A method and system for constructing an active fault database

Abstract

The present application provides a method and system for constructing an active fault database, which relates to the field of earthquake monitoring. Among them, the method includes: receiving active fault detection data sent by node devices of various data management agencies participating in the target project; batch loading the active fault detection data into the thematic database corresponding to the detection topic; performing quality inspection on each thematic database, and after all thematic databases have passed the quality inspection, selecting an active fault database template corresponding to the required parameters of the target project, and obtaining the feature classes and database tables required for the active fault database template from each thematic database; using the feature classes and database tables required by the active fault database template, combined with active fault knowledge graphs, smart contracts and blockchain technology, to construct a target active fault database with a data sharing mechanism. The technical solution provided by the present application improves the quality and construction efficiency of the active fault database.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of earthquake monitoring technology, and in particular to a method and system for constructing an active fault database. Background Art

[0002] In the field of seismology and geology, the study of active faults is crucial for assessing earthquake risks, planning urban construction, and formulating disaster prevention measures. With the advancement of detection technology and data collection methods, more and more active fault detection data are obtained by various data management agencies. In order to effectively manage and utilize these data, it is necessary to build a reliable and efficient active fault database.

[0003] The existing method for building an active fault database requires manual selection and configuration of database templates, which is a time-consuming and error-prone process. In addition, in the existing active fault database construction process, data quality control is usually performed after all data are loaded, which may result in a large amount of unqualified data that needs to be reworked and corrected, increasing workload and time costs. Since different data management agencies use different detection technologies and data formats, the existing method for building an active fault database is difficult to ensure data consistency. In addition, the existing method for building an active fault database lacks an effective data sharing mechanism, especially when multiple data management agencies are involved. Authority management is very complicated, which limits cross-institutional cooperation. Summary of the invention

[0004] The embodiments of the present application provide a method and system for constructing an active fault database, so as to solve the problems of poor quality and low construction efficiency of the active fault database existing in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for constructing an active fault database, comprising:

[0006] Receive active fault detection data sent by node devices of each data management agency participating in the target project. Each agency participates in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, seismic structure map compilation, seismic structure analysis, active fault hazard assessment and earthquake hazard assessment;

[0007] Batch loading the active fault detection data into a thematic database corresponding to the detection topic, wherein the thematic database includes: a plurality of element classes and database tables, and the structure and content of each element class and database table are defined by a smart contract;

[0008] Performing quality inspection on each thematic database, after all the thematic databases have passed the quality inspection, selecting an active fault database template corresponding to the required parameters of the target project, and obtaining the element classes and database tables required by the active fault database template from each of the thematic databases;

[0009] Utilizing the feature classes and database tables required by the active fault database template, combined with active fault knowledge graph, smart contracts and blockchain technology, a target active fault database with a data sharing mechanism is constructed. The data sharing mechanism allows the node devices of each data management agency participating in the target project to access and use the data in the target active fault database according to the corresponding permissions.

[0010] Optionally, the quality inspection of each thematic database is performed, and after all the thematic databases have passed the quality inspection, an active fault database template corresponding to the requirement parameters of the target project is selected, including:

[0011] Obtaining the project requirement document, using natural language processing technology to perform structured analysis on the project requirement document, and generating requirement analysis results, the requirement analysis results include the following requirement parameters: quality standards of each thematic database, and the detection range, detection accuracy and detection function of the active fault database, the quality standards include data integrity, consistency, accuracy and update frequency;

[0012] Based on the quality standards of each subject database, a multi-dimensional quality assessment method is used to perform quality inspection on each subject database;

[0013] After all thematic databases have passed the quality inspection, an input feature vector is constructed according to the detection range, detection accuracy and detection function of the active fault database, and the similarity between the template feature vector of each candidate template in the preset template library and the input feature vector is calculated by using the cosine similarity calculation method, and the candidate template with the greatest similarity to the input feature vector is taken as the preliminary matching result;

[0014] Based on the preliminary matching results, combined with the domain expert knowledge, the reinforcement learning method is applied to generate the final matching results;

[0015] The machine learning model is used to adjust the final matching results according to the historical project data to obtain the active fault database template.

[0016] Optionally, the generating of the final matching result based on the preliminary matching result and combining the domain expert knowledge with the application of the reinforcement learning method includes:

[0017] In combination with domain expert knowledge, a rule engine is applied to adjust the preliminary matching results and generate intermediate matching results;

[0018] A state space, a template selection action space and a reward function are defined by using a reinforcement learning method; the state in the state space includes a detection range, a detection accuracy and a detection function, as well as an intermediate matching result; the template selection action space includes a template selection action corresponding to each combination template; the combination template is obtained by combining the intermediate matching result with some parameters in other candidate templates; the other candidate templates are other candidate templates in a preset template library except for the preliminary matching result; the reward function includes multiple objectives: the similarity between the template feature vector of the combination template and the input feature vector, the functional synergy of the combination template, user feedback on the combination template and the performance index of the combination template;

[0019] Based on the reward function, the combination template corresponding to the action with the largest reward value is determined as the final matching result.

[0020] Optionally, the reward function adopts the following formula:

[0021] ;

[0022] in, yes The reward function when It's time. is the weight coefficient of the similarity between the template feature vector of the combined template and the input feature vector, is the weight coefficient of the functional synergy of the combined template, is the weight coefficient of the user's feedback on the combined template, is the weight coefficient of the performance index of the combined template, is the similarity between the template feature vector of the combined template and the input feature vector, It is the functional synergy of the combined templates. It is the user's feedback on the combination template. It is the performance index of the combined template. They are the time decay factors set for similarity, functional synergy, user feedback on the combined template, and performance indicators.

[0023] Optionally, the active fault database template is constructed by utilizing the element classes and database tables required by the active fault database template, combining active fault knowledge graph, smart contracts and blockchain technology to build a target active fault database with a data sharing mechanism, including:

[0024] Using the feature classes and database tables required by the active fault database template, construct an initial active fault database of the target project;

[0025] Based on the initial active fault database, display a three-dimensional geological structure model of the active fault;

[0026] User feedback information of the three-dimensional geological structure model and quality inspection results of the initial active fault database are collected, and the initial active fault database is optimized according to the user feedback information and the quality inspection results. During the optimization process, data sharing rules and authority management rules in the smart contract are introduced, and the target active fault database with a data sharing mechanism is obtained by combining blockchain technology.

[0027] Optionally, the collecting of user feedback information of the three-dimensional geological structure model and the quality inspection results of the initial active fault database, optimizing the initial active fault database according to the user feedback information and the quality inspection results, introducing data sharing rules and authority management rules in the smart contract during the optimization process, and combining blockchain technology to obtain a target active fault database with a data sharing mechanism, including:

[0028] Displaying a user interface, allowing node devices of various data management institutions participating in the target project to submit opinions and suggestions on the three-dimensional geological structure model in a specified form based on the user interface, wherein the specified form includes: questionnaire survey, scoring and free text input, integrating the opinions and suggestions submitted by the node devices of all institutions to form user feedback information of the three-dimensional geological structure model; using a clustering algorithm to classify the user feedback information into first quality events of different categories;

[0029] Sending the initial active fault database and the active fault detection data sent by the node devices of each data management agency participating in the target project to a database quality detection agency to obtain a quality detection result, where the quality detection result is obtained by the database quality detection agency performing a quality detection on the initial active fault database based on the active fault detection data sent by the node devices of each data management agency participating in the target project; analyzing the quality detection result to identify a second quality event;

[0030] Performing a comprehensive analysis on the first quality events and the second quality events of different categories to obtain a comprehensive analysis result, wherein the comprehensive analysis result includes a priority processing order of each quality event;

[0031] According to the comprehensive analysis results, combined with the data sharing rules and authority management rules in the smart contract and blockchain technology, the initial active fault database is optimized to obtain a target active fault database with a data sharing mechanism.

[0032] Optionally, the first quality events and the second quality events of different categories are comprehensively analyzed to obtain a comprehensive analysis result, wherein the comprehensive analysis result includes a priority processing order of each quality event, including:

[0033] Obtain sentiment scores of first quality events of different categories from user feedback information, use the sentiment score as one of the factors for evaluating severity, determine the severity of the first quality event in combination with technical evaluation, and use the weighted sum of the severity, impact scope, and frequency of the first quality event as the comprehensive score of the first quality event;

[0034] Obtaining the severity, impact scope and frequency of the second quality event from the quality detection result, and taking the weighted sum of the severity, impact scope and frequency of the second quality event as the comprehensive score of the second quality event;

[0035] Sort the comprehensive scores of all quality events from large to small to obtain the priority processing order of each quality event.

[0036] In a second aspect, an embodiment of the present application provides a method for constructing an active fault database, including:

[0037] A receiving module is used to receive active fault detection data sent by node devices of various data management agencies participating in the target project. Each agency participates in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, seismic structure map compilation, seismic structure analysis, active fault hazard assessment and earthquake hazard assessment;

[0038] A loading module, used for loading the active fault detection data in batches into a thematic database corresponding to the detection topic, wherein the thematic database includes: a plurality of element classes and database tables, and the structure and content of each element class and database table are defined by a smart contract;

[0039] The detection and acquisition module is used to perform quality detection on each thematic database. After all the thematic databases have passed the quality detection, an active fault database template corresponding to the required parameters of the target project is selected, and the element classes and database tables required by the active fault database template are obtained from each of the thematic databases.

[0040] A construction module is used to utilize the feature classes and database tables required by the active fault database template, combine active fault knowledge graphs, smart contracts and blockchain technology, and construct a target active fault database with a data sharing mechanism. The data sharing mechanism allows node devices of various data management agencies participating in the target project to access and use data in the target active fault database according to corresponding permissions.

[0041] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for constructing an active fault database as described in any one of the first aspects.

[0042] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a method for constructing an active fault database as described in any one of the first aspects.

[0043] In an embodiment of the present application, the embodiment of the present application provides a method for constructing an active fault database, including: receiving active fault detection data sent by node devices of various data management agencies participating in a target project, each agency participating in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, seismic structural map compilation, seismic structural analysis, active fault hazard assessment and earthquake hazard assessment; batch loading the active fault detection data into a thematic database corresponding to the corresponding detection topic, the thematic database including: multiple feature classes and database tables, the structure and content of each feature class and database table are defined by a smart contract; quality inspection is performed on each thematic database, and after all thematic databases have passed the quality inspection, an active fault database template corresponding to the required parameters of the target project is selected, and the feature classes and database tables required for the active fault database template are obtained from each thematic database; using the feature classes and database tables required by the active fault database template, combined with the active fault knowledge graph, smart contracts and blockchain technology, a target active fault database with a data sharing mechanism is constructed, and the data sharing mechanism allows the node devices of various data management agencies participating in the target project to access and use the data in the target active fault database according to corresponding permissions.

[0044] The embodiment of the present application batch loads active fault detection data, improves the efficiency of building the thematic database, and the structure and content of the feature class and database table are defined by smart contracts, ensuring that data from different sources can be quickly integrated according to unified standards, reducing manual intervention, improving the consistency and standardization of data, and thus improving the quality of the active fault database. In addition, the required data is extracted from each thematic database in a targeted manner, which can ensure the effective use of resources, avoid the storage of redundant data, and ensure that all necessary data are included. The automated template matching and data extraction process not only speeds up the work progress, but also reduces the possibility of human error, making database construction more efficient. Permission management can ensure that only authorized personnel can access sensitive or critical data, thereby improving the security and confidentiality of data. Reasonable permission allocation can help ensure that only properly trained personnel can modify data, thereby maintaining high data quality and consistency. The flexible database template selection mechanism can be customized according to specific project requirements, enhancing the adaptability and flexibility of the construction system of the active fault database, so that it can better respond to different research purposes.

[0045] These and other aspects of the present application will become more apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 A flowchart of a method for constructing an active fault database provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of the structure of a geospatial database model provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a storage structure corresponding to the hidden detection provided in an embodiment of the present application;

[0050] Figure 4 A flowchart of an exemplary method for constructing an active fault database provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of the structure of a system for constructing an active fault database provided in an embodiment of the present application;

[0052] Figure 6 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0054] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The sequence numbers of the operations, such as 11, 12, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0056] Figure 1 A flowchart of a method for constructing an active fault database provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0057] S11. Receive active fault detection data sent by the node devices of each data management agency participating in the target project. Each agency participates in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, earthquake structure map compilation, earthquake structure analysis, active fault hazard assessment and earthquake hazard assessment.

[0058] It should be understood that active faults are also called active faults, and topics are also called themes. Active fault detection data may refer to data obtained through various methods (such as geophysical exploration of active faults, age testing of stratum samples, fault activity identification, etc.) during the active fault detection process. In order to effectively utilize and manage the above multi-source data, the embodiments of the present application can store these data in a specified format. The active fault database finally constructed contains all the information and results obtained in the active fault detection and activity identification. It is a database that can reflect the geometry, kinematics and dynamic characteristics of active faults, and record various original detection records and comprehensive analysis results of active fault positioning, dating and activity. It can be used in various fields such as urban construction planning and land use, site selection of major projects, building seismic fortification and rapid assessment of earthquake disasters, and emergency rescue of command departments.

[0059] It should also be understood that the active fault database can adopt the geospatial database model provided by the preset geographic information system software. The construction, maintenance and management of the active fault database, as well as the query, display and print output of the results can all be achieved using the preset geographic information system software.

[0060] like Figure 2 As shown, the geospatial database model ( Figure 2 The database in the database includes feature sets, database tables (referred to as tables) and others. Among them, feature sets include feature classes using the same spatial reference system. Feature classes include faces, lines, points and topology. Others include fields and domains.

[0061] Among them, the feature set is a collection of feature classes that share the same spatial reference system. The feature class is a collection of features with the same geometric type and attribute structure. It refers to the collection of information of a certain type of geographic entity in a computer. In the embodiment of the present application, the feature class can also be referred to as a "layer". And the feature can refer to a geographic entity with geometric form and attributes, which is an instance of a feature class. For the database table, non-spatial data information is stored in the table. A field can represent a variable associated with a feature, and can also be referred to as a "column of a data item or attribute table". Its types include text, double precision, long integer, etc. The value domain is used to describe the value rules of a certain field. There are two types of value domains: range and coded values. The value domain can be used to set the value range of a certain field (range type), or to set which specified codes are filled in a certain field (coded type), which provides convenience for the construction of an active fault database. The active fault database constructed in the embodiment of the present application can use multiple value domains. The spatial reference system can include a coordinate system, a spatial domain, and precision. The coordinate system can be geographic coordinates or projected coordinates; the spatial domain is used to specify the maximum spatial extent of the feature set; the precision is used to specify the number of system units for each measurement unit. Topological relationships describe the spatial relationship between features or feature classes, and also define the geometric rules between features or feature classes.

[0062] Since the active fault detection data sent by the node devices of each data management agency participating in the target project needs to be received, cross-platform operations need to be implemented between different node devices. Therefore, the embodiment of the present application can use a geographic database that supports a multi-user storage format. Table 1 shows the difference between a geographic database that supports a multi-user storage format and a geographic database that supports a single-user storage format.

[0063] Table 1 Differences between geographic databases that support multi-user storage formats and those that support single-user storage formats

[0064]

[0065] For example, among the received active fault detection data, an active fault detection and earthquake hazard assessment project in a certain area of ​​a certain city provides a large amount of basic data, as shown in Table 2.

[0066] Table 2 Workload Statistics

[0067] ;

[0068]

[0069] As can be seen from Table 2, the project specifically includes but is not limited to the following: the detection area is 25,600 square kilometers, with a scale of 1:250,000; the target area is 1,500 square kilometers, with a scale of 1:50,000; a total of 57,581 aeromagnetic lines, 457 crust thickness lines, 34 gravity magnetic lines and 1,967 gravity field lines have been measured; 1 map section has been produced; for example, an active fault database and a thematic database of several GB in size have been constructed, and 6 mapping files have been produced; shallow artificial seismic detection has been implemented, with a total length of 141.328 kilometers, involving 63 detection points; the number of drill holes is 77, with a cumulative depth of 3,098 meters; 697 field observation points have been set up; a total of 24 cubic meters of earth have been excavated for trenching; 141 age samples have been collected in the field, and 137 samples have been sent to the laboratory for analysis.

[0070] In order to ensure the smooth submission of the active fault database and realize data sharing, the construction of the database can follow relevant national standards such as the National Basic Geographic Information Database.

[0071] Exemplarily, the standard of basic data can be implemented in accordance with the national basic geographic information database "National 1:50000 DLG Data" specification, in which specific provisions are made for the accuracy requirements, timeliness requirements, data interface requirements, metadata requirements, etc. of the terrain elements of the basic data, and data organization (for example: element stratification, attribute definition, classification code, data format, data results and organizational form) are clearly stipulated. In the embodiment of the present application, the active fault coordinate system can be unified into the WGS1984 coordinate system. The data structure, data items and content of each database can be established according to the corresponding database template requirements to meet the needs of active fault detection research, fault activity identification and other work, and comply with the "Technical Regulations for the Submission of Active Fault Detection Data".

[0072] S12. Batch load the active fault detection data into the thematic database corresponding to the detection topic. The thematic database includes: multiple feature classes and database tables. The structure and content of the feature classes and database tables are defined through smart contracts. The database table includes: attribute table, engineering table, archive table and association table. The archive table includes archive data. Among them, the feature class is a collection of features with the same geometric type and attribute structure, which is used to represent the information of a certain type of geographic entity. For example, drilling-point, sampling point-point, etc. The database table stores non-spatial data information, including attribute table, engineering table, archive table, association table, etc. For example, drilling engineering table, sampling engineering table, literature database, etc. There are corresponding coding rules for records in feature classes and database tables, as well as records in archive tables, to achieve the association and management between different elements.

[0073] It should be understood that the thematic database may also be called thematic library, theme database, theme library, etc. In the thematic database, each record in the feature class and database table has a corresponding code. Coding is very important for the construction of each database. For example, in each database, the association between different feature classes, the association between feature classes and database tables, and the association between different database tables can all be achieved through coding. In addition, after the active fault database is built, the query and display of various information are inseparable from coding. In the construction process of each thematic database, the editing of the code can be completed by the user defining a code less than eight digits, and then using an automatic coding tool.

[0074] For example, a first coding strategy consisting of administrative division code, subject number and user-defined code is defined, and a second coding strategy consisting of administrative division code, subject number, user-defined code and document code is predefined; the first coding strategy is used to perform corresponding coding on each feature class and each record in the database table in each thematic database, and the second coding strategy is used to perform corresponding coding on each record in the archive table in each thematic database.

[0075] The first coding strategy can refer to the coding rules of elements and tables: ××××××-×××-×××××××××, which is used to represent: administrative division code-topic number-user-defined code. Among them, the administrative division code is the city-level administrative division code of the detection area; the topic number is defined by the user according to the corresponding topic; the user-defined code is defined by the user himself, which is less than eight digits. If it is less than eight digits, it is padded with #. According to the above rules, the code of the first record of the geophysical survey line (GeophySvyLine) is: 371300102#######1, and so on. The coding methods of other records are similar and will not be repeated here.

[0076] The archive mainly includes reports, images, raw data, etc. generated during the detection process. The report number, image number, raw data number, archive field name and its corresponding content are shown in Table 3.

[0077] Table 3 Contents of archives in the database and corresponding archive tables

[0078]

[0079] The second coding strategy can refer to the coding rules of archives. The archive table is a special database table in the database, so it can be listed independently. The coding rules of archives: ××××××-×××-×××××××××-×××, used to represent: administrative division code-topic number-user-defined code-document code.

[0080] As shown in Table 4, a thematic database is established, and the last three digits of the name are the thematic number, such as Subject371300102 is the shallow seismic detection theme of the main hidden faults in the target area. The feature sets, feature classes, and database tables in the thematic database are established according to the active tectonic database template, and the English part of their names retains the naming in the template. B5_GeophysicalSurvey is the feature set in the shallow seismic detection theme of the main hidden faults in the target area, GeophySvyLine is the shallow seismic line feature class, and InternalDataTable is the internal data table in the database.

[0081] Table 4 List of subject databases

[0082]

[0083] It should be understood that the borehole detection, concealed detection, activity identification, seismic tectonic map compilation, seismic tectonic analysis, active fault hazard assessment and seismic hazard assessment in S11 are the functional abbreviations of standard borehole detection and Quaternary stratigraphic profile establishment, geophysical detection of concealed faults, identification of fault activity in the target area, seismic tectonic map compilation in the detection area and target area, deep seismic tectonic environment detection and analysis research, active fault seismic hazard assessment and seismic hazard assessment of active faults in the target area in Table 4, respectively.

[0084] It should also be understood that all data generated during the construction of the subject database and all archive data collected can be classified and stored in a dedicated folder, namely, the 371300 folder. The data corresponding to each subject and the collected archive data can be stored according to the subject classification. Taking the 102 subject as an example, its storage structure is as follows: Figure 3As shown. A thematic database of a certain area in a certain city has a total of 5 thematic folders, each of which has subfolders, and each subfolder includes multiple files, among which the subfolders are: 1-Features Class (used to represent 1-feature class), 2-AttributeTable (used to represent 2-attribute class), 3-Archive Table (used to represent 3-archive table), 4-ArchiveFile (used to represent archive file) and 5-HugeFile (used to represent large file). Among them, the contents stored in the 1-Features Class subfolder are the tables corresponding to the feature classes in the thematic database, such as GeophySvyLine-geophysical survey line-line.xls, etc.; the contents stored in the 2-Attribute Table subfolder are the tables corresponding to the attribute tables in the thematic database, such as B5_GeophySvyDataTable-geophysical detection data table-attribute table.xls, etc.; the archive tables are stored in the 3-Archive Table subfolder, such as E_ArchiveRawDataTable-original archive table-attribute table.xls, etc.; the tables in the above three subfolders can be copied from the corresponding database templates; the contents stored in the 4-ArchiveFile subfolder are archive data (such as: pictures, documents, graphics, original files, etc.); the contents stored in the 5-HugeFile subfolder are archive data with a single file data volume greater than 1G, such as seismic reflection data*.sgy, etc.

[0085] The editing and storage of geometric elements in the subject database is completed through the preset geographic information system software. First, fill the attribute data into the EXCEL table, and then use the storage instructions in the preset geographic information system software to complete the storage of attribute data. The archive data stored in the subfolder "4-ArchiveFile" under each subject folder is also stored in the corresponding subject database using the storage instructions. After the subject database is built, it is tested using the subject database detection software, and manual testing is performed at the same time to ensure that the content in the subject database is consistent with the actual situation. Modify and supplement according to the detection situation to establish a complete subject database.

[0086] The present application example analyzes the contents of each topic separately:

[0087] For Topic 1: Borehole Detection, the topic database name is Subject371300101.gdb, and the structure and content of its feature classes and database tables are defined through smart contracts. The feature class names include: Borehole-point, Sampling point-point, Target area-surface. The database table names include: Drilling Engineering Table-Attribute Table, Sampling Engineering Table-Attribute Table, Literature Database-Attribute Table, Sample Data Table-Attribute Table, Sample Test Result Table-Attribute Table, Achievement Report Table, Image Archive Table, Original Archive Table, Report Archive Table, Internal Data Table, etc.

[0088] For Topic 2: Hidden Detection, the topic database name is Subject371300102.gdb. The structure and content of its feature classes and database tables are defined through smart contracts. The feature class names include: geophysical survey lines, geophysical survey points, geophysical detection breakpoints, target areas-surfaces, 1:50,000 rock mass-surfaces, 1:50,000 strata-surfaces, 1:50,000 fault-lines. The database table names include: geophysical detection project table, geophysical detection data table, big data file table, results map table, results report table, literature database-attribute table, image archive table, original archive table, report archive table, internal data table, etc.

[0089] For Topic 3: Activity Identification, the name of the topic database is Subject371300103.gdb. The structure and content of its feature classes and database tables are defined through smart contracts. The names of the feature classes include: fault observation point-point, geological and geomorphological survey observation point-point, geological survey observation point-point, stratigraphic observation point-point, exploration trench-point, sampling point-point, collection borehole-point, cross-fault drilling breakpoint-point, borehole-point, cross-fault drilling profile-line, 1:50,000 fault-line, active fault-line, cartographic auxiliary line-line, cartographic auxiliary point-point, cartographic auxiliary surface-surface, geomorphological line-line, image index table-surface, 1:50,000 rock mass-surface, aerial and satellite image interpretation line-line, 1:50,000 stratigraphic isopach line-line, 1:50,000 stratigraphic surface, target area-surface. The names of the database tables include: geological survey project table, sampling project table, drilling project table, fault segment paleoseismic events and trench association table - attribute table, fault segment paleoseismic events table - attribute table, geomorphic line and geological and geomorphic point association table - attribute table, trench paleoseismic events - attribute table, trench and sampling project association table - attribute table, sample data table - attribute table, sample test result table - attribute table, literature database - attribute table, big data file table - attribute table, achievement map table - attribute table, achievement report table, image archive table, original archive table, report archive table, internal data table.

[0090] For Topic 4: Compilation of Seismic Tectonic Maps, the thematic database name is Subject371300104.gdb. The structure and content of its feature classes and database tables are defined through smart contracts. The feature class names include: borehole-point, collection borehole-point, cross-fault drilling breakpoint-point, cross-fault drilling profile-line, sampling point-point, geophysical survey line, geophysical detection breakpoint, fault observation point-point, stratigraphic observation point-point, geological and geomorphological survey observation point-point, geological survey observation point-point, work area-surface, 1:250,000 fault-line, 1:250,000 fault strike-point, 1:250,000 stratigraphic-surface, 1:250,000 stratigraphic isopach-line, 1:250,000 stratigraphic line-line, 1:250,000 rock mass-surface, 1:250,000 rock mass line-line, 1:250,000 basin-surface, geological profile line-line, profile line inflection point auxiliary mapping map-point, 4 before 1970 3_4 and above strong earthquake catalog - point, earthquake catalog since 1970 - point, 1:250,000 geotectonic unit division - surface, 1:250,000 new tectonic unit division - surface, stratigraphic contact relationship - line, cartographic auxiliary line - line, cartographic auxiliary point - point, cartographic auxiliary surface - surface, cartographic auxiliary annotation - point. Database table names include: drilling engineering table - attribute table, sampling engineering table - attribute table, sample data table - attribute table, sample test result table - attribute table, geophysical detection engineering table, geological survey engineering table - attribute table, literature database - attribute table, image archive table, original archive table, report archive table, internal data table, achievement report table, achievement map table. The thematic database may include the following notes: storage of cartographic auxiliary lines, storage of cartographic auxiliary points, storage of cartographic auxiliary surfaces, storage of stratigraphic symbols, columnar text, etc.

[0091] For Topic 5: Seismic Tectonic Analysis, the topic database name is Subject371300105.gdb, and the structure and content of its feature classes and database tables are defined through smart contracts. The feature class names include: geophysical detection breakpoints-points, geophysical survey lines-lines, geophysical survey points-points, aeromagnetic-lines, crust thickness-lines, gravity fields-lines, small earthquake relocation catalog-points, earthquake catalogs since 1970-points, catalogs of strong earthquakes above 4 3_4 before 1970-points, focal mechanism solution data-points, work areas-surfaces, 1:250,000 faults-lines, gravity and magnetic interpretation lines-lines. The database table names include: geophysical detection engineering table-attribute table, geophysical detection data table-attribute table, big data file table-attribute table, achievement map table-attribute table, achievement report table, literature database-attribute table, image archive table-attribute table, original archive table, report archive table, and internal data table.

[0092] For Topic 6: Active Fault Hazard Assessment, the topic database name is Subject371300106.gdb, and the structure and content of its feature classes and database tables are defined through smart contracts. The feature class names include: 1:50,000 fault-line, fault earthquake hazard analysis-line, target area-surface. The database table names include: literature database-attribute table, achievement map table-attribute table, achievement report table-attribute table, image archive table-attribute table, original archive table, report archive table, and internal data table.

[0093] For Topic 7: Earthquake Hazard Assessment, the topic database name is Subject371300107.gdb, and the structure and content of its feature classes and database tables are defined through smart contracts. The feature class names include: target area-surface, response spectrum peak and period distribution point map-point, three-dimensional underground structure model layer grid point-point, surface rupture zone table prediction-surface, 3D underground structure discretization model point-point, target area time history peak point map-point. The database table names include: earthquake hazard analysis result table-attribute table, earthquake time history curve response spectrum curve-attribute table, strong earthquake prediction basic data table-attribute table, fault segmentation analysis result magnitude estimation subtable-attribute table, literature database-attribute table, achievement report table-attribute table, original archive table, report archive table, internal data table.

[0094] S13. Perform quality inspection on each thematic database. After all the thematic databases have passed the quality inspection, select an active fault database template corresponding to the required parameters of the target project, and obtain the feature classes and database tables required by the active fault database template from each thematic database.

[0095] It should be understood that the active fault database template refers to selecting an appropriate database structure and format based on the required parameters of the target project to meet the needs of a specific project.

[0096] S14. Utilize the feature classes and database tables required by the active fault database template, combine the active fault knowledge graph, smart contracts and blockchain technology, and build a target active fault database with a data sharing mechanism. The data sharing mechanism allows the node devices of each data management agency participating in the target project to access and use the data in the target active fault database according to the corresponding permissions.

[0097] It should be understood that in order to continue the name of the subject database, the name of the target active fault database may be Subject371300108.gdb, which is used to represent the total active fault detection database.

[0098] For example, Figure 4A flowchart of a construction method of an exemplary active fault database provided for an embodiment of the present application. In order to make the data and information provided by each agency during the active fault detection process meet the needs of database construction as much as possible, in the shallow seismic exploration, drilling and other working stages, the present application embodiment can inform the field construction personnel of the content and format of the data and information required to be collected, and it is particularly important to note that the provided measurement coordinate values ​​use the WGS1984 coordinate system. The construction of the active fault database should be carried out simultaneously with the detection work, and the database construction personnel can prepare the database data and collect and organize the data and information required for database construction in a timely manner. After the database construction personnel obtain the data and information of the geophysical exploration, drilling and other departments, they perform attribute data operations and spatial database construction according to the corresponding topics, and then batch storage to establish a thematic database. Exemplarily, attribute data operations can be completed under Microsoft Office Excel software by filling in the Excel format database template table. Its content includes filling in the feature class attribute table and the separate attribute table. Spatial data storage requires the conversion from the document data model to the ArcGIS data model. Exemplarily, the embodiment of the present application can create an ArcGIS database, then create a spatial geometry feature class, and then implement the storage of spatial geometry features. After the above work is completed, the embodiment of the present application can use the active structure database batch storage software to implement batch storage of data, including feature class attribute data storage, separate attribute table data storage and archive data storage. The last step is for the active fault detection data submission and management center to test the built thematic databases. After the test is passed, the active fault database (i.e. Figure 4 The final output is the Joint Photographic Experts Group file (jpg), ArcMap Document File (mxd), Tagged Image File Format (tiff) and other formats.

[0099] After the database construction personnel complete the construction of the active fault database, the embodiment of the present application can send the active fault database to the National Earthquake Active Fault Research Center for data quality detection. If unqualified content is detected, the existing problems need to be modified until it can be submitted as required. The embodiment of the present application can be in accordance with the management method for the submission and sharing of active fault detection data. When a project is completed, in order to ensure the integrity of the data document, when submitting the active fault database in a preset format, it is also necessary to submit the Excel format data used when constructing the active fault database in a preset format and all original materials. The main content includes an active fault detection folder in a certain area of ​​a city - 371300108, which contains five subfolders (1-Features Class, 2-Attribute Table, 3-Archive Table, 4-ArchiveFile, 5-HugeFile) and an active fault database (Subject 371300108.gdb), and also contains three established thematic map drawing documents.

[0100] For example, the embodiments of the present application may submit results according to the following rules:

[0101] (1) The thematic database and active fault database must be updated according to the new database template; (2) Since the database has been repeatedly modified during the construction process, in order to ensure that the submitted results are the final results, it is necessary to ensure that the table contents under the subfolders 1-Features Class, 2-Attribute Table, and 3-Archive Table are consistent with the contents in the database; (3) The archive records in the database are consistent with the archive contents in the 4-ArchiveFile and 5-HugeFile folders; (4) All data in the thematic map drawing document are derived from the Subject 371300108.gdb active fault database. Data outside the active fault database cannot be used to avoid affecting data sharing.

[0102] Optionally, in order to maximize the positive effects of the data sharing mechanism, the embodiments of the present application may consider adopting some technologies when constructing the active fault database, such as: role-based access control, attribute-based access control, and distributed permission management mechanism supported by blockchain technology. In addition, the embodiments of the present application combine smart contracts to automate part of the permission management process, which can further simplify the permission setting and enhance the flexibility and security of the construction system of the active fault database.

[0103] By executing S11~S14, the embodiment of the present application batch loads active fault detection data, improves the construction efficiency of the thematic database, and the structure and content of the feature class and database table are defined by smart contracts, ensuring that data from different sources can be quickly integrated according to unified standards, reducing manual intervention, improving the consistency and standardization of data, and thus improving the quality of the active fault database. In addition, the required data is extracted from each thematic database in a targeted manner, which can ensure the effective use of resources, avoid the storage of redundant data, and ensure that all necessary data are included. The automated template matching and data extraction process not only speeds up the work progress, but also reduces the possibility of human error, making the database construction more efficient. Permission management can ensure that only authorized personnel can access sensitive or critical data, thereby improving the security and confidentiality of data. Reasonable permission allocation can help ensure that only properly trained personnel can modify data, thereby maintaining high data quality and consistency. The flexible database template selection mechanism can be customized according to specific project requirements, enhancing the adaptability and flexibility of the construction system of the active fault database, so that it can better respond to different research purposes.

[0104] In some optional embodiments, S13, quality inspection is performed on each thematic database. After all the thematic databases have passed the quality inspection, an active fault database template corresponding to the requirement parameters of the target project is selected, including:

[0105] Step 131, obtain the project requirement document, use natural language processing technology to perform structured analysis on the project requirement document, and generate requirement analysis results. The requirement analysis results include the following requirement parameters: quality standards of each thematic database, and the detection range, detection accuracy and detection function of the active fault database. The quality standards include data integrity, consistency, accuracy and update frequency.

[0106] It should be understood that the embodiment of the present application uses natural language processing technology to perform structured analysis on the project requirements document, which can accurately extract the various parameters and standards required for the project, ensuring that subsequent work fully meets the actual requirements of the customer or project. It reduces the time cost of manually interpreting the requirements document, improves efficiency, and reduces the risk of errors caused by human understanding bias.

[0107] Step 132: Based on the quality standards of each subject database, a multi-dimensional quality assessment method is used to perform quality inspection on each subject database.

[0108] It should be understood that the multi-dimensional quality assessment method can comprehensively check the key indicators of the data integrity, consistency, accuracy and update frequency of the thematic database, thereby ensuring that the data foundation used to build the active fault database is high-quality and reliable. In addition, the embodiments of the present application can identify and solve problems that may affect database performance in advance, reducing later maintenance costs and technical debt.

[0109] Step 133: After all thematic databases have passed the quality inspection, an input feature vector is constructed according to the detection range, detection accuracy and detection function of the active fault database. The cosine similarity calculation method is used to calculate the similarity between the template feature vector of each candidate template in the preset template library and the input feature vector, and the candidate template with the greatest similarity to the input feature vector is used as the preliminary matching result.

[0110] It should be understood that the embodiment of the present application constructs an input feature vector based on detection range, accuracy and function, and uses cosine similarity calculation to measure the similarity between candidate templates. This method provides an objective basis for selecting the template that best suits the current project. In addition, the embodiment of the present application can quickly screen out the template that is closest to the requirements as the preliminary matching result, simplifying the complexity of subsequent optimization work.

[0111] Step 134: Based on the preliminary matching results and in combination with domain expert knowledge, a reinforcement learning method is applied to generate a final matching result.

[0112] In an embodiment of the present application, domain expert knowledge may refer to the understanding and judgment criteria of experts in the field of earthquake monitoring and active fault research on how to evaluate and select suitable active fault database templates. This knowledge can help identify which features are important and which are secondary, and how to balance the relationship between different goals to achieve the optimal solution. The application rule engine is a software tool or framework that allows business logic to be abstracted into a series of "if-then" rules and performs automated decision-making accordingly. In the selection process of the active fault database template, the rule engine can automatically adjust the preliminary matching results according to a set of pre-set rules (for example, a certain type of template should be given priority under certain conditions) to generate a more reasonable intermediate matching result. This approach can greatly reduce the workload of manual configuration while ensuring that all decisions meet established professional standards.

[0113] By introducing the knowledge of domain experts, template selection not only relies on algorithms, but also takes into account industry experience and best practices, enhancing the rationality of decision-making. Reinforcement learning methods are used to dynamically adjust template selection strategies and continuously optimize models according to actual conditions to adapt to changing needs and technological advances.

[0114] As a possible implementation, step 134, based on the preliminary matching result and in combination with domain expert knowledge, applying a reinforcement learning method to generate a final matching result, includes:

[0115] Step a1: Combine domain expert knowledge, apply the rule engine, adjust the preliminary matching results, and generate intermediate matching results. It should be understood that domain expert knowledge refers to the specialized knowledge and technical experience possessed by professionals in a specific industry or field.

[0116] Step a2, using the reinforcement learning method to define the state space, template selection action space and reward function; the state in the state space includes the detection range, detection accuracy and detection function, as well as the intermediate matching results, the template selection action space includes the template selection action corresponding to each combination template, the combination template is obtained by combining the intermediate matching results with some parameters in other candidate templates, and the other candidate templates are other candidate templates in the preset template library except for the preliminary matching results, and the reward function includes multiple objectives: the similarity between the template feature vector of the combination template and the input feature vector, the functional synergy of the combination template, the user's feedback on the combination template and the performance index of the combination template. Exemplarily, the performance index includes at least one of computing resource consumption and efficiency. When the performance index includes computing resource consumption and efficiency, the embodiment of the present application can design corresponding weights for computing resource consumption and efficiency, respectively.

[0117] Exemplarily, the reward function may adopt the following formula:

[0118] ;

[0119] in, yes The reward function when It's time. is the weight coefficient of the similarity between the template feature vector of the combined template and the input feature vector, is the weight coefficient of the functional synergy of the combined template, is the weight coefficient of the user's feedback on the combined template, is the weight coefficient of the performance index of the combined template, is the similarity between the template feature vector of the combined template and the input feature vector, It is the functional synergy of the combined templates. It is the user's feedback on the combination template. It is the performance index of the combined template. They are the time decay factors set for similarity, functional synergy, user feedback on the combined template, and performance indicators.

[0120] The above reward function formula comprehensively considers multiple key factors of the combined template and introduces a time decay factor to dynamically adjust the importance of these factors, thereby ensuring the optimal evaluation of the template selection action at different time points. This design enables the system to flexibly respond to changing needs and technological developments in the selection process of the active fault database template, not only based on the current best matching results, but also combined with the learning of historical data. Therefore, this formula realizes an accurate, efficient and user-friendly active fault database template selection mechanism, providing a solid foundation for building a high-quality target active fault database.

[0121] Step a3: Based on the reward function, the combination template corresponding to the action with the largest reward value is determined as the final matching result.

[0122] By executing steps a1 to a3, the embodiment of the present application has the following advantages: (1) By introducing the knowledge of domain experts, it can be ensured that the complexity and special circumstances in actual applications are taken into account when adjusting the preliminary matching results, so that the intermediate matching results are closer to the actual situation, thereby improving the accuracy of the final matching results. (2) The application of the rule engine allows the system to automatically process data according to preset logical rules, which not only simplifies the need for manual intervention, but also enhances the flexibility of the system and its adaptability to different application scenarios. At the same time, the state space and action space are dynamically defined using the reinforcement learning method, which enables the system to continuously optimize its decision-making process over time. (3) The design of the reward function comprehensively considers multiple key factors (such as similarity, functional synergy, user feedback and performance indicators) and assigns them appropriate weight coefficients, which can ensure that the selected template is not only technically superior, but also has a good user experience, low computing resource consumption, and better overall performance. (4) Since the reward function contains a time decay factor, this means that the system will automatically adjust the influence of various parameters as time and environment change, thereby maintaining its advancedness and competitiveness and supporting long-term self-optimization. (5) Through rigorous evaluation of state variables such as detection range, detection accuracy, and detection function, as well as comprehensive comparison of candidate templates, the selected template is ensured to be highly reliable and stable and suitable for various active fault database construction tasks.

[0123] Step 135: Use a machine learning model to adjust the final matching result according to historical project data to obtain an active fault database template.

[0124] It should be understood that by using historical project data to adjust the final matching results through machine learning models, the selection of new templates is based on both existing data and past successful cases, which improves the robustness and predictability of the solution. As more project data is accumulated, the machine learning model will gradually become smarter and more accurate, helping to maintain high-performance performance in the long term.

[0125] By executing steps 131 to 135, the embodiment of the present application integrates multiple technologies such as NLP, multi-dimensional quality assessment, cosine similarity calculation, reinforcement learning, and machine learning in the entire process, and realizes intelligent management of the entire process from demand analysis to template selection, which not only improves work efficiency and reduces the possibility of human intervention, but more importantly ensures that the constructed active fault database template has a high degree of applicability and reliability, providing data support for research in earthquake monitoring and related fields. At the same time, this systematic template selection mechanism is also convenient for subsequent expansion and upgrading to adapt to new challenges that may arise in the future.

[0126] In some possible embodiments, S14, using the element classes and database tables required by the active fault database template, combined with the active fault knowledge graph, smart contracts and blockchain technology, a target active fault database with a data sharing mechanism is constructed, including:

[0127] Step 141: Use the element classes and database tables required by the active fault database template to build an initial active fault database for the target project. It should be understood that the present embodiment of the application uses a predefined active fault database template to quickly build an initial database structure that meets project requirements, greatly shortening the project preparation time. Building a database based on the element classes and database tables required by the template ensures consistency and standardization of data storage, facilitating subsequent data management and analysis.

[0128] Step 142: Based on the initial active fault database, display the three-dimensional geological structure model of the active fault. It should be understood that the three-dimensional geological structure model can intuitively display the spatial distribution of underground active faults, help modelers and decision makers better understand the geological structure and improve decision-making efficiency. Visual display methods facilitate communication between institutions with different backgrounds, making complex technical information easier to understand and accept.

[0129] Step 143, collect user feedback information of the three-dimensional geological structure model and the quality inspection results of the initial active fault database, optimize the initial active fault database according to the user feedback information and the quality inspection results, introduce the data sharing rules and authority management rules in the smart contract in the optimization process, and combine the blockchain technology to obtain the target active fault database with a data sharing mechanism. Among them, the three-dimensional geological structure model is constructed based on the initial active fault database to intuitively display the spatial distribution of underground active faults. User feedback information is the user's opinions and suggestions on the displayed three-dimensional geological structure model, which can be collected through questionnaires, scoring, and free text input.

[0130] It should be understood that collecting users' opinions and suggestions on the three-dimensional geological structure model and optimizing it in combination with the quality inspection results can ensure that the final product is closer to user needs and improve satisfaction. Optimizing according to the quality inspection results ensures that the data in the database meets high standards in terms of integrity, consistency and accuracy, enhancing the reliability and practicality of the data. Introducing data sharing rules and permission management rules in smart contracts during the optimization process, combined with blockchain technology, not only improves the security and transparency of data, but also promotes the legal and compliant sharing of data and supports multi-party collaborative research.

[0131] The immutable nature of blockchain technology ensures the authenticity and security of data. Smart contracts automatically execute preset rules, simplifying the data sharing process while ensuring that all operations are traceable and increasing trust. Smart contracts enable sophisticated permission control to ensure that only authorized users can access specific data, protecting sensitive information while promoting cooperation.

[0132] As a possible implementation method, step 143 collects user feedback information of the three-dimensional geological structure model and quality inspection results of the initial active fault database, optimizes the initial active fault database according to the user feedback information and the quality inspection results, introduces data sharing rules and authority management rules in the smart contract during the optimization process, and combines blockchain technology to obtain a target active fault database with a data sharing mechanism, including:

[0133] Step b1, displaying a user interface, allowing the node devices of each data management agency participating in the target project to submit opinions and suggestions on the three-dimensional geological structure model in a specified form based on the user interface. The specified form includes: questionnaire survey, scoring and free text input, integrating the opinions and suggestions submitted by the node devices of all agencies to form user feedback information of the three-dimensional geological structure model; using a clustering algorithm to classify the user feedback information into different categories of first quality events.

[0134] It should be understood that the embodiment of the present application provides an intuitive user interface, which enables each data management agency to easily submit opinions and suggestions, thereby improving user participation and satisfaction. It supports various forms of feedback such as questionnaires, scoring, and free text input, ensuring the comprehensiveness and flexibility of information collection. By integrating the opinions and suggestions submitted by all node devices, a systematic three-dimensional geological structure model user feedback information is formed, providing a rich data basis for subsequent analysis. The clustering algorithm is used to classify user feedback information into first quality events of different categories, which improves the accuracy and efficiency of problem identification.

[0135] Step b2: Send the initial active fault database and the active fault detection data sent by the node devices of each data management agency participating in the target project to the database quality inspection agency to obtain the quality inspection result. The quality inspection result is obtained by the database quality inspection agency by performing quality inspection on the initial active fault database based on the active fault detection data sent by the node devices of each data management agency participating in the target project; analyze the quality inspection result to identify the second quality event.

[0136] It should be understood that sending the initial active fault database and detection data to a professional database quality inspection agency for quality inspection ensures the professionalism and authority of the inspection results. Quality inspection of the database based on actual detection data makes the quality assessment more objective and real, and reduces subjective bias. By analyzing the quality inspection results, the existing second quality events can be accurately identified, providing a clear direction for subsequent optimization.

[0137] Step b3: Comprehensively analyze the first quality events and the second quality events of different categories to obtain a comprehensive analysis result, which includes a priority processing order for each quality event.

[0138] It should be understood that the comprehensive analysis results include the priority processing order of user feedback information and technical quality test results, which are used to guide the optimization of the active fault database. Comprehensive analysis of first quality events and second quality events of different categories ensures comprehensive consideration of all quality issues. Determining the priority processing order of each quality event based on the comprehensive analysis results helps to reasonably allocate resources and improve the efficiency of problem solving. Providing a clear priority processing order provides strong decision-making support for management and technical teams, ensuring that the most critical issues are resolved in a timely manner.

[0139] Specifically, step b3, comprehensively analyzing the first quality events and the second quality events of different categories to obtain a comprehensive analysis result, the comprehensive analysis result includes a priority processing order of each quality event, including:

[0140] Step b31, obtain the emotional scores of the first quality events of different categories from the user feedback information, use the emotional score as one of the factors for evaluating the severity, determine the severity of the first quality event in combination with the technical evaluation, and use the weighted sum of the severity, impact range and frequency of the first quality event as the comprehensive score of the first quality event. It should be understood that using the emotional score in the user feedback as one of the factors for evaluating the severity, combined with the technical evaluation, provides a more comprehensive basis for judging the severity of quality events. This not only takes into account technical issues, but also pays attention to user experience and perception. By analyzing the user's emotional feedback, the user's actual use experience becomes an important reference for improvement, which enhances the user's sense of participation in the quality management process and improves user satisfaction. Emotional scores can help identify those problems that are not technically the most serious but have a great impact on the user experience, so as to give priority to solving these high-sensitivity problems.

[0141] Step b32, obtain the severity, impact range and frequency of the second quality event from the quality test results, and use the weighted sum of the severity, impact range and frequency of the second quality event as the comprehensive score of the second quality event. It should be understood that the embodiment of the present application calculates the comprehensive score of the second quality event based on severity, impact range and frequency, ensuring the objectivity and consistency of the evaluation criteria. The data dependent on the test results are weighted and summed, so that the score of each quality event is based on empirical data, supporting the data-driven decision-making process.

[0142] Step b33, sort the comprehensive scores of all quality events in order from large to small, and obtain the priority processing order of each quality event. It should be understood that the embodiment of the present application can reasonably allocate limited resources to the most critical issues by sorting all quality events according to the comprehensive scores, ensuring that the most important issues are handled in a timely and effective manner. The priority processing order of each quality event is clarified, which helps the team to concentrate on solving problems, avoid resource dispersion and inefficient work, and improve overall work efficiency. Prioritizing high-scoring quality events can effectively reduce potential risks, protect the stability and reliability of the system, and reduce possible negative effects.

[0143] By executing steps b31 to b33, the embodiment of the present application integrates sentiment analysis and technical evaluation of user feedback, as well as objective scoring based on quality inspection results, to achieve scientific quantification and priority sorting of quality events. This method not only improves the accuracy and effectiveness of quality management, but also promotes continuous improvement of user experience. At the same time, the clear priority processing order provides the team with clear work guidance, helps to improve the speed and quality of problem solving, and ultimately ensures the high performance and reliability of the active fault database.

[0144] Step b4: Based on the comprehensive analysis results, combined with the data sharing rules and authority management rules in the smart contract and blockchain technology, the initial active fault database is optimized to obtain the target active fault database with a data sharing mechanism.

[0145] It should be understood that the combination of data sharing rules and authority management rules in smart contracts and blockchain technology ensures data security and transparency, and promotes legal and compliant data sharing. The initial active fault database is continuously optimized based on the comprehensive analysis results, and finally the target active fault database with data sharing mechanism is obtained, which ensures the high performance and reliability of the database.

[0146] By executing steps b1 to b4, the embodiment of the present application integrates user interface design, clustering algorithm, professional quality inspection, comprehensive analysis, smart contract and blockchain technology, and realizes full-process intelligent management from user feedback collection to database optimization. It not only improves user experience and data quality, reduces the possibility of human intervention, but more importantly ensures that the constructed active fault database has a high degree of applicability, reliability and security.

[0147] By executing steps 141 to 143, the embodiment of the present application integrates 3D modeling, user feedback collection, quality inspection, and blockchain and smart contract technology in the entire process, and realizes intelligent management of the entire process from database construction to optimization. This not only improves work efficiency and data quality, reduces the possibility of human intervention, but more importantly ensures that the constructed active fault database has a high degree of applicability, reliability and security.

[0148] Figure 5 A schematic diagram of a system for constructing an active fault database provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the system includes:

[0149] The receiving module 51 is used to receive active fault detection data sent by the node devices of each data management agency participating in the target project. Each agency participates in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, earthquake structure map compilation, earthquake structure analysis, active fault hazard assessment and earthquake hazard assessment.

[0150] The loading module 52 is used to load active fault detection data in batches into a thematic database corresponding to the detection topic. The thematic database includes: multiple feature classes and database tables. The structure and content of each feature class and database table are defined by smart contracts.

[0151] The detection and acquisition module 53 is used to perform quality detection on each thematic database. After all the thematic databases have passed the quality detection, an active fault database template corresponding to the required parameters of the target project is selected, and the feature classes and database tables required by the active fault database template are obtained from each thematic database.

[0152] Construction module 54 is used to utilize the feature classes and database tables required by the active fault database template, combined with the active fault knowledge graph, smart contracts and blockchain technology, to construct a target active fault database with a data sharing mechanism. The data sharing mechanism allows the node devices of each data management agency participating in the target project to access and use the data in the target active fault database according to the corresponding permissions.

[0153] Figure 5 The active fault database construction system can execute Figure 1 The implementation principle and technical effect of the method for constructing the active fault database described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the construction system of the active fault database in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0154] In one possible design, Figure 5 The system for constructing the active fault database of the embodiment shown can be implemented as a computing device, such as Figure 6 As shown, the computing device may include a storage component 61 and a processing component 62 .

[0155] The storage component 61 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 62. The processing component 62 is used to: execute the method for constructing the active fault database constituted by S11 to S14 above.

[0156] The processing component 62 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0157] The storage component 61 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as random access memory (RAM), static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0158] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc. The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.

[0159] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0160] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The method for constructing an active fault database of the illustrated embodiment.

[0161] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing an active fault database, characterized in that: include: Receive active fault detection data sent by node devices of each data management agency participating in the target project. Each agency participates in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, seismic structure map compilation, seismic structure analysis, active fault hazard assessment and earthquake hazard assessment; Batch loading the active fault detection data into a thematic database corresponding to the detection topic, wherein the thematic database includes: a plurality of element classes and database tables, and the structure and content of each element class and database table are defined by a smart contract; Performing quality inspection on each thematic database, after all the thematic databases have passed the quality inspection, selecting an active fault database template corresponding to the required parameters of the target project, and obtaining the element classes and database tables required by the active fault database template from each of the thematic databases; Utilizing the feature classes and database tables required by the active fault database template, combined with active fault knowledge graph, smart contracts and blockchain technology, a target active fault database with a data sharing mechanism is constructed. The data sharing mechanism allows the node devices of each data management agency participating in the target project to access and use the data in the target active fault database according to the corresponding permissions.

2. The method according to claim 1, characterized in that: The quality inspection of each thematic database is performed, and after all the thematic databases have passed the quality inspection, an active fault database template corresponding to the required parameters of the target project is selected, including: Obtaining the project requirement document, using natural language processing technology to perform structured analysis on the project requirement document, and generating requirement analysis results, the requirement analysis results include the following requirement parameters: quality standards of each thematic database, and the detection range, detection accuracy and detection function of the active fault database, the quality standards include data integrity, consistency, accuracy and update frequency; Based on the quality standards of each thematic database, a multi-dimensional quality assessment method is used to perform quality inspection on each thematic database; After all thematic databases have passed the quality inspection, an input feature vector is constructed according to the detection range, detection accuracy and detection function of the active fault database, and the similarity between the template feature vector of each candidate template in the preset template library and the input feature vector is calculated by using the cosine similarity calculation method, and the candidate template with the greatest similarity to the input feature vector is taken as the preliminary matching result; Based on the preliminary matching results, combined with the domain expert knowledge, the reinforcement learning method is applied to generate the final matching results; The machine learning model is used to adjust the final matching results according to the historical project data to obtain the active fault database template.

3. The method according to claim 2, characterized in that The method of generating the final matching result based on the preliminary matching result and combining the domain expert knowledge with the reinforcement learning method includes: In combination with domain expert knowledge, a rule engine is applied to adjust the preliminary matching results and generate intermediate matching results; A state space, a template selection action space and a reward function are defined by using a reinforcement learning method; the state in the state space includes a detection range, a detection accuracy and a detection function, as well as an intermediate matching result; the template selection action space includes a template selection action corresponding to each combination template; the combination template is obtained by combining the intermediate matching result with some parameters in other candidate templates; the other candidate templates are other candidate templates in a preset template library except for the preliminary matching result; the reward function includes multiple objectives: the similarity between the template feature vector of the combination template and the input feature vector, the functional synergy of the combination template, user feedback on the combination template and the performance index of the combination template; Based on the reward function, the combination template corresponding to the action with the largest reward value is determined as the final matching result.

4. The method according to claim 3, characterized in that The reward function uses the following formula: ； in, yes The reward function when It's time. is the weight coefficient of the similarity between the template feature vector of the combined template and the input feature vector, is the weight coefficient of the functional synergy of the combined template, is the weight coefficient of the user's feedback on the combined template, is the weight coefficient of the performance index of the combined template, is the similarity between the template feature vector of the combined template and the input feature vector, It is the functional synergy of the combined templates. It is the user's feedback on the combination template. It is the performance index of the combined template. They are the time decay factors set for similarity, functional synergy, user feedback on the combined template, and performance indicators.

5. The method according to claim 1, characterized in that The active fault database template uses the element classes and database tables required by the active fault database template, combines active fault knowledge graphs, smart contracts and blockchain technology, and constructs a target active fault database with a data sharing mechanism, including: Using the feature classes and database tables required by the active fault database template, construct an initial active fault database of the target project; Based on the initial active fault database, display a three-dimensional geological structure model of the active fault; User feedback information of the three-dimensional geological structure model and quality inspection results of the initial active fault database are collected, and the initial active fault database is optimized according to the user feedback information and the quality inspection results. During the optimization process, data sharing rules and authority management rules in the smart contract are introduced, and the target active fault database with a data sharing mechanism is obtained by combining blockchain technology.

6. The method according to claim 5, characterized in that The user feedback information of the three-dimensional geological structure model and the quality detection results of the initial active fault database are collected, and the initial active fault database is optimized according to the user feedback information and the quality detection results. In the optimization process, the data sharing rules and authority management rules in the smart contract are introduced, and the target active fault database with a data sharing mechanism is obtained by combining the blockchain technology, including: Displaying a user interface, allowing node devices of various data management institutions participating in the target project to submit opinions and suggestions on the three-dimensional geological structure model in a specified form based on the user interface, wherein the specified form includes: questionnaire survey, scoring and free text input, integrating the opinions and suggestions submitted by the node devices of all institutions to form user feedback information of the three-dimensional geological structure model; using a clustering algorithm to classify the user feedback information into first quality events of different categories; Sending the initial active fault database and the active fault detection data sent by the node devices of each data management agency participating in the target project to a database quality detection agency to obtain a quality detection result, where the quality detection result is obtained by the database quality detection agency performing a quality detection on the initial active fault database based on the active fault detection data sent by the node devices of each data management agency participating in the target project; analyzing the quality detection result to identify a second quality event; Performing a comprehensive analysis on the first quality events and the second quality events of different categories to obtain a comprehensive analysis result, wherein the comprehensive analysis result includes a priority processing order of each quality event; According to the comprehensive analysis results, combined with the data sharing rules and authority management rules in the smart contract and blockchain technology, the initial active fault database is optimized to obtain a target active fault database with a data sharing mechanism.

7. The method according to claim 6, characterized in that The first quality events and the second quality events of different categories are comprehensively analyzed to obtain a comprehensive analysis result, wherein the comprehensive analysis result includes a priority processing order of each quality event, including: Obtain sentiment scores of first quality events of different categories from user feedback information, use the sentiment score as one of the factors for evaluating severity, determine the severity of the first quality event in combination with technical evaluation, and use the weighted sum of the severity, impact scope, and frequency of the first quality event as the comprehensive score of the first quality event; Obtaining the severity, impact scope and frequency of the second quality event from the quality detection result, and taking the weighted sum of the severity, impact scope and frequency of the second quality event as the comprehensive score of the second quality event; Sort the comprehensive scores of all quality events from large to small to obtain the priority processing order of each quality event.

8. A system for constructing an active fault database, characterized in that: include: A receiving module is used to receive active fault detection data sent by node devices of various data management agencies participating in the target project. Each agency participates in at least one detection topic in the target project: drilling detection, hidden detection, activity identification, seismic structure map compilation, seismic structure analysis, active fault hazard assessment and earthquake hazard assessment; A loading module, used for loading the active fault detection data in batches into a thematic database corresponding to the detection topic, wherein the thematic database includes: a plurality of element classes and database tables, and the structure and content of each element class and database table are defined by a smart contract; The detection and acquisition module is used to perform quality detection on each thematic database. After all the thematic databases have passed the quality detection, an active fault database template corresponding to the required parameters of the target project is selected, and the element classes and database tables required by the active fault database template are obtained from each of the thematic databases. A construction module is used to utilize the feature classes and database tables required by the active fault database template, combine active fault knowledge graphs, smart contracts and blockchain technology, and construct a target active fault database with a data sharing mechanism. The data sharing mechanism allows node devices of various data management agencies participating in the target project to access and use data in the target active fault database according to corresponding permissions.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for constructing an active fault database as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the method for constructing an active fault database as described in any one of claims 1 to 7 is implemented.

Images