Real-scene three-dimensional achievement quality inspection knowledge graph management system

Abstract

The invention provides a live-action three-dimensional achievement quality inspection knowledge graph management system. The system comprises the following steps: step 1, integrating existing reference data and related data; 2, unifying quality inspection standards and evaluation standards of the live-action three-dimensional achievements; and step 3, establishing an ontology model, and applying the standard to a live-action three-dimensional result quality inspection activity. According to the method, the blank of the real-scene three-dimensional achievement quality inspection knowledge graph is filled, aiming at real-scene three-dimensional achievement quality inspection, a quality inspection knowledge graph framework is designed, a quality inspection ontology model is established, meanwhile, a knowledge graph updating mechanism is established, and a solid foundation is laid for intelligent quality inspection and achievement evaluation. According to the method, the problems that real-scene three-dimensional achievement quality inspection work has high requirements for personnel quality and traditional inspection work is low in efficiency are solved, the quality inspection knowledge graph is applied to the inspection work, quality inspection personnel can be helped to rapidly obtain knowledge bases of corresponding achievement inspection schemes, evaluation knowledge and the like, existing inspection knowledge is rapidly called, and the quality inspection efficiency is improved. And the quality inspection efficiency of inspectors is improved.

Description

Technical Field

[0001] The present invention relates to the field of product inspection technology, and in particular to a real-life three-dimensional product quality inspection knowledge graph management system. Background Art

[0002] At present, the efficiency and accuracy of the quality inspection of real-life 3D results are important parts to ensure the quality of the results. At present, the intelligent inspection level of real-life 3D results is low, and the efficiency is not high, which limits the development of quality inspection and the credibility of the results. The existing quality inspection methods often rely on manual work and experience, lack of systematicness and automation, and are difficult to meet the data inspection needs of large-scale and complex scenes. On the other hand, the types of real-life 3D results are novel and diverse, and the inspection of such results has risks such as inconsistent inspection content and evaluation indicators, and incomplete inspection.

[0003] Realistic 3D construction is in full swing, and the types of construction results are diverse. Traditional inspection knowledge can no longer meet the inspection needs of real-scene 3D results. Traditional surveying and mapping results quality inspection work mainly includes internal methods such as manual verification, comparison and analysis, and field methods such as geographic inspection and accuracy verification. During the inspection process, inspectors need to collect quality inspection procedures, rules and existing data based on the results and the survey area, which prolongs the inspection time of surveying and mapping results. Therefore, in order to improve the intelligence level of real-scene 3D results quality inspection, integrate existing reference data and related materials, unify the quality inspection standards and evaluation standards of real-scene 3D results, and apply the concept of knowledge graph to the quality inspection activities of real-scene 3D results.

[0004] Therefore, improving the level of intelligent inspection of real-life 3D results and unifying quality inspection standards are important issues that need to be urgently addressed in the quality management of real-life 3D results. Summary of the invention

[0005] In view of this, in order to solve the problems existing in the technical background, the present invention proposes a real-scene three-dimensional results quality inspection knowledge graph management system, and the specific technical solution is as follows:

[0006] A real-life three-dimensional results quality inspection knowledge graph management system, comprising the following steps:

[0007] Step 1: Integrate existing reference data and related information;

[0008] Step 2: Unify the quality inspection and evaluation standards for real-life 3D results;

[0009] Step 3: Establish the ontology model and apply the above standards to the quality inspection activities of real-life 3D results.

[0010] Furthermore, in step one, relevant technical regulations and inspection regulations for real-scene 3D are collected and sorted, such as a series of technical documents on new basic surveying and mapping and real-scene 3D China construction, provincial-level relevant implementation plans, etc., and they are classified into product knowledge, inspection knowledge, evaluation knowledge, support knowledge, and service knowledge required to construct a knowledge graph.

[0011] Furthermore, in the step 2, based on the process of the quality inspection activity of the real scene 3D results and the knowledge required for intelligent quality inspection, the quality inspection knowledge of the real scene 3D results is divided into: supporting knowledge, product knowledge, evaluation knowledge, inspection knowledge, service knowledge, etc.;

[0012] The supporting knowledge is various basic data and information required for intelligent quality inspection, including inspection sample library data of inspection points in previous years, etc.;

[0013] The product knowledge includes geographic scene result data, basic geographic entity data, DOM, DEM, DSM data, etc.;

[0014] The inspection knowledge mainly refers to the various knowledge required in the implementation process of real-life 3D results inspection, such as results sampling, general inspection, detailed inspection, etc.; the evaluation knowledge mainly refers to the error counting, scoring and judgment of the inspection results after the inspection is completed;

[0015] The service knowledge mentioned above mainly includes the knowledge of result statistics and result analysis carried out on quality inspection results to support industry management.

[0016] Furthermore, in the step three, the semantic relationship between the achievement quality inspection ontologies is constructed according to the real-scene three-dimensional achievement quality inspection knowledge. Based on the above-mentioned concept system and semantic relationship, a real-scene three-dimensional achievement quality inspection product ontology model and an inspection ontology model are established. The product ontology model should cover all achievement types and related information in the real scene, and the inspection ontology model should include various knowledge required for various achievement inspection activities.

[0017] The above technical solution has the following beneficial effects:

[0018] The present invention fills the gap in the knowledge graph for quality inspection of real-life three-dimensional results: for quality inspection of real-life three-dimensional results, a quality inspection knowledge graph framework is designed, a quality inspection ontology model is established, and a knowledge graph update mechanism is established, laying a solid foundation for intelligent quality inspection and results evaluation.

[0019] The present invention solves the problem that the quality inspection of real-life three-dimensional results requires high personnel quality and the efficiency of traditional inspection work is low: applying the quality inspection knowledge graph to the inspection work can help quality inspectors quickly obtain the corresponding results inspection plan, evaluation knowledge and other knowledge bases, quickly call on existing inspection knowledge, and improve the quality inspection efficiency of inspectors. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a real-scene three-dimensional achievement inspection method based on a quality inspection knowledge graph of the present invention;

[0021] Figure 2 It is a conceptual system diagram of the knowledge ontology of quality inspection of real-scene three-dimensional results of a real-scene three-dimensional results inspection method based on the quality inspection knowledge graph of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] As an emerging relational data management and mining technology, the knowledge graph technology of the present invention has shown great potential. By constructing a network structure of entities and their relationships, the knowledge graph can efficiently organize and integrate large-scale data and mine the deep connections between data. It realizes the association and integration between knowledge by representing different types of knowledge in the form of a graph, providing an intuitive and efficient way of expressing knowledge. The knowledge graph can not only help users better understand data and information, but also support machine intelligent decision-making and provide support for various application scenarios. This feature just fits the needs of multi-source complex data management and analysis in real-life three-dimensional quality inspection.

[0024] The specific implementation method of this embodiment is as follows:

[0025] 1) Construction of knowledge graph for quality inspection of real-life 3D results: mainly includes collection and organization of relevant information, design of knowledge graph framework, establishment of ontology model, and update mechanism.

[0026] a. Data collection and collation: Since the quality of real-scene 3D results is novel and diverse, and the technical regulations required for inspection are numerous, it is necessary to collect and collate relevant technical regulations and inspection regulations for real-scene 3D, such as a series of technical documents on new basic surveying and mapping and real-scene 3D China construction, provincial-level relevant implementation plans, etc., and form them into product knowledge, inspection knowledge, evaluation knowledge, support knowledge, service knowledge, etc. required to build a knowledge map;

[0027] b. Knowledge graph framework design: Based on the process of quality inspection activities for real-scene 3D results and the knowledge required for intelligent quality inspection, the knowledge of quality inspection for real-scene 3D results is divided into: support knowledge, product knowledge, evaluation knowledge, inspection knowledge, service knowledge, etc. Support knowledge refers to various basic data and information required for intelligent quality inspection, including inspection sample library data of inspection points in previous years, etc.; product knowledge includes geographic scene results data, basic geographic entity data, DOM, DEM, DSM data, etc.; inspection knowledge mainly refers to various knowledge required in the implementation process of real-scene 3D results inspection, such as results sampling, general inspection, detailed inspection, etc.; evaluation knowledge mainly refers to the counting, scoring and judgment of errors and omissions of inspection results after the inspection is completed; service knowledge mainly refers to the knowledge of result statistics and result analysis for quality inspection results supporting industry management.

[0028] c. Establishment of ontology model: Construct semantic relationships between the ontology of quality inspection of results based on the knowledge of quality inspection of real-life 3D results. Based on the above concept system and semantic relationships, establish the product ontology model and inspection ontology model of quality inspection of real-life 3D results. The product ontology model should cover all types of results and related information in the construction of real-life 3D Jiangxi; the inspection ontology model should include all kinds of knowledge required for various types of results inspection activities.

[0029] 2) Establish a knowledge graph management system for quality inspection of real-life 3D results: Based on the established quality inspection knowledge graph and Neo4j knowledge graph database, use the Django service framework to build services, the Django template template engine framework, and build front-end technology to realize the functions of the entire system.

[0030] First, import the knowledge graph to complete the storage of the knowledge graph;

[0031] Secondly, the overall architecture of the knowledge graph management system is designed;

[0032] Finally, functions such as user authentication, semantic search, and intelligent query are implemented in the functional module, and the knowledge graph update function is also realized.

[0033] The present invention fills the gap in the knowledge graph for quality inspection of real-life three-dimensional results: for quality inspection of real-life three-dimensional results, a quality inspection knowledge graph framework is designed, a quality inspection ontology model is established, and a knowledge graph update mechanism is established, laying a solid foundation for intelligent quality inspection and results evaluation.

[0034] The present invention solves the problem that the quality inspection of real-life three-dimensional results requires high personnel quality and the efficiency of traditional inspection work is low: applying the quality inspection knowledge graph to the inspection work can help quality inspectors quickly obtain the corresponding results inspection plan, evaluation knowledge and other knowledge bases, quickly call on existing inspection knowledge, and improve the quality inspection efficiency of inspectors.

[0035] The basic principles and main features of the present invention are described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for illustrating the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which shall fall within the scope of the present invention to be protected. The scope of protection of the invention shall be defined by the attached claims and their equivalents.

Claims

1. A real-life 3D results quality inspection knowledge graph management system, comprising the following steps: Step 1: Integrate existing reference data and related information; Step 2: Unify the quality inspection and evaluation standards for real-life 3D results; Step 3: Establish the ontology model and apply the above standards to the quality inspection activities of real-life 3D results.

2. A real-life 3D results quality inspection knowledge graph management system according to claim 1, characterized in that: In the step one, relevant technical regulations and inspection regulations for real-life 3D are collected and sorted, such as a series of technical documents on new basic surveying and mapping and real-life 3D China construction, provincial-level relevant implementation plans, etc., and they are classified into product knowledge, inspection knowledge, evaluation knowledge, support knowledge, and service knowledge required to construct a knowledge graph.

3. A real-life 3D results quality inspection knowledge graph management system according to claim 1, characterized in that: In the step 2, based on the process of quality inspection activities for real-scene 3D results and the knowledge required for intelligent quality inspection, the quality inspection knowledge for real-scene 3D results is divided into: supporting knowledge, product knowledge, evaluation knowledge, inspection knowledge, service knowledge, etc.; The supporting knowledge is various basic data and information required for intelligent quality inspection, including inspection sample library data of inspection points in previous years, etc.; The product knowledge includes geographic scene result data, basic geographic entity data, DOM, DEM, DSM data, etc.; The inspection knowledge mainly refers to the various knowledge required in the implementation process of real-life 3D results inspection, such as results sampling, general inspection, detailed inspection, etc.; the evaluation knowledge mainly refers to the error counting, scoring and judgment of the inspection results after the inspection is completed; The service knowledge mentioned above mainly includes the knowledge of result statistics and result analysis carried out on quality inspection results to support industry management.

4. A real-life 3D results quality inspection knowledge graph management system according to claim 1, characterized in that: In the step three, the semantic relationship between the achievement quality inspection ontologies is constructed according to the real-scene three-dimensional achievement quality inspection knowledge. Based on the above-mentioned concept system and semantic relationship, a real-scene three-dimensional achievement quality inspection product ontology model and an inspection ontology model are established. The product ontology model should cover all achievement types and related information in the real scene, and the inspection ontology model should include various knowledge required for various achievement inspection activities.

Images