Information processing systems, information processing methods, and programs

Abstract

We provide an information processing system that receives information from users regarding the purpose of implementation and other relevant details, and creates requests for proposals tailored to each user. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program, wherein in the reception step, input information of a user considering the introduction of a service is received, the input information includes at least one of user information, a category of service the user is considering, and the user's purpose for introduction; in the requirements generation step, based on the input information, requirements for introducing a service are generated by a large-scale language model using a case database in which service introduction cases are accumulated; and in the request for proposal generation step, a request for proposal is generated by a large-scale language model based on the requirements.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , , , ,

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

Background Art

[0002] Patent Document 1 describes a method and an information processing apparatus for extracting, as candidates for introduction, a cloud service that satisfies system requirements and a cloud service that satisfies the potential needs of users from among a plurality of cloud services.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, when a user newly considers introducing a service, it is necessary to request materials from many vendors and conduct a comparative study. In addition, when there is a request for materials, sales from vendors often come, but it is not efficient for either the user or the vendor to conduct sales from the vendor to a user who only intends to request materials. There is still room for technical improvement in a system for supporting the introduction of services.

[0005] In view of the above circumstances, the present invention provides an information processing system that receives information such as the purpose of introduction from a user and creates a request form or the like regarding a proposal according to the user.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor configured to perform the following steps by reading a program, wherein in the reception step, input information of a user considering the introduction of a service is received, the input information includes at least one of user information, a category of service the user is considering, and the user's purpose for introduction; in the requirements generation step, based on the input information, requirements for introducing the service are generated by a large-scale language model using a case database in which service introduction cases are accumulated; and in the request for proposal generation step, a request for proposal is generated by a large-scale language model based on the requirements.

[0007] In this configuration, it is possible to provide an information processing system that receives information from users, such as the purpose of implementation, and creates requests for proposals tailored to the user.

[0008] Embodiments of the present invention will be described below. The various features shown in the embodiments below can be combined with each other. [Brief explanation of the drawing]

[0009] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] Block diagram showing the hardware configuration of Server 2. [Figure 3] This is a block diagram showing the hardware configuration of user terminal 3. [Figure 4] This flowchart shows an overview of the processes performed by Information Processing System 1. [Figure 5] This is an activity diagram illustrating a specific example of the process performed by Information Processing System 1 up to the point of presenting the requirements list. [Figure 6] This is an activity diagram illustrating a specific example of processing that utilizes a requirements list, which is executed by Information Processing System 1. [Figure 7]Confirmation screen 4 shows an example of a screen that illustrates the exchange of confirmation items and responses regarding candidate requirements. [Figure 8] This figure shows Requirement List 5, which is an example of a requirements list. [Figure 9] This figure shows a Request for Proposal 6, which is an example of a request for proposals. [Figure 10] Confirmation screen 7 shows an example of a screen illustrating the exchange of questions and answers regarding the draft Request for Proposal. [Figure 11] This is an example of confirmation screen 8 for verifying the recipient of the Request for Proposal. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0011] Incidentally, the program for implementing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or it may be provided as a downloadable medium from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0012] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as "reference information") is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a pre-trained model that has learned the correlation between input and output in advance, or a large-scale language model that can output a desired result by inputting a prompt.

[0013] Also, in one embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Further, in one embodiment, various types of information are handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0014] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit (Circuit), circuitry (Circuitry), a processor (Processor), a memory (Memory), etc. Also, the processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), programmable logic devices (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0015] 1. Hardware Configuration In this section, the hardware configuration will be described.

[0016] <Information Processing System 1> FIG. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes a server 2 and a user terminal 3. The server 2 stores a database DB. The server 2 and the user terminal 3 are configured to be communicable through a telecommunication line. Here, the system exemplified by the information processing system 1 is composed of one or more devices or components. Therefore, note that even the server 2 alone, or at least a combination of two of the server 2 and the user terminal 3, may be included in the information processing system 1. Also, the database DB may be stored in a server different from the server 2. More specifically, the information processing system 1 may include an element selected from the group consisting of the server 2 and the user terminal 3. Even if the unselected element is not included in the information processing system 1, it may be electrically connected to the selected element as an external element. Note that the configuration shown in FIG. 1 and the like is an example, and other modes can be adopted as long as there is no inconvenience in implementation. Hereinafter, these components will be described.

[0017] <Server 2> FIG. 2 is a block diagram showing the hardware configuration of the server 2. The server 2 includes a communication unit 21, a storage unit 22, and a control unit 23, and these components are electrically connected via a communication bus 20 inside the server 2. Each component will be further described.

[0018] The communication unit 21 preferably uses wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), and wired LAN network communication, but may include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, and BLUETOOTH (registered trademark) communication as needed. That is, it is more preferable to implement it as a set of these multiple communication means. That is, the server 2 may communicate various information from the outside via the communication unit 21 and the network.

[0019] The memory unit 22 stores various types of information as defined above. This can be done, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the server 2 executed by the control unit 23, or as memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The memory unit 22 stores various programs and variables related to the server 2 executed by the control unit 23.

[0020] The control unit 23 performs processing and control of the overall operation related to the server 2. The control unit 23 is, for example, a central processing unit (CPU) not shown. The control unit 23 realizes various functions related to the server 2 by reading predetermined programs stored in the memory unit 22. That is, information processing by software stored in the memory unit 22 is concretely realized by the control unit 23, which is an example of hardware, so that each step related to each function described later can be executed. These will be described in more detail in the next section. Note that the control unit 23 is not limited to being a single unit, and may be implemented with multiple control units 23 for each function, or a combination thereof.

[0021] Server 2 may be on-premises or in a cloud environment. A cloud-based Server 2 may provide the aforementioned functions and processing in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] Server 2 may be distributed across two or more devices, or it may be replaced by a cloud computing system. Furthermore, the functions of Server 2 may be distributed across two or more devices, or the functions of two or more devices may be centralized into a single device. Also, the actions performed by one function may be distributed across two or more functions, or two or more functions may be integrated into a single function. In short, as long as the necessary functions of the information processing system 1 as a whole are realized, the devices that realize those functions can be configured in any way.

[0023] <User Terminal 3> Figure 3 is a block diagram showing the hardware configuration of user terminal 3. User terminal 3 comprises a communication unit 31, a storage unit 32, a control unit 33, a display unit 34, and an input unit 35, and these components are electrically connected within user terminal 3 via a communication bus 30. User terminal 3 may be a multifunction information terminal, a mobile information terminal, a tablet terminal, a personal computer, AR glasses, etc., used by the user. The explanation of the communication unit 31, storage unit 32, and control unit 33 is the same as the explanation of each part in server 2 and is therefore omitted.

[0024] The display unit 34 may be included in the user terminal 3 housing or it may be an external component. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. This is preferably done by using different display devices such as a CRT display, liquid crystal display, organic EL display, and plasma display, depending on the type of user terminal 3.

[0025] The input unit 35 may be included in the casing of the user terminal 3 or it may be an external component. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. If it is a touch panel, the user can input tap operations, swipe operations, etc. Of course, a switch button, mouse, QWERTY keyboard, etc. may be used instead of a touch panel. In other words, the input unit 35 receives operation input made by the user. This input is transmitted as a command signal to the control unit 33 via the communication bus 30, and the control unit 33 can perform predetermined controls and calculations as needed.

[0026] <database DB> The database (DB) is configured to store, search, and edit various types of data. The database is located in the storage unit (22) of server (2). The control unit (23) can store data in the database (DB), search for data stored in the database (DB), and retrieve data from the database (DB) based on queries using query languages ​​such as SQL. The control unit (23) can place, for example, a case study database containing implementation examples and related knowledge, or a product information database containing product information, in the storage unit (22).

[0027] The case study database is a database that stores information on service implementation cases. This information includes user information of the implementing company and information on the implemented service. User information of the implementing company includes, for example, information on the user's industry, employee size, number of employees, number of locations, presence of subsidiaries, sales, profits, and company attributes. Information on the implemented service includes, for example, information on the category of the implemented service, purpose of implementation, implementation timing, and deciding factors for implementation. The case study database may also include information on other services used by companies that have implemented services in the past.

[0028] The control unit 23 may collect information obtained from interviews with companies that have previously implemented the service, information posted on the internet by companies that have previously implemented the service, etc., and store it in the case database. The control unit 23 may also store information obtained by analyzing the collected information in the case database. The control unit 23 may also collect and store knowledge related to the cases stored in the case database. Related knowledge includes information obtained from interviews with companies that have previously implemented the service, information posted on the internet by companies that have previously implemented the service, product information related to the stored cases, vendor information, articles, posts, word-of-mouth, etc. corresponding to the product information. The control unit 23 may store information about service implementation cases and knowledge related to the cases, etc., along with information about the sources of reference. Information about sources of reference refers to the basis or source of the information.

[0029] The product information database is a database that stores product information related to a service. A product refers to a specific item or service that a company or individual provides to the market. For example, a product may be software or hardware that meets user needs. Product information may include information such as service content, service features, software functions, specifications required to use the service (specifications for hardware, software, internet connection, etc.), vendor information, pricing plans, security, support system, and customer reviews. For example, the product information database is a database that stores product information for SaaS products. The product information database may also store detailed functions and features of each SaaS product. The control unit 23 may collect information about products published on a website and store it in the product information database. The control unit 23 may also store information about the source of the references along with the product information related to the service. Information about the source of the references refers to the basis or origin of the information.

[0030] 2. Functional configuration of Server 2 This section describes the functional configuration of the server 2 in this embodiment. Information processing by a program, which is an example of software stored in the memory unit 22, is specifically realized by the control unit 23, which is an example of hardware. The control unit 23 (at least one processor provided in the information processing system 1) is configured to perform the following steps: The control unit 23 is configured to perform a reception step, an extraction step, a presentation step, a generation step, an acquisition step, an update step, a transmission step, a determination step, and a display control step.

[0031] The control unit 23 is configured to receive information from the user terminal 3 or other information processing terminals as part of the reception step. Furthermore, the control unit 23 is configured to receive various types of information by reading various types of information stored in the storage area, which is at least a part of the memory unit 22, and writing the read information to the work area, which is at least a part of the memory unit 22. The storage area is, for example, the area of ​​the memory unit 22 that functions as a storage device such as an SSD. The work area is, for example, the area that functions as memory such as RAM. For example, the control unit 23 can receive input information from a user considering introducing the service as part of the reception step.

[0032] The control unit 23 can extract information from a predetermined database as an extraction step. For example, as a first extraction step, the control unit 23 can extract similar cases from a case database based on the received input information. Based on the received input information, the control unit 23 can extract similar cases, which are examples of service implementation cases, and related knowledge from the case database using queries generated by a large-scale language model. In addition, as a second extraction step, the control unit 23 may extract one or more product information from a product information database where product information for services is stored, based on a requirements list. In this case, as a second extraction step, the control unit 23 may extract one or more product information based on the degree of compatibility between the requirements list and the product information for services.

[0033] The control unit 23 performs processing to present various information to each terminal as a presentation step. As a presentation step, the control unit 23 can present various information extracted or acquired in the information processing system 1. For example, as a presentation step, the control unit 23 can present extracted service-related information. As service-related information, the control unit 23 can present similar cases, related knowledge, requirements lists, product information extracted in the extraction step, vendor information corresponding to the product information, etc. Also, as a presentation step, the control unit 23 can present proposals acquired from vendors, etc. As a presentation step, the control unit 23 may present various information in a selectable manner or in a modifiable manner.

[0034] The control unit 23 can generate various types of information by referring to reference information stored in the storage unit 22 of the server 2 as a generation step. The control unit 23 may also use an artificial intelligence module when generating various types of information as a generation step. The control unit 23 can generate various types of information using the artificial intelligence module based on input information and reference information. The artificial intelligence module used by the server 2 to execute each step may be a common one, or it may be individually prepared for each step.

[0035] The artificial intelligence module may include a trained model constructed using a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answers). A language model is an example of a learning model using a machine learning algorithm. Specific machine learning algorithms include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence module can apply the above algorithms as appropriate. The language model may be a general-purpose model that can be used universally for a wide range of tasks, rather than one trained for a specific task.

[0036] The artificial intelligence module may be an external component of server 2. In this case, the external artificial intelligence module may be provided by, for example, an artificial intelligence service server, which is configured to receive input from server 2, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to server 2. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that performs language processing tasks using a language model. The artificial intelligence service server may receive prompt input in the form of text, images, audio, etc., and generate and respond with answers to those prompts.

[0037] A language model is a pre-trained model that has learned from large datasets consisting of text data, etc. (for example, (i) web content on the internet, or (ii) data stored in a predetermined database). By being given a task, it can perform various language processing tasks, and according to given prompts, it can perform a wide range of natural language processing tasks such as understanding sentence patterns and context, answering questions, and generating sentences. Such a general-purpose learning model includes language models that can handle various tasks without fine-tuning using One-shot Learning or Few-shot Learning. Furthermore, a general-purpose learning model may also be configured to handle various tasks using Zero-shot Learning.

[0038] Large language models (LLMs) are language models constructed using large amounts of data and deep learning techniques. These language models utilize the probability of occurrence of sentences and words. Large language models include transformers such as GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, GPT-4, and GPT-4o), BERT (Bidirectional Encoder Representations from Transformers), and BART (Bidirectional and Auto-regressive Transformer), as well as language models such as recurrent neural networks (RNNs), and generative AI. Furthermore, large language models may also include image generation models such as DALL-E, Stable Diffusion, and MidJourney.

[0039] The large-scale language model is configured to receive prompt input from the control unit 23 and generate output based on the input prompt. The large-scale language model can perform additional learning as transfer learning or fine-tuning individually at each step executed by the control unit 23. For example, the large-scale language model may perform additional learning and fine-tuning each time the case database or the product information database containing service product information is updated, using these as new training data. This improves the accuracy of the information output from the large-scale language model.

[0040] The control unit 23 can generate queries that allow searching the database based on various information as a query generation step. For example, the control unit 23 can generate queries that allow searching the case database based on input information as a query generation step. The control unit 23 can generate queries based on input information and reference information. The reference information may be predetermined rules, a trained model, or a large-scale language model. That is, the control unit 23 may generate queries using a query generation model that has been trained to take the input information as input and output queries that search the case database. In this case, the control unit 23 may input the input information into the query generation model and have the query generation model output queries. The control unit 23 may weight the search condition items of the query and tune the query generation model so that items that greatly affect the validity of referencing as a case (e.g., product category or industry) are given more weight.

[0041] The control unit 23 may generate a query using a large-scale language model as a query generation step. The control unit 23 may input a prompt to the large-scale language model that includes an instruction to take input information as input and output a search query corresponding to said input information, causing the large-scale language model to output the search query. The control unit 23 may generate a prompt that gives the large-scale language model an instruction to create a search query corresponding to the input information, and input said prompt to the large-scale language model. In addition to the search query creation and output instruction and input information, the control unit 23 may input a prompt to the large-scale language model that includes, for example, one or more samples of input information and one or more samples of corresponding search queries as input and output samples. The large-scale language model may generate a search query according to the input prompt.

[0042] As a requirements generation step, the control unit 23 may generate candidate service requirements corresponding to the input information using a large-scale language model based on similar cases or related knowledge. The control unit 23 inputs a prompt to the large-scale language model that includes an instruction to output a list of requirements corresponding to similar cases or related knowledge, and causes the large-scale language model to output candidate requirements. The control unit 23 may also generate a prompt that gives the large-scale language model an instruction to generate candidate requirements corresponding to similar cases or related knowledge, and input this prompt to the large-scale language model. Alternatively, the control unit 23 may input a prompt to the large-scale language model that includes an instruction to generate and output candidate requirements, as well as similar cases or related knowledge, and, as input and output samples, for example, one or more samples of similar cases or related knowledge and one or more samples of corresponding candidate requirements. The large-scale language model generates candidate requirements according to the input prompt. The control unit 23 may also generate a requirements list based on the candidate requirements as a requirements generation step. Here, the requirements list is a list summarizing the requirements for introducing the service.

[0043] The control unit 23 may, as a requirement generation step, generate a list of requirements based on similar cases and answers using a large-scale language model.

[0044] As a Request for Proposal (RFP) generation step, the control unit 23 can generate a Request for Proposal for service vendors using a large-scale language model based on a requirements list. The control unit 23 takes candidate requirements or a requirements list as input, inputs prompts to the large-scale language model that include instructions to output an RFP for proposals corresponding to the candidate requirements or requirements list, and causes the large-scale language model to output an RFP for proposals. The control unit 23 may also generate a prompt that gives instructions to the large-scale language model to generate an RFP for proposals corresponding to the candidate requirements or requirements list, and input this prompt to the large-scale language model. Alternatively, the control unit 23 may input prompts to the large-scale language model that include instructions to generate and output an RFP for proposals, as well as candidate requirements or requirements lists, and, in addition, input and output samples such as one or more sample candidate requirements or requirements lists and one or more sample RFPs for proposals corresponding to them. The large-scale language model generates an RFP for proposals according to the input prompts.

[0045] The control unit 23 may, as a generation step, generate confirmation items and questions regarding the generated service-related information. The control unit 23 may present the confirmation items and questions to the user via a chat system and receive responses from the user. After receiving responses from the user, the control unit 23 may generate further confirmation items and questions based on the user's responses. Specifically, the control unit 23 generates confirmation items for the user regarding the generated service-related information and presents them to the user. Upon receiving responses from the user, the control unit 23 may analyze the intent of the user's responses using natural language processing technology and generate further confirmation items and questions. The control unit 23 may sequentially display the responses with the user on the user's screen. The control unit 23 may generate confirmation items and questions using a predefined template, or it may generate confirmation items and questions using an artificial intelligence module.

[0046] The control unit 23 can acquire information from the user terminal 3 or other information processing terminal as an acquisition step. The control unit 23 is also configured to acquire various information by reading various information stored in the storage area, which is at least a part of the memory unit 22, and writing the read information to the work area, which is at least a part of the memory unit 22. The storage area is, for example, the area of ​​the memory unit 22 that is implemented as a storage device such as an SSD. The work area is, for example, the area that is implemented as memory such as RAM. As a first acquisition step, the control unit 23 may acquire answers to confirmation items by presenting confirmation items to the user for generating a requirements list. As a second acquisition step, the control unit 23 can acquire vendor change instructions corresponding to product information. As a third acquisition step, the control unit 23 may acquire proposals created from vendors based on a request for proposals.

[0047] The control unit 23 can perform a process to update reference information as an update step. For example, as a first update step, the control unit 23 may update the case database based on the input information and the information presented to the user. As a second update step, the control unit 23 may collect information published on the website and update the case database or the product information database where product information of the service is stored.

[0048] The control unit 23 can transmit various types of information as a transmission step. For example, as a first transmission step, the control unit 23 can send a request for proposals to selected vendors. Furthermore, as a second transmission step, the control unit 23 can send information to vendors corresponding to selected proposals to schedule meetings with users.

[0049] The control unit 23 can determine various pieces of information based on the acquired information and reference information as a determination step. The control unit 23 may also be configured to read reference information stored in the storage area, which is at least a part of the memory unit 22, as a determination step, and to determine various pieces of information based on the read reference information. The control unit 23 may also determine the degree of compatibility between the request form for the proposal generated based on the input information and the acquired proposal.

[0050] The control unit 23 is configured to enable the display of a reception screen on the display unit 34 of the user terminal 3 as a display control step. The control unit 23 executes processing to display system screens related to the information processing system 1 on each terminal as a display control step. The control unit 23 performs processing such as generating and sending an HTML (Hyper Text Markup Language) file as a display control step to display a web page showing the system screen on the display unit 34 of the user terminal 3. The control unit 23 may also perform processing such as generating and sending display data for applications that use the information processing system 1 as a display control step. Specifically, the control unit 23 controls the display of visual information such as screens, images including still images or videos, icons, and messages on the display unit 34 of the user terminal 3 as a display control step. The control unit 23 may also generate only rendering information for displaying visual information on the display unit 34 of the user terminal 3 as a display control step. The control unit 23 may also perform processing such as generating and sending display data for applications that use the information processing system 1 as a display control step. 3. Information Processing Flow This section describes the flow of the information processing method executed by the information processing system 1. As shown below, the information processing method comprises each step executed by the information processing system. The information processing program of this embodiment causes the computer to execute each step of the information processing system. The order of processing can be changed as appropriate, multiple processes may be executed simultaneously, and some processes may be omitted.

[0051] 3.1 Overview Considering the introduction of new services is not a routine task for many companies, which means that the know-how for properly defining the requirements of services suited to their specific needs is often not accumulated internally. Because the appropriate service varies depending on each company's industry, size, and existing systems, it is extremely difficult for users to identify the service that best suits their needs.

[0052] On the other hand, while vendors offer products that provide a variety of services, they also face the problem that inquiries from users who are unclear about their specific service requirements or the feasibility of implementing those services make sales activities difficult.

[0053] Therefore, by providing information processing systems that propose information processing-related services tailored to the user, users can understand the appropriate requirements for their own company, thereby promoting the smooth introduction of information processing-related services. Furthermore, since they can conduct business negotiations with vendors that meet those requirements after understanding the appropriate requirements, efficient business negotiations become possible for both parties.

[0054] A service refers to actions or support provided in response to specific needs or requests. Examples of services include those provided using information processing technology, and those that can be applied for or used via computer. Services provided using information processing technology include cloud services, on-premise systems, and various services via applications. Examples of services provided using information processing technology include data storage services, database management services, network management services, and cybersecurity services. Cloud services (IaaS, PaaS, SaaS, etc.) offer a variety of products and functions. On-premise systems are systems where software and hardware are installed and operated within a company's own facilities. Various services via applications refer to various functions and support provided through applications for user terminal 3. Examples of services via applications include online shopping applications, transportation reservation systems, digital payment systems, messaging services, and music and video streaming services. By introducing services provided using information processing technology, users can benefit from increased operational efficiency, among other advantages. Information processing system 1 is a system that can support users considering the introduction of services.

[0055] Figure 4 is a flowchart outlining the processes performed by the information processing system 1. In this process, first, the control unit 23 receives input information from a user considering introducing the service as a reception step (step S001). Here, the input information includes user information, the category of service the user is considering, and the user's purpose for introducing the service. Next, as a requirements generation step, the control unit 23 generates requirements for introducing the service using a large-scale language model based on the input information and a case database containing accumulated service introduction examples (step S002). Next, as a request for proposal generation step, the control unit 23 generates a request for proposal using a large-scale language model based on the requirements (step S003).

[0056] In summary, the information processing system according to one embodiment comprises at least one processor. The processor executes the following steps by reading a program. The control unit 23, as a reception step, receives input information from a user considering introducing a service. The input information includes at least one of user information, the category of service the user is considering, and the user's purpose for introducing the service. As a requirements generation step, the control unit 23 generates requirements for introducing the service using a large-scale language model based on the input information and a case database in which service introduction examples are accumulated. As a request for proposal generation step, the control unit 23 generates a request for proposal using a large-scale language model based on the requirements. According to this embodiment, it is possible to provide an information processing system that receives information such as the purpose of introduction from a user and creates a request for proposal etc. tailored to the user company.

[0057] 3.2 Specific Examples Figure 5 is an activity diagram showing a specific example of the process performed by Information Processing System 1 up to the point of presenting the requirements list. Figure 6 is an activity diagram showing a specific example of the process performed by Information Processing System 1 using the requirements list. The specific examples may be included within the scope defined in the overview described above. The following will explain each activity in this activity diagram.

[0058] <Process until the requirements list is presented> As shown in Figure 5, first, the control unit 23 displays the system screen on the user's terminal 3 (Activity A101). The system screen is configured to accept input information, and when input information is entered by the user, the control unit 33 of the user terminal 3 transmits the entered input information to the control unit 23. The user is an individual or organization considering the introduction of information processing-related services, and if the user is an organization, the user includes the person in charge of the organization considering the introduction of the service. The following explanation uses the case where the user is a company as an example, but organizations other than companies are also included as users.

[0059] Next, the control unit 23 receives input information from a user considering the introduction of an information processing-related service as a reception step (Activity A102). The input information includes user information, the category of service the user is considering, and at least one of the user's purpose for introduction. The control unit 23 may obtain some of the input information from the user in advance, and in Activity A102, the control unit 23 may read and obtain the user information obtained in advance from the storage unit 22. The control unit 23 may also obtain some of the input information from another information processing system that stores user information via a network.

[0060] User information may include, for example, information about the user's industry, company size, number of employees, number of locations, presence of subsidiaries, sales, profits, and company attributes. User information may also include other important company-specific characteristics and requirements. Company size refers, for example, to the number of employees belonging to the user's company who use the system. The service categories the user is considering are, for example, expense reimbursement systems, invoice generation systems, and sales management systems. The user's purpose for implementation is, for example, to improve the speed of accounting processing or to digitize invoices.

[0061] The input information may include the planned implementation date, existing services that need to be integrated, and information about other services the user is already using. In this manner, it may be possible to provide proposals that include integration between other services already in use and the newly introduced service.

[0062] Next, the control unit 23 performs a first extraction step by extracting similar cases from the case database based on the received input information. Specifically, based on the received input information, the control unit 23 performs a first extraction step by extracting service-related information from the case database, which contains accumulated service implementation examples, using the input information and a large-scale language model. An example of the information processing for extracting service-related information based on input information is shown below. Note that service-related information is information related to the service.

[0063] Next, the control unit 23 generates a query based on the input information as a query generation step (activity A103). The query is used to extract information from the case database. The control unit 23 may generate a query based on the input information and reference information. The reference information may be a predetermined rule, a learning model, or a large-scale language model. For example, the control unit 23 may generate a query to extract cases related to the input information received from the user.

[0064] Next, the control unit 23 sends a query to the case database (Activity A104).

[0065] Next, the control unit 23 searches the case database by query and determines whether or not there are any similar cases that can be extracted (Activity A105). Here, a similar case is a case that has attributes similar to the input information. If no similar cases are extracted by the query, the control unit 23 may determine that there are no similar cases that can be extracted by the query.

[0066] Furthermore, similar cases may also be cases that possess attributes whose similarity to the content of the input information is equal to or greater than a predetermined value. The control unit 23 may calculate the similarity between the content of the input information and the attributes of the cases stored in the database based on the query, and if there are no cases that satisfy the predetermined conditions, it may determine that there are no similar cases that can be extracted by the query.

[0067] Here, "content of input information" can include, for example, industry, product category, purpose of implementation, employee size, and attributes of products that need to be linked. The degree of similarity with the content of input information may be determined based on "similarity judgment information" (information that defines the range of similarity of attributes) included in the reference information. The similarity judgment information may define at least one similar keyword for a keyword that indicates an attribute, or it may define a similarity criterion for features obtained by vectorizing the keyword or text that indicates an attribute. The similarity criterion for features may be a threshold for the difference (vector distance) between the features of two attributes. For example, attributes whose feature difference is less than the threshold (or whose cosine similarity is greater than or equal to the threshold) may be determined to be similar to each other.

[0068] Furthermore, the similarity judgment information may include information that has been pre-grouped with similar attributes. In this case, attributes belonging to the same group will be judged as similar to each other. The control unit 23 may also determine that industries belonging to the same group have a similarity score equal to or greater than a predetermined value.

[0069] The case database may also be a vector search database. The control unit 23 may generate a query for vector search, calculate the similarity between the query and the vector of existing data in the database, and extract similar cases that have attributes whose similarity is greater than or equal to a predetermined value. The control unit 23 may use methods such as cosine similarity, Euclidean distance, or dot product for calculating similarity.

[0070] If activity A105 determines that there are similar cases, the control unit 23 then performs a first extraction step, which is to extract similar cases from the case database using a query (activity A106).

[0071] On the other hand, if it is determined in Activity A105 that no similar cases exist, the control unit 23 then proceeds to Activity A107, and as a query generation step, generates a query with modified search conditions using a large-scale language model (Activity A107). That is, the control unit 23 may use a large-scale language model to generate a query for extracting cases that are considered to have a high degree of similarity to the input information. The control unit 23 may use a large-scale language model to generate a query that expands the search scope by adding synonyms for words in the original query. The control unit 23 may also use a large-scale language model to add semantically related terms to the original query. Furthermore, the control unit 23 may use a large-scale language model to generate a query that adds related terms based on the intent of the original query. In this embodiment, similar cases can be extracted by a query with modified (expanded) search conditions.

[0072] Furthermore, the control unit 23 may generate a query as a query generation step to extract examples of industries similar to the user's company's industry. When no similar examples exist in the same industry, examples in similar industries may be helpful. For example, similar industries may be defined in advance in the consideration items. For example, if the industry of the input information is the service industry, the control unit 23 may identify industries with a high degree of similarity to the service industry based on predetermined consideration items and indicators, and generate a query to search for such similar industries. Predetermined consideration items may include, for example, "Is it labor-intensive?", "Does it require specialized knowledge?", "Does it have contact with many customers?", "Is it a heavily regulated industry?", etc. Predetermined indicators may include, for example, "The proportion of part-time workers or the importance of daily settlements, etc." The control unit 23 may also generate a query to extract similar examples with a high degree of similarity based on the input information and consideration items, etc., using a large-scale language model.

[0073] Furthermore, the control unit 23 may accept additional input information from the user in order to modify the query. Based on the input information, including the added information, the control unit 23 can generate a query.

[0074] Next, the control unit 23 returns to activity A104 and sends the modified query to the case database. In activity A105, the control unit 23 determines whether or not there are similar cases. If there are similar cases, it proceeds to activity A106; otherwise, it proceeds to activity A107, repeating this process until similar cases are found. In this way, the control unit 23 repeatedly generates queries and sends them to the case database by adjusting the selection of consideration items until it can extract similar cases with a high degree of similarity.

[0075] The control unit 23 proceeds to activity A106 to extract similar cases. Subsequently, the control unit 23 extracts relevant knowledge related to the similar cases (activity A108). Here, the relevant knowledge may be stored in the case database or may include information published on a website. Specifically, as a first extraction step, the control unit 23 may extract service-related information from the case database using the input information and a large-scale language model, and as a second acquisition step, it may acquire information published on a website based on the service-related information using the large-scale language model. The control unit 23 may also acquire information published on a website via a search engine. The control unit 23 may generate a search query using the large-scale language model to acquire information from a website using a search engine, based on the input information and similar cases, and acquire information published on a website. In other words, the control unit 23 may acquire knowledge related to the introduction of a service based on the service-related information using the large-scale language model. Note that information published on a website is information provided in a form that is generally accessible through a website on the internet. Information published on a website may be in any format, including text, images, videos, and audio.

[0076] Next, the control unit 23 generates a requirements list using a large-scale language model based on the extracted similar cases, as part of the requirements generation step. The requirements include, for example, the functions, performance, and constraints that the service to be introduced must meet. The requirements may include not only system requirements related to the functions and performance of the system, but also budget, delivery date, support system, usability, etc. The requirements list is a list summarizing the requirements for introducing the service.

[0077] Next, we will explain the information processing flow for the control unit 23 to generate a requirements list according to the input information.

[0078] When the control unit 23 generates a list of requirements based on the input information, it first inputs the extracted similar cases into the large-scale language model (Activity A109). The control unit 23 may also input related knowledge along with the similar cases into the large-scale language model. The large-scale language model can extract candidate requirements that must be met in order to introduce the service from the similar cases and related knowledge. Based on the similar cases and related knowledge, the control unit 23 may generate prompts to generate candidate requirements that match the input information and input them into the large-scale language model.

[0079] If the control unit 23 determines that the information from similar cases and related knowledge contained in the case database is insufficient, it may obtain additional related knowledge by searching for information using search queries on a network search engine or by searching for information using search queries in a commercial database in which information about organizations is registered. For example, the control unit 23 may use a large-scale language model to obtain information published on a website and use that information as related knowledge to generate candidate requirements. The control unit 23 may also input prompts to the large-scale language model for extensive information gathering and inference to generate candidate requirements.

[0080] Next, the control unit 23 generates candidate requirements as a generation step (activity A110).

[0081] Next, the control unit 23 presents the generated candidate requirements to the user and asks for confirmation from the user (Activity A111). The control unit 23 may also present a draft requirement list that lists the candidate requirements, or it may present the generated requirement list as a presentation step.

[0082] The control unit 23 may present requirement candidates in a way that distinguishes between highly reliable and less reliable requirements. For example, the control unit 23 may use information extracted from a case database as highly reliable information. Alternatively, the control unit 23 may generate a prompt instructing the large-scale language model to present the reliability of the requirement candidates generated along with the requirement candidates, input this prompt into the large-scale language model, and then distinguish between highly reliable and less reliable requirement candidates based on the reliability of the requirement candidates obtained from the large-scale language model.

[0083] Next, as the first acquisition step, the control unit 23 presents the user with confirmation items for generating the requirements list, and obtains responses from the user to these confirmation items. This allows the control unit 23 to accept instructions to modify the candidate requirements (Activity A112).

[0084] Here, the control unit 23 may generate confirmation items for the user regarding candidate requirements. When generating confirmation items, the control unit 23 may read a template of confirmation items from reference information and generate confirmation items based on the template. The control unit 23 may also generate confirmation items using a large-scale language model. By presenting confirmation items for candidate requirements with low confidence and receiving responses from the user, the control unit 23 can generate a requirement list that is more tailored to the user.

[0085] The control unit 23 may present confirmation items to the user and accept modification instructions for the candidate requirements in a chat format. In the chat format, the control unit 23 displays questions and confirmation items on the display unit 34, and when it receives a response from the user, the control unit 23 responds in real time by generating questions and confirmation items in response to the received answer. Specifically, the control unit 23 generates confirmation items for the user regarding the generated service-related information and presents them to the user. When the control unit 23 receives a response from the user, it can analyze the intent of the user's response using natural language processing technology and output appropriate questions and answers. The control unit 23 may sequentially display the sending and receiving of messages with the user. In this configuration, a requirement list that is more tailored to the user can be generated.

[0086] When the control unit 23 receives a response from the user, it then modifies the candidate requirement (activity A113). If the control unit 23 modifies the candidate requirement, it can present the modified candidate requirement. The control unit 23 repeats the process of modifying the candidate requirement based on the modification instruction and presenting the modified candidate requirement until it receives a confirmation instruction. As a requirement generation step, the control unit 23 may generate a requirement list based on similar cases and responses using a large-scale language model. By chatting with the user, the requirement list can be modified while seeking confirmation from the user, making it possible to present a requirement list that better reflects the user's intentions.

[0087] Next, when the control unit 23 receives an instruction to confirm the candidate requirements as a reception step, the control unit 23 confirms the requirements list (activity A114). The control unit 23 can then store the confirmed requirements list in the storage unit 22.

[0088] Figure 7 shows confirmation screen 4, an example of a screen showing the exchange of confirmation items and responses regarding candidate requirements. Confirmation screen 4 includes areas 41, 42, 43, and 44. Area 41 is the area that displays confirmation items from information processing system 1. Area 41 displays, "We have created a draft of requirements that a trading company with 1001-5000 employees should consider when introducing an electronic invoicing SaaS for the purpose of improving productivity and speeding up monthly closing. Regarding the RFP, could you please let us know if there are any items that need to be revised before the RFP is sent?" Area 42 is the area that displays responses from the user. Area 42 displays, "Please include AI functionality as a required requirement," "Please include multilingual support as a desired requirement," and "Please make mobile compatibility mandatory as we have many field employees." Area 43 is the area that displays confirmation items from information processing system 1. Area 43 displays the message: "Understood. We have revised the requirements list to match your feedback. Could you please review it again? If there are no problems, we will create an RFP based on this requirements list and propose potential vendors to send it to." Area 44 is an area for receiving additional responses from the user. The control unit 23 can receive input from the user via area 44.

[0089] As shown in confirmation screen 4, the exchange of confirmation items and answers regarding the candidate requirements may be repeated multiple times. The control unit 23 may generate additional confirmation items based on the user's answers. For example, when the control unit 23 receives a response from the user displayed in area 42, it modifies the candidate requirements based on the user's response, generates confirmation items based on the modified candidate requirements, and displays them in area 43. The control unit 23 may ask the user for final confirmation of the modified candidate requirements, or it may display a document explaining the process after final confirmation. The control unit 23 may use a template of confirmation items as reference information and generate confirmation items corresponding to the candidate requirements and the chat exchange using a large-scale language model.

[0090] Figure 8 shows Requirement List 5, an example of a requirements list. Requirement List 5 includes areas 51, 52, and 53. Area 51 is the area that displays the title of the list. Area 51 indicates that it is a requirements list for product selection. Area 52 is the area that displays mandatory requirements. Mandatory requirements are those that are essential for the user to implement the service. Examples of mandatory requirements in Area 52 include: "1. Integration with the implementing company's existing accounting system (XXX), 2. Cost allocation function between multiple locations / businesses, 3. Intuitive and easy-to-use user interface, 4. Secure cloud-based solution, 5. Invoice scanning and OCR function, 6. Approval workflow function." Area 53 is the area that displays desired requirements. Desired requirements are those that are not mandatory but would be desirable to have. Examples of desired requirements in Area 53 include: "1. Support for use on mobile devices, 2. Automatic extraction and classification of invoice data using AI function, 3. Reporting function."

[0091] In requirement list 5 above, "integration with the implementing company's existing accounting system (XXX)" is included as a mandatory requirement. However, the input information may include information from other services that the user is already using. The requirement list may also include the requirement that the system be able to integrate with other services. In this manner, it is possible to provide an information processing system, etc., that proposes products of services that can integrate with services that the user is already using.

[0092] Next, the control unit 23 presents the extracted service-related information as a presentation step (Activity A115). Service-related information is information related to the service. This service-related information includes requirements lists, similar cases, relevant knowledge, requests for proposals, product information, product lists, vendor lists, etc. The control unit 23 may also present service-related information about similar cases as a presentation step. In this configuration, an information processing system can be provided that proposes services tailored to the user based on similar cases. The control unit 23 may also present information including knowledge as service-related information as a presentation step. In this configuration, the user can grasp knowledge related to the introduction of the service. The control unit 23 may also present the service price and support system of the extracted product as information including knowledge.

[0093] Furthermore, if the requirements list includes a requirement that the system be able to cooperate with other information processing-related services, the control unit 23 may, as a presentation step, present service-related information regarding services that can cooperate with other information processing-related services.

[0094] Furthermore, the control unit 23 may, as a presentation step, present the source of the service-related information along with the service-related information. In this manner, the user can confirm the source of the presented service-related information.

[0095] In the above embodiment, after extracting similar cases and related knowledge from the case database, a requirements list was generated using the similar cases and related knowledge. However, some steps may be omitted. That is, as a requirements generation step, the control unit 23 may generate requirements for introducing a service using a large-scale language model based on the input information and the case database in which service introduction cases are accumulated. Alternatively, as a requirements generation step, the control unit 23 may generate a requirements list summarizing the requirements based on the requirements.

[0096] <Processing using a requirements list> Next, we will explain an example of a process that utilizes the finalized requirements list.

[0097] As shown in Figure 6, first, the control unit 23 receives a generation instruction via the user terminal 3 to generate a Request for Proposal (RFP) or the like as a request for proposal (Activity A201).

[0098] The control unit 23 may receive instructions to generate a Request for Proposal (RFP) or similar document along with an instruction to finalize the requirements list. Based on the requirements list, the control unit 23 can generate an RFP or similar document, extract product candidates, and extract vendor candidates. An RFP is a document used by a user to request specific proposals from vendors. For example, an RFP is a document that requests vendors to submit proposals that include the purpose of implementation, requirements, budget, schedule, etc.

[0099] A vendor refers to a company or business that provides specific products or services. The control unit 23 can extract potential vendors by extracting products that match the requirements list. One vendor may be associated with one product, or multiple vendors may be associated with one product. For example, if a product is supplied by multiple sales agents, or if a product from a foreign company is supplied by multiple Japanese agents, multiple vendors may be associated with one product.

[0100] When the control unit 23 receives an instruction to generate a Request for Proposal (CPO), it reads a CPO template stored in the memory unit 22 (Activity A202). The template may define the basic structure and format of the CPO. The template may have fixed and variable parts, with information dynamically embedded in the variable parts.

[0101] Next, the control unit 23, as a Request for Proposal generation step, generates a Request for Proposal, which is an example of a request for proposal to be provided to a service vendor, based on the requirements list and using a large-scale language model. In this configuration, it is possible to provide an information processing system, etc., that generates a Request for Proposal based on a requirements list.

[0102] As a generation step, the control unit 23 generates a draft Request for Proposal (CPO) based on the finalized requirements list and template (Activity A203). For example, the control unit 23 may embed the information from the finalized requirements list into the variable parts of the template and generate the CPO. Alternatively, the control unit 23 may obtain information to be embedded in the variable parts of the template from another information processing system (not shown) and generate the CPO.

[0103] As a step in generating a Request for Proposal (RFP), the control unit 23 generates an RFP, which is an example of a request for proposal, using a large-scale language model based on the requirements list. For example, the control unit 23 may take the requirements list as input and input prompts to the large-scale language model that include instructions to output an RFP for proposal corresponding to the requirements list, causing the large-scale language model to generate an RFP for proposal.

[0104] Here, a Request for Proposal can be any document that requests information about a proposal from a vendor. A Request for Proposal may also be called an Information Request, which requests information from the vendor as a preliminary step before asking for a specific proposal or detailed estimate, or conversely, it may be called a Quotation Request, which requests a detailed estimate from the vendor.

[0105] Specifically, as a Request for Proposal (RPO) generation step, the control unit 23 may generate a RPO, which is an example of a request for proposal, using a large-scale language model based on the generated requirements list and a pre-created template. The control unit 23 may input the template as reference information into the large-scale language model. The control unit 23 may input a prompt into the large-scale language model that includes an instruction to output a RPO according to the requirements list using the template as reference information, causing the large-scale language model to generate a RPO. Alternatively, the control unit 23 may input a prompt into the large-scale language model that includes an instruction to generate information to be embedded in the variable parts of the template based on the requirements list, causing the large-scale language model to generate a RPO. In addition to inserting information into the template, the control unit 23 may, if necessary, generate a RPO that includes additional information outside the template.

[0106] Figure 9 shows an example of a Request for Proposal 6, which is a Request for Proposal for the Introduction of an Electronic Invoicing System. The Request for Proposal 6 is a "Request for Proposal for the Introduction of an Electronic Invoicing System," and its items include, for example, "Overview," "Profile of the Implementing Company," "Current Situation and Challenges," "Project Objectives," "Requirements," "Current System Configuration," "Content to be Included in the Proposal," "Selection Criteria," "Schedule," and "Information Disclosure and Inquiries." The "Requirements" include "Mandatory Requirements" and "Desired Requirements."

[0107] Next, as a presentation step, the control unit 23 presents the generated Request for Proposal (CPR) as a draft CPR, along with the items to be confirmed regarding the generated draft CPR, to the user (Activity A204). The items to be confirmed may be information that is missing from the generated draft CPR, or information that is presented to the user along with the draft CPR. The control unit 23 may generate the items to be confirmed based on reference information. For example, the control unit 23 may read a template for the items to be confirmed from the reference information and generate the items to be confirmed based on that template. By presenting the items to be confirmed regarding the generated draft CPR and receiving the user's responses to the items to be confirmed, the control unit 23 can generate a CPR that is more tailored to the user.

[0108] Next, as a reception step, the control unit 23 receives responses from the user via the network from the user terminal 3 to the items to be confirmed (Activity A205).

[0109] Figure 10 shows confirmation screen 7, an example of a screen showing the exchange of confirmation items and responses regarding the draft Request for Proposal. Confirmation screen 7 is a screen that presents confirmation items regarding the draft Request for Proposal and accepts responses from the user to those confirmation items. Confirmation screen 7 includes areas 71 and 72. Area 71 is an example of an area that displays confirmation items from information processing system 1. Area 71 displays confirmation items from information processing system 1, such as "Please let us know if there are any points you would like to revise regarding the RFP," "When is the deadline for vendor proposals?", "When would you like the vendor presentations to take place?", and "If there are no problems with this content, we will select candidate vendors based on the requirements list and send the RFP. Please be assured that your company's contact information will not be disclosed until we have reviewed the proposals from the vendors."

[0110] Area 72 is an area for receiving responses from the user. When the user enters a response into area 72, the control unit 33 accepts the input response and transmits the user's response to the control unit 23.

[0111] If the control unit 23 receives the user's response, it then modifies the draft request for proposal based on the user's response (Activity A206).

[0112] After revising the draft Request for Proposal (CPO), the control unit 23 returns to activity A204 and presents the revised CPO again. If there are any additional questions regarding the CPO, the control unit 23 presents those questions. In this way, the process of revising the CPO based on user responses and presenting the revised CPO is repeated.

[0113] Next, when the user gives a confirmation instruction regarding the draft request for proposal via the user terminal 3, the control unit 33 transmits the confirmation instruction to the control unit 23, and the control unit 23 accepts the confirmation instruction (Activity A207).

[0114] Next, the control unit 23 finalizes the contents of the draft Request for Proposal and, based on the finalized Request for Proposal, generates a query to search the product information database as a generation step (Activity A208). As a query generation step, the control unit 23 can generate a query that can search the product information database based on the Request for Proposal. The control unit 23 can generate a query based on the Request for Proposal and reference information. The reference information may be a predetermined rule, a trained model, or a large-scale language model.

[0115] Next, the control unit 23 searches the product information database based on the generated query (Activity A209).

[0116] Next, the control unit 23 extracts one or more product candidates from the product information database (Activity A210). The control unit 23 may also extract product information with a high degree of relevance to the query from the product information stored in the product information database as product candidates.

[0117] In the above embodiment, a request for proposal (RFP) was created after the requirements list was finalized, and products and vendors were extracted based on the RFP. However, some steps may be omitted. Specifically, the control unit 23 may, as a second extraction step, extract one or more product information from a product information database where product information for services is stored, based on the requirements list. More precisely, the control unit 23 may, as a second extraction step, extract one or more product information based on the degree of compatibility between the requirements list and the product information for services.

[0118] Next, the control unit 23 presents one or more product information items as a presentation step (Activity A211). The product information may include service details, service features, software functions, specifications required to use the service (hardware, software, internet connection specifications, etc.), information on the vendor providing the product, pricing plans, security, support system, customer reviews, etc. In this manner, the user can review product information for product candidates that meet their requirements. This allows the user to review the presented product information and select product candidates for which they wish to receive specific proposals.

[0119] Next, the control unit 23 accepts instructions to modify the product candidates (activity A212). That is, the control unit 23 can accept instructions to delete or add product candidates. The control unit 23 may also accept manual input instructions for adding product candidates.

[0120] If the control unit 23 receives a modification instruction, the control unit 23 then modifies the product candidate based on the modification instruction (Activity A213).

[0121] After executing the correction process, the control unit 23 returns to activity A211 and presents the corrected product candidate again. The control unit 23 repeats the process of correcting the product candidate based on the correction instruction and presenting the corrected product candidate until it receives a confirmation instruction.

[0122] On the other hand, if the control unit 23 receives a confirmation instruction, the control unit 23 confirms the product candidates. If there is a one-to-one correspondence between product candidates and vendors, once the product candidate for which a specific proposal is desired is confirmed, the vendor to whom the Request for Proposal will be sent is confirmed (Activity A214). If multiple vendors are associated with a product candidate, the control unit 23 may further accept the selection of the vendor to which the proposal will be sent.

[0123] Figure 11 shows an example of confirmation screen 8 for confirming the recipients of the Request for Proposal (RFP). Confirmation screen 8 includes areas 81 and 82. Area 81 is the area that displays questions from Information Processing System 1. Area 81 displays the following: "Based on the list of requirements you have confirmed, we have created a list of vendors to whom the RFP will be sent. Please review it and let us know if there are any vendors you would like to remove from the list or add. Your company's contact information will not be disclosed until we have reviewed the proposals from the vendors." Area 82 is the area that accepts user input for responses.

[0124] Next, the control unit 23, as a presentation step, presents a selection of vendors corresponding to the product information. Here, the control unit 23 may also present a selection of vendors corresponding to the product information in a way that allows for addition or modification. The control unit 23 may, as a second acquisition step, accept the addition or modification of vendors corresponding to the product information. Note that modification includes deleting any of the multiple vendors. In this configuration, the user can manually add or modify vendors not included in the vendor list. The control unit 23 may also send the user a copy of the Request for Proposal to be sent. In this configuration, the user can understand the contents of the transmission.

[0125] Next, as a first transmission step, the control unit 23 sends a Request for Proposal (RFP), which is an example of a request for proposal, to the selected vendor (Activity A215). In this case, as a first transmission step, the control unit 23 may send a Request for Proposal, which is an example of a request for proposal, to the vendor that does not contain any information that identifies the user's name. With this configuration, the user can anonymously send the Request for Proposal to the vendor selected by the user. The control unit 23 may also send a copy of the Request for Proposal to the user. With this configuration, the user can understand the contents of the transmission.

[0126] In Activity A215, when sending a Request for Proposal to a vendor, the Request for Proposal may include advice for the vendor. The advice may be generated based on a case database. Specifically, the control unit 23 may extract information regarding advice for the vendor from the case database based on the Request for Proposal, and generate advice for the vendor using a large-scale language model based on the information regarding advice for the vendor. The control unit 23 may send the advice to the vendor only. That is, the control unit 23 may send a Request for Proposal including advice to the vendor, and send a Request for Proposal without advice to the user.

[0127] Upon receiving a Request for Proposal (RFP), the vendor can create a proposal in response to the RFP and send the created proposal to the control unit 23.

[0128] Next, as a third acquisition step, the control unit 23 acquires proposals from vendors based on a Request for Proposal (RFP), which is an example of a request for proposals (Activity A216).

[0129] Next, the control unit 23 performs a determination step in which it determines the degree of compatibility between the input information received from the user and the proposal (Activity A217). The control unit 23 may also determine the degree of compatibility between the Request for Proposal (RFP) generated based on the input information and the acquired proposal. Alternatively, the control unit 23 may calculate and determine the degree of compatibility with each item of the RFP for each proposal. If there are multiple proposals, the control unit 23 may compare the degree of compatibility for each item in each proposal.

[0130] Next, the control unit 23 presents the proposal obtained from the vendor to the user as a presentation step (Activity A218).

[0131] Here, the control unit 23 may present the proposals in a selectable manner as a presentation step. The control unit 23 can accept a selection of proposals from the user (activity A219). In this manner, the user can select a proposal.

[0132] Here, the control unit 23 may present information regarding the proposal and its suitability as a presentation step. Furthermore, if the control unit 23 receives multiple proposals from multiple vendors, it may present the proposals received from each vendor to the user in a comparable manner. The user can then compare and consider the presented proposals and select the one that best suits their needs.

[0133] Next, as a second transmission step, the control unit 23 transmits information to the vendor corresponding to the selected proposal for setting up a meeting with the user (Activity A220). If the control unit 23 has not provided the vendor with information that identifies the user, the control unit 23 may transmit information that identifies the user as the information for setting up the meeting. In this manner, detailed requirements and needs are shared in advance between the selected vendor and the user, enabling efficient and productive business negotiations toward concrete implementation.

[0134] This approach significantly improves the transparency and efficiency of the selection process for information processing-related services. Furthermore, it enables decision-making based on reliable information, which is expected to yield valuable results for both users and vendors. This process reduces uncertainty in service implementation and increases the likelihood of more appropriate product selection and smoother deployment.

[0135] Furthermore, the control unit 23 may update the case database based on the information collected during this process. That is, as a first update step, the control unit 23 updates the case database based on the input information and the information presented to the user. This configuration allows for the enrichment of the case database.

[0136] Furthermore, as a second update step, the control unit 23 may collect information published on the website and update the case database or the product information database where product information for services is stored. This configuration allows for the enrichment of both the case database and the product information database.

[0137] Furthermore, the control unit 23 may store various information presented to the user, as well as responses and instructions obtained from the user, in the storage unit 22. The control unit 23 may also store a series of interactions with the user in the storage unit 22. In this configuration, the selection process for information processing-related services can be recorded. In addition, the control unit 23 may present this stored information to the user in response to instructions from the user. In this configuration, the user can review the selection process.

[0138] 5. Variations Furthermore, the following embodiments may be adopted.

[0139] When the control unit 23 receives business challenges or concerns as a reception step in activity A102, it may identify a service category based on the received challenges or concerns and reference information, and use the identified service category as input information. The control unit 23 may also identify a service category based on "category similarity judgment information (information defining the range of similarity of categories)" included in the reference information. The category similarity judgment information may define at least one similar keyword for a keyword indicating a category, or it may define a similarity criterion for features obtained by vectorizing keywords or sentences indicating a category. The similarity criterion for features may be a threshold for the difference (vector distance) between the features of two categories. For example, attributes where the difference in features is less than the threshold (or the cosine similarity is greater than or equal to the threshold) may be judged as similar to each other. The category similarity judgment information may also include information that has been pre-grouped similar categories. In this manner, the control unit 23 can identify the service category that the user is considering based on the user's business challenges or concerns. The control unit 23 may identify the category of service the user is considering by interacting with the user via chat, based on the user's challenges and concerns.

[0140] In activity A105 of the above embodiment, if it is determined that there are no similar cases, the control unit 23 may inform the user that no extractable similar cases were found. This is because the information that no similar cases were found may also be valuable to the user.

[0141] In Activity A115, the control unit 23 may, after presenting the extracted service-related information, accept a request for information from the user. Based on the received request for information, the control unit 23 may request information from the vendor, and may also send the information to the user. In this case, the control unit 23 may send the request for information to the vendor without including any information that identifies the user's name. In this configuration, the user can request information from the vendor anonymously.

[0142] The above-described information processing configuration is merely an example. The present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention. The information processing in the above embodiment may include any exception processing not shown. Exception processing includes interrupting the information processing or omitting each process. The selection or input performed in the information processing may be based on user operation or may be performed automatically without user operation.

[0143] <Other variations> The output destination for information or data (hereinafter referred to as "information, etc.") may be other devices, displays, storage units (including built-in and external storage units), etc. Acquisition of information, etc. includes not only acquiring information, etc. transmitted from other devices, but also acquiring information, etc. generated by the device itself. The table associating parameters is not limited to the illustrated table; the number of parameters may be reduced or increased. Furthermore, information, etc. corresponding to parameters may be obtained using mathematical formulas or conditional expressions, etc., without using a table.

[0144] <Note> Furthermore, they may be provided in the following embodiments.

[0145] (1) An information processing system comprising at least one processor, wherein the processor is configured to perform the following steps by reading a program, wherein in the reception step, input information of a user considering the introduction of a service is received, where the input information includes at least one of user information, the category of the service the user is considering, and the user's purpose for introduction; in the requirements generation step, based on the input information, requirements for introducing the service are generated by a large-scale language model using a case database in which examples of service introductions have been accumulated; and in the request for proposal generation step, a request for proposal is generated by the large-scale language model based on the requirements.

[0146] In this configuration, it is possible to provide an information processing system that receives information from users, such as the purpose of implementation, and creates a request form for a proposal tailored to the user company.

[0147] (2) An information processing system as described in (1) above, wherein in the requirements generation step, a requirements list is generated based on the requirements, and in the request for proposal generation step, a request for proposal is generated by the large-scale language model based on the generated requirements list and a pre-created template.

[0148] In this configuration, it is possible to provide an information processing system, etc., that creates requests for proposals tailored to user companies.

[0149] (3) An information processing system as described in (2) above, wherein in the first extraction step, similar cases are extracted from the case database based on the received input information, where the similar cases are cases that have attributes whose similarity to the content of the input information is equal to or greater than a predetermined value, and in the requirements generation step, the requirements list is generated by the large-scale language model based on the extracted similar cases.

[0150] In this manner, a list of requirements can be generated based on similar cases.

[0151] (4) An information processing system as described in (3) above, wherein in the first acquisition step, the system obtains answers from the user to the confirmation items by presenting the confirmation items to the user for generating the requirements list, and in the requirements generation step, the system generates the requirements list based on the similar cases and the answers using the large-scale language model.

[0152] In this configuration, a list of requirements that is more tailored to the user can be generated through chat with the user.

[0153] (5) An information processing system according to any one of (2) to (4) above, wherein in a second extraction step, one or more product information is extracted from a product information database where product information for the service is stored, based on the requirements list, and in a presentation step, the one or more product information is presented.

[0154] In this manner, product information can be presented to the user.

[0155] (6) An information processing system as described in (5) above, wherein in the presentation step, a plurality of vendors corresponding to the product information are presented for selection, and in the first transmission step, a request for the proposal is sent to the selected vendor.

[0156] In this configuration, the user can send a request for proposals, etc., to the vendor of their choice.

[0157] (7) An information processing system as described in (6) above, wherein in the presentation step, a plurality of vendors corresponding to the product information are presented in an additional or changeable manner, and in the second acquisition step, the addition or change of vendors corresponding to the product information is acquired.

[0158] In this configuration, vendors not included in the vendor list can be manually added or modified.

[0159] (8) An information processing system as described in (7) above, wherein in the first transmission step, a request for the proposal that does not contain information identifying the name of the user is transmitted.

[0160] In this configuration, users can anonymously send requests for proposals and other documents to vendors of their choice.

[0161] (9) An information processing system described in any one of (6) to (8) above, wherein in the third acquisition step, a proposal prepared based on the request for the proposal is acquired from the vendor, and in the presentation step, the acquired proposal is presented to the user.

[0162] In this manner, the vendor can present the proposal they have created to the user.

[0163] (10) An information processing system as described in (9) above, wherein in the determination step, the degree of conformity between the input information and the proposal is determined, and in the presentation step, information relating to the proposal and the degree of conformity is presented.

[0164] In this configuration, the degree of compatibility between the proposal created by the vendor and the input information can be determined, and the determined information can be presented to the user.

[0165] (11) An information processing system as described in (9) or (10) above, wherein in the presentation step, the proposal is presented in a selectable manner, and in the second transmission step, information for setting up a meeting with the user is transmitted to the vendor corresponding to the selected proposal.

[0166] This configuration allows for mediating meetings between users and vendors.

[0167] (12) An information processing system described in any one of (1) to (11) above, wherein in the first update step, the case database is updated based on the input information and the information presented to the user.

[0168] This approach allows for the enrichment of the case database.

[0169] (13) An information processing system described in any one of (1) to (12) above, wherein in the second update step, information published on a website is collected and the case database or the product information database in which product information of the service is stored is updated.

[0170] This approach allows for the enrichment of the case database.

[0171] (14) An information processing method comprising each step performed by the information processing system described in any one of (1) to (13) above.

[0172] (15) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (13) above. Of course, this is not always the case. Furthermore, the embodiments and modifications described above may be implemented in any combination.

[0173] Finally, various embodiments of the present invention have been described, but these are presented as examples only and are not intended to limit the scope of the invention. Novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. Embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0174] 1: Information Processing System 2: Server 20: Communications bus 21: Communications Department 22: Storage section 23: Control Unit 3: User terminal 30: Communications bus 31: Communications Department 32: Storage section 33: Control Unit 34:Display section 35: Input section 4: Confirmation screen 41 :Area 42 :Area 43 :Area 44 :Area 5: Requirements List 51 :Area 52 :Area 53: area 6: Request for Proposal 7: Confirmation screen 71 :Area 72 :Area 8: Confirmation screen 81 :Area 82 :Area DB: Database

Claims

1. An information processing system, Equipped with at least one processor, The aforementioned processor is configured to perform the following steps by reading a program: In the registration step, input information from a user considering introducing the service is received, and said input information includes at least one of the following: user information, the category of the service the user is considering, and the user's purpose for introducing the service. In the requirements generation step, based on the input information, a large-scale language model is used to generate requirements for introducing the service, using a case database containing examples of service implementations. In the proposal request generation step, an information processing system generates a request for proposals using the large-scale language model based on the aforementioned requirements.

2. In the information processing system described in claim 1, In the requirements generation step, a requirements list is generated based on the requirements, In the aforementioned proposal request generation step, an information processing system generates a request for proposal using the large-scale language model based on the generated requirements list and a pre-created template.

3. In the information processing system described in claim 2, Furthermore, in the first extraction step, similar cases are extracted from the case database based on the received input information, where the similar cases are cases that have attributes whose similarity to the content of the input information is equal to or greater than a predetermined value. In the requirements generation step, an information processing system generates the requirements list using the large-scale language model based on the extracted similar cases.

4. In the information processing system described in claim 3, Furthermore, in the first acquisition step, the user is presented with confirmation items for generating the requirements list, and the user's responses to the confirmation items are obtained. An information processing system that, in the requirements generation step, generates the requirements list based on the similar cases and the answers using the large-scale language model.

5. In the information processing system described in claim 2, Furthermore, in the second extraction step, based on the requirements list, one or more product information entries are extracted from the product information database where the product information for the service is stored. Furthermore, the information processing system presents one or more of the aforementioned product information in the presentation step.

6. In the information processing system described in claim 5, In the aforementioned presentation step, multiple vendors corresponding to the product information are presented for selection, Furthermore, in the first transmission step, the information processing system transmits a request for the proposal to the selected vendor.

7. In the information processing system described in claim 6, In the presentation step, multiple vendors corresponding to the product information are presented in a way that allows for addition or modification. Furthermore, in the second acquisition step, the information processing system acquires additions or changes to the vendor corresponding to the product information.

8. In the information processing system described in claim 7, An information processing system that, in the first transmission step, transmits a request for the proposal that does not contain information identifying the user's name.

9. In the information processing system described in claim 6, Furthermore, in the third acquisition step, the proposal prepared based on the request for the aforementioned proposal is obtained from the vendor. The information processing system, in the presentation step, presents the acquired proposal to the user.

10. In the information processing system described in claim 9, Furthermore, in the determination step, the degree of compatibility between the input information and the proposal is determined. An information processing system that, in the presentation step, presents the proposal and information regarding the degree of suitability.

11. In the information processing system described in claim 9, In the presentation step, the proposals are presented in an selectable manner, Furthermore, in the second transmission step, the information processing system transmits information to the vendor corresponding to the selected proposal for setting up a meeting with the user.

12. In the information processing system described in claim 1, Furthermore, in the first update step, the information processing system updates the case database based on the input information and the information presented to the user.

13. In the information processing system described in claim 1, Furthermore, in the second update step, an information processing system collects information published on the website and updates the case database or the product information database in which product information of the service is stored.

14. Information processing method, An information processing method comprising each step performed by the information processing system according to any one of claims 1 to 13.

15. It is a program, A program that causes a computer to perform each step of the information processing system described in any one of claims 1 to 13.

Images