Geological data quality inspection method and device and storage medium

Abstract

The invention relates to a geological data quality inspection method and device and a storage medium, and the method comprises the steps: building a multi-dimensional operator rule base based on the spatial topological relation of geological objects; the multi-dimensional operator rule base comprises a plurality of operator rule groups with different dimensions; obtaining to-be-checked geological data and quality inspection scene information for the to-be-checked geological data; performing semantic analysis processing on the quality inspection scene information to obtain quality inspection key features; retrieving a multi-dimensional operator rule base based on the quality inspection scene information, and determining a plurality of target operator rule groups based on a retrieval result; determining a target operator rule template in the target operator rule group according to the quality inspection key features; instantiating each target operator rule template to generate a corresponding target quality inspection operator, and performing modular assembly processing on each target quality inspection operator to generate a dynamic quality inspection script; and performing quality inspection processing on the to-be-inspected geological data based on the dynamic quality inspection script to obtain a quality inspection result. According to the invention, the problem of low accuracy of geological data quality inspection is solved.

Description

Technical Field

[0001] The present application relates to the field of geology, and in particular to a method, device and storage medium for quality inspection of geological data. Background Art

[0002] With the widespread application of geographic information systems (GIS) technology, geological data is playing an increasingly important role in resource exploration, disaster warning, urban planning, and other fields. However, geological data is multi-source, heterogeneous, and dynamically changing, resulting in uneven data quality, which seriously affects the effectiveness of applications based on geological data. Therefore, it is necessary to check the quality of geological data.

[0003] Geological data quality inspection refers to the process of systematically verifying and evaluating geological data's accuracy, completeness, logical consistency, and other quality characteristics based on professional standards and technical specifications. Its core goal is to ensure the reliability of geological data in production, management, and application, providing reliable data support for decision-making in geological surveys, resource exploration, environmental assessments, and other areas. In related technologies, quality inspection methods are still primarily manual or based on simple human-computer interaction. Faced with massive amounts of complex geographic data, manual inspection is time-consuming and labor-intensive, and is significantly influenced by subjective factors, making it difficult to guarantee accuracy.

[0004] Currently, no effective solution has been proposed to address the problem of low accuracy in geological data quality inspection in related technologies. Summary of the Invention

[0005] The embodiments of the present application provide a geological data quality inspection method, device, and storage medium to at least solve the problem of low accuracy of geological data quality inspection in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a geological data quality inspection method, the method comprising:

[0007] Based on the spatial topological relationship of geological objects, a multidimensional operator rule base is established; the multidimensional operator rule base includes a plurality of operator rule groups of different dimensions;

[0008] Acquire the geological data to be checked and quality inspection scene information for the geological data to be checked; perform semantic analysis on the quality inspection scene information to obtain key features of quality inspection;

[0009] Retrieving the multidimensional operator rule base based on the quality inspection scenario information, and determining a plurality of target operator rule groups based on the retrieval results;

[0010] Determine the target operator rule template in the target operator rule group according to the quality inspection key features; instantiate each of the target operator rule templates to generate a corresponding target quality inspection operator, and perform modular assembly processing on each of the target quality inspection operators to generate a dynamic quality inspection script;

[0011] The geological data to be checked is quality inspected based on the dynamic quality inspection script to obtain a quality inspection result.

[0012] In some embodiments, the multidimensional operator rule base is established based on the spatial topological relationship of the geological objects, including:

[0013] Acquiring the spatial topological relationship of the geological objects and establishing a spatial dimension model including a plurality of sets of indicating spatial operator rules;

[0014] Based on a preset first knowledge base, a logic rule model including multiple sets of indicative logic operator rules is established; based on preset scenario information, a business semantic model including multiple sets of indicative semantic operator rules is established;

[0015] The spatial dimension model, the logical rule model and the business semantic model are fused to establish the multidimensional operator rule library.

[0016] In some embodiments, the dynamic quality inspection script is generated by assembling a spatial quality inspection operator in the spatial dimension model, a semantic quality inspection operator in the business semantic model, and a logical quality inspection operator in the logical rule model; and performing quality inspection on the geological data to be inspected based on the dynamic quality inspection script to obtain a quality inspection result includes:

[0017] Get the shared entity identifier;

[0018] Based on the shared entity identifier, the spatial quality inspection operator is associated with the semantic quality inspection operator, a mapping relationship between spatial features and business semantics is established, and the logical quality inspection operator is embedded in the spatial semantic relationship chain as a trigger condition to generate a dynamic reasoning path;

[0019] Based on the dynamic reasoning path, the geological data to be checked is subjected to quality inspection to obtain the quality inspection result.

[0020] In some embodiments, instantiating each target operator rule template to generate a corresponding target quality inspection operator includes:

[0021] Obtaining a parameter type based on the operator rule type of the target operator rule template;

[0022] In the case where the parameter type is a static type, a statically assigned parameter is generated based on the target operator rule template, and the statically assigned parameter is injected into the target operator rule template for instantiation to generate the target quality inspection operator;

[0023] When the parameter type is a dynamic type, the input parameter instruction is parsed to generate the dynamic parameter, or the preset second knowledge base is called to generate the dynamic parameter; the dynamic parameter is injected into the target operator rule template for instantiation to generate the target quality inspection operator.

[0024] In some embodiments, the modular assembly processing of each target quality inspection operator to generate a dynamic quality inspection script includes:

[0025] Based on the operator rule type, a dependency topology relationship of each target quality inspection operator is generated; and modular assembly processing is performed on each target quality inspection operator according to the dependency topology relationship to generate the dynamic quality inspection script.

[0026] In some embodiments, generating a dependency topology relationship of each target quality inspection operator based on the operator type of the target quality inspection operator includes:

[0027] Defining a dependency triplet for each target quality inspection operator and constructing an initial dependency topology graph based on the dependency triplet;

[0028] Determining a dynamic operator subset and an independent operator subset in the initial dependency topology graph based on the operator type, and adjusting the initial dependency topology graph based on the dynamic operator subset and the independent operator subset to generate a target dependency topology graph;

[0029] Based on the target dependency topology graph, the dependency topology relationship is generated.

[0030] In some embodiments, after obtaining the quality inspection results, the method further includes:

[0031] Storing the quality inspection results as a structured database;

[0032] The structured database is queried to generate geological disaster risk prevention information and geological element error reports, and visualization results are generated based on the geological disaster risk prevention information and the geological element error reports.

[0033] In some embodiments, obtaining the geological data to be checked includes:

[0034] Obtaining original geological data;

[0035] Redundant information in the original geological data is identified and removed to obtain cleaned geological data; and the attribute table structure of the cleaned geological data is adjusted to a preset standard result to obtain the geological data to be checked.

[0036] In a second aspect, an embodiment of the present application provides a geological data quality inspection device, comprising:

[0037] A library building module is used to build a multi-dimensional operator rule base based on the spatial topological relationship of geological objects; the multi-dimensional operator rule base includes a plurality of operator rule groups of different dimensions;

[0038] An acquisition module is used to acquire the geological data to be checked and quality inspection scene information for the geological data to be checked; perform semantic analysis on the quality inspection scene information to obtain key features of quality inspection;

[0039] A retrieval module, configured to retrieve the multidimensional operator rule base based on the quality inspection scenario information, and determine a plurality of target operator rule groups based on the retrieval results;

[0040] An instantiation module is used to determine the target operator rule template in the target operator rule group according to the quality inspection key features; instantiate each target operator rule template to generate a corresponding target quality inspection operator, and perform modular assembly processing on each target quality inspection operator to generate a dynamic quality inspection script;

[0041] The quality inspection module is used to perform quality inspection on the geological data to be checked based on the dynamic quality inspection script to obtain quality inspection results.

[0042] In a third aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the program is executed by a processor, the geological data quality inspection method as described in the first aspect above is implemented.

[0043] Compared with related technologies, the geological data quality inspection method, device and storage medium provided in the embodiments of the present application establish a multidimensional operator rule base based on the spatial topological relationship of geological objects; the multidimensional operator rule base includes multiple operator rule groups of different dimensions; the geological data to be checked and the quality inspection scene information for the geological data to be checked are obtained; the quality inspection scene information is semantically parsed to obtain key quality inspection features; the multidimensional operator rule base is retrieved based on the quality inspection scene information, and multiple target operator rule groups are determined based on the retrieval results; the target operator rule template in the target operator rule group is determined according to the key quality inspection features; each target operator rule template is instantiated to generate a corresponding target quality inspection operator, and each target quality inspection operator is modularly assembled to generate a dynamic quality inspection script; the geological data to be checked is quality inspected based on the dynamic quality inspection script to obtain a quality inspection result.

[0044] Based on this, a multi-semantic relationship geological feature inspection method based on operator rules was proposed to address the diverse and dynamically changing quality inspection requirements of geological data. By constructing an inspection operator rule library that supports complex semantic relationship modeling and integrating it with a rule engine to enable flexible configuration and automated execution of the inspection process, the accuracy, efficiency, and adaptability of geological feature inspection were significantly improved. Furthermore, by instantiating specific inspection tasks from a predefined inspection operator rule library, this method supports the modular assembly and automated execution of the quality inspection process. Compared with traditional fixed-script quality inspection methods, this method offers greater flexibility and maintainability. Users can quickly configure inspection rule combinations based on different application scenarios, and the system automatically schedules execution and outputs structured inspection results. This effectively reduces errors caused by human intervention and improves the consistency and stability of data quality, thereby effectively addressing the issue of low accuracy in geological data quality inspection.

[0045] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0047] Figure 1 This is a hardware structure block diagram of a terminal of a geological data quality inspection method according to an embodiment of the present application;

[0048] Figure 2 This is a flow chart of a geological data quality inspection method according to an embodiment of the present application;

[0049] Figure 3 This is a schematic diagram of a geological data quality inspection software display interface according to an embodiment of the present application;

[0050] Figure 4 This is a structural block diagram of a geological data quality inspection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means and should not be understood as the contents disclosed in the present application being insufficient.

[0052] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0053] Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this application belongs. The terms "a," "an," "an," "the," and similar expressions used herein do not denote limitations on quantity and may refer to either the singular or the plural. The terms "comprise," "include," "have," and any variations thereof, used herein, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules (units) is not limited to the listed steps or units but may also include steps or units not listed, or may include other steps or units inherent to the process, method, product, or apparatus. The terms "connected," "connected," "coupled," and similar expressions used herein are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. As used herein, "plurality" means greater than or equal to two. "And / or" describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" may mean: A exists alone; A and B exist simultaneously; or B exists alone. The terms "first", "second", "third" and the like involved in this application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0054] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 This is a hardware structure diagram of a terminal of a geological data quality inspection method according to an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0055] Memory 104 can be used to store computer programs, such as software programs and modules for application software, such as the computer program corresponding to the geological data quality inspection method in the embodiments of the present application. Processor 102 executes the computer programs stored in memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned method. Memory 104 can include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located from processor 102, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0056] Transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the terminal's communications provider. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0057] This embodiment provides a geological data quality inspection method. Figure 2 is a flow chart of a geological data quality inspection method according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0058] Step S210: establishing a multidimensional operator rule base based on the spatial topological relationship of the geological objects; the multidimensional operator rule base includes a plurality of operator rule groups of different dimensions.

[0059] Among other things, checking for polysemantic relationships helps identify inconsistencies in geological element content, such as interactions between slope units and their associated debris flow basins, risk prevention zones, and other elements. This ensures that the hazard index within a slope unit not only conforms to its own logical requirements (e.g., extreme rainstorm hazard index > heavy rain hazard index > rainstorm hazard index > heavy rain hazard index) but also remains consistent with population and property risk values. Operators for polysemantic relationships support checking for multidimensional semantic relationships between similar geological elements and across different geological element types. For example, intra-class consistency ensures logical consistency between attribute values ​​within a layer, while cross-class consistency ensures consistency between attribute values ​​of related fields across different layers, such as consistency in hazard levels and risk values ​​between slope units and debris flow basins.

[0060] Specifically, based on the spatial topological relationships of geological objects (such as geometric association features such as adjacency, inclusion, and intersection), GIS tools or spatial database functions are first used to extract topological structure data between geological elements. For example, the spatial positional relationships between faults and rock layers, and landslides and residential areas are identified. Subsequently, logical rules in the geological field (such as "faults should not pass through intact bedrock") and business calculation models (such as "hazard = stability × rainfall coefficient") are combined to construct a multidimensional operator rule library covering spatial dimensions (topological relationship verification), logical dimensions (business rationality verification), and business dimensions (indicator quantitative calculation). This rule library is divided into multiple operator rule groups according to dimensions. For example, the spatial topology rule group contains templates such as "distance threshold check" and "direction relationship verification", the logical constraint rule group contains templates such as "lithology matching verification" and "parameter boundary check", and the business calculation rule group contains templates such as "hazard classification formula" and "loss estimation model". Each group of rules is linked across dimensions through a unique identifier, ultimately forming a structured rule set that supports dynamic quality inspection reasoning.

[0061] Step S220 , obtaining the geological data to be checked and quality inspection scene information for the geological data to be checked; performing semantic analysis on the quality inspection scene information to obtain key features for quality inspection.

[0062] In this step, the geological data to be checked (such as geological layers, monitoring sensor data, field survey records, etc.) are first obtained through the data interface or file import method, and the corresponding quality inspection scenario information (such as "post-earthquake landslide disaster emergency assessment" or "routine stability inspection of mineral mining areas") is obtained. Subsequently, natural language processing (NLP) technology is used to perform semantic analysis of the scene information, and a BERT-based pre-training model is used to perform word segmentation and entity recognition on the quality inspection scene information. The geological knowledge graph is combined to perform relationship extraction and extract structured quality inspection key features, such as {disaster type: debris flow, time threshold: 24h, spatial range: mountainous area}. Key features are extracted through word segmentation, entity recognition and relationship extraction. For example, "the risk of debris flow in mountainous areas caused by heavy rain" can be parsed into time features ("24 hours after heavy rain"), spatial features ("mountainous areas with slopes > 30°") and business objectives ("debris flow hazard classification"), ultimately forming a structured set of quality inspection key features, such as {disaster type: debris flow, time threshold: 24h, spatial range: mountainous area, evaluation indicators: hazard}.

[0063] In an optional embodiment, the above-mentioned acquisition of the geological data to be checked may further include the following steps: obtaining original geological data; identifying and removing redundant information in the original geological data to obtain cleaned geological data; adjusting the attribute table structure of the cleaned geological data to a preset standard result to obtain the geological data to be checked.

[0064] Specifically, considering the non-standardization of actual geological data, such as the fact that layer names may carry administrative division information, custom identifiers, and other non-uniformities, it is first necessary to standardize and preprocess these raw data. This process includes renaming the names of each layer in accordance with regulations to ensure that they conform to the standard format, such as removing unnecessary prefixes or suffixes, and uniformly using prescribed abbreviations and codes to represent specific geographical areas or feature types. In addition, it is necessary to check and standardize the attribute table structure within each layer to confirm that the number, name, type, and length of fields meet the standard requirements and that all required fields are correctly filled in. Through this series of data cleaning and standardization operations, it can be ensured that the subsequent quality inspection process based on operator matching can be carried out smoothly, thereby improving the accuracy and reliability of the entire geological hazard risk assessment work. This step is the basis for efficient and automated quality inspection, and provides structured and consistent data support for multi-semantic relationship analysis.

[0065] Step S230 , searching a multidimensional operator rule base based on the quality inspection scenario information, and determining a plurality of target operator rule groups based on the search results.

[0066] Step S240 , determining the target operator rule template in the target operator rule group according to the quality inspection key features; instantiating each target operator rule template to generate a corresponding target quality inspection operator, and performing modular assembly processing on each target quality inspection operator to generate a dynamic quality inspection script.

[0067] In steps S230 to S240, the applicable operator group is determined based on the specific quality inspection requirement. For example, if the quality inspection requirement involves checking data integrity, the corresponding "Integrity Check" operator group will be selected; if the requirement is for checking the validity of attribute value domains or cross-layer consistency, the "Value Domain Standardization Check" or "Cross-Layer Consistency Check" operator group will be selected. Next, specific operator entries within this group are further filtered based on the specific content of the quality inspection requirement. For example, when checking the area field of a slope unit surface layer, a specific operator specifically designed to detect whether a numeric field is positive and within a reasonable range will be selected. Subsequently, based on the selected operator and its parameter requirements, the operator is instantiated. This process involves converting a general operator template into a specialized rule applicable to the current quality inspection task by inputting specific parameter values. For example, for a requirement to verify that the area field of a slope unit surface layer is greater than zero and does not exceed a certain upper limit, an operator with these specific threshold parameters will be instantiated and given a clear rule name, such as "Slope Unit Area Validity Check Rule_001." Ultimately, these instantiated operators will be integrated into the entire quality inspection solution in the form of rules.

[0068] To achieve the above goals, the input-output dependencies of the target quality inspection operators (such as spatial topology verification, logical condition verification, and business indicator calculation) are analyzed based on their rule types, and a dependency topology is constructed to clarify the execution sequence and data transmission path between operators. Subsequently, based on the strong dependencies (such as the blocking of subsequent operators if the preceding operator is not completed) and weak dependencies (such as independent operators that can be executed in parallel) in the topological relationship, a modular assembly strategy is adopted to encapsulate the operators into components with clear interfaces (such as spatial verification components and logical decision-making components). The dependency parsing engine automatically arranges the component calling sequence, ultimately generating a dynamic quality inspection script that supports conditional branching (such as "if the distance is <50 meters, execute the high-risk process"), parallel computing (such as running "slope verification" and "lithology verification" simultaneously), and dynamic backtracking (such as automatically triggering data re-collection when verification fails). This ensures that geological quality inspection tasks can flexibly combine operator logic according to the needs of complex scenarios, realizing full automation and intelligence of the entire process from data quality inspection to risk assessment.

[0069] Specifically, based on the target dependency topology, a directed acyclic graph (DAG) scheduling algorithm is employed to orchestrate the target quality inspection operators into an execution process in dependency order. This supports conditional branching (e.g., "If rainfall exceeds a threshold, trigger the warning process") and parallel computing (e.g., executing the "slope verification" and "lithology verification" operators simultaneously), ultimately generating an executable dynamic quality inspection script. This dual logging mechanism provides intuitive user feedback while ensuring in-depth technical support, thereby achieving an efficient and reliable automated quality inspection process and significantly improving the accuracy and efficiency of geological hazard risk assessment. This process not only simplifies operational processes but also enhances the system's maintainability and scalability.

[0070] For example, the following is the pseudo code of a dynamic quality inspection script. This pseudo code takes the quality inspection of the slope unit surface layer in the geological hazard risk assessment results as an example, covering multiple dimensions such as spatial topology verification, attribute value range verification, and business logic verification:

[0071] / / Define the global configuration of dynamic quality inspection scripts

[0072] CONFIG {

[0073] DATA_SOURCE: "PA2 " / / Slope unit surface layer data source

[0074] OUTPUT_LOG: "QualityCheckLog.txt" / / Log output path

[0075] ERROR_THRESHOLD: 5 / / Error threshold, exceeding it triggers backtracking

[0076] PARALLEL_EXECUTION: TRUE / / Whether to enable parallel computing

[0077] }

[0078] / / Define the quality inspection operator component interface

[0079] INTERFACE QualityCheckComponent {

[0080] INPUT: DataLayer / / Input data layer

[0081] OUTPUT: CheckResult / / Check result (Pass / Fail + ErrorMessage)

[0082] EXECUTE(): CheckResult / / Execute quality inspection logic

[0083] DEPENDENCIES: List <component> / / Dependent pre-components

[0084] }

[0085] / / Define the quality inspection result structure

[0086] STRUCT CheckResult {

[0087] STATUS: Boolean / / Quality inspection status (True: Pass, False: Fail)

[0088] MESSAGE: String / / Quality inspection details or error description

[0089] DATA: Object / / processed data or intermediate results

[0090] }

[0091] / / Define specific quality inspection operator components (example: area validity check)

[0092] COMPONENT AreaValidityCheck IMPLEMENTS QualityCheckComponent {

[0093] INPUT: PA2

[0094] OUTPUT: CheckResult

[0095] DEPENDENCIES: [ ] / / No pre-dependencies

[0096] EXECUTE() {

[0097] result = new CheckResult()

[0098] FOR each feature in SlopeUnitLayer {

[0099] IF feature.Area <= 0 {

[0100] result.STATUS = FALSE

[0101] result.MESSAGE = "Area value must be greater than 0for feature ID: " + feature.ID

[0102] BREAK

[0103] }

[0104] }

[0105] IF result.STATUS != FALSE {

[0106] result.STATUS = TRUE

[0107] result.MESSAGE = "All area values ​​are valid."

[0108] }

[0109] RETURN result

[0110] }

[0111] }

[0112] / / Define a specific quality inspection operator component (for example: slope value range check)

[0113] COMPONENT SlopeAngleCheck IMPLEMENTS QualityCheckComponent {

[0114] INPUT: PA2

[0115] OUTPUT: CheckResult

[0116] DEPENDENCIES: [ ] / / No pre-dependencies, can be run in parallel with area check

[0117] EXECUTE() {

[0118] result = new CheckResult()

[0119] FOR each feature in PA2 {

[0120] IF feature.SlopeAngle < 0 OR feature.SlopeAngle > 90 {

[0121] result.STATUS = FALSE

[0122] result.MESSAGE = "Slope angle must be between 0 and90 for feature ID: " + feature.ID

[0123] BREAK

[0124] }

[0125] }

[0126] IF result.STATUS != FALSE {

[0127] result.STATUS = TRUE

[0128] result.MESSAGE = "All slope angle values ​​are valid."

[0129] }

[0130] RETURN result

[0131] }

[0132] }

[0133] / / Define specific quality inspection operator components (example: comprehensive risk level inspection)

[0134] COMPONENT RiskLevelCheck IMPLEMENTS QualityCheckComponent {

[0135] INPUT: PA2

[0136] OUTPUT: CheckResult

[0137] DEPENDENCIES: [AreaValidityCheck] / / Dependency area check completed

[0138] EXECUTE() {

[0139] result = new CheckResult()

[0140] FOR each feature in SlopeUnitLayer {

[0141] IF feature.ComprehensiveRiskLevel IN ["Medium Risk Area", "High Risk Area", "Extremely High Risk Area"] {

[0142] IF feature.IsRiskPreventionZone != "yes" {

[0143] result.STATUS = FALSE

[0144] result.MESSAGE = "Risk prevention zone must be defined for high risk level, feature ID: " + feature.ID

[0145] BREAK

[0146] }

[0147] }

[0148] }

[0149] IF result.STATUS != FALSE {

[0150] result.STATUS = TRUE

[0151] result.MESSAGE = "Risk level and prevention zone settings are consistent."

[0152] }

[0153] RETURN result

[0154] }

[0155] }

[0156] / / Define the dynamic quality inspection script execution process

[0157] SCRIPT DynamicQualityCheck {

[0158] / / Define the operator component list

[0159] COMPONENTS: [

[0160] areaCheck = new AreaValidityCheck(),

[0161] slopeCheck = new SlopeAngleCheck(),

[0162] riskCheck = new RiskLevelCheck() ]

[0164] / / Build dependency topology graph (DAG)

[0165] TOPOLOGY:

[0166] areaCheck -> riskCheck / / Area check is a prerequisite for risk level check

[0167] slopeCheck -> None / / Slope check has no post-dependencies and can be executed in parallel

[0168] }

[0169] / / Execution process

[0170] EXECUTE() {

[0171] errorCount = 0

[0172] results = [ ]

[0173] / / Parallel execution of operators with no or weak dependencies

[0174] IF PARALLEL_EXECUTION {

[0175] PARALLEL {

[0176] results.append(areaCheck.EXECUTE())

[0177] results.append(slopeCheck.EXECUTE())

[0178] }

[0179] } ELSE {

[0180] results.append(areaCheck.EXECUTE())

[0181] results.append(slopeCheck.EXECUTE())

[0182] }

[0183] / / Execute strong dependency operators in dependency order

[0184] IF areaCheck.Result.STATUS == TRUE {

[0185] results.append(riskCheck.EXECUTE())

[0186] } ELSE {

[0187] LOG("Skipping RiskLevelCheck due to AreaValidityCheckfailure.")

[0188] }

[0189] / / Check result summary and dynamic backtracking

[0190] FOR each result in results {

[0191] IF result.STATUS == FALSE {

[0192] errorCount++

[0193] LOG(result.MESSAGE, OUTPUT_LOG)

[0194] }

[0195] }

[0196] / / Conditional branch: If the number of errors exceeds the threshold, trigger backtracking

[0197] IF errorCount > ERROR_THRESHOLD {

[0198] LOG("Error count exceeds threshold, triggering data re-collection.", OUTPUT_LOG)

[0199] TRIGGER_RECOLLECTION()

[0200] } ELSE {

[0201] LOG("Quality check completed with acceptable errorlevel.", OUTPUT_LOG)

[0202] }

[0203] RETURN results

[0204] }

[0205] / / Dynamic backtracking logic

[0206] TRIGGER_RECOLLECTION() {

[0207] / / Trigger data re-collection logic (example)

[0208] SEND_NOTIFICATION("Data quality issue detected, please re-collect data for PA2 .")

[0209] UPDATE_STATUS("Pending Re-collection")

[0210] }

[0211] }

[0212] / / Main program entry

[0213] MAIN {

[0214] script = new DynamicQualityCheck()

[0215] results = script.EXECUTE()

[0216] FOR each result in results {

[0217] PRINT(result.MESSAGE)

[0218] }

[0219] }

[0220] Step S250: Perform quality inspection on the geological data to be inspected based on the dynamic quality inspection script to obtain a quality inspection result.

[0221] Specifically, during the automated quality inspection execution phase, each rule in the quality inspection plan is configured as optional, allowing users to flexibly select the rules to execute based on their specific needs. Users initiate the quality inspection process by clicking the "Start" button, and the system will perform a comprehensive inspection of the geological data in the order of the selected rules. The entire quality inspection process is fully logged, ensuring detailed tracking of the status and results of each step. Log content includes, but is not limited to, the name of the currently executed rule, the geological elements involved (such as slope unit surfaces and debris flow basin surfaces), the quality inspection progress, any errors, warnings, and prompts encountered. To enhance user experience and transparency, key information is displayed in real-time in the user interface, including a progress bar, a list of successful and failed tasks, and immediate warnings and prompts. These visual outputs help users keep abreast of quality inspection progress and quickly respond to potential issues. Furthermore, more detailed background logs are generated and stored, primarily for use by developers and technical support teams. These logs contain all technical details, such as specific error stack traces and system call information, facilitating troubleshooting and subsequent optimization. The background log not only records the success and failure of each step, but also captures various warning and prompt information that may affect the quality inspection results, ensuring the stability and reliability of the system.

[0222] For example, see Figure 3 The figure shows the display interface of the self-developed quality inspection software; the user clicks "New Project" or "Open Project" in the interface to import batch quality inspection data; and clicks the "Start Inspection" button; the quality inspection software automatically executes the above series of control processes and displays the quality inspection results in detail in the center of the display interface.

[0223] Through the above steps S210 to S250, a multi-semantic relationship geological element inspection method based on operator rules is proposed to address the diverse and dynamically changing quality inspection requirements in geological data quality inspection. By constructing an inspection operator rule library that supports complex semantic relationship modeling and combining it with a rule engine to achieve flexible configuration and automated execution of the inspection process, the accuracy, efficiency, and adaptability of geological element inspection are significantly improved. In addition, by instantiating specific inspection tasks through the predefined inspection operator rule library, the modular assembly and automated execution of the quality inspection process are supported. Compared with the traditional fixed script quality inspection method, this method has higher flexibility and maintainability. Users can quickly configure inspection rule combinations according to different application scenarios, and the system automatically schedules execution and outputs structured inspection results, effectively reducing errors caused by human intervention and improving the consistency and stability of data quality, thereby effectively solving the problem of low accuracy in geological data quality inspection.

[0224] In some embodiments, the above-mentioned establishment of a multidimensional operator rule base based on the spatial topological relationship of geological objects may further include the following steps:

[0225] Acquire the spatial topological relationship of geological objects and establish a spatial dimension model including multiple sets of indicating spatial operator rules; based on the preset first knowledge base, establish a logical rule model including multiple sets of indicating logical operator rules; based on the preset scene information, establish a business semantic model including multiple sets of indicating semantic operator rules; fuse the spatial dimension model, logical rule model and business semantic model to establish a multidimensional operator rule base.

[0226] Traditional geological element inspection methods usually only focus on the compliance judgment of a single layer or attribute field, and are difficult to deal with the complex spatial-semantic dependencies between geological elements. In order to improve this problem, in an embodiment of the present application, a spatial-semantic multidimensional relationship modeling mechanism is introduced into the field of geological data quality inspection, which not only considers the attribute characteristics of a single geological object itself, but also deeply analyzes the spatial, logical and business semantic relationships between it and other geological elements. For example, when checking and evaluating the hazard index, not only the risk value of a single slope unit is used, but also the influence of factors such as its surrounding environment (such as population density, building / property distribution) is comprehensively considered, so as to achieve a more comprehensive and scientific risk assessment and quality control.

[0227] Among them, the spatial-semantic multidimensional relationship modeling mechanism mainly includes the following key stages: spatial relationship modeling (spatial dimension); semantic relationship modeling (logical and business dimension); multidimensional relationship fusion and reasoning; quality assessment.

[0228] The following describes the detailed implementation process:

[0229] In the process of building a multidimensional operator rule library, the spatial relationship modeling (spatial dimension) phase begins with spatial topological relationship identification. GIS spatial analysis tools or spatial database functions are used to determine the topological relationships between geometric objects: adjacency, inclusion, intersection, and proximity. For spatial distance and direction modeling, Euclidean distance, path distance, and azimuth are calculated between different geological objects to quantify the impact of a particular geological hazard on surrounding buildings. For spatial buffer analysis, buffer zones are established for high-risk areas (such as landslide sources) to identify sensitive targets within their impact zones (such as residential areas and roads). For spatial network analysis, a spatial connection network of geological objects is constructed to simulate the propagation paths of geological events (such as seismic waves and debris flow diffusion). Using the geological object ID as the primary key, a one-to-many mapping is performed between spatial operator rules (such as 'Distance between landslide and residential area < 100 meters') and semantic operator rules (such as 'Hazard level = distance weight × 0.6 + slope weight × 0.4'). This creates a spatial-semantic joint index table, enabling efficient retrieval and invocation of multidimensional rules.

[0230] During the semantic relationship modeling phase, a primary knowledge base is constructed based on expert knowledge. This knowledge base is then combined with logical rule modeling to define reasonable logical relationships between geological features using ontologies or rule engines. For example, rules such as "faults should not penetrate intact bedrock," "landslides should occur above weak rock layers," and "collapses should occur on steep slopes" can be expressed using formal languages ​​such as SQL-like rules. Simultaneously, business semantic modeling is performed, integrating actual application scenarios to establish a business logic model. Here, hazard = f(slope stability, rainfall, human activity); potential loss = f(population density, building density, economic value). For unstructured text descriptions (such as field records), natural language processing (NLP) techniques can be used to extract semantic features and perform matching analysis to achieve semantic similarity matching.

[0231] Next, in the multidimensional relationship fusion and reasoning stage, a reasoning mechanism based on the Drools rule engine was used to convert spatial relationship rules (such as 'the distance between the landslide body and the residential area is less than 100 meters') and semantic rules (such as 'hazard level = distance weight × 0.6 + slope weight × 0.4') into executable rule sets, and quality inspection conclusions were automatically derived through forward chaining. Specifically, by sharing entity identifiers (such as the unique ID of a geological object), spatial operator rules in the spatial dimension model (such as "the distance between the landslide and residential area is less than 100 meters" and "the angle between the fault strike and the stratum dip is greater than 30 degrees") are deeply linked with semantic operator rules in the business semantic model (such as "hazard level = distance weight × 0.6 + slope weight × 0.4" and "repair cost = affected area × unit cost"), establishing a mapping relationship chain from spatial features to business semantics. Simultaneously, logical operator rules in the logical rule model (such as "if the fault passes through bedrock, block stability calculation" and "if rainfall exceeds a threshold, trigger a debris flow warning") are embedded as conditional trigger nodes in this mapping chain, forming a dynamic reasoning path from spatial feature verification to logical condition triggering, and then to business semantic calculation. For example, when the spatial operator detects "the distance between the landslide and residential area is 80 meters," it triggers the logical rule "distance < 100 meters," which in turn activates the semantic operator "hazard level = high." Ultimately, by integrating these association rules and trigger chains, a multidimensional operator rule library covering spatial constraints, logical verification, and business quantification is generated, realizing automated closed-loop reasoning from raw geological data to risk assessment conclusions.

[0232] Through the above-mentioned embodiments, a spatial-semantic multidimensional relationship modeling mechanism is introduced. By constructing a complex relationship network between geological elements and conducting multidimensional fusion analysis, the limitations of traditional single attribute inspection are broken through, and the quality and risk status of geological data can be evaluated more scientifically and comprehensively. It has broad application prospects, especially in the fields of geological disaster warning. In addition, by introducing semantic analysis capabilities and rule engine technology, intelligent identification and consistency verification of complex relationships between geological elements are realized, which significantly improves the automation level, accuracy and flexibility of the quality inspection process. This method based on the Drools rule engine not only provides powerful reasoning capabilities, but also supports flexible configuration and expansion, making the quality inspection process more adaptable to the needs of diverse geological scenarios.

[0233] In some embodiments, the instantiation of each target operator rule template to generate the corresponding target quality inspection operator may further include the following steps:

[0234] Get the parameter type based on the operator rule type of the target operator rule template;

[0235] When the parameter type is static, statically assigned parameters are generated based on the target operator rule template, and the statically assigned parameters are injected into the target operator rule template for instantiation to generate the target quality inspection operator.

[0236] When the parameter type is dynamic, the input parameter instruction is parsed to generate dynamic parameters, or the preset second knowledge base is called to generate dynamic parameters; the dynamic parameters are injected into the target operator rule template for instantiation to generate the target quality inspection operator.

[0237] An example of the target algorithm rule template is shown in Table 1:

[0238] Table 1

[0239]

[0240] In Table 1 above, the parameter type includes static or dynamic type; N / A indicates not applicable; SlopeAreaValidityTemplate indicates the slope validity template; rainfall_threshold indicates the rainfall threshold; min_area indicates the minimum area threshold; and CheckResult indicates the quality inspection result. The rule code identifies the source of the rule, such as a general quality inspection rule from quality inspection technical requirements. The template name identifies the purpose of the template and facilitates retrieval. Static parameters in the parameter field have a fixed value of 0, indicating that the "Area" field must be greater than 0. A static parameter type means that the parameter value is fixed when the template is defined and does not depend on external data. The corresponding parameter value provides an example value for the static parameter. If the parameter is dynamic, it is obtained from an external source. Dynamic parameters in the parameter field, for example, thresholds that change based on real-time data (such as the threshold field of a rule), have a dynamic parameter type, meaning that the parameter value must be parsed at runtime or obtained from a secondary knowledge base. The corresponding parameter value provides an example value for a dynamic parameter. For example, real-time rainfall is obtained from a meteorological data interface. Dependencies ensure that data is cleaned before template instantiation (for example, general quality inspection rules require that the submitted data file can be opened normally to ensure data file integrity). Output fields include, for example, output status (pass / fail) and message.

[0241] Specifically, the metadata structure of the target operator rule template is first parsed to identify the parameter type fields defined therein (e.g., param_type: "static" or param_type: "dynamic"). Furthermore, the dynamic requirements of the parameters are further inferred by combining the business semantic tags of the rule template (e.g., "spatial distance threshold" and "rainfall weighting coefficient"). For example, if the rule template contains a "slope threshold" and is marked as static, a fixed value (e.g., 30°) is directly read from the template configuration. If the rule template contains a "real-time rainfall" and is marked as dynamic, the real-time value must be obtained through an external data interface or knowledge base. This ultimately forms a clear mapping between parameter type and value acquisition method.

[0242] When the parameter type is determined to be static, the system directly extracts fixed values ​​from the preset parameter pool of the target operator rule template (such as "Maximum allowable slope = 35°" and "Fault buffer distance = 200 meters"), or generates statically assigned parameters based on the default values ​​configured in the template. These parameters are then injected into the parameter placeholders of the rule template as key-value pairs (such as {"slope_threshold": 35}), completing the instantiation of the operator rule and ultimately generating an independently executable target quality inspection operator (such as "Slope verification operator: Trigger warning if actual slope > 35°"). This operator does not require external data interaction in the subsequent quality inspection process.

[0243] If the parameter type is dynamic, the system first checks whether there is a user-entered parameter instruction (such as {"rainfall": "real-time monitoring value"} in the API request). If so, the dynamic value is extracted through the instruction parser. If no external instruction is received, the system calls the preset second knowledge base (such as the meteorological bureau data service) through the RESTful API interface to obtain current rainfall data, or obtains geological monitoring data (such as displacement rate and stress change) through the sensor Internet of Things platform. The dynamic parameter (such as {"rainfall_threshold": 85}) is then injected into the dynamic parameter slot of the target operator rule template to generate a target quality inspection operator that relies on real-time data (such as "rainfall warning operator: if 85mm>threshold 60mm, upgrade the risk level") to ensure that the operator can adaptively adjust the quality inspection logic according to environmental changes.

[0244] Through the above embodiment, by distinguishing between static / dynamic parameter types, fixed thresholds and real-time data can be automatically adapted to avoid rule failure problems caused by hard-coded parameters, thereby effectively reducing the traditional quality inspection system's dependence on static data and improving decision-making accuracy under complex geological conditions.

[0245] In some embodiments, the modular assembly process of each target quality inspection operator to generate a dynamic quality inspection script may further include the following steps:

[0246] Based on the operator rule type, the dependency topology relationship of each target quality inspection operator is generated; according to the dependency topology relationship, each target quality inspection operator is modularly assembled to generate a dynamic quality inspection script.

[0247] The system analyzes the input-output dependencies of target quality inspection operators based on their rule types (e.g., spatial topology verification, logical condition validation, and business indicator calculation), constructs dependency topology relationships, and clarifies the execution sequence and data transfer paths between operators. Subsequently, based on strong dependencies (e.g., subsequent operators are blocked if the preceding operator is not completed) and weak dependencies (e.g., independent operators that can be executed in parallel) in the topological relationships, a modular assembly strategy is adopted to encapsulate the operators into components with clear interfaces (e.g., spatial verification components and logical decision-making components). The dependency parsing engine automatically arranges the component calling sequence, ultimately generating dynamic quality inspection scripts that support conditional branching (e.g., "execute high-risk processes if the distance is <50 meters"), parallel computing (e.g., running "slope verification" and "lithology verification" simultaneously), and dynamic backtracking (e.g., automatically triggering data re-collection if verification fails). This ensures that geological quality inspection tasks can flexibly combine operator logic according to the needs of complex scenarios, achieving full automation and intelligence throughout the entire process, from data quality inspection to risk assessment.

[0248] In some embodiments, the above-mentioned generation of the dependency topology relationship of each target quality inspection operator based on the operator type of the target quality inspection operator may further include the following steps:

[0249] Define dependency triples for each target quality inspection operator and construct an initial dependency topology graph based on the dependency triples. Based on the operator type, determine the dynamic operator subset and the non-dependency operator subset in the initial dependency topology graph, and adjust the initial dependency topology graph based on the dynamic operator subset and the non-dependency operator subset to generate a target dependency topology graph. Based on the target dependency topology graph, generate the dependency topology relationship.

[0250] Specifically, a dependency triple (<operator ID, input dependency set, output identifier>) is first defined for each target quality inspection operator. The input dependency set specifies the prerequisite data or intermediate results required for the operator to execute, and the output identifier marks the unique data identifier generated by the operator. Based on the dependency triples of all operators, an initial dependency topology graph is constructed using a graph theory algorithm. The nodes in the graph represent operators, and the directed edges indicate the data flow (for example, the edge from the "coordinate extraction operator" to the "distance calculation operator" is labeled "output coordinate").

[0251] Next, based on operator type (static / dynamic) and dependency characteristics (such as the initial data acquisition operator), the topology graph is divided into a dynamic operator subset (operators that rely on real-time data or external interfaces, such as the "rainfall monitoring operator") and a non-dependent operator subset (independently executed root node operators, such as the "geological layer loading operator"). The initial topology graph is optimized through dynamic edge weight adjustment (such as adding a "data ready" trigger condition to dynamic operators) and redundant edge pruning (such as removing false dependencies between non-dependent operators). The resulting target dependency topology graph clearly presents the execution order between operators in a structured form (such as the "lithology classification operator" must be completed before the "stability coefficient operator" can be executed), parallel relationships (such as the "slope verification operator" and the "fault detection operator" can run simultaneously), and dynamic triggering logic (such as "activating the debris flow warning branch when real-time rainfall exceeds the threshold"). This provides a precise dependency control basis for the modular assembly and execution scheduling of subsequent dynamic quality inspection scripts.

[0252] In some embodiments, after obtaining the quality inspection results, the geological data quality inspection method may further include the following steps:

[0253] The quality inspection results are stored as a structured database; the structured database is queried to generate geological hazard risk prevention information and geological element error reports, and visualization results are generated based on the geological hazard risk prevention information and geological element error reports.

[0254] In the final stage of generating the risk assessment report, the quality inspection results can be output in the form of a structured database to ensure the comprehensiveness and traceability of the information. The output content is divided into two main parts:

[0255] First, the summary of geological hazard risk prevention zone information covers data statistics and analysis across multiple key dimensions. These include: the total number; the number of key prevention zones (including the number of designated key prevention zones and their detailed information); the number and distribution of key and general prevention zones; the number of susceptibility zones (including the number of zones categorized by "high susceptibility," "medium susceptibility," "low susceptibility," and "low susceptibility"); and the number of hazard zones under various rainstorm conditions (including the number of zones classified by hazard level (e.g., low hazard, medium hazard, high hazard, and extremely high hazard)) for heavy rain, torrential rain, severe rainstorm, and extremely heavy rainstorm conditions.

[0256] Secondly, a detailed error report is provided for the output of geological element errors. This report includes: graphics, which contain the specific graphical elements involved in the error (such as slope unit surfaces and debris flow basin surfaces); attributes, which contain information about the attribute fields associated with the error; corresponding rules, which contain the name and description of the specific quality inspection rule that caused the error; error content, which contains a detailed description of the error and explains the specific reasons for non-compliance; and improvement suggestions, which provide specific improvement recommendations based on the error content, to help users quickly locate the problem and make corrections. This data is systematically stored in the database for subsequent query and analysis. More specifically, the error report output consists of an error suggestion table and a table of point, line, and surface elements with errors. The error suggestion table stores all errors discovered during the quality inspection process. Each record corresponds to a specific error item and contains basic information about the error and the relevant rules. The point, line, and surface element table stores the geographic elements (points, lines, and surfaces) found in the quality inspection process. The attributes of each element contain the specific error problem. The generated risk assessment report not only provides a scientific basis for geological hazard management decisions, but also improves data quality and reliability through detailed error reporting. This process not only simplifies the data analysis process but also lays a solid foundation for subsequent risk management and disaster prevention efforts. In addition, this structured output method supports further data mining and visualization, enhancing the transparency and usability of information.

[0257] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0258] This embodiment also provides a geological data quality inspection device, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, terms such as "module," "unit," and "subunit" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0259] Figure 4 This is a structural block diagram of a geological data quality inspection device according to an embodiment of the present application. Figure 4 As shown, the device includes: a database building module 10, an acquisition module 20, a retrieval module 30, an instantiation module 40 and a quality inspection module 50; wherein:

[0260] The database construction module 10 is used to establish a multidimensional operator rule base based on the spatial topological relationship of the geological object; the multidimensional operator rule base includes multiple operator rule groups of different dimensions; the acquisition module 20 is used to obtain the geological data to be checked and the quality inspection scene information for the geological data to be checked; the quality inspection scene information is semantically parsed to obtain the key features of quality inspection; the retrieval module 30 is used to retrieve the multidimensional operator rule base based on the quality inspection scene information, and determine multiple target operator rule groups based on the retrieval results; the instantiation module 40 is used to determine the target operator rule template in the target operator rule group according to the key features of quality inspection; each target operator rule template is instantiated to generate the corresponding target quality inspection operator, and each target quality inspection operator is modularly assembled to generate a dynamic quality inspection script; the quality inspection module 50 is used to perform quality inspection on the geological data to be checked based on the dynamic quality inspection script to obtain quality inspection results.

[0261] In some embodiments, the above-mentioned database building module 10 is also used to obtain the spatial topological relationship of geological objects, establish a spatial dimension model including multiple groups of indicating spatial operator rules; based on a preset first knowledge base, establish a logical rule model including multiple groups of indicating logical operator rules; based on preset scene information, establish a business semantic model including multiple groups of indicating semantic operator rules; and fuse the spatial dimension model, the logical rule model and the business semantic model to establish a multidimensional operator rule library.

[0262] In some embodiments, the quality inspection module 50 is also used to obtain a shared entity identifier; based on the shared entity identifier, the spatial quality inspection operator is associated with the semantic quality inspection operator, a mapping relationship from spatial features to business semantics is established, and the logical quality inspection operator is embedded in the spatial semantic relationship chain as a trigger condition to generate a dynamic reasoning path; based on the dynamic reasoning path, the geological data to be checked is quality inspected to obtain the quality inspection results.

[0263] In some embodiments, the instantiation module 40 is also used to obtain a parameter type based on the operator rule type of the target operator rule template; when the parameter type is a static type, a static assignment parameter is generated based on the target operator rule template, and the static assignment parameter is injected into the target operator rule template for instantiation to generate a target quality inspection operator; when the parameter type is a dynamic type, the input parameter instruction is parsed to generate a dynamic parameter, or a preset second knowledge base is called to generate a dynamic parameter; the dynamic parameter is injected into the target operator rule template for instantiation to generate a target quality inspection operator.

[0264] In some embodiments, the instantiation module 40 is further configured to generate a dependency topology of each target quality inspection operator based on the operator rule type; and to perform modular assembly processing on each target quality inspection operator according to the dependency topology to generate a dynamic quality inspection script.

[0265] In some embodiments, the instantiation module 40 is also used to define dependency triples for each target quality inspection operator, and construct an initial dependency topology graph based on the dependency triples; based on the operator type, determine the dynamic operator subset and the non-dependency operator subset in the initial dependency topology graph, and adjust the initial dependency topology graph based on the dynamic operator subset and the non-dependency operator subset to generate a target dependency topology graph; based on the target dependency topology graph, generate a dependency topology relationship.

[0266] In some embodiments, the above-mentioned geological data quality inspection device also includes a visualization module; the visualization module is used to store the quality inspection results as a structured database; query the structured database, generate geological disaster risk prevention information and geological element error reports, and generate visualization results based on the geological disaster risk prevention information and geological element error reports.

[0267] In some embodiments, the acquisition module 20 is further used to acquire original geological data; identify and remove redundant information in the original geological data to obtain cleaned geological data; and adjust the attribute table structure of the cleaned geological data to a preset standard result to obtain the geological data to be checked.

[0268] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0269] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0270] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0271] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0272] S1, based on the spatial topological relationship of geological objects, a multidimensional operator rule base is established; the multidimensional operator rule base includes operator rule groups of multiple different dimensions.

[0273] S2, obtaining the geological data to be checked and the quality inspection scene information for the geological data to be checked; performing semantic analysis on the quality inspection scene information to obtain key features of quality inspection.

[0274] S3, retrieves a multidimensional operator rule base based on the quality inspection scenario information, and determines multiple target operator rule groups based on the retrieval results.

[0275] S4, determining the target operator rule template in the target operator rule group according to the key features of quality inspection; instantiating each target operator rule template to generate the corresponding target quality inspection operator, and performing modular assembly processing on each target quality inspection operator to generate a dynamic quality inspection script.

[0276] S5, performing quality inspection on the geological data to be inspected based on the dynamic quality inspection script to obtain quality inspection results.

[0277] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0278] In addition, in conjunction with the geological data quality inspection method in the above embodiments, the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any of the geological data quality inspection methods in the above embodiments is implemented.

[0279] Those skilled in the art should understand that the various technical features of the above-described embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0280] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.< / component>

Claims

1. A geological data quality inspection method, characterized in that: The method comprises: Based on the spatial topological relationship of geological objects, a multidimensional operator rule base is established; the multidimensional operator rule base includes a plurality of operator rule groups of different dimensions; Acquire the geological data to be checked and quality inspection scene information for the geological data to be checked; perform semantic analysis on the quality inspection scene information to obtain key features of quality inspection; Retrieving the multidimensional operator rule base based on the quality inspection scenario information, and determining a plurality of target operator rule groups based on the retrieval results; Determine the target operator rule template in the target operator rule group according to the quality inspection key features; instantiate each of the target operator rule templates to generate a corresponding target quality inspection operator, and perform modular assembly processing on each of the target quality inspection operators to generate a dynamic quality inspection script; The geological data to be checked is quality inspected based on the dynamic quality inspection script to obtain a quality inspection result.

2. The geological data quality inspection method according to claim 1, characterized in that: The multidimensional operator rule base is established based on the spatial topological relationship of the geological objects, including: Acquiring the spatial topological relationship of the geological objects and establishing a spatial dimension model including a plurality of sets of indicating spatial operator rules; Based on a preset first knowledge base, a logic rule model including multiple sets of indicative logic operator rules is established; based on preset scenario information, a business semantic model including multiple sets of indicative semantic operator rules is established; The spatial dimension model, the logical rule model and the business semantic model are fused to establish the multidimensional operator rule library.

3. The geological data quality inspection method according to claim 2, characterized in that: The dynamic quality inspection script is generated by assembling the spatial quality inspection operator in the spatial dimension model, the semantic quality inspection operator in the business semantic model, and the logical quality inspection operator in the logical rule model; The method of performing quality inspection on the geological data to be inspected based on the dynamic quality inspection script to obtain a quality inspection result includes: Get the shared entity identifier; Based on the shared entity identifier, the spatial quality inspection operator is associated with the semantic quality inspection operator, a mapping relationship between spatial features and business semantics is established, and the logical quality inspection operator is embedded in the spatial semantic relationship chain as a trigger condition to generate a dynamic reasoning path; Based on the dynamic reasoning path, the geological data to be checked is subjected to quality inspection to obtain the quality inspection result.

4. The geological data quality inspection method according to claim 1, characterized in that: Instantiating each target operator rule template to generate a corresponding target quality inspection operator includes: Obtaining a parameter type based on the operator rule type of the target operator rule template; In the case where the parameter type is a static type, a statically assigned parameter is generated based on the target operator rule template, and the statically assigned parameter is injected into the target operator rule template for instantiation to generate the target quality inspection operator; When the parameter type is a dynamic type, the input parameter instruction is parsed to generate the dynamic parameter, or the preset second knowledge base is called to generate the dynamic parameter; the dynamic parameter is injected into the target operator rule template for instantiation to generate the target quality inspection operator.

5. The geological data quality inspection method according to claim 4, characterized in that: The modular assembly process of each target quality inspection operator to generate a dynamic quality inspection script includes: Based on the operator rule type, a dependency topology relationship of each target quality inspection operator is generated; and modular assembly processing is performed on each target quality inspection operator according to the dependency topology relationship to generate the dynamic quality inspection script.

6. The geological data quality inspection method according to claim 5, characterized in that: The generating of the dependency topological relationship of each target quality inspection operator based on the operator type of the target quality inspection operator includes: Defining a dependency triplet for each target quality inspection operator and constructing an initial dependency topology graph based on the dependency triplet; Determining a dynamic operator subset and an independent operator subset in the initial dependency topology graph based on the operator type, and adjusting the initial dependency topology graph based on the dynamic operator subset and the independent operator subset to generate a target dependency topology graph; Based on the target dependency topology graph, the dependency topology relationship is generated.

7. The geological data quality inspection method according to claim 1, characterized in that: After obtaining the quality inspection results, the method further includes: Storing the quality inspection results as a structured database; The structured database is queried to generate geological disaster risk prevention information and geological element error reports, and visualization results are generated based on the geological disaster risk prevention information and the geological element error reports.

8. The geological data quality inspection method according to any one of claims 1 to 7, characterized in that: The obtaining of the geological data to be checked includes: Obtaining original geological data; Redundant information in the original geological data is identified and removed to obtain cleaned geological data; and the attribute table structure of the cleaned geological data is adjusted to a preset standard result to obtain the geological data to be checked.

9. A geological data quality inspection device, characterized in that: include: The database building module is used to build a multi-dimensional operator rule library based on the spatial topological relationship of geological objects; The multidimensional operator rule base includes a plurality of operator rule groups of different dimensions; An acquisition module is used to acquire the geological data to be checked and quality inspection scene information for the geological data to be checked; perform semantic analysis on the quality inspection scene information to obtain key features of quality inspection; A retrieval module, configured to retrieve the multidimensional operator rule base based on the quality inspection scenario information, and determine a plurality of target operator rule groups based on the retrieval results; An instantiation module, configured to determine a target operator rule template in the target operator rule group according to the quality inspection key features; Instantiate each target operator rule template to generate a corresponding target quality inspection operator, and perform modular assembly processing on each target quality inspection operator to generate a dynamic quality inspection script; The quality inspection module is used to perform quality inspection on the geological data to be checked based on the dynamic quality inspection script to obtain quality inspection results.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the geological data quality inspection method according to any one of claims 1 to 8 when running.

Images