Information Processing Method, Information Processing System, and Program

Abstract

To enable users without technical knowledge to easily obtain the necessary core system information for each company. 【Solution means】The information processing method includes: a computer obtaining user identification information capable of identifying a user, obtaining first request information regarding a core system, applying the user identification information and the first request information to a learned model to generate second request information associated with the company to which the user belongs, and generating instruction information for generating at least one response core system information corresponding to the second request information among the core system information stored in the core system. The learned model is based on the relationship between the core system information and company identification information characterizing the company to which the user belongs.

Description

Technical Field

[0001] The present invention relates to an information processing method, an information processing system, and a program for assisting in generating core system information.

Background Art

[0002] In recent years, attention has been focused on technologies for generating response sentences for question sentences input to terminals. Patent Document 1 discloses a technology for generating a response sentence (output sentence) including keywords included in a question sentence (input sentence).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] On the other hand, conventionally, when the input information is natural language, ambiguous information is input, so the output response sentence also becomes ambiguous information, and there are cases where the required information cannot be obtained. In addition, in order to obtain information stored in the core system (also referred to as "core system information"), it is necessary to generate instruction information (prompt information) using a programming language such as SQL (Structured Query Language). Therefore, users without specialized knowledge cannot easily obtain the information stored in the core system.

[0005] One object of the present invention is to enable users without technical knowledge to easily obtain the necessary core system information for each company. Another object of the present invention is to enable users to directly inquire of the core system in natural language. Another object of the present invention is to easily generate the necessary information for the input question information.

Means for Solving the Problem

[0006] According to an embodiment of the present invention, there is provided an information processing method for assisting in the generation of core system information, in which a computer acquires user identification information capable of identifying a user, acquires first request information regarding a core system, applies the user identification information and the first request information to a learned model to generate second request information associated with the company to which the user belongs, and generates instruction information for generating at least one response core system information corresponding to the second request information among the core system information stored in the core system. The learned model is based on the relationship between the core system information and company identification information characterizing the company to which the user belongs, and an information processing method is provided.

[0007] In the above information processing method, the instruction information may include prompt information for generating SQL (Structured Query Language).

[0008] In the above information processing method, when generating the at least one response core system information, a part of the core system information may be excluded based on the user identification information.

[0009] In the above information processing method, the excluded core system information may be set according to the degree of association with the user.

[0010] In the above information processing method, it may further include acquiring category information corresponding to the category of the core system information, and generating the instruction information based on the second request information and the category information.

[0011] In the above information processing method, it may further include obtaining category information corresponding to the category of the backbone system information, and correcting at least a part of the instruction information according to the database information corresponding to the category information.

[0012] In the above information processing method, the user interface displayed on the terminal device of the user includes a plurality of category information corresponding to the category of the backbone system information, and when at least one piece of category information among the plurality of category information is selected, it may include generating at least one question candidate information based on the selected category information.

[0013] In the above information processing method, the at least one question candidate information includes a plurality of question candidate information, and when at least one piece of question candidate information among the plurality of question candidate information is selected, it may include generating first request candidate information that is a candidate for the first request information.

[0014] According to an embodiment of the present invention, a program for causing a computer to execute the above information processing method is provided.

[0015] According to an embodiment of the present invention, an information processing system for assisting in the generation of backbone system information, which obtains user identification information capable of identifying a user, obtains first request information regarding the backbone system, applies the user identification information and the first request information to a learned model to generate second request information associated with the company to which the user belongs, and generates instruction information for generating at least one response backbone system information corresponding to the second request information among the backbone system information stored in the backbone system, includes a control unit, and the learned model is provided with information processing system user identification information based on the relationship between the backbone system information and company identification information characterizing the company to which the user belongs.

[0016] In the above information processing system, the instruction information may include prompt information for generating SQL (Structured Query Language).

[0017] In the above information processing system, when generating the at least one answer backbone system information, the control unit may exclude a part of the backbone system information based on the user identification information.

[0018] In the above information processing system, the excluded backbone system information may be set according to the degree of relevance to the user.

[0019] In the above information processing system, the control unit may obtain category information corresponding to the category of the backbone system information, and generate the instruction information based on the second request information and the category information.

[0020] In the above information processing system, the control unit may obtain category information corresponding to the category of the backbone system information, and correct at least a part of the instruction information according to the database information corresponding to the category information.

[0021] In the above information processing system, the user interface displayed on the user's terminal device includes a plurality of category information corresponding to the category of the backbone system information. When at least one category information among the plurality of category information is selected, the control unit may generate at least one question candidate information based on the selected category information.

[0022] In the above information processing system, the at least one question candidate information includes a plurality of question candidate information. When at least one question candidate information among the plurality of question candidate information is selected, the control unit may generate first request candidate information that is a candidate for the first request information.

Advantages of the Invention

[0023] According to an embodiment of the present invention, even a user without technical knowledge can easily obtain necessary core system information. Further, according to an embodiment of the present invention, a user can directly inquire of the core system in natural language. Further, according to an embodiment of the present invention, it is to easily generate necessary information for the input question information.

Brief Description of the Drawings

[0024]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Embodiments for Carrying Out the Invention

[0025] The following embodiments are examples of embodiments of the present invention, and the present invention is not limited to these embodiments. In the drawings referred to in this embodiment, the same parts or parts having the same function are denoted by the same reference numerals or similar reference numerals, and the repeated description thereof may be omitted.

[0026] <First Embodiment> The information processing system in this embodiment will be described in detail with reference to the drawings.

[0027] (1-1. Overall Configuration of Information Processing System) FIG. 1 is a diagram for explaining the information processing system 1 in this embodiment. The information processing system 1 includes an information processing server 10, a database 20, a backbone system 2 (a backbone system server 30 and a database 40), and a terminal device 50.

[0028] The database 20 is connected to the information processing server 10. The database 40 is connected to the backbone system server 30. The backbone system 2 is configured by the backbone system server 30 and the database 40. In FIG. 1, the information processing server 10, the backbone system server 30, and the terminal device 50 are connected to a network NW. The network NW is a communication network such as the Internet or an intranet, and an appropriate network is used according to the communication environment.

[0029] In this embodiment, the information processing system 1 may be constructed using a cloud platform. The form of the cloud platform is not particularly limited, and Infrastructure as a Service (IaaS), Platform as a Service (PaaS), or Software as a Service (SaaS) can be applied. As specific examples of the cloud platform, Microsoft Azure (manufactured by Microsoft), Amazon Web Services (manufactured by Amazon), and Google Cloud Platform (manufactured by Google) can be applied. Note that the information processing system 1 may be constructed without being limited to the cloud platform.

[0030] According to the information processing system 1, in order to assist in generating backbone system information, from the backbone system request information (first request information) using natural language such as character information input to the terminal device 50 and reconfigured to correspond to the enterprise, backbone system request information (second request information) can be generated, and backbone system information corresponding to the second request information stored in the backbone system 2 (backbone system server 30 or database 40) can be generated. The generated backbone system information is displayed on the terminal device 50. Hereinafter, the configuration of the information processing system 1 for realizing such processing will be described.

[0031] (1-2. Hardware Configuration) FIG. 2 is a diagram for explaining the hardware configuration of each device constituting the information processing system 1.

[0032] (1-2-1. Information Processing Server 10) The information processing server 10 includes a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11, the storage unit 12, and the communication unit 13 may be connected by a communication bus. In this example, a cloud server is used as the information processing server 10. Also, depending on the system environment, the information processing server 10 may be an on-premises server or other processing device. The control unit 11 is an example of a computer including an arithmetic processing circuit such as a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array). The control unit 11 executes the program stored in the storage unit 12 to realize various functions in the information processing server 10. Thereby, various information processes by the information processing server 10 in the information processing system 1 are executed.

[0033] The storage unit 12 includes a storage device and stores an information processing program. Also, the storage unit 12 stores various data used when the information processing program is executed. Note that this program may be provided in a state recorded on a computer-readable recording medium such as a magnetic recording medium, an optical recording medium, a magneto-optical recording medium, or a semiconductor memory. In this case, the information processing server 10 only needs to include an interface for connecting the recording medium. Here, the storage medium may be defined as a medium different from the storage unit 12 included in the information processing server 10, or may be the medium used for the storage unit 12.

[0034] The communication unit 13 includes a communication module and is connected to the network NW under the control of the control unit 11 to transmit and receive information with other devices connected to the network NW. In this example, the communication unit 13 is further connected to a database 20 (also referred to as a database server) to transmit and receive information. Information registered in the database 20 will be described later. Note that the communication unit 13 may be connected to the database 20 via the network NW. Also, the information registered in the database 20 may be stored in the storage unit 12. In this case, the database 20 may not exist.

[0035] In addition to the above configuration, the information processing server 10 may have other configurations (input / output interfaces) such as a display unit, an audio output unit, and a light emitting unit.

[0036] (1-2-2. Backbone System Server 30) The backbone system server 30 includes a control unit 31, a storage unit 32, and a communication unit 33. The control unit 31 has basically the same configuration as the above-described control unit 11 and realizes various functions in the backbone system in the backbone system server 30. Thereby, the processing by the backbone system server 30 in the information processing system 1 is executed.

[0037] The storage unit 32 has basically the same configuration as the storage unit 12, and stores programs related to the core system, programs related to the information processing system, and various other information. Since the communication unit 33 has basically the same configuration as the communication unit 13, its description is omitted. Also, the communication unit 33 is also connected to the database 40 to perform transmission and reception of information. Various information related to the core system is stored in the database 40. A relational database (RDB) is used for the database 40. The relational database manages data in a tabular format. In a relational database, data is stored separately in multiple tables (data tables). Therefore, it is possible to efficiently manage and operate data by utilizing the relationships between the data tables. As the database 40, for example, DB2 for i (manufactured by IBM), SQL Server (manufactured by Microsoft), Oracle RDB, MySQL (registered trademark) (manufactured by Oracle), etc. are used. In addition to the RDB, an SAP (Systems, Applications and Products in Data Processing) database or other types of databases may be used.

[0038] (1-2-3. Terminal device 50) The terminal device 50 (enterprise terminal) is composed of at least one of a desktop PC (personal computer), a notebook PC, a mobile phone, a smartphone, a tablet terminal, and other electronic application devices. The terminal device 50 can function as a client. The terminal device includes a control unit 51, a storage unit 52, a communication unit 53, a display unit 54, and an operation unit 55. The control unit 51 has basically the same configuration as the above-described control unit 11, and realizes various functions in the terminal device 50. It executes the processing in the terminal device 50 in the information processing system 1.

[0039] The memory unit 52 has basically the same configuration as the memory unit 12, and since the content of the instructions of the stored program is different to some extent, its description is omitted. The communication unit 53 has basically the same configuration as the communication unit 13, and since the connectable network is different to some extent, its description is omitted.

[0040] The display unit 54 includes a display device whose display content is controlled by the control of the control unit 51. The operation unit 55 can include a keyboard, a switch, a handle, etc., and outputs information corresponding to the operation to the control unit 51. Further, the operation unit 55 may include a touch sensor and output information corresponding to the position operated by the user to the control unit 51. The touch sensor may be provided on the display area of the display unit 54. That is, the display unit 54 and the operation unit 55 may constitute a touch panel.

[0041] (1-3. Software Configuration of Information Processing Server) FIG. 3 is a diagram showing the software configuration in the control unit 11 of the information processing server 10. The control unit 11 includes an acquisition unit 11a, a preprocessing unit 11b, a machine learning unit 11c, an inference processing unit 11d, a generation unit 11e, and a display control unit 11f.

[0042] The acquisition unit 11a has a function of acquiring various information from each device. For example, the acquisition unit 11a acquires various information such as corporate information, core system information, and requirement information regarding the core system. The acquired information is stored in the database 20.

[0043] The preprocessing unit 11b performs preprocessing on the acquired information. In this example, the preprocessing unit 11b preprocesses the core master data of the enterprise. As the preprocessing, techniques such as chunking and vectorization may be used. Through these preprocessings, optimization can be achieved in the data search process specific to the enterprise. The preprocessed information is appropriately stored in the database 20.

[0044] The machine learning unit 11c has a function of performing machine learning based on the acquired information. In this example, machine learning is performed by associating the core system information with the company identification information characterizing the nature and culture of the company, etc. Thereby, company-specific information can be learned, and more accurate search results can be provided.

[0045] The inference processing unit 11d has a function of inferring the content of the core system requirement information based on the acquired core system requirement information and user identification information.

[0046] The generation unit 11e has a function of generating various types of information. In this example, the generation unit 11e generates generation prompt information of the core system information for the core system server 30 based on the inferred core system requirement information.

[0047] The display control unit 11f has a function of controlling the display of the core system information acquired from the core system server 30 to the terminal device 50.

[0048] (1-4. Various data tables) Subsequently, various data tables used in the information processing system 1 will be described.

[0049] (1-4-1. Customer master data table) FIG. 4 shows the customer master data table 100. The customer master data table 100 includes information regarding customers who are business partners of the company. In this example, the customer master data table 100 includes customer number information 101, customer name information 103, postal code information 105, prefecture information 107, and address information 109. The customer master data table 100 may be stored in the database 20 of the information processing server 10 or may be stored in the database 40 of the core system server 30.

[0050] (1-4-2. Branch office master data table) Figure 5 is the office master data table 200. The office master data table 200 contains information about the offices of an enterprise. In this example, the office master data table 200 includes office number information 201, office name information 203, prefecture information 205, and address information 207. The office master data table 200 may be stored in the database 20 of the information processing server 10 or in the database 40 of the core system server 30.

[0051] (1-4-3. Warehouse master data table) Figure 6 is the warehouse master data table 300. The warehouse master data table 300 contains information about the warehouses through which an enterprise ships (distributes) its products. In this example, the warehouse master data table 300 includes warehouse number information 301 and shipping origin information 303. The warehouse master data table 300 may be stored in the database 20 of the information processing server 10 or in the database 40 of the core system server 30.

[0052] (1-4-4. Product master data table) Figure 7 is the product master data table 400. The product master data table 400 contains information about the products manufactured and sold by an enterprise. In this example, the product master data table 400 includes product number information 401, product name information 403, product unit price information 405, and product description information 407. The product master data table 400 may be stored in the database 20 of the information processing server 10 or in the database 40 of the core system server 30.

[0053] (1-4-5. Core system information table) FIG. 8 shows the backbone system information table 500. The backbone system information table 500 contains information related to corporate activities associated with the backbone system. In this example, the backbone system information table 500 contains information related to orders. More specifically, the backbone system information table 500 includes an order number 501, order date information 502, customer name information 503, product name information 504, order quantity information 505, order unit price information 506, order amount information 507, and delivery date information 508. The backbone system information table 500 is stored in the database 40 of the backbone system server 30.

[0054] FIG. 9 shows the corporate special information data table 600. The corporate special information data table 600 contains special information unique to the company in conducting corporate activities. In this example, the corporate special information data table 600 includes a corporate special information number 601, item information 603, and corporate special information 605. The corporate special information data table 600 may be stored in the database 20 of the information processing server 10 or may be stored in the database 40 of the backbone system server 30.

[0055] (1-5. Information Processing Method) Subsequently, an information processing method realized in the information processing system in this embodiment will be described. FIGS. 9 to 12 are flowcharts showing the information processing of the information processing system 1 in this embodiment.

[0056] (1-5-1. Learning Process) Figures 10 to 11 are flowcharts showing pre-training processing for performing backbone system information generation support processing in the present embodiment. First, as shown in FIG. 14, a user interface 700 is displayed on the terminal device 50 (step S101). The user interface 700 is an input screen for user identification information for logging in. User identification information refers to information that can identify a user. In this example, the user interface 700 includes a user name input section 701, a password input section 703, and a login button 705, but the input content such as a company code or employee number can be changed as appropriate. Also, information other than text data such as face authentication data may be input. At this time, a user such as an information manager of a company inputs user identification information into the user interface 700 (step S103). The input user identification information is transmitted to the information processing server 10 (step S105), and the information processing server 10 acquires the user identification information (step S107). At this time, the information processing server 10 executes user authentication processing based on the user identification information (step S109). At this time, information (company identification information) for identifying the company to which the user belongs is authenticated (acquired) together with the user identification information. The company identification information may include a plurality of pieces of information for identifying a company.

[0057] When user authentication is completed, the information processing server 10 generates instruction information for displaying a backbone master data registration screen (step S111), and transmits the display instruction information for the backbone master data registration screen to the terminal device 50 (step S113). When the terminal device 50 acquires the instruction information, it displays a user interface for registering backbone master data on the display unit 54 (step S115). The user inputs information (backbone master data registration request information) regarding the backbone master data used in learning on the backbone master data registration request screen displayed on the terminal device 50 (S117). The input backbone master data registration request information is transmitted to the information processing server 10 (step S119), and the information processing server 10 acquires the backbone master data registration request information (step S121).

[0058] The information processing server 10 generates instruction information for requesting master data corresponding to the company identification information and basic system information for learning based on the core master data registration request information (step S123), and the instruction information is transmitted to the core system server 30 (step S125). The core system server 30 transmits the master data corresponding to the company identification information stored in the database 40 and the basic system information for learning to the information processing server 10 based on the acquired request information (step S127) (step S129). As a result, the information processing server 10 acquires the master data and the basic system information for learning (step S131). The acquired master data may be stored in the database 20.

[0059] In this example, the master data includes company-specific information (such as company-specific terms or business rules) based on user identification information (and company identification information). In this example, the master data includes customer master data shown in FIG. 4, business location master data shown in FIG. 5, warehouse master data shown in FIG. 6, and product master data shown in FIG. 7. Further, as the master data, company-specific special information specialized for each company as shown in FIG. 9 may be included. For example, the company-specific special information may include the closing month, quarter, company-specific business days, company-specific common language, etc., or may include document data such as the company's employment regulations, business procedure manuals, system manuals, API specifications, etc. Furthermore, the master data may include abbreviation data or specific business term data used within the company.

[0060] The basic system information for learning is a part of the basic system information stored in the database 40 of the basic system. As shown in FIG. 8, in this example, the basic system information table 500 includes the order number 501, order date information 502, customer name information 503, product name information 504, order quantity information 505, order unit price information 506, order amount information 507, and delivery date information 508, but may include other information as appropriate.

[0061] Next, the information processing server 10 can perform preprocessing on the core master data before the machine learning process (step S133). In this example, the information processing server 10 performs a split (vectorization) process on the core master data. As vectorization methods, various methods such as Bag of Words (BoW), TF-IDF (Term Frequency-Inverse Document Frequency), Word2Vec, and BERT (Bidirectional Encoder Representations from Transformers) are used. By converting the core master data (for example, text data) into vectors, the similarity between different sentences can be compared numerically. By vectorizing, numerical comparison and operation between data become possible, and it becomes easier to learn company-specific information.

[0062] Next, machine learning is performed using the acquired core master data (step S135). Known learning methods such as the backpropagation method and the genetic algorithm (GA) may be used for machine learning. At this time, information combined with the core master data and the company identification information may be applied as teacher data. By repeating the machine learning, a learned model is generated (step S137). This learned model is based on the relationship between the core system information and the company identification information characterizing the company to which the user belongs. Therefore, based on the company-specific business terms and rules understood by machine learning for the input information, results (reconstructed core system requirement information, second requirement information) based on company-specific information (knowledge) can be generated. Also, with the above learned model, it is possible to accurately respond to company-specific terms included in the user's question information.

[0063] Note that fine-tuning processing may be appropriately performed on the generated learned model using new data. Thereby, the performance of the learned model can be optimized.

[0064] (1-5-2. Core System Information Generation Support Process) Figs. 12 to 13 are flowcharts showing the core system information generation support process. First, an employee (user) of a company inputs user identification information into a user interface for logging in (see Fig. 14) based on the information processing program displayed on the terminal device 50 (steps S201, S203). The input information is transmitted to the information processing server 10 (step S205), and the information processing server 10 acquires the user identification information (step S207). At this time, the information processing server 10 executes user authentication processing based on the user identification information (step S209). As a result, the user identification information (and the company identification information associated with the user identification information) is authenticated.

[0065] When the user authentication is completed, the information processing server 10 generates instruction information for displaying a screen for inputting request information regarding the core system (core system request information, also referred to as "first request information") (step S211), and transmits the instruction information to the terminal device 50 (step S213). When the terminal device 50 acquires the instruction information, it displays a user interface 800 shown in Fig. 15 on the display unit 54 (step S215). The user interface 800 is an input screen for the core system request information. The user interface 800 includes a request information input unit 801 and a transmission button 803. The user inputs the core system request information on the input screen displayed on the terminal device 50 (step S217). Fig. 16 is a user interface 900 in which the core system request information is input. In this example, the following is input into the request information input unit 901. "Please display the sales list of Kawano Light Industry Co., Ltd. in the following order JKTKCD: Customer Code TKTKNM: Customer Name JYJYNO: Order Number JYJNBN: Product Number JYJYDT: Order Date JYJYTK: Order Unit Price JYJYSU: Order Quantity JYJYKN: Order Amount JYNBNK: Desired Delivery Date The input core system requirement information is transmitted to the information processing server 10 by pressing (clicking) the send button 903 (step S219), and the information processing server 10 acquires the core system requirement information (step S221).

[0066] Next, the information processing server 10 applies the acquired core system requirement information and user identification information to the learned model for calculation (step S223). At this time, the information processing server 10 executes an inference process so that the acquired core system requirement information conforms to the core system information of the company to which the user belongs through the calculation process using the learned model (step S225). As a result, the reconfigured (modified) core system requirement information (also referred to as "second requirement information") is generated and output (step S227).

[0067] Next, the information processing server 10 generates generation prompt information for generating desired core system information (also referred to as "answer core system information") corresponding to the modified core system requirement information (second core system requirement information) among the core system information stored in the core system 2 (step S229). FIG. 17 is an example of the generated generation prompt information 1000. At this time, an SQL statement configured to generate desired core system information is generated as the generation prompt information 1000. The generated generation prompt information (SQL statement) is transmitted to the core system server 30 (step S231), and the core system server 30 acquires the generation prompt information (step S233).

[0068] Next, the core system server 30 applies the acquired SQL statement to the generation model to generate core system information (response core system information) (step S235). At this time, general large language models (LLMs) such as ChatGPT (manufactured by OpenAI), BERT, T5, LLaMa, and Claude can be used as the generation model. Also, when generating the core system information, Graph RAG (Graph Retrieval-Augmented Generation) processing may be executed. Graph RAG refers to the process of applying a graph structure to search and generation processing. By performing Graph RAG processing, the relationships and structures between data can be utilized, enabling more advanced applications. The generated core system information may be one or multiple according to the second core system request information (generation prompt information). The generated core system information is transmitted to the information processing server 10 (step S237), and the information processing server 10 acquires the core system information (step S239).

[0069] Next, the information processing server 10 generates instruction information for displaying the acquired core system information (step S241). The generated display instruction information for the core system information is transmitted to the terminal device 50 (step S243), and the terminal device 50 acquires the core system information (step S245). Finally, as shown in FIG. 18, the terminal device 50 displays the user interface 1100 based on the acquired core system information on the display unit 54 (step S247). FIG. 18 is an example of the user interface 1100. The user interface 1100 is a display screen of the generated core system information. In this example, the user interface 1100 includes question information 1101, answer information 1103, and core system information 1105. In this example, the core system information 1105 is tabular data, but it may also be graph data, text data, or image data. Thus, the core system information generation support process ends.

[0070] By using this embodiment, since the learning process is performed in advance to conform to the core system requirement information according to each company, the content of the core system information acquisition request can be quickly understood, and the time required for acquiring the core system information can be shortened.

[0071] Also, by using this embodiment, the user only needs to intuitively input the request information in natural language using the user interface displayed on the terminal device 50, and request information composed of a programming language such as SQL based on natural language is generated, and the necessary core system information can be acquired. That is, by using this embodiment, the user can acquire the necessary core system information more conveniently and quickly than before without acquiring special technologies such as programming languages.

[0072] <Second Embodiment> In this embodiment, an information processing method different from that of the first embodiment will be described. Specifically, an example of generating prompt information by combining category information and request information displayed on the input screen of the terminal device will be described. Note that descriptions of parts overlapping with the first embodiment will be omitted as appropriate.

[0073] FIG. 19 is an example of the user interface 1200. The user interface 1200 is an input screen for core system request information. The user interface 1200 includes a category button 1205 in addition to the input unit 1201 and the send button 1203. The category button 1205 corresponds to the category (schema) of the core system information. In this example, as the category button 1205, category information corresponding to six categories is displayed. Specifically, the category information includes "Library 1. Sales and Order Related", "Library 2. Product and Inventory Related", "Library 3. Intra-company Personnel Related", "Library 4. In-out Stock Information", "Library 5. Master Information", and "Library 6. Others".

[0074] When the terminal device 50 acquires instruction information for displaying an input screen of backbone system requirement information, it displays a user interface 1200 (input screen) on the display unit 54. The user inputs backbone system requirement information to the user interface 1200 (step S115 in FIG. 12), and also inputs category information by pressing the category button 1205, and the information processing server 10 acquires the selected category information. In this case, in the subsequent backbone system information generation support process, the information processing server 10 generates generation prompt information based on the second requirement information and the category information. By using this embodiment, only the area corresponding to the category information is searched, and the generation process of the answer information (backbone system information) is executed. As a result, since the area to be searched is limited, the backbone system information can be generated more quickly.

[0075] <Third Embodiment> In this embodiment, an information processing method different from that of the second embodiment will be described. Specifically, an example of supporting the generation of basic system requirement information based on the category information displayed on the input screen of the terminal device will be described. Note that the description of the parts overlapping with the first and second embodiments will be omitted as appropriate.

[0076] FIG. 20 is an example of a user interface 1300. The user interface 1300 is an input screen for backbone system requirement information. The user interface 1300 includes a field candidate information 1307 and a question candidate information 1309 in addition to an input unit 1301, a transmission button 1303, and a category information button 1305. The field candidate information 1307 includes field information related to the category information. The question candidate information 1309 includes question information related to the category information.

[0077] Figure 21 is a flowchart showing the information processing (the generation process of backbone system request information) in this embodiment. As shown in Figure 21, in this embodiment, when the terminal device 50 acquires the instruction information for displaying the input screen of the backbone system request information, it displays the user interface 1200 of Figure 19 on the display unit 54 (step S215). The user inputs the category information by pressing (clicking) the category button 1205 (step S2161). At this time, the input category information is transmitted to the information processing server 10 (step S2162), and the information processing server 10 acquires the category information (step S2163). Next, the information processing server 10 generates the field candidate information and the question candidate information based on the acquired category information (step S2164).

[0078] When the field candidate information and the question candidate information are transmitted to the terminal device 50 (step S2165), as shown in Figure 20, the field candidate information 1307 and the question candidate information 1309 are displayed on the input screen (step S2166). In this example, based on the result that "Library 1. Sales and Order Related" and "Library 2. Product and Inventory Related" are selected as the category buttons 1205, 12 field candidate information and 6 question candidate information are displayed.

[0079] When the user selects (inputs) a part of the field candidate information and question candidate information displayed on the terminal device 50 (step S2167), the selected field (candidate) information and question (candidate) information are transmitted to the information processing server 10 (step S2168), and the information processing server 10 acquires the selected field (candidate) information and question (candidate) information (step S2169). In this example, the field information corresponding to the field (candidate) information "JYTKCD: customer code", "TKTKNM: customer name", "JYJYNO: order number", "JYJNBN: item number", "JYJYDT: order date", "JYJYTK: order unit price", "JYJYSU: order quantity", "JYJYKN: order amount", "JYJBNK: desired delivery date" is selected and input, and the question information corresponding to the question (candidate) information "Please tell me the sales list with the customer code 'TK1234'" is selected and input.

[0080] Next, the information processing server 10 generates backbone system information request candidate information (also referred to as "first request candidate information") based on the acquired field (candidate) information and question (candidate) information (step S21610). The backbone system request candidate information is information that is a candidate for the backbone system request information. The generated backbone system request candidate information is transmitted to the terminal device 50 (step S21611) and displayed on the input unit 1301 of the display unit 54 (step S21612).

[0081] At this time, the user may perform a correction input on the displayed backbone system request candidate information or leave it as it is. The backbone system request information is input by pressing the transmission button (step S217).

[0082] By using this embodiment, the user can easily generate the backbone system request information without having to think about detailed questions himself / herself. Also, since the information processing server 10 generates the backbone system request information, it is possible to prevent the subsequent backbone system information generation process from including ambiguous information. Therefore, the time required for the inference process and search can be shortened. Thus, the backbone system information can be generated more quickly.

[0083] In addition, in this embodiment, an example in which the information input to the terminal device 50 is sequentially acquired by the information processing server 10 has been shown, but the present invention is not limited to this. Based on an information processing program related to the generation support of the core system information acquired in advance by the terminal device 50, the terminal device 50 may generate field candidate information and question candidate information, and generate core system request candidate information.

[0084] <Fourth Embodiment> In this embodiment, an information processing system and an information processing method different from those of the first to third embodiments will be described. Specifically, an example in which different databases are provided for each category (schema) will be described. Note that the description of the parts overlapping with the first to third embodiments will be omitted as appropriate.

[0085] (4-1. Overall Configuration of Information Processing System) FIG. 22 is a diagram for explaining the information processing system 1A in this embodiment. The information processing system 1A includes an information processing server 10, a core system 2A (core system server 30A and database 40A), and a terminal device 50.

[0086] The core system server 30A is connected to a plurality of databases 40A (in this example, databases 40A-1, 40A-2, ···, 40A-N). Each of the plurality of databases 40A corresponds to a category (schema) of the core system information. For example, as shown in FIG. 18, different databases may be provided for the category information "Library 1. Sales and Order Related", "Library 2. Product and Inventory Related", "Library 3. Company Internal Personnel Related", "Library 4. Incoming and Outgoing Information", "Library 5. Master Information", and "Library 6. Others", respectively.

[0087] (4-2. Core System Information Generation Support Processing) When the terminal device 50 acquires instruction information for displaying an input screen for backbone system requirement information, it displays a user interface 1200 shown in FIG. 19 on the display unit 54. The user inputs the backbone system requirement information and also inputs category information by pressing a category information button. The information processing server 10 acquires the selected category information. At this time, in subsequent backbone system information generation support processing, the information processing server 10 generates generation prompt information (SQL syntax) corresponding to the category information. Further, in the present embodiment, the information processing server 10 may generate generation prompt information by adding information corresponding to the database corresponding to the category information. At this time, the information processing server 10 may correct at least a part of the generation prompt information according to the database information corresponding to the category information.

[0088] Specifically, for each database, "surrounding characters" surrounding each name such as "schema name", "table name", "column name", "alias", etc. may be set as additional information. In this case, the surrounding characters include double quotes, backticks, and curly braces. In addition to the surrounding characters, the upper limit value of the number of records (the number of rows of data stored in the database table), the data table name, the expression method of date and time, the output method of backbone system information, or other information may also be set as appropriate.

[0089] By using the present embodiment, generation prompt information (SQL) suitable for each database is generated, so that it is possible to easily and quickly access the necessary backbone system information without being affected by differences in databases.

[0090] <Fifth Embodiment> In the present embodiment, an information processing system and an information processing method different from those of the first to fourth embodiments will be described. Specifically, an example of restricting (excluding) a part of the backbone system information to be generated in accordance with the input user identification information will be described. Note that descriptions of parts overlapping with the first to fourth embodiments will be omitted as appropriate.

[0091] (5-1. Exclusion Data Table) FIG. 23 shows an exclusion data table 1400. The exclusion data table 1400 includes information whose generation is restricted among the core system information. In this example, the exclusion data table 1400 includes an exclusion number 1401, controlled information 1403, and target user information 1405. In this example, as the controlled information 1403, "unit price information", "trading partner information", and "unrelated information" are included. The exclusion data table 1400 is stored in the database 20.

[0092] (5-2. Core System Information Generation Support Process) FIG. 24 is a flowchart showing a generation prompt information generation process S225B for core system information. As shown in FIG. 24, first, the information processing server 10 acquires the second core system request information (step S227 in FIG. 13) generated through the inference process (step S2251). Next, the information processing server 10 acquires user identification information that is used at the time of user authentication and stored in the database 20 (step S2252).

[0093] Next, the information processing server 10 determines whether the acquired user identification information satisfies a predetermined condition (step S2253). In this example, the predetermined condition is to correspond to the target user information 1405 in the exclusion data table 1400. If the predetermined condition is not satisfied (step S2253; No), the information processing server 10 generates generation prompt information for unrestricted (normal) core system information (step S2254).

[0094] On the other hand, when the user identification information satisfies the predetermined condition (step S2253; Yes), the information processing server 10 adds (incorporates) control information to the core system request information. As a result, a part of the target core system information is set to be excluded from the generation prompt information. Finally, the information processing server 10 generates generation prompt information for restricted core system information based on the second core system request information to which the control information is added (step S2256). Thus, the generation prompt information generation process S225B ends.

[0095] By using this embodiment, it is possible to control the information that can be publicly disclosed according to the positions, departments, or other classification information within the company. As a result, while appropriately managing the company's information, it is possible to easily obtain the necessary core system information.

[0096] Note that in this embodiment, the core system information to be excluded may be set according to the degree of relevance between the target information and the user. For example, if an employee in the marketing department is determined to have a low degree of relevance to the personnel department, the core system information that can only be viewed by the employees in the personnel department may be excluded.

[0097] <Modification Example> The present disclosure is not limited to the above-described embodiments, and includes various other modification examples. For example, the above-described embodiments have been described in detail for the purpose of explaining the present disclosure clearly, and are not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add, delete, or replace other configurations for a part of the configuration of each embodiment. Hereinafter, some modification examples will be described. Note that the examples obtained by modifying each embodiment can also be applied as examples of modifying other embodiments.

[0098] In one embodiment of the present invention, an example of obtaining information (core master data) for each company using the terminal device 50 (company terminal) has been shown, but the present invention is not limited thereto. For example, in addition to companies, it is also applicable to sole proprietors, other corporations, hospitals, research institutes, and other organizations.

[0099] In the first embodiment of the present invention, an example of executing learning processing using core master data has been shown, but the present invention is not limited to this. For example, connection destination IP (Internet Protocol) information, or a database of the connection destination, etc. may also be acquired and learning processing may be executed. Thereby, information regarding a company can be learned more precisely.

[0100] Also, in the first embodiment of the present invention, an example of learning based on core master data existing in the core system server 30 or the database 40 has been shown, but the present invention is not limited to this. For example, learning processing may be executed based on information input to the terminal device 50. At this time, it may be uploaded as CSV data and used as core master data, or answer information for question information transmitted from the input information processing server 10 (or preset in the program) may be used as core master data. Also, learning processing may be executed based on information (answer information) input in response to question information transmitted from the information processing server 10 (or preset in the program). Further, the user may directly input core master information to the terminal device 50. FIG. 25 is an example of the user interface 1500. The user interface 1500 is an input of core master information (in this example, order registration information). The user interface 1500 includes order number information 1501, product name information 1503, quantity information 1505, amount information 1507, and a transmission button 1509. The user inputs the order number information 1501, product name information 1503, quantity information 1505, and amount information 1507, and by pressing (clicking) the transmission button 1509, the core master information is transmitted to the information processing server 10.

[0101] In the first embodiment of the present invention, an example was shown in which the information processing server 10 generates an SQL statement as generation prompt information for generating core system information, and instructs to display, extract, or search for the core system information. However, the present invention is not limited to this. For example, the information processing server 10 may instruct to execute different processes using the information stored in the core system server (or database). More specifically, among the processes (functions) prepared in advance, a process corresponding to an instruction (in this example, "send ○○ by email", "notify ~", etc.) may be selected and executed. Thereby, even when using natural language, it is possible to easily execute appropriate processes using the core system information for each company.

[0102] In the first embodiment of the present invention, an example was shown in which the information processing server 10 and the core system server 30 are separated. However, the present invention is not limited to this. In one embodiment of the present invention, the information processing server 10 and the core system server 30 may be configured by one server, the information processing server 10 may be configured by a plurality of servers according to functions, or further different servers (such as a web server, an application server, etc.) may be provided to execute each process according to the information processing system of one embodiment of the present invention.

[0103] In the first embodiment of the present invention, an example was shown in which preprocessing (vectorization) is performed in the learning process. However, the present invention is not limited to this. Vectorization processing may also be performed at the timing of generating the core system information.

Explanation of Reference Numerals

[0104] 1... Information processing system, 2... Core system, 2A... Core system, 10... Information processing server, 11... Control unit, 11a... Acquisition unit, 11b... Preprocessing unit, 11c... Machine learning unit, 11d... Inference processing unit, 11e... Generation unit, 11f... Display control unit, 12... Memory unit, 13... Communication unit, 20... Database, 30... Core system server, 30A... Core system server, 31... Control unit, 32... Memory unit, 33... Communication unit, 40... Database, 40A... Database, 40A-1... Database, 40A-2... Database, 40A-N... Database, 50... Terminal device, 51... Control unit, 52... Memory unit, 53... Communication unit, 54... Display unit, 55... Operation unit, 100... Customer master data table, 101... Customer number information, 103... Customer name information, 105... Zip code information, 107... Prefecture information, 109... Address information, 110... Customer master data table, 200... Business office master data table, 201... Business office number information, 203... Business office name information, 207... Prefecture information, 209... Address information, 300... Warehouse master data table, 301... Warehouse number information, 303... Shipping origin information, 400... Product master data table, 401... Product number information, 403... Product name information, 405... Product unit price information, 407... Product description information, 500... Core system information table, 501... Order number information, 502... Order date information, 503... Customer name information, 504... Product name information, 505... Order quantity information, 506... Order unit price information, 507... Order amount information, 508... Delivery date information, 600... Enterprise special information data table, 601... Enterprise special information number, 603... Item information, 605... Enterprise special information, 700... User interface, 701... User name input part, 703... Password input part, 705... Login button, 800... User interface, 801... Request information input part, 803... Send button, 900... User interface, 901... Request information input part, 903... Send button, 1000... Generation prompt information, 1100... User interface, 1101... Question information,1103 ··· Response information, 1105 ··· Core system information, 1200 ··· User interface, 1201 ··· Input section, 1203 ··· Send button, 1205 ··· Category button, 1300 ··· User interface, 1301 ··· Input section, 1303 ··· Send button, 1305 ··· Category information button, 1307 ··· Field candidate information, 1309 ··· Question candidate information, 1400 ··· Exclusion data table, 1403 ··· Control target information, 1405 ··· Target user information, 1500 ··· User interface, 1501 ··· Order number information, 1503 ··· Product name information, 1505 ··· Quantity information, 1507 ··· Amount information, 1509 ··· Send button,

Claims

1. An information processing method for assisting in generating core system information, comprising: a computer obtaining user identification information capable of identifying a user; obtaining first request information regarding a core system; applying the user identification information and the first request information to a learned model to generate second request information associated with the company to which the user belongs; generating instruction information for generating at least one response core system information corresponding to the second request information from among the core system information stored in the core system; wherein the learned model is based on the relationship between the core system information and company identification information characterizing the company to which the user belongs; information processing method.

2. The instruction information includes prompt information for generating SQL (Structured Query Language), The information processing method according to claim 1.

3. When generating the at least one response core system information, excluding a part of the core system information based on the user identification information, The information processing method according to claim 1.

4. The excluded core system information is set according to the degree of association with the user, The information processing method according to claim 3.

5. obtaining category information corresponding to the category of the core system information; further comprising generating the instruction information based on the second request information and the category information, The information processing method according to claim 1.

6. obtaining category information corresponding to the category of the core system information; further comprising correcting at least a part of the instruction information according to the database information corresponding to the category information, The information processing method according to claim 1.

7. The user interface displayed on the user's terminal device includes a plurality of category information corresponding to the category of the core system information, when at least one of the plurality of category information is selected, generating at least one question candidate information based on the selected category information, The information processing method according to claim 1.

8. The at least one question candidate information includes a plurality of question candidate information, ​ generating first request candidate information that is a candidate for the first request information when at least one piece of question candidate information among the plurality of pieces of question candidate information is selected The information processing method according to claim 7.

9. A program for causing a computer to execute the information processing method according to any one of claims 1 to 8.

10. An information processing system for assisting in generating core system information, comprising acquiring user identification information capable of identifying a user acquiring first request information regarding a core system applying the user identification information and the first request information to a learned model to generate second request information associated with the company to which the user belongs including a control unit that generates instruction information for generating at least one piece of answer core system information corresponding to the second request information among the core system information stored in the core system The learned model is based on the relationship between the core system information and company identification information characterizing the company to which the user belongs Information processing system

11. The instruction information includes prompt information for generating SQL (Structured Query Language). The information processing system according to claim 10.

12. The control unit when generating the at least one piece of answer core system information excludes a part of the core system information based on the user identification information The information processing system according to claim 10.

13. The excluded core system information is set according to the degree of relevance to the user The information processing system according to claim 12.

14. The control unit acquires category information corresponding to the category of the core system information generates the instruction information based on the second request information and the category information The information processing system according to claim 10.

15. The control unit acquires category information corresponding to the category of the core system information corrects at least a part of the instruction information according to the database information corresponding to the category information The information processing system according to claim 10.

16. The user interface displayed on the terminal device of the user includes a plurality of pieces of category information corresponding to the category of the core system information The control unit When at least one piece of category information among the plurality of pieces of category information is selected, at least one piece of question candidate information is generated based on the selected category information. The information processing system according to claim 10.

17. The at least one piece of question candidate information includes a plurality of pieces of question candidate information. The control unit When at least one piece of question candidate information among the plurality of pieces of question candidate information is selected, first request candidate information that is a candidate for the first request information is generated. The information processing system according to claim 16.

Images