Data analysis device, data analysis method, data analysis program, and data analysis system

Abstract

The data analysis device accepts request data that requests data analysis related to the manufacturing industry and is expressed in natural language. The data analysis device inputs the received request data into a pre-trained generative model and obtains response data output from the generative model. The data analysis device uses the analysis tool data, which represents the type of analysis tool to be used when performing the data analysis represented by the request data, the instruction data for the analysis tool, and the target data, which represents the data to be analyzed from among multiple types of data related to the manufacturing industry, all contained in the response data, to perform the data analysis represented by the request data, thereby obtaining data analysis results corresponding to the request data and outputting the data analysis results.

Description

Technical Field

[0001] The present disclosure relates to a data analysis apparatus, a data analysis method, a data analysis program, and a data analysis system.

Background Art

[0002] Conventionally, an operation method of a computer for managing a plurality of drawing data representing a set of components has been known (for example, Japanese Patent No. 7413445). This operation method includes a step of determining whether or not target drawing data included in a plurality of drawing data is related to existing drawing data already stored, and when the result of the determination is affirmative, a step of acquiring performance information when the performance information associated with the existing drawing data is stored, and a step of transmitting performance display information for displaying the performance information to a terminal. The determination includes a determination as to whether the existing drawing data represents a component having the same attributes as the component represented by the target drawing data, and the attributes are materials, surface treatments, processing methods, or combinations of two or more of these.

[0003] In addition, a technique of using a large language model for analyzing patent information to provide new value has been known (for example, Japanese Patent No. 7421740). A patent information analysis program corresponding to this technique causes a computer to execute steps of acquiring technical information including a technical idea, acquiring target patent information to be compared with the technical information, specifying the technical information and the patent information for a predetermined instruction sentence for evaluating the relevance of the two pieces of information from a specific perspective, and outputting an evaluation result indicating the relevance between the technical information and the patent information for the perspective based on the result obtained from the large language model by inputting the specified instruction sentence of the technical information and the patent information into the large language model. [[ID=*********]] [[ID=*********]]

[0004] [[ID=*********]] Furthermore, a building drawing creation support system suitable for adapting editable elements in building drawings to the specifications of a finishing schedule is known (for example, Japanese Patent No. 7341581). In this building drawing creation support system, the drawing creation support device 100 inputs a request to a large-scale language model that includes finishing schedule data and editing elements, and a request to generate conformance element information relating to conformance elements that conform to the specifications of those finishing elements and are described in the building drawing. The drawing creation support device 100 then obtains the conformance element information output from the large-scale language model in response to the request, and if the obtained editing element and the conformance element do not match, it displays a message indicating that there is a defect in the editing element. [Overview of the project] [Problems that the invention aims to solve]

[0005] By the way, it is difficult to easily analyze data related to the manufacturing industry. For example, data related to the manufacturing industry may include multiple types of data, such as image data (e.g., drawing data), document data (e.g., text in drawings or various specifications and reports related to manufacturing), and numerical data (e.g., sales data of manufactured products or dimensional data in drawings). In such a situation, if a user wants to analyze this manufacturing-related data and obtain analysis results, it is often not immediately clear which data to analyze and how to analyze it in order to obtain the desired results.

[0006] The technologies disclosed in the above-mentioned Japanese Patent Publications No. 7413445, No. 7421740, and No. 7341581 do not take into consideration the problems that exist when analyzing data related to the manufacturing industry.

[0007] This disclosure is made in light of the circumstances described above, and aims to simplify data analysis when manufacturing-related data consists of multiple types of data. [Means for solving the problem]

[0008] To achieve the above objective, a first aspect of this disclosure is a data analysis device that includes: a receiving unit that receives request data expressing in natural language, which is request data for data analysis relating to the manufacturing industry; a response data acquisition unit that acquires response data output from a pre-trained generative model by inputting the received request data to the generative model; and an analysis unit that acquires data analysis results corresponding to the request data and outputs the data analysis results by performing the data analysis representing the request data using analysis tool data, which is included in the response data, which represents the type of analysis tool to be used when performing the data analysis representing the request data; instruction data for the analysis tool; and data to be analyzed, which represents the data to be analyzed from among multiple types of data relating to the manufacturing industry.

[0009] Furthermore, a second aspect of this disclosure is a data analysis method in which a computer performs the processing, which involves receiving request data that requests data analysis relating to the manufacturing industry and is expressed in natural language, inputting the received request data to a pre-trained generative model to obtain response data output from the generative model, and using analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, instruction data for the analysis tool, and data to be analyzed, which represents the data to be analyzed from among multiple types of data relating to the manufacturing industry, to perform the data analysis represented by the request data, thereby obtaining data analysis results corresponding to the request data and outputting the data analysis results.

[0010] Furthermore, a third aspect of this disclosure is a data analysis program for causing a computer to perform a process that receives request data expressing in natural language, which is request data analysis relating to the manufacturing industry, inputs the received request data to a pre-trained generative model to obtain response data output from the generative model, and uses analysis tool data, which is included in the response data, which represents the type of analysis tool to be used when performing the data analysis represented by the request data, instruction data for the analysis tool, and data to be analyzed, which is data among multiple types of data relating to the manufacturing industry to be analyzed, to perform the data analysis represented by the request data to obtain data analysis results corresponding to the request data and output the data analysis results. [Effects of the Invention]

[0011] According to this disclosure, when manufacturing-related data consists of multiple types of data, the effect is that data analysis can be easily performed. [Brief explanation of the drawing]

[0012] [Figure 1] This figure shows an example of the schematic configuration of the data analysis system of this embodiment. [Figure 2] This figure shows an example of data related to the manufacturing industry. [Figure 3] This is an example of a screen displayed on the user terminal's display unit. [Figure 4] This is an example of a screen displayed on the user terminal's display unit. [Figure 5] This is an example of a screen displayed on the user terminal's display unit. [Figure 6] This is an example of a screen displayed on the user terminal's display unit. [Figure 7] This is an example of a screen displayed on the user terminal's display unit. [Figure 8] This is a schematic block diagram of the computers that function as each component in a data analysis system. [Figure 9] This diagram illustrates the processes performed by the data analysis system of this embodiment. [Modes for carrying out the invention]

[0013] The embodiments will be described in detail below with reference to the drawings.

[0014] <System Configuration of Data Analysis System>

[0015] Figure 1 is a block diagram of the data analysis system 10 of this embodiment. As shown in Figure 1, the data analysis system 10 of this embodiment comprises a data analysis device 16 and a plurality of user terminals 18A, 18B, 18C. In the following, unless a specific terminal is being referred to, one user terminal will be referred to as user terminal 18. The data analysis device 16 and the user terminals 18 are connected to each other via a network 19, such as the Internet.

[0016] The data analysis system 10 of this embodiment simplifies data analysis when the data related to the manufacturing industry consists of multiple types of data.

[0017] FIG. 2 shows an example of data related to manufacturing. As shown in FIG. 2, for example, when the manufacturing industry is related to metal processing, multiple types of data such as the ID of the metal processed product, price, drawing number of the drawing on which the metal processed product is drawn, name, material, surface finish, maximum dimension, thickness, and processing category become the analysis target data. Note that the data shown in FIG. 2 is an example, and for example, as multiple types of data related to the manufacturing industry, various types of data are assumed. For example, as multiple types of data related to the manufacturing industry, manufacturing document data, which is document data related to the object displayed in the drawing data, manufacturing numerical data, which is numerical data related to the object displayed in the drawing data, drawing document data, which is document data existing in the drawing data, and drawing numerical data, which is numerical data existing in the drawing data, etc. are assumed. Thus, when data related to the manufacturing industry is composed of multiple types of data, it is difficult to execute the data analysis.

[0018] Therefore, the data analysis system 10 of the present embodiment uses a large language model, which is an example of a pre-trained generation model, to execute data analysis on data related to the manufacturing industry.

[0019] FIGS. 3 to 7 are diagrams for explaining an example of the operation of the data analysis system 10 of the present embodiment. As shown in FIG. 3, the data analysis system 10 causes a dialogue-style screen S to be displayed on the display unit of the user terminal 18 between the user.

[0020] The user operates their own user terminal 18 to input a message, which is request data expressed in natural language, into the input field B1 and presses the "Send" button. For example, the user inputs a message "Please create a price distribution" as shown in FIG. 1 into the input field B1.

[0021] The data analysis device 16 receives a message input by a user and inputs the message into a large language model. Then, based on the response data output from the large language model, the data analysis device 16 identifies analysis target data from multiple types of data stored in at least one or more databases, performs an analysis using the analysis target data, and outputs the analysis result. Specifically, the data analysis device 16 outputs an analysis result R1 as shown in FIG. 1.

[0022] Also, for example, when a message such as "Please create a scatter plot of X price and Y price" as shown in FIG. 4 is input into the input field B1, the data analysis device 16 outputs an analysis result R2 as shown in FIG. 4.

[0023] Also, for example, when a message such as "Please present drawing data similar to the drawing data of drawing number xxx" as shown in FIG. 5 is input into the input field B1, the data analysis device 16 outputs an analysis result R3 as shown in FIG. 5. Each of the squares in the analysis result R3 is drawing data. Since the database of this embodiment also stores drawing data, the data analysis device 16 can also output an analysis result R3 as shown in FIG. 5.

[0024] Also, as shown in FIG. 6, it is possible to display a file input field B3 on the screen S. Therefore, the user can also use the data in the file D1 as analysis target data by dragging and dropping the file D1.

[0025] Furthermore, as shown in Figure 7, the analysis objective input field B4 can also be displayed on screen S. By inputting the analysis objective, the large-scale language model can output response data that aligns with the analysis objective. For example, as shown in Figure 7, the user can enter the analysis objective "Review of suppliers" in the analysis objective input field B4 and "First, please calculate the order amount and number of items for each supplier" in input field B1. In this case, for example, as shown in Figure 7, analysis results R4 and R5 will be output. Analysis result R4 is information representing the analysis procedure, and selecting P in the figure will display the program code used for the analysis.

[0026] The following provides a detailed explanation.

[0027] (Data analysis device 16) The data analysis device 16 is a server for analyzing data. As shown in Figure 1, the data analysis device 16 functionally comprises a reception unit 20, a response data acquisition unit 22, an analysis unit 24, a generation model storage unit 26, a manufacturing document database 28, a drawing document related database 30, a drawing database 32, and a manufacturing structured database 34.

[0028] The generative model memory unit 26 stores a large-scale language model, which is an example of a generative model. The large-scale language model is a model that has been pre-built using known artificial intelligence and machine learning techniques. Furthermore, the large-scale language model can also process image data.

[0029] The manufacturing document database 28 stores manufacturing document data, which is document data related to the object displayed in the drawing data. Manufacturing document data includes, for example, various specifications related to the manufactured product, customer catalogs, or reports related to the manufactured product.

[0030] The drawing document-related database 30 stores drawing document data, which is document data present within the drawing data, and drawing numerical data, which is numerical data present within the drawing data. Drawing document data is, for example, document data present in the title block drawn in the drawing data, and includes not only text but also symbols related to processing, etc. Drawing numerical data is, for example, numerical data such as the dimensions of objects depicted in the drawing data.

[0031] The drawing database 32 stores drawing data of manufactured products.

[0032] The manufacturing structured database 34 stores structured data related to objects displayed in the drawing data. Structured data may include data with various attributes. For example, structured data may include numerical data with attributes such as the dimensions, cost, unit price, production quantity, or sales quantity of the object, or textual information with attributes such as product name, material name, supplier name, or customer name.

[0033] Therefore, in this embodiment, at least one database stores multiple types of data related to the manufacturing industry. Furthermore, these multiple types of data related to the manufacturing industry include drawing data.

[0034] (User terminal 18) The user terminal 18 is a terminal operated by the user. Specifically, the user exchanges information with the data analysis device 16 by operating the user terminal 18.

[0035] Each of the data analysis device 16 and user terminal 18 of the data analysis system 10 can be implemented, for example, by a computer 70 as shown in Figure 8. The computer 70 includes a CPU 71, a memory 72 as a temporary storage area, and a non-volatile storage unit 73. The computer 70 also includes an input / output interface (I / F) 74 to which input / output devices (not shown) are connected, and a read / write (R / W) unit 75 that controls the reading and writing of data to the recording medium. The computer 70 also includes a network I / F 76 that connects to a network such as the Internet. The CPU 71, memory 72, storage unit 73, input / output I / F 74, R / W unit 75, and network I / F 76 are connected to each other via a bus 77.

[0036] The storage unit 73 can be implemented using a hard disk drive (HDD), solid state drive (SSD), flash memory, etc. The storage unit 73, as a storage medium, stores the program necessary for the computer 70 to function. The CPU 71 reads the program from the storage unit 73, loads it into memory 72, and sequentially executes the processes contained in the program.

[0037] <Function of Data Analysis System 10>

[0038] Next, the operation of the data analysis system 10 of this embodiment will be described.

[0039] The user operates their user terminal 18 to input request data related to manufacturing data analysis, expressed in natural language (for example, "Please create a price distribution" in Figure 3), into input field B1 on screen S. The data analysis device 16 executes the data analysis processing routine shown in Figure 9.

[0040] In step S100, the reception unit 20 receives the request data entered by the user. At this time, the user may, for example, input a file D1 as shown in Figure 6 into the screen S, thereby making data D1 the data to be analyzed.

[0041] In step S102, the response data acquisition unit 22 inputs the request data received in step S100 into the large-scale language model stored in the generative model storage unit 26. The response data acquisition unit 22 also inputs the analysis tool list, which is a list of tools used for analysis, into the large-scale language model stored in the generative model storage unit 26.

[0042] In step S104, the response data acquisition unit 22 acquires the response data output from the large-scale language model.

[0043] The response data output from the large-scale language model of this embodiment includes analysis tool data representing the type of analysis tool to be used when performing the data analysis represented by the request data, instruction data for the analysis tool, and analysis target data representing the data to be analyzed from among multiple types of data related to the manufacturing industry.

[0044] For example, let's consider a case where the requested data is "10 results with the highest actual prices, limited to those with blackening as the surface treatment." In this case, "10 results with the highest actual prices, limited to those with blackening as the surface treatment" and the analysis tool list are input into the large-scale language model. Additionally, prompts to output appropriate response data are also input to the large-scale language model.

[0045] In this case, the large-scale language model outputs response data such as "Extract to manufacturing data (argument: SELECT * …)". Of this response data, "manufacturing data" corresponds to the data to be analyzed among several types of data related to manufacturing. Furthermore, "Extract" in the response data corresponds to the analysis tool data, representing the type of analysis tool used when performing the data analysis. Finally, "(argument: SELECT * …)" in the response data corresponds to the instruction data for the analysis tool. This instruction data is, for example, actual program code. Therefore, in the above example, the data to be analyzed is manufacturing data, the analysis tool is an extraction tool, and the specific instruction data is "SELECT * …..".

[0046] In step S106, the analysis unit 24 uses the analysis tool data, the instruction data for the analysis tool, and the data to be analyzed, which are included in the response data obtained in step S102, to perform the data analysis represented by the request data received in step S100, thereby obtaining the data analysis result corresponding to the request data.

[0047] For example, the analysis unit 24 executes the program code "SELECT * …" which is the instruction data, on the manufacturing structure database 34 where the "manufacturing data" to be analyzed is stored, using an analysis tool corresponding to the analysis tool data "extraction" included in the response data. This executes a query on the manufacturing document database 28 according to the requested data. Note that the analysis tool corresponding to "extraction" corresponds to at least one of the analysis tools listed in the analysis tool list, for example. In the above example, the case where analysis is selected from the word "extraction" was explained, but in some cases, a specific analysis tool name may be output from the large-scale language model instead of the word "extraction". Then, for example, the analysis unit 24 obtains the query result table: "id, price, surface treatment, …". Next, the analysis unit 24 performs specific analysis processing using the query result table: "id, price, surface treatment, …". For example, the analysis unit 24 obtains analysis results according to the requested data by inputting the query result table "id, price, surface treatment, …", the requested data "10 items with the highest actual prices, limited to blackening surface treatment", and a predetermined prompt to the large-scale language model. When performing a specific analysis, the analysis unit 24 may use known analytical processing tools instead of large-scale language models.

[0048] Furthermore, if drawing data is identified as the data to be analyzed, the analysis unit 24 analyzes the drawing data, for example, by using a known image analysis tool. For example, if the analysis unit 24 aims to obtain an analysis result R3 as shown in Figure 5, it analyzes the image data corresponding to the drawing data stored in the drawing database 32 using a known image analysis tool, and obtains the analysis result R3 as shown in Figure 5 by analyzing the image features within the drawing data. Alternatively, the analysis unit 24 may also analyze the document data and numerical data within the drawing data using a known image analysis tool.

[0049] In step S108, the analysis unit 24 outputs the analysis results obtained in step S106, and this processing routine ends.

[0050] The analysis results output from the analysis unit 24 are sent to the user terminal 18. The user then checks the analysis results displayed on the display unit (not shown) of their user terminal 18.

[0051] As described above, the data analysis device according to this embodiment receives request data that requests data analysis related to the manufacturing industry and is expressed in natural language. The data analysis device then inputs the received request data to a large-scale language model, which is an example of a pre-trained generative model, and obtains response data output from the large-scale language model. The data analysis device uses the analysis tool data, which represents the type of analysis tool to be used when performing the data analysis represented by the request data, the instruction data for the analysis tool, and the data to be analyzed from among multiple types of data related to the manufacturing industry, all contained in the response data, to perform the data analysis represented by the request data and obtain data analysis results corresponding to the request data. The data analysis device then outputs the data analysis results. This makes it possible to easily perform data analysis when data related to the manufacturing industry consists of multiple types of data.

[0052] Furthermore, in this embodiment, at least one database stores multiple types of data related to the manufacturing industry, and these multiple types of data related to the manufacturing industry include drawing data. When drawing data is identified as the data to be analyzed, the data analysis device analyzes the drawing data using an image analysis tool. This makes it possible to easily perform data analysis even when drawing data is included in the data related to the manufacturing industry.

[0053] Furthermore, by using data analysis equipment, it becomes possible to simultaneously analyze multiple types of data, such as images (e.g., drawing data) and documents (e.g., text in drawings or various specifications and reports), as well as numerical data such as sales figures or dimensions of manufactured products. This makes it possible for users to perform analyses related to manufacturing even without specialized knowledge.

[0054] Traditionally, manufacturing data, such as drawing data (image data) and sales data (numerical data) for the products depicted in those drawings, have been handled in separate data formats, systems, methods, and locations. In contrast, the data analysis device of this embodiment allows users to specify an image via prompts and perform processes such as displaying sales figures. Furthermore, user instructions can be given in natural language, eliminating the need for data extraction processes using programming languages. Additionally, the steps required for data analysis—data extraction, formatting, and visualization—can be performed through a single interactive screen using simple prompts.

[0055] This disclosure is not limited to the embodiments described above, and various modifications and applications are possible without departing from the gist of this disclosure.

[0056] For example, in the above embodiment, the data analysis device 16 was described as having a large-scale language model, which is an example of a generative model, in its own memory unit, the generative model memory unit 26, but it is not limited to this. For example, the data analysis device 16 may utilize a large-scale language model provided via the network 19 from an external large-scale language model system different from the data analysis device 16.

[0057] Furthermore, the large-scale language model in the above embodiment may be a model that has been pre-trained to output analysis tool data, instruction data, and data to be analyzed when request data is input (a so-called fine-tuned model).

[0058] Furthermore, although the above embodiment describes a case where the data analysis device 16 has various databases of its own, it is not limited to this. For example, the data analysis device 16 may acquire various data from an external database different from the data analysis device 16 via the network 19. Also, although the above embodiment describes a case where multiple types of data related to the manufacturing industry are stored in multiple databases, it is not limited to this. Multiple types of data related to the manufacturing industry may be stored in a single database.

[0059] Furthermore, in the above embodiment, each process that the CPU reads and executes software (programs) may be executed by various processors other than the CPU. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits that are processors with circuit configurations specifically designed to execute specific processes, such as ASICs (Application Specific Integrated Circuits). Each process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0060] Furthermore, although the above embodiment describes a configuration in which each program is pre-stored (installed) on a storage device, the invention is not limited to this configuration. Programs may be provided in a form stored on a storage medium such as a CD-ROM, DVD-ROM, Blu-ray disc, or USB memory. Programs may also be provided in a form that can be downloaded from an external device via a network.

[0061] (Note) The following is an addendum regarding the nature of this disclosure.

[0062] (Note 1) A receiving unit that receives request data for data analysis related to the manufacturing industry, and that is expressed in natural language. A response data acquisition unit obtains response data output from a pre-trained generative model by inputting the received request data to the generative model. An analysis unit that uses analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, instruction data for the analysis tool, and data to be analyzed, which represents the data to be analyzed from among multiple types of data related to the manufacturing industry, to perform the data analysis represented by the request data, thereby obtaining the data analysis results corresponding to the request data and outputting the data analysis results, A data analysis device that includes [specific components / features]. (Note 2) At least one database contains multiple types of data related to the manufacturing industry. The data analysis device described in Appendix 1. (Note 3) The various types of data related to the manufacturing industry include drawing data. When drawing data is identified as the data to be analyzed, the analysis unit analyzes the drawing data using an image analysis tool. A data analysis device as described in Appendix 1 or Appendix 2. (Note 4) The various types of data related to manufacturing include manufacturing document data, which is document data relating to the object displayed in the drawing data; manufacturing numerical data, which is numerical data relating to the object displayed in the drawing data; drawing document data, which is document data present in the drawing data; and drawing numerical data, which is numerical data present in the drawing data. A data analysis device as described in any one of the items in Appendix 1 to Appendix 3. (Note 5) At least a portion of the data to be analyzed is data entered by the user. A data analysis device as described in any one of the appendices 1 to 4. (Note 6) When the response data acquisition unit outputs the response data from the generation model, it inputs the analysis tool data and the instruction data and prompts to the generation model, thereby acquiring the response data which includes the analysis tool data, the instruction data and the data to be analyzed. A data analysis device as described in any one of the items in Appendix 1 to Appendix 5. (Note 7) When the response data acquisition unit outputs the response data from the generation model, it inputs the request data and the analysis tool list, which is a list of tools used for analysis, into the generation model. The data analysis device described in Appendix 6. (Note 8) The generation model is a model that has been pre-trained so that when the request data is input, the analysis tool data, the instruction data, and the data to be analyzed are output. A data analysis device as described in any one of the items in Appendix 1 to Appendix 7. (Note 9) We accept request data that requests data analysis related to the manufacturing industry, and that is expressed in natural language. By inputting the received request data into a pre-trained generative model, the response data output from the generative model is obtained. By using the analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, the instruction data for the analysis tool, and the data to be analyzed from among multiple types of data related to the manufacturing industry, the data analysis represented by the request data is performed to obtain the data analysis results corresponding to the request data and output the data analysis results. A data analysis method in which a computer performs the processing. (Note 10) We accept request data that requests data analysis related to the manufacturing industry, and that is expressed in natural language. By inputting the received request data into a pre-trained generative model, the response data output from the generative model is obtained. By using the analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, the instruction data for the analysis tool, and the data to be analyzed from among multiple types of data related to the manufacturing industry, the data analysis represented by the request data is performed to obtain the data analysis results corresponding to the request data and output the data analysis results. A data analysis program that instructs a computer to perform processing. (Note 11) A data analysis system including multiple user terminals and a data analysis device described in any one of the items 1 to 8 of the appendix, Any one of the user terminals transmits the request data to the data analysis device. The data analysis device receives the request data transmitted from the user terminal and transmits the data analysis result corresponding to the request data to the user terminal. The user terminal displays the data analysis results on a display unit. A data analysis system.

[0063] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

Claims

1. A receiving unit that receives request data for data analysis related to the manufacturing industry, and that is expressed in natural language. A response data acquisition unit obtains response data output from a pre-trained generative model by inputting the received request data to the generative model. An analysis unit that uses analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, instruction data for the analysis tool, and data to be analyzed, which represents the data to be analyzed from among multiple types of data related to the manufacturing industry, to perform the data analysis represented by the request data, thereby obtaining the data analysis results corresponding to the request data and outputting the data analysis results, A data analysis device that includes [specific components / features].

2. At least one database contains multiple types of data related to the manufacturing industry. The data analysis apparatus according to claim 1.

3. The various types of data related to the manufacturing industry include drawing data. When drawing data is identified as the data to be analyzed, the analysis unit analyzes the drawing data using an image analysis tool. A data analysis apparatus according to claim 1 or claim 2.

4. The various types of data related to the manufacturing industry include: Manufacturing document data, which is document data relating to the object displayed in the drawing data, Manufacturing numerical data, which is numerical data relating to the object displayed in the aforementioned drawing data, The drawing document data is document data that exists within the aforementioned drawing data, The drawing data includes numerical data that exists within the aforementioned drawing data, A data analysis apparatus according to claim 1 or claim 2.

5. At least a portion of the data to be analyzed is data entered by users. A data analysis apparatus according to claim 1 or claim 2.

6. When the response data acquisition unit outputs the response data from the generation model, it inputs the analysis tool data and the instruction data and prompts to the generation model, thereby acquiring the response data which includes the analysis tool data, the instruction data and the data to be analyzed. A data analysis apparatus according to claim 1 or claim 2.

7. When the response data acquisition unit outputs the response data from the generation model, it inputs the request data and the analysis tool list, which is a list of tools used for analysis, into the generation model. The data analysis apparatus according to claim 6.

8. The generation model is a model that has been pre-trained so that when the request data is input, the analysis tool data, the instruction data, and the data to be analyzed are output. A data analysis apparatus according to claim 1 or claim 2.

9. We accept request data that requests data analysis related to the manufacturing industry, and that is expressed in natural language. By inputting the received request data into a pre-trained generative model, the response data output from the generative model is obtained. By using the analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, the instruction data for the analysis tool, and the data to be analyzed from among multiple types of data related to the manufacturing industry, the data analysis represented by the request data is performed to obtain the data analysis results corresponding to the request data and output the data analysis results. A data analysis method in which a computer performs the processing.

10. We accept request data that requests data analysis related to the manufacturing industry, and that is expressed in natural language. By inputting the received request data into a pre-trained generative model, the response data output from the generative model is obtained. By using the analysis tool data, which is included in the response data and represents the type of analysis tool to be used when performing the data analysis represented by the request data, the instruction data for the analysis tool, and the data to be analyzed from among multiple types of data related to the manufacturing industry, the data analysis represented by the request data is performed to obtain the data analysis results corresponding to the request data and output the data analysis results. A data analysis program that instructs a computer to perform processing.

11. A data analysis system comprising a plurality of user terminals and a data analysis device according to claim 1 or claim 2, Any one of the user terminals transmits the request data to the data analysis device. The data analysis device receives the request data transmitted from the user terminal and transmits the data analysis result corresponding to the request data to the user terminal. The user terminal displays the data analysis results on a display unit. A data analysis system.

Images