A data management and user behavior analysis system based on production whole-process management and control

Abstract

The application discloses a kind of data management and user behavior analysis system based on production whole-process management and control, it is related to user behavior analysis technical field, the application is first by real-time acquisition equipment operation data with preset early warning threshold comparison equipment operation state is abnormal, when abnormal, automatically trigger fault early warning, again acquisition multi-dimensional production behavior data of inspection personnel and form standardization dataset, calculate group matching coefficient to divide different characteristic personnel group, carry out behavior characteristic analysis, then combined with equipment fault information matching with corresponding disposal capacity of inspection personnel, push fault regulation and control and standby equipment switching instruction, finally according to matching result to corresponding inspection personnel issue execution and complete fault disposal and production process regulation and control.The application improves fault response and disposal efficiency, effectively reduces equipment fault downtime, guarantees production process continuous stable operation, while standardizes inspection operation behavior.

Description

Technical Field

[0001] This invention relates to the field of user behavior analysis technology, specifically to a data management and user behavior analysis system based on the control of the entire production process. Background Technology

[0002] The entire production process encompasses multiple procedures, equipment, and quality nodes. Significant differences exist in the technological characteristics, operating states, and environmental conditions of each stage, leading to fragmented production data and ineffective communication of user needs. Constructing a comprehensive production process data management and user behavior analysis system can achieve unified governance, end-to-end traceability, and dynamic visualization of production data. It can also deeply integrate user behavior, feedback, and production processes, supporting precise control and intelligent optimization. This system holds significant engineering importance and core practical value for enhancing data value transformation, improving production adaptability, and driving process iteration and product upgrades based on user needs.

[0003] Existing technology, such as the invention patent application with announcement number CN115696169A, discloses a data acquisition method for a MES production management system. This method includes acquiring MES system production management data for management; automatically classifying all equipment production management data types in the MES system production management data using a single-layer feedforward neural network to obtain a dataset of average equipment usage for management; performing data mining based on the field of equipment production management data type identification using a single-layer feedforward neural network; setting algorithm parameters and abnormal production management alarm signals for equipment production management data types through an interface for inspection personnel on the MES server; inputting each frame of equipment production management monitoring image acquired by equipment production management monitoring into the equipment production management data type identification model to obtain the identification result of the equipment production management data type; and inputting the identification result of the equipment production management data type into a Deep-sort algorithm to track the production management data types. This invention is used to accurately and efficiently identify equipment production management data type information.

[0004] As can be seen from the above solutions, the existing production process control and user behavior analysis system has obvious defects: data collection is scattered, no unified standardized dataset is formed, and it is difficult to integrate and utilize efficiently; there is a lack of real-time risk warning mechanism, and the response to anomalies is delayed and inefficient; there is no classification and control based on user behavior characteristics, and the control strategy is simplistic; there is no correlation analysis between user behavior and production failures, it is impossible to match inspection personnel, there is a lack of closed-loop feedback mechanism, and it is difficult to ensure production continuity and operational safety. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the present invention aims to provide a data management and user behavior analysis system based on the overall production process control.

[0006] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a data management and user behavior analysis system based on the whole production process control, including the following modules: Fault early warning module: used to collect equipment operation data in real time through sensors, compare the equipment operation data with the preset early warning threshold, determine whether the equipment operation status is abnormal, and automatically trigger fault early warning when the equipment operation data exceeds the preset early warning threshold.

[0007] Data acquisition module: Used to collect multi-dimensional production behavior data of each inspection personnel and preprocess it, extracting basic attribute data, behavior preference data, interaction operation data and production adaptation data of each inspection personnel to form a standardized dataset for production control.

[0008] Inspection personnel classification module: Based on a standardized dataset for production control, this module calculates the group matching coefficient of each inspection personnel against the production process control standards, and classifies inspection personnel into groups with different characteristics based on the distribution of the group matching coefficient interval.

[0009] Inspection Personnel Behavior Analysis Module: This module is used to analyze the behavioral characteristics of inspection personnel groups with different features based on a standardized dataset specifically designed for production control.

[0010] Fault Inspection Matching Module: Based on equipment fault information and the analysis results of the behavior of each inspection personnel, this module matches inspection personnel with the corresponding handling capabilities and pushes fault control instructions and backup equipment switching instructions.

[0011] Control and execution module: Based on the matching results, control instructions are issued to the corresponding inspection personnel to execute equipment failure handling and production process control.

[0012] The beneficial effects of this invention are as follows: This invention provides a data management and user behavior analysis system based on full-process production control. First, it collects real-time equipment operation data through sensors and compares it with preset warning thresholds to determine if the equipment's operating status is abnormal. If an abnormality is detected, a fault warning is automatically triggered. Then, it collects multi-dimensional production behavior data from inspection personnel and forms a standardized dataset. A group matching coefficient is calculated to segment personnel groups with different characteristics, and behavioral feature analysis is performed. Next, it combines equipment fault information to match inspection personnel with corresponding handling capabilities, pushes fault control and backup equipment switching instructions, and finally, based on the matching results, issues execution orders to the corresponding inspection personnel to complete fault handling and production process control. This invention improves fault response and handling efficiency, effectively reduces equipment downtime, ensures continuous and stable production process operation, and standardizes inspection work behavior. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the system structure connection of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] See Figure 1 As shown, a data management and user behavior analysis system based on full-process production control includes the following modules: Fault early warning module: used to collect equipment operation data in real time through sensors, compare the equipment operation data with preset early warning thresholds, determine whether the equipment operation status is abnormal, and automatically trigger fault early warning when the equipment operation data exceeds the preset early warning thresholds.

[0017] In one specific embodiment, the fault warning module performs the following process: real-time collection of equipment operating status data, comparison of the equipment operating data with a preset warning threshold, and determination of whether the equipment operating status is abnormal.

[0018] When the device status data is greater than or equal to the warning threshold, an early warning is immediately triggered, and the device fault information is integrated and pushed to the management terminal, and fault linkage analysis is started simultaneously.

[0019] When the device status data is less than the warning threshold, no warning is triggered, and only routine data collection and status monitoring are maintained.

[0020] It should be noted that the preset warning threshold is a critical value used to determine whether the device status data triggers a warning. It is set by professionals according to the judgment requirements, and no specific numerical limit is set here.

[0021] Data acquisition module: Used to collect multi-dimensional production behavior data of each inspection personnel and preprocess it, extracting basic attribute data, behavior preference data, interaction operation data and production adaptation data of each inspection personnel to form a standardized dataset for production control.

[0022] In a specific embodiment, the data acquisition module performs the following process: it collects multi-dimensional data of inspection personnel required for production through a multi-source data interface, performs preprocessing, and then performs standardization processing to form a standardized dataset for production control. The multi-dimensional data of inspection personnel includes basic attribute data, behavioral preference data, interactive operation data, and production adaptation data.

[0023] It should be noted that basic attribute data refers to the basic information data used by inspection personnel for identification, access control and work access throughout the entire production process, including operation permission level and equipment binding information.

[0024] Behavioral preference data: refers to the operational habits and behavioral characteristics formed by inspection personnel during production operations, including equipment usage frequency and production process execution preferences.

[0025] Interactive operation data: refers to the actual operation record data performed by inspection personnel on production equipment, including the number of compliant operations and the number of non-compliant operations.

[0026] Production Adaptation Data: This refers to data related to the degree of matching between the operations of inspection personnel and production processes, production tasks, or production resources, including the completion status of production tasks and the number of compliant production operations.

[0027] Inspection personnel classification module: Based on a standardized dataset for production control, this module calculates the group matching coefficient of each inspection personnel against the production process control standards, and classifies inspection personnel into groups with different characteristics based on the distribution of the group matching coefficient interval.

[0028] In a specific embodiment, the specific process of the inspection personnel classification module is as follows: extracting the operation specification data of the inspection personnel for the past 12 production cycles from the basic attribute data; extracting the equipment operation stability used by the inspection personnel from the behavioral preference data; extracting the actual load of the equipment used by the inspection personnel from the interactive operation data; and extracting the number of compliant production operations of the inspection personnel from the production adaptation data.

[0029] Based on the operational data of the inspection personnel for nearly 12 production cycles, the ratio of the number of on-time and compliant operations to the total number of operations is calculated to obtain the basic attribute matching score.

[0030] The behavioral preference matching score is obtained by normalizing the ratio of the equipment operation stability used by the inspection personnel to the industry standard stability benchmark.

[0031] The interactive operation matching score is obtained based on the ratio of the actual load of the equipment used by the inspection personnel to the rated standard load.

[0032] The production fit score is obtained by comparing the number of compliant production operations performed by inspection personnel with the total number of production operations.

[0033] Preset weights are configured for the four dimensions. Each matching score is multiplied by its corresponding weight and then summed to obtain the group matching coefficient. The group of inspection personnel for the entire production process is then divided based on the range of the group matching coefficient.

[0034] It should be noted that the group matching coefficient is a comprehensive quantitative indicator obtained by weighting and summing four dimensions of inspection personnel's basic attributes, behavioral preferences, interactive operations, and production adaptation through preset weights. It is used to represent the degree of matching between inspection personnel and the production process control standards.

[0035] Number of timely and compliant operations: The number of effective operations completed by inspection personnel in accordance with preset production specifications within the past 12 operating cycles.

[0036] Preset production standards are threshold values ​​used to determine whether the operations completed by inspection personnel are compliant. They are dynamically adjusted by professionals based on the production scenario, process type, and equipment characteristics.

[0037] Total number of operations: The total number of times that inspection personnel need to perform standard operations within the last 12 operation cycles.

[0038] Industry standard stable benchmark: Based on industry classification standards, the reference values ​​for the use and operation specifications of equipment in the industry are statistically derived.

[0039] Preset weights: such as basic attributes 30%, behavioral preferences 25%, interactive operations 25%, and production adaptation 20%, and the weights can be dynamically adjusted.

[0040] Inspection Personnel Behavior Analysis Module: This module is used to analyze the behavioral characteristics of inspection personnel groups with different features based on a standardized dataset specifically designed for production control.

[0041] In a specific embodiment, the specific process of the inspection personnel behavior analysis module is as follows: extract the behavioral characteristics corresponding to various inspection personnel groups from the production control-specific standardized dataset. The behavioral characteristics include basic attribute matching score, behavioral preference matching score, interactive operation matching score, and production adaptation matching score.

[0042] The feature values ​​corresponding to the four behavioral characteristics of each inspection personnel group are statistically analyzed. Abnormal discrete data are removed by cluster analysis, and the standard behavioral feature values ​​corresponding to each inspection personnel group are calculated. The standard behavioral feature values ​​are the average values ​​of the basic attribute matching score, behavioral preference matching score, interactive operation matching score and production adaptation matching score of the group.

[0043] Establish a one-to-one mapping relationship between the types of inspection personnel and the four standard behavioral characteristics.

[0044] For each individual inspector, four actual behavioral characteristic values ​​are extracted and compared with the four standard behavioral characteristic values ​​of the group to which they belong, and the behavioral deviation is calculated: Behavioral deviation = |Actual behavioral characteristic value − Group standard behavioral characteristic value|; The degree of behavioral compliance is calculated based on the behavioral deviation: Degree of behavioral compliance = 1 − Behavioral deviation ÷ Group standard behavioral characteristic value.

[0045] By combining behavioral deviations and the degree of behavioral achievement based on the four behavioral characteristics, an individual behavioral characteristic analysis result is generated and output.

[0046] It should be noted that the behavioral characteristics of inspection personnel refer to quantitative indicators used to represent the work patterns and operating habits of inspection personnel, including the standardization of inspection execution and inspection efficiency.

[0047] Inspection personnel group: refers to the group of inspection personnel with similar work habits, operational levels and behavioral patterns, obtained by group matching coefficient.

[0048] Abnormal discrete data: refers to isolated data that deviates significantly from the distribution pattern of group behavior characteristics during the grouping and classification process, caused by misoperation, abnormal data collection, or special scenarios, and deviates from the overall sample data distribution pattern. Such data will interfere with the accuracy of the coefficient and needs to be removed through cluster analysis.

[0049] The specific calculation process of cluster analysis can be found on the Internet, as it is existing technology and will not be elaborated here.

[0050] Behavioral deviation: refers to the absolute difference between the actual behavioral characteristics of an individual inspector and the standard behavioral characteristics of the group to which they belong, and is used to measure the degree of behavioral deviation.

[0051] Behavioral compliance level: refers to a quantitative indicator calculated based on behavioral deviations and group standard behavioral characteristic values, used to represent the degree to which the behavior of an individual inspector conforms to group standards.

[0052] Fault Inspection Matching Module: Based on equipment fault information and the analysis results of the behavior of each inspection personnel, this module matches inspection personnel with the corresponding handling capabilities and pushes fault control instructions and backup equipment switching instructions.

[0053] In a specific embodiment, the specific process of the fault inspection matching module is as follows: obtain equipment fault information, determine the fault type corresponding to the equipment fault data, and perform preliminary screening of candidates based on the fault type and the classification results of the inspection personnel group.

[0054] Among the screened candidates, based on the analysis results of individual behavioral characteristics, corresponding weights were assigned to skill suitability, work standardization, and historical handling efficiency. The overall matching degree of each inspector in the candidate group was calculated as follows: Overall matching degree = Skill suitability × 0.4 + Work standardization × 0.3 + Historical handling efficiency × 0.3.

[0055] Based on the overall matching degree from highest to lowest, the inspection personnel with the highest overall matching degree are selected as the inspection personnel with corresponding handling capabilities, and the fault control instructions and backup equipment switching instructions are pushed to the matched inspection personnel simultaneously.

[0056] It should be noted that skill fit refers to the degree to which the operational skills and professional capabilities of the inspection personnel match the requirements for handling current equipment malfunctions. Skill fit = number of successfully matched malfunction types ÷ total number of malfunction types that need to be handled.

[0057] Operational standardization level: refers to the level of compliance of inspection personnel in performing tasks in accordance with the preset production process and operating standards during production operations. Operational standardization level = number of compliant operations ÷ total number of operations.

[0058] Historical handling efficiency: refers to the speed and effectiveness of troubleshooting and equipment restoration completed by inspection personnel in historical fault handling tasks per unit time. Historical handling efficiency = number of effective handling completed ÷ total number of handling tasks.

[0059] Preferably, the specific process of determining the fault type and screening candidates based on group classification is as follows: the equipment fault data is compared with a preset fault type determination threshold. When the equipment fault data is less than or equal to the preset fault type determination threshold, it is determined to be a normal fault type; when the equipment fault data is greater than the preset fault type determination threshold, it is determined to be a professional fault type.

[0060] If it is a common fault type, the inspectors with the highest group matching coefficient are selected as candidates based on the inspection personnel group classification results, and idle personnel are selected in combination with work status information.

[0061] If the fault is a specialized type, the specific skill requirements corresponding to that type are extracted, and these requirements are matched with the professional skill information of the inspectors. Based on the classification results of the inspectors, inspectors whose group matching coefficient is within the preset qualified range and whose professional skills match the specialized skill requirements are selected to form a group of candidates for handling specialized faults. The current work status information of each inspector in the group of candidates for handling specialized faults is obtained in real time to determine whether the inspectors are in an idle and dispatchable state. Inspectors who are busy, performing tasks, or undispatchable are removed, and the target personnel are selected from the remaining idle and dispatchable inspectors.

[0062] It should be noted that equipment fault data refers to abnormal data obtained by collecting and analyzing the operating status of production equipment, including fault parameters and the time of fault occurrence.

[0063] The fault type determination threshold is a critical value used to determine the type of equipment fault. It is set by technicians according to the judgment requirements and is specifically divided into ordinary fault types and professional fault types.

[0064] Common fault types: These refer to simple equipment faults that can be handled with routine operations and do not require professional skills, such as routine resets and simple parameter adjustments.

[0065] Specialized fault types: These refer to complex equipment faults that require specific professional knowledge, skills, or tools to handle, such as core component failures and control logic anomalies.

[0066] The preset qualified range is a critical value used to determine whether the group behavior of inspection personnel meets the standard. It is a range of group matching coefficient values ​​preset by technical personnel that can participate in professional fault handling, and no specific numerical limit is imposed here.

[0067] Work status information: refers to information indicating the current work status of inspection personnel, including statuses such as idle and in the process of inspecting faults, which is used to determine whether the inspection personnel are in a dispatchable state.

[0068] Idle personnel: refers to inspection personnel who are not currently performing tasks, are not occupied, and can immediately handle faults.

[0069] Professional skills information: refers to relevant information used to indicate the professional competence of inspection personnel, such as their professional skills, the types of faults they are good at inspecting, the types of equipment they are responsible for, and their historical inspection experience.

[0070] Preferably, the specific process of pushing the backup device switching instruction is as follows: real-time acquisition of device fault parameters, comparison of device fault parameters with preset normal operating thresholds of the device, and statistics of fault duration.

[0071] Based on the comparison results, fault duration, and preset switching threshold, a comprehensive judgment is made as to whether the conditions for switching to backup equipment are met and the timing of the switching is determined.

[0072] If the equipment fault parameters exceed the preset normal operating threshold and the duration reaches the preset time limit, or reach the preset switching threshold, then the standby equipment switching conditions are met, and the switching time is the current moment. If the equipment fault parameters exceed the preset normal operating threshold but the duration does not reach the preset time limit and the preset switching threshold is not reached, the fault parameters and duration will be continuously monitored until the switching conditions are met and the switching timing is determined.

[0073] If the equipment fault parameters recover to the normal operating threshold range after fluctuations, it is determined that there is no need to perform standby equipment switching, and the switching judgment process is terminated.

[0074] Record the comparison results of equipment fault parameters, duration statistics and final judgment conclusions, and push the switching timing information along with the standby equipment switching command to the matching inspection personnel.

[0075] It should be noted that equipment fault parameters refer to quantitative parameters collected in real time to reflect the current abnormal operating state of the equipment, including key operating parameters such as current and voltage.

[0076] The normal operating threshold is a parameter range used to determine whether the equipment is in a normal working state. If it exceeds this range, it is determined that the equipment is operating abnormally. It is set by technicians according to the judgment requirements, and no specific numerical limit is set here.

[0077] Fault duration: The cumulative time from the moment the real-time fault parameters of the equipment first exceed the normal operating threshold to the current moment or the moment the fault is recovered.

[0078] The preset switching threshold is a critical condition used to determine whether to trigger the switching of standby equipment. It can be composed of fault level, fault impact range and production continuity requirements, etc. It is set by technicians according to the judgment requirements, and no specific numerical limit is set here.

[0079] Standby equipment switching conditions: The judgment conditions set by comprehensively comparing fault parameters, fault duration, fault level and switching threshold are used to determine whether to switch to standby equipment.

[0080] Switching timing: When the conditions for switching to standby equipment are met, determine the specific time to activate the standby equipment and deactivate the faulty equipment.

[0081] After fluctuations, the equipment returns to the normal operating threshold range: This refers to the unstable state in which the real-time fault parameters of the equipment briefly exceed the normal operating threshold and then fall back on their own. This change is caused by factors such as instantaneous interference, signal jitter, and environmental influences. It does not constitute a continuous fault and there is no need to switch to backup equipment.

[0082] Control and execution module: Based on the matching results, control instructions are issued to the corresponding inspection personnel to execute equipment failure handling and production process control.

[0083] In a specific embodiment, the specific process of the control execution module is as follows: based on the fault inspection matching results, a fault control instruction is issued to the corresponding inspection personnel; the inspection personnel perform equipment fault handling and backup equipment switching operations according to the fault control instruction; after the handling is completed, the equipment operating parameters and control execution data are collected again in real time to re-determine whether the equipment operating status has returned to normal.

[0084] Calculate the overall difference rate between the equipment fault parameters before and after fault handling and the preset normal operating threshold of the equipment. Overall difference rate = |current equipment fault parameters − normal operating threshold of the equipment| ÷ normal operating threshold of the equipment.

[0085] Next, calculate the overall difference rate deviation of the equipment fault parameters before and after fault handling. Overall difference rate deviation = |Overall difference rate after handling - Overall difference rate before handling| ÷ Overall difference rate before handling.

[0086] If the equipment's operating status is determined to be normal and the overall difference rate deviation value is ≤0.1, it indicates that the fault has been effectively resolved, and the current control is terminated. If it is still abnormal or the deviation value is >0.1, the control process continues and the control parameters are adjusted. The data collection, judgment, and control steps are repeated until the equipment's operating status returns to normal and the overall difference rate deviation value is ≤0.1.

[0087] It should be noted that fault control instructions are used to guide inspection personnel in performing control commands for troubleshooting equipment faults, adjusting parameters, and switching to standby equipment.

[0088] Equipment operating parameters: These refer to quantitative parameters collected in real time that reflect the current operating status of the equipment, including current and voltage.

[0089] Control execution data: refers to the operation records, execution time, and execution results generated by inspection personnel during the process of handling faults and switching to backup equipment.

[0090] The database is used to store production process data, control result feedback data, basic attribute data, behavioral preference data, interactive operation data, and production adaptation data. It is also used to store early warning thresholds, fault type determination thresholds, normal equipment operation thresholds, and switching thresholds.

[0091] The examples described in this invention are not limited to the specific embodiments listed above. The examples are merely illustrative to facilitate understanding of the invention and do not constitute a limitation on the scope of protection of this invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of this invention should be included within the scope of protection.

[0092] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. A data management and user behavior analysis system based on full-process production control, characterized in that, Includes the following modules: Fault warning module: Used to collect equipment operation data in real time through sensors, compare the equipment operation data with preset warning thresholds to determine whether the equipment operation status is abnormal, and automatically trigger fault warning when the equipment operation data exceeds the preset warning thresholds; Data acquisition module: used to collect multi-dimensional production behavior data of each inspection personnel and preprocess it, extracting basic attribute data, behavior preference data, interaction operation data and production adaptation data of each inspection personnel to form a standardized dataset for production control. Inspection personnel classification module: Based on a standardized dataset dedicated to production control, this module calculates the group matching coefficient of each inspection personnel against the production process control standards, and classifies inspection personnel into groups with different characteristics based on the distribution of the group matching coefficient interval. Inspection Personnel Behavior Analysis Module: Used to analyze the behavioral characteristics of inspection personnel groups with different features based on a standardized dataset specifically for production control. Fault Inspection Matching Module: Based on equipment fault information and the analysis results of the behavior of each inspection personnel, it matches inspection personnel with corresponding handling capabilities and pushes fault control instructions and backup equipment switching instructions. Control and execution module: Based on the matching results, control instructions are issued to the corresponding inspection personnel to execute equipment failure handling and production process control.

2. The data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The specific process of the fault early warning module is as follows: Real-time collection of equipment operating status data, comparison of equipment operating data with preset warning thresholds to determine whether the equipment operating status is abnormal; When the equipment status data is greater than or equal to the warning threshold, an early warning is immediately triggered, and the equipment fault information is integrated and pushed to the management terminal, and fault linkage analysis is started simultaneously. When the device status data is less than the warning threshold, no warning is triggered, and only routine data collection and status monitoring are maintained.

3. The data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The specific process of the data acquisition module is as follows: By collecting multi-dimensional data from inspection personnel required for production through multi-source data interfaces, preprocessing the data, and then standardizing it, a standardized dataset for production control is formed. The multi-dimensional data of inspection personnel includes basic attribute data, behavioral preference data, interactive operation data, and production adaptation data.

4. The data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The specific process of the inspection personnel classification module is as follows: Extract operational standard data for each inspector over nearly 12 production cycles from basic attribute data; extract the equipment operation stability used by each inspector from behavioral preference data; extract the actual equipment load used by each inspector from interactive operation data; and extract the number of compliant production operations performed by each inspector from production adaptation data. Based on the operational standard data of each inspection personnel for nearly 12 production cycles, the ratio of the number of on-time and compliant operations to the total number of operations is calculated to obtain the basic attribute matching score; Based on the ratio of the operational stability of the equipment used by each inspection personnel to the industry standard stability benchmark, a behavioral preference matching score is obtained after normalization. The interactive operation matching score is obtained based on the ratio of the actual load of the equipment used by each inspection personnel to the rated standard load. The production fit score is obtained by comparing the number of compliant production operations performed by each inspection personnel with the total number of production operations. Preset weights are configured for the four dimensions. Each matching score is multiplied by its corresponding weight and then summed to obtain the group matching coefficient. Based on the range of the group matching coefficient, the inspection personnel of each inspection team in the entire production process are classified.

5. The data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The specific process of the inspection personnel behavior analysis module is as follows: The behavioral features of various inspection personnel groups are extracted from the standardized dataset for production control. The behavioral features include basic attribute matching score, behavioral preference matching score, interactive operation matching score, and production adaptation matching score. The feature values ​​corresponding to the four behavioral characteristics of each inspection personnel group are statistically analyzed. Abnormal discrete data are removed by cluster analysis. The standard behavioral feature value corresponding to each inspection personnel group is calculated. The standard behavioral feature value is the average value of the basic attribute matching score, behavioral preference matching score, interactive operation matching score and production adaptation matching score of the group. Establish a one-to-one mapping relationship between the types of inspection personnel and the four standard behavioral characteristics; For each individual inspector, four actual behavioral characteristic values ​​are extracted and compared with the four standard behavioral characteristic values ​​of the group to which they belong, and the behavioral deviation is calculated: Behavioral deviation = |actual behavioral characteristic value − group standard behavioral characteristic value|; the degree of behavioral compliance is calculated based on the behavioral deviation: degree of behavioral compliance = 1 − behavioral deviation ÷ group standard behavioral characteristic value; By combining behavioral deviations and the degree of behavioral achievement based on the four behavioral characteristics, an individual behavioral characteristic analysis result is generated and output.

6. The data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The specific process of the fault inspection and matching module is as follows: Obtain equipment fault information, determine the fault type corresponding to the equipment fault data, and conduct preliminary screening of candidates based on the fault type and the classification results of the inspection personnel group. Among the screened candidates, based on the analysis results of individual behavioral characteristics, corresponding weights were assigned to skill suitability, work standardization, and historical handling efficiency. The overall matching degree of each inspector in the candidate group was calculated as follows: Overall matching degree = Skill suitability × 0.4 + Work standardization × 0.3 + Historical handling efficiency × 0.

3. Based on the overall matching degree from highest to lowest, the inspection personnel with the highest overall matching degree are selected as the inspection personnel with corresponding handling capabilities, and the fault control instructions and backup equipment switching instructions are pushed to the matched inspection personnel simultaneously.

7. A data management and user behavior analysis system based on full-process production control as described in claim 6, characterized in that, The specific process of determining the fault type and screening candidates based on group classification is as follows: The equipment fault data is compared with the preset fault type judgment threshold. When the equipment fault data is less than or equal to the preset fault type judgment threshold, it is judged as a normal fault type. When the equipment fault data exceeds the preset fault type judgment threshold, it is judged as a professional fault type; If it is a common fault type, the inspectors with the largest group matching coefficient are selected as candidates based on the inspection personnel group classification results, and idle personnel are selected in combination with the work status information. If it is a professional fault type, extract the specific skill requirements corresponding to that professional fault type and match the specific skill requirements with the professional skill information of the inspection personnel; Based on the classification results of the inspection personnel group, inspection personnel whose group matching coefficient is within the preset qualified range and whose professional skills match the special skill requirements are selected to form a professional fault handling candidate group; the current work status information of each inspection personnel in the professional fault handling candidate group is obtained in real time to determine whether the inspection personnel are in an idle and dispatchable state; inspection personnel who are busy, performing tasks, or undispatchable are eliminated, and target personnel are selected from the remaining idle and dispatchable inspection personnel.

8. The data management and user behavior analysis system based on full-process production control according to claim 7, characterized in that, The specific process of pushing the backup device switching command is as follows: The system acquires equipment fault parameters in real time, compares these parameters with preset normal operating thresholds, and calculates the duration of the fault. Based on the comparison results, fault duration, and preset switching threshold, a comprehensive judgment is made as to whether the conditions for switching to backup equipment are met and to determine the timing of the switchover. If the equipment fault parameters exceed the preset normal operating threshold and the duration reaches the preset time limit, or reach the preset switching threshold, then the standby equipment switching conditions are met, and the switching time is the current moment. If the equipment fault parameters exceed the preset normal operating threshold but the duration does not reach the preset time limit and the preset switching threshold is not reached, the fault parameters and duration will be continuously monitored until the switching conditions are met and the switching timing is determined. If the equipment fault parameters recover to the normal operating threshold range after fluctuations, it is determined that there is no need to perform standby equipment switching, and the switching judgment process is terminated. Record the comparison results of equipment fault parameters, duration statistics and final judgment conclusions, and push the switching timing information along with the standby equipment switching command to the matching inspection personnel.

9. A data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The specific process of the control execution module is as follows: Based on the fault inspection matching results, fault control instructions are issued to the corresponding inspection personnel. The inspection personnel perform equipment fault handling and backup equipment switching operations according to the fault control instructions. After the handling is completed, the equipment operating parameters and control execution data are collected again in real time to re-determine whether the equipment operating status has returned to normal. Calculate the overall difference rate between the equipment fault parameters before and after fault handling and the preset normal operating threshold of the equipment. Overall difference rate = |current equipment fault parameters − normal operating threshold of the equipment| ÷ normal operating threshold of the equipment. Next, calculate the overall difference rate deviation of the equipment fault parameters before and after fault handling. Overall difference rate deviation = |Overall difference rate after handling - Overall difference rate before handling| ÷ Overall difference rate before handling; If the equipment's operating status is determined to be normal and the overall difference rate deviation value is ≤0.1, it indicates that the fault has been effectively resolved, and the current control is terminated. If it is still abnormal or the deviation value is >0.1, the control process continues and the control parameters are adjusted. The data collection, judgment, and control steps are repeated until the equipment's operating status returns to normal and the overall difference rate deviation value is ≤0.

1.

10. A data management and user behavior analysis system based on full-process production control as described in claim 1, characterized in that, The database is used to store production process data, control result feedback data, basic attribute data, behavioral preference data, interactive operation data, and production adaptation data. It is also used to store early warning thresholds, fault type determination thresholds, normal equipment operation thresholds, and switching thresholds.

Images