A knowledge base structure-based intelligent data processing system and method

Abstract

This invention discloses an intelligent data processing system and method based on a knowledge base structure, relating to the field of hydropower data management technology. The method includes receiving data entry requests, classifying the data to be entered according to field types, including equipment identifiers, measurement parameters, equipment connection relationships, spatiotemporal markers, and semantic description fields; and performing range drift conflict detection, spatial topology conflict detection, physical law conflict detection, and semantic ambiguity conflict detection on the data to be entered. If any type of conflict exists in the data to be entered, it is determined that it cannot be entered, the conflict type and location are marked, a failure message is generated, and the entry request is rejected. This invention, through multi-dimensional detection of range drift, spatial topology, physical laws, and semantic ambiguity, accurately filters abnormal data, prevents erroneous information from entering the knowledge base, and ensures the reliability of hydropower equipment operation monitoring and decision-making.

Description

Technical Field

[0001] This invention belongs to the field of hydropower data management technology, and in particular relates to an intelligent data processing system and method based on a knowledge base structure. Background Technology

[0002] In the field of hydropower data management, the knowledge base serves as the core support for equipment operation monitoring, fault diagnosis, and scheduling decisions. The accuracy of its data directly impacts the operation and maintenance efficiency and safety stability of hydropower systems. Existing hydropower data entry and processing technologies have significant limitations: 1. The verification dimension is singular, relying heavily on static threshold checks, making it difficult to identify range drift caused by environmental changes or logical conflicts arising from equipment connection topology changes, easily allowing abnormal data to flow into the knowledge base; 2. Physical rules and semantic specifications are disconnected in verification. For example, when turbine operating parameters are within the range but violate energy conversion laws, traditional methods cannot effectively detect this; 3. Conflict feedback is vague, only indicating data errors without specifying the location and cause, increasing the difficulty for maintenance personnel to correct; 4. There is a lack of self-optimization mechanisms, and historical conflict information is not reused, leading to repeated occurrences of similar errors. This problem of low data verification efficiency is particularly prominent in complex systems such as cascade hydropower stations. In summary, with the advancement of digital transformation in hydropower systems, the scale of data is surging and the correlation is increasing. Traditional processing methods can no longer meet the needs of building a high-precision and high-efficiency knowledge base. Therefore, it is necessary to design an intelligent data processing system and method under a knowledge base structure to solve the above problems. Summary of the Invention

[0003] The technical problem to be solved by this invention is to provide an intelligent data processing system and method under a knowledge base structure. It aims to solve the problems of single verification dimension, disconnect between physical rules and semantic specifications verification, ambiguous conflict feedback and lack of self-optimization mechanism in the existing technology. Through multi-dimensional detection of range drift, spatial topology, physical laws and semantic ambiguity, it can accurately filter abnormal data, prevent erroneous information from entering the knowledge base and ensure the reliability of hydropower equipment operation monitoring and decision-making.

[0004] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for intelligent processing of input data under a knowledge base structure includes the following steps: S1 receives a data entry request and parses the request message to obtain the data to be entered. The data to be entered is categorized according to field type, including device identifier, measurement parameters, device connection relationship, spatiotemporal marker, and semantic description field. S2 performs conflict detection on the categorized data to be entered. Conflict detection includes: Range drift conflict detection is performed on the measurement parameters, and a dynamic range model is constructed. When the measurement parameters exceed the dynamic threshold range, it is determined that there is a range drift conflict. Spatial topology conflict detection is performed on device connection relationships and spatiotemporal markers to verify whether the device connection relationships conform to the spatial topology map. When data interaction or discontinuous transmission paths are detected between unconnected devices, a spatial topology conflict is determined to exist. Physical law conflict detection is performed on the measurement parameters and equipment connection relationship. The numerical simulation calculation is used to verify whether it meets the constraints of the physical rule base. When the deviation between the parameter and the theoretical calculation value exceeds the preset threshold, it is determined that there is a physical law conflict. Semantic ambiguity conflict detection is performed on semantic description fields. Terminology standardization mapping and concept consistency analysis are performed through the constructed standard terminology library. When a term is detected to be inconsistent with the standard definition or the concept relationship is contradictory, a semantic ambiguity conflict is determined. S3: If any conflict exists in the data to be entered, it is determined that it cannot be entered, the conflict type and location are marked, a failure message is generated and the entry request is rejected. S4 records conflict information to the historical conflict statistics database, corrects the dynamic range model based on the historical conflict statistics database, and updates the standard terminology database.

[0005] Preferably, the device identifier includes the device type code, the system identifier, and the device unique number; the measurement parameters include the parameter name, the measurement value, and the unit of measurement; the device connection relationship includes the source device identifier, the target device identifier, and the connection type; the spatiotemporal marker includes the measurement timestamp, the data recording time, and the device installation location information; and the semantic description field includes the status description text, the operation instruction description, and the description of abnormal phenomena. Step S1 also includes format standardization processing of the extracted fields, including: This involves standardizing the encoding format of device identifiers, converting the units of measurement parameters to standard units of measurement, standardizing the description format of device connection relationships, standardizing the coordinate system and time format of spatiotemporal markers, and extracting keywords and entity names from semantic description fields.

[0006] Preferably, range drift conflict detection of the measurement parameters includes: A dynamic range model is constructed to detect range drift conflicts. The dynamic range model includes equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients. The extracted measurement parameters are input into the dynamic range model to calculate the dynamic threshold range under the current environmental conditions; the measured values ​​of the measurement parameters are compared with the dynamic threshold range, and when the measured values ​​exceed the dynamic threshold range, it is determined that there is a range drift conflict. For conflicting measurement parameters, a confidence level assessment is conducted. The confidence level is based on a comprehensive evaluation of the degree to which the measured value deviates from the threshold, the frequency of similar deviations in historical data, and the fluctuation range of environmental parameters. The confidence level assessment formula is as follows: ; Where Conf represents the conflict confidence level of the measurement parameter; w D w F and w V This represents the confidence assessment weight; D represents the normalization degree of the measured value deviating from the threshold; F represents the frequency of similar deviations in historical data; and V represents the fluctuation range of the environmental parameter. When the confidence level of a measurement parameter exceeds a preset threshold, it is identified as conflicting data with valid range drift and is marked.

[0007] Preferably, constructing a dynamic range model to detect range drift conflicts includes: Obtain the equipment calibration parameters, including the upper and lower limits of the measurement range, sensitivity coefficient, and accuracy class set by the equipment at the factory. Historical operation statistics boundaries are obtained based on historical operation data. These boundaries include the historical maximum, minimum, mean, and standard deviation of the parameters, and are continuously updated through a preset sliding time window. Environmental parameters, including temperature, pressure, and humidity, are collected and environmental compensation coefficients are obtained. Regression analysis is used to determine the weight of each environmental parameter on the measured value. By combining equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients, a dynamic range model is constructed, specifically including: Using equipment calibration parameters as the baseline threshold, historical operational statistical boundaries are overlaid. These boundaries are updated using a sliding time window, taking into account historical maximum, minimum, mean, and standard deviation values. An environmental compensation coefficient is also introduced. Through regression analysis, the influence weights of temperature, pressure, and humidity are determined, constructing a dynamic range model to achieve dynamic threshold adaptation of the measurement parameters. The formula for the dynamic threshold range is as follows: ; Among them, T dynamic Represented as dynamic threshold boundary; T cal This is represented as the baseline threshold in the equipment calibration parameters; E is expressed as the historical standard deviation calculated using a sliding time window. comp Expressed as environmental compensation; and Represented as weighting coefficients; ; Among them, E compIt is expressed as environmental compensation; ΔT represents the deviation of temperature from standard operating conditions; ΔH represents the deviation of pressure from the standard operating condition; ΔH represents the deviation of humidity from the standard operating condition; w1, w2, and w3 represent the weights of the environmental parameters determined by the regression analysis.

[0008] Furthermore, the environmental parameter weights are obtained through multiple linear regression analysis. Historical measurement data of the equipment under different environmental conditions are collected, with the measured value as the dependent variable and temperature deviation ΔT, pressure deviation ΔP, and humidity deviation ΔH as independent variables to construct a regression model. The least squares method is used to solve the model parameters to obtain the influence coefficients of each environmental parameter on the measured value, namely w1, w2, and w3, which satisfy w1+w2+w3=1.

[0009] Preferably, spatial topological conflict detection of device connection relationships and spatiotemporal markers includes: Construct a spatial topology graph, which includes a set of device nodes, a physical connection matrix, and a media transmission path graph. Each device node contains a device type code and spatial location coordinates. Analyze the device connection relationships in the data to be entered, extract the source device identifier and target device identifier, query the physical connection relationship matrix, and verify whether there is an allowed connection relationship between the source device and the target device; when data interaction is detected between devices that have not established an allowed connection relationship, it is determined that there is a spatial topology conflict; the formula for verifying the physical connection relationship matrix is ​​as follows: ; This is represented as a topological conflict identifier, where 1 indicates a conflict and 0 indicates no conflict; M conn Represented as a physical connection matrix; S and T represent the matrix indices of the source and destination devices; This is represented as the connection blocking threshold; This is represented as the allowed connection threshold; Analyze the data to be entered, obtain the transmission path node sequence, compare it with the medium transmission path diagram, and verify the continuity and directionality of the node sequence. When a missing path node or a transmission direction that violates the path diagram definition is detected, a spatial topology conflict is determined. The transmission path continuity verification formula is as follows: ; in, This represents the path validity identifier, where 1 indicates valid and 0 indicates invalid; N i Let represent the i-th node in the path; i represents the index of the node in the path; n represents the total number of nodes in the path. Represented as node N i With N i+1 The physical connection between the two entities is indicated by 1 (existence) and 0 (non-existence). This indicates whether the transmission direction matches a predefined direction; 1 indicates a match, and 0 indicates a mismatch.

[0010] Furthermore, the sequence of transmission path nodes in the data to be entered is extracted and compared with the predefined medium transmission path diagram to verify whether the nodes are continuous and whether the transmission direction conforms to physical laws. This double verification ensures the physical and logical consistency of the transmission path and avoids invalid data entry due to path breakage or incorrect direction.

[0011] Preferably, the physical law conflict detection of the measurement parameters and equipment connection relationship includes: A physical rule base is constructed, which includes a set of basic physical laws, a library of equipment characteristic curves, and a set of system operation rules. The set of basic physical laws contains qualitative and quantitative constraints describing energy conversion relationships, mass conservation relationships, and fluid motion laws. The library of equipment characteristic curves includes the correspondence between the input and output parameters of the equipment. The set of system operation rules includes parameter matching constraints for multi-device cooperative operation. Extract physical parameters from measurement parameters and equipment connection relationships. Physical parameters include equipment operating status parameters, media property parameters, and system-related parameters. Match corresponding physical rules from the physical rule base according to the category of physical parameters. Based on the matched physical rules, perform numerical simulation calculations on the physical parameters to generate theoretical parameter calculation values. The physical parameters are compared with the theoretical parameters calculated by numerical simulation to determine the parameter deviation value. When the parameter deviation value exceeds the preset threshold, it is determined that there is a conflict of physical laws.

[0012] Preferably, semantic ambiguity conflict detection of the semantic description field includes: A standard terminology library is constructed, which includes a standard terminology mapping table, a concept relationship network, and a domain ontology model. The standard terminology mapping table includes the mapping relationship between industry standard terms and common non-standard expressions. The concept relationship network includes the logical association rules describing the relationship between devices, states, and operating entities. The domain ontology model includes the hierarchical system of device functions, failure modes, and operating instructions. Parse the text content in the semantic description field, identify and extract entity terms, query the standard term mapping table, and convert the identified terms into standard term expressions; Based on the concept relationship network analysis, the logical relationships between standard terminology expressions are analyzed; the associations between entities are verified to conform to predefined domain rules; and contradictions or conflicts are detected in term combinations. A semantic ambiguity conflict is determined when a term cannot be mapped to a standard term mapping table, a term combination violates the constraint rules in the concept relation network, or the text description does not match the hierarchical definition of the domain ontology model.

[0013] Preferably, step S3 includes the following steps: Summarize conflict information, which includes identifiers for range drift conflicts, spatial topology conflicts, physical law conflicts, and semantic ambiguity conflicts; Location annotation is performed on conflict information. The location annotation includes the field name, parameter number, starting position of the text paragraph and the corresponding device identifier or spatiotemporal marker involved in the conflict. Generate a failure message, which includes the conflict type name, location label details, and conflict determination criteria; The system rejects the current data entry request and sends a failure message to the terminal that initiated the data entry request.

[0014] Preferably, step S4 specifically includes the following steps: Record conflict information to a historical conflict statistics database. Conflict information includes conflict type, occurrence time, equipment identifiers involved, conflict determination criteria, and deviation quantification value. Store the records in the historical conflict statistics database according to conflict type and establish an association index between conflict and equipment type, parameter category, and environmental parameter. Based on the records of range drift conflicts in the historical conflict statistics database, the deviation patterns of similar equipment under the same environmental conditions are analyzed, and the threshold parameters of the dynamic range model are adjusted. The adjustment includes correcting the update cycle of the historical operation statistics boundary and optimizing the weight ratio of the environmental compensation coefficient. Based on the records of semantic ambiguity conflicts in the historical conflict statistics database, the standard term mapping table in the standard terminology library is revised, new correspondences between non-standard expressions and standard terms are added, the priority of association rules in the concept relationship network is adjusted, and the concept attribution of the hierarchical system in the domain ontology model is updated.

[0015] Preferably, a knowledge base structure-based intelligent data processing system is provided for executing the aforementioned knowledge base structure-based intelligent data processing method. The system includes: The data receiving module is used to receive data entry requests and complete data parsing, classification and standardization processing; The conflict detection module includes a range drift detection module, a spatial topology detection module, a physical law detection module, and a semantic ambiguity detection module. The range drift detection module is used to construct a dynamic range model and determine whether there are valid range drift conflicts. The spatial topology detection module is used to construct a spatial topology relationship map and determine whether there are spatial topology conflicts. The physical law detection module is used to determine whether there are physical law conflicts based on a physical rule base. The semantic ambiguity detection module is used to construct a standard terminology base and determine whether there are semantic ambiguity conflicts. The conflict handling module is used to receive the judgment result of the conflict detection module and mark the field name, parameter number, text paragraph start position and associated device identifier or spatiotemporal marker involved in the conflict. The knowledge base module is used to store and manage dynamic range models, spatial topology maps, physical rule bases, standard terminology bases, and historical conflict statistics databases. The feedback module allows data entry when there is no conflict, and refuses entry and sends a failure message to the terminal that initiated the data entry request when there is a conflict.

[0016] The beneficial effects of this invention are as follows: 1. This invention uses multi-dimensional detection based on range drift, spatial topology, physical laws, and semantic ambiguity to accurately filter abnormal data, prevent erroneous information from entering the knowledge base, and ensure the reliability of hydropower equipment operation monitoring and decision-making.

[0017] 2. This invention addresses the complex connections and closely related parameters of hydropower equipment by verifying physical rules and topological logic, effectively identifying hidden conflicts such as mismatches between pressure parameters and flow rates in water pipelines, and reducing operation and maintenance risks.

[0018] 3. This invention automates verification to replace manual checking, and combines precise marking of conflict locations to reduce the time spent on data correction. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of an intelligent data processing method based on a knowledge base structure according to the present invention. Figure 2 This is a schematic diagram of the intelligent data processing system based on a knowledge base structure according to the present invention. Detailed Implementation

[0020] Example 1: like Figure 1 As shown, an intelligent data processing method based on a knowledge base structure includes the following steps: S1 receives a data entry request and parses the request message to obtain the data to be entered. The data to be entered is categorized according to field type, including device identifier, measurement parameters, device connection relationship, spatiotemporal marker, and semantic description field. S2 performs conflict detection on the categorized data to be entered. Conflict detection includes: Range drift conflict detection is performed on the measurement parameters, and a dynamic range model is constructed. When the measurement parameters exceed the dynamic threshold range, it is determined that there is a range drift conflict. Spatial topology conflict detection is performed on device connection relationships and spatiotemporal markers to verify whether the device connection relationships conform to the spatial topology map. When data interaction or discontinuous transmission paths are detected between unconnected devices, a spatial topology conflict is determined to exist. Physical law conflict detection is performed on the measurement parameters and equipment connection relationship. The numerical simulation calculation is used to verify whether it meets the constraints of the physical rule base. When the deviation between the parameter and the theoretical calculation value exceeds the preset threshold, it is determined that there is a physical law conflict. Semantic ambiguity conflict detection is performed on semantic description fields. Terminology standardization mapping and concept consistency analysis are performed through the constructed standard terminology library. When a term is detected to be inconsistent with the standard definition or the concept relationship is contradictory, a semantic ambiguity conflict is determined. S3: If any conflict exists in the data to be entered, it is determined that it cannot be entered, the conflict type and location are marked, a failure message is generated and the entry request is rejected. S4 records conflict information to the historical conflict statistics database, corrects the dynamic range model based on the historical conflict statistics database, and updates the standard terminology database.

[0021] Preferably, the device identifier includes the device type code, the system identifier, and the device unique number; the measurement parameters include the parameter name, the measurement value, and the unit of measurement; the device connection relationship includes the source device identifier, the target device identifier, and the connection type; the spatiotemporal marker includes the measurement timestamp, the data recording time, and the device installation location information; and the semantic description field includes the status description text, the operation instruction description, and the description of abnormal phenomena. Step S1 also includes format standardization processing of the extracted fields, including: This involves standardizing the encoding format of device identifiers, converting the units of measurement parameters to standard units of measurement, standardizing the description format of device connection relationships, standardizing the coordinate system and time format of spatiotemporal markers, and extracting keywords and entity names from semantic description fields.

[0022] Preferably, range drift conflict detection of the measurement parameters includes: A dynamic range model is constructed to detect range drift conflicts. The dynamic range model includes equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients. The extracted measurement parameters are input into the dynamic range model to calculate the dynamic threshold range under the current environmental conditions; the measured values ​​of the measurement parameters are compared with the dynamic threshold range, and when the measured values ​​exceed the dynamic threshold range, it is determined that there is a range drift conflict. For conflicting measurement parameters, a confidence level assessment is conducted. The confidence level is based on a comprehensive evaluation of the degree to which the measured value deviates from the threshold, the frequency of similar deviations in historical data, and the fluctuation range of environmental parameters. The confidence level assessment formula is as follows: ; Where Conf represents the conflict confidence level of the measurement parameter; w D w F and w V This represents the confidence assessment weight; D represents the normalization degree of the measured value deviating from the threshold; F represents the frequency of similar deviations in historical data; and V represents the fluctuation range of the environmental parameter. When the confidence level of a measurement parameter exceeds a preset threshold, it is identified as conflicting data with valid range drift and is marked.

[0023] Preferably, constructing a dynamic range model to detect range drift conflicts includes: Obtain the equipment calibration parameters, including the upper and lower limits of the measurement range, sensitivity coefficient, and accuracy class set by the equipment at the factory. Historical operation statistics boundaries are obtained based on historical operation data. These boundaries include the historical maximum, minimum, mean, and standard deviation of the parameters, and are continuously updated through a preset sliding time window. Environmental parameters, including temperature, pressure, and humidity, are collected and environmental compensation coefficients are obtained. Regression analysis is used to determine the weight of each environmental parameter on the measured value. By combining equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients, a dynamic range model is constructed, specifically including: Using equipment calibration parameters as the baseline threshold, historical operational statistical boundaries are overlaid. These boundaries are updated using a sliding time window, taking into account historical maximum, minimum, mean, and standard deviation values. An environmental compensation coefficient is also introduced. Through regression analysis, the influence weights of temperature, pressure, and humidity are determined, constructing a dynamic range model to achieve dynamic threshold adaptation of the measurement parameters. The formula for the dynamic threshold range is as follows: ; Among them, T dynamic Represented as dynamic threshold boundary; T cal This is represented as the baseline threshold in the equipment calibration parameters; E is expressed as the historical standard deviation calculated using a sliding time window. comp Expressed as environmental compensation; and Represented as weighting coefficients; ; Among them, E comp It is expressed as environmental compensation; ΔT represents the deviation of temperature from standard operating conditions; ΔH represents the deviation of pressure from the standard operating condition; ΔH represents the deviation of humidity from the standard operating condition; w1, w2, and w3 represent the weights of the environmental parameters determined by the regression analysis.

[0024] Furthermore, the environmental parameter weights are obtained through multiple linear regression analysis. Historical measurement data of the equipment under different environmental conditions are collected, with the measured value as the dependent variable and temperature deviation ΔT, pressure deviation ΔP, and humidity deviation ΔH as independent variables to construct a regression model. The least squares method is used to solve the model parameters to obtain the influence coefficients of each environmental parameter on the measured value, namely w1, w2, and w3, which satisfy w1+w2+w3=1.

[0025] Preferably, spatial topological conflict detection of device connection relationships and spatiotemporal markers includes: Construct a spatial topology graph, which includes a set of device nodes, a physical connection matrix, and a media transmission path graph. Each device node contains a device type code and spatial location coordinates. Analyze the device connection relationships in the data to be entered, extract the source device identifier and target device identifier, query the physical connection relationship matrix, and verify whether there is an allowed connection relationship between the source device and the target device; when data interaction is detected between devices that have not established an allowed connection relationship, it is determined that there is a spatial topology conflict; the formula for verifying the physical connection relationship matrix is ​​as follows: ; This is represented as a topological conflict identifier, where 1 indicates a conflict and 0 indicates no conflict; M conn Represented as a physical connection matrix; S and T represent the matrix indices of the source and destination devices; This is represented as the connection blocking threshold; This is represented as the allowed connection threshold; Analyze the data to be entered, obtain the transmission path node sequence, compare it with the medium transmission path diagram, and verify the continuity and directionality of the node sequence. When a missing path node or a transmission direction that violates the path diagram definition is detected, a spatial topology conflict is determined. The transmission path continuity verification formula is as follows: ; in, This represents the path validity identifier, where 1 indicates valid and 0 indicates invalid; N i Let represent the i-th node in the path; i represents the index of the node in the path; n represents the total number of nodes in the path. Represented as node N i With N i+1 The physical connection between the two entities is indicated by 1 (existence) and 0 (non-existence). This indicates whether the transmission direction matches a predefined direction; 1 indicates a match, and 0 indicates a mismatch.

[0026] Furthermore, the sequence of transmission path nodes in the data to be entered is extracted and compared with the predefined medium transmission path diagram to verify whether the nodes are continuous and whether the transmission direction conforms to physical laws. This double verification ensures the physical and logical consistency of the transmission path and avoids invalid data entry due to path breakage or incorrect direction.

[0027] Preferably, the physical law conflict detection of the measurement parameters and equipment connection relationship includes: A physical rule base is constructed, which includes a set of basic physical laws, a library of equipment characteristic curves, and a set of system operation rules. The set of basic physical laws contains qualitative and quantitative constraints describing energy conversion relationships, mass conservation relationships, and fluid motion laws. The library of equipment characteristic curves includes the correspondence between the input and output parameters of the equipment. The set of system operation rules includes parameter matching constraints for multi-device cooperative operation. Extract physical parameters from measurement parameters and equipment connection relationships. Physical parameters include equipment operating status parameters, media property parameters, and system-related parameters. Match corresponding physical rules from the physical rule base according to the category of physical parameters. Based on the matched physical rules, perform numerical simulation calculations on the physical parameters to generate theoretical parameter calculation values. The physical parameters are compared with the theoretical parameters calculated by numerical simulation to determine the parameter deviation value. When the parameter deviation value exceeds the preset threshold, it is determined that there is a conflict of physical laws.

[0028] Preferably, semantic ambiguity conflict detection of the semantic description field includes: A standard terminology library is constructed, which includes a standard terminology mapping table, a concept relationship network, and a domain ontology model. The standard terminology mapping table includes the mapping relationship between industry standard terms and common non-standard expressions. The concept relationship network includes the logical association rules describing the relationship between devices, states, and operating entities. The domain ontology model includes the hierarchical system of device functions, failure modes, and operating instructions. Parse the text content in the semantic description field, identify and extract entity terms, query the standard term mapping table, and convert the identified terms into standard term expressions; Based on the concept relationship network analysis, the logical relationships between standard terminology expressions are analyzed; the associations between entities are verified to conform to predefined domain rules; and contradictions or conflicts are detected in term combinations. A semantic ambiguity conflict is determined when a term cannot be mapped to a standard term mapping table, a term combination violates the constraint rules in the concept relation network, or the text description does not match the hierarchical definition of the domain ontology model.

[0029] Preferably, step S3 includes the following steps: Summarize conflict information, which includes identifiers for range drift conflicts, spatial topology conflicts, physical law conflicts, and semantic ambiguity conflicts; Location annotation is performed on conflict information. The location annotation includes the field name, parameter number, starting position of the text paragraph and the corresponding device identifier or spatiotemporal marker involved in the conflict. Generate a failure message, which includes the conflict type name, location label details, and conflict determination criteria; The system rejects the current data entry request and sends a failure message to the terminal that initiated the data entry request.

[0030] Preferably, step S4 specifically includes the following steps: Record conflict information to a historical conflict statistics database. Conflict information includes conflict type, occurrence time, equipment identifiers involved, conflict determination criteria, and deviation quantification value. Store the records in the historical conflict statistics database according to conflict type and establish an association index between conflict and equipment type, parameter category, and environmental parameter. Based on the records of range drift conflicts in the historical conflict statistics database, the deviation patterns of similar equipment under the same environmental conditions are analyzed, and the threshold parameters of the dynamic range model are adjusted. The adjustment includes correcting the update cycle of the historical operation statistics boundary and optimizing the weight ratio of the environmental compensation coefficient. Based on the records of semantic ambiguity conflicts in the historical conflict statistics database, the standard term mapping table in the standard terminology library is revised, new correspondences between non-standard expressions and standard terms are added, the priority of association rules in the concept relationship network is adjusted, and the concept attribution of the hierarchical system in the domain ontology model is updated.

[0031] like Figure 2 As shown, a knowledge base structure-based intelligent data processing system is used to execute the aforementioned knowledge base structure-based intelligent data processing method. The system includes: The data receiving module is used to receive data entry requests and complete data parsing, classification and standardization processing; The conflict detection module includes a range drift detection module, a spatial topology detection module, a physical law detection module, and a semantic ambiguity detection module. The range drift detection module is used to construct a dynamic range model and determine whether there are valid range drift conflicts. The spatial topology detection module is used to construct a spatial topology relationship map and determine whether there are spatial topology conflicts. The physical law detection module is used to determine whether there are physical law conflicts based on a physical rule base. The semantic ambiguity detection module is used to construct a standard terminology base and determine whether there are semantic ambiguity conflicts. The conflict handling module is used to receive the judgment result of the conflict detection module and mark the field name, parameter number, text paragraph start position and associated device identifier or spatiotemporal marker involved in the conflict. The knowledge base module is used to store and manage dynamic range models, spatial topology maps, physical rule bases, standard terminology bases, and historical conflict statistics databases. The feedback module allows data entry when there is no conflict, and refuses entry and sends a failure message to the terminal that initiated the data entry request when there is a conflict.

[0032] Example 2: This embodiment provides a technical solution, a method for intelligent processing of input data under a knowledge base structure, the method including the following steps: S100: Receive data entry request, parse the request message to obtain the data content to be entered, and classify the data content to be entered according to the field type. The classification includes device identifier, measurement parameters, device connection relationship, spatiotemporal marker and semantic description field. Specifically, the equipment identifier includes the equipment type code, system identifier, and unique equipment number; the measurement parameters include the parameter name, measurement value, and unit of measurement; the equipment connection relationship includes the source equipment identifier, target equipment identifier, and connection type; the spatiotemporal marker includes the measurement timestamp, data recording time, and equipment installation location information; the semantic description field includes status description text, operation instruction description, and abnormal phenomenon description; the extracted fields undergo format standardization processing; the format standardization processing includes unifying the encoding format of the equipment identifier, converting the units of the measurement parameters to standard units of measurement, standardizing the description format of the equipment connection relationship, unifying the coordinate system and time format of the spatiotemporal marker, and extracting keywords and entity names from the semantic description field; For example: Upon receiving a data entry request, the message is parsed to obtain the data to be entered. The data is then categorized by field type, resulting in the following data: Equipment Identifier: Turbine-T01-S001, Equipment Type Code: Turbine-T01, System Identifier: Power Generation System, Unique Number: S001; Measurement parameters: Rotational speed: 3000 r / min, Outlet pressure: 9.2 MPa, Flow rate: 50 m³ / min 3 / s; Equipment connection relationship: Source equipment: water pump-P01, target equipment: water turbine-T01, connection type: water pipeline; Spatiotemporal markers: Measurement timestamp: 2025-01-01-00:00:00, Installation location: 00°00'N, 0°00'E; Semantic description field: Status description text: The turbine's current rotational speed is too high; S200. Detect range drift conflict for the measurement parameters, construct a dynamic range model, and determine that there is a range drift conflict when the measurement parameters exceed the dynamic threshold range. Specifically, step S200 includes: S210. Construct a dynamic range model to detect range drift conflicts. The dynamic range model includes equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients. Furthermore, step S210 includes: S211. Obtain the equipment calibration parameters, including the upper and lower limits of the measurement range, sensitivity coefficient, and accuracy class set by the equipment at the factory. S212. Obtain historical operation statistics boundaries based on historical operation data. The historical operation statistics boundaries include the historical maximum, minimum, mean, and standard deviation of the parameters, and are continuously updated through a preset sliding time window. S213. Collect environmental parameters and obtain environmental compensation coefficients. Environmental parameters include temperature, pressure and humidity. Determine the influence weight of each environmental parameter on the measured value through regression analysis. S214. Combine equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients to construct a dynamic range model; Using the equipment calibration parameters as the baseline threshold, historical operation statistical boundaries are superimposed. The historical operation statistical boundaries are updated with historical maximum, minimum, mean and standard deviation through a sliding time window. An environmental compensation coefficient is introduced. The influence weights of temperature, pressure and humidity are determined through regression analysis using the environmental compensation coefficient. A dynamic range model is constructed to achieve dynamic threshold adaptation of the measurement parameters. The dynamic threshold range is calculated using the following formula: ; Among them, T dynamic Represented as dynamic threshold boundary; T cal This is represented as the baseline threshold in the equipment calibration parameters; E is expressed as the historical standard deviation calculated using a sliding time window. comp Expressed as environmental compensation; and Represented as weighting coefficients; ; Among them, E comp ΔT represents the environmental compensation amount; ΔP represents the deviation of temperature from standard operating conditions; ΔH represents the deviation of humidity from standard operating conditions; w1, w2, and w3 represent the weights of environmental parameters determined by regression analysis. The environmental parameter weights were obtained through multiple linear regression analysis. Historical measurement data of the equipment under different environmental conditions were collected. The measured value was used as the dependent variable, and the temperature deviation ΔT, pressure deviation ΔP, and humidity deviation ΔH were used as independent variables to construct a regression model. The least squares method was used to solve the model parameters to obtain the influence coefficients of each environmental parameter on the measured value, namely w1, w2, and w3, which satisfy w1+w2+w3=1. For example: Equipment calibration parameters: Turbine-T01 factory measurement range 0-10MPa, sensitivity coefficient 0.01MPa, accuracy class ±0.5%; Historical operating statistical boundaries: calculated through a 30-day sliding time window, historical mean 8.0MPa, standard deviation σ hist =0.5MPa; Environmental compensation coefficient: Collected environmental parameters: Temperature 35℃, standard operating condition 25℃, ΔT=10℃; Pressure 101kPa, standard operating condition 100kPa, ΔP=1kPa; Humidity 60%, standard operating condition 50%, ΔH=10%. Through regression analysis, the weights are obtained as w1=0.4, w2=0.3, w3=0.3, and the environmental compensation amount E. comp =0.4×10+0.3×1+0.3×10=7.3, after normalization: 7.3 / 18.5≈0.3; S220. Input the extracted measurement parameters into the dynamic range model and calculate the dynamic threshold range under the current environmental conditions; compare the measured value of the measurement parameter with the dynamic threshold range. When the measured value exceeds the dynamic threshold range, it is determined that there is a range drift conflict. For example: Calculate the dynamic threshold range: Lower limit of dynamic threshold: 8.0 - 1.2 × 0.5 + 0.8 × 0.3 = 7.46 MPa; Upper limit of dynamic threshold: 8.0 + 1.2 × 0.5 + 0.8 × 0.3 = 8.54 MPa; The measured value of 9.2 MPa exceeds the upper limit, and it is preliminarily determined that there is a range drift conflict; S230. Conflicting measurement parameters are assessed for confidence level. The confidence level is based on a comprehensive assessment of the degree to which the measured value deviates from the threshold, the frequency of similar deviations in historical data, and the fluctuation range of environmental parameters. The confidence level assessment formula is as follows: ; Where Conf represents the conflict confidence level of the measurement parameter; w D w F and w V This represents the confidence assessment weight; D represents the normalization degree of the measured value deviating from the threshold; F represents the frequency of similar deviations in historical data; and V represents the fluctuation range of the environmental parameter. For example: D=|9.2-8.54| / (8.54-7.46)=0.64 / 1.08≈0.59; Frequency of similar deviations in the past 30 days is 20%: F=0.2; Overall fluctuation range of environmental parameters V=0.3; The conflict confidence level of the measurement parameters is obtained as follows: Conf = 0.4 × 0.59 + 0.3 × 0.2 + 0.3 × 0.3 = 0.236 + 0.06 + 0.09 = 0.386; S240. When the confidence level of the measurement parameter exceeds the preset threshold, it is determined to be conflicting data with effective range drift conflict and marked; for example: the preset threshold is 0.25, the conflict confidence level of the measurement parameter Conf=0.386>0.25, it is determined to be effective range drift conflict.

[0033] S300: Perform spatial topology conflict detection on device connection relationships and spatiotemporal markers to verify whether the device connection relationships conform to the spatial topology relationship map. When data interaction or discontinuous transmission paths are detected between unconnected devices, it is determined that there is a spatial topology conflict. Specifically, step S300 includes: S310. Construct a spatial topology graph, which includes a set of device nodes, a physical connection matrix, and a media transmission path graph; each device node contains a device type code and spatial location coordinates; the physical connection matrix includes the allowed connection types between devices and media transmission attributes. For example: Physical connection matrix M conn Record allowed connection relationships, M conn [Pump-P01][Pipe-M02]=1, permitted; M conn [Water Pump-P01][Generator-G03]=0, not allowed; Media transmission path diagram: Predefined valid path: Pump-P01 → Pipeline-M02 → Turbine-T01 → Generator-G03; S320. Analyze the device connection relationships in the data to be entered, extract the source device identifier and the target device identifier, query the physical connection relationship matrix, and verify whether there is an allowed connection relationship between the source device and the target device; when data interaction is detected between devices that have not established an allowed connection relationship, it is determined that there is a spatial topology conflict. The physical connectivity matrix is ​​verified using the following formula: ; Conflict topo This is represented as a topological conflict identifier, where 1 indicates a conflict and 0 indicates no conflict; M conn Represented as a physical connection matrix; S and T represent the matrix indices of the source and destination devices; This is represented as the connection blocking threshold; This is represented as the allowed connection threshold; For example: The device connection relationship in the data to be entered is: Source device [Water Pump-P01] → Target device [Generator-G03]. Query M... conn Get M conn [P01][G03]=0 (γ0=0, connection prohibited), but the data shows that there is data interaction between the two, which is determined to be a spatial topology conflict; S330. Analyze the data to be entered, obtain the transmission path node sequence, compare it with the medium transmission path diagram, verify the continuity and directionality of the node sequence, and determine that there is a spatial topology conflict when a missing path node or a transmission direction violates the path diagram definition is detected. The formula for verifying the continuity of the transmission path is as follows: ; in, This represents the path validity identifier, where 1 indicates valid and 0 indicates invalid; N i Let represent the i-th node in the path; i represents the index of the node in the path; n represents the total number of nodes in the path. Represented as node N i With N i+1 The physical connection between the two entities is indicated by 1 (existence) and 0 (non-existence). This indicates whether the transmission direction matches a predefined direction; 1 indicates a match, and 0 indicates a mismatch. For example: The transmission path to be entered is: Water Pump-P01→Generator-G03, but the node sequence is missing Pipe-M02 and Turbine-T01, and the direction is not according to the predefined path. This is invalid and is determined to be a spatial topological conflict. Extract the transmission path node sequence from the data to be entered, compare it with the predefined medium transmission path diagram, and verify whether the nodes are continuous and whether the transmission direction conforms to physical laws. This double verification ensures the physical and logical consistency of the transmission path and avoids invalid data entry due to path breakage or incorrect direction.

[0034] S400: Perform physical law conflict detection on the measurement parameters and equipment connection relationship, and verify whether they meet the constraints of the physical rule base through numerical simulation calculation. When the deviation between the parameter and the theoretical calculation value exceeds the preset threshold, it is determined that there is a physical law conflict. Step S400 includes: S410. Construct a physical rule base, which includes a set of basic physical laws, a library of equipment characteristic curves, and a set of system operation rules. The set of basic physical laws contains qualitative and quantitative constraints describing energy conversion relationships, mass conservation relationships, and fluid motion laws. The library of equipment characteristic curves includes the correspondence between the input and output parameters of the equipment. The set of system operation rules includes parameter matching constraints for multi-device cooperative operation. For example: Basic physical law: Water turbine power P=ρghQη, ρ=1000kg / m 3 g = 9.8 m / s 2 η=0.9; Equipment characteristic curve: Flow rate Q=50m³ 3 At a speed of / s, the theoretical power Ptheoretical = 1000 × 9.8 × 10 × 50 × 0.9 = 4.41 × 10-16 W=4410kW; S420. Extract the physical parameters from the measurement parameters and equipment connection relationships. The physical parameters include equipment operating status parameters, medium property parameters, and system-related parameters. Based on the category of the physical parameters, match the corresponding physical rules from the physical rule base. Based on the matched physical rules, perform numerical simulation calculations on the physical parameters to generate theoretical parameter calculation values. For example: Extract the measured power P_measured = 5000kW, and generate the theoretical value of 4410kW based on the above formula; S430. Compare the physical parameters with the calculated theoretical parameters obtained from numerical simulation to determine the parameter deviation value. When the parameter deviation value exceeds the preset threshold, it is determined that there is a conflict of physical laws. By setting a threshold, combining the accuracy level marked in the equipment characteristic curve library and the allowable deviation of the basic laws in the physical rule library, and verifying through historical compliance data, the critical criteria for judging the conflict of physical laws are determined.

[0035] For example: Deviation value ΔP=|5000-4410|=590kW; Preset threshold, combined with equipment accuracy ±5% and energy conservation allowable deviation ±10%, the preset threshold is taken as 441kW; Since 590kW>441kW, it is determined to be a conflict of physical laws.

[0036] S500. Perform semantic ambiguity conflict detection on the semantic description field, perform term standardization mapping and concept consistency analysis, and determine that there is a semantic ambiguity conflict when the term usage does not conform to the standard definition or the concept relationship is contradictory. Specifically, S510 involves constructing a standard terminology library, which includes a standard terminology mapping table, a concept relationship network, and a domain ontology model. The standard terminology mapping table includes the mapping relationship between industry standard terms and common non-standard expressions. The concept relationship network includes the logical association rules describing the relationships between devices, states, and operating entities. The domain ontology model includes the hierarchical system of device functions, failure modes, and operating instructions. S520. Parse the text content in the semantic description field, identify and extract entity terms, query the standard term mapping table, and convert the identified terms into standard term expressions. S530. Based on the concept relationship network, analyze the logical relationships between standard terminology expressions; verify whether the associations between entities conform to predefined domain rules; detect whether there are contradictions or conflicts in term combinations. S540. When a term cannot be mapped to a standard term mapping table, a combination of terms violates the constraint rules in the concept relationship network, or the text description does not match the hierarchical definition of the domain ontology model, a semantic ambiguity conflict is determined. For example, the semantic description field is: The water turbine is currently in a shutdown state and is being started; Standard Terminology Map: Shutdown corresponds to normal shutdown, where the equipment is not running; Startup corresponds to the power-on process, where the equipment goes from standby to running. Conceptual Relationship Network: Shutdown and Startup are mutually exclusive and cannot coexist at the same time. The entity terms "stop" and "start" were successfully mapped to standard terms. Analysis showed that the simultaneous occurrence of "stop" and "start" violated the mutual exclusion rule. Because the term combination violated the concept relationship network constraints, it was determined to be a semantic ambiguity conflict.

[0037] S600: If any conflict exists in the data to be entered, it is determined that it cannot be entered, the conflict type and location are marked, a failure message is generated and the entry request is rejected. Specifically, step S600 includes: S610. Summarize conflict information, including identifiers of range drift conflict, spatial topology conflict, physical law conflict, and semantic ambiguity conflict. S620. Mark the location of the conflict information. The location mark includes the field name, parameter number, text paragraph start position and corresponding device identifier or spatiotemporal marker involved in the conflict. For example: Range drift conflict: Measurement parameter: outlet pressure, parameter number P001; Spatial topology conflict: Equipment connection relationship: water pump-P01→generator-G03, equipment identifiers P001, G003; Physical law conflict: Measurement parameter: power, parameter number P002; Semantic ambiguity conflict: Semantic description field: status description text, paragraph start position, characters 5-10; S630. Generate a failure message, which includes the conflict type name, location label details, and conflict determination criteria. For example: There are 4 conflicts: 1. Range drift conflict: The outlet pressure of 9.2 MPa exceeds the threshold range of 7.46-8.54 MPa; 2. Spatial topology conflict: Pump-P01 and Generator-G03 have an interaction despite not being allowed to connect; 3. Physical law conflict: Power deviation of 590kW exceeds the threshold of 441kW; 4. Semantic ambiguity conflict: Shutdown and startup are mutually exclusive; S640: Reject the current data entry request and send a failure message to the terminal that initiated the data entry request; Furthermore, conflict information is recorded in a historical conflict statistics database, including conflict type, occurrence time, involved equipment identifiers, conflict determination criteria, and deviation quantification values. Records in the historical conflict statistics database are categorized and stored according to conflict type, and an association index is established between conflicts and equipment type, parameter category, and environmental parameters. Based on the records of range drift conflicts in the historical conflict statistics database, the deviation patterns of similar equipment under the same environmental conditions are analyzed, and the threshold parameters of the dynamic range model are adjusted, including adjusting the update cycle of correcting historical operational statistical boundaries and optimizing the weighting of environmental compensation coefficients. Based on the records of semantically ambiguous conflicts in the historical conflict statistics database, the standard terminology mapping table in the standard terminology library is revised, supplementing the new correspondence between non-standard expressions and standard terms, adjusting the priority of association rules in the concept relationship network, and updating the concept attribution of the hierarchical system in the domain ontology model.

Claims

1. A method for intelligent processing of input data under a knowledge base structure, characterized in that, Includes the following steps: S1 receives a data entry request and parses the request message to obtain the data to be entered. The data to be entered is categorized according to field type, including device identifier, measurement parameters, device connection relationship, spatiotemporal marker, and semantic description field. S2 performs conflict detection on the categorized data to be entered. Conflict detection includes: Range drift conflict detection is performed on the measurement parameters, and a dynamic range model is constructed. When the measurement parameters exceed the dynamic threshold range, it is determined that there is a range drift conflict. Spatial topology conflict detection is performed on device connection relationships and spatiotemporal markers to verify whether the device connection relationships conform to the spatial topology map. When data interaction or discontinuous transmission paths are detected between unconnected devices, a spatial topology conflict is determined to exist. Physical law conflict detection is performed on the measurement parameters and equipment connection relationship. The constraint conditions of the physical rule base are verified by numerical simulation calculation. When the deviation between the parameter and the theoretical calculation value exceeds the preset threshold, it is determined that there is a physical law conflict. Semantic ambiguity conflict detection is performed on semantic description fields. Terminology standardization mapping and concept consistency analysis are performed through the constructed standard terminology library. When a term is detected to be inconsistent with the standard definition or the concept relationship is contradictory, a semantic ambiguity conflict is determined. S3: If any conflict exists in the data to be entered, it is determined that it cannot be entered, the conflict type and location are marked, a failure message is generated and the entry request is rejected. S4 records conflict information to the historical conflict statistics database, corrects the dynamic range model based on the historical conflict statistics database, and updates the standard terminology database.

2. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, The device identifier includes the device type code, the system identifier, and the device unique number; the measurement parameters include the parameter name, the measurement value, and the unit of measurement; the device connection relationship includes the source device identifier, the target device identifier, and the connection type; the spatiotemporal markers include the measurement timestamp, the data recording time, and the device installation location information; The semantic description field includes status description text, operation instruction description, and description of abnormal phenomena; Step S1 also includes format standardization processing of the extracted fields, including: This involves standardizing the encoding format of device identifiers, converting the units of measurement parameters to standard units of measurement, standardizing the description format of device connection relationships, standardizing the coordinate system and time format of spatiotemporal markers, and extracting keywords and entity names from semantic description fields.

3. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, Range drift and conflict detection of measurement parameters includes: A dynamic range model is constructed to detect range drift conflicts. The dynamic range model includes equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients. The extracted measurement parameters are input into the dynamic range model to calculate the dynamic threshold range under the current environmental conditions; the measured values ​​of the measurement parameters are compared with the dynamic threshold range, and when the measured values ​​exceed the dynamic threshold range, it is determined that there is a range drift conflict. For conflicting measurement parameters, a confidence level assessment is conducted. The confidence level is based on a comprehensive evaluation of the degree to which the measured value deviates from the threshold, the frequency of similar deviations in historical data, and the fluctuation range of environmental parameters. The confidence level assessment formula is as follows: ； Where Conf represents the conflict confidence level of the measurement parameter; w D w F and w V This represents the confidence assessment weight; D represents the normalization degree of the measured value deviating from the threshold; F represents the frequency of similar deviations in historical data; and V represents the fluctuation range of the environmental parameter. When the confidence level of a measurement parameter exceeds a preset threshold, it is identified as conflicting data with valid range drift and is marked.

4. The intelligent data processing method for input data under a knowledge base structure according to claim 3, characterized in that, Constructing a dynamic range model to detect range drift conflicts includes: Obtain the equipment calibration parameters, including the upper and lower limits of the measurement range, sensitivity coefficient, and accuracy class set by the equipment at the factory. Historical operation statistics boundaries are obtained based on historical operation data. These boundaries include the historical maximum, minimum, mean, and standard deviation of the parameters, and are continuously updated through a preset sliding time window. Environmental parameters, including temperature, pressure, and humidity, are collected and environmental compensation coefficients are obtained. Regression analysis is used to determine the weight of each environmental parameter on the measured value. By combining equipment calibration parameters, historical operating statistical boundaries, and environmental compensation coefficients, a dynamic range model is constructed, specifically including: Using equipment calibration parameters as the baseline threshold, historical operational statistical boundaries are overlaid. These boundaries are updated using a sliding time window, taking into account historical maximum, minimum, mean, and standard deviation values. An environmental compensation coefficient is also introduced. Through regression analysis, the influence weights of temperature, pressure, and humidity are determined, constructing a dynamic range model to achieve dynamic threshold adaptation of the measurement parameters. The formula for the dynamic threshold range is as follows: ； Among them, T dynamic Represented as dynamic threshold boundary; T cal This is represented as the baseline threshold in the equipment calibration parameters; E is expressed as the historical standard deviation calculated using a sliding time window. comp Expressed as environmental compensation; and Represented as weighting coefficients; ； Among them, E comp It is expressed as environmental compensation; ΔT represents the deviation of temperature from standard operating conditions; ΔH represents the deviation of pressure from the standard operating condition; ΔH represents the deviation of humidity from the standard operating condition; w1, w2, and w3 represent the weights of the environmental parameters determined by the regression analysis.

5. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, Spatial topology conflict detection of device connectivity and spatiotemporal markers includes: Construct a spatial topology graph, which includes a set of device nodes, a physical connection matrix, and a media transmission path graph. Each device node contains a device type code and spatial location coordinates. Analyze the device connection relationships in the data to be entered, extract the source device identifier and target device identifier, query the physical connection relationship matrix, and verify whether there is an allowed connection relationship between the source device and the target device; when data interaction is detected between devices that have not established an allowed connection relationship, it is determined that there is a spatial topology conflict; the formula for verifying the physical connection relationship matrix is ​​as follows: ； This is represented as a topological conflict identifier, where 1 indicates a conflict and 0 indicates no conflict; M conn Represented as a physical connection matrix; S and T represent the matrix indices of the source and destination devices; This is represented as the connection blocking threshold; This is represented as the allowed connection threshold; Analyze the data to be entered, obtain the transmission path node sequence, compare it with the medium transmission path diagram, and verify the continuity and directionality of the node sequence. When a missing path node or a transmission direction that violates the path diagram definition is detected, a spatial topology conflict is determined. The transmission path continuity verification formula is as follows: ； in, This represents the path validity identifier, where 1 indicates valid and 0 indicates invalid; N i Let represent the i-th node in the path; i represents the index of the node in the path; n represents the total number of nodes in the path. Represented as node N i With N i+1 The physical connection between the two entities is indicated by 1 (existence) and 0 (non-existence). This indicates whether the transmission direction matches a predefined direction; 1 indicates a match, and 0 indicates a mismatch.

6. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, Physical conflict detection of measurement parameters and equipment connection relationships includes: A physical rule base is constructed, which includes a set of basic physical laws, a library of equipment characteristic curves, and a set of system operation rules. The set of basic physical laws contains qualitative and quantitative constraints describing energy conversion relationships, mass conservation relationships, and fluid motion laws. The library of equipment characteristic curves includes the correspondence between the input and output parameters of the equipment. The set of system operation rules includes parameter matching constraints for multi-device cooperative operation. Extract physical parameters from measurement parameters and equipment connection relationships. Physical parameters include equipment operating status parameters, media property parameters, and system-related parameters. Match corresponding physical rules from the physical rule base according to the category of physical parameters. Based on the matched physical rules, perform numerical simulation calculations on the physical parameters to generate theoretical parameter calculation values. The physical parameters are compared with the theoretical parameters calculated by numerical simulation to determine the parameter deviation value. When the parameter deviation value exceeds the preset threshold, it is determined that there is a conflict of physical laws.

7. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, Semantic ambiguity and conflict detection for semantic description fields includes: A standard terminology library is constructed, which includes a standard terminology mapping table, a concept relationship network, and a domain ontology model. The standard terminology mapping table includes the mapping relationship between industry standard terms and common non-standard expressions. The concept relationship network includes the logical association rules describing the relationship between devices, states, and operating entities. The domain ontology model includes the hierarchical system of device functions, failure modes, and operating instructions. Parse the text content in the semantic description field, identify and extract entity terms, query the standard term mapping table, and convert the identified terms into standard term expressions; Based on the concept relationship network analysis, the logical relationships between standard terminology expressions are analyzed; the associations between entities are verified to conform to predefined domain rules; and contradictions or conflicts are detected in term combinations. A semantic ambiguity conflict is determined when a term cannot be mapped to a standard term mapping table, a term combination violates the constraint rules in the concept relation network, or the text description does not match the hierarchical definition of the domain ontology model.

8. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, Step S3 includes the following steps: Summarize conflict information, which includes identifiers for range drift conflicts, spatial topology conflicts, physical law conflicts, and semantic ambiguity conflicts; Location annotation is performed on conflict information. The location annotation includes the field name, parameter number, starting position of the text paragraph and the corresponding device identifier or spatiotemporal marker involved in the conflict. Generate a failure message, which includes the conflict type name, location label details, and conflict determination criteria; The system rejects the current data entry request and sends a failure message to the terminal that initiated the data entry request.

9. The intelligent data processing method for input data under a knowledge base structure according to claim 1, characterized in that, Step S4 specifically includes the following steps: Record conflict information to a historical conflict statistics database. Conflict information includes conflict type, occurrence time, equipment identifiers involved, conflict determination criteria, and deviation quantification value. Store the records in the historical conflict statistics database according to conflict type and establish an association index between conflict and equipment type, parameter category, and environmental parameter. Based on the records of range drift conflicts in the historical conflict statistics database, the deviation patterns of similar equipment under the same environmental conditions are analyzed, and the threshold parameters of the dynamic range model are adjusted. The adjustment includes correcting the update cycle of the historical operation statistics boundary and optimizing the weight ratio of the environmental compensation coefficient. Based on the records of semantic ambiguity conflicts in the historical conflict statistics database, the standard term mapping table in the standard terminology library is revised, new correspondences between non-standard expressions and standard terms are added, the priority of association rules in the concept relationship network is adjusted, and the concept attribution of the hierarchical system in the domain ontology model is updated.

10. A knowledge base structure-based intelligent data processing system, used to execute the knowledge base structure-based intelligent data processing method according to any one of claims 1-9, characterized in that, The system includes: The data receiving module is used to receive data entry requests and complete data parsing, classification and standardization processing; The conflict detection module includes a range drift detection module, a spatial topology detection module, a physical law detection module, and a semantic ambiguity detection module. The range drift detection module is used to construct a dynamic range model and determine whether there are valid range drift conflicts. The spatial topology detection module is used to construct a spatial topology relationship map and determine whether there are spatial topology conflicts. The physical law detection module is used to determine whether there are physical law conflicts based on a physical rule base. The semantic ambiguity detection module is used to construct a standard terminology base and determine whether there are semantic ambiguity conflicts. The conflict handling module is used to receive the judgment result of the conflict detection module and mark the field name, parameter number, text paragraph start position and associated device identifier or spatiotemporal marker involved in the conflict. The knowledge base module is used to store and manage dynamic range models, spatial topology maps, physical rule bases, standard terminology bases, and historical conflict statistics databases. The feedback module allows data entry when there is no conflict, and refuses entry and sends a failure message to the terminal that initiated the data entry request when there is a conflict.

Images