Information processing system, information processing method, and program

Abstract

This system provides an information processing system, information processing method, and program that assist in setting request information necessary for generating workflows that link services used by users in their work. [Solution] In an information processing system comprising a storage unit 110 and a UI unit 140, the UI unit comprises: an input acquisition unit 144 that acquires user input including instructions from the user to a service; a query generation unit 148 that generates a query to cause a generating AI to generate request information to set the instructions to the service in a manner that the service can accept, based on the user input, service identification information that can identify the service, and service design information of the service; and a request information acquisition unit 154 that inputs the query to the generating AI and acquires the request information output from the generating AI.

Description

Technical Field

[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 storage device that holds an interface DB storing information related to data input / output interfaces in each SaaS (Software as a Service), and a set of SaaSs whose data formats in the interface are common to each other is specified based on the interface DB (DataBase), and information related to the set is output to a predetermined device. When a request for cooperation setting from a user for the set is received from the predetermined device, a predetermined algorithm corresponding to data cooperation processing between SaaSs is obtained. An arithmetic device that executes a process of storing, as a cooperation API, in a storage device by attaching predetermined information defining the set as a group of SaaSs to be cooperated with to an API (Application Programming Interface) for obtaining the execution result. [Prior Art Document] [Patent Document] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2016-224578

Summary of the Invention

Means for Solving the Problems

[0003] According to one embodiment of the present invention, an information processing system is provided. The information processing system may include an input acquisition unit that acquires user input, including instructions from a user for a service. The information processing system may include a query generation unit that generates a query to cause a generating AI to generate request information to set the instructions for the service in a manner that the service can accept, based on the user input, service identification information that can identify the service, and service design information for the service. The information processing system may include a request information acquisition unit that inputs the query to the generating AI and acquires the request information output from the generating AI.

[0004] In the aforementioned information processing system, the service design information may include a plurality of setting items for the service and a description of the plurality of setting items.

[0005] In the aforementioned information processing system, the service identification information may include at least one of the following: service identification information capable of identifying the service, the URL of the service, and service description information describing the service.

[0006] In the aforementioned information processing system, if request information is set for the service, the query generation unit may generate the query based on the set request information.

[0007] In the aforementioned information processing system, the service may be SaaS, and the request information may include at least one of the method information, header information, body information, and request URL for making an HTTP request to the service.

[0008] In the aforementioned information processing system, the service may be a SaaS, and the service design information may be the API documentation for the SaaS.

[0009] In the information processing system, the service design information may include a plurality of setting items in the service, the information processing system may include a storage unit that stores the plurality of setting items in a vector database, and the query generation unit may generate the query based on the service design information including the plurality of setting items stored in the storage unit in a vector database, the user input and the service identification information.

[0010] In the information processing system, the input acquisition unit may acquire user input for a service included in a workflow configured by arranging multiple services in sequence, and the query generation unit may, when generating a query for one of the multiple services included in the workflow, generate the query based on response information from a service that is earlier in the sequence than the one service, the response information acquisition unit has acquired the response information, the user input for the one service, the service identification information for the one service, and the service design information for the one service, if such response information has been acquired by the response information acquisition unit.

[0011] In the information processing system, the input acquisition unit may acquire WF user input including a description of the workflow desired by the user, the query generation unit may generate a WF query based on the WF user input to generate the workflow desired by the user, and the information processing system may include a WF generation unit that generates the workflow using the generation AI based on the WF query. The query generation unit may generate a WF query to cause the generation AI to generate a workflow in which multiple services are arranged in order to realize the workflow desired by the user, and the WF generation unit may input the WF query to the generation AI and acquire the workflow output from the generation AI.

[0012] According to one embodiment of the present invention, a program is provided for causing a computer to function as the information processing system.

[0013] According to one embodiment of the present invention, an information processing method performed by a computer is provided. The information processing method may include a user input acquisition step of acquiring user input including instructions from a user to a service. The information processing method may include a query generation step of generating a query to cause a generating AI to generate request information that sets the instructions to the service in a manner that the service can accept, based on the user input, service identification information that can identify the service, and service design information of the service. The information processing method may include a request information acquisition step of inputting the query to the generating AI and acquiring the request information output from the generating AI.

[0014] It should be noted that the above summary of the invention does not list all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0015] [Figure 1] An example of information processing system 100 is shown in outline. [Figure 2] This is an explanatory diagram illustrating an example of input and output to the generated AI 400 by the information processing system 100. [Figure 3] An example of the processing flow of the information processing system 100 is shown in outline. [Figure 4] An example of the processing flow of the information processing system 100 is shown in outline. [Figure 5] An example of the processing flow of the information processing system 100 is shown in outline. [Figure 6] This is an explanatory diagram illustrating an example of input and output to the generated AI 400 by the information processing system 100. [Figure 7] An example of the processing flow of the information processing system 100 is shown in outline. [Figure 8] An example of the functional configuration of the information processing system 100 is shown in general terms. [Figure 9]A schematic example of the hardware configuration of a computer 1200 that functions as an information processing system 100 is shown. [Modes for carrying out the invention]

[0016] The present invention will be described below through embodiments of the invention, but these embodiments are not intended to limit the invention as defined in the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] Traditionally, in order to link multiple types of services such as SaaS to complete a single process, it was necessary to programmatically format request information such as HTTP requests based on knowledge of the design information defined for each service. However, this required advanced knowledge, making it difficult to ask end users to do so. The information processing system 100 according to this embodiment functions as a business support platform that assists in setting the request information necessary to generate a workflow that links services used by a user in their work.

[0018] Figure 1 schematically shows an example of an information processing system 100. The information processing system 100 may be implemented by a computer 200 operated by a user 202. The information processing system 100 implemented by the computer 200 supports the user 202's operation of the computer 200.

[0019] In the form where the computer 200 accesses the server 300 to execute various processes, the information processing system 100 may be realized by the server 300. For example, in the case of a thin client environment, most functions are arranged in the server 300, and the computer 200 executes limited functions such as input and display. However, the information processing system 100 realized by the server 300 supports the operation of the computer 200 by the user 202 for performing the processes in the server 300. The computer 200 and the server 300 may communicate via the network 20. The network 20 may include a cloud. The network 20 may include the Internet. The network 20 may include a mobile communication network. The network 20 may include a LAN (Local Area Network).

[0020] The information processing system 100 may have a plurality of skills available to the user 202. The skills may constitute a workflow that coordinates multiple types of services. The services may be so-called SaaS. The services may be services provided by applications. Different workflows are configured for each skill. For example, a certain skill constitutes a workflow that coordinates a calendar application that provides a calendar service and a messaging application that provides a messaging service. For example, a certain skill constitutes a workflow that coordinates a web conferencing application that provides a web conferencing service, an AI application that provides a service for transcribing the voice of a web conference to create minutes, an AI application that provides a summarization service for summarizing the minutes, and a CRM (Customer Relationship Management) application that provides a CRM service for storing and managing the conference and summarized minutes. The workflow may coordinate any number of services. The workflow may coordinate any type of services. The information processing system 100 may generate and manage a plurality of skills using so-called iPaaS (Integration Platform as a Service).

[0021] As described above, in order to generate such skills, advanced knowledge is required, and it may be difficult to require the user 202 to have it. The information processing system 100 according to the present embodiment supports the generation of skills by the user 202. For example, the information processing system 100 aims to provide the user 202 with an environment in which skills can be generated only by inputting natural language. As a specific example, the information processing system 100 supports the generation of HTTP requests necessary for linking SaaS applications with each other.

[0022] For example, with respect to a workflow generated by the user 202 arranging a plurality of services in order, the information processing system 100 supports the generation of HTTP requests for linking the plurality of services included in the workflow with each other. The information processing system 100 may support the user 202 including the arrangement of a plurality of services. For example, the information processing system 100 receives an explanation of a workflow desired by the user 202, arranges a plurality of services in order to realize the workflow, and generates an HTTP request for linking the plurality of services with each other.

[0023] The information processing system 100 may support the user 202 by using the generation AI 400. The generation AI 400 may be an LLM (Large Language Model). The generation AI 400 may be a so-called dialogue-type generation AI. The generation AI 400 may be a generation AI that combines a dialogue-type UI with an LLM. Examples of the generation AI 400 include ChatGPT, Gemini, and Claude (registered trademark), etc., but are not limited thereto, and any existing generation AI may be used. Further, the generation AI 400 may be a generation AI generated for the information processing system 100. The information processing system 100 may communicate with the generation AI 400 via the network 20. Note that the information processing system 100 may include the generation AI 400.

[0024] By appropriately inputting the necessary information to the generating AI 400, highly accurate output can be obtained. For example, the information processing system 100 may acquire user input including instructions from user 202 to a service, and based on the user input, service identification information that can identify the service, and service design information of the service, generate a query to cause the generating AI 400 to generate request information that sets the service in a manner that the service can accept the instructions from user 202, and input this query to the generating AI 400. As a specific example, when the information processing system 100 acquires user input including instructions for a calendar application to output user 202's schedule for a specific period, it generates a query based on the user input, the name and URL (Uniform Resource Locator) of the calendar application, and the API documentation of the calendar application. For example, the information processing system 100 generates a query including instructions to generate request information including method information, request URL, header information, and body information for the calendar application identified by the name and URL to output in response to user 202's instructions, according to the contents of the API documentation.

[0025] It is possible to have an existing generation AI generate an HTTP request by instructing it to generate an HTTP request that outputs specified information to an application. However, it is difficult to generate a normal HTTP request, and even if the application is configured to receive the HTTP request, it may not function correctly, result in an error, or output information different from what was expected. This is particularly likely to occur if the target application is a minor application or, even if it is a major application, does not publicly disclose much information. In contrast, the information processing system 100 according to this embodiment, upon acquiring user input including user instructions for a certain application, can generate a query using the user input, along with accurate identification information of the application and design information such as the application's API documentation, thereby generating an HTTP request that conforms to the application's request requirements and can accurately receive the user's instructions.

[0026] Figure 2 is an explanatory diagram illustrating an example of input and output to the generation AI 400 by the information processing system 100. Here, we first explain the input and output when the generation AI 400 is made to generate request information 120 for a single application to produce the output desired by user 202. Next, we explain the input and output when the generation AI 400 is made to generate request information to link multiple applications in a workflow where multiple applications are arranged sequentially but the request information has not yet been set.

[0027] When the information processing system 100 obtains user input 111, which includes instructions from user 202 to an application, it generates a query to cause the generation AI 400 to generate request information 120 to set the application in a manner that the application can accept the instructions from user 202, based on the user input 111, the application identification information 112 of the application, and the application design information 114 of the application. The information processing system 100 inputs the generated query to the generation AI 400 and obtains the request information 120 from the generation AI 400. For example, for an application identified by the application identification information 112, the information processing system 100 generates a query that includes instructions to generate request information 120 to set the instructions included in user input 111, according to the contents described in the application design information 114.

[0028] User input 111 may be text. For example, user input 111 may be text entered via an input device such as a keyboard or touch panel on the computer 200. User input 111 may also be text selected by range text selection. User input 111 may also be an image. For example, user input 111 may be an image generated by taking a screenshot of part or all of the computer 200 screen. User input 111 may be an image of a region of the computer 200 screen specified by user 202. User input 111 may be a strip-selected image. User input 111 may be an image selected by range screenshot format selection. User input 111 may also be audio. User input 111 may also include other types of input from user 202.

[0029] The application identification information 112 may be any information that can identify the application. The application identification information 112 may include application identification information that can identify the application. The application identification information may be the name of the application or an ID assigned to the application. The application identification information 112 may include the URL of the application. The application identification information 112 may be included in application description information that describes the application. The application description information may include at least one of the purpose, type, and function of the application. If the target application is well-known, there is a large amount of information about the application on the network, so it is highly likely that the generating AI 400 has learned what kind of application it is. However, if the target application is a minor application, the generating AI 400 may not have learned what kind of application it is. In such cases, by including application description information in the application identification information 112, the generating AI 400 can be given knowledge of the purpose, type, and function of the application.

[0030] The application identification information 112 may be input by the user 202 along with the user input 111. The information processing system 100 may store the application identification information 112 of multiple applications in a storage unit in advance, and may determine the target application from the user input 111 and read the application identification information 112 of the target application from the storage unit.

[0031] The application design information 114 is the design information of the application and may include multiple configuration items of the application. The application design information 114 may include descriptions of multiple configuration items. The application design information 114 may include description rules for multiple configuration items. The application design information 114 may be, for example, the API documentation of the application. The information processing system 100 may store the application design information 114 of multiple applications in a storage unit in advance. The information processing system 100 may read the application design information 114 of the target application from the storage unit. The application design information 114 may also be input by the user 202 along with the user input 111.

[0032] Request information 120 may be information that sets the user 202's instructions to the application in a manner that the application can accept. Request information 120 may include information for making an HTTP request to the application to produce output according to the user's instructions. Request information 120 may include method information. Request information 120 may include a request URL. Request information 120 may include header information. Request information 120 may include body information.

[0033] The information processing system 100 may set the request information 120 obtained from the generating AI 400 to the application. The information processing system 100 may have the application execute the processing corresponding to the set request information 120 and obtain the output from the application. The information processing system 100 may present the obtained output from the application to the user 202. This allows the user 202 to check whether the request information 120 that produces the desired output has been generated. If the desired output has not been obtained, the user 202 may reconsider the user input 111 and input it to the information processing system 100. The information processing system 100 may perform the same processing on the input user input 111. This process may be repeated until the request information 120 that produces the output desired by the user 202 is generated.

[0034] When the information processing system 100 generates a query, if request information has already been set for an application, it may generate the query based on the already set request information. That is, in this case, the information processing system 100 may generate the query based on user input 111, application identification information 112, application design information 114, and current request information 121. As a specific example, for an application identified by the application identification information 112, the information processing system 100 may generate a query that includes instructions to generate request information for setting the instructions included in user input 111, referring to the current request information 121 and according to the contents described in the application design information 114. The information processing system 100 may also generate a query that includes instructions to generate request information for setting the instructions included in user input 111 by modifying the current request information 121, according to the contents described in the application design information 114, for an application identified by the application identification information 112. Including the current request information 121 in the query can contribute to improving the accuracy of request information 120 generated by the generation AI 400.

[0035] In a workflow where multiple applications are arranged in sequence but request information has not yet been configured, if the AI ​​400 is to generate request information to link the multiple applications together, the information processing system 100 may perform the same processing as described above for each application in order. In this case, when processing the second or subsequent applications among the multiple applications, the information processing system 100 may generate a query based on the response information 123 from the previous applications. That is, when the information processing system 100 generates a query for one of the multiple applications included in the workflow, if it has obtained response information from an application that is earlier in the sequence than the application in question, it may generate a query based on that response information, the user input 111 for the application, the application identification information 112 for the application, and the application design information 114 for the application. The response information 123 may be information output from an application after request information 120 has been input to a previous application. For example, in a workflow that summarizes meeting transcripts and sends them to a communication service such as Slack, the workflow includes a meeting minutes service, an AI summarization service, and a communication service. When the information processing system 100 generates request information 120 for the communication service, it may further generate a query based on the response information 123 (summarization result by the AI ​​summarization service) of the AI ​​summarization service. The information processing system 100 may further generate a query based on the current request information 121.

[0036] Figure 3 schematically shows an example of the processing flow by the information processing system 100. Here, we explain the processing flow for generating request information 120 to cause a single application to produce the output desired by user 202.

[0037] In step 102 (steps may be abbreviated as S), the information processing system 100 obtains user input 111, which includes user instructions for the application. In step S104, the information processing system 100 obtains application identification information 112 for the target application. In step S106, the information processing system 100 obtains application design information 114 for the target application.

[0038] In S108, the information processing system 100 uses the user input 111 acquired in S102, the application identification information 112 acquired in S104, and the application design information 114 acquired in S106 to generate a query for the generation AI 400 to generate request information to set the user 202's instructions contained in the user input 111 in a manner that the target application can accept.

[0039] In S110, the information processing system 100 inputs the query generated in S108 to the generation AI 400 and obtains the request information 120 output from the generation AI 400. In S112, the information processing system 100 sets the request information 120 obtained in S110 to the target application and executes it.

[0040] In S114, the information processing system 100 determines whether or not it has obtained approval for the request information 120 from the user 202 who has confirmed the execution result. If approval is obtained, the process ends; otherwise, the process proceeds to S116.

[0041] In S116, the current request information 121, which was set for the target application in S112, is retrieved, and the system returns to S102. In S102, S104, and S106, the information processing system 100 retrieves the user input 111, which has been reviewed by the user 202, along with the application identification information 112 and the application design information 114. In S108, the information processing system 100 generates a query using the user input 111, the application identification information 112, the application design information 114, and the current request information 121.

[0042] The information processing system 100 repeatedly performs this process until it obtains approval from user 202 in S114.

[0043] Figure 4 schematically shows an example of the processing flow by the information processing system 100. Here, we explain the processing flow for generating request information 120 to cause each of the multiple applications included in a single workflow to produce the output desired by the user 202.

[0044] In S202, the information processing system 100 obtains user input 111, which includes instructions from the user to the application. In S204, the information processing system 100 obtains application identification information 112 for the target application. In S206, the information processing system 100 obtains application design information 114 for the target application.

[0045] In S208, the information processing system 100 determines whether or not there is a preceding application in the workflow. If it determines that there is, it proceeds to S210; otherwise, it proceeds to S212. In S210, the information processing system 100 obtains the response information 123 of the preceding applications.

[0046] In S212, the information processing system 100 generates a query. If it is determined in S208 that there is no user input, the information processing system 100 uses the user input 111 obtained in S202, the application identification information 112 obtained in S204, and the application design information 114 obtained in S206 to generate a query that causes the generation AI 400 to generate request information to set the user 202's instructions contained in the user input 111 in a manner that the target application can accept. If it is determined in S208 that there is user input, the information processing system 100 further uses the application response information 123 obtained in S210 to generate a query.

[0047] In S214, the information processing system 100 inputs the query generated in S212 to the generation AI 400 and obtains the request information 120 output from the generation AI 400. In S216, the information processing system 100 sets the request information 120 obtained in S214 to the target application and executes it.

[0048] In S218, the information processing system 100 determines whether or not it has obtained approval for the request information 120 from the user 202 who has confirmed the execution result. If approval is obtained, it proceeds to S222; otherwise, it proceeds to S220. In S220, it obtains the current request information 121 that was set for the target application in S216 and returns to S202. In S202, the information processing system 100 obtains the user input 111 that has been reviewed by the user 202.

[0049] In S222, it is determined whether the configuration of all applications included in the workflow has been completed. If it is determined that the configuration has been completed, the process ends; otherwise, it returns to S202 and configures the next application. The information processing system 100 repeatedly performs this process until it is determined in S222 that the process has been completed.

[0050] Figure 5 is an explanatory diagram illustrating an example of input and output to the generation AI 400 by the information processing system 100. Here, we describe the input and output when the information processing system 100 receives a WF user input 115 containing a description of the workflow desired by user 202, and causes the generation AI 400 to generate the workflow desired by user 202. Note that the format of the WF user input 115 may be the same as that of user input 111.

[0051] To generate a workflow, it is basically necessary to select the applications to be included in the workflow, arrange the applications in the appropriate order, and generate the application request information 120. The information processing system 100 may have the generation AI 400 perform all of the following: application selection, application arrangement, and generation of the request information 120.

[0052] The user 202 may perform some of the tasks, including application selection, application deployment, and request information 120 generation. For example, the user 202 may select the application, while the information processing system 100 has the generation AI 400 perform the application deployment and request information 120 generation.

[0053] First, we will describe the case where the generation AI 400 is responsible for selecting the application, deploying the application, and generating the request information 120. The information processing system 100 generates a WF query to generate the workflow desired by user 202 based on the WF user input 115. For example, the information processing system 100 generates a WF query that includes instructions to generate a workflow that realizes the description of the workflow desired by user 202 included in the WF user input 115. The information processing system 100 may also include application identification information 112 and application design information 114 for a number of pre-registered applications in the query. The information processing system 100 inputs the WF query to the generation AI 400 and obtains a workflow 130 from the generation AI 400 that includes multiple applications and has request information 120 for multiple applications set. The information processing system 100 may modify the applications to be included in the workflow 130, the application deployment, and the request information 120 according to instructions from user 202.

[0054] Next, we will describe a case where user 202 selects an application, and the information processing system 100 instructs the generation AI 400 to deploy the application and generate request information 120. In this case, the information processing system 100 obtains the WF user input 115, the application identification information 112 of the multiple applications specified by user 202, and the application design information 114 of the multiple applications, and generates a query. The information processing system 100 generates a query that includes instructions to generate a workflow consisting of the multiple applications identified by the obtained multiple application identification information 112, in order to realize the description of the workflow desired by user 202 included in the WF user input 115, with the request information 120 of the multiple applications set according to the contents of the multiple application design information 114. The information processing system 100 inputs the WF query to the generation AI 400 and obtains a workflow 130 from the generation AI 400 that includes the multiple applications and has the request information 120 of the multiple applications set. The information processing system 100 may modify the application deployment and the request information 120 according to instructions from user 202.

[0055] Next, we will describe the case where user 202 selects and places applications, and the information processing system 100 instructs the generation AI 400 to generate request information 120. In this case, the information processing system 100 obtains WF user input 115, application identification information 112 for multiple applications specified by user 202, application design information 114 for those multiple applications, and placement information 131 for those multiple applications, and generates a WF query. The information processing system 100 generates a WF query that includes instructions to generate a workflow in which the multiple applications identified by the obtained multiple application identification information 112 are configured in the placement indicated by the placement information 131, and in order to realize the description of the workflow desired by user 202 included in the WF user input 115, the request information 120 for the multiple applications is set according to the contents included in the multiple application design information 114. The information processing system 100 inputs the WF query to the generation AI 400 and obtains a workflow 130 from the generation AI 400 that includes multiple applications and has the request information 120 for those applications set. The information processing system 100 may modify the application deployment and request information 120 in response to instructions from the user 202.

[0056] Figure 6 schematically shows an example of the processing flow by the information processing system 100. Here, we explain the processing flow when a workflow 130 containing request information 120 for multiple applications is generated using the generation AI 400 in response to WF user input 115, and then modified as necessary.

[0057] In S302, the information processing system 100 obtains the WF user input 115. In S304, the information processing system 100 generates a WF query based on the WF user input 115 to generate the workflow desired by user 202. As described above, the information processing system 100 may include multiple application-specific information 112 and multiple application-design information 114 in the WF query.

[0058] In S306, the information processing system 100 inputs the WF query generated in S304 into the generation AI 400 to obtain a workflow 130 in which request information 120 for multiple applications is configured.

[0059] In S308, the information processing system 100 executes the workflow 130 acquired in S306. Through the execution of workflow 130, multiple applications coordinate their inputs and outputs based on the request information 120 of the multiple applications.

[0060] In S310, the information processing system 100 determines whether or not it has obtained approval for workflow 130 from user 202, who has reviewed the execution results. If approval is obtained, the process ends; otherwise, it proceeds to S312.

[0061] In S312, the information processing system 100 performs a workflow modification process. The workflow modification may involve modifying the request information 120 of the application to be modified. The information processing system 100 may modify the request information 120 of the application to be modified by performing the process described in Figure 2.

[0062] Figure 7 schematically shows an example of the processing flow by the information processing system 100. Here, we explain the processing flow in which, in response to the WF user input 115, the placement of the applications that make up the workflow is first determined, and then the request information 120 of the multiple applications included in the workflow is set.

[0063] In S402, the information processing system 100 obtains the WF user input 115. In S404, the information processing system 100 generates a WF query based on the WF user input 115 to cause the generation AI 400 to generate a workflow in which multiple applications are arranged in sequence. As described above, the information processing system 100 may include multiple application identification information 112 and multiple application design information 114 in the WF query.

[0064] In S406, the information processing system 100 inputs the WF query generated in S404 into the generation AI 400 to obtain a workflow 130 in which multiple applications are arranged in sequence. This workflow may be in a state where the request information 120 has not been set.

[0065] In S408, the information processing system 100 determines whether or not it has obtained approval for workflow 130 from user 202, who has reviewed workflow 130. If approval is obtained, the process proceeds to S410; otherwise, it returns to S402. In S402, the information processing system 100 obtains the WF user input 115 that user 202 has reviewed.

[0066] In S410, the information processing system 100 executes the workflow 130 configuration process. The information processing system 100 may configure the workflow 130 by executing the process described in Figure 4.

[0067] Figure 8 schematically shows an example of the functional configuration of the information processing system 100. The information processing system 100 includes a storage unit 110 and a UI unit 140.

[0068] The memory unit 110 stores various types of information. For example, the memory unit 110 stores service identification information 102 that can identify a service. The application identification information 112 described above may be an example of service identification information 102. The memory unit 110 also stores service design information 104. The application design information 114 described above may be an example of service design information 104.

[0069] The storage unit 110 stores, for example, request information 120. The storage unit 110 may store request information 120 set for the service by a user 202 or the like. The storage unit 110 may store request information 120 generated by the information processing system 100 to the generation AI 400. The storage unit 110 stores, for example, response information 123.

[0070] The memory unit 110 stores, for example, a workflow 130. The memory unit 110 may store a workflow 130 generated by a user 202 or the like. It may also store a workflow 130 generated by the generation AI 400 when the information processing system 100 has it generated.

[0071] The UI unit 140 may function as an interface with the user 202. The UI unit 140 includes a presentation unit 142, an input acquisition unit 144, a registration unit 146, a query generation unit 148, a request information acquisition unit 150, a request information setting unit 152, a processing unit 154, a response information acquisition unit 155, and a WF generation unit 156. It is not mandatory for the UI unit 140 to have all of these.

[0072] The presentation unit 142 provides various presentations to the user 202. The input acquisition unit 144 acquires various inputs from the user 202. The presentation unit 142 may display various information on the screen of the computer 200. The input acquisition unit 144 may acquire user input entered via the input device of the computer 200. The input acquisition unit 144 may acquire user input 111, which includes instructions from the user 202 regarding the service. The input acquisition unit 144 may acquire WF user input 115, which includes a description of the workflow desired by the user.

[0073] The registration unit 146 registers various types of information. The registration unit 146 stores the registered information in the storage unit 110. For example, the registration unit 146 registers service identification information 102 for multiple services. For example, the registration unit 146 registers service design information 104 for multiple services.

[0074] The service identification information 102 may be any information that can identify the service. The service identification information 102 may include service identification information that can identify the service. The service identification information may be the name of the service, or it may be an ID assigned to the service. The service identification information 102 may include the URL of the service. The service identification information 102 may include service description information 103 that describes the service. The service description information 103 may include at least one of the purpose, type, and function of the service. The service design information 104 includes multiple configuration items in the service. The service design information 104 may include descriptions of the multiple configuration items. The service design information 104 may include description rules for the multiple configuration items. The service design information 104 may be, for example, the API documentation for the service. The storage unit 110 may store the multiple configuration items of the service design information 104 in a vector database.

[0075] The query generation unit 148 generates queries for input to the generation AI 400. For example, the query generation unit 148 generates a query to cause the generation AI 400 to generate request information 120. Based on the user input 111, the service identification information 102 of the target service, and the service design information 104 of the target service acquired by the input acquisition unit 144, the query generation unit 148 may generate a query to cause the generation AI 400 to generate request information 120 to set the user 202's instructions included in the user input 111 to the target service in a manner that the target service can accept. For example, the query generation unit 148 generates a query that includes instructions to generate request information 120 to set the instructions included in the user input 111 to the service identified by the service identification information 102, in accordance with the contents described in the service design information 104.

[0076] The query generation unit 148 may generate a query based on the configured request information 120 if request information 120 has been configured for the target service. For example, if user 202 has configured request information 120 for the target service but the processing is not performed as desired and the request information 120 is modified, or if user 202 has configured request information 120 generated by generation AI 400 for the target service but the processing is not performed as desired and the request information 120 is modified, the query generation unit 148 will generate a query based on the configured request information 120. For example, for a service specified by service identification information 102, the query generation unit 148 will generate a query that includes instructions to generate request information 120 for configuring the instructions included in user input 111, referring to the current request information 120 according to the contents described in service design information 104. The information processing system 100 may, for example, generate a query that includes instructions to generate request information 120 for setting instructions included in user input 111, in accordance with the contents described in service design information 104, for a service identified by service identification information 102, by modifying the current request information 120.

[0077] The request information acquisition unit 150 inputs the query generated by the query generation unit 148 to the generation AI 400 and acquires the request information 120 output from the generation AI 400. The request information acquisition unit 150 stores the acquired request information 120 in the storage unit 110. The request information 120 acquired by the request information acquisition unit 150 may be presented to the user 202 by the presentation unit 142. The user 202 may view the request information 120 to confirm whether the generated request information 120 meets their needs.

[0078] The request information acquisition unit 150 generates a configured workflow 130 using the request information 120 of multiple services that constitute the workflow 130. The workflow 130 may include the arrangement of multiple services and the request information 120 of multiple services.

[0079] The request information setting unit 152 sets the request information 120 acquired by the request information acquisition unit 150 to the target service. The request information setting unit 152 sets the request information 120 of multiple services included in the workflow 130 generated by the request information acquisition unit 150 to multiple services.

[0080] The processing unit 154 executes various processes. The processing unit 154 causes services to execute processes. For example, the processing unit 154 causes a service for which the request information setting unit 152 has set request information 120 to execute a process according to the request information 120. For example, if the request information setting unit 152 has set request information 120 for multiple services included in the workflow 130, the processing unit 154 causes the multiple services included in the workflow 130 to execute a process according to the request information 120 in sequence.

[0081] Request information 120 for multiple services may be configured to enable coordination between services. For example, in a workflow 130 consisting of a first service, a second service, and a third service, the request information 120 for the first service may be configured to cause the first service to output its processing result and input it to the second service, and the request information 120 for the second service may be configured to cause the second service to output its processing result and input it to the third service. In this case, after the request information setting unit 152 sets the request information 120 for the first service, the second service, and the third service, the processing unit 154 causes the first service to execute processing according to the request information 120.

[0082] However, the request information 120 for multiple services may be configured to be linked via the information processing system 100. For example, in a workflow 130 consisting of a first service, a second service, and a third service, the request information 120 for the first service may be configured to cause the first service to output a processing result and send it to the information processing system 100, and the request information 120 for the second service may be configured to cause the second service to output a processing result and send it to the information processing system 100 in accordance with the information received from the information processing system 100. In this case, after the request information 120 is set for the first service, the second service, and the third service by the request information setting unit 152, the processing unit 154 causes the first service to execute processing according to the request information 120, causes the second service to execute processing according to the request information 120 in response to receiving output from the first service, and causes the third service to execute processing according to the request information 120 in response to receiving output from the second service.

[0083] The response information acquisition unit 155 acquires response information 123 output from a service when the processing unit 154 causes the service for which the request information 120 has been set by the request information setting unit 152 to execute processing in accordance with the request information 120. When the query generation unit 148 generates a query for one of several services included in a workflow, if the response information acquisition unit 155 has acquired response information 123 from a service that is earlier in the sequence than the one service among the several services, the query generation unit 148 may generate a query based on the response information 123, user input 111 for the one service, service identification information 102 for the one service, and service design information 104 for the one service. For example, the query generation unit 148 generates a query for a service identified by the service identification information 102, which includes instructions to generate request information 120 for setting instructions included in the user input 111, taking into account the content of the response information 123 in accordance with the content described in the service design information 104.

[0084] The WF generation unit 156 generates the workflow 130. The WF generation unit 156 may generate the workflow 130 by controlling the query generation unit 148, the request information acquisition unit 150, and the request information setting unit 152.

[0085] When the input acquisition unit 144 acquires WF user input that includes a description of the workflow desired by user 202, the WF generation unit 156 may cause the query generation unit 148 to generate a WF query based on the WF user input to generate the workflow desired by user 202. Based on the WF query generated by the query generation unit 148, the WF generation unit 156 may use the generation AI 400 to generate the workflow 130.

[0086] The WF generation unit 156 may have the generation AI 400 perform all of the following: service selection, service placement, and request information generation 120. The WF generation unit 156 may have the generation AI 400 perform service placement and request information generation 120 for multiple services selected by the user 202. The WF generation unit 156 may have the generation AI 400 perform request information generation 120 for multiple services selected and whose placement has been determined by the user 202.

[0087] When the generation AI 400 is to perform all of the tasks of service selection, service placement, and request information 120 generation, the WF generation unit 156 instructs the query generation unit 148 to generate a WF query based on the WF user input 115 to generate the workflow desired by the user 202. The query generation unit 148 generates a query that includes, for example, instructions to generate a workflow that realizes the description of the workflow desired by the user 202 included in the WF user input 115. The query generation unit 148 may also include pre-registered application identification information 112 and application design information 114 for multiple services in the WF query. The WF generation unit 156 may instruct the request information acquisition unit 150 to input the WF query generated by the query generation unit 148 to the generation AI 400, and have the generation AI 400 acquire a workflow 130 that includes multiple services and has request information 120 for multiple services set.

[0088] When user 202 selects a service and the generation AI 400 is instructed to deploy the service and generate request information 120, the WF generation unit 156 instructs the query generation unit 148 to acquire the WF user input 115, application identification information 112 for multiple services specified by user 202, and application design information 114 for those multiple services, and to generate a query. The query generation unit 148 may generate a query that includes instructions to generate a workflow consisting of multiple services identified by the acquired application identification information 112, in which the request information 120 for multiple services is set according to the contents of the application design information 114 in order to realize the description of the workflow desired by user 202 included in the WF user input 115. The WF generation unit 156 instructs the request information acquisition unit 150 to input the WF query to the generation AI 400, and the generation AI 400 acquires a workflow 130 that includes multiple services and has the request information 120 for multiple services set.

[0089] When user 202 selects and places services and instructs generation AI 400 to generate request information 120, WF generation unit 156 instructs query generation unit 148 to acquire WF user input 115, application identification information 112 for multiple services specified by user 202, application design information 114 for those multiple services, and placement information for those multiple services, and to generate a query. The query generation unit 148 generates a query that includes instructions to generate a workflow in which the multiple services identified by the acquired application identification information 112 are configured in the placement indicated by placement information 131, and in order to realize the description of the workflow desired by user 202 included in WF user input 115, the request information acquisition unit 150 instructs generation AI 400 to input the WF query, and instructs generation AI 400 to acquire a workflow 130 that includes multiple services and has the request information 120 for those services set.

[0090] Figure 9 schematically shows an example of the hardware configuration of a computer 1200 that functions as an information processing system 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the apparatus according to this embodiment, or to cause the computer 1200 to execute operations associated with the apparatus according to this embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0091] The computer 1200 according to this embodiment includes a CPU 1212, RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0092] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0093] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0094] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 upon activation. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0095] The program is provided on a computer-readable storage medium such as a DVD-ROM or IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0096] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as RAM 1214, storage device 1224, DVD-ROM, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area provided on the recording medium.

[0097] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), or an IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

[0098] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies the predetermined condition.

[0099] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0100] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0101] A computer-readable storage medium may include any tangible device capable of storing instructions that can be executed by a suitable device, and as a result, a computer-readable storage medium having instructions stored therein will comprise a product that includes instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0102] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0103] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or another programmable data processing device, so that the processor or programmable circuit of the programmable data processing device, such as a computer, may execute the instructions to generate means for performing operations specified in a flowchart or block diagram. Here, the computer may be a PC (personal computer), a tablet computer, a smartphone, a workstation, a server computer, a general-purpose computer, or a special-purpose computer, and may also be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system and is a computer in a broad sense. In a distributed computing system, multiple computers execute a program collectively by each computer executing a part of the program and passing data during program execution between computers as needed.

[0104] Examples of processors include computer processors, central processing units, processing units, microprocessors, digital signal processors, controllers, and microcontrollers. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of the program, and the processors collectively execute the program by passing program execution data between them as needed. For example, in the execution of multitasks, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which part of a program each processor executes changes dynamically. Which part of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0105] By using the invention according to this embodiment, it is possible to support the setting of request information necessary for users to generate workflows that link services used in their work, thereby contributing to the achievement of Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0106] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0107] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is essential to perform the operations in that order. [Explanation of symbols]

[0108] 20 Network, 100 Information Processing System, 102 Service Identification Information, 103 Service Description Information, 104 Service Design Information, 110 Storage Unit, 111 User Input, 112 Application Identification Information, 114 Application Design Information, 115 WF User Input, 120, 121 Request Information, 123 Response Information, 130 Workflow, 131 Deployment Information, 140 UI Unit, 142 Presentation Unit, 144 Input Acquisition Unit, 146 Registration Unit, 148 Query Generation Unit, 150 Request Information Acquisition Unit, 152 Request Information Setting Unit, 154 Processing Unit, 155 Response Information Acquisition Unit, 156 WF Generation Unit, 200 Computer, 202 User, 300 Server, 400 Generation AI, 1200 Computer, 1210 Host Controller, 1212 CPU, 1214 RAM, 1216 Graphics Controller, 1218 Display device, 1220 I / O controller, 1222 communication interface, 1224 storage device, 1230 ROM, 1240 I / O chip

Claims

1. An input acquisition unit that acquires user input, including instructions from the user regarding the service, A query generation unit generates a query to cause a generating AI to generate request information to set the instruction to the service in a manner that the service can accept, based on the user input, service identification information that can identify the service, and service design information of the service. A request information acquisition unit inputs the query to the generating AI and acquires the request information output from the generating AI. An information processing system equipped with the following features.

2. The information processing system according to claim 1, wherein the service design information includes a plurality of setting items for the service and a description of the plurality of setting items.

3. The information processing system according to claim 1, wherein the service identification information includes at least one of service identification information that can identify the service, the URL of the service, and service description information that describes the service.

4. The information processing system according to claim 1, wherein the query generation unit generates the query based on the configured request information if request information is configured for the service.

5. The aforementioned service is SaaS, The information processing system according to claim 1, wherein the request information includes at least one of method information, header information, body information, and request URL for making an HTTP request to the service.

6. The aforementioned service is SaaS, The information processing system according to claim 1, wherein the service design information is an API document of the SaaS.

7. The service design information includes multiple setting items in the service, The information processing system includes a storage unit that stores the multiple setting items in a vector database, The information processing system according to claim 1, wherein the query generation unit generates the query based on the service design information, which includes the plurality of setting items stored in the storage unit as a vector database, the user input and the service identification information.

8. The input acquisition unit acquires the user input for the service included in the workflow, which is configured by arranging multiple services in sequence. The information processing system according to any one of claims 1 to 7, wherein the query generation unit generates the query for one of the multiple services included in the workflow, and when the response information acquisition unit has acquired response information from a service that is earlier in the sequence than the one service among the multiple services, the query generation unit generates the query based on the response information, the user input for the one service, the service identification information for the one service, and the service design information for the one service.

9. The input acquisition unit acquires WF user input, which includes a description of the workflow desired by the user. The query generation unit generates a WF query based on the WF user input to generate the workflow desired by the user. The aforementioned information processing system is WF generation unit generates the workflow using the generation AI based on the WF query. An information processing system according to any one of claims 1 to 7, comprising:

10. The query generation unit generates a WF query to cause the generation AI to generate a workflow in which multiple services are arranged in sequence, in order to realize the workflow desired by the user. The information processing system according to claim 9, wherein the WF generation unit inputs the WF query to the generation AI and obtains the workflow output from the generation AI.

11. A program for causing a computer to function as an information processing system according to any one of claims 1 to 7.

12. A method of information processing performed by a computer, The user input acquisition stage involves obtaining user input, including instructions from the user regarding the service, A query generation step in which a query is generated to cause a generating AI to generate request information to set the instruction to the service in a manner that the service can accept, based on the user input, service identification information that can identify the service, and service design information of the service, The process involves inputting the query into the generating AI and obtaining the request information output from the generating AI. An information processing method comprising the following:

Images