Information processing system, information processing method, and program

Abstract

An information processing system, an information processing method, and a program are provided that support the setting of request information required for generating a workflow that links together services used by a user in his or her business. [Solution] In an information processing system comprising a memory unit 110 and a UI unit 140, the UI unit comprises an input acquisition unit 144 that acquires user input including user instructions for a service, a query generation unit 148 that generates a query to cause a generation AI to generate request information to set in the service in a manner that allows the service to accept the instructions, based on the user input, service specification information that can identify the service, and service design information for the service, and a request information acquisition unit 154 that inputs the query to the generation AI and acquires the request information output from the generation AI.

Description

[Technical Field]

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

[0002] Patent Document 1 describes a SaaS inter-data integration support system that includes: a storage device that holds an interface DB that stores information about the data input / output interface of each SaaS (Software as a Service); and a computing device that identifies a set of SaaS that have a common data format in the interface based on the interface DB (DataBase), outputs information about the set to a specified device, and, when a request for integration settings for the set is received from a user from the specified device, adds specified information that defines the set as a group of SaaS to be integrated to an API (Application Programming Interface) that obtains the execution result of a specified algorithm corresponding to the data integration processing between SaaS, and stores the information in the storage device as an integration API. [Prior art document] [Patent documents] [Patent Document 1] JP 2016-224578 A Summary of the Invention [Means for solving the problem]

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

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

[0005] In the information processing system, the service specification information may include at least one of service identification information capable of identifying the service, a URL of the service, and service description information that describes the service.

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

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

[0008] In the information processing system, the service may be SaaS, and the service design information may be an API document for the SaaS.

[0009] In the information processing system, the service design information may include a plurality of setting items for the service, and the information processing system may be provided with a memory 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 memory unit in a vector database format, the user input, and the service specification information.

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

[0011] In the information processing system, the input acquisition unit may acquire a WF user input including a description of a workflow desired by a user, the query generation unit may generate a WF query for generating the workflow desired by the user based on the WF user input, 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 for causing the generation AI to generate a workflow in which a plurality of 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, there is provided a program for causing a computer to function as the information processing system.

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

[0014] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions. [Brief explanation of the drawings]

[0015] [Figure 1] 1 illustrates an example of an information processing system 100. [Figure 2] 10 is an explanatory diagram illustrating an example of input and output to a generated AI 400 by the information processing system 100. FIG. [Figure 3] 1 shows an example of a processing flow of the information processing system 100. [Figure 4] 1 shows an example of a processing flow of the information processing system 100. [Figure 5] 1 shows an example of a processing flow of the information processing system 100. [Figure 6] 10 is an explanatory diagram illustrating an example of input and output to a generated AI 400 by the information processing system 100. FIG. [Figure 7] 1 shows an example of a processing flow of the information processing system 100. [Figure 8] 1 illustrates an example of a functional configuration of an information processing system 100. [Figure 9]1 shows an example of a hardware configuration of a computer 1200 that functions as the information processing system 100. DETAILED DESCRIPTION OF THE INVENTION

[0016] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] Conventionally, in order to link multiple types of services such as SaaS to complete a single process, it was necessary to appropriately format request information such as an HTTP request using a program based on knowledge of design information defined for each service, but 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 supports, for example, the setting of request information required to generate a workflow that links services used by users in their business.

[0018] 1 schematically illustrates an example of an information processing system 100. The information processing system 100 may be realized by a computer 200 operated by a user 202. The information processing system 100 realized by the computer 200 supports the operation of the computer 200 by the user 202.

[0019] In a configuration in which 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 a thin client environment, most of the functions are arranged in the server 300, and the computer 200 executes limited functions such as input and display, but the information processing system 100 realized in the server 300 supports the user 202 in operating the computer 200 to execute processes in the server 300. The computer 200 and the server 300 may communicate via a 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 multiple skills available to the user 202. A skill may constitute a workflow that links multiple types of services. A service may be what is known as SaaS. A service may be a service provided by an application. A different workflow is configured for each skill. For example, a certain skill constitutes a workflow that links a calendar app that provides a calendar service and a message app that provides a message service. For example, a certain skill constitutes a workflow that links a web conference app that provides a web conference service, an AI app that provides a service that transcribes web conference audio and creates minutes, an AI app that provides a summarization service that summarizes the minutes, and a customer relationship management (CRM) app that provides a CRM service that stores and manages meeting and summary minutes. A workflow may link any number of services. A workflow may link any type of services. The information processing system 100 may create and manage multiple skills using what is known as iPaaS (Integration Platform as a Service).

[0021] As described above, generating such skills requires advanced knowledge, and it may be difficult to request this from the user 202. The information processing system 100 according to this embodiment supports the user 202 in generating skills. For example, the information processing system 100 aims to provide the user 202 with an environment in which the user can generate skills simply by inputting natural language. As a specific example, the information processing system 100 supports the generation of HTTP requests required for linking SaaS applications.

[0022] For example, the information processing system 100 supports the generation of HTTP requests for linking multiple services included in a workflow that the user 202 has created by arranging multiple services in an order. The information processing system 100 may also support the user 202 in arranging multiple services. For example, the information processing system 100 receives a description of a workflow desired by the user 202, and, in order to realize the workflow, arranges multiple services in an order and generates HTTP requests for linking multiple services together.

[0023] The information processing system 100 may use the generated AI 400 to assist the user 202. The generated AI 400 may be an LLM (Large Language Model). The generated AI 400 may be a so-called interactive generated AI. The generated AI 400 may be a generated AI that combines an LLM with an interactive UI. Examples of the generated AI 400 include ChatGPT, Gemini, and Claude (registered trademark), but are not limited to these, and may be any existing generated AI. Furthermore, the generated AI 400 may be a generated AI generated for the information processing system 100. The information processing system 100 may communicate with the generated AI 400 via the network 20. Note that the information processing system 100 may include the generated AI 400.

[0024] By appropriately inputting necessary information to the generation AI 400, highly accurate output can be obtained. For example, the information processing system 100 may acquire user input including instructions from the user 202 for a service, and based on the user input, service identification information that can identify the service, and service design information for the service, generate a query to cause the generation AI 400 to generate request information to set for the service in a manner that allows the service to accept the instructions from the user 202, and input the query to the generation AI 400. As a specific example, when the information processing system 100 acquires user input including an instruction to a calendar app to output the user 202's schedule for a specific period, the information processing system 100 generates a query based on the user input, the name and uniform resource locator (URL) of the calendar app, and the API document of the calendar app. For example, the information processing system 100 generates a query including an instruction to generate request information including method information, a request URL, header information, and body information for causing the calendar app identified by the name and URL to perform output in response to the instructions from the user 202 in accordance with the content of the API document.

[0025] It is possible to generate an HTTP request by instructing an existing generation AI to generate an HTTP request that outputs specified information to an application. However, generating a correct HTTP request is difficult, and even if the HTTP request is set in an application, it may not work properly, may result in an error, or may output information different from the desired information. This is particularly likely to occur when the target application is a minor application or, even if it is a major application, does not disclose much information. In contrast, the information processing system 100 of this embodiment, when receiving user input including a user instruction for an application, can generate an HTTP request that accurately accepts the user instruction in accordance with the request requirements of the application by generating a query using the user input, accurate identification information of the application, and design information such as the application's API documentation.

[0026] 2 is an explanatory diagram illustrating an example of input / output to / from the generation AI 400 by the information processing system 100. Here, first, input / output when the generation AI 400 is made to generate request information 120 for one application to perform the output desired by the user 202 will be described. Next, input / output when the generation AI 400 is made to generate request information for linking multiple applications in a workflow in which multiple applications are arranged in order but the request information has not yet been set will be described.

[0027] When the information processing system 100 acquires a user input 111 including an instruction from a user 202 for an application, the information processing system 100 generates a query to cause a generation AI 400 to generate request information 120 for setting the application in a manner that allows the application to accept the instruction from the user 202, based on the user input 111, application specification information 112 for the application, and application design information 114 for the application, and inputs the generated query to the generation AI 400 to acquire the request information 120 from the generation AI 400. For example, the information processing system 100 generates a query including an instruction to generate request information 120 for setting the instruction included in the user input 111 for an application identified by the application specification information 112, in accordance with the contents described in the application design information 114.

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

[0029] The application identification information 112 may be any information capable of identifying an application. The application identification information 112 may include application identification information capable of identifying an 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, and therefore it is highly likely that the generation AI 400 has learned what kind of application the application is. However, if the target application is an obscure application, the generation AI 400 may not have learned what kind of application the application is. In such cases, including application description information in the application identification information 112 can provide the generation AI 400 with knowledge of the purpose, type, function, etc. of the application.

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

[0031] The application design information 114 is design information of an application and may include multiple setting items of the application. The application design information 114 may include descriptions of multiple setting items. The application design information 114 may include description rules for multiple setting items. The application design information 114 may be, for example, an API document 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 a target application from the storage unit. Note that the application design information 114 may be input by the user 202 together with the user input 111.

[0032] The request information 120 may be information that sets instructions from the user 202 to the application in a format that the application can accept. The request information 120 may include information for making an HTTP request to the application to cause output in accordance with the user's instructions. The request information 120 may include method information. The request information 120 may include a request URL. The request information 120 may include header information. The request information 120 may include body information.

[0033] The information processing system 100 may set the request information 120 acquired from the generation AI 400 for an application. The information processing system 100 may cause the application to execute processing corresponding to the set request information 120 and acquire output from the application. The information processing system 100 may present the acquired output from the application to the user 202. This allows the user 202 to confirm whether the request information 120 that provides the desired output has been generated. If the desired output has not been acquired, the user 202 may reconsider the user input 111 and input it into the information processing system 100. The information processing system 100 may perform the same processing on the input user input 111. In this manner, the processing may be repeated until the request information 120 that provides the desired output for the user 202 is generated.

[0034] When generating a query, if request information has already been set for an application, the information processing system 100 may generate the query based on the set request information. That is, in this case, the information processing system 100 may generate the query based on the user input 111, the application specifying information 112, the application design information 114, and the current request information 121. As a specific example, the information processing system 100 may generate a query for an application specified by the application specifying information 112, including an instruction to generate request information for setting an instruction included in the user input 111 by referring to the current request information 121 in accordance with the content described in the application design information 114. The information processing system 100 may generate a query for an application specified by the application specifying information 112, including an instruction to generate request information for setting an instruction included in the user input 111 by modifying the current request information 121 in accordance with the content described in the application design information 114. Including the current request information 121 in the query may contribute to improving the accuracy of generation of the request information 120 by the generation AI 400.

[0035] When the generation AI 400 generates request information for linking multiple applications in a workflow in which multiple applications are arranged in order but request information has not yet been set, the information processing system 100 may perform the same processing as described above for each application in order. In this case, when processing a second or subsequent application among the multiple applications, the information processing system 100 may generate a query based on response information 123 from the previous application. That is, when generating a query for one of the multiple applications included in the workflow, if the information processing system 100 has acquired response information from an application that precedes the first application, the query may be generated based on the response information, the user input 111 for the first application, the application specification information 112 for the first application, and the application design information 114 for the first application. The response information 123 may be information output from the previous application in response to input of request information 120 to the previous application. For example, in the case of a workflow that summarizes a meeting transcript and sends it to a communication service such as Slack, the workflow includes a minutes service, an AI summarization service, and a communication service, and when generating request information 120 for the communication service, the information processing system 100 may generate a query further based on response information 123 of the AI summarization service (summarization result by the AI summarization service).The information processing system 100 may also generate a query further based on current request information 121.

[0036] 3 shows an example of a processing flow by the information processing system 100. Here, the processing flow for generating request information 120 for causing one application to perform an output desired by the user 202 will be described.

[0037] In step (sometimes abbreviated as S) 102, the information processing system 100 acquires user input 111 including instructions from the user for the application. In S104, the information processing system 100 acquires application specification information 112 for the target application. In S106, the information processing system 100 acquires 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 specific information 112 acquired in S104, and the application design information 114 acquired in S106 to generate a query to cause the generation AI 400 to generate request information to be set in the target application in a manner that enables the target application to accept the instructions of the user 202 contained in the user input 111.

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

[0040] In S114, the information processing system 100 determines whether or not approval of the request information 120 has been obtained from the user 202 who has confirmed the execution result. If approval has been obtained, the process ends, and if approval has not been obtained, the process proceeds to S116.

[0041] In S116, the current request information 121 set for the target application in S112 is acquired, and the process returns to S102. In S102, S104, and S106, the information processing system 100 acquires the user input 111 reviewed by the user 202, the application specifying 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 specifying information 112, the application design information 114, and the current request information 121.

[0042] The information processing system 100 repeats this process until approval from the user 202 is obtained in S114.

[0043] 4 shows an example of a processing flow by the information processing system 100. Here, the processing flow for generating request information 120 for causing each of a plurality of applications included in one workflow to perform an output desired by the user 202 will be described.

[0044] In S202, the information processing system 100 acquires a user input 111 including a user instruction for an application. In S204, the information processing system 100 acquires application specification information 112 of the target application. In S206, the information processing system 100 acquires application design information 114 of the target application.

[0045] In S208, the information processing system 100 determines whether or not there is a previous application in the workflow. If it is determined that there is, the process proceeds to S210, and if it is determined that there is not, the process proceeds to S212. In S210, the information processing system 100 acquires response information 123 of the previous application.

[0046] In S212, the information processing system 100 generates a query. If it is determined in S208 that there is no such application, the information processing system 100 generates a query for causing the generation AI 400 to generate request information to be set in the target application in a manner that enables the target application to accept the instruction of the user 202 included in the user input 111, using the user input 111 acquired in S202, the application specification information 112 acquired in S204, and the application design information 114 acquired in S206. If it is determined in S208 that there is such application, the information processing system 100 generates a query by further using the response information 123 of the previous application acquired in S210.

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

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

[0049] In S222, it is determined whether the settings for all of the applications included in the workflow have been completed. If it is determined that the settings have been completed, the process ends. If it is determined that the settings have not been completed, the process returns to S202 and the settings for the next application are performed. The information processing system 100 repeatedly executes this process until it is determined that the settings have been completed in S222.

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

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

[0052] The user 202 may select an application, deploy the application, and generate some of the request information 120. For example, the user 202 may select an application, and the information processing system 100 may cause the generation AI 400 to deploy the application and generate the request information 120. For example, the user 202 may select and deploy an application, and the information processing system 100 may cause the generation AI 400 to generate the request information 120.

[0053] First, a case will be described in which the generation AI 400 is caused to perform all of the following: application selection, application placement, and generation of request information 120. The information processing system 100 generates a WF query for generating a workflow desired by the user 202 based on a WF user input 115. For example, the information processing system 100 generates a WF query including an instruction to generate a workflow that realizes a description of a workflow desired by the user 202, which is included in the WF user input 115. The information processing system 100 may include the application specification information 112 and application design information 114 of multiple pre-registered applications in the query. The information processing system 100 inputs the WF query into the generation AI 400 and obtains, from the generation AI 400, a workflow 130 that includes multiple applications and in which request information 120 for the multiple applications is set. The information processing system 100 may modify the applications to be included in the workflow 130, the placement of the applications, and the request information 120 in response to instructions from the user 202.

[0054] Next, a case will be described in which the user 202 selects an application and the information processing system 100 causes the generation AI 400 to allocate the application and generate request information 120. In this case, the information processing system 100 acquires a WF user input 115, application specification information 112 for multiple applications specified by the user 202, and application design information 114 for the multiple applications, and generates a query. The information processing system 100 generates a query including an instruction to generate a workflow configured by multiple applications specified by the acquired application specification information 112, in which request information 120 for the multiple applications is set according to the content included in the application design information 114, in order to realize the workflow description desired by the user 202 included in the WF user input 115. The information processing system 100 inputs the WF query into the generation AI 400 and acquires from the generation AI 400 a workflow 130 including multiple applications and in which request information 120 for the multiple applications is set. The information processing system 100 may modify the application allocation and the request information 120 in response to an instruction from the user 202.

[0055] Next, a case will be described in which the user 202 selects and arranges applications, and the information processing system 100 causes the generation AI 400 to generate request information 120. In this case, the information processing system 100 acquires a WF user input 115, application specification information 112 of multiple applications specified by the user 202, application design information 114 of the multiple applications, and arrangement information 131 of the multiple applications, and generates a WF query. The information processing system 100 generates a WF query including an instruction to generate a workflow in which request information 120 of multiple applications is set according to the content included in the application design information 114, so as to realize a workflow description desired by the user 202 included in the WF user input 115. The information processing system 100 inputs the WF query to the generation AI 400 and acquires from the generation AI 400 a workflow 130 including multiple applications and in which request information 120 of the multiple applications is set. The information processing system 100 may modify the application placement and request information 120 in response to instructions from the user 202 .

[0056] 6 shows an example of a processing flow by the information processing system 100. Here, the processing flow will be described when a workflow 130 in which request information 120 of multiple applications is set in response to a WF user input 115 is generated using a generation AI 400, and the workflow is modified as necessary.

[0057] In S302, the information processing system 100 acquires a WF user input 115. In S304, the information processing system 100 generates a WF query for generating a workflow desired by the user 202, based on the WF user input 115. As described above, the information processing system 100 may include multiple pieces of application specification information 112 and multiple pieces of 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 acquire the workflow 130 in which the request information 120 of a plurality of applications is set.

[0059] In S308, the information processing system 100 executes the workflow 130 acquired in S306. By executing the workflow 130, the input and output of the multiple applications are coordinated according to the request information 120 of the multiple applications.

[0060] In S310, the information processing system 100 determines whether or not approval of the workflow 130 has been obtained from the user 202 who confirmed the execution result. If approval has been obtained, the process ends, and if approval has not been obtained, the process proceeds to S312.

[0061] In S312, the information processing system 100 executes a process for correcting the workflow. The correction of the workflow may be to correct the request information 120 of the application to be corrected. The information processing system 100 may correct the request information 120 of the application to be corrected by executing the process described in FIG.

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

[0063] In S402, the information processing system 100 acquires a WF user input 115. In S404, the information processing system 100 generates a WF query for causing the generation AI 400 to generate a workflow in which multiple applications are arranged in order, based on the WF user input 115. As described above, the information processing system 100 may include multiple pieces of application specification information 112 and multiple pieces of 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 order. The workflow may be in a state in which the request information 120 is not set.

[0065] In S408, the information processing system 100 determines whether approval of the workflow 130 has been obtained from the user 202 who has checked the workflow 130. If approval has been obtained, the process proceeds to S410, and if approval has not been obtained, the process returns to S402. In S402, the information processing system 100 acquires the WF user input 115 reviewed by the user 202.

[0066] In S410, the information processing system 100 executes the setting process for the workflow 130. The information processing system 100 may set the workflow 130 by executing the process described with reference to FIG.

[0067] 8 shows an example of a 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 storage unit 110 stores various types of information. The storage unit 110 stores, for example, service specification information 102 that can specify a service. The above-described application specification information 112 may be an example of the service specification information 102. The storage unit 110 stores, for example, service design information 104. The above-described application design information 114 may be an example of the service design information 104.

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

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

[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 essential that the UI unit 140 include all of these units.

[0072] The presentation unit 142 presents various information 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 a user input entered via an input device of the computer 200. The input acquisition unit 144 may acquire a user input 111 including an instruction from the user 202 for a service. The input acquisition unit 144 may acquire a WF user input 115 including a description of a 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. The registration unit 146 registers, for example, service specification information 102 for a plurality of services. The registration unit 146 registers, for example, service design information 104 for a plurality of services.

[0074] The service specification information 102 may be any information capable of identifying a service. The service specification information 102 may include service identification information capable of identifying a service. The service identification information may be the name of the service or an ID assigned to the service. The service specification information 102 may include a URL of the service. The service specification 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 setting items for the service. The service design information 104 may include descriptions of the multiple setting items. The service design information 104 may include description rules for the multiple setting items. The service design information 104 may be, for example, an API document for the service. The storage unit 110 may store the multiple setting items of the service design information 104 in a vector database.

[0075] The query generation unit 148 generates a query to be 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. The query generation unit 148 may generate a query to cause the generation AI 400 to generate request information 120 that sets an instruction from the user 202 included in the user input 111 in the target service in a manner that allows the target service to accept the instruction, based on the user input 111, service specification information 102 of the target service, and service design information 104 acquired by the input acquisition unit 144. The query generation unit 148 generates a query including an instruction to generate request information 120 for setting the instruction included in the user input 111 in the target service in accordance with the content described in the service design information 104, for the service identified by the service specification information 102, for example.

[0076] When request information 120 is set for a target service, the query generation unit 148 may generate a query further based on the set request information 120. For example, in a case where the user 202 sets the request information 120 for the target service but the processing is not performed as desired and the request information 120 is revised, or in a case where the request information 120 generated by the generation AI 400 is set for the target service but the processing is not performed as desired and the request information 120 is revised, the query generation unit 148 generates a query further based on the set request information 120. For example, for a service identified by the service identification information 102, the query generation unit 148 generates a query including an instruction to generate request information 120 for setting the instruction included in the user input 111, in accordance with the content described in the service design information 104 and with reference to the current request information 120. For example, the information processing system 100 may generate a query for a service identified by the service identification information 102, including an instruction to generate request information 120 for setting an instruction included in the user input 111 by modifying the current request information 120 in accordance with the contents described in the service design information 104.

[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 check whether the request information 120 that meets their wishes has been generated.

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

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

[0080] The processing unit 154 executes various processes. The processing unit 154 causes a service to execute a process. 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 in accordance with the request information 120. For example, when the request information setting unit 152 sets request information 120 for multiple services included in the workflow 130 for multiple services, the processing unit 154 causes the multiple services included in the workflow 130 to execute a process in accordance with the request information 120 in order.

[0081] The request information 120 of the multiple services may be configured to execute cooperation between the services. For example, for a workflow 130 consisting of a first service, a second service, and a third service, the request information 120 of the first service may be configured to cause the first service to output a processing result and input it to the second service, and the request information 120 of the second service may be configured to cause the second service to output a 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 in accordance with the request information 120.

[0082] However, the request information 120 of a plurality of services may be configured to cooperate with each other via the information processing system 100. For example, for a workflow 130 including a first service, a second service, and a third service, the request information 120 of the first service may be configured to cause the first service to output a processing result and transmit it to the information processing system 100, and the request information 120 of the second service may be configured to cause the second service to output a processing result and transmit it to the information processing system 100 in accordance with information received from the information processing system 100. 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 in accordance with the request information 120, causes the second service to execute processing in accordance with the request information 120 in response to receiving the output from the first service, and causes the third service to execute processing in accordance with the request information 120 in response to receiving the 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 a service for which request information 120 is set by the request information setting unit 152 to execute processing in accordance with the request information 120. When generating a query for one of multiple services included in a workflow, if the response information acquisition unit 155 has acquired response information 123 from a service that precedes the one of the multiple services, the query generation unit 148 may generate the query based on the response information 123, the user input 111 for the one service, the service specification information 102 for the one service, and the service design information 104 for the one service. For example, the query generation unit 148 generates a query including an instruction to generate request information 120 for setting an instruction included in the user input 111 for a service specified by the service specification information 102, in accordance with the content described in the service design information 104 and taking into account the content of the response information 123, for the service specified by the service specification information 102.

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

[0085] When the input acquisition unit 144 acquires a WF user input including a description of a workflow desired by the user 202, the WF generation unit 156 may cause the query generation unit 148 to generate a WF query for generating the workflow desired by the user 202 based on the WF user input. The WF generation unit 156 may generate the workflow 130 using the generation AI 400 based on the WF query generated by the query generation unit 148.

[0086] The WF generation unit 156 may cause the generation AI 400 to select a service, arrange the service, and generate the request information 120. The WF generation unit 156 may cause the generation AI 400 to arrange the service and generate the request information 120 for multiple services selected by the user 202. The WF generation unit 156 may cause the generation AI 400 to generate the request information 120 for multiple services selected by the user 202 and whose arrangement has been determined.

[0087] When the generation AI 400 is caused to perform all of the service selection, service placement, and generation of the request information 120, the WF generation unit 156 causes the query generation unit 148 to generate a WF query for generating a workflow desired by the user 202 based on the WF user input 115. The query generation unit 148 generates a query including, for example, an instruction to generate a workflow that realizes the description of the workflow desired by the user 202, which is included in the WF user input 115. The query generation unit 148 may include the application specification information 112 and application design information 114 of multiple pre-registered services in the WF query. The WF generation unit 156 may cause the request information acquisition unit 150 to input the WF query generated by the query generation unit 148 to the generation AI 400 and acquire, from the generation AI 400, a workflow 130 that includes multiple services and in which request information 120 for the multiple services is set.

[0088] When the user 202 selects a service and causes the generation AI 400 to allocate the service and generate the request information 120, the WF generation unit 156 causes the query generation unit 148 to acquire the WF user input 115, the application specification information 112 of the multiple services specified by the user 202, and the application design information 114 of the multiple services, and to generate a query. The query generation unit 148 may generate a query including an instruction to generate a workflow configured by the multiple services specified by the acquired application specification information 112, in which the request information 120 of the multiple services is set according to the content included in the multiple application design information 114, in order to realize the description of the workflow desired by the user 202, which is included in the WF user input 115. The WF generation unit 156 causes the request information acquisition unit 150 to input the WF query to the generation AI 400 and acquire from the generation AI 400 a workflow 130 including the multiple services and in which the request information 120 of the multiple services is set.

[0089] When the user 202 selects and arranges services and causes the generation AI 400 to generate request information 120, the WF generation unit 156 causes the query generation unit 148 to acquire the WF user input 115, the application specification information 112 of multiple services specified by the user 202, the application design information 114 of the multiple services, and the arrangement information of the multiple services, and generates a query. The query generation unit 148 generates a query including an instruction to generate a workflow in which the request information 120 of the multiple services is set according to the content included in the application design information 114, so as to realize the description of the workflow desired by the user 202 included in the WF user input 115. The WF generation unit 156 causes the request information acquisition unit 150 to input the WF query to the generation AI 400 and acquire from the generation AI 400 a workflow 130 that includes multiple services and in which the request information 120 of the multiple services is set.

[0090] 9 schematically illustrates an example of the hardware configuration of a computer 1200 that functions as the information processing system 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or can cause the computer 1200 to perform operations associated with the apparatus according to the present embodiment or one or more "parts," and / or can cause the computer 1200 to perform a process according to the present embodiment or steps of the process. Such a program can be executed by the CPU 1212 to cause the computer 1200 to perform 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, a 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 communications 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, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. The computer 1200 also includes a ROM 1230 and legacy input / output units such as a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0092] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphics controller itself, and causes the image data to be 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 therein a boot program or the like that is executed by the computer 1200 upon activation, and / or programs that depend on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0095] The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and causes cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing operations or processing of information in accordance with the use of the computer 1200.

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

[0097] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and may perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data 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 may undergo information processing. The CPU 1212 may perform various types of processing on data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored on the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

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

[0100] The blocks in the flowcharts and block diagrams in the present embodiments may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, including integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), including AND, OR, XOR, NAND, NOR, 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 are executed by an appropriate device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. 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 disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, etc.

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

[0103] Computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or another programmable data processing device, or a programmable circuit, either locally or via a local area network (LAN), a wide area network (WAN) such as the Internet, so that the processor of the programmable data processing device, such as a computer, or the programmable circuit executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Here, the computer may be a personal computer (PC), a tablet computer, a smartphone, a workstation, a server computer, a general-purpose computer, a special-purpose computer, or the like, or may 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 broad definition of computers. In a distributed computing system, multiple computers collectively execute a program by each executing a portion of the program and passing data between the computers as needed during program execution.

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

[0105] By using the invention related to this embodiment, it is possible to assist users in setting the request information necessary to generate a workflow that links the services they use in their work, thereby contributing to the achievement of Goal 9 of the Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable industrialization, and promote innovation and resilience."

[0106] Although the present invention has been described above using the 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 and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0107] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order. [Explanation of symbols]

[0108] 20 network, 100 information processing system, 102 service specific information, 103 service description information, 104 service design information, 110 memory unit, 111 user input, 112 application specific information, 114 application design information, 115 WF user input, 120, 121 request information, 123 response information, 130 workflow, 131 placement 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 graphic controller, 1218 Display device, 1220 input / output controller, 1222 communication interface, 1224 storage device, 1230 ROM, 1240 input / output chip

Claims

1. an input acquisition unit that acquires a user input including a user instruction for a service; a query generation unit that generates a query to cause a generation AI to generate request information that is set in the service in a manner that allows the service to accept the instruction, based on the user input, service specification information that can specify the service, and service design information of the service; and a request information acquisition unit that inputs the query to the generation AI and acquires the request information output from the generation AI; Equipped with When request information is set for the service, the query generation unit generates the query for the service identified by the service specification information, in accordance with the contents described in the service design information, with reference to the current request information, including an instruction to generate the request information for setting the instructions included in the user input.

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

3. 2. The information processing system according to claim 1, wherein the service specification information includes service identification information capable of identifying the service, a URL of the service, and service description information describing the service including at least one of a purpose, a type, and a function of the service.

4. the service is SaaS; 2. The information processing system according to claim 1, wherein the request information includes at least one of method information, header information, body information, and a request URL for making an HTTP request to the service.

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

6. the service design information includes a plurality of setting items for the service; the information processing system includes a storage unit that stores the plurality of setting items in a vector database; 2. The information processing system according to claim 1, wherein the query generation unit generates the query based on the service design information including the plurality of setting items stored in the storage unit as a vector database, the user input, and the service specification information.

7. the input acquisition unit acquires the user input for a service included in a workflow configured by sequentially arranging a plurality of services; 7. The information processing system of claim 1, wherein when generating the query for one of the plurality of services included in the workflow, if response information from a service that precedes the one of the plurality of services has been acquired by the response information acquisition unit, the query generation unit generates the query for the one service including an instruction to generate request information for setting instructions included in the user input for the one service, taking into account the content of the response information, in accordance with the content described in the service design information of the one service.

8. the input acquisition unit acquires a WF user input including a description of a workflow desired by a user; the query generation unit generates a WF query including service specification information and service design information of a plurality of pre-registered services and an instruction to generate a workflow in which a plurality of services are sequentially arranged to realize a workflow desired by the user included in the WF user input; The information processing system includes: a WF generation unit that generates the workflow using the generation AI based on the WF query, and causes the request information acquisition unit to input the WF query generated by the query generation unit to the generation AI and acquire the workflow from the generation AI; The information processing system according to claim 1 , comprising:

9. An information processing system, an input acquisition unit that acquires a user input including a user instruction for a service; a query generation unit that generates a query to cause a generation AI to generate request information that is set in the service in a manner that allows the service to accept the instruction, based on the user input, service specification information that can specify the service, and service design information of the service; and a request information acquisition unit that inputs the query to the generation AI and acquires the request information output from the generation AI; Equipped with the input acquisition unit acquires a WF user input including a description of a workflow desired by a user; the query generation unit generates a WF query including service specification information and service design information of a plurality of pre-registered services and an instruction to generate a workflow in which a plurality of services are sequentially arranged to realize a workflow desired by the user included in the WF user input; The information processing system includes: The information processing system includes a WF generation unit that inputs the WF query generated by the query generation unit to the generation AI in the request information acquisition unit and causes the generation AI to acquire a workflow.

10. A program for causing a computer to function as the information processing system according to any one of claims 1 to 6 and 9.

11. 1. A computer-implemented information processing method, comprising: a user input acquisition stage for acquiring user input including instructions by a user for a service; a query generation step of generating a query to cause a generation AI to generate request information to set in the service in a manner that the service can accept the instruction, based on the user input, service specification information that can specify the service, and service design information of the service; a request information acquisition step of inputting the query to the generating AI and acquiring the request information output from the generating AI; Equipped with The query generation step generates, when request information is set for the service, the query including an instruction to generate the request information for setting the instruction included in the user input, in accordance with the contents described in the service design information and with reference to the current request information, for the service identified by the service specification information.

12. An information processing method implemented by a computer, comprising: a user input acquisition stage for acquiring user input including instructions by a user for a service; a query generation step of generating a query to cause a generation AI to generate request information to set in the service in a manner that the service can accept the instruction, based on the user input, service specification information that can specify the service, and service design information of the service; a request information acquisition step of inputting the query to the generating AI and acquiring the request information output from the generating AI; Equipped with a WF user input acquisition step of acquiring a WF user input including a description of a workflow desired by a user; a WF query generation step of generating a WF query including service specification information and service design information of a plurality of pre-registered services and an instruction to generate a workflow in which a plurality of services are sequentially arranged to realize a workflow desired by the user included in the WF user input; a WF generating step of inputting the WF query generated in the WF query generating step into the generating AI and acquiring a workflow from the generating AI; The information processing method further comprises:

Images