RD project identification method, system and device applied to high-enterprise affirmation and medium

Abstract

The invention discloses an RD project identification method, system, equipment and medium applied to enterprise high-enterprise identification, and relates to the technical field of enterprise scientific and technological innovation management, the method comprises the following steps: obtaining a project document uploaded by a user, converting an unstructured project document into a numerical vector which can be learned by a machine, and storing the numerical vector in a database; processing the numerical vector of each project document by utilizing a classification model to obtain a classification result of the project documents; through entity technology identification and entity technology association identification, constructing a graph structure of an entity technology representing the project document and an association technology of the entity technology; generating a standard data set of the project documents based on a preset rule set and a fact set, and obtaining decision actions of the project documents; based on the classification result, the graph structure, the standard data set and the decision action, forming a project identification result of each project document; the problems that at present, RD items are difficult to recognize, material arrangement is tedious, rules are complex and difficult to follow, and data are dispersed and difficult to integrate are solved.

Description

Technical Field

[0001] The present invention relates to the field of enterprise scientific and technological innovation management technology, and more specifically, to RD project identification methods, systems, equipment and media applied to enterprise high-tech enterprise certification. Background Art

[0002] RD projects refer to the identification of enterprise R&D projects during the high-tech enterprise certification process. Traditional methods rely on manual organization, which is inefficient and prone to errors. Existing tools are mostly general document management systems that lack intelligent functions for high-tech enterprise certification and the ability to automatically parse and match high-tech enterprise certification rules. In general, existing technologies have the following problems: 1. Difficulty in identifying RD projects: Enterprises have a large number of R&D projects, and manual identification and classification are inefficient, and key projects are easily missed.

[0003] 2. Complicated material preparation: High-tech enterprise certification requires submission of a large amount of technical documents, which is time-consuming and error-prone when manually prepared.

[0004] 3. The rules are complex and difficult to follow: The rules for identifying high-tech enterprises are changing dynamically, and manual judgment of whether an enterprise meets the identification standards is subjective and uncertain.

[0005] 4. Data is scattered and difficult to integrate: Enterprise R&D data is scattered across different departments, making it difficult to organize and summarize. Summary of the Invention

[0006] The purpose of the present invention is to provide an RD project identification method, system, device and medium for use in high-tech enterprise certification to solve the problems existing in the above-mentioned background technology.

[0007] The above technical objectives of the present invention are achieved through the following technical solutions: First, this application provides an RD project identification method for high-tech enterprise certification, including the following specific steps: Obtain project documents uploaded by users, convert unstructured project documents into machine-learnable numerical vectors, and use a preset classification model to process the numerical vectors of each project document to obtain the classification results of the project documents; Through entity technology identification and entity technology association identification, a graph structure representing entity technology and its associated technologies of project documents is constructed; Generate a standard data set for project documents based on a preset set of rules and facts, and obtain decision actions for each project document based on the standard data set; Based on the classification results, graph structure, standard data set and decision actions, the project identification results of each project document are formed.

[0008] On the basis of the above technical solution, the present invention can also be improved as follows.

[0009] Furthermore, before processing the project documents, based on the strongly relevant keywords preset by the RD project, strong distinguishing features in each project document are screened, specifically: ; Where, represents the difference between the observed value and the expected value, represents the total number of features, Indicates the expected value, Represents the observed value.

[0010] Furthermore, the above converts unstructured project documents into machine-learnable numerical vectors, specifically: ; Where, represents the numerical vector obtained after transformation, is the word frequency, indicating the word t In the project documentation d Frequency of occurrence in To inverse document frequency, reduce the importance of common words.

[0011] Furthermore, the numerical vectors of each project document are processed using the preset classification model, specifically: ,and ; Where, represents the weight vector, Represents project documentation i A numeric vector of , represents the bias term, represents the slack variable, Represents a preset project document i The project category label, when the equation holds true for the project document i The category label that belongs to this type of project.

[0012] Furthermore, the above entity technical identification is specifically as follows: ; Where, Represents the input project document Tag sequence of attributed entity technology The conditional probability of represents the normalization factor, Indicates the length of the label sequence, represents the characteristic function, represents the number of characteristic functions, represents the label sequence at time step t, Represents model training parameters.

[0013] Furthermore, the entity-technology association identification mentioned above is specifically as follows: ; Where, Represents the association similarity of entity technology association identification, represents the query vector, represents the dimension of the key vector, represents the key vector, Indicates a value vector, superscript is the matrix transpose operation.

[0014] Furthermore, the above decision-making actions are specifically as follows: ; Where, Represents properties in project documents A For the dataset S The information gain of , i.e., the decision action; Representation dataset S Information entropy, which measures the uncertainty of data; Representation attributes A All possible values ​​of Representation attributes A The value is u A subset of Representation attributes A A specific value of Representation attributes The value is A subset of .

[0015] In a second aspect, the present application provides an RD project identification system for high-tech enterprise certification, which is applied to any of the RD project identification methods for high-tech enterprise certification in the first aspect, including: The first module is used to obtain project documents uploaded by users, convert unstructured project documents into machine-learnable numerical vectors, and use a preset classification model to process the numerical vectors of each project document to obtain the classification results of the project documents; The second module is used to construct a graph structure representing the entity technology and its associated technologies of the project document through entity technology identification and entity technology association identification; The third module is used to generate a standard data set of project documents based on a preset rule set and fact set, and obtain a decision action for each project document based on the standard data set; The fourth module is used to form project identification results for each project document based on classification results, graph structure, standard data set and decision actions.

[0016] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the methods in the first aspect when executing the computer program.

[0017] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to execute any one of the methods in the first aspect.

[0018] Compared with the prior art, the present invention has at least the following beneficial effects: In this application, by introducing natural language processing technology and intelligent algorithms, the system can conduct in-depth analysis of massive data within the enterprise and automatically identify R&D projects that meet the standards for high-tech enterprise certification; reduce the workload of traditional manual screening, improve recognition efficiency and accuracy, and at the same time reduce the risks caused by human omissions.

[0019] In this application, based on the support of knowledge graph and automated rule engine, the system can intelligently extract key information and automatically generate application materials that meet the requirements for high-tech enterprise certification; avoid errors or omissions that may be caused by manual operations, thereby greatly reducing the cost and complexity of material compilation.

[0020] In this application, authoritative high-tech enterprise recognition standards are preset, and dynamic updates and precise matching are achieved through a rule engine; during the generation of application materials, the system will automatically verify whether the content meets the relevant requirements to ensure that all submitted materials are highly compliant and avoid review failures due to deviations in the understanding of the standards.

[0021] In this application, in order to address the common problem of "data islands" in R&D management of enterprises, a unified data management platform can be built to centrally store, classify and efficiently utilize R&D data scattered across different departments and systems; promote cross-departmental collaboration, and provide solid data support for the company's long-term scientific and technological innovation strategy, helping to achieve more efficient resource allocation and decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings: Figure 1 A flowchart of an identification method according to an embodiment of the present invention; Figure 2 This is a connection diagram of an identification system in an embodiment of the present invention; Figure 3 Schematic diagram of the connection of electronic equipment in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0026] In the description of the embodiments of the present invention, "a plurality of" means at least two.

[0027] Example 1: In order to solve the current problems of difficulty in identifying RD projects, cumbersome material organization, complex rules that are difficult to follow, and scattered data that are difficult to integrate, this example provides an RD project identification method for high-tech enterprise certification, such as Figure 1 As shown, the following specific steps are included: S1, obtains the project documents uploaded by the user, converts the unstructured project documents into machine-learnable numerical vectors, and uses the preset classification model to process the numerical vectors of each project document to obtain the classification results of the project documents.

[0028] Specifically, before processing the project documents, based on the strongly relevant keywords preset in the RD project, the strong discriminative features in each project document are screened out. In order to screen out the keywords that are strongly relevant to the RD project from a large number of text features, the Chi-Square Test can be used for feature selection. This method calculates the correlation between features and categories to screen out the most discriminative features. Specifically: ; Where, represents the difference between the observed value and the expected value, represents the total number of features, Indicates the expected value, Represents the observed value.

[0029] Among them, the project documents uploaded by users include technical reports, patent documents, etc. In order to convert unstructured text data into machine-learnable numerical representations, the method of converting them into numerical vectors can be adopted. The above-mentioned method of converting unstructured project documents into machine-learnable numerical vectors is specifically as follows: ; Where, represents the numerical vector obtained after transformation, is the word frequency, indicating the word t In the project documentation d Frequency of occurrence in To inverse document frequency, reduce the importance of common words.

[0030] Furthermore, the constructed RD project classification model is used to process the numerical vectors of each project document, thereby obtaining the classification results of the project documents, specifically: ,and ; Where, represents the weight vector, Represents project documentation i A numeric vector of , represents the bias term, represents the slack variable, Represents a preset project document i The project category label, when the equation holds true for the project document i The category label that belongs to this type of project.

[0031] S2, through entity technology identification and entity technology association identification, construct a graph structure representing the entity technology and its associated technology of the project document.

[0032] The knowledge graph construction can extract entities and their relationships from documents and store them in a graph structure to form an enterprise's R&D technology association network. It can also extract technical entities (such as patent numbers and technical fields) from documents. Named entity recognition uses the conditional random field (CRF) model to model the sequence labeling task and identify key technical entities in the document. Specifically, the following methods can be used: ; Where, Represents the input project document Tag sequence of attributed entity technology The conditional probability of represents the normalization factor, Indicates the length of the label sequence, represents the characteristic function, represents the number of characteristic functions, represents the label sequence at time step t, Represents model training parameters.

[0033] Furthermore, relationship extraction is based on the attention mechanism. By calculating the similarity between the query vector, key vector, and value vector, it can extract the relationship between entities (i.e., entity-technology association). Relationship extraction can analyze the association between technical entities (such as "Project A depends on Technology B"). The above entity-technology association identification is specifically as follows: ; Where, Represents the association similarity of entity technology association identification, represents the query vector, represents the dimension of the key vector, represents the key vector, Indicates a value vector, superscript is the matrix transpose operation.

[0034] S3: Based on the preset rule set and fact set, a standard data set of the project documents is generated, and the decision action of each project document is obtained based on the standard data set.

[0035] This step is implemented through a rule engine algorithm, which uses dynamic rule matching and reasoning to achieve automated approval of high-tech enterprise certification standards. Rule matching is based on the Drools rule engine, which implements dynamic loading and matching of rules by defining rule sets and fact sets: ; : rule set, : Fact set, matching conditions: The prerequisites and The properties are consistent.

[0036] Furthermore, the decision actions for each project document can be obtained through decision tree path selection. The decision tree path selection selects the best splitting rule and optimizes the approval process by maximizing the information gain principle. The above decision actions are specifically: ; Where, Represents properties in project documents A For the dataset S The information gain of , i.e., the decision action; Representation dataset S Information entropy, which measures the uncertainty of data; Representation attributes A All possible values ​​of Representation attributes A The value is u A subset of Representation attributes A A specific value of Representation attributes The value is A subset of .

[0037] S4, based on the classification results, graph structure, standard data set and decision actions, forms the project identification results of each project document.

[0038] Among them, based on the classification results, graph structure, standard data set and decision actions obtained above, the project identification results of each project document are formed, and then the application materials are automatically generated through the generation tool and based on the template engine (the template engine usually generates documents by replacing placeholders, such as easyPoi).

[0039] In this embodiment, by combining NLP, knowledge graph and rule engine, intelligent organization and summarization of RD projects are achieved; at the same time, manual intervention is reduced through automated material generation process; it has the advantages of high RD project recognition accuracy, improved material generation efficiency, and improved compliance matching accuracy.

[0040] Example 2: This application embodiment provides an RD project identification system for high-tech enterprise certification, which is applied to the RD project identification method for high-tech enterprise certification in Example 1, such as Figure 2 Shown, including: The first module is used to obtain project documents uploaded by users, convert unstructured project documents into machine-learnable numerical vectors, and use a preset classification model to process the numerical vectors of each project document to obtain the classification results of the project documents; The second module is used to construct a graph structure representing the entity technology and its associated technologies of the project document through entity technology identification and entity technology association identification; The third module is used to generate a standard data set of project documents based on a preset rule set and fact set, and obtain a decision action for each project document based on the standard data set; The fourth module is used to form project identification results for each project document based on classification results, graph structure, standard data set and decision actions.

[0041] Example 3: To address the need for organizing and summarizing RD projects during the high-tech enterprise certification process, this embodiment of the application provides an intelligent management system. This system adopts a B / S architecture, is based on microservice design concepts, and combines natural language processing (NLP), knowledge graphs, and rule engine technologies to achieve automatic identification, classification, summarization, and application material generation for RD projects. The system architecture includes the following modules: 1. User management module: multi-role permission control (R&D personnel, reviewers, administrators); 2. RD project identification module: automatic identification and classification of R&D projects based on NLP; 3. Knowledge graph module: Build enterprise R&D technology association graph to support project association analysis; 4. Rule engine module: automatically matches high-tech enterprise identification rules and generates compliance reports; 5. Material generation module: automatically generate application materials for high-tech enterprise certification; 6. Data analysis module: RD project value assessment and application success rate prediction.

[0042] Furthermore, the above system realizes the organization and summary of RD projects through the following process: 1. Users upload R&D project documents (such as technical reports, patent documents, etc.).

[0043] 2. The system uses NLP technology to extract key project information (technical fields, innovation points, R&D investment, etc.).

[0044] 3. Analyze the technical correlation between projects based on knowledge graph.

[0045] 4. The rule engine automatically matches the high-tech enterprise identification standards and generates compliance reports.

[0046] 5. The system automatically generates application materials for high-tech enterprise certification and supports users to edit and export them online.

[0047] The following is a further description of each module in the system: 1. User layer (user management module): The user layer is the core interface for interaction between the system and end users. Corresponding functional modules are designed according to the needs of different roles: 1.1. R&D Personnel Functions: Submit R&D Project Documents: Supports uploading R&D project-related documents in multiple formats (such as PDF, Word, and Excel). View Project Identification Results: View the system's automatic identification results for submitted documents in real time, including key information such as technical areas, innovations, and R&D investment. View Compliance Reports: Obtain a compliance analysis report generated by the system based on the HSE recognition rules to determine whether the project meets the application requirements. Provide Feedback and Correction Suggestions: Allow R&D personnel to supplement or correct the system's identification results to improve data accuracy.

[0048] 1.2. Auditor Functions: Review RD Project Identification Results: Review the system-generated identification results to ensure their accuracy and comprehensiveness. Review Application Materials: Check whether the automatically generated application materials meet the HSE certification standards. Modify and Improve: Support online editing and modification of application materials. Generate Final Application Documents: Export the approved materials into a standardized format for formal submission.

[0049] 1.3. Administrator Functions: Manage system users and permissions: Create, delete, and manage user accounts, and assign permissions to different roles. Monitor system operation status: View system operation logs in real time, monitor resource usage and performance indicators. Data Backup and Recovery: Perform regular data backup tasks and provide one-click restore functionality. System Configuration Management: Adjust system parameters such as rule engine matching thresholds and knowledge graph update frequency.

[0050] 2. Application layer (including RD project identification module, knowledge graph module, rule engine module, material generation module and data analysis module): The application layer is the core functional module of the system, responsible for realizing intelligent RD project organization and induction.

[0051] 2.1. RD Project Identification Module. Functions: Automatically identify and classify R&D projects. This module uses NLP technology to extract key information from documents, identifying technical areas, R&D directions, and innovations. It also provides feedback on identification results, generating detailed identification reports and marking uncertain items for manual review. It also supports batch processing, enabling simultaneous processing of multiple documents, significantly improving work efficiency.

[0052] 2.2 Knowledge Graph Module, Functions: Build a technology association graph: Extract entities and their relationships from R&D projects to build an internal technology association network. Support project association analysis: Through graph analysis, potential connections between projects are discovered to support decision-making. Provide visualization: Present the technology association graph graphically for easy understanding and analysis.

[0053] 2.3. Rules Engine Module, Functions: Automated matching of HTE certification rules: Automatically verifies project compliance with application requirements based on the latest standards. Compliance report generation: Detailed listing of project compliance across various indicators, identifying areas for improvement. Dynamic rule base update: Supports real-time updates to the rule base, ensuring the system always adheres to the latest HTE certification standards.

[0054] 3. Service layer: The service layer provides underlying technical support for the application layer to ensure the efficient operation of the system.

[0055] 3.1. RD Project Identification Service, Function: Provides R&D project identification and classification services. Opens API interfaces to external systems, supporting third-party calls. Supports multilingual processing: Compatible with document processing in multiple languages, including Chinese and English. Real-time response: Ensures rapid response in high-concurrency environments.

[0056] 3.2 Knowledge Graph Service, Function: Provides technical correlation analysis services, supporting external system query and analysis of technical correlation graphs. Supports incremental updates, regularly updating graph data to maintain its timeliness. Provides a graph query interface, supporting complex query operations to meet diverse needs.

[0057] 3.3. Rule Matching Service, Function: Provides rule matching services for high-tech enterprise identification, supporting external system calls for rule matching. Supports dynamic rule loading, updating the rule base in real time based on standard changes. Provides matching result explanations, detailing the logic and basis for rule matching.

[0058] Example 4: This embodiment of the present application provides an electronic device, such as Figure 3 As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method of embodiment 1 is implemented.

[0059] Example 5: The embodiment of the present application provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable the computer to execute the method of Example 1.

[0060] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0064] Those skilled in the art will understand that all or part of the steps in implementing the above facts and methods can be completed by instructing relevant hardware through a program, and the program involved or the program can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: the corresponding method steps are then brought out, and the storage medium can be ROM / RAM, a disk, an optical disk, etc.

[0065] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The RD project identification method used in high-tech enterprise certification is characterized by: The specific steps include: Obtain project documents uploaded by users, convert unstructured project documents into machine-learnable numerical vectors, and use a preset classification model to process the numerical vectors of each project document to obtain the classification results of the project documents; Through entity technology identification and entity technology association identification, a graph structure representing entity technology and its associated technologies of project documents is constructed; Generating a standard data set of the project documents based on a preset rule set and a fact set, and obtaining a decision action for each project document based on the standard data set; Based on the classification results, the graph structure, the standard data set and the decision action, a project identification result for each of the project documents is formed.

2. The RD project identification method for high-tech enterprise certification according to claim 1 is characterized in that: The method further includes: before processing the project documents, based on the strongly relevant keywords preset by the RD project, screening to obtain strong distinguishing features in each project document, specifically: ； Where, represents the difference between the observed value and the expected value, represents the total number of features, Indicates the expected value, Represents the observed value.

3. The RD project identification method for high-tech enterprise certification according to claim 1 is characterized in that: Convert unstructured project documents into machine-learnable numerical vectors, specifically: ； Where, represents the numerical vector obtained after transformation, is the word frequency, indicating the word t In the project documentation d Frequency of occurrence in To inverse document frequency, reduce the importance of common words.

4. The RD project identification method for high-tech enterprise certification according to claim 1 is characterized in that: The numerical vectors of each project document are processed using the preset classification model, specifically: ； and: ; Where, represents the weight vector, Represents project documentation i A numeric vector of , represents the bias term, represents the slack variable, Represents a preset project document i The project category label, when the equation holds true for the project document i The category label that belongs to this type of project.

5. The RD project identification method for high-tech enterprise certification according to claim 1 is characterized in that: The entity technical identification is specifically: ； Where, Represents the input project document Tag sequence of attributed entity technology The conditional probability of represents the normalization factor, Indicates the length of the label sequence, represents the characteristic function, represents the number of characteristic functions, represents the label sequence at time step t, Represents model training parameters.

6. The RD project identification method for high-tech enterprise certification according to claim 1 is characterized in that: The entity technology association identification is specifically: ； Where, Represents the association similarity of entity technology association identification, represents the query vector, represents the dimension of the key vector, represents the key vector, Indicates a value vector, superscript is the matrix transpose operation.

7. The RD project identification method for high-tech enterprise certification according to claim 1 is characterized in that: The decision-making actions are specifically: ； Where, Represents properties in project documents A For the dataset S The information gain of , i.e., the decision action; Representation dataset S Information entropy, which measures the uncertainty of data; Representation attributes A All possible values ​​of Representation attributes A The value is u A subset of Representation attributes A A specific value of Representation attributes The value is A subset of .

8. An RD project identification system for high-tech enterprise certification, applied to an RD project identification method for high-tech enterprise certification according to any one of claims 1 to 7, characterized in that: include: The first module is used to obtain project documents uploaded by users, convert unstructured project documents into machine-learnable numerical vectors, and use a preset classification model to process the numerical vectors of each project document to obtain the classification results of the project documents; The second module is used to construct a graph structure representing the entity technology and its associated technologies of the project document through entity technology identification and entity technology association identification; A third module is configured to generate a standard data set of the project documents based on a preset rule set and a fact set, and obtain a decision action for each project document based on the standard data set; The fourth module is used to form a project identification result for each of the project documents based on the classification result, the graph structure, the standard data set and the decision action.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method according to any one of claims 1 to 7 is implemented when the processor executes the computer program.

10. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, which enable a computer to execute the method of any one of claims 1 to 7.

Images