Data analysis and risk management and control method for standardizing inspection and detection industry behaviors

Abstract

The invention belongs to the technical field of normative inspection and detection industry behaviors, particularly relates to a data analysis and risk management and control method for normative inspection and detection industry behaviors, and aims to solve the problems that no software for normative industry operation behaviors and risk prompts exists in the existing market, wide collection and multi-scenario application of data are inconvenient, and the risk is poor. According to the technical scheme, the method comprises the following steps that S1, a data analysis and risk management and control system is prepared, the data analysis and risk management and control system comprises an application scene module, the application scene module is connected with a data collection module, and the data collection module is connected with an analysis model module; according to the system, industry operation behaviors and risk prompts can be standardized, and wide collection and multi-scenario application of data are facilitated, so that industry behaviors and achievements can be effectively supervised.

Description

Technical Field

[0001] The present invention relates to the field of technical standards for the behavior of the inspection and testing industry, and in particular to a data analysis and risk control method for standardizing the behavior of the inspection and testing industry. Background Art

[0002] The inspection and testing industry involves testing organizations, commissioned by government regulatory agencies, manufacturers, or product users, using specialized technical means and equipment to inspect and test samples for quality, safety, performance, and environmental protection, in accordance with applicable standards and technical specifications. The organizations then issue inspection and testing reports to assess compliance with government, industry, and user standards and requirements for quality, safety, and performance. Inspection and testing requires high technical expertise, integrating multiple disciplines, including chemistry, physics, materials science, electronics, biology, and food science.

[0003] In the existing technology, there is currently no software on the market that regulates industry operating behaviors and risk warnings, which is not convenient for the extensive collection and multi-scenario application of data, resulting in the inability to effectively supervise industry behaviors and results. To this end, we propose a data analysis and risk control method for regulating the behavior of the inspection and testing industry to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to solve the shortcomings in the existing technology that there is no software on the market that regulates industry operating behaviors and risk warnings, which makes it inconvenient to collect data extensively and apply it in multiple scenarios, resulting in the inability to effectively supervise industry behaviors and results. A data analysis and risk control method for regulating the behavior of the inspection and testing industry is proposed.

[0005] The data analysis and risk control method provided in this application for standardizing the behavior of the inspection and testing industry adopts the following technical solutions:

[0006] The data analysis and risk management method used to standardize the behavior of the inspection and testing industry includes the following steps:

[0007] S1: Prepare a data analysis and risk management system, which includes an application scenario module, the application scenario module is connected to a data collection module, the data collection module is connected to an analysis model module, the analysis model module is connected to a learning optimization module, and the application scenario module includes a personnel structure unit and a task allocation unit;

[0008] S2: Use the application scenario module to create application scenarios in which the company assigns tasks, frontline employees complete tasks, quality control personnel monitor risks, and managers make decisions;

[0009] S3: The data collection module collects real-time parameters of staff structure, equipment performance, auxiliary material types, national standards, working environment, working time and working space;

[0010] S4: Then the analysis model module is based on standard specifications and operating procedures, and uses a computational model combining logic, support vector, decision tree, and random forest to derive a standardized and rationalized working model;

[0011] S5: Through the learning optimization module, data is continuously collected and updated, and the computing model is continuously optimized and trained to provide more efficient suggestions for task allocation, personnel structure, and on-site operations.

[0012] Furthermore, the data collection module includes a summary unit, a first recording unit, a second recording unit and a third recording unit, the summary unit is connected to the first recording unit, the first recording unit is connected to the second recording unit, and the second recording unit is connected to the third recording unit.

[0013] Furthermore, the third recording unit is connected to a collecting unit, the collecting unit is connected to a fourth recording unit, the fourth recording unit is connected to a fifth recording unit, and the fifth recording unit is connected to a sixth recording unit.

[0014] Furthermore, the analysis model module includes a comparison unit, a first inspection unit, a second inspection unit and a first analysis unit, the comparison unit is connected to the first inspection unit, the first inspection unit is connected to the second inspection unit, and the second inspection unit is connected to the first analysis unit.

[0015] Furthermore, the first analyzing unit is connected to a display unit, the display unit is connected to a second analyzing unit, the second analyzing unit is connected to a third analyzing unit, and the third analyzing unit is connected to a supplementing unit.

[0016] Furthermore, the learning optimization module includes a task allocation optimization unit, a personnel collocation optimization unit and a real-time monitoring unit, the task allocation optimization unit is connected to the personnel collocation optimization unit, and the personnel collocation optimization unit is connected to the real-time monitoring unit.

[0017] Furthermore, the real-time monitoring unit is connected to a real-time feedback unit, the real-time feedback unit is connected to an automatic update unit, and the automatic update unit is connected to an abnormality collection unit.

[0018] Furthermore, the summary unit is used to summarize the workload based on the enterprise, the first recording unit is used to record the responsible personnel corresponding to each enterprise, the second recording unit is used to record the sampling equipment used by each enterprise, the third recording unit is used to record the auxiliary materials used by each enterprise; the collection unit is used to collect policies, regulations, national standards, local standards, industry standards, and guidelines required for the work; the fourth recording unit is used to record the pollution sources and emission outlets of each enterprise; the fifth recording unit is used to record the time of key events of each team; and the sixth recording unit is used to record the location of key events of each team.

[0019] Furthermore, the comparison unit is used to compare the daily turnover with the average daily cost of the enterprise, the first inspection unit is used to check whether there is duplication between the personnel of each team, the second inspection unit is used to check whether there is duplication between the equipment of each team, the first analysis unit is used to analyze the consistency of the workload and the number of auxiliary material types, the display unit is used to display the standardized process steps of each task, the second analysis unit is used to analyze the consistency of the working environment, the third analysis unit is used to analyze the consistency of the working hours, and the supplement unit is used to enrich the relationship between working hours and work locations.

[0020] Furthermore, the task allocation optimization unit is used to optimize task allocation by combining workload, distance between enterprises and price; the personnel matching optimization unit is used to optimize personnel matching by combining task allocation; the real-time monitoring unit is used to monitor the equipment operation time, performance status, and update iterations in real time; the real-time feedback unit is used to provide real-time feedback on auxiliary material usage and storage conditions; the automatic update unit is used for automatic network update and update optimization judgment conditions; the exception collection unit is used to collect abnormal emergencies and improve the logic of the suggestion collection.

[0021] In summary, this application includes at least one of the following beneficial technical effects:

[0022] 1. This solution enables on-site understanding of work status and results, providing standard guidance and data reference for frontline sampling and testing personnel;

[0023] 2. This solution can monitor operational benefits and risks in real time, providing accurate information and correct direction for company management and decision-makers;

[0024] 3. This plan can effectively supervise industry behavior and results, and provide management basis and decision-making direction for ecological environment and market supervision departments;

[0025] 4. It can consolidate and improve the level of industry development, making the industry more high-quality, dynamic and healthy in the long run.

[0026] The present invention can standardize industry operating behaviors and risk warnings, facilitate the extensive collection and multi-scenario application of data, and thus effectively supervise industry behaviors and results. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a structural diagram of the data analysis and risk management system in the data analysis and risk management method for standardizing the behavior of the inspection and testing industry proposed in the present invention;

[0028] Figure 2 This is a structural block diagram of the application scenario module in the data analysis and risk control method for standardizing the behavior of the inspection and testing industry proposed in the present invention;

[0029] Figure 3 This is a structural block diagram of the data collection module in the data analysis and risk control method for standardizing the behavior of the inspection and testing industry proposed in the present invention;

[0030] Figure 4 This is a structural block diagram of the analysis model module in the data analysis and risk control method for standardizing the behavior of the inspection and testing industry proposed in the present invention;

[0031] Figure 5 This is a structural diagram of the learning optimization module in the data analysis and risk management method for standardizing the behavior of the inspection and testing industry proposed in the present invention;

[0032] Figure 6 This is a workflow diagram of the data analysis and risk management method proposed in this invention for standardizing the behavior of the inspection and testing industry. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0034] Example 1

[0035] Reference Figures 1-6 , a data analysis and risk management method for standardizing the behavior of the inspection and testing industry, including the following steps:

[0036] S1: Prepare a data analysis and risk management system. The data analysis and risk management system includes an application scenario module, which is connected to a data collection module, which is connected to an analysis model module, which is connected to a learning optimization module. The application scenario module includes a personnel structure unit and a task allocation unit.

[0037] S2: Use the application scenario module to create application scenarios in which the company assigns tasks, frontline employees complete tasks, quality control personnel monitor risks, and managers make decisions;

[0038] S3: The data collection module collects real-time parameters of staff structure, equipment performance, auxiliary material types, national standards, working environment, working time and working space;

[0039] S4: Then the analysis model module is based on standard specifications and operating procedures, and uses a computational model combining logic, support vector, decision tree, and random forest to derive a standardized and rationalized working model;

[0040] 1. Logical Algorithm

[0041] A logical algorithm describes a problem-solving approach through a series of logical commands and control structures. It typically consists of three phases: input, processing, and output. In the input phase, the algorithm receives external data, such as user input or file reading. In the processing phase, the algorithm performs calculations and operations on the input data to solve the problem. In the output phase, the algorithm returns the results to the user or writes them to a file, for example.

[0042] 2. Support Vector

[0043] Support vectors are one of the key concepts in the Support Vector Machine (SVM) algorithm. A support vector machine is a supervised learning algorithm used for classification and regression analysis. In an SVM, a support vector is the sample point in the training data that is closest to the decision boundary (or hyperplane). This hyperplane separates data from different categories, keeping data points of the same category on the same side of the hyperplane. The goal of a support vector machine is to find an optimal hyperplane that maximizes the distance from the support vector to the hyperplane.

[0044] 3. Decision Tree

[0045] Decision tree analysis is a risk-based decision-making method that uses probability and graph theory to compare different decision options to determine the optimal solution. A graph theory tree is a connected, loop-free directed graph. Nodes with an in-degree of 0 are called roots, and points with an out-degree of 0 are called leaves. Points outside the leaves are called interior nodes. A decision tree consists of a root (decision node), interior nodes (option nodes, status nodes), leaves (end points), branches (option branches, probability branches), probability values, and profit and loss values.

[0046] 4. Random Forest

[0047] Random Forest is an extension of Bagging (a parallel ensemble learning method). Its base learner is fixed as a decision tree, and multiple trees form a forest. The "randomness" lies in the random selection of partition attributes. When training the base learner, Random Forest also uses replacement sampling to add sample perturbations. At the same time, it also introduces an attribute perturbation. That is, in the training process of the base decision tree, when selecting the partition attribute, Random Forest first randomly selects a subset containing K attributes from the candidate attribute set, and then selects the optimal partition attribute from this subset. It is generally recommended that K = log2(d).

[0048] S5: Through the learning optimization module, data is continuously collected and updated, and the computing model is continuously optimized and trained to provide more efficient suggestions for task allocation, personnel structure, and on-site operations.

[0049] Reference Figure 3 The data collection module includes a summary unit, a first recording unit, a second recording unit and a third recording unit. The summary unit is connected to the first recording unit, the first recording unit is connected to the second recording unit, the second recording unit is connected to the third recording unit, the third recording unit is connected to the collection unit, the collection unit is connected to the fourth recording unit, the fourth recording unit is connected to the fifth recording unit, and the fifth recording unit is connected to the sixth recording unit. The summary unit is used to summarize the workload based on the enterprise. The first recording unit is used to record the responsible personnel corresponding to each enterprise, the second recording unit is used to record the sampling equipment used by each enterprise, and the third recording unit is used to record the auxiliary materials used by each enterprise. The collection unit is used to collect the policies, regulations, national standards, local standards, industry standards, and guidelines required for the work. The fourth recording unit is used to record the pollution sources and emission outlets of each enterprise. The fifth recording unit is used to record the time of key events of each team and the sixth recording unit is used to record the location of key events of each team.

[0050] Reference Figure 4The analysis model module includes a comparison unit, a first inspection unit, a second inspection unit and a first analysis unit. The comparison unit is connected to the first inspection unit, the first inspection unit is connected to the second inspection unit, the second inspection unit is connected to the first analysis unit, the first analysis unit is connected to a display unit, the display unit is connected to the second analysis unit, the second analysis unit is connected to a third analysis unit, and the third analysis unit is connected to a supplement unit. The comparison unit is used to compare the daily turnover with the average daily cost of the enterprise. The first inspection unit is used to check whether there is duplication between the personnel of each team, the second inspection unit is used to check whether there is duplication between the equipment of each team, the first analysis unit is used to analyze the consistency of the workload and the number of auxiliary material types, the display unit is used to display the standardized process steps of each work, the second analysis unit is used to analyze the consistency of the working environment, the third analysis unit is used to analyze the consistency of the working hours, and the supplement unit is used to enrich the relationship between working hours and work locations.

[0051] Reference Figure 5 The learning optimization module includes a task allocation optimization unit, a personnel matching optimization unit and a real-time monitoring unit. The task allocation optimization unit is connected to the personnel matching optimization unit, the personnel matching optimization unit is connected to the real-time monitoring unit, the real-time monitoring unit is connected to the real-time feedback unit, the real-time feedback unit is connected to the automatic update unit, and the automatic update unit is connected to the exception collection unit. The task allocation optimization unit is used to optimize task allocation by combining workload, inter-enterprise distance and price. The personnel matching optimization unit is used to optimize personnel matching by combining task allocation. The real-time monitoring unit is used to monitor the equipment running time, performance status, and update iterations in real time. The real-time feedback unit is used to provide real-time feedback on the auxiliary material usage and storage conditions. The automatic update unit is used for automatic updating via the Internet and updating the optimization judgment conditions. The exception collection unit is used to collect abnormal emergencies and improve the logic of the suggestion collection.

[0052] Case:

[0053] Work assignment: Guangdong Huaqing Testing Technology Co., Ltd., 5 VOC discharge outlets, covering an area of ​​250m×20m=5000m2.

[0054] On-site situation: The pollution source is on the 1st floor, the discharge outlet is on the 5th floor of the same factory building, there is no elevator but there is a platform, the weather is sunny, and the temperature is 30℃.

[0055] Work team: 3 people, 2 testing equipment, 1 calibration equipment.

[0056] 1. On-site arrival (contacting customers, surveying the site (distribution of pollution sources, testing locations)) 34.26 minutes

[0057] (1) Contact customers

[0058] ① Case 1: Normal, 10 minutes;

[0059] ②Case 2: Abnormal, manually enter the waiting time.

[0060] (2) On-site survey (distribution of pollution sources, detection locations)

[0061] ① Case 1: No confirmation required, 0 minutes;

[0062] ② Case 2: No on-site rectification is required after personal confirmation, pollution source on the 1st floor and emission location on the 5th floor, 24.26 minutes;

[0063] ③ Case 3: On-site rectification is required after personal confirmation. The pollution source is on the 1st floor and the emission location is on the 5th floor. The time required is 24.26 minutes plus the time required to manually enter the on-site rectification (platform construction, sampling port reset, working condition adjustment, etc.).

[0064] ④Case 4: After personal confirmation, if on-site rectification is not possible, another working time will be arranged.

[0065] On-site survey statistics

[0066]

[0067]

[0068]

[0069] 2. Before sampling (instrument calibration, instrument handling) 32.59 minutes

[0070] (1) Instrument calibration

[0071] ① Case 1: No on-site calibration required, 0 minutes;

[0072] ② Case 2: On-site calibration, 2 devices passed verification, 5.0 minutes;

[0073] ③Case 3: On-site calibration, 1 device failed verification, 1 device passed verification, 8.0 minutes; ④Case 4: On-site calibration, 2 devices failed verification, 9.0 minutes.

[0074] Statistics table of instrument calibration before sampling (2 people, 1 calibration device)

[0075]

[0076] (2) Arrival location (carrying equipment)

[0077] ① Case 1: The handling equipment arrives at the discharge port in 24.59 minutes.

[0078] Statistics of weight-bearing stair climbing

[0079]

[0080] 3. Sampling (instrument assembly, sampling) 233 minutes

[0081] ① Case 1: Normal, 233 minutes;

[0082] ②Case 2: Abnormal, manually enter the time to handle the sudden abnormal situation.

[0083] Sampling statistics table (3 people, 2 testing equipment)

[0084]

[0085]

[0086]

[0087] 4. After sampling (return to the original place, instrument calibration) 29.59 minutes

[0088] (1) Return to the origin (packing up the instrument, moving the instrument)

[0089] ① Case 1: The transport equipment arrives at the initial position, 24.59 minutes.

[0090] Statistics of weight-bearing descents

[0091]

[0092]

[0093] (2) Instrument calibration

[0094] ① Case 1: No on-site calibration required, 0 minutes;

[0095] ② Case 2: On-site calibration, 2 devices passed verification, 5.0 minutes;

[0096] ③Case 3: On-site calibration, one device fails verification, one device passes verification, and the time for handling sudden abnormal conditions is manually entered;

[0097] ④Case 4: On-site calibration, 2 devices failed verification, and the time for handling sudden abnormal conditions was manually entered.

[0098] Statistics of instrument calibration after sampling (2 people, 1 calibration device)

[0099]

[0100] 5. Leave the site (work confirmation (sample verification, workload confirmation, data collection), system confirmation, next task) 10 minutes

[0101] (1) Work confirmation (sample verification, workload confirmation, data collection)

[0102] ① Case 1: Normal, 10 minutes;

[0103] ②Case 2: Abnormal, manually enter the waiting time.

[0104] (2) System confirmation

[0105] ① Situation 1: The working hours are reasonable and the next task is assigned;

[0106] ② Situation 2: The working hours are unreasonable. After on-site verification and confirmation by the enterprise risk manager, the next task will be assigned;

[0107] ③ Situation 3: The working hours are unreasonable and require rectification after on-site verification. After the rectification is confirmed as feasible by the enterprise risk manager, the team must make on-site rectifications and re-report to the enterprise risk manager. After the manager confirms that everything is correct, the next task will be assigned. At the same time, the manager must immediately note the on-site situation in the task.

[0108] ④ Situation 4: The working hours are unreasonable and are verified to be correct on site, but are rejected and corrective suggestions are made when reported to the enterprise risk manager for confirmation. The team must make on-site corrections and report back to the enterprise risk manager. After the manager confirms that it is feasible, the next task will be assigned; at the same time, the manager must immediately note the on-site situation in the task.

[0109] (3) Next task

[0110] ①The system captures the real-time location and time of departure, etc.;

[0111] ②The system captures the navigation information for the next task;

[0112] ③ Repeat the above calculation and analysis process for the next task.

[0113] 6. Work Summary

[0114] (1) Theoretical working time of system calculation: 34.26+32.59+233+29.59+10=339.44 minutes

[0115] (2) Actual working time captured by the system (contacting the customer - work confirmation): X minutes

[0116] (3) Systematically analyze whether the actual working hours are reasonable

[0117] ①Compare the duration of this work (excluding the time for handling unexpected exceptions) with the theoretical duration;

[0118] ②(-∞,-20%) is unreasonable, [-20%, 20%] is reasonable, (20%, ∞) is unreasonable;

[0119] ③ For "unreasonable" situations, after the "Departure-Work Confirmation" is completed, the system will immediately notify the team leader on site and will not assign the next task for the time being. At the same time, a copy of the information will be sent to the enterprise risk manager. Only after the manager confirms that everything is correct can the next task be assigned and the team leave the site.

[0120] ④The above data will be included in the performance appraisal.

[0121] (4) Sudden abnormal situations and handling time:

[0122] ① Case 1: Waiting for customers, a minutes;

[0123] ② Case 2: On-site rectification of the inspection port and finding a temporary platform, b minutes;

[0124] ③ Case 3: During the second sampling process of discharge port 1, the flow rate is unstable and the sample is resampled for c minutes;

[0125] ④Case 4: Collect information and wait for customers, d minutes.

[0126] (5) Average efficiency of the system analysis team in handling sudden abnormal situations

[0127] ①Comparison of this processing time with the average processing time of each team in history;

[0128] ②(-∞,-10%) low efficiency, [-10%, 10%] normal, (10%, ∞) high efficiency;

[0129] ③The above data will be included in the performance appraisal content;

[0130] (6) The key factors affecting on-site working time are as follows:

[0131] ①Internal-Team Structure;

[0132] ② Internal - logistics support (technical support, equipment status);

[0133] ③ External-Enterprise (elevator status, platform type, enterprise cooperation);

[0134] ④External-weather temperature;

[0135] ⑤….

[0136] (7) Assist in management

[0137] ①Task arrangement - scientific optimization of team building, task distribution, and itinerary arrangement;

[0138] ② Equipment management - automatic supervision of equipment status, operating hours, and upgrades;

[0139] ③ Learning and Growth - real-time updates of policies, regulations, national standards, local standards, industry standards, and guidelines, and update of theoretical time ④ Sudden Abnormalities - summarize the ability to handle abnormal and sudden situations, and provide a collection of suggestions.

[0140] The implementation principle of this embodiment is as follows: when in use, an application scenario module is used to create an application scenario in which the company assigns tasks, front-line employees complete tasks, quality control personnel supervise risks, and managers make decisions; the data collection module collects real-time parameters of staff structure, equipment performance, auxiliary material types, national standards, working environment, working time, and working space; the summary unit can summarize the workload by enterprise; the first recording unit can record the responsible personnel corresponding to each enterprise; the second recording unit can record the sampling equipment used by each enterprise; the third recording unit can record the auxiliary materials used by each enterprise; the collection unit can collect policies, regulations, national standards, local standards, industry standards, and guidelines required for the work; the fourth recording unit can record the pollution sources and emission outlets of each enterprise; the fifth recording unit can record the time of key events of each team; and the sixth recording unit can record the location of key events of each team; then the analysis model module uses a calculation model combining logic, support vector, decision tree, and random forest based on standard specifications and working processes to derive a standardized and rationalized working mode; the comparison unit can compare the single-day turnover with the average daily cost of the enterprise, which can provide feedback to enterprise managers to understand and predict the operating status of the enterprise and provide effective data for decision-making; the first inspection unit can inspect the personnel of each team The second inspection unit can check whether there is duplication between the equipment of each team. The first analysis unit can analyze the consistency of the workload and the number of auxiliary material types. The display unit can display the standardized process steps of each task. The second analysis unit can analyze the consistency of the working environment. The third analysis unit can analyze the consistency of the working hours. The supplementary unit can enrich the relationship between working hours and working locations. It can provide feedback to the team leader and risk manager. If any point exceeds or does not meet the judgment result, the person concerned's operation interface will immediately issue an alarm and suspend the dispatch of the next task. At the same time, the information will be copied to the risk manager interface: the next task can only be carried out after the alarm is lifted. step-by-step work; through the learning optimization module, data is continuously collected and updated, and the calculation model is continuously optimized and trained to provide more efficient suggestions for task allocation, personnel structure, and on-site operations. The task allocation optimization unit can combine workload, distance between enterprises and price to optimize task allocation. The personnel matching optimization unit can combine task allocation to optimize personnel matching. The real-time monitoring unit can monitor the equipment's operating time, performance status, and update iterations in real time. The real-time feedback unit can provide real-time feedback on the amount of auxiliary materials and storage conditions. The automatic update unit can automatically update online and update the optimization judgment conditions. The abnormal collection unit can collect abnormal emergencies and improve the logic of the suggestion collection.

[0141] Example 2

[0142] The difference between this embodiment and embodiment 1 is that the data collection module is connected to a data backup module, which is connected to a data recovery module. The data backup module can back up the collected data to avoid data loss, and the data recovery module can restore data deleted after the backup.

[0143] The above are only preferred specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A data analysis and risk management method for standardizing the behavior of the inspection and testing industry, characterized by: The following steps are involved: S1: Prepare a data analysis and risk management system, which includes an application scenario module, the application scenario module is connected to a data collection module, the data collection module is connected to an analysis model module, the analysis model module is connected to a learning optimization module, and the application scenario module includes a personnel structure unit and a task allocation unit; S2: Use the application scenario module to create application scenarios in which the company assigns tasks, frontline employees complete tasks, quality control personnel monitor risks, and managers make decisions; S3: The data collection module collects real-time parameters of staff structure, equipment performance, auxiliary material types, national standards, working environment, working time and working space; S4: Then the analysis model module is based on standard specifications and operating procedures, and uses a computational model combining logic, support vector, decision tree, and random forest to derive a standardized and rationalized working model; S5: Through the learning optimization module, data is continuously collected and updated, and the computing model is continuously optimized and trained to provide more efficient suggestions for task allocation, personnel structure, and on-site operations.

2. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 1 is characterized by: The data collection module includes a summary unit, a first recording unit, a second recording unit and a third recording unit. The summary unit is connected to the first recording unit, the first recording unit is connected to the second recording unit, and the second recording unit is connected to the third recording unit.

3. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 2 is characterized by: The third recording unit is connected to a collecting unit, the collecting unit is connected to a fourth recording unit, the fourth recording unit is connected to a fifth recording unit, and the fifth recording unit is connected to a sixth recording unit.

4. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 3 is characterized by: The analysis model module includes a comparison unit, a first inspection unit, a second inspection unit and a first analysis unit, the comparison unit is connected to the first inspection unit, the first inspection unit is connected to the second inspection unit, and the second inspection unit is connected to the first analysis unit.

5. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 4 is characterized by: The first analyzing unit is connected to a display unit, the display unit is connected to a second analyzing unit, the second analyzing unit is connected to a third analyzing unit, and the third analyzing unit is connected to a supplementing unit.

6. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 5 is characterized by: The learning optimization module includes a task allocation optimization unit, a personnel collocation optimization unit and a real-time monitoring unit. The task allocation optimization unit is connected to the personnel collocation optimization unit, and the personnel collocation optimization unit is connected to the real-time monitoring unit.

7. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 6 is characterized by: The real-time monitoring unit is connected to a real-time feedback unit, the real-time feedback unit is connected to an automatic updating unit, and the automatic updating unit is connected to an abnormality collecting unit.

8. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 7 is characterized by: The summary unit is used to summarize the workload based on the enterprise. The first recording unit is used to record the responsible personnel corresponding to each enterprise. The second recording unit is used to record the sampling equipment used by each enterprise. The third recording unit is used to record the auxiliary materials used by each enterprise. The collection unit is used to collect policies, regulations, national standards, local standards, industry standards, and guidelines required for the work. The fourth recording unit is used to record the pollution sources and emission outlets of each enterprise. The fifth recording unit is used to record the time of key events of each team. The sixth recording unit is used to record the location of key events of each team.

9. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 8 is characterized by: The comparison unit is used to compare the daily turnover with the average daily cost of the enterprise, the first inspection unit is used to check whether there is duplication between the personnel of each team, the second inspection unit is used to check whether there is duplication between the equipment of each team, the first analysis unit is used to analyze the consistency of the workload and the number of auxiliary material types, the display unit is used to display the standardized process steps of each task, the second analysis unit is used to analyze the consistency of the working environment, the third analysis unit is used to analyze the consistency of the working hours, and the supplement unit is used to enrich the relationship between working hours and work locations.

10. The data analysis and risk management method for standardizing the behavior of the inspection and testing industry according to claim 9 is characterized by: The task allocation optimization unit is used to optimize task allocation by combining workload, distance between enterprises and price. The personnel matching optimization unit is used to optimize personnel matching by combining task allocation. The real-time monitoring unit is used to monitor the equipment operation time, performance status and update iteration in real time. The real-time feedback unit is used to provide real-time feedback on auxiliary material usage and storage conditions. The automatic update unit is used for automatic update via the Internet and update optimization judgment conditions. The exception collection unit is used to collect abnormal and sudden situations and improve the logic of the suggestion collection.

Images