Detection and inspection mechanism operation risk prediction method and system based on multi-source data

Abstract

The invention provides a detection and inspection mechanism operation risk prediction method and system based on multi-source data, and relates to the technical field of risk prediction. The method comprises the following steps: firstly, inputting a first detection standard into a first adjustment dimension determination model to obtain first and second adjustment dimensions respectively representing subjective requirement change and objective requirement change, and then analyzing and obtaining second risk information used for representing subjective factors by combining personnel change information corresponding to a detection standard adjustment time interval, third risk information used for representing objective factors is obtained through analysis based on the second adjustment dimension and the first detection condition, and finally the second risk information and the third risk information are synthesized to obtain target risk information of the detection mechanism. According to the technical scheme of the invention, the big data time sequence information and the machine learning model are combined, and the potential association relationship among the detection standard change, the detection personnel change and the detection risk is extracted, so that the risk prediction result of the detection mechanism is more accurate and meets the actual requirements.

Description

Technical Field

[0001] The present invention belongs to the technical field of risk prediction, and particularly relates to a method and system for predicting the operation risk of inspection and testing institutions based on multi-source data. Background Art

[0002] In the technical field of predicting the operation risk of inspection and testing institutions, existing methods mostly focus on equipment status monitoring or single-dimensional data analysis, and there is a significant lack of collaborative analysis. Traditional technical solutions usually process the detection standard update information and personnel operation data separately. Neither a dynamic coupling model of standard version evolution and personnel qualification status is established, nor the compatibility between standard parameter adjustment and personnel operation habits is quantitatively evaluated. Especially in the scenario of frequent standard updates, existing systems cannot effectively identify typical compound risks such as "personnel operating high-risk equipment without completing training within the implementation period of the new standard", nor can they warn of hidden risks caused by "incompatibility between personnel operation experience and the complexity of the new standard". This blind spot in the analysis of standard-personnel collaborative change information directly leads to an increase in the false alarm rate of the risk prediction model in dynamic scenarios and cannot accurately reflect the overall risk situation of the man-machine-environment system during the standard iteration process. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for predicting the operation risk of inspection and testing institutions based on multi-source data, so as to solve the technical problem of the increased false alarm rate of the risk prediction model in dynamic scenarios in the prior art.

[0004] The present invention proposes a method for predicting the operation risk of inspection and testing institutions based on multi-source data, and the method includes: S1: Perform a first analysis and processing on the first detection standard information and the first previous detection standard information to determine a plurality of first adjustment dimensions and a plurality of second adjustment dimensions; The first analysis and processing refers to a comparison and analysis of the new and old detection standard information; the first adjustment dimension refers to an adjustment dimension related to subjective operation, and the second adjustment dimension refers to an adjustment dimension related to the objective detection environment; S2: Obtain first personnel information and first previous personnel information according to the first detection standard information and the first previous detection standard information respectively; Wherein, the first detection standard information corresponds to the first personnel information, and the first previous detection standard information corresponds to the first previous personnel information; S3: Perform a first differential analysis on the first personnel information and the first previous personnel information to obtain first risk information; S4: Determine second risk information according to the first risk information and a plurality of the first adjustment dimensions; S5: Determine the third risk information based on the multiple second adjustment dimensions and the first detection condition information; S6: Determine the target risk information according to the second risk information and the third risk information.

[0005] Preferably, the S1 includes the following sub-steps: Step S11: Obtain the first difference information between the first detection standard information and the first previous detection standard information, and determine the structured revised feature dataset based on the first difference information; the structured revised feature dataset includes multiple revised feature data items; Step S12: Conduct the first operation responsibility analysis and the first human factor constraint analysis on each of the multiple revised feature data items one by one to obtain multiple first subjective adjustment dimension information; Step S13: Conduct the first numerical feature structuring analysis on each of the multiple revised feature data items in the structured revised feature dataset one by one to obtain multiple first objective adjustment dimension information; Step S14: Conduct the first conflict analysis on the multiple first subjective adjustment dimension information and the multiple first objective adjustment dimension information to obtain the first priority adjustment information; Step S15: Adjust the multiple first subjective adjustment dimension information and the multiple first objective adjustment dimension information based on the first priority adjustment information to obtain multiple first adjustment dimensions and multiple second adjustment dimensions.

[0006] Preferably, the S2 includes the following sub-steps: S21: Obtain the first time interval of the first detection standard information and the second time interval of the first previous detection standard information; S22: Determine the first personnel information and the first previous personnel information according to the first time interval and the second time interval.

[0007] Preferably, in the first personnel information and the first previous personnel information, it includes personnel basic information and historical violation operation information.

[0008] Preferably, the S3 includes the following sub-steps: S31: Determine the first personnel risk vector and the first previous personnel risk vector according to the first personnel information and the first previous personnel information; S32: Input the first personnel risk vector and the first previous personnel risk vector into the first risk information determination model to output the first risk information.

[0009] Preferably, the S4 includes: Match the first risk information with multiple first adjustment dimensions, and determine multiple first adjustment dimensions that meet the similarity requirement as the second risk information.

[0010] Preferably, S5 includes: Match each of the second adjustment dimensions with the first detection condition information one by one, and determine the third risk information based on at least one of the second adjustment dimensions that meet the similarity requirement.

[0011] Preferably, the first conflict analysis includes: Determine multiple first detection contradiction items based on multiple pieces of the first subjective adjustment dimension information and multiple pieces of the first objective adjustment dimension information; Among them, the multiple first detection contradiction items are used to represent the contradiction information between at least one piece of the first subjective adjustment dimension information and at least one piece of the first objective adjustment dimension information.

[0012] This application also proposes a detection and inspection agency operation risk prediction system based on multi-source data, which is used to implement the above-mentioned detection and inspection agency operation risk prediction method based on multi-source data.

[0013] The detection and inspection agency operation risk prediction method and system based on multi-source data proposed in this application relate to the technical field of risk prediction. First, input the latest adjusted first detection standard into the first adjustment dimension determination model to obtain the first and second adjustment dimensions respectively representing the changes in subjective requirements and objective requirements. Then, combine the personnel change information corresponding to the detection standard adjustment time interval to analyze and obtain the second risk information representing subjective factors. Then, based on the second adjustment dimension and the first detection condition, analyze and obtain the third risk information representing objective factors. Finally, synthesize the second and third risk information to obtain the target risk information of the detection agency. The technical solution of this application combines big data time series information and machine learning models to extract the potential correlation relationship between detection standard changes - detection personnel changes - detection risks, so that the risk prediction result of the detection agency is more accurate and meets the actual requirements. Brief Description of the Drawings

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, without creative efforts, other implementation drawings can be obtained based on the provided drawings.

[0015] Figure 1 It is the execution flowchart of the detection and inspection agency operation risk prediction method based on multi-source data in the present invention.

[0016] Figure 2 This is an example of the time interval for using the new and old detection standards in the present invention. Detailed implementation manners

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments, and the illustrative embodiments and descriptions are only used to explain the present invention, but not to limit the present invention.

[0019] The method and system for predicting the operation risk of a detection and inspection agency based on multi-source data of the present invention will be described in detail below.

[0020] There is a close relationship between the detection standards and detection conditions of a detection agency and the latest detection standards. Under different detection standards, there will be significant differences in the requirements for the detection process and detection conditions of the same detection agency.

[0021] There are multiple risk sources in the key links of the detection process (such as sample collection and processing, instrument calibration and maintenance, test method execution, data analysis and interpretation, and environmental conditions), mainly including: insufficient sample representativeness or contamination / damage resulting in result deviation; inaccurate instrument calibration or equipment failure affecting measurement accuracy; inappropriate test method selection or operation errors (such as human errors, out-of-control conditions); data processing errors or incorrect result judgments (such as calculation errors, ignoring outliers); and the influence of environmental factors (temperature and humidity changes) and cross-contamination on high-sensitivity detection.

[0022] Analyzing the above risk causes from subjective and objective reasons, the subjective reasons may include: contamination during sample collection, failure to select a suitable detection method, human errors during the detection experiment, data processing errors and incorrect judgments due to insufficient human experience, etc. The objective reasons may include: the sample collection volume not meeting the requirements of the detection standard, the equipment calibration or maintenance cycle not meeting the requirements of the detection standard, the environmental factors and cross-contamination during detection not meeting the requirements of the detection standard.

[0023] The updates of the detection standards mainly focus on improving accuracy and quality, and the content types cover: stricter requirements for instrument calibration and verification (such as more frequent or precise calibration); adjustment of test parameters (environmental conditions, processing time, etc.); changes in data processing methods and report formats; addition or upgrade of equipment functions required to support new methods; personnel training and skill improvement to cope with new standards; changes in sample preparation processes (size, pretreatment, etc.); and strengthening of compliance and documentation requirements to ensure traceability and compliance.

[0024] The above types of changes in detection standards can be further divided into changes in objective requirements and changes in subjective requirements. The changes in objective requirements refer to higher standards objectively put forward for equipment, detection processes or detection environments, and the changes in subjective requirements refer to higher standards put forward for the familiarity of operators with new software or new analysis methods.

[0025] After analyzing the reasons for the occurrence of historical detection risks, it can be known that the main reasons may include that when significant changes occur in detection standards, the detection environment and the operation ability of detection personnel have not been adaptively adjusted. After further in-depth analysis, it can be known that when different types of changes in detection standards are associated with different types of operators to form combined influencing factors, the probabilities of causing different types of detection risks will also change correspondingly.

[0026] Facing the above technical problems, the present invention proposes a technical solution to explore the potential relationship among changes in detection standards - detection personnel capabilities - detection risks, so as to accurately predict the detection risks of detection institutions within a preset future time period.

[0027] This embodiment proposes a method for predicting the operation risks of detection and inspection institutions based on multi-source data, and the specific process is as Figure 1 shown.

[0028] S1: Perform a first analysis and processing on the first detection standard information and the first previous detection standard information to determine a plurality of first adjustment dimensions and a plurality of second adjustment dimensions.

[0029] Among them, the first adjustment dimension refers to the adjustment dimension related to the subjective operation of the operator, and the second adjustment dimension refers to the objective operation dimension related to the operation environment, etc. The first analysis and processing refers to comparing and analyzing the new and old detection standard information, and obtaining a plurality of first and second adjustment dimensions used to characterize subjective and objective changes through semantic analysis means.

[0030] Among them, the first previous detection standard information refers to the detection standard information before the adjustment of the first detection standard information, that is to say, the first detection standard information is obtained by adjusting on the basis of the first previous detection standard information.

[0031] The above S1 is the basis for the technical solution of this application to accurately predict the detection risk. Because only by comprehensively and accurately analyzing the newly revised first detection standard information can the adjustments of subjective and objective factors brought about by the new version revision be accurately extracted, so as to provide basic support for subsequent detection risk prediction.

[0032] The above S1 includes the following sub-steps: Step S11: Obtain the first difference information between the first detection standard information and the first previous detection standard information, and determine the structured revision feature dataset based on the first difference information.

[0033] Among them, the structured revision feature dataset includes multiple revision feature data items.

[0034] The above S11 specifically includes: 1) Input the standard documents of the old and new versions (the first detection standard information is the latest version), extract the hierarchical structure features of the standard documents through a pre-trained document structure parsing model (CNN based on the ResNet-50 architecture), and identify the topological relationship of the chapter clauses; 2) Perform text sequence comparison on the standard documents of the old and new versions to generate a revised content index table with position identifiers, including: revision type (new / delete / modify), clause number, revised text fragment, associated context location coordinates; 3) Output the structured revision feature dataset, which is composed of multiple revision feature data items combined.

[0035] Exemplary revision feature data item is as follows: {revision ID: C001, type: parameter modification, location: Article 5.2.3, old text: "temperature range 20 - 25°C", new text: "temperature control 23 ± 0.5°C", context keywords: [constant temperature box calibration, environmental monitoring]}.

[0036] 4) Perform two-dimensional semantic marking on the structured revision feature dataset.

[0037] Input each of the revision feature data items in the structured revision feature dataset into the semantic classification model one by one: The semantic classification model uses a fine-tuned model based on BERT to identify the statements containing the responsibilities of the operation subject and the physical property constraints of numerical parameters, and outputs the probability value (i.e., confidence) P_subj and the marked type (such as personnel qualifications, operation procedures, decision-making authority, equipment parameters, environmental indicators, material properties).

[0038] Generate semantic labels with confidence scores: {Revision ID: C001, Subjective dimension label: Empty, Objective dimension label: Temperature control parameter (confidence 0.92)}.

[0039] Each of the semantic tags is a revision feature data item, and the structured revision feature data set can be obtained according to a plurality of the revision feature data items.

[0040] Step S12: performing a first operation responsibility analysis and a first human factor constraint analysis on the plurality of revision feature data items in the structured revision feature data set one by one to obtain a plurality of first subjective adjustment dimension information.

[0041] The S12 specifically includes: 1) Operational responsibility relationship modeling: A plurality of subjective dimension labels are selected from the first semantic label set outputted in step S11 and used as input, and an operation responsibility network is constructed through a dependency parser (based on an improved Stanford CoreNLP).

[0042] Extract the triple relationship: <operating subject, action verb, controlled object>, for example, from the clause "the inspector must complete the calibration under the witness of the supervisor", extract: <inspector, complete, calibration>, <supervisor, witness, calibration>; Establish the first subjective adjustment dimension information caused by the operation constraint conditions: convert the conditional adverbial clause into a logical expression, for example, "If data anomalies occur, retesting is required after approval by the technical person in charge" → retest trigger condition = data anomaly ∩ approval status = true; 2) Modeling of human factors constraint rules: Convert semantic analysis results into executable rules: Use the Drools rule engine syntax to generate a decision table. For example, convert "Only senior technicians can operate Class X equipment" into a rule: IF equipment type = X THEN operator, qualification level ≥ 3; Construct an operation timing constraint matrix: for example, encode "the interval between two detections ≥ 4 hours" as a prohibited interval [t_start, t_start+4h) on the time axis; The first subjective adjustment dimension information caused by the output standard upgrade may specifically include the above-mentioned operation authority constraints or operation time interval constraints. For example, {adjustment dimension ID: S001, type: operation authority change, affected object: X-type equipment operation authority, constraint condition: qualification level ≥ 3}.

[0043] Step S13: Perform first numerical feature structuring analysis on multiple pieces of the revised feature data items in the structured revised feature dataset to obtain multiple pieces of first objective adjustment dimension information.

[0044] Specifically, S13 may include: For multiple objective dimension tags screened out from the first semantic tag set output in step S11, adopt a multi-level parsing strategy: First-level parsing: Regular expression matching of numerical patterns (e.g., "23±0.5℃" → {reference value: 23, fluctuation range: ±0.5, unit: ℃}); Second-level parsing: Context association analysis to determine the parameter scope of action (e.g., "test chamber temperature" is associated with the temperature control module of equipment number Lab-201); Third-level parsing: Dimensional consistency verification, automatically converting units to the reference system (e.g., unifying "50kPa" to "0.05MPa"); Generate multiple pieces of first objective adjustment dimension information. For example, it can be {parameter ID: P032, parameter name: temperature control accuracy, old value: ±1.0℃, new value: ±0.5℃, affected equipment: [constant temperature incubator HWS-201, incubator PQX-305]}.

[0045] Step S14: Perform first conflict analysis on multiple pieces of the first subjective adjustment dimension information and multiple pieces of the first objective adjustment dimension information to obtain first priority adjustment information.

[0046] In the first detection standard information, there are multiple pieces of subjective adjustment information and multiple pieces of objective adjustment information, and there may be contradictions and conflicts between different subjective adjustment information and objective adjustment information. Therefore, it is necessary to first perform first conflict analysis on the above information to adaptively adjust the priorities of multiple pieces of the first subjective adjustment dimension information and multiple pieces of the first objective adjustment dimension information.

[0047] Specifically, S14 may include: 1) Dual-dimension adjustment feature fusion and conflict detection: Perform correlation analysis on multiple pieces of the first subjective adjustment dimension information in step S12 and multiple pieces of the first objective adjustment dimension information in step S13: Establish a human-machine-environment constraint relationship matrix to detect contradictory items (e.g., the new standard requires "shortening the detection time to 2 hours", but the equipment parameter adjustment results in 2.5 hours for a single detection); Identify implicit dependencies (e.g., "increasing the review frequency of inspectors" requires corresponding increase in the capacity of the data storage server).

[0048] 2) Adjustment priority calculation: Build a priority evaluation model based on the Analytic Hierarchy Process (AHP): The evaluation indicators include: standard mandatory level, number of affected devices, difficulty of personnel training, and implementation cost; Calculate the comprehensive weight of each adjustment dimension. For example, the priority score of the objective dimension P032 is 8.7 (out of 10); Output the adjustment task sequence with priorities as the first priority adjustment information. An example is as follows: {Task ID: T001, Dimension type: Objective, Parameter ID: P032, Priority: Urgent, Latest implementation time: 2023-12-01}, {Task ID: T002, Dimension type: Subjective, Adjustment ID: S001, Priority: High, Associated training plan: TR-2023-09} 。

[0049] Step S15: Adjust multiple pieces of the first subjective adjustment dimension information and multiple pieces of the first objective adjustment dimension information based on the first priority adjustment information to obtain multiple first adjustment dimensions and multiple second adjustment dimensions.

[0050] In this step, it is possible to select, according to the first priority adjustment information, the adjustment information that meets the preset priority requirements from multiple pieces of the first subjective adjustment dimension information and multiple pieces of the first objective adjustment dimension information as multiple first adjustment dimensions and multiple second adjustment dimensions.

[0051] Preferably, the specific priority screening requirements can be set according to the tolerance of detection risks. The higher the tolerance, the lower the priority threshold can be set.

[0052] S2: Obtain the first personnel information and the first pre-order personnel information according to the first detection standard information and the first pre-order detection standard information respectively.

[0053] In S1, multiple first adjustment dimensions and multiple second adjustment dimensions for characterizing the subjective dimension and the objective dimension are analyzed from the first detection standard information. To further analyze the correlation between the above adjustment dimensions and personnel changes and detection risks, in this step, the first personnel information and the first pre-order personnel information corresponding to the new and old detection standards need to be obtained.

[0054] The S2 specifically includes: S21: Obtain the first time interval of the first detection standard information and the second time interval of the first pre-order detection standard information.

[0055] The first detection standard information and the first pre - detection standard information are successively announced and continuously used. Therefore, each detection standard has a corresponding usage time interval, which are the first time interval and the second time interval respectively.

[0056] As Figure 2 As an example of the usage time intervals of the old and new detection standards, the usage interval of the first pre - detection standard information is from March 1, 2023 to March 1, 2024, and the usage interval of the first detection standard information is from March 2, 2024 to March 1, 2025.

[0057] S22: Determine the first personnel information and the first pre - personnel information according to the first time interval and the second time interval.

[0058] Within two adjacent time intervals, the personnel information of the same detection agency will change. Therefore, in this step, the corresponding first personnel information and first pre - personnel information need to be determined respectively.

[0059] In the first personnel information and the first pre - personnel information, there are basic information and historical violation operation information of the corresponding personnel, etc.

[0060] S3: Conduct a first differential analysis on the first personnel information and the first pre - personnel information to obtain the first risk information.

[0061] The first differential analysis refers to obtaining the first risk information due to personnel changes. The first risk information refers to the corresponding changes in the detection risk information of the subjective cause type caused by the change of operators.

[0062] S3 is mainly used to analyze and profile the first personnel information and the first pre - personnel information, so as to overall evaluate the subjective risk factors brought by the change of the personnel team. S3 specifically includes the following sub - steps: S31: Determine the first personnel risk vector and the first pre - personnel risk vector according to the first personnel information and the first pre - personnel information.

[0063] In this step, through the first risk profiling determination model, the characteristics of the first personnel information and the first pre - personnel information are extracted in the form of risk vectors.

[0064] Specifically, the information dimensions included in the first personnel risk vector and the first previous personnel risk vector should be the same to ensure that subsequent similar comparisons can be made. The specific information dimensions in the risk vector can be set according to specific needs and should preferably have a corresponding relationship with the multiple first adjustment dimensions in step S1. For example, it can be set as [gender, years of experience, historical operation responsibility violation information 1, historical operation responsibility violation information 2, historical human factor constraint violation information 1, historical human factor constraint violation information 2]. In the above risk vector format, the basic information of the inspection personnel is recorded, and the risk detection behaviors caused by operation responsibility violations and human factor constraint rule violations are recorded.

[0065] The above is only an example, and the information dimensions of the subjective reasons in S1 and this step can also be adjusted according to specific needs.

[0066] Since both the first personnel information and the first previous personnel information contain multiple natural persons, in this step, a risk vector needs to be generated for each natural person in a specified format, and after clustering, the first personnel risk vector and the first previous personnel risk vector that can be used to represent the overall first personnel information or the first previous personnel information are refined.

[0067] S32: Input the first personnel risk vector and the first previous personnel risk vector into the first risk information determination model to output the first risk information.

[0068] The first risk information determination model is obtained by training based on a machine learning model, and is mainly used to analyze the differences between the first personnel risk vector and the first previous personnel risk vector, and finally obtain the first risk information based on the differences.

[0069] Preferably, the first risk information determination model can be obtained by training based on a convolutional neural network model, and the historical data belonging to the same standard testing agency is used to complete the training of the model.

[0070] In the output first risk information, at least one risk dimension included in the risk vector is included, and the risk dimensions are all caused by the adjustments of the inspection personnel.

[0071] S4: Determine the second risk information according to the first risk information and the multiple first adjustment dimensions.

[0072] In this step, according to the multiple first adjustment dimensions associated with the first detection standard information, the corresponding second risk information is determined from the first risk information. That is to say, in the first risk information, at least a part of the information has a high degree of association with the multiple first adjustment dimensions, and this part of the information is determined as the second risk information.

[0073] In the specific implementation process, each piece of the first risk information can be matched with multiple first adjustment dimensions one by one for similarity. If a first adjustment dimension with a similarity meeting the preset value can be found, the first risk information can be determined as the second risk information. Through the above steps, the second risk information with high incidence can be determined from two dimensions: detection standard adjustment and personnel adjustment.

[0074] S5: Determine the third risk information based on multiple second adjustment dimensions and the first detection condition information.

[0075] The first detection condition information refers to environmental conditions, equipment conditions, layout information of detection instruments, etc. during the detection process of the target detection institution. If the above detection conditions do not match the multiple second adjustment dimensions included in the first detection standard information, the third risk information will be generated.

[0076] In the specific implementation process, each second adjustment dimension can be matched with the first detection condition information one by one for similarity, and a first similarity is determined for each second adjustment dimension. The third risk information is determined based on at least one second adjustment dimension with a first similarity greater than the preset value.

[0077] S6: Determine the target risk information based on the second risk information and the third risk information.

[0078] The target risk information combines the objective requirement adjustment and subjective requirement adjustment information reflected in the first detection standard information, so as to comprehensively and accurately reflect the target risk information of the detection institution within a preset time interval in the future.

[0079] Preferably, the target risk information can be obtained by mechanically superimposing the second risk information and the third risk information, or obtained by screening after setting priorities based on preset rules, which is not specifically limited here.

[0080] This application also proposes a detection and inspection institution operation risk prediction system based on multi-source data, which is used to execute the above-mentioned detection and inspection institution operation risk prediction method based on multi-source data.

[0081] The detection and inspection agency operation risk prediction method and system based on multi-source data proposed in this application relate to the technical field of risk prediction. First, the first detection standard after the latest adjustment is input into the first adjustment dimension determination model, so as to obtain the first and second adjustment dimensions respectively representing subjective requirement changes and objective requirement changes. Then, combined with the personnel change information corresponding to the detection standard adjustment time interval, the second risk information used to represent subjective factors is analyzed and obtained. Then, based on the second adjustment dimension and the first detection condition, the third risk information used to represent objective factors is analyzed and obtained. Finally, the second and third risk information are integrated to obtain the target risk information of the detection agency. The technical solution of this application combines big data time series information and machine learning models to refine the potential correlation relationship between detection standard changes - detection personnel changes - detection risks, so that the risk prediction result of the detection agency is more accurate and meets the actual requirements.

[0082] The above are only the preferred embodiments of the present invention. Therefore, all equivalent changes or modifications made according to the structure, features, and principles described in the scope of the present invention patent application are included in the scope of the present invention patent application.

Claims

1. A method for predicting the operation risk of inspection and testing institutions based on multi-source data, characterized in that, The method includes: S1: Perform a first analysis and processing on the first detection standard information and the first previous detection standard information to determine multiple first adjustment dimensions and multiple second adjustment dimensions; The first analysis and processing refers to a comparison and analysis of the new and old detection standard information; the first adjustment dimension refers to an adjustment dimension related to subjective operations, and the second adjustment dimension refers to an adjustment dimension related to the objective detection environment; S2: Obtain first personnel information and first previous personnel information according to the first detection standard information and the first previous detection standard information respectively; Wherein, the first detection standard information corresponds to the first personnel information, and the first previous detection standard information corresponds to the first previous personnel information; S3: Perform a first differential analysis on the first personnel information and the first previous personnel information to obtain first risk information; S4: Determine second risk information according to the first risk information and multiple first adjustment dimensions; S5: Determine third risk information based on multiple second adjustment dimensions and first detection condition information; S6: Determine target risk information according to the second risk information and the third risk information.

2. The method for predicting the operation risk of a detection and inspection agency based on multi-source data according to claim 1, wherein The S1 includes the following sub-steps: Step S11: Obtain the first difference information between the first detection standard information and the first previous detection standard information, and determine a structured revised feature data set based on the first difference information; the structured revised feature data set includes multiple revised feature data items; Step S12: Perform a first operation responsibility analysis and a first human factor constraint analysis on each of the multiple revised feature data items to obtain multiple first subjective adjustment dimension information; Step S13: Perform a first numerical feature structuring analysis on each of the multiple revised feature data items in the structured revised feature data set to obtain multiple first objective adjustment dimension information; Step S14: Perform a first conflict analysis on the multiple first subjective adjustment dimension information and the multiple first objective adjustment dimension information to obtain first priority adjustment information; Step S15: Adjust the multiple first subjective adjustment dimension information and the multiple first objective adjustment dimension information based on the first priority adjustment information to obtain multiple first adjustment dimensions and multiple second adjustment dimensions.

3. The method for predicting the operation risk of a detection and inspection institution based on multi-source data according to claim 2, wherein The S2 includes the following sub-steps: S21: Obtain the first time interval of the first detection standard information and the second time interval of the first previous detection standard information; S22: Determine the first personnel information and the first previous personnel information according to the first time interval and the second time interval.

4. The method for predicting the operation risk of a detection and inspection institution based on multi-source data according to claim 2, wherein, In the first personnel information and the first previous personnel information, it includes personnel basic information and historical violation operation information.

5. The method for predicting the operation risk of a detection and inspection agency based on multi-source data according to claim 4, wherein, The S3 includes the following sub-steps: S31: Determine a first personnel risk vector and a first previous personnel risk vector according to the first personnel information and the first previous personnel information; S32: Input the first personnel risk vector and the first previous personnel risk vector into a first risk information determination model to output first risk information.

6. The method for predicting the operation risk of a detection and inspection agency based on multi-source data according to claim 5, wherein, The S4 includes: Match the first risk information with multiple first adjustment dimensions, and determine multiple first adjustment dimensions that meet the similarity requirement as the second risk information.

7. The method for predicting the operation risk of a detection and inspection agency based on multi-source data according to claim 6, wherein The S5 includes: Match each of the second adjustment dimensions with the first detection condition information one by one, and determine the third risk information according to at least one of the second adjustment dimensions that meet the similarity requirement.

8. The method for predicting the operation risk of a detection and inspection agency based on multi-source data according to claim 7, wherein, The first conflict analysis includes: Determine multiple first detection contradiction items according to multiple first subjective adjustment dimension information and multiple first objective adjustment dimension information; Among them, the multiple first detection contradiction items are used to represent the contradiction information of at least one of the first subjective adjustment dimension information and at least one of the first objective adjustment dimension information.

9. A detection and inspection agency operation risk prediction system based on multi-source data, characterized in that, It is used to implement the detection and inspection agency operation risk prediction method based on multi-source data in the above claims 1-8.

Images