiencies, and inconsistencies. Based on the analysis results, it identifies information that should be newly obtained from user U and generates appropriate questions to elicit that information. The generated questions are optimized in expression to match user U's field of expertise and level of understanding, and are created in a format that is easy for user U to answer, such as using technical terms and providing concrete examples. Furthermore, in order to deepen the requirements definition in system development, it is also possible to generate questions that resolve relationships and contradictions with existing requirements definitions. In addition, in response to new answers and reactions from user U, questions can be dynamically generated using the trained model 222 to collect detailed information.

[0052] The question provision unit 242 efficiently collects information and clarifies the requirements definition by selecting and generating questions according to various factors such as the user U's situation, the state of the requirements definition, and any missing or inconsistent information. Specifically, the information processing unit 246 analyzes the requirements definition output in the previous process, and if it detects a lack of information in at least one of the questions and answers, it selects and generates additional questions for user U to obtain the missing information. For example, consider a case where user U provides "inventory management system" as the main function of the system, but the details are unclear. When the information processing unit 246 analyzes this answer, it detects that specific information such as the types and quantities of products to be managed, the need for real-time inventory updates, and access rights to inventory data are missing. In this case, the question provision unit 242 selects or generates additional questions such as "Please tell us specifically the types and quantities of products managed by the inventory management system," "Does the inventory information need to be updated in real time?", and "Are access rights to inventory data different for each user?", and processes them to provide to user U in order to obtain the missing information.

[0053] Another example is a lack of information regarding non-functional requirements. For instance, suppose user U has not provided specific information regarding the system's performance requirements. When the information processing unit 246 detects this lack of information, the question provision unit 242 selects or generates questions such as "Is there a target value for the system's response time? For example, the time from user operation to screen display," "What is the maximum expected number of users using the system simultaneously?", and "What processing speed is required when processing large amounts of data?" and processes them to provide to user U, thereby requesting user U to provide more detailed information.

[0054] Furthermore, another example is when the details of security requirements are unclear. When user U only requests "high security," the specific security measures required are unknown. When the information processing unit 246 detects this lack of information, the question provision unit 242 selects or generates specific questions such as "What method of user authentication do you prefer (e.g., ID / password, two-factor authentication, biometric authentication, etc.)", "Is data encryption necessary? If so, should you encrypt stored data or communication data?", and "Will you set security policies such as account locking based on the number of login failures or periodic password changes?" and processes them to provide to user U, thereby collecting the necessary information from user U. In this embodiment, as an example, when the information processing unit 246 analyzes and detects a lack of information in at least one of the questions and answers, the question provision unit 242 inputs the content of the deficiency and a prompt instructing the output of a question to obtain the information necessary to resolve the deficiency into the trained model 222, and selects a question in the user information DB that is similar to the output result (a question to obtain the necessary information). On the other hand, if a similar question does not exist in the user information database, the output result is regenerated into a question that is easy for user U to understand, based on the various information about user U described above.

[0055] Furthermore, the question-providing unit 242, when the information processing unit 246 analyzes the multiple requirement definitions output in the previous processing and detects any inconsistencies between the multiple requirement definitions, selects and generates additional questions for user U to resolve those inconsistencies. For example, suppose user U provides two requirements as instructions (answers): "The system needs to operate 24 hours a day, 365 days a year" and "We want to perform regular system maintenance." The information processing unit 246 analyzes these requirements and detects a contradiction regarding the system's operating time and maintenance time. In this case, to resolve the inconsistency, the question-providing unit 242 generates a question, for example, "What specific operations are you considering to achieve both 24 / 7 system operation and regular maintenance? For example, please let us know if you have any requests or plans regarding acceptable system downtime during maintenance, or implementing maintenance without downtime through system redundancy." and provides this question to user U.

[0056] As another example, if user U provides instructions (answers) stating that "the system needs to maintain a high level of security" and simultaneously "I want to make it accessible without user authentication," the information processing unit 246 detects an inconsistency between the security requirements and the access requirements. In response, the question provision unit 242 generates questions such as, "What specific security measures are you considering to maintain a high level of security while allowing access without user authentication? For example, methods such as limiting the information that can be viewed, restricting the IP address from which access is coming, and anonymizing the data could be considered. Could you please consider these options?"

[0057] Furthermore, if user U provides instructions (answers) stating that "the system is intended for use on mobile devices" and "it needs to handle a large number of high-resolution images," the information processing unit 246 detects an inconsistency between the characteristics of mobile devices and the handling of a large number of high-resolution images. In this case, the question provision unit 242 generates questions such as, "You mentioned that the system is intended for use on mobile devices and needs to handle a large number of high-resolution images. Do you have any concerns regarding data communication volume or display speed in a mobile environment? For example, there are countermeasures such as image compression, the use of thumbnail display, and loading images as needed. Please let us know your requests and expected behaviors."

[0058] In this embodiment, as an example, the question provision unit 242, when the information processing unit 246 analyzes and detects any inconsistencies between multiple requirement definitions, inputs the details of the inconsistencies and a prompt instructing the trained model 222 to output a question to obtain the information necessary to resolve the inconsistencies. If a question similar to the output result (the question to obtain the necessary information) exists in the user information database, it is selected. On the other hand, if no similar question exists in the user information database, the output result is converted into a question that is easy for user U to understand based on the various information of user U described above.

[0059] Furthermore, the question provider unit 242 has the function of providing background information related to the question (see the background information BI in Figure 5 as an example of background information) when presenting a question to user U. Specifically, in the process of generating or selecting a question to provide to user U, the question provider unit 242 collects background information related to that question. This background information is obtained from the acquired information DB 224 (prompts and instructions previously entered by user U), user information DB 226 (user U's account information and attributes, past answer history), and processing result DB 230 (request definitions generated so far, their analysis results, data on missing information and inconsistencies). The question provider unit 242 refers to this data and uses the trained model 222 to extract background information related to the question. First, it analyzes the relevant past request definitions, answer history, and analysis results to identify information useful to user U. Then, based on the extracted information, it generates background information in a format that is easy for user U to understand. In this process, the background information is adjusted in terms of its expression and level of detail, taking into account the user's attributes stored in the user information DB226, such as their area of ​​expertise, level of understanding, and job title. The background information thus generated is integrated with the question and presented to user U. This allows user U to understand the intent and purpose of the question more deeply and provide an accurate answer. For example, if the question provider 242 generates the question, "Please tell me in detail about the main functional requirements of the new system," the question provider 242, based on past answers and issues, provides user U with background information such as, "From your previous responses, it appears that the current system has challenges in improving the efficiency of inventory management and real-time analysis of sales data. Also, the sales department has requested access via mobile devices. Taking these points into consideration, please tell us specifically about the functions that will be emphasized in the new system and the areas that you would like to improve."

[0060] The information acquisition unit 244 has the function of acquiring answers from user U to questions provided by the question provision unit 242 (see Answer A in Figure 5 as an example of an answer; this answer also includes answers to additional questions), and acquiring various information necessary for processing by the question provision unit 242 and the information processing unit 246. Specifically, the information acquisition unit 244 performs the following processing. First, in acquiring answers from user U, the information acquisition unit 244 receives answers to questions provided to user U by the question provision unit 242 and stores the contents in the processing result DB 230 of the storage unit 22. User U's answers are written in natural language, and the information acquisition unit 244 saves the answers in an appropriate format. In addition, metadata such as user U's account information and answer timestamps are also acquired and recorded in association with the answers.

[0061] Next, in acquiring various types of information, the information acquisition unit 244 acquires data necessary for processing by the question provision unit 242 and the information processing unit 246. Specifically, it acquires information stored in the storage unit 22 or various types of data that can be obtained from external sources using API linkage, etc.

[0062] The information processing unit 246 has the function of generating requirements definitions using the trained model 222 based on the answers obtained from user U. Specifically, using the answers from user U obtained by the information acquisition unit 244 as input data, the information processing unit 246 instructs the trained model 222 to generate requirements definitions. Then, it acquires the information of the requirements definitions generated by the trained model 222.

[0063] Furthermore, the information processing unit 246 has the function of generating an evaluation based on predetermined evaluation criteria and the basis for that evaluation based on the response obtained from user U (see, for example, evaluation E and the basis for evaluation BE1 in Figure 6). Examples of these predetermined evaluation criteria include the specificity, validity, consistency, and comprehensiveness of the response. First, to evaluate the specificity of the response, it determines whether the response contains specific numerical values, examples, or detailed explanations. For example, it can determine whether abstract expressions are used excessively and encourage the provision of specific information. Next, in the evaluation of validity, it determines whether the content of the response is technically and logically correct and realistic. This is done by comparing the content of the response with information from existing technical knowledge bases and industry standards to check for contradictions or unrealistic requirements. In the evaluation of consistency, it checks whether the response does not contradict past responses or existing requirement definitions by comparing it with data stored in the processing result DB 230. In the evaluation of comprehensiveness, it determines whether the response contains sufficient information necessary for the question and whether the expected response items are included. Based on these evaluation criteria, the information processing unit 246 generates evaluation results and their basis and provides them to user U as feedback. Furthermore, the information processing unit 246 prompts the question provision unit 242 to provide questions regarding whether to revise the input response during this feedback process and whether to proceed to the next question (see questions CA and PQ in Figure 6 as an example). This allows user U to review their response and, if necessary, make revisions or provide additional information, or to skip revising the response for the time being. Note that the evaluation method described above is just one example and is not limited to this.

[0064] Furthermore, the information processing unit 246 has a function to analyze the generated requirements definition and determine whether there is any missing information in at least one of the questions and answers (see BE1, the basis for evaluation in Figure 6, as an example). If the analysis of the requirements definition identifies missing information or areas lacking detail and determines that it is necessary to supplement them, the information processing unit 246 communicates this to the question provision unit 242 and executes processing to provide additional questions. The information processing unit 246 also has a function to determine whether there are any inconsistencies between multiple generated requirements definitions (see BE2, the basis for evaluation in Figure 7, as an example). If there are contradictions or discrepancies between the requirements definitions, it detects them and determines that there are inconsistencies. If inconsistencies are detected, the information processing unit 246 communicates this information to the question provision unit 242 and executes processing to provide additional questions to resolve the inconsistencies.

[0065] The output unit 248 controls the system to output the processing results of the question provision unit 242 and the information processing unit 246 to the user terminal 14. Specifically, the output unit 248 outputs at least one of the questions, additional questions, and background information, which are the processing results of the question provision unit 242, to the user terminal 14. The output unit 248 also outputs at least one of the requirements definition, the evaluation based on predetermined evaluation criteria for the answer, and the basis for said evaluation, which are the processing results of the information processing unit 246, to the user terminal 14.

[0066] (Processing performed by the information processing system 10) Next, the operation of the information processing system 10 will be explained. Figure 4 is a flowchart showing an example of the processing flow by the information processing system 10. Processing is performed when the processor 120 reads the program 220 stored in the storage 124, expands it into the memory 122, and executes it. Although not shown in the figure, if the processor 120 receives information about the termination of operation of the information processing system 10, or information about the termination of operation from the user terminal 14 during the execution of a determination process (these are simply referred to as "termination operations"), it will terminate the processing based on the program 220 that is currently being processed.

[0067] The processor 120 receives a prompt from user U or the like to define a request (step S100), and then, depending on the content of the prompt, it performs at least one of acquiring and generating a question and outputs it to the user terminal 14 to provide the question to user U (step S102). Then, it provides the user U with background information related to the question provided to user U by outputting it to the user terminal 14 (step S104), and also displays an input screen for answering the provided question on the user terminal 14 (step S106).

[0068] The processor 120 determines whether or not it has received an answer from user U to the question it provided (step S108). If no answer is received (step S108: NO), the processor 120 proceeds to step S106. On the other hand, if an answer is received (step S108: YES), the processor 120 provides user U with an evaluation of the answer based on predetermined criteria and the basis for the evaluation by displaying them on the user terminal 14 (step S110).

[0069] The processor 120 presents to user U whether or not to correct the answer by displaying it on the user terminal 14, and determines whether or not user U has entered an instruction to correct it (step S112). If an instruction to correct is received (step S112: YES), the processor 120 proceeds to step S106. On the other hand, if there is no instruction to correct (step S112: NO), the processor 120 generates a requirement definition based on the entered answer (step S114), and performs various analyses of the question, the answer to it, and the requirement definition (step S116). In this embodiment, this analysis includes, but is not limited to, determining whether or not there is any lack of information in at least one of the question and the answer, and determining whether or not there are any inconsistencies between the generated multiple requirement definitions.

[0070] The processor 120 determines whether there is any missing information as a result of the analysis (step S118). If there is missing information (step S118: YES), the processor 120 proceeds to step S102 to provide additional questions. On the other hand, if there is no missing information (step S118: NO), the processor 120 determines whether there are any inconsistencies between the requirement definitions if multiple requirement definitions are generated as a result of the analysis (step S120). If there are inconsistencies (step S120: YES), the processor 120 proceeds to step S102 to provide additional questions to resolve the inconsistencies. On the other hand, if there are no inconsistencies (step S120: NO), the processor 120 outputs information regarding the generated requirement definitions to be displayed on the user terminal 14 (step S122; see requirement definition RD, which is information regarding the requirement definitions in Figure 10, as an example).

[0071] The processor 120 determines whether or not user U has issued a command to terminate processing (step S124). If no termination command has been issued (step S124: NO), the processor 120 proceeds to step S102. On the other hand, if a termination command has been issued (step S124: YES), the processor 120 terminates processing based on program 220. Steps S102 and S104 described above correspond to the "question provision step" described in claim 1, steps S106 and S108 correspond to the "answer acquisition step" described in claim 1, steps S110 and S112 correspond to the "output generation step" described in claims 1 and 3, and steps S116 and S118 correspond to the "verification step" described in claim 4.

[0072] (Effects of the first embodiment) According to the information processing system 10 of this embodiment, the system performs a question provision step of performing at least one of selecting a question and generating a question for obtaining a requirements definition; an answer acquisition step of obtaining an answer to a question; and an output generation step of generating a requirements definition from an answer using a trained model 222 that has been trained on at least text data and generates a requirements definition estimated from the answer when information including the answer is input. In other words, by having the trained model 222 estimate and extract potential requirements definitions from the user U's answers, it is possible to collect requirements that the user U has not explicitly stated or needs that have been overlooked. This is because the trained model 222 has learned a large amount of text data and has the ability to deeply understand the content of the user U's answers using natural language processing technology and to infer the underlying intentions and requirements. As a result, the information obtained from the user U is not limited to the answers presented, but is comprehensively collected including the background and related information. Therefore, it becomes possible to identify requirements definitions that are not limited in scope of application, and the accuracy and comprehensiveness of requirements definitions in system development can be improved. This advanced requirements definition collection process is expected to reduce requirements omissions and ambiguities in the early stages of development, contributing to increased efficiency and quality throughout system development. Furthermore, by identifying the potential needs of user U early on, it reduces the risk of subsequent specification changes and additional development, thereby increasing the project's success rate. This allows for the identification of requirements without limitations on their scope, supporting system development.

[0073] Furthermore, since the information processing system 10 includes a process in the question generation step to provide background information along with the question, user U can gain a deeper understanding of the intent, purpose, and relevant context of the presented question, making it easier for them to provide more specific and detailed answers tailored to their own situation and needs. From another perspective, the provision of background information also allows user U to become aware of potential requirements definitions and needs they may not have noticed or overlooked. For example, by providing information such as current business challenges, market trends, and constraints of existing systems as background information for a question about a specific function of the system, user U can consider requirements definitions from a broader perspective. This makes it possible to effectively identify requirements definitions that are not limited in scope, thereby effectively supporting system development.

[0074] Furthermore, since the information processing system 10 includes a process in the output generation step to generate an evaluation of the answer based on predetermined evaluation criteria and at least one of the grounds for said evaluation, user U can understand how their answer was evaluated and the grounds for that evaluation. By receiving feedback on the evaluation results and grounds, user U can recognize the shortcomings and areas for improvement in their answer and is encouraged to provide more specific and accurate information. This improves the quality of information provided by user U and increases the accuracy and comprehensiveness of the requirements definition. As a result, it becomes possible to more effectively identify requirements that are not limited in scope, and to support system development more effectively. In particular, through the evaluation of the answer and the provision of its grounds, communication with user U is deepened, and it becomes possible to clarify potential needs and overlooked requirements. This is expected to reduce requirements omissions and discrepancies in understanding in the early stages of development and increase the success rate of system development projects.

[0075] Furthermore, the information processing system 10 includes a verification step in which it analyzes the requirements definition generated by the output generation step and detects a lack of information in at least one of the questions and answers, and, if a lack of information is detected in the verification step, it repeats the question generation step to provide additional questions to obtain the missing information, and repeats the answer acquisition step to obtain the additional answers. In this way, the information processing system 10 verifies the generated requirements definition and repeats the process of additional questions and answers to supplement the lack of information. Through this action, the information obtained from user U becomes richer, and the comprehensiveness and accuracy of the requirements definition are improved. Therefore, it becomes possible to more effectively identify requirements definitions that are not limited in scope of application, and to more effectively support system development. In particular, by detecting a lack of information and asking additional questions to supplement it, the potential needs and overlooked requirements of user U are also clarified, and the effect of reducing requirements omissions and ambiguities in the early stages of development is obtained.

[0076] Furthermore, the information processing system 10 determines whether there are any inconsistencies between the multiple requirement definitions generated in the output generation step. If an inconsistency is found, it re-executes the question generation step to provide additional questions to obtain the information necessary to resolve the inconsistency, and also re-executes the answer acquisition step to obtain additional answers. This process enables the effective collection of information to resolve inconsistencies between requirement definitions. Specifically, if contradictions or discrepancies are detected between the generated requirement definitions, the information processing system 10 automatically identifies the inconsistency and provides appropriate additional questions to user U. This allows user U to reconfirm and provide detailed explanations about the information causing the inconsistency. The information processing system 10 updates the requirement definition using the newly acquired answers to resolve the inconsistency. This action improves the consistency and accuracy of the requirement definitions obtained from user U, enabling more effective identification of requirement definitions with unrestricted scope of application. As a result, system development can be supported more effectively. In particular, automating the process of detecting and resolving requirement definition inconsistencies early on is expected to reduce requirements omissions and misunderstandings in the early stages of development, thereby increasing the project's success rate.

[0077] (Second embodiment) Next, an information processing system 40 according to the second embodiment of the present invention will be described with reference to Figures 8-11. The information processing system 40 according to the second embodiment has the same basic configuration as the first embodiment, and is characterized by determining the dependencies between multiple generated requirement definitions, acquiring and outputting information regarding said dependencies, and providing questions including confirmation of whether or not previously generated requirement definitions have been updated. Components identical to those in the first embodiment are denoted by the same reference numerals and their descriptions are omitted.

[0078] (Functional Configuration) The functional configuration of the server 50 as an information processing device in the information processing system 40 will now be described. Figure 8 shows an example of the functional configuration of the server 50. When executing various programs, the server 50 uses the same hardware resources as the server 12 in the first embodiment to realize various functions. The server 50 has a communication unit 20, a storage unit 60, and a control unit 70 as the functional configuration that the server 50 realizes. Each functional configuration is realized when the processor 120 reads and executes a program 600 stored in the memory 122 or storage 124.

[0079] The memory unit 60 is implemented by memory 122 and storage 124. The memory unit 60 stores the program 600, the trained model 222, the acquired information DB 224, the user information DB 226, the user information DB, and the processing result DB 230.

[0080] The control unit 70 is realized when the processor 120 reads and executes the program 600 from the memory 122 (see Figure 2) and works in cooperation with other hardware components. The control unit 70 comprises a question provision unit 700, an information acquisition unit 702 as an answer acquisition unit, an information processing unit 704 as an output generation unit, and an output unit 706.

[0081] The question provision unit 700, like the question provision unit 242 in the first embodiment, has the function of providing questions to user U, and performs at least one of the following: selecting and generating questions. Furthermore, the question provision unit 700 has the function of providing questions that include confirmation of whether or not there have been any updates to previously generated request definitions. Specifically, the question provision unit 700, based on the results of the information processing unit 704 referring to past request definitions and processing result DB 230 stored in the storage unit 22, generates or selects questions that, if necessary, include confirmation of whether these request definitions are still valid or whether changes or updates are needed, and provides them to user U.

[0082] The information acquisition unit 702, like the information acquisition unit 244 in the first embodiment, has the function of acquiring answers from user U to questions provided by the question provision unit 242 (including answers to additional questions), and acquiring various information necessary for processing by the question provision unit 242 and the information processing unit 246. Furthermore, the information acquisition unit 702 has the function of processing deletion instructions for request definitions. Specifically, the information acquisition unit 702 receives an instruction from user U to delete a specific request definition and records the deletion instruction in the processing result DB 230 of the storage unit 22. This allows user U to appropriately delete request definitions that are no longer needed, thereby maintaining the up-to-dateness and consistency of the request definitions. Based on the acquired deletion instruction, the information acquisition unit 702 works in cooperation with the information processing unit 246 to execute the deletion process for the corresponding request definition.

[0083] The information processing unit 704 performs processing based on prompts, similar to the information processing unit 246 in the first embodiment. The information processing unit 704 also stores the processing results corresponding to the acquired information DB224 in the storage unit 60, linking the acquired information DB224 with the user information DB226.

[0084] The information processing unit 704, similar to the information processing unit in the first embodiment, has the function of generating requirement definitions using the trained model 222 based on the answers obtained from user U. It also has the function of generating an evaluation based on predetermined evaluation criteria and the basis for that evaluation based on the answers obtained from user U, the function of analyzing the generated requirement definitions to detect missing information, and the function of determining whether there are any inconsistencies between multiple requirement definitions. Furthermore, the information processing unit 704 has the function of determining the dependencies between the multiple generated requirement definitions, and if there are dependencies, acquiring and outputting information about those dependencies. Specifically, the information processing unit 704 analyzes the relationships and dependencies between the generated requirement definitions, stores these relationships in the storage unit 60 in the form of text data or graphs (not shown), and presents them to user U. This makes it possible to clarify the priority and scope of impact of the requirement definitions and support project planning and risk management.

[0085] Furthermore, the information processing unit 704 sets a predetermined requirement definition as a standard requirement definition from among multiple requirement definitions, and performs a standard determination process to determine at least one of the following based on the standard requirement definition: whether there is a lack of information, an inconsistency, or whether an update is necessary for other requirement definitions. Specifically, as shown in Figure 10, the information processing unit 704 displays the requirement definitions RD (including those generated in the past) on the user terminal 14, and also displays lock / unlock instruction buttons LB that can be operated for each predetermined classification (in this embodiment, chapters as an example), and receives instructions from the user U on which requirement definition to lock or unlock. A requirement definition that has been instructed to be locked becomes a standard requirement definition, and the locked requirement definition is not changed, while only other requirement definitions related to it are subject to modification or update. On the other hand, if an unlock instruction is given for a locked requirement definition, that requirement definition is excluded from the standard requirement definition, and it becomes clear that it is subject to modification or update. In other words, unlocking is performed on a requirement definition that was locked. The information processing unit 704 then re-determines whether there is a lack of information, an inconsistency, or the need for update for the unlocked requirement definition compared to other requirement definitions. Then, if necessary, the question provision unit 700 is notified, and additional questions are generated and provided to collect information and regenerate (update) the contents of the unlocked requirement definition (see Figure 11). In this way, unlocking is performed on the locked requirement definition, and the unlocked requirement definition becomes subject to review and updating again. The information processing unit 704 plays a role in improving the accuracy, consistency, and flexibility of requirement definitions in system development by flexibly managing the criteria and targets of changes to the requirement definition based on the lock and unlock instructions from the user U. The above-mentioned standard requirement definition corresponds to the "standard requirement" described in claim 8.

[0086] Furthermore, the information processing unit 704 performs a process to obtain a deletion instruction for a requirement definition, and when it obtains such a deletion instruction, it executes a process to delete that requirement definition. Specifically, it receives a deletion instruction from user U via the information acquisition unit 702 and deletes the corresponding requirement definition from the processing result DB 230, etc. Also, if dependencies or inconsistencies arise as a result of the deletion, it performs dependency checks and inconsistency detection again and updates the related requirement definitions as necessary. In this way, the consistency and up-to-dateness of the requirement definitions are maintained, and the system development process can proceed smoothly.

[0087] Furthermore, the information processing unit 704 has a function to determine whether or not to retrieve the requirements definition from the storage unit at a predetermined timing. The predetermined timing includes cases where it is determined that it is necessary to re-retrieve the requirements definition based on the content of a prompt entered by the user, and scheduled timings for periodic reviews. For example, if user U enters "I would like to review the functional requirements in light of recent market trends" in a new prompt, the information processing unit 704 analyzes the content and determines that it is necessary to retrieve the existing requirements definition from the storage unit. It is also possible to automatically re-retrieve the requirements definition when the project transitions or at regular intervals to check the latest status. The information processing unit 704 then notifies the question provision unit 700 to provide questions regarding the retrieved requirements definition, including whether or not there are any updates, as described above.

[0088] The output unit 706 controls the output to the user terminal 14, similar to the output unit 248 in the first embodiment, to output the processing results of the question provision unit 242 and the information processing unit 246. Furthermore, the output unit 706 has a function to output information to the user terminal 14 when dependencies between multiple generated requirement definitions are recognized and information regarding those dependencies is generated. Specifically, it acquires information on the dependencies between requirement definitions analyzed by the information processing unit 704 and displays it as text data or graph data so that the user can check it.

[0089] (Processing performed by the information processing system 40) Next, the operation of the information processing system 40 will be described. Figure 9 is a flowchart showing an example of the processing flow by the information processing system 40. Processing is performed when the processor 120 reads the program 600 stored in the storage 124, expands it into the memory 122, and executes it. Note that the same reference numerals are used for the same processing as in the first embodiment, and their descriptions are omitted.

[0090] After processing in step S100, the processor 120 analyzes the contents of the prompt (step S200) and determines whether to retrieve the request definition stored in the memory unit 60 at a predetermined timing (step S202). If it does not retrieve it (step S202: NO), the processor 120 proceeds to step S102. On the other hand, if it does retrieve it (step S202: YES), the processor 120 retrieves the request definition that it has determined to retrieve from the memory unit 60 (step S204), and also provides the user U with questions including confirmation of whether the retrieved request definition is still valid and whether any changes or updates are needed (step S206), and then proceeds to the processing in step S104.

[0091] After processing in step S114, the processor 120 stores the generated request definitions in the storage unit 60 (processing result DB230) (step S208) and determines whether or not it has received instructions from user U on which request definitions to lock or unlock (step S210). If no instructions have been received (step S210: NO), the processor 120 proceeds to step S214, which will be described later. On the other hand, if instructions have been received (step S210: YES), the processor 120 reflects the locking or unlocking of the request definitions targeted by the instructions and then regenerates the request definitions other than those that have been locked using the same processing as in step S114 (step S212).

[0092] The processor 120 determines whether or not it has received an instruction from user U to delete a specific request definition (step S214). If no instruction has been received (step S212: NO), the processor 120 proceeds to step S218, which will be described later. On the other hand, if an instruction has been received (step S212: YES), the processor 120 deletes the request definition to be deleted from the processing result DB 230, etc., based on the instruction, and reflects the instruction (step S216).

[0093] The processor 120 performs analysis of at least one of the questions and answers, or the requirement definitions (step S218). In this embodiment, the analysis includes not only the analysis in the first embodiment, but also the determination of dependencies between the multiple requirement definitions that have been generated. After the results of this analysis are stored in the storage unit 60, the process proceeds to step S118.

[0094] If there are no inconsistencies in step S120 (step S120: NO), the processor 120 outputs information regarding the generated request definitions for display on the user terminal 14 (step S220). In step S220, if it was determined in step S218 that there are dependencies between multiple request definitions, information regarding those dependencies is also output. After that, the processor 120 proceeds to step S124. Steps S210, S212, S218, S118, and S120 correspond to the "criteria determination process" described in claim 8.

[0095] (Effects of the second embodiment) In the information processing system 40 according to this embodiment, the configuration is the same as in the first embodiment, except that it determines the dependencies between multiple generated requirement definitions, acquires and outputs information regarding those dependencies, and provides questions including confirmation of whether previously generated requirement definitions have been updated. Therefore, the same effects and advantages as in the first embodiment can be obtained. Furthermore, since the information processing system 40 performs the process of determining the dependencies between multiple generated requirement definitions, acquiring and outputting information regarding those dependencies, user U can clearly grasp the relationships and priorities between requirement definitions. Specifically, it becomes possible to understand how one requirement definition affects other requirement definitions, or whether a particular requirement definition depends on other requirement definitions. This leads to an improvement in the quality of responses from user U, enabling the identification of requirement definitions with an unlimited scope of application, and further supporting system development.

[0096] Furthermore, the information processing system 40 stores the requirements definitions in the storage unit 60 and includes a process to retrieve the requirements definitions from the storage unit 60 at predetermined timings and provide a question, including confirmation of whether the requirements definitions have been updated. This allows the system to periodically check whether existing requirements definitions are up-to-date and appropriately ask user U about the need for updates. The predetermined timing includes instructions from the user and the passage of a certain period of time. For example, when the project phase progresses or when market trends change, the system automatically retrieves past requirements definitions from the storage unit 60 and provides the user with a question such as, "Have there been any changes or additions to the requirements definitions you previously provided?" This allows the user to communicate new needs and changes to the system, and the requirements definitions are updated smoothly. As a result, it becomes possible to identify requirements definitions with no limited scope of application, further supporting system development. Specifically, it contributes to the efficiency of the development process and the improvement of product quality by enabling a quick response to user requests and market changes. In addition, by preventing omissions in requirements definitions and development based on outdated information, the overall project risk is reduced and the success rate is increased.

[0097] Furthermore, the information processing system 40 includes a process for setting a predetermined requirement definition as a standard requirement definition (lock process) from among multiple requirement definitions, and a standard determination process for determining at least one of the following regarding the other requirement definitions: whether there is a lack of information, an inconsistency, or whether an update is necessary, based on the standard requirement definition. Therefore, user U can set a predetermined requirement definition as a standard requirement definition from among multiple requirement definitions and perform a lock process on it. The lock process fixes the standard requirement definition so that it cannot be changed. Through this function, user U can clearly reflect their intention of "I do not want to change this requirement definition" in the system. In addition, the information processing system 40 sets the standard requirement definition locked by user U as a reference point. This ensures that when comparing and verifying other requirement definitions with the standard requirement definition, the standard is clear and consistent. Specifically, based on the standard requirement definition, the system executes a standard determination process that determines at least one of the following regarding other requirement definitions: whether there is a lack of information, an inconsistency, or whether an update is necessary. As a result, it is possible to identify requirement definitions that accurately reflect user U's intentions and have no limited scope of application. This leads to more effective support for system development.

[0098] Furthermore, the information processing system 40 includes a process that provides questions to resolve any missing, inconsistent, or outdated information in other requirement definitions, based on the judgment result of the standard judgment process. This allows the system to collect necessary information from user U and resolve or update missing, inconsistent, or outdated information in the requirement definitions. This action enables the timely supplementation and resolution of missing, inconsistent, or outdated information in the requirement definitions. As a result, it is possible to identify requirement definitions without limiting their scope of application, further supporting system development. In particular, by including a process that verifies other requirement definitions based on a standard requirement definition and proactively resolves problems, the accuracy and comprehensiveness of the requirement definitions are improved, contributing to increased efficiency and improved quality in the development process.

[0099] In the second embodiment described above, the information processing system 40 is configured to determine the dependencies between the multiple generated requirement definitions, acquire information about those dependencies, and output it for presentation to the user U. However, it is not limited to this configuration, and the information about dependencies may be acquired and used in internal processing without outputting it for presentation to the user U. As an example of such internal processing, when a specified requirement definition is changed, the system can refer to the information about dependencies and automatically change other requirement definitions that have dependencies on it. This makes it possible to implement changes to requirement definitions without any omissions or errors.

[0100] (Third embodiment) Next, an information processing system 80 according to the third embodiment of the present invention will be described using Figures 12-14. The information processing system 80 according to the third embodiment has the same basic configuration as the first and second embodiments, and is characterized by including a process for generating documents that classify the requirements definitions according to predetermined criteria, and a process for inputting the requirements definitions for each document classification into a trained model 222 and outputting requirements definitions as secondary requirements. Components identical to those in the first and second embodiments are denoted by the same reference numerals and their descriptions are omitted. Furthermore, the requirements definition in this embodiment differs from the requirements definition in the embodiments described above in that it specifically summarizes what functions the system to be developed based on the requirements definitions should have and what it should be like.

[0101] (Functional Configuration) The functional configuration of the server 82 as an information processing device in the information processing system 80 will be described. Figure 12 is a diagram showing an example of the functional configuration of the server 82. When executing various programs, the server 82 uses the same hardware resources as the server 12 of the first embodiment to realize various functions. The server 82 has a communication unit 20, a storage unit 90, and a control unit 1000 as the functional configuration that the server 82 realizes. Each functional configuration is realized when the processor 120 reads and executes a program 900 stored in the memory 122 or storage 124.

[0102] The memory unit 90 is implemented by memory 122 and storage 124. The memory unit 90 stores the program 900, the trained model 222, the acquired information DB 224, the user information DB 226, the user information DB, and the processing result DB 230.

[0103] The control unit 1000 is realized when the processor 120 reads and executes the program 900 from the memory 122 (see Figure 2) and works in cooperation with other hardware components. The control unit 1000 includes a question provision unit 700, an information acquisition unit 1002 as an answer acquisition unit, an information processing unit 1004 as an output generation unit, and an output unit 1006.

[0104] Similar to the information acquisition unit in the first embodiment, the information acquisition unit 1002 has the function of acquiring answers from user U to questions provided by the question provision unit 242 (including answers to additional questions), as well as acquiring various information necessary for processing by the question provision unit 242 and the information processing unit 1004. Furthermore, the information acquisition unit 1002 acquires a document that classifies the requirement definitions generated by the information processing unit 1004 according to predetermined criteria, i.e., a requirement definition document (details will be described later).

[0105] The information processing unit 1004 has the same functions as the information processing unit 246 in the first embodiment and the information processing unit 704 in the second embodiment. Furthermore, the information processing unit 1004 has the function of generating a requirements definition document (see the requirements definition RD in Figure 10 as an example) as an example of a document that classifies requirements definitions according to predetermined criteria. Specifically, as an example, suppose that requirements definitions for "user authentication function" and "product search function" already exist. If a new requirement definition for "recommendation function" is added, the information processing unit 1004 integrates these requirements definitions and creates a consistent requirements definition document. First, it examines the existing requirements definitions to check for any inconsistencies or overlaps with the new requirements definitions. Next, it classifies each requirement definition according to predetermined criteria and organizes them into chapters such as "Chapter 1: System Overview," "Chapter 2: Functional Requirements," and "Chapter 3: Non-functional Requirements." In this embodiment, these predetermined criteria are defined as classification by chapter structure based on content. Specifically, "Chapter 1: System Overview" describes the system's purpose, background, and overall concept. Chapter 2, "Functional Requirements," details the requirements for specific functions the system should have, such as user authentication, product search, and shopping cart functions. Chapter 3, "Non-Functional Requirements," describes the requirements for non-functional qualities and constraints, such as performance, security, scalability, and reliability. However, these are not the only criteria that can be used. In other words, another specific criterion is "classification by priority." Requirements are classified into "high priority," "medium priority," and "low priority" based on their importance and urgency. For example, high priority includes requirements that must be implemented as basic functions of the system. Medium priority includes requirements that are important but can be addressed in the next phase, and low priority includes requirements that will be considered as future expansions or options. Furthermore, "classification by function" can also be used as a specific criterion. For example, "user management function" includes requirements for user registration, login, and password reset. "Product management function" summarizes requirements for product registration, editing, and inventory management. "Order processing function" includes adding products to the cart, purchase procedures, and displaying order history. This makes it easier to organize the requirements definition for each function and to divide the work among the relevant departments and teams.Another specific criterion is "classification by user type." By dividing the requirements definition into those for general users and those for administrators, it is possible to clearly define the functions that meet the needs of each user group. The requirements definition for general users should include requirements related to browsing the site, searching for products, and purchasing procedures, while the requirements definition for administrators should include requirements related to overall site management, user account management, and updating product data. These prescribed criteria may be a combination of the other specific criteria mentioned above, or they may be other criteria altogether.

[0106] The information processing unit 1004 is also capable of generating detailed versions of each requirement definition using the trained model 222. Specifically, it obtains the output of inputting the requirement definition and prompts instructing it to supplement specialized knowledge and appropriate expressions into the trained model 222. During this process, adjustments are made to reflect the user U's intentions and the overall system objectives through the adjustment of the prompts. The contents of each generated chapter are integrated by the information processing unit 1004 and compiled into a requirements definition document. Finally, the created requirements definition document is provided to the user U through the output unit 1006 and stored in the storage unit 60 (processing result DB 230).

[0107] Furthermore, the information processing unit 1004 analyzes the generated requirements definition document and inputs the requirements definitions from the requirements definition document into the trained model 222 for each classification of the requirements definition document, and outputs the requirements definitions, which are secondary requirements. This makes it possible to generate efficient and high-quality requirements definitions from the requirements definitions. Specifically, the information processing unit 1004 first executes processing for each classification of the requirements definition document RD. Specifically, as shown in Figure 15, it processes the requirements definitions chapter by chapter, such as "Chapter 1: System Overview (corresponding to node "1" in the figure)", "Chapter 2: Functional Requirements (corresponding to node "2" in the figure)", and "Chapter 3: Non-Functional Requirements (corresponding to node "3" in the figure)". First, it inputs the requirements definition for "Chapter 1: System Overview" into the trained model 222 to generate the requirements definition for the entire system (corresponding to the edge from RD to node 1 in the figure). At this time, the information processing unit 1004 sets and inputs appropriate prompts so that requirements definitions can be obtained from the requirements definition RD, and adjusts to obtain the expected output from the trained model 222. In this embodiment, the prompt is output to the user terminal 14 to be presented to user U, and at least one of the changes, modifications, and additions to the prompt by user U can be accepted and obtained. However, the system is not limited to this, and may be configured to automatically execute processing without presenting it to user U. Next, when processing "Chapter 2: Functional Requirements," the requirements definition for "Chapter 2: Functional Requirements" is input to the trained model 222 along with the appropriate prompt as described above to generate the requirements definition for the functional requirements (the edge from RD to node 2 in the figure corresponds to this), and in parallel, an edge (dependency) is built to refer to the requirements definition for "Chapter 1: System Overview" that was generated earlier (the edge from node 1 to node 2 in the figure corresponds to this). As a result, the information from "Chapter 1" is taken into consideration when generating "Chapter 2: Functional Requirements," and a consistent requirements definition is generated.Similarly, when processing "Chapter 3: Non-Functional Requirements," the requirements definition for "Chapter 3: Non-Functional Requirements" is input to the trained model 222 with appropriate prompts, as described above, to generate the requirements definition for functional requirements (corresponding to the edge from RD to node 3 in the diagram). In parallel, edges are built between this and the previously generated requirements definitions for "Chapter 1" and "Chapter 2" (corresponding to the edges from node 1 to node 3 and from node 2 to node 3 in the diagram). This ensures that the aforementioned information is utilized when generating "Chapter 3: Non-Functional Requirements," resulting in a consistent requirements definition for the entire system. This sequential processing and edge building allows information between chapters to be linked, making it possible to efficiently generate high-quality requirements definition documents that are consistent with each other.

[0108] The output unit 1006, similar to the output unit 248 of the first embodiment and the output unit 706 of the second embodiment, controls the output to the user terminal 14 to output the processing results of the question provision unit 242 and the information processing unit 246, as well as information regarding the dependencies between multiple requirement definitions. Furthermore, the output unit 706 can be controlled to output the requirement definition document and the requirements definition document to the user terminal 14.

[0109] (Processing performed by the information processing system 80) Next, the operation of the information processing system 80 will be explained. Figure 13 is a flowchart showing an example of the processing flow by the information processing system 80. Processing is performed when the processor 120 reads the program 600 stored in the storage 124, expands it into the memory 122, and executes it. Note that the same reference numerals are used for processing that is the same as in the first and second embodiments, and their descriptions are omitted.

[0110] After processing in step S200, the processor 120 determines whether or not it has received an instruction from user U to output the requirements definition document (step S300). If it has not received an output instruction (step S300: NO), the processor 120 proceeds to step S124. On the other hand, if it has received an output instruction (step S300: YES), the processor 120 outputs the requirements definition document and stores it in the storage unit 90 (step S302).

[0111] The processor 120 retrieves the requirements definition document stored in the memory unit 90 (step S304), analyzes the requirements definition document (step S306), outputs a prompt to the user terminal 14 for defining requirements from the requirements definition document set by the processor 120, and executes a process to display a screen on the user terminal 14 for accepting at least one of changes, modifications, and additions to the prompt (step S308).

[0112] The processor 120 determines whether to obtain at least one instruction from user U regarding change, modification, and addition in response to the prompt (step S310). If no instruction is obtained (step S310: NO), the processor 120 proceeds to step S314, which will be described later. On the other hand, if an instruction is obtained (step S310: YES), the processor 120 reflects the content of the instruction in the prompt (step S312) and generates requirements definitions for each classification in the requirements definition document. The requirements definitions are generated sequentially for each classification (for example, each chapter structure) as described above, and processing involving edge construction as needed.

[0113] The processor 120 determines whether the generation process of requirements definitions for all classifications in the requirements definition document has been completed (step S316). If the process is not completed (step S316: NO), the processor 120 proceeds to step S314. On the other hand, if the process is completed (step S316: YES), the processor 120 executes a process to output the generated requirements definitions to the user terminal 14 in order to present them to user U (step S318).

[0114] The processor 120 stores the generated requirements definition in the storage unit 60 (processing result DB230) (step S318) and determines whether or not it has received instructions from user U on which requirements definition to lock or unlock (step S320). If no instructions have been received (step S320: NO), the processor 120 proceeds to step S324, which will be described later. On the other hand, if instructions have been received (step S320: YES), the processor 120 reflects the locking or unlocking of the requirements definition to be instructed based on those instructions (step S322).

[0115] The processor 120 determines whether or not it has received an instruction from user U to delete a specific requirement definition (step S324). If no instruction has been received (step S324: NO), the processor 120 proceeds to step S328, which will be described later. On the other hand, if an instruction has been received (step S324: YES), the processor 120 deletes the requirement definition to be deleted from the processing result DB 230, etc., based on the instruction, and reflects the instruction (step S326).

[0116] The processor 120 analyzes at least one of the questions and their answers, and the requirements definitions (step S328). In this embodiment, the analysis also includes determining the dependencies between the multiple requirements definitions that have been generated. After that, the process proceeds to step S330.

[0117] The processor 120 determines whether there is any missing information as a result of the analysis (step S330). If there is missing information (step S330: YES), the processor 120 proceeds to step S314 to generate the requirements definition again. On the other hand, if there is no missing information (step S330: NO), the processor 120 determines whether there are any inconsistencies between the requirements definitions if multiple requirements definitions have been generated as a result of the analysis (step S332). If there are inconsistencies (step S332: YES), the processor 120 proceeds to step S314 to generate the requirements definition again to resolve the inconsistencies. On the other hand, if there are no inconsistencies (step S332: NO), the processor 120 outputs information regarding the generated requirements definitions for display on the user terminal 14 (step S334). Note that in this output, not only the requirements definitions but also the requirements definitions may be output as a requirements definition document organized according to a predetermined format. Specifically, the processor 120 first obtains predefined templates and formats (e.g., requirements definition documents, design specifications, project plans, etc.) from the storage unit 90 or external storage. Next, it classifies the requirements definitions based on predetermined classification criteria (e.g., by function, by priority, by module, etc.). According to this classification result, it assigns each requirements definition to the corresponding chapter or section of the document. After that, the processor 120 places the detailed content of each requirements definition into the corresponding location in the template. At this time, it automatically generates headings and item numbers as needed to organize the overall structure of the document. It also applies predetermined formatting settings such as font, paragraph, indentation, and bullet points to the placed content. This improves the readability and consistency of the document. Finally, after the above processing, a document conforming to a predetermined format, including the requirements definitions, is generated. This document is output as an electronic file (e.g., PDF, Word, HTML, etc.), stored in the storage unit 90, and made available to user U via the output unit 1006. The "documents" mentioned above include information recorded on paper, electronic, or other recording media. After the above processing, the processor 120 proceeds to step S124.

[0118] (Effects of the third embodiment) In the information processing system 80 according to this embodiment, the configuration is the same as in the first and second embodiments, except that it includes a process for generating documents that classify requirements definitions according to predetermined criteria, and a process for inputting requirements definitions into the trained model 222 for each document classification and outputting requirements definitions. Therefore, the same effects and advantages as in the first and second embodiments can be obtained. Furthermore, because it includes a process for generating a requirements definition document, which is a document that classifies requirements definitions according to predetermined criteria, and a process for inputting requirements definitions into the trained model 222 for each document classification and outputting requirements definitions, it becomes possible to generate detailed requirements definitions suitable for each classification. In other words, if the entire requirements definition document is processed at once rather than by document classification, the characteristics of each requirements definition may not be sufficiently reflected, and the content tends to be superficial. This is because the trained model 222 may have limitations on the length and amount of information it can process at once, and if the entire requirements definition document is input at once, the trained model 222 tries to process the entire input evenly, thus distributing the processing resources for each requirements definition. As a result, the details and characteristics of each requirements definition may not be sufficiently understood by the trained model 222, and the output requirements definition may become superficial and shallow. Furthermore, processing a large amount of information at once can make it difficult for the trained model 222 to evaluate the importance and relevance of the information. Important requirements and special conditions may get buried among other information and are less likely to be properly reflected. Thus, the overall quality deteriorates as the computational resources of the trained model 222 are distributed. Moreover, processing the entire requirements document at once makes it difficult to accurately capture the dependencies and relationships between each requirements. If the model cannot properly understand the interactions of each requirements, there is a risk of generating inconsistent requirements definitions. In contrast, by processing sequentially by classification (chapter by chapter) as in this embodiment, the trained model 222 can concentrate its computational resources on processing the requirements definitions of each chapter. This makes it possible to generate requirements definitions that fully reflect the characteristics and details of each requirements definition. In addition, by referencing the information generated in the previous chapter through edge construction, it is possible to maintain consistency and coherence of the requirements definitions between chapters.This allows for the identification of appropriate requirements and specifications without limiting the scope of application, thereby further supporting system development.

[0119] Furthermore, since the information processing system 80 includes the process of translating requirements definitions into requirements definition documents organized according to a prescribed format, it streamlines the management, sharing, and communication of requirements definitions. This makes it possible to unify understandings and facilitate communication among relevant stakeholders in system development projects.

[0120] In the first to third embodiments described above, the requirements are defined as requirements in system development, but they are not limited to these. They may also include safety and design requirements in various projects, quality and cost requirements in product development, customer satisfaction and response speed requirements in the service industry, performance conditions and scope of liability requirements in legal contracts, learning outcomes and curriculum requirements in education, and other such requirements. Furthermore, in the third embodiment described above, the secondary requirements are defined as requirements, but they are not limited to these. They may also include secondary requirements for seismic performance and fire resistance derived from safety requirements in various projects, secondary requirements for durability and ease of use derived from quality requirements in product development, secondary requirements for staff response skills and service delivery time derived from customer satisfaction requirements in the service industry, and secondary requirements for the richness of teaching materials and individual instruction derived from learning outcomes requirements in education, and other such requirements.

[0121] <Note> This embodiment includes the following disclosures.

[0122] (Note 1) An information processing method performed by an information processing device, A question provision step that performs at least one of selecting questions to obtain requirements and generating said questions, The answer acquisition step involves obtaining the answer to the aforementioned question, An information processing method comprising: an output generation step of generating requirements from answers using a trained model that has been trained on at least text data and, upon input of information including the answers, generates requirements estimated from the answers.

[0123] (Note 2) The step of providing the question includes a process of providing background information related to the question along with the question, The information processing method described in Appendix 1.

[0124] (Note 3) The output generation step includes a process to generate an evaluation of the response based on predetermined evaluation criteria and at least one of the grounds for said evaluation, The information processing method described in Appendix 1 or Appendix 2.

[0125] (Note 4) A verification step which involves analyzing the requirements generated by the output generation step and detecting any lack of information in at least one of the questions and answers, If a lack of information is detected in the verification step, the process includes repeating the question provision step to provide additional questions to obtain the missing information, and repeating the answer acquisition step to obtain the additional answers. The information processing method described in any one of the appendices 1 to 3.

[0126] (Note 5) The process includes determining whether there are any inconsistencies among the multiple requirements generated in the output generation step, and if an inconsistency is determined, repeating the question provision step to provide additional questions to obtain information necessary to resolve the inconsistency, and repeating the answer acquisition step to obtain additional answers. The information processing method described in any one of the appendices 1 to 4.

[0127] (Note 6) This process includes determining the dependencies between the multiple generated requirements and obtaining information about those dependencies. The information processing method described in any one of the appendices 1 to 5.

[0128] (Note 7) The process includes storing the aforementioned requirements in a storage unit, retrieving the requirements from the storage unit at a predetermined timing, and providing a question that includes confirming whether or not the requirements have been updated. The information processing method described in any one of the appendices 1 to 6.

[0129] (Note 8) The process includes setting a predetermined requirement as a standard requirement from among a plurality of the aforementioned requirements, and determining, based on the said standard requirement, whether there is any deficiency, inconsistency, or update of information for the other aforementioned requirements, The information processing method described in any one of the appendices 1 to 7.

[0130] (Note 9) Based on the determination result of the aforementioned criteria determination process, if there is any missing, inconsistent, or update-needed information regarding other requirements, the process includes providing a question to resolve these issues. The information processing method described in Appendix 8.

[0131] (Note 10) The process includes obtaining a deletion instruction for the aforementioned requirements, and performing the deletion of the deletion instruction when it is obtained. The information processing method described in any one of the appendices 1 to 9.

[0132] (Note 11) A process for generating a document that classifies the aforementioned requirements according to predetermined criteria, The process includes inputting the requirements for each classification of the document into the trained model and outputting secondary requirements, The information processing method described in any one of the appendices 1 to 10.

[0133] (Note 12) This includes the process of putting the aforementioned secondary requirements into a document organized according to a prescribed format, The information processing method described in Appendix 11.

[0134] (Note 13) In an information processing device, A question provision step that performs at least one of selecting questions to obtain requirements and generating said questions, The answer acquisition step involves obtaining the answer to the aforementioned question, An output generation step of generating requirements from the answers using a trained model that has been trained on at least text data and, upon input of information including the answers, generates requirements estimated from the answers; A program for executing an information processing method that includes this method.

[0135] (Note 14) An information processing system executed by an information processing device, A question providing unit that performs at least one of selecting questions to obtain requirements and generating said questions, An answer acquisition unit that obtains the answer to the aforementioned question, An output generation unit that generates requirements from the answers using a trained model that has been trained on at least text data and, upon input of information including the answers, generates requirements estimated from the answers, An information processing system having

[0136] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims, not in the sense described above, and is intended to include all modifications in the sense and scope equivalent to the claims. Furthermore, the present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0137] 10 Information Processing Systems 12. Server (Information Processing Device) 22 Memory section 40 Information Processing Systems 50 Servers (Information Processing Devices) 60 Storage section 80 Information Processing Systems 82. Server (Information Processing Device) 220 programs 222 Pre-trained Models 242 Question provision department 244 Information acquisition unit (answer acquisition unit) 246 Information Processing Unit (Output Generation Unit) 600 programs 700 Question provision department 702 Information acquisition unit (answer acquisition unit) 704 Information Processing Unit (Output Generation Unit) 900 programs 1002 Information acquisition section (answer acquisition section) 1004 Information Processing Unit (Output Generation Unit)

Claims

1. An information processing method performed by an information processing device, A question provision step that performs at least one of selecting questions to obtain requirements and generating said questions, The answer acquisition step involves obtaining the answer to the aforementioned question, An output generation step of generating requirements from the answers using a trained model that has been trained on at least text data and, upon input of information including the answers, generates requirements estimated from the answers; Information processing methods including

2. The step of providing the question includes a process of providing background information related to the question along with the question, The information processing method according to claim 1.

3. The output generation step includes a process to generate an evaluation of the response based on predetermined evaluation criteria and at least one of the grounds for said evaluation, The information processing method according to claim 1.

4. A verification step which involves analyzing the requirements generated by the output generation step and detecting any lack of information in at least one of the questions and answers, If a lack of information is detected in the verification step, the process includes repeating the question provision step to provide additional questions to obtain the missing information, and repeating the answer acquisition step to obtain the additional answers. The information processing method according to claim 1.

5. The process includes determining whether there are any inconsistencies among the multiple requirements generated in the output generation step, and if an inconsistency is determined, repeating the question provision step to provide additional questions to obtain information necessary to resolve the inconsistency, and repeating the answer acquisition step to obtain additional answers. The information processing method according to claim 1.

6. This process includes determining the dependencies between the multiple generated requirements and obtaining information about those dependencies. The information processing method according to claim 1.

7. The process includes storing the aforementioned requirements in a storage unit, retrieving the requirements from the storage unit at a predetermined timing, and providing a question that includes confirming whether or not the requirements have been updated. The information processing method according to claim 1.

8. The process includes setting a predetermined requirement as a standard requirement from among a plurality of the aforementioned requirements, and determining, based on the said standard requirement, whether there is any deficiency, inconsistency, or update of information for the other aforementioned requirements, The information processing method according to claim 1.

9. Based on the determination result of the aforementioned criteria determination process, if there is any missing, inconsistent, or update-needed information regarding other requirements, the process includes providing a question to resolve these issues. The information processing method according to claim 8.

10. The process includes obtaining a deletion instruction for the aforementioned requirements, and performing the deletion of the deletion instruction when it is obtained. The information processing method according to claim 1.

11. A process for generating a document that classifies the aforementioned requirements according to predetermined criteria, The process includes inputting the requirements for each classification of the document into the trained model and outputting secondary requirements, The information processing method according to claim 1.

12. This includes the process of putting the aforementioned secondary requirements into a document organized according to a prescribed format, The information processing method according to claim 11.

13. In an information processing device, A question provision step that performs at least one of selecting questions to obtain requirements and generating said questions, The answer acquisition step involves obtaining the answer to the aforementioned question, An output generation step of generating requirements from the answers using a trained model that has been trained on at least text data and, upon input of information including the answers, generates requirements estimated from the answers; A program for executing an information processing method that includes this method.

14. An information processing system executed by an information processing device, A question providing unit that performs at least one of selecting questions to obtain requirements and generating said questions, An answer acquisition unit that obtains the answer to the aforementioned question, An output generation unit that generates requirements from the answers using a trained model that has been trained on at least text data and, upon input of information including the answers, generates requirements estimated from the answers, An information processing system having

Images