Information processing system, program, and information processing method

Abstract

An information processing system, a program, and an information processing method are provided that execute a data search using graph data that represents configuration information included in a search prompt. [Solution] In an information processing system in which an application platform, an information processing device, a database, and a communication terminal communicate via a network, the information processing device includes an information storage unit that stores configuration information indicating the configuration of graph data consisting of multiple nodes and edges connecting two of the multiple nodes, an acquisition unit that acquires a data search query, a generation unit that generates a search prompt for performing a data search including the query and the configuration information of the graph data, and an output unit that outputs the search prompt to a storage function that stores the graph data used for the data search, and the acquisition unit acquires the search results of the data search from the storage function.

Description

[Technical Field]

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

[0002] Patent Document 1 describes a technology that can appropriately search for deployment plans for microservices in multiple base systems. [Prior art document] [Patent documents] [Patent Document 1] JP 2023-135792 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 information storage unit that stores configuration information indicating a configuration of graph data composed of a plurality of nodes and edges connecting two of the plurality of nodes. The information processing system may include an acquisition unit that acquires a data search query. The information processing system may include a generation unit that generates a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data. The information processing system may include an output unit that outputs the search prompt to a storage function that stores the graph data used in the data search. The acquisition unit may acquire search results of the data search from the storage function.

[0004] In the information processing system, the information storage unit may store the configuration information of the graph data generated based on a plurality of structured data.

[0005] In any of the information processing systems, the information storage unit may store the configuration information of the graph data generated based on the plurality of structured data corresponding to log data of an application executed on an application platform.

[0006] Any of the information processing systems may further include a selection unit that selects the configuration information of the graph data to be used for the data search from the configuration information of multiple graph data based on the query and the configuration information of the multiple graph data stored in the information storage unit, and the generation unit may generate the search prompt for performing the data search, including the query and the configuration information of the graph data selected by the selection unit.

[0007] In any of the information processing systems, the selection unit may select the configuration information of the graph data to be used for the data search based on a processing result obtained by performing natural language processing (NLP) on the query.

[0008] Any of the information processing systems may further include a determination unit that determines whether or not there are multiple pieces of graph data that can be used for the data search, based on the query and the configuration information of the multiple pieces of graph data, and when the determination unit determines that there are multiple pieces of graph data that can be used for the data search, the selection unit may preferentially select, from the configuration information of the multiple pieces of graph data that can be used for the data search, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search.

[0009] Any of the information processing systems may further include a learning data storage unit that stores learning data including a data search query, search data indicating graph data used in a data search to answer the query, and search time data indicating a search time for the data search; and a model generation unit that generates, by machine learning, a selection model using the plurality of learning data stored in the learning data storage unit as teacher data, from the data search query, which selects configuration information of graph data that can execute a data search to answer the query in a shorter time, and the selection unit may use the selection model to select, from the query, the configuration information of the graph data that can execute the data search in a shorter time.

[0010] In any of the information processing systems, the information storage unit may further store configuration information indicating a configuration of the structured data, and the information processing system may further include a determination unit that determines whether or not the data search can be performed using the structured data based on the query and the configuration information of the structured data, and the generation unit may generate a search prompt for performing the data search, including the query and the configuration information of the structured data, when the determination unit determines that the data search can be performed using the structured data, and when the determination unit determines that the data search cannot be performed using the structured data, and the configuration information of the graph data, and when the generation unit generates the search prompt including the query and the configuration information of the structured data, the output unit may output the search prompt including the query and the configuration information of the structured data to a storage function that stores the structured data to be used for the data search, and when the generation unit generates the search prompt including the query and the configuration information of the graph data, the output unit may output the search prompt including the query and the configuration information of the graph data to the storage function that stores the graph data to be used for the data search.

[0011] In any of the information processing systems, the generation unit may further generate an answer generation prompt that generates an answer to the query based on the query and the search results, the output unit may output the answer generation prompt to a conversion function that converts a programming language into a natural language, and the acquisition unit may acquire the search results expressed in natural language from the conversion function as an answer to the query.

[0012] In any of the information processing systems, the output unit may output the search prompt and the answer generation prompt to a generation AI equipped with the storage function and the conversion function.

[0013] In any of the information processing systems, the output section may output the answer to the query.

[0014] According to one embodiment of the present invention, a program is provided for causing an information processing system that stores configuration information indicating the configuration of graph data consisting of a plurality of nodes and edges connecting two of the plurality of nodes to execute the following steps: a query acquisition step for acquiring a data search query; a generation step for generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data; an output step for outputting the search prompt to a storage function that stores the graph data used in the data search; and a search result acquisition step for acquiring search results of the data search from the storage function.

[0015] According to one embodiment of the present invention, there is provided an information processing method executed by an information processing system that stores configuration information indicating a configuration of graph data consisting of a plurality of nodes and edges connecting two of the plurality of nodes. The information processing method may include a query acquisition step of acquiring a query for a data search. The information processing method may include a generation step of generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data. The information processing method may include an output step of outputting the search prompt to a storage function that stores the graph data used in the data search. The information processing method may include a search result acquisition step of acquiring search results of the data search from the storage function.

[0016] 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]

[0017] [Figure 1] An example of a system 10 is shown schematically. [Figure 2] 10 is an explanatory diagram for explaining an example of data stored in a storage function 240. FIG. [Figure 3] FIG. 2 is an explanatory diagram for explaining an example of graph data 280. [Figure 4] FIG. 2 is an explanatory diagram illustrating an example of a processing flow of the information processing device 300. [Figure 5] FIG. 10 is an explanatory diagram illustrating another example of the processing flow of the information processing device 300. [Figure 6] 2 shows an example of a functional configuration of an information processing device 300. [Figure 7] An example of the hardware configuration of a computer 1200 that functions as the application platform 200 or the information processing device 300 is shown in schematic form. DETAILED DESCRIPTION OF THE INVENTION

[0018] Currently, research and development of conversational AI (artificial intelligence) using natural language processing and large language models (LLMs) is actively underway. Conversational AI enables natural conversation between humans and computers. Current trends in conversational AI research and development have led to a growing need for efficient use of accumulated data through the use of conversational AI. Similarly to the research and development of conversational AI, research and development of application platforms is also currently underway. Application platforms provide an environment that serves as the foundation for applications. Trends in research and development of conversational AI and application platforms have led to a new need for efficient use of log data from applications on application platforms through the use of conversational AI. The system according to this embodiment employs a mechanism for performing data search using graph data consisting of, for example, multiple nodes and edges connecting two of the multiple nodes. For example, the system according to this embodiment generates a prompt for performing a data search, including a data search query and configuration information indicating the configuration of the graph data, and performs a data search using the graph data based on the prompt. In particular, the system according to this embodiment further employs a mechanism for generating graph data in advance based on multiple structured data corresponding to the log data of an application executed on an application platform, or a mechanism for outputting the prompt to the conversational AI, thereby causing the conversational AI to perform a data search using the graph data.

[0019] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit 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. In the drawings, the same reference numerals are used to designate the same or similar parts, and redundant explanations may be omitted.

[0020] 1 schematically illustrates an example of a system 10. The system 10 may include an application platform 200. The system 10 may include an information processing device 300. The system 10 may include a database 400. The system 10 may be an example of an information processing system.

[0021] The communication terminal 100 may be any communication terminal that can access the network 20. For example, the communication terminal 100 may be a mobile phone such as a smartphone, a tablet terminal, a wearable terminal, or the like. The communication terminal 100 may also be a PC (Personal Computer). FIG. 1 shows an example in which the communication terminal 100 is a smartphone.

[0022] The network 20 may include a core network provided by a telecommunications carrier. The core network may conform to, for example, a 5G (5th Generation) communication system. The core network may conform to a 6G (6th Generation) communication system or later mobile communication system. The core network may conform to a 3G (3rd Generation) communication system. The core network may conform to an LTE (Long Term Evolution) communication system. The network 20 may include the Internet.

[0023] The application platform 200 may provide an underlying environment for the applications 220. For example, the application platform 200 provides an underlying environment for executing the applications 220. For example, one or more applications 220 run on the application platform 200. For example, the application platform 200 provides an underlying environment for developing the applications 220. For example, one or more applications 220 are developed on the application platform 200.

[0024] The application 220 may be any application that can be executed or developed on the application platform 200. The application 220 may be a free application or a paid application. Note that an application may be referred to as an app.

[0025] The application 220 is, for example, a mobile application, a PC native application, or a web application.

[0026] A user 150 of the communication terminal 100, for example, uses the communication terminal 100 to execute the application 220 on the application platform 200. Note that the communication terminal 100 may be an example of a front end, and an application installed on the communication terminal 100 in order for the communication terminal 100 to execute the application 220 on the application platform 200 may be an example of a front end application.

[0027] The communication terminal 100 communicates with the database 400, the server, etc., by executing the application 220 on the application platform 200, for example. In this case, the communication terminal 100 communicates with the database 400, the server, etc., via the application platform 200. The database 400, the server, etc. may be an example of a backend.

[0028] The application platform 200 acquires, for example, log data of the application 220 executed by the communication terminal 100 on the application platform 200. The application platform 200 collects, for example, log data of the application 220 executed by each of the multiple communication terminals 100 on the application platform 200.

[0029] The application platform 200 stores, for example, log data of the application 220 executed on the application platform 200 in the storage function 240. The application platform 200 stores, for example, log data of the application 220 in the storage function 240 for each application 220 executed on the application platform 200.

[0030] The log data includes, for example, user data that records the user 150 of the communication terminal 100 who executed the application 220 on the application platform 200. The log data includes, for example, model data that records the model of the communication terminal 100. The log data includes, for example, OS data that records the OS (Operating System) of the communication terminal 100. The log data includes, for example, OS version data that records the OS version of the communication terminal 100. The log data includes, for example, app name data that records the name of the application 220. The log data includes, for example, app version data that records the version of the application 220. The log data includes, for example, execution time data that records the execution time of the application 220. The log data includes, for example, operation history data that records the operation history accepted by the communication terminal 100. The log data includes, for example, communication target data that records the communication target of the communication terminal 100 in API (Application Programming Interface) communication of the application 220. The communication target may be a database 400, a server, etc. The log data includes, for example, channel data that records the channel used for API communication of the application 220. The log data includes, for example, communication time data that records the communication time of the API communication of the application 220. The log data includes, for example, environment data that records the execution environment of the application 220. The execution environment of the application 220 may be the application platform 200.

[0031] The storage function 240 may store various types of data. The storage function 240 is, for example, a database.

[0032] The storage function 240 stores, for example, log data of the application 220 executed on the application platform 200. The storage function 240 stores, for example, structured data corresponding to the log data of the application 220.

[0033] The structured data may be data that has been formatted into a predetermined structure. Here, a table structure is exemplified as an example of the predetermined structure.

[0034] The structured data corresponding to the log data of the application 220 is, for example, structured data for each record item of the log data of the application 220. The record items of the log data include, for example, the user 150 of the communication terminal 100 who executed the application 220. The record items of the log data include, for example, the model of the communication terminal 100. The record items of the log data include, for example, the OS of the communication terminal 100. The record items of the log data include, for example, the version of the OS of the communication terminal 100. The record items of the log data include, for example, the name of the application 220. The record items of the log data include, for example, the version of the application 220. The record items of the log data include, for example, the execution time of the application 220. The record items of the log data include, for example, the operation history accepted by the communication terminal 100. The record items of the log data include, for example, the communication target of the communication terminal 100 in the API communication of the application 220. The record items of the log data include, for example, the channel used for the API communication of the application 220. The log data record items include, for example, the communication time of the API communication of the application 220. The log data record items include, for example, the execution environment of the application 220.

[0035] The application platform 200 includes, for example, a generation AI 250. The generation AI 250 may generate content. The generation AI 250 generates the content using, for example, computational resources such as a central processing unit (CPU) or a graphics processing unit (GPU) installed in the application platform 200. Here, text data, image data, video data, and audio data are exemplified as examples of content to be generated by the generation AI 250.

[0036] The generated AI 250 is, for example, a conversational AI. Here, a chatbot and a virtual assistant are exemplified as examples of the conversational AI.

[0037] The generation AI 250 includes, for example, a conversion function 290. The conversion function 290 may perform conversion processing for various languages.

[0038] The conversion function 290 performs, for example, a conversion process between a program language and a natural language. The conversion function 290 performs, for example, a conversion process between a program language and a natural language based on a processing result of natural language processing performed on a conversion target. Here, Japanese, English, Chinese, Spanish, French, and German are exemplified as examples of natural languages.

[0039] The generation AI 250 may further include a storage function 240. That is, the generation AI 250 may include the storage function 240 and the conversion function 290.

[0040] The application platform 200 has, for example, a data generation function. The application platform 200 generates, for example, graph data. The application platform 200 may store the generated graph data in the storage function 240.

[0041] The application platform 200 generates graph data based on, for example, a plurality of pieces of structured data stored in the storage function 240. The application platform 200 generates graph data based on, for example, the plurality of pieces of structured data corresponding to log data of the application 220 executed on the application platform 200.

[0042] The application platform 200 generates graph data by, for example, executing batch processing on the plurality of structured data. Here, examples of execution intervals for batch processing are 1 minute, 5 minutes, 10 minutes, 30 minutes, 1 hour, 6 hours, 12 hours, and 24 hours.

[0043] Graph data may be data that is composed of a plurality of nodes and edges that connect two of the plurality of nodes, and may further be data that is composed of properties that represent attributes of the nodes.

[0044] The graph represented by the graph data may be, for example, an undirected graph. An undirected graph is a graph in which the edges that make up the graph have no direction. The graph represented by the graph data may be, for example, a directed graph. A directed graph is a graph in which the edges that make up the graph have a direction.

[0045] The application platform 200 has, for example, a data search function. The application platform 200 performs a data search using, for example, structured data stored in the storage function 240. The application platform 200 performs a data search using, for example, graph data stored in the storage function 240.

[0046] The application platform 200 has, for example, a data analysis function. The application platform 200 performs data analysis using, for example, structured data stored in the storage function 240. The application platform 200 performs data analysis using, for example, graph data stored in the storage function 240.

[0047] The application platform 200 may perform data analysis, for example, for the purpose of maintaining IT governance. IT governance may refer to a framework for aligning an organization's IT strategy with its business strategy and effectively managing and operating its IT resources. The application platform 200 may perform data analysis, for example, for the purpose of improving application insights. Application insights may refer to monitoring application performance and usage. The application platform 200 may perform data analysis, for example, for the purpose of enhancing application engagement. Application engagement may refer to the relationship or connection formed between an application and an application user.

[0048] For example, generation AI 250 functions as at least one of a data generation function, a data retrieval function, and a data analysis function of application platform 200. For example, storage function 240 functions as at least one of a data retrieval function and a data analysis function of application platform 200.

[0049] The application platform 200 has, for example, a communication function and communicates via the network 20, for example.

[0050] The application platform 200 communicates with, for example, the communication terminal 100. The application platform 200 communicates with, for example, the information processing device 300. The application platform 200 communicates with, for example, the database 400.

[0051] The application platform 200 transmits, for example, various types of data. The application platform 200 transmits, for example, various types of data stored in the storage function 240.

[0052] The application platform 200 transmits, for example, configuration information indicating the configuration of the structured data stored in the storage function 240. The configuration information of the structured data includes, for example, record item information indicating the record items of the log data of the application 220 executed on the application platform 200. The configuration information of the structured data may include any other information related to the configuration of the structured data.

[0053] The application platform 200 transmits, for example, configuration information indicating the configuration of graph data stored in the storage function 240. The configuration information of the graph data includes, for example, node count information indicating the number of nodes that make up the graph data. The configuration information of the graph data includes, for example, relationship information that indicates the relationship between two nodes connected by an edge that makes up the graph data. The configuration information of the graph data includes, for example, direction information that indicates the direction of the edge that makes up the graph data. The configuration information of the graph data includes, for example, property information that indicates properties that represent attributes of the nodes that make up the graph data. The configuration information of the graph data includes, for example, structured data information that indicates multiple structured data used to generate the graph data. The configuration information of the graph data may include any other information related to the configuration of the graph data.

[0054] For example, the application platform 200 receives various types of data and may store the received various types of data in the storage function 240.

[0055] The information processing device 300 executes various information processes based on various information stored in the information processing device 300, for example.

[0056] The database 400 stores various data and may be an example of a storage function.

[0057] The database 400 stores, for example, various data related to the application 220 executed on the application platform 200. For example, if the application 220 is an SFA (Sales Force Automation) application, the database 400 stores business history data, product sales history data, etc. The product may be a commodity or a service.

[0058] The database 400 stores, for example, structured data. The database 400 stores, for example, graph data.

[0059] The database 400 provides, for example, various data stored in the device itself. The database 400 provides, for example, various data stored in the device itself by transmitting the various data via the network 20.

[0060] The database 400 provides, for example, various data to the application platform 200. The database 400 provides, for example, various data to the information processing device 300.

[0061] The database 400 provides, for example, structured data. The database 400 provides, for example, configuration information of the structured data. The database 400 provides, for example, graph data. The database 400 provides, for example, configuration information of the graph data.

[0062] The application platform 200 may use various data provided to the database 400. The information processing device 300 may use various data provided to the database 400.

[0063] Here, an example will be described in which the user 150 searches for data using the communication terminal 100. Here, the search is performed using graph data stored in the storage function 240 of the application platform 200.

[0064] The communication terminal 100 may accept input of a data search query from the user 150. The query may be expressed in natural language.

[0065] The communication terminal 100 may provide the received query to the information processing device 300. The communication terminal 100 provides the query to the information processing device 300 by, for example, transmitting the query to the information processing device 300 via the network 20.

[0066] Based on the provided query, the information processing device 300 may generate a search prompt for executing the data search to answer the query. The search prompt may include, for example, the query and configuration information of the graph data stored in the information processing device 300.

[0067] The information processing device 300 may output the generated search prompt to the application platform 200. The information processing device 300 outputs the search prompt to the application platform 200 by, for example, transmitting the search prompt to the application platform 200 via the network 20.

[0068] The generation AI 250 may generate search results for the data search based on the input search prompt. For example, the generation AI 250 generates search results for the data search by executing the data search using graph data stored in the storage function 240 based on the search prompt. The search results for the data search based on the search prompt may be expressed in a programming language. Note that the search results for the data search expressed in a programming language may be an example of content to be generated by the generation AI 250.

[0069] The generation AI 250 may output the generated search results of the data search to the information processing device 300. The generation AI 250 outputs the search results of the data search to the information processing device 300, for example, by transmitting the search results of the data search to the information processing device 300 via the network 20.

[0070] The information processing device 300 may generate an answer generation prompt for generating an answer to the query. The information processing device 300 generates the answer generation prompt based on, for example, the query provided by the communication terminal 100 and the search results of the data search output from the application platform 200.

[0071] The answer generation prompt includes, for example, specified language information that specifies the natural language in which the answer to the query is expressed. Note that the natural language in which the answer to the query is expressed may be the same natural language as the natural language in which the query is expressed, or may be a natural language different from the natural language in which the query is expressed. Furthermore, multiple natural languages ​​may be specified as the natural languages ​​in which the answer to the query is expressed. The answer generation prompt includes, for example, the search results of the data search expressed in a programming language.

[0072] The information processing device 300 may output the generated answer generation prompt to the application platform 200. The information processing device 300 may output the answer generation prompt to the application platform 200 in the same manner as when outputting a search prompt to the application platform 200.

[0073] The generation AI 250 may convert the search results of the data search from a programming language to a natural language using the conversion function 290. For example, the generation AI 250 converts the search results of the data search from a programming language to a natural language using the conversion function 290 based on an input answer generation prompt. Note that the search results of the data search expressed in a natural language may be an example of content to be generated by the generation AI 250.

[0074] The generation AI 250 may output the search results of the data search expressed in a natural language to the information processing device 300. The generation AI 250 may output the search results of the data search expressed in a natural language to the information processing device 300 in the same way as when the search results of the data search expressed in a programming language are output to the information processing device 300.

[0075] The information processing device 300 may output the search results of the data search expressed in natural language as a response to the query to the communication terminal 100. The information processing device 300 outputs the response to the query to the communication terminal 100, for example, by transmitting the response to the query to the communication terminal 100 via the network 20. Thereafter, the user 150 may check the response to the query using the communication terminal 100.

[0076] 1 shows an example in which the application platform 200 and the information processing device 300 are different devices. The application platform 200 and the information processing device 300 may be the same device. That is, the application platform 200 and the information processing device 300 may be an integrated device.

[0077] 1 illustrates an example in which the application platform 200 stores structured data and graph data in the storage function 240. The application platform 200 may store at least one of the structured data and the graph data in an external device such as a database 400. For example, the application platform 200 stores at least one of the structured data and the graph data in the external device by transmitting at least one of the structured data and the graph data to the external device via the network 20. In this case, the external device may have functions similar to the data search function and the data analysis function of the application platform 200.

[0078] When generating search results for the data search based on a search prompt, the generation AI 250 may generate search results for the data search expressed in a natural language. In this case, the search prompt may further include specified language information.

[0079] As mentioned above, research and development of generative AI, such as conversational AI, and application platforms is actively underway. This active research and development of generative AI and application platforms is creating a growing need for the efficient use of large-scale, complex data sets, such as big data. More specifically, when launching a business project, there is a particularly growing need for the efficient use of such data sets.

[0080] Here, an example of a current method for launching a business project using the dataset will be described. For example, when formulating project guidelines, project members of the project request a data analyst to analyze the dataset. The data analyst, upon accepting the request, analyzes the dataset and reports the analysis results to the project members. The project members formulate project guidelines based on the analysis results reported by the data analyst. Thereafter, when a certain amount of the dataset has been newly accumulated, the project members request the data analyst to perform additional analysis of the dataset. The project members revise the project guidelines based on the analysis results of the additional analysis reported by the data analyst. In this way, the project members progress the project by requesting a data analyst to analyze the dataset when a certain amount of the dataset has been accumulated.

[0081] In the current method for launching a business project using the aforementioned dataset, project members must request a data analyst to analyze the dataset once a certain amount of the dataset has been accumulated. The analysis of the dataset by the data analyst requires significant financial and time costs. Furthermore, the quality of the analysis results of the dataset by the data analyst depends heavily on the ability and experience of the data analyst.

[0082] For the above reasons, it is desirable to be able to use the dataset efficiently. More specifically, it is particularly desirable to be able to use the dataset efficiently when launching a business project using the dataset.

[0083] In contrast, according to the system 10 of this embodiment, when the information processing device 300 receives a data search query, it generates a search prompt including the query and configuration information of the graph data used in the data search, and outputs the search prompt to the storage function 240 that stores the graph data, thereby obtaining search results for the data search from the storage function 240. For example, the graph data is generated based on multiple structured data corresponding to log data of the application 220 executed on the application platform 200. Note that the graph data may be an example of a large-scale, complex dataset.

[0084] By outputting a search prompt to the storage function 240 that includes not only the query but also configuration information of the graph data used in the data search, the storage function 240 can appropriately perform a data search using the dataset without the intervention of a human, such as a data analyst. This allows the system 10 according to this embodiment to contribute to the efficient use of the dataset. Furthermore, according to the system 10 according to this embodiment, the information processing device 300 further generates an answer generation prompt based on the query and the search results of the data search, and outputs the answer generation prompt to the conversion function 290 to obtain the search results of the data search expressed in natural language as an answer to the query. The information processing device 300 then outputs the search results of the data search expressed in natural language as an answer to the query. By outputting the search results of the data search expressed in natural language as an answer to the query, the system 10 according to this embodiment can output an answer to the query in a manner that is more easily understandable to the user. Additionally, according to the system 10 according to this embodiment, the generation AI 250 equipped with the storage function 240 and the conversion function 290 performs the data search and language conversion of the search results of the data search. This improves the accuracy of the generative model of the generation AI 250, allowing the system 10 according to this embodiment to achieve more efficient use of the dataset. Furthermore, if the generation AI 250 is an interactive AI, the user 150 can perform a detailed analysis of the dataset without the intervention of a human, such as a data analyst, by repeatedly searching the data while interacting with the generation AI 250. Therefore, the system 10 according to this embodiment can achieve a detailed analysis of the dataset with less economic and time costs. As a result, the system 10 according to this embodiment can contribute to the success of business projects.

[0085] 2 is an explanatory diagram illustrating an example of data stored in the storage function 240. Here, it is assumed that the structured data is data having a table structure, and the graph represented by the graph data is an undirected graph.

[0086] The upper diagram of Fig. 2 schematically shows an example of the storage function 240. As shown in the upper diagram of Fig. 2, the storage function 240 stores a plurality of structured data 270 and a plurality of graph data 280.

[0087] 2 is an explanatory diagram for explaining an example of generating graph data 280. Here, an example of generating graph data 280 by generation AI 250 will be mainly explained. Note that graph data 280 may be an example of content to be generated by generation AI 250.

[0088] The generation AI 250 generates graph data 280 based on, for example, a plurality of pieces of structured data 270. The generation AI 250 generates the graph data 280 by, for example, assigning a node to each piece of structured data 270 and connecting two nodes having a relationship among the plurality of pieces of structured data 270 with an edge.

[0089] The relationship between two nodes includes, for example, that the two nodes have a common characteristic. For example, that the rows of the two nodes have a common characteristic. For example, that the columns of the two nodes have a common characteristic.

[0090] The relationship between two nodes includes, for example, that the two nodes have corresponding features. The relationship between two nodes includes, for example, that the rows of the two nodes have corresponding features. The relationship between two nodes includes, for example, that the columns of the two nodes have corresponding features.

[0091] The generation AI 250 generates the graph data 280 by, for example, assigning a property representing an attribute of a node to each of the multiple nodes that make up the graph data 280. The attribute of a node is, for example, a record item of the log data of the application 220 executed on the application platform 200.

[0092] For example, if the structured data 270 is user data, the attribute of a node of the structured data 270 is the user 150 of the communication terminal 100 who executed the application 220. For example, if the structured data 270 is model data, the attribute of a node of the structured data 270 is the model of the communication terminal 100. For example, if the structured data 270 is OS data, the attribute of a node of the structured data 270 is the OS of the communication terminal 100. For example, if the structured data 270 is OS version data, the attribute of a node of the structured data 270 is the version of the OS of the communication terminal 100. For example, if the structured data 270 is application name data, the attribute of a node of the structured data 270 is the name of the application 220. For example, if the structured data 270 is application version data, the attribute of a node of the structured data 270 is the version of the application 220. For example, if the structured data 270 is execution time data, the attribute of a node in the structured data 270 is the execution time of the application 220. For example, if the structured data 270 is operation history data, the attribute of a node in the structured data 270 is the operation history accepted by the communication terminal 100. For example, if the structured data 270 is communication target data, the attribute of a node in the structured data 270 is the communication target of the communication terminal 100 in the API communication of the application 220. For example, if the structured data 270 is channel data, the attribute of a node in the structured data 270 is the channel used for the API communication of the application 220. For example, if the structured data 270 is communication time data, the attribute of a node in the structured data 270 is the communication time of the API communication of the application 220. For example, if the structured data 270 is environment data, the attribute of a node in the structured data 270 is the execution environment of the application 220.

[0093] 3 is an explanatory diagram illustrating an example of graph data 280. In the graph data 280 illustrated in FIG. 3, a node 282 for the property "User" is connected to a node 282 for the properties "Model" and "OS" by an edge 284, a node 282 for the property "Model" and "OS" is connected to a node 282 for the property "OS Ver." by an edge 284, a node 282 for the property "OS Ver." is connected to a node 282 for the property "App Ver." by an edge 284, a node 282 for the property "App Ver." is connected to a node 282 for the property "Channel" by an edge 284, a node 282 for the property "Channel" is connected to a node 282 for the property "Application Name" by an edge 284, and a node 282 for the property "Application Name" is connected to a node 282 for the property "Environment" by an edge 284. The graph represented by the graph data 280 illustrated in FIG. 3 is a directed graph. Here, an example in which the generation AI 250 executes a data search using the graph data 280 will be mainly described.

[0094] For example, the generation AI 250 performs natural language processing on a data search query included in the search prompt. Then, based on the processing result of the natural language processing performed on the query, the generation AI 250 performs the data search using graph data 280 whose structure is indicated by the structure information included in the search prompt. Note that the processing result of the natural language processing performed on the query may be an example of content to be generated by the generation AI 250.

[0095] For example, the generation AI 250 identifies a node 282 that is the start point of the data search and a node 282 that is the end point of the data search based on the processing result of executing natural language processing on the query. The generation AI 250 identifies the node 282 that is the start point of the data search and the node 282 that is the end point of the data search, for example, by extracting specific terms from the processing result of executing natural language processing on the query. Thereafter, the generation AI 250 executes the data search using the graph data 280 by transitioning from the node 282 that is the start point of the data search to the node 282 that is the end point of the data search in the graph data 280.

[0096] The node that is the starting point of the data search may be referred to as the start node. The node that is the end point of the data search may be referred to as the end node. Note that the specific term may be a term for identifying the start node and the end node.

[0097] 3 is an explanatory diagram illustrating an example in which, when a search prompt is input to the generation AI 250, the generation AI 250 executes a data search using the graph data 280. Here, the search prompt includes the query in natural language, such as "Please tell me the OS version of User A's communication device," and configuration information of the graph data 280.

[0098] In the example shown in the upper diagram of Figure 3, the generation AI 250 extracts the term "User A" and the term "OS Ver. of communication terminal" from the processing results of executing natural language processing on the query included in the search prompt, thereby determining that the node 282 of the property "User" is the start node and the node 282 of the property "OS Ver." is the end node. Then, the generation AI 250 searches for data indicating the OS Ver. of user A's communication terminal by transitioning from the node 282 of the property "User" to the node 282 of the properties "Model" and "OS," and from the node 282 of the properties "Model" and "OS" to the node 282 of the property "OS Ver." in the graph data 280.

[0099] The lower diagram in Figure 3 is an explanatory diagram illustrating another example in which, when a search prompt is input to the generation AI 250, the generation AI 250 executes a data search using the graph data 280. Here, the search prompt is assumed to include the query in natural language, "Please tell me the App Ver. of the most used application in OS Ver. 2.0," and configuration information of the graph data 280.

[0100] In the example shown in the lower diagram of Figure 3, the generation AI 250 extracts the terms "OS Ver." and "App Ver." from the processing results of natural language processing performed on the query included in the search prompt, thereby determining that node 282 for the property "OS Ver." is the start node and node 282 for the property "App Ver." is the end node. Then, the generation AI 250 transitions from node 282 for the property "OS Ver." to node 282 for the property "App Ver." in the graph data 280, thereby searching for data indicating the App Ver. of the most used application for OS Ver. 2.0.

[0101] 4 is an explanatory diagram illustrating an example of the flow of processing by the information processing device 300. Here, the description will be given assuming that the information processing device 300 is in a start state in which it has not yet acquired a query for data search.

[0102] In step (step may be abbreviated as S) 102, the information processing device 300 acquires a data search query. In S104, the information processing device 300 determines whether or not it is possible to execute a data search to answer the query acquired in S102 using the structured data 270 stored in the storage function 240 of the application platform 200. The information processing device 300 determines whether or not it is possible to execute the data search using the structured data 270, for example, based on the query and the configuration information of the structured data 270 stored in the information processing device 300. If the information processing device 300 determines that it is possible to execute the data search using the structured data 270, it proceeds to S106. If the information processing device 300 determines that it is not possible to execute the data search using the structured data 270, it proceeds to S108.

[0103] In S106, the information processing device 300 generates a search prompt including the query acquired in S102 and configuration information of the structured data 270. In S108, the information processing device 300 generates a search prompt including the query acquired in S102 and configuration information of the graph data 280.

[0104] In S110, the information processing device 300 outputs the generated search prompt to the application platform 200. For example, if the information processing device 300 determines in S104 that a data search for answering the query acquired in S102 can be performed using the structured data 270, the information processing device 300 outputs the search prompt generated in S106 to the application platform 200. In this case, the application platform 200 performs the data search using the structured data 270. On the other hand, if the information processing device 300 determines in S104 that the data search cannot be performed using the structured data 270, the information processing device 300 outputs the search prompt generated in S108 to the application platform 200. In this case, the application platform 200 performs the data search using the graph data 280.

[0105] In S112, the information processing device 300 acquires, from the application platform 200, the search results of a data search for responding to the query acquired in S102. For example, if a search prompt generated by the information processing device 300 in S106 is input to the application platform 200 in S110, the information processing device 300 acquires, from the application platform 200, the search results of the data search using the structured data 270. On the other hand, if a search prompt generated by the information processing device 300 in S108 is input to the application platform 200 in S110, the information processing device 300 acquires, from the application platform 200, the search results of the data search using the graph data 280. Thereafter, the processing of the information processing device 300 when acquiring the data search query ends.

[0106] A data search using graph data 280 is a more advanced data search than a data search using structured data 270. On the other hand, a data search using structured data 270 is a faster data search than a data search using graph data 280. Therefore, it is desirable to be able to realize an appropriate data search according to the search difficulty based on the respective characteristics of structured data 270 and graph data 280.

[0107] 4, when a data search for answering a query can be performed by using the structured data 270, the information processing device 300 causes the application platform 200 to perform the data search using the structured data 270, and when the data search cannot be performed by using the structured data 270, the information processing device 300 causes the application platform 200 to perform the data search using the graph data 280. As a result, when the search difficulty is low, a high-speed data search can be performed using the structured data 270, and when the search difficulty is high, an advanced data search can be performed using the graph data 280. Therefore, the system 10 shown in FIG. 4 can realize an appropriate data search according to the search difficulty based on the respective characteristics of the structured data and the graph data.

[0108] 5 is an explanatory diagram illustrating another example of the processing flow of the information processing device 300. Here, the description will be given assuming that the information processing device 300 is in a state where it has not yet acquired a data search query as a starting state. In the example of the processing flow of the information processing device 300 shown in FIG. 5, it is assumed that a data search is performed using graph data 280.

[0109] In S202, the information processing device 300 acquires a query for data search. In S204, the information processing device 300 executes natural language processing on the query acquired in S202.

[0110] In S206, the information processing device 300 selects, based on the processing result of the natural language processing executed in S204, configuration information of the graph data 280 to be used for data search for answering the query, from configuration information of the plurality of graph data 280 stored in the information processing device 300. In S208, the information processing device 300 generates a search prompt including the query acquired in S202 and the configuration information of the graph data 280 selected in S206. In S210, the information processing device 300 outputs the search prompt generated in S208 to the application platform 200.

[0111] At S212, the information processing device 300 acquires the search results of a data search for answering the query acquired at S202 from the application platform 200 to which the search prompt was input at S210. At S214, the information processing device 300 generates an answer generation prompt based on the query acquired at S202 and the search results of the data search acquired from the application platform 200 at S212. At S216, the information processing device 300 outputs the answer generation prompt generated at S214 to the application platform 200.

[0112] In S218, the information processing device 300 acquires an answer to the query acquired in S202 from the application platform 200 to which the answer generation prompt was input in S216. In S220, the information processing device 300 outputs the answer to the query acquired in S218. Thereafter, the processing of the information processing device 300 in the case where a data search query is acquired ends.

[0113] 6 schematically illustrates an example of the functional configuration of the information processing device 300. The information processing device 300 includes an information storage unit 302, an acquisition unit 304, a generation unit 306, a selection unit 308, an application platform 310, an output unit 312, a determination unit 314, a training data storage unit 316, a model generation unit 318, and a model storage unit 322. Note that it is not essential that the information processing device 300 includes all of these components.

[0114] The information storage unit 302 stores various types of information and is, for example, a database.

[0115] The acquisition unit 304 acquires various types of information. For example, the acquisition unit 304 acquires various types of information by receiving the various types of information via the network 20. For example, the acquisition unit 304 acquires various types of information by receiving the various types of information via the application platform 200. The acquisition unit 304 may acquire various types of information by an input unit included in the information processing device 300 accepting input of the various types of information from a user of the information processing device 300. The acquisition unit 304 may store the acquired various types of information in the information storage unit 302.

[0116] The acquisition unit 304 acquires various information from, for example, the communication terminal 100. The acquisition unit 304 acquires various information from, for example, the application platform 200. The acquisition unit 304 may acquire various information from other external devices such as a database 400.

[0117] The acquisition unit 304 acquires, for example, configuration information of the structured data. The acquisition unit 304 acquires, for example, configuration information of the structured data 270 stored in the storage function 240 of the application platform 200. The acquisition unit 304 acquires, for example, configuration information of the structured data stored in the database 400.

[0118] The acquisition unit 304 acquires, for example, configuration information of graph data. The acquisition unit 304 acquires, for example, configuration information of graph data 280 stored in the storage function 240 of the application platform 200. The acquisition unit 304 acquires, for example, configuration information of graph data stored in the database 400.

[0119] The configuration information of the structured data stored in the information storage unit 302 may be an example of the configuration information stored in the information storage unit 302. The configuration information of the graph data stored in the information storage unit 302 may be an example of the configuration information stored in the information storage unit 302.

[0120] The acquisition unit 304 acquires, for example, a data search query. The acquisition unit 304 acquires the query, for example, from the communication terminal 100. The acquisition unit 304 acquires the query, for example, from the application platform 200. The acquisition unit 304 may acquire the query by, for example, an input unit included in the information processing device 300 accepting input of the query.

[0121] The generation unit 306 generates various prompts. For example, the generation unit 306 generates various prompts based on various information stored in the information storage unit 302. For example, the generation unit 306 generates various prompts based on various information acquired by the acquisition unit 304.

[0122] The generation unit 306 generates, for example, a search prompt. The generation unit 306 generates, for example, a search prompt including a data search query acquired by the acquisition unit 304 and configuration information of structured data stored in the information storage unit 302. The generation unit 306 generates, for example, a search prompt including the query and configuration information of graph data stored in the information storage unit 302. The generation unit 306 generates, for example, a search prompt further including specified language information.

[0123] The selection unit 308 executes various selection processes. For example, when the acquisition unit 304 acquires a data search query, the selection unit 308 executes various selection processes.

[0124] The selection unit 308 executes various selection processes based on, for example, various pieces of information stored in the information storage unit 302. The generation unit 306 executes various selection processes based on, for example, various pieces of information acquired by the acquisition unit 304.

[0125] The selection unit 308 selects configuration information to be used for the data search, for example, based on the query and a plurality of pieces of configuration information stored in the information storage unit 302. The selection unit 308 selects configuration information to be used for the data search, for example, based on the processing result of executing natural language processing on the query.

[0126] For example, the selection unit 308 extracts a specific term from the processing result and identifies a search target for the data search from the extracted specific term. Next, the selection unit 308 identifies data that can be searched for the search target for the data search based on the multiple pieces of configuration information. Thereafter, the selection unit 308 selects configuration information of data that can be searched for the search target for the data search as configuration information to be used for the data search. Note that the specific term may be a term for identifying the search target for the data search.

[0127] The selection unit 308 selects, for example, configuration information of structured data to be used for the data search from among the configuration information of multiple pieces of structured data stored in the information storage unit 302. The selection unit 308 selects, for example, configuration information of graph data to be used for the data search from among the configuration information of multiple pieces of graph data stored in the information storage unit 302. The generation unit 306 may generate a search prompt including the configuration information to be used for the data search selected by the selection unit 308.

[0128] The output unit 312 outputs various types of information. The output unit 312 outputs various types of information, for example, by transmitting the various types of information. The output unit 312 outputs various types of information, for example, by transmitting the various types of information via the network 20. The output unit 312 outputs various types of information, for example, by transmitting the various types of information via the application platform 200.

[0129] The output unit 312 outputs, for example, various types of information to the communication terminal 100. The output unit 312 outputs, for example, various types of information to the application platform 200. The output unit 312 outputs, for example, various types of information to other external devices such as the database 400.

[0130] The output unit 312 may output the various information by displaying the various information on a display included in the information processing device 300. The output unit 312 may output the various information by outputting the various information as audio to a speaker included in the information processing device 300.

[0131] The output unit 312 outputs, for example, the search prompt generated by the generation unit 306. The output unit 312 outputs, for example, the search prompt to a storage function that stores structured data used in a data search to respond to a data search query acquired by the acquisition unit 304. The output unit 312 outputs, for example, the search prompt to a storage function that stores graph data used in the data search.

[0132] The output unit 312 outputs, for example, a search prompt to the storage function 240 of the application platform 200. The output unit 312 outputs, for example, a search prompt to the database 400.

[0133] The determining unit 314 executes various determination processes. For example, when the acquiring unit 304 acquires a data search query, the determining unit 314 executes various determination processes.

[0134] The determination unit 314 executes various determination processes based on, for example, various pieces of information stored in the information storage unit 302. The determination unit 314 executes various determination processes based on, for example, various pieces of information acquired by the acquisition unit 304.

[0135] The determination unit 314 determines, for example, whether the data search can be performed using the data to be determined. The determination unit 314 determines, for example, whether the data search can be performed using the data to be determined, based on the processing results of natural language processing performed on the query. For example, the determination unit 314 extracts specific terms from the processing results and identifies the search target of the data search from the extracted specific terms. Thereafter, the determination unit 314 determines, based on the configuration information of the data to be determined stored in the information storage unit 302, whether the search target of the data search can be searched for using structured data.

[0136] The data to be determined may be, for example, structured data or graph data.

[0137] The determination unit 314 determines, for example, whether the data search can be performed using the structured data. The determination unit 314 determines, for example, whether the data search can be performed using the structured data based on the query and the configuration information of the structured data stored in the information storage unit 302.

[0138] For example, when the determination unit 314 determines that the data search can be performed using the structured data, the generation unit 306 generates a search prompt including the query and configuration information of the structured data. In this case, the output unit 312 may output the search prompt to a storage function that stores the structured data.

[0139] On the other hand, if the determination unit 314 determines that the data search cannot be performed using the structured data, the generation unit 306 generates a search prompt including the query and configuration information of the graph data. In this case, the output unit 312 may output the search prompt to a storage function that stores the graph data.

[0140] The determination unit 314 determines, for example, whether or not there are multiple pieces of graph data that can be used for the data search. The determination unit 314 determines, for example, based on the query and configuration information of the multiple pieces of graph data stored in the information storage unit 302, whether or not there are multiple pieces of graph data that can be used for the data search.

[0141] For example, if the determination unit 314 determines that the data search can be performed using the graph data, it determines that the graph data can be used for the data search. On the other hand, if the determination unit 314 determines that the data search cannot be performed using the graph data, it determines that the graph data cannot be used for the data search.

[0142] For example, when the determination unit 314 determines that there are multiple pieces of graph data that can be used for the data search, the selection unit 308 selects configuration information of graph data to be used for the data search from the configuration information of the multiple pieces of graph data that can be used for the data search. For example, the selection unit 308 preferentially selects configuration information of graph data that can execute the data search in a short time as configuration information of graph data to be used for the data search from the configuration information of the multiple pieces of graph data that can be used for the data search. For example, the selection unit 308 preferentially selects configuration information of graph data that has a small number of transition nodes for the data search as configuration information of graph data to be used for the data search from the configuration information of the multiple pieces of graph data that can be used for the data search.

[0143] The acquiring unit 304 acquires the search results of the data search, for example, from a storage function to which the search prompt output by the output unit 312 has been input. The acquiring unit 304 acquires the search results of the data search, for example, expressed in a programming language. The acquiring unit 304 acquires the search results of the data search, for example, expressed in a natural language.

[0144] For example, when the acquisition unit 304 acquires the search results of the data search expressed in a programming language, the generation unit 306 generates the answer generation prompt. For example, the generation unit 306 generates the answer generation prompt based on the query and the search results of the data search expressed in a programming language.

[0145] The output unit 312 outputs the answer generation prompt generated by the generation unit 306 to a conversion function that converts a program language into a natural language. The output unit 312 outputs the answer generation prompt to the conversion function 290, for example.

[0146] The acquiring unit 304 acquires, for example, a search result of the data search expressed in natural language as an answer to the query from the conversion function to which the answer generation prompt output by the output unit 312 has been input. The output unit 312 outputs, for example, the answer to the query acquired by the acquiring unit 304.

[0147] The acquiring unit 304 may acquire, for example, learning data. The learning data may include, for example, a data search query, search data indicating graph data used in the data search to answer the query, and search time data indicating the search time for the data search. The acquiring unit 304 may store the acquired learning data in the learning data storage unit 316.

[0148] The model generation unit 318 generates, from a data search query, a selection model that selects configuration information of graph data that enables a data search to be performed in a shorter time to answer the query. The model generation unit 318 generates the selection model by machine learning, for example, using a plurality of training data stored in the training data storage unit 316 as training data. The model generation unit 318 may store the generated selection model in the model storage unit 322.

[0149] The acquiring unit 304 acquires a selection model from an external device such as a model generating device. The acquiring unit 304 acquires, from the external device, a selection model similar to the selection model generated by the model generating unit 318. The acquiring unit 304 may store the acquired selection model in the model storage unit 322.

[0150] The selection unit 308 selects configuration information of graph data, for example, by using a selection model stored in the model storage unit 322. For example, the selection unit 308 uses the selection model to select, from a data search query acquired by the acquisition unit 304, configuration information of graph data that enables a data search to respond to the query to be executed in a shorter time.

[0151] The application platform 310 provides a base environment for the application 320. The application platform 310 provides, for example, a base environment for executing the application 320. The application platform 310 provides, for example, a base environment for developing the application 320. The application platform 310 may have similar functions to the application platform 200.

[0152] The application 320 may be any application that can be executed or developed on the application platform 310. The application 320 may be an application similar to the application 220.

[0153] The application platform 310 includes, for example, an application development unit 321. The application platform 310 includes, for example, an application execution unit 323. The application platform 310 includes, for example, a storage function 340. The application platform 310 includes, for example, a generation AI 350. The generation AI 350 is, for example, an interactive AI.

[0154] The application development unit 321 develops an application 320. The application development unit 321 develops, for example, an application 320 that runs on the application platform 310. The application development unit 321 may develop an application 320 that runs on an application platform other than the application platform 310.

[0155] The application execution unit 323 executes the application 320. For example, the application execution unit 323 executes the application 320 developed by the application development unit 321. The application execution unit 323 may execute the application 320 developed by an external device such as an application development device and installed on the application platform 310.

[0156] For example, the application execution unit 323 acquires log data of the application 320 executed on the application platform 310. The application execution unit 323 may store the acquired log data in the storage function 340.

[0157] The storage function 340 stores various data. The storage function 340 is, for example, a database. The storage function 340 may have the same functions as the storage function 240.

[0158] The storage function 340 stores, for example, a plurality of structured data 370. The storage function 340 stores, for example, a plurality of structured data 370 corresponding to log data of the application 320 executed on the application platform 310.

[0159] The generation AI 350 generates content. The generation AI 350 generates the content using, for example, computational resources such as a CPU or a GPU mounted on the information processing device 300. The generation AI 350 may store the generated content in the storage function 340.

[0160] The generation AI 350 may have the same functions as the generation AI 250. Therefore, the generation AI 350 may generate content similar to the content generated by the generation AI 250.

[0161] The generation AI 350 includes, for example, a conversion function 390. The conversion function 390 may perform conversion processing for various languages. The conversion function 390 may have the same functions as the conversion function 290.

[0162] The generation AI 350 may further include a storage function 340. That is, the generation AI 350 may include the storage function 340 and the conversion function 390.

[0163] The generation AI 350 generates, for example, graph data 380. The generation AI 350 generates the graph data 380 based on, for example, a plurality of pieces of structured data 370 stored in the storage function 340.

[0164] The acquisition unit 304 acquires, for example, from the application platform 310, configuration information of the structured data 370 stored in the storage function 340. The acquisition unit 304 acquires, for example, from the application platform 310, configuration information of the graph data 380 stored in the storage function 340.

[0165] The output unit 312, for example, outputs the search prompt generated by the generation unit 306 to the application platform 310. The storage function 340, to which the search prompt output by the output unit 312 is input, may perform a data search based on the search prompt to answer the data search query acquired by the acquisition unit 304. The acquisition unit 304 may acquire the search results of the data search from the storage function 340.

[0166] The output unit 312 may, for example, output the answer generation prompt generated by the generation unit 306 to the conversion function 390. The conversion function 390 may receive the answer generation prompt output by the output unit 312 and convert the search results of the data search from a programming language into a natural language based on the answer generation prompt. The acquisition unit 304 may acquire the search results of the data search expressed in a natural language from the conversion function 390 as an answer to the query.

[0167] For example, generation AI 350 functions as a data generation function, a data retrieval function, and / or a data analysis function for application platform 310. For example, storage function 340 functions as a data retrieval function and / or a data analysis function for application platform 310.

[0168] 6 shows an example of the functional configuration of an information processing device 300 including an application platform 310. The information processing device 300 does not necessarily have to include the application platform 310.

[0169] 7 schematically illustrates an example of the hardware configuration of a computer 1200 functioning as the application platform 200 or the information processing device 300. 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.

[0170] 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 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 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.

[0171] 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.

[0172] 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 1226 reads programs or data from a DVD-ROM 1227 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.

[0173] 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.

[0174] The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 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.

[0175] 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, the DVD-ROM 1227, 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.

[0176] 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, the DVD drive 1226 (DVD-ROM 1227), 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] A computer-readable medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that the computer-readable medium having instructions stored thereon comprises an article of manufacture containing instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable media may include electronic, magnetic, optical, electromagnetic, and semiconductor storage media. More specific examples of computer-readable 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, and the like.

[0181] 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.

[0182] The computer-readable instructions may be provided to a processor or programmable circuit of a programmable data processing device, such as a computer, locally or via a wide area network (WAN) such as a local area network (LAN) or the Internet, and the computer-readable instructions may be executed to create 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 computer. In a distributed computing system, the 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.

[0183] Examples of processors include a computer processor, a central processing unit (CPU), a processing unit, a microprocessor, a digital signal processor, a controller, a microcontroller, 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.

[0184] This invention can contribute to the success of business projects, thereby contributing to the achievement of Goal 8 of the Sustainable Development Goals (SDGs), "Decent Work and Economic Growth."

[0185] 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 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.

[0186] 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]

[0187] 10 System, 20 Network, 100 Communication terminal, 150 User, 200 Application platform, 220 Application, 240 Storage function, 250 Generative AI, 270 Structured data, 280 Graph data, 282 Node, 284 Edge, 290 Conversion function, 300 Information processing device, 302 Information storage unit, 304 Acquisition unit, 306 Generation unit, 308 Selection unit, 310 Application platform, 312 Output unit, 314 Judgment unit, 316 Learning data storage unit, 318 Model generation unit, 320 Application, 321 Application development unit, 322 Model storage unit, 323 Application execution unit, 340 Storage function, 350 Generative AI, 370 Structured data, 380 Graph data, 390 Conversion function, 400 Database, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 graphics controller, 1218 display device, 1220 input / output controller, 1222 communication interface, 1224 storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 input / output chip

Claims

1. An information storage unit for storing configuration information indicating a configuration of graph data that is composed of a plurality of nodes and edges connecting two nodes among the plurality of nodes; an acquisition unit that acquires a query for a data search of the graph data stored in the storage function; a determination unit that determines whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection unit that, when the determination unit determines that a plurality of pieces of graph data that can be used for the data search exist, selects, with higher priority, the configuration information of the graph data having a smaller number of transition nodes for the data search from the configuration information of the plurality of pieces of graph data that can be used for the data search, as the configuration information of the graph data to be used for the data search; a generator for generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data selected by the selector; an output unit that outputs the search prompt to the storage function that stores graph data used in the data search and functions as a data search function for the graph data; Equipped with the acquisition unit acquires, from the storage function, a search result of the data search performed by the storage function; Information processing system.

2. The information processing system according to claim 1 , wherein the information storage unit stores the configuration information of the graph data generated based on a plurality of structured data.

3. The information processing system according to claim 2 , wherein the information storage unit stores the configuration information of the graph data generated based on the plurality of structured data corresponding to log data of an application executed on an application platform.

4. 4. The information processing system according to claim 1, wherein the selection unit selects the configuration information of the graph data to be used for the data search based on a processing result obtained by executing natural language processing (NLP) on the query.

5. An information storage unit for storing configuration information indicating a configuration of graph data that is composed of a plurality of nodes and an edge connecting two nodes among the plurality of nodes; an acquisition unit that acquires a query for a data search of the graph data stored in the storage function; a determination unit that determines whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection unit that, when the determination unit determines that a plurality of pieces of graph data that can be used for the data search exist, selects, with higher priority, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search; a generator for generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data selected by the selector; an output unit that outputs the search prompt to the storage function that stores graph data used in the data search and functions as a data search function for the graph data; Equipped with the acquisition unit acquires, from the storage function, a search result of the data search performed by the storage function; Information processing system.

6. An information storage unit for storing configuration information indicating the configuration of structured data and configuration information indicating the configuration of graph data consisting of a plurality of nodes and edges connecting two nodes among the plurality of nodes; an acquisition unit that acquires a query for a data search of structured data or graph data stored in the storage function; a determination unit that determines whether the data search can be performed using the structured data based on the query and the configuration information of the structured data; a generation unit that generates a search prompt for executing the data search, including the query and the configuration information of the structured data, when the determination unit determines that the data search can be executed using the structured data, and generates a search prompt for executing the data search, including the query and the configuration information of the graph data, when the determination unit determines that the data search cannot be executed using the structured data; an output unit that, when the generation unit generates the search prompt including the query and the configuration information of the structured data, outputs the search prompt including the query and the configuration information of the structured data to the storage function that stores the structured data used in the data search and functions as a data search function for the structured data, and when the generation unit generates the search prompt including the query and the configuration information of the graph data, outputs the search prompt including the query and the configuration information of the graph data to the storage function that stores the graph data used in the data search and functions as a data search function for the graph data; Equipped with the acquisition unit acquires, from the storage function, a search result of the data search performed by the storage function; Information processing system.

7. the generating unit further generates an answer generation prompt that generates an answer to the query based on the query and the search results; the output unit outputs the answer generation prompt to a conversion function that converts a programming language into a natural language; the obtaining unit obtains the search results expressed in natural language as an answer to the query from the conversion function. The information processing system according to claim 1 .

8. The information processing system according to claim 7 , wherein the output unit outputs the search prompt and the answer generation prompt to a generation AI having the storage function and the conversion function.

9. The information processing system according to claim 7 , wherein the output unit outputs the answer to the query.

10. An information storage unit for storing configuration information indicating a configuration of graph data consisting of a plurality of nodes and edges connecting two nodes among the plurality of nodes; an acquisition unit that acquires a query for a data search of the graph data stored in the storage function; a determination unit that determines whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection unit that, when the determination unit determines that a plurality of pieces of graph data that can be used for the data search exist, selects, with higher priority, the configuration information of the graph data having a smaller number of transition nodes for the data search from the configuration information of the plurality of pieces of graph data that can be used for the data search, as the configuration information of the graph data to be used for the data search; a generator for generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data selected by the selector; an output unit that outputs the search prompt to a generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; Equipped with The acquisition unit acquires the search results of the data search by the generation AI output by the generation AI. Information processing system.

11. An information storage unit for storing configuration information indicating a configuration of graph data consisting of a plurality of nodes and an edge connecting two nodes among the plurality of nodes; an acquisition unit that acquires a query for a data search of the graph data stored in the storage function; a determination unit that determines whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection unit that, when the determination unit determines that a plurality of pieces of graph data that can be used for the data search exist, selects, with higher priority, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search; a generator for generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data selected by the selector; an output unit that outputs the search prompt to a generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; Equipped with The acquisition unit acquires the search results of the data search by the generation AI output by the generation AI. Information processing system.

12. An information storage unit for storing configuration information indicating the configuration of structured data and configuration information indicating the configuration of graph data consisting of a plurality of nodes and edges connecting two nodes among the plurality of nodes; an acquisition unit that acquires a query for a data search of structured data or graph data stored in the storage function; a determination unit that determines whether the data search can be performed using the structured data based on the query and the configuration information of the structured data; a generation unit that generates a search prompt for executing the data search, including the query and the configuration information of the structured data, when the determination unit determines that the data search can be executed using the structured data, and generates a search prompt for executing the data search, including the query and the configuration information of the graph data, when the determination unit determines that the data search cannot be executed using the structured data; an output unit that, when the generation unit generates the search prompt including the query and the configuration information of the structured data, outputs the search prompt including the query and the configuration information of the structured data to a generation AI that functions as a data search function for structured data stored in the storage function that stores structured data used for the data search, and when the generation unit generates the search prompt including the query and the configuration information of the graph data, outputs the search prompt including the query and the configuration information of the graph data to the generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used for the data search; Equipped with The acquisition unit acquires the search results of the data search by the generation AI output by the generation AI. Information processing system.

13. An information processing system that stores configuration information indicating a configuration of graph data that is configured by a plurality of nodes and an edge connecting two nodes among the plurality of nodes, a query acquisition step for acquiring a query for data search of the graph data stored in the storage function; a determination step of determining whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that there are a plurality of pieces of graph data that can be used for the data search, preferentially selecting, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that has a smaller number of transition nodes for the data search as the configuration information of the graph data to be used for the data search; a generating step of generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selecting step; an output step of outputting the search prompt to the storage function that stores graph data used in the data search and functions as a data search function for the graph data; a search result acquisition step of acquiring, from the storage function, a search result of the data search by the storage function; A program to execute.

14. An information processing system for storing configuration information indicating a configuration of graph data consisting of a plurality of nodes and edges connecting two nodes among the plurality of nodes, a query acquisition step for acquiring a query for data search of the graph data stored in the storage function; a determination step of determining whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that a plurality of pieces of graph data that can be used for the data search exist, selecting, with higher priority, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search; a generating step of generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selecting step; an output step of outputting the search prompt to the storage function that stores graph data used in the data search and functions as a data search function for the graph data; a search result acquisition step of acquiring, from the storage function, a search result of the data search by the storage function; A program to execute.

15. An information processing system storing configuration information indicating a configuration of structured data and configuration information indicating a configuration of graph data consisting of a plurality of nodes and an edge connecting two nodes out of the plurality of nodes, a query acquisition step for acquiring a query for data search of structured data or graph data stored in the storage function; a determination step of determining whether the data search can be performed using the structured data based on the query and the configuration information of the structured data; a generation step of generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the structured data, when it is determined in the determination step that the data search can be executed using the structured data, and generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data, when it is determined in the determination step that the data search cannot be executed using the structured data; an output step of, when the search prompt including the query and the configuration information of the structured data is generated in the generation step, outputting the search prompt including the query and the configuration information of the structured data to the storage function that stores the structured data used in the data search and functions as a data search function for the structured data, and when the search prompt including the query and the configuration information of the graph data is generated in the generation step, outputting the search prompt including the query and the configuration information of the graph data to the storage function that stores the graph data used in the data search and functions as a data search function for the graph data; a search result acquisition step of acquiring, from the storage function, a search result of the data search by the storage function; A program to execute.

16. An information processing system for storing configuration information indicating a configuration of graph data consisting of a plurality of nodes and edges connecting two nodes among the plurality of nodes, a query acquisition step for acquiring a query for data search of the graph data stored in the storage function; a determination step of determining whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that there are a plurality of pieces of graph data that can be used for the data search, preferentially selecting, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that has a smaller number of transition nodes for the data search as the configuration information of the graph data to be used for the data search; a generating step of generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selecting step; an output step of outputting the search prompt to a generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; a search result acquisition step for acquiring the search results of the data search by the generated AI, which are output by the generated AI; A program to execute.

17. An information processing system for storing configuration information indicating a configuration of graph data consisting of a plurality of nodes and edges connecting two nodes among the plurality of nodes, a query acquisition step for acquiring a query for data search of the graph data stored in the storage function; a determination step of determining whether or not there are a plurality of graph data that can be used for the data search, based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that a plurality of pieces of graph data that can be used for the data search exist, selecting, with higher priority, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search; a generating step of generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selecting step; an output step of outputting the search prompt to a generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; a search result acquisition step for acquiring the search results of the data search by the generated AI, which are output by the generated AI; A program to execute.

18. An information processing system that stores configuration information indicating a configuration of structured data and configuration information indicating a configuration of graph data that is composed of a plurality of nodes and an edge connecting two nodes out of the plurality of nodes, a query acquisition step for acquiring a query for data search of structured data or graph data stored in the storage function; a determination step of determining whether the data search can be performed using the structured data based on the query and the configuration information of the structured data; a generation step of generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the structured data, when it is determined in the determination step that the data search can be executed using the structured data, and generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data, when it is determined in the determination step that the data search cannot be executed using the structured data; an output procedure for, when the search prompt including the query and the configuration information of the structured data is generated in the generation procedure, outputting the search prompt including the query and the configuration information of the structured data to a generation AI that functions as a data search function for structured data stored in the storage function that stores structured data used in the data search, and when the search prompt including the query and the configuration information of the graph data is generated in the generation procedure, outputting the search prompt including the query and the configuration information of the graph data to the generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; a search result acquisition step for acquiring the search results of the data search by the generated AI, which are output by the generated AI; A program to execute.

19. 1. An information processing method executed by an information processing system that stores configuration information indicating a configuration of graph data that is configured by a plurality of nodes and an edge connecting two nodes among the plurality of nodes, a query acquisition stage for acquiring a query for data search of the graph data stored in the storage function; a determining step of determining whether there are a plurality of graph data that can be used for the data search based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that there are a plurality of pieces of graph data that can be used for the data search, preferentially selecting, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that has a smaller number of transition nodes for the data search as the configuration information of the graph data to be used for the data search; generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selection step; an output step of outputting the search prompt to the storage facility that stores graph data used in the data search and that functions as a data search facility for the graph data; a search result acquisition step of acquiring, from the storage function, a search result of the data search by the storage function; An information processing method comprising:

20. An information processing method executed by an information processing system that stores configuration information indicating a configuration of graph data that is composed of a plurality of nodes and edges connecting two nodes among the plurality of nodes, comprising: a query acquisition stage for acquiring a query for data search of the graph data stored in the storage function; a determining step of determining whether there are a plurality of graph data that can be used for the data search based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that there are a plurality of pieces of graph data that can be used for the data search, selecting, with higher priority, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search from the configuration information of the plurality of pieces of graph data that can be used for the data search; generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selection step; an output step of outputting the search prompt to the storage facility that stores graph data used in the data search and that functions as a data search facility for the graph data; a search result acquisition step of acquiring, from the storage function, a search result of the data search by the storage function; An information processing method comprising:

21. An information processing method executed by an information processing system that stores configuration information indicating a configuration of structured data and configuration information indicating a configuration of graph data that is composed of a plurality of nodes and edges connecting two nodes among the plurality of nodes, comprising: a query acquisition stage for acquiring a query for data search of structured data or graph data stored in the storage function; a determining step of determining whether the data search can be performed using the structured data based on the query and the configuration information of the structured data; a generating step of generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the structured data, when it is determined in the determining step that the data search can be executed using the structured data, and generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data, when it is determined in the determining step that the data search cannot be executed using the structured data; an output step of, when the search prompt including the query and the configuration information of the structured data is generated in the generation step, outputting the search prompt including the query and the configuration information of the structured data to the storage function that stores the structured data used in the data search and functions as a data search function for the structured data, and when the search prompt including the query and the configuration information of the graph data is generated in the generation step, outputting the search prompt including the query and the configuration information of the graph data to the storage function that stores the graph data used in the data search and functions as a data search function for the graph data; a search result acquisition step of acquiring, from the storage function, a search result of the data search by the storage function; An information processing method comprising:

22. An information processing method executed by an information processing system that stores configuration information indicating a configuration of graph data that is composed of a plurality of nodes and edges connecting two nodes among the plurality of nodes, comprising: a query acquisition stage for acquiring a query for data search of the graph data stored in the storage function; a determining step of determining whether there are a plurality of graph data that can be used for the data search based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that there are a plurality of pieces of graph data that can be used for the data search, preferentially selecting, from the configuration information of the plurality of pieces of graph data that can be used for the data search, the configuration information of the graph data that has a smaller number of transition nodes for the data search as the configuration information of the graph data to be used for the data search; generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selection step; an output step of outputting the search prompt to a generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; a search result acquisition step of acquiring search results of the data search by the generated AI output by the generated AI; An information processing method comprising:

23. An information processing method executed by an information processing system that stores configuration information indicating a configuration of graph data that is composed of a plurality of nodes and edges connecting two nodes among the plurality of nodes, comprising: a query acquisition stage for acquiring a query for data search of the graph data stored in the storage function; a determining step of determining whether there are a plurality of graph data that can be used for the data search based on the query and the configuration information of the plurality of graph data; a selection step of, when it is determined in the determination step that there are a plurality of pieces of graph data that can be used for the data search, selecting, with higher priority, the configuration information of the graph data that can execute the data search in a short time as the configuration information of the graph data to be used for the data search from the configuration information of the plurality of pieces of graph data that can be used for the data search; generating a search prompt for performing the data search, the search prompt including the query and the configuration information of the graph data selected in the selection step; an output step of outputting the search prompt to a generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used in the data search; a search result acquisition step of acquiring search results of the data search by the generated AI output by the generated AI; An information processing method comprising:

24. An information processing method executed by an information processing system that stores configuration information indicating a configuration of structured data and configuration information indicating a configuration of graph data that is composed of a plurality of nodes and edges connecting two nodes among the plurality of nodes, comprising: a query acquisition stage for acquiring a query for data search of structured data or graph data stored in the storage function; a determining step of determining whether the data search can be performed using the structured data based on the query and the configuration information of the structured data; a generating step of generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the structured data, when it is determined in the determining step that the data search can be executed using the structured data, and generating a search prompt for executing the data search, the search prompt including the query and the configuration information of the graph data, when it is determined in the determining step that the data search cannot be executed using the structured data; an output step of, when the search prompt including the query and the configuration information of the structured data is generated in the generation step, outputting the search prompt including the query and the configuration information of the structured data to a generation AI that functions as a data search function for structured data stored in the storage function that stores structured data used for the data search, and when the search prompt including the query and the configuration information of the graph data is generated in the generation step, outputting the search prompt including the query and the configuration information of the graph data to the generation AI that functions as a data search function for graph data stored in the storage function that stores graph data used for the data search; a search result acquisition step of acquiring search results of the data search by the generated AI output by the generated AI; An information processing method comprising:

Images