Monitoring data checking method and device, computer equipment and storage medium

Abstract

The invention relates to a monitoring data checking method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of performing validity judgment on monitoring data based on measurement parameters and quality control parameters of monitoring equipment corresponding to the monitoring data to obtain a validity judgment result; detecting the monitoring equipment based on the monitoring log and the inspection record of the monitoring equipment to obtain a detection result of the monitoring equipment; based on historical monitoring data of a target monitoring point corresponding to the monitoring data, historical upstream monitoring data of an upstream monitoring point corresponding to the target monitoring point, historical downstream monitoring data of a downstream monitoring point corresponding to the target monitoring point, and meteorological parameters and other monitoring data of the target monitoring point, performing rationality judgment on the monitoring data; obtaining a rationality judgment result; and based on the validity judgment result, the detection result and the rationality judgment result, obtaining an inspection result of the monitoring data. By adopting the method, the accuracy of monitoring data inspection can be improved.

Description

Technical Field

[0001] The present application relates to the field of automation technology, and in particular to a monitoring data inspection method, device, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of automation technology, water quality monitoring data can be automatically obtained through water quality environment monitoring equipment, and then the quality and pollution of water can be determined based on the water quality monitoring data.

[0003] In traditional technology, before determining the quality and pollution of water based on water quality monitoring data, auditors compare the water quality monitoring data with national standard data, and determine whether the water quality monitoring data is abnormal based on the size relationship between the water quality monitoring data and the national standard data, resulting in low accuracy of water quality monitoring data anomaly inspection. Summary of the invention

[0004] Based on this, it is necessary to provide a monitoring data inspection method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of monitoring data inspection in response to the above technical problems.

[0005] In a first aspect, the present application provides a monitoring data checking method. The method comprises:

[0006] Based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, the effectiveness of the monitoring data is judged to obtain a validity judgment result;

[0007] Based on the monitoring log and inspection record of the monitoring device, the monitoring device is tested to obtain the test result of the monitoring device;

[0008] Based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, the rationality of the monitoring data is judged to obtain a rationality judgment result; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point excluding the monitoring data;

[0009] Based on the validity judgment result, the detection result and the rationality judgment result, the inspection result of the monitoring data is obtained.

[0010] In one embodiment, the validity judgment of the monitoring data is performed based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data to obtain the validity judgment result, including:

[0011] Determining computational reference data corresponding to the monitoring data based on measurement parameters of the monitoring device;

[0012] Based on the magnitude relationship between the monitoring data and the calculation reference data, a measurement validity result is obtained;

[0013] Based on the magnitude relationship between the quality control parameter and the quality control threshold, a quality control effectiveness result is obtained;

[0014] Based on the measurement validity result and the quality control validity result, a validity judgment result is obtained.

[0015] In one embodiment, the detecting of the monitoring device based on the monitoring log and the inspection record of the monitoring device to obtain the detection result of the monitoring device includes:

[0016] Determining a device abnormality level of the monitoring device based on the device status parameters in the monitoring log;

[0017] Determine an inspection feature vector corresponding to the inspection record;

[0018] For each decision tree, determining an abnormality prediction result corresponding to the inspection feature vector based on the decision tree;

[0019] Determining a device prediction result of the monitoring device based on the plurality of abnormal prediction results;

[0020] Based on the device abnormality level and the device prediction result, a detection result of the monitoring device is obtained.

[0021] In one embodiment, the rationality judgment of the monitoring data is performed based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point to obtain a rationality judgment result, including:

[0022] Based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, the rationality of the monitoring data is judged to obtain a first judgment result;

[0023] Based on the meteorological parameters and other monitoring data of the target monitoring point, a rationality judgment is performed on the monitoring data to obtain a second judgment result;

[0024] Based on the first judgment result and the second judgment result, a rationality judgment result is obtained.

[0025] In one embodiment, the rationality judgment of the monitoring data is performed based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point to obtain a first judgment result, including:

[0026] Determine a first mean and a first standard deviation corresponding to the first difference vector based on a first difference vector between an upstream vector corresponding to the historical upstream monitoring data of the upstream monitoring point and a target vector corresponding to the historical monitoring data of the target monitoring point;

[0027] Determine a second mean and a second standard deviation corresponding to the second difference vector based on a second difference vector between a downstream vector corresponding to the historical downstream monitoring data of the downstream monitoring point and the target vector;

[0028] Determine an upstream difference between the upstream monitoring data corresponding to the upstream monitoring point and the monitoring data; the upstream monitoring data and the monitoring data are measured at the same time;

[0029] Determine a downstream difference between the downstream monitoring data corresponding to the downstream monitoring point and the monitoring data; the downstream monitoring data and the monitoring data are measured at the same time;

[0030] A first judgment result is obtained based on the upstream difference, the downstream difference, the first mean, the first standard deviation, the second mean and the second standard deviation.

[0031] In one embodiment, the rationality judgment of the monitoring data based on the meteorological parameters and other monitoring data of the target monitoring point to obtain the second judgment result includes:

[0032] Inputting the meteorological parameters and other monitoring data of the target monitoring point into a first model to obtain a plurality of first prediction confidences and a first confidence interval corresponding to each of the first prediction confidences; the first model is a linear neural network model;

[0033] Determine the first prediction confidence corresponding to the first confidence interval in which the monitoring data is located as the first confidence of the monitoring data;

[0034] Inputting the meteorological parameters and other monitoring data of the target monitoring point into a second model to obtain a plurality of second prediction confidences and a second confidence interval corresponding to each second prediction confidence; the second model is a nonlinear neural network model;

[0035] Determine the second prediction confidence corresponding to the second confidence interval in which the monitoring data is located as the second confidence of the monitoring data;

[0036] Based on the first confidence level and the second confidence level, a second judgment result is obtained.

[0037] In a second aspect, the present application also provides a monitoring data checking device. The device comprises:

[0038] The validity judgment module is used to judge the validity of the monitoring data based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, and obtain the validity judgment result;

[0039] An equipment detection module, used to detect the monitoring equipment based on the monitoring log and inspection record of the monitoring equipment, and obtain the detection result of the monitoring equipment;

[0040] A rationality judgment module is used to judge the rationality of the monitoring data based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point to obtain a rationality judgment result; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point excluding the monitoring data;

[0041] An anomaly detection module is used to obtain the inspection result of the monitoring data based on the effectiveness judgment result, the detection result and the rationality judgment result.

[0042] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0044] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0045] The above-mentioned monitoring data inspection method, device, computer equipment, storage medium and computer program product judge the validity of the monitoring data through the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, and obtain the validity judgment result of the monitoring data; detect the monitoring equipment through the monitoring log and inspection record of the monitoring equipment, and obtain the detection result of the monitoring equipment; judge the rationality of the monitoring data through the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, and obtain the rationality judgment result of the monitoring data, that is, the validity judgment result of the comprehensive monitoring data, whether the monitoring equipment measuring the monitoring data is abnormal and the rationality judgment result of the monitoring data, judge whether the monitoring data is abnormal, and improve the accuracy of monitoring data inspection compared with only comparing the monitoring data with national standard data. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] FIG1 is a diagram showing an application environment of a monitoring data checking method according to an embodiment;

[0047] FIG2 is a schematic diagram of a flow chart of a monitoring data checking method in one embodiment;

[0048] FIG3 is a schematic diagram of a measurement parameter display interface in one embodiment;

[0049] FIG4 is a schematic diagram of a quality control parameter display interface in one embodiment;

[0050] FIG5 is a schematic diagram of a monitoring log display interface in one embodiment;

[0051] FIG6 is a schematic diagram of an inspection record display interface in one embodiment;

[0052] FIG7 is a flow chart of the steps of determining the detection result in one embodiment;

[0053] FIG8 is a schematic diagram of a device status parameter display interface in one embodiment;

[0054] FIG9 is a flow chart of a first judgment result determination step in one embodiment;

[0055] FIG10 is a schematic diagram of a schematic diagram of upstream and downstream data in one embodiment;

[0056] FIG11 is a schematic diagram of training and using a first model and a second model in one embodiment;

[0057] FIG12 is a flow chart of monitoring data checking in one embodiment;

[0058] FIG13 is a structural block diagram of a measurement data checking device in one embodiment;

[0059] FIG. 14 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] The monitoring data checking method provided in the embodiment of the present application can be applied in the application environment as shown in Figure 1. Among them, the terminal 102 communicates with the server 104 via a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Both the terminal and the server can be used alone to execute the monitoring data checking method provided in the embodiment of the present application. The terminal and the server can also be used in collaboration to execute the monitoring data checking method provided in the embodiment of the present application. For example, the terminal 102 performs validity judgment on the monitoring data based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, and obtains the validity judgment result; based on the monitoring log and inspection record of the monitoring equipment, the monitoring equipment is tested to obtain the detection result of the monitoring equipment; based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, the monitoring data is judged for rationality, and the rationality judgment result is obtained; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point except the monitoring data; based on the validity judgment result, the detection result and the rationality judgment result, the inspection result of the monitoring data is obtained. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0062] In one embodiment, as shown in FIG2 , a monitoring data checking method is provided, which can be applied to a computer device, which can be a terminal or a server, and can be executed by the terminal or the server itself alone, or can be implemented through interaction between the terminal and the server. This embodiment is described by taking the method applied to a computer device as an example, and includes steps 202 to 208.

[0063] Step 202: Based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, the monitoring data is judged for validity to obtain a validity judgment result.

[0064] Among them, monitoring data refers to data measured by monitoring equipment, and monitoring data can be environmental monitoring data, such as water quality monitoring data. Monitoring equipment refers to equipment that collects monitoring data, and monitoring equipment can be environmental monitoring equipment, such as water quality monitoring equipment. Measurement parameters refer to equipment parameters when the monitoring equipment collects monitoring data. For example, in the measurement parameter display interface shown in Figure 3, the measurement parameters include measurement range, measurement accuracy, measurement interval, measurement detection limit, digestion temperature, digestion time, blank calibration time, standard sample calibration time, measurement signal value, curve intercept, curve slope, linear phase relationship, quadratic polynomial coefficient and dilution factor.

[0065] Quality control parameters refer to the data obtained by the monitoring equipment when measuring the standard solution, and the quality control parameters include but are not limited to the first standard solution measurement value, the first standard solution measurement span value, the second standard solution measurement value and the second standard solution measurement span value; the first standard solution measurement value refers to the data obtained by the monitoring equipment when measuring the standard solution of the first concentration; the first standard solution measurement span value refers to the difference between the first standard solution measurements obtained by the monitoring equipment twice measuring the standard solution of the first concentration in the interval time period; the second standard solution measurement value refers to the data obtained by the monitoring equipment when measuring the standard solution of the second concentration; the second standard solution measurement span value refers to the difference between the second standard solution measurements obtained by the monitoring equipment twice measuring the standard solution of the second concentration in the interval time period; the first concentration, the second concentration and the interval time period can be set according to actual needs and are not limited here. For example, in the quality control parameter display interface shown in Figure 4, the quality control parameters include the instrument measurement value corresponding to the zero point check, the instrument measurement value corresponding to the span check, the 24-hour drift span value of the zero point check and the 24-hour drift span value of the span check. The instrument measurement value corresponding to the zero point check is the measurement value of the first standard solution obtained by the monitoring equipment on a standard solution with a concentration of 0%; the instrument measurement value corresponding to the span check is the measurement value of the second standard solution obtained by the monitoring equipment on a standard solution with a concentration of 8%; the 24-hour drift span value of the zero point check is the difference between the first standard solution measurements obtained by the monitoring equipment twice measuring the 0% standard solution at an interval of 24 hours; the 24-hour drift span value of the span check refers to the difference between the second standard solution measurements obtained by the monitoring equipment twice measuring the 8% standard solution at an interval of 24 hours.

[0066] Validity judgment refers to judging the validity of the monitoring data measured by the monitoring equipment. Validity judgment result refers to the result of validity judgment. Validity judgment result can be measurement validity result and quality control validity result; validity judgment result can also be the result obtained by comprehensive judgment based on measurement validity judgment result and quality control validity result, and validity judgment result is valid or invalid.

[0067] Exemplarily, a computer device obtains monitoring data, and then obtains measurement parameters and quality control parameters of the monitoring device corresponding to the monitoring data, obtains measurement validity results based on the monitoring data, obtains quality control validity results based on the quality control parameters, and determines the validity judgment result based on the measurement validity results and the quality control validity results.

[0068] Step 204: Based on the monitoring log and inspection record of the monitoring device, the monitoring device is inspected to obtain the inspection result of the monitoring device.

[0069] Among them, the monitoring log refers to the log of monitoring data collected by the monitoring equipment, for example, the monitoring log corresponding to the permanganate index displayed in the monitoring log display interface shown in Figure 5. The inspection record refers to the record of the inspection personnel's inspection of the monitoring equipment, for example, the inspection record display interface shown in Figure 6 displays the inspection records corresponding to multiple different reporting dates. The test result refers to the result of the test on the monitoring equipment. The test result can be the equipment abnormality level and the equipment prediction result; the test result can also be the result obtained by comprehensive judgment based on the equipment abnormality level and the equipment prediction result, and the test result is that the monitoring equipment is normal or the monitoring equipment is abnormal.

[0070] Exemplarily, the computer device determines the device abnormality level based on the monitoring log, determines the abnormality prediction result based on the inspection record, and determines the detection result of the monitoring device based on the device abnormality level and the abnormality prediction result.

[0071] Step 206, based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, the rationality of the monitoring data is judged to obtain a rationality judgment result; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point excluding the monitoring data.

[0072] Among them, the target monitoring point refers to the location where monitoring data is collected, the upstream monitoring point refers to the location upstream of the target monitoring point, and the downstream monitoring point refers to the location downstream of the target monitoring point. The distance between the upstream monitoring point and the target monitoring point, as well as the distance between the target monitoring point and the downstream monitoring point, can be set according to actual needs and are not limited here. Historical monitoring data refers to historical data collected by the monitoring equipment at the target monitoring point, historical upstream monitoring data refers to historical data collected by the upstream monitoring equipment located at the upstream monitoring point at the upstream monitoring point, historical downstream monitoring data refers to historical data collected by the downstream monitoring equipment located at the downstream monitoring point at the downstream monitoring point, and historical data refers to data collected within a preset time period before the monitoring data is collected. For example, the historical data may be data collected within 30 days before the monitoring data is collected. Meteorological parameters refer to parameters that characterize the meteorology of the target monitoring point when the monitoring data is collected. Other monitoring data refers to other monitoring data collected at the target monitoring point. It can be understood that the monitoring data set collected at the target monitoring point is used to judge the quality and pollution of the water quality at the target monitoring point. When a monitoring data check is performed on a monitoring value in the monitoring data set, the monitoring value subject to the monitoring data check is the monitoring data, and the remaining monitoring values ​​in the monitoring data set are other monitoring data.

[0073] Exemplarily, the computer device determines a first judgment result based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point; determines a second judgment result based on the meteorological parameters and other monitoring data of the target monitoring point; and determines a rationality judgment result based on the first judgment result and the second judgment result.

[0074] Step 208, based on the effectiveness judgment result, the detection result and the rationality judgment result, obtain the inspection result of the monitoring data.

[0075] The inspection result refers to the result of the abnormality inspection of the monitoring data, and the inspection result can be normal or abnormal.

[0076] Exemplarily, the computer device determines whether the monitoring data is abnormal based on the effectiveness judgment result, the detection result and the rationality judgment result to obtain the inspection result of the monitoring data.

[0077] In one embodiment, if the validity judgment result is invalid, the inspection result of the monitoring data is determined to be abnormal; if the validity judgment result is valid, whether the monitoring data is abnormal is judged based on the detection result and the rationality judgment result to obtain the inspection result of the monitoring data.

[0078] In the above-mentioned monitoring data inspection method, the validity of the monitoring data is judged by the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data to obtain the validity judgment result of the monitoring data, the monitoring equipment is inspected by the monitoring log and inspection record of the monitoring equipment to obtain the inspection result of the monitoring equipment, the rationality of the monitoring data is judged by the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point to obtain the rationality judgment result of the monitoring data, that is, the validity judgment result of the comprehensive monitoring data, whether the monitoring equipment measuring the monitoring data is abnormal and the rationality judgment result of the monitoring data are judged whether the monitoring data is abnormal, which improves the accuracy of monitoring data inspection compared with only comparing the monitoring data with national standard data.

[0079] In one embodiment, based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, the monitoring data is judged for validity, and the validity judgment result is obtained, including:

[0080] Based on the measurement parameters of the monitoring equipment, the calculation reference data corresponding to the monitoring data is determined; based on the size relationship between the monitoring data and the calculation reference data, the measurement validity result is obtained; based on the size relationship between the quality control parameters and the quality control threshold, the quality control validity result is obtained; based on the measurement validity result and the quality control validity result, the validity judgment result is obtained.

[0081] The calculation reference data refers to the measurement data calculated according to the measurement parameters of the monitoring equipment. The quality control threshold refers to a pre-set value for comparison with the quality control parameter. The quality control threshold corresponds to the quality control parameter one by one. For example, the quality control parameter includes the first standard solution measurement value, the first standard solution measurement span value, the second standard solution measurement value and the second standard solution measurement span value. Then the quality control threshold includes the first standard solution measurement threshold, the first standard solution measurement span threshold, the second standard solution measurement threshold and the second standard solution measurement span threshold.

[0082] Exemplarily, the computer device substitutes the measurement parameters of the monitoring device into the inverse calculation formula to obtain the calculation reference data corresponding to the monitoring data, compares the monitoring data with the calculation reference data, and determines the measurement validity result based on the comparison result of the monitoring data and the calculation reference data; determines the quality control validity result based on the size relationship between the quality control parameter and the quality control threshold; determines the validity judgment result of the monitoring data based on the measurement validity result and the quality control validity result.

[0083] In one embodiment, the monitoring data and the operation reference data are compared, and the measurement validity result is determined based on the comparison result of the monitoring data and the operation reference data, including: comparing the monitoring data and the operation reference data, if the monitoring data and the operation reference data are different, then the measurement validity result is determined to be invalid; if the monitoring data and the operation reference data are the same, then the measurement validity result is determined to be valid.

[0084] In one embodiment, when the quality control parameters include the first standard solution measurement value, the first standard solution measurement span value, the second standard solution measurement value and the second standard solution measurement span value, and the quality control threshold includes the first standard solution measurement threshold, the first standard solution measurement span threshold, the second standard solution measurement threshold and the second standard solution measurement span threshold, based on the size relationship between the quality control parameters and the quality control threshold, determining the quality control validity result includes: comparing the absolute error between the first standard solution measurement value and the first standard solution value with the first standard solution measurement threshold, if the absolute error between the first standard solution measurement value and the first standard solution value is greater than the first standard solution measurement threshold, determining the quality control validity result as Invalid; compare the measured span value of the first standard solution with the measured span threshold of the first standard solution. If the measured span value of the first standard solution is greater than the measured span threshold of the first standard solution, the quality control validity result is determined to be invalid; compare the absolute error between the measured value of the second standard solution and the second standard solution value with the measurement threshold of the second standard solution. If the absolute error between the measured value of the second standard solution and the second standard solution value is greater than the measurement threshold of the second standard solution, the quality control validity result is determined to be invalid; compare the measured span value of the second standard solution with the measurement span threshold of the second standard solution. If the measured span value of the second standard solution is greater than the measurement span threshold of the second standard solution, the quality control validity result is determined to be invalid.

[0085] In this embodiment, the calculation reference data corresponding to the monitoring data is determined by the measurement parameters of the monitoring equipment; the measurement validity result is obtained based on the size relationship between the monitoring data and the calculation reference data, that is, the calculation reference data is obtained by calculating the measurement parameters, and the monitoring data should theoretically be equal to the calculation reference data. If the monitoring data is not equal to the calculation reference data, it means that the monitoring data has been tampered with, and the validity of the monitoring data can be determined through the size relationship between the monitoring data and the calculation reference data; the quality control validity result is obtained based on the size relationship between the quality control parameter and the quality control threshold, that is, the validity of the monitoring data measured by the monitoring equipment is determined by judging the accuracy of the standard solution measured by the monitoring equipment; the validity judgment result is obtained based on the measurement validity result and the quality control validity result, which provides basic data for subsequent determination of the inspection result of the monitoring data.

[0086] In one embodiment, as shown in FIG. 7 , based on the monitoring log and inspection record of the monitoring device, the monitoring device is tested to obtain the test result of the monitoring device, including:

[0087] Step 702: Determine the device abnormality level of the monitored device based on the device status parameters in the monitoring log.

[0088] Among them, the equipment status parameters refer to the parameters that characterize the status of the monitoring equipment, which can be understood as the parameters that characterize the status of the monitoring equipment when measuring the monitoring data. For example, the equipment status parameter display interface is shown in Figure 8. The equipment status parameters in the monitoring log include the working status, the communication status between the analyzer and the data acquisition instrument, the reaction reagent residue and the analyzer alarm status. The equipment abnormality level refers to the level of abnormality of the monitoring equipment. The equipment abnormality level includes but is not limited to level one, level two and level three. The lower the level, the higher the degree of abnormality.

[0089] Exemplarily, the computer device obtains the abnormality level mapping relationship, and obtains the device status parameters from the monitoring log, and determines the device abnormality level of the monitoring device based on the abnormality level mapping relationship and the device status parameters. The abnormality level mapping relationship refers to the corresponding relationship between the device status parameters and the device abnormality level. For example, the device abnormality level corresponding to the reaction reagent remaining amount of 0 is level one, and the device abnormality level corresponding to the alarm state of the analyzer is alarm is level two.

[0090] Step 704: Determine the inspection feature vector corresponding to the inspection record.

[0091] Among them, the inspection feature vector refers to the vector that represents the characteristics of the inspection record.

[0092] Exemplarily, the computer device digitally encodes the information in the inspection record to obtain an inspection feature vector.

[0093] Step 706: for each decision tree, determine the abnormality prediction result corresponding to the inspection feature vector based on the decision tree.

[0094] Among them, the decision tree refers to a machine learning model used for classification and regression problems. It gradually divides the data through a series of decision rules to form a classification model similar to a tree structure. The decision tree is a component of the random forest model, which includes multiple decision trees. The abnormal prediction result refers to the prediction result output by the decision tree based on the inspection feature vector.

[0095] Exemplarily, the computer device inputs the inspection feature vector into the random forest model, and each decision tree in the random forest model outputs an abnormality prediction result.

[0096] Step 708: Determine a device prediction result of the monitoring device based on the multiple abnormal prediction results.

[0097] Among them, the equipment prediction result refers to the prediction result of the abnormal situation of the monitoring equipment.

[0098] Exemplarily, the computer device determines a device prediction result of the monitoring device based on a plurality of abnormal prediction results.

[0099] In one embodiment, the inspection feature vector is X=(x1,x2,…,xn), the abnormal prediction result output by the i-th decision tree Ti is yi, and multiple abnormal prediction results are classified to obtain the equipment prediction result yrf, that is, yrf=majority_vote{y1,y2,…,yn}; or multiple abnormal prediction results are averaged to obtain the equipment prediction result yrf, that is .

[0100] Step 710, based on the device abnormality level and the device prediction result, obtain the detection result of the monitoring device.

[0101] Exemplarily, the computer device obtains the detection result of the monitoring device according to the device abnormality level and the device prediction result.

[0102] In one embodiment, the computer device displays the detection result of the monitoring device based on the detection result of the monitoring device.

[0103] In this embodiment, the equipment abnormality level of the monitoring equipment is determined by the equipment status parameters in the monitoring log, and the equipment prediction result of the monitoring equipment is determined by the inspection feature vector corresponding to the inspection record. That is, the abnormal situation of the monitoring equipment is judged by the monitoring log, and the abnormal situation of the equipment is predicted by the inspection record. The detection result of the monitoring equipment is obtained based on the equipment abnormality level and the equipment prediction result, providing basic data for the subsequent determination of the inspection result of the monitoring data.

[0104] In one embodiment, the monitoring data is judged for rationality based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, and the rationality judgment result is obtained, including:

[0105] Based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, the rationality of the monitoring data is judged to obtain a first judgment result; based on the meteorological parameters and other monitoring data of the target monitoring point, the rationality of the monitoring data is judged to obtain a second judgment result; based on the first judgment result and the second judgment result, a rationality judgment result is obtained.

[0106] The first judgment result refers to the result obtained by judging the rationality of the monitoring data using the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point. The second judgment result refers to the result obtained by judging the rationality of the monitoring data using the meteorological parameters and other monitoring data of the target monitoring point.

[0107] Exemplarily, the computer device converts the historical monitoring data of the target monitoring point corresponding to the monitoring data into a target vector, converts the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point into an upstream vector, and converts the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point into a downstream vector, and makes a rationality judgment on the monitoring data based on the target vector, the upstream vector, and the downstream vector to obtain a first judgment result; inputs the meteorological parameters and other monitoring data of the target monitoring point into the first model to obtain the first model output result, inputs the meteorological parameters and other monitoring data of the target monitoring point into the second model to obtain the second model output result, and makes a rationality judgment on the monitoring data based on the first model output result and the second model output result to obtain a second judgment result; and obtains a rationality judgment result based on the first judgment result and the second judgment result. Wherein, the first model is a linear neural network model, and the second model is a nonlinear neural network model;

[0108] In this embodiment, the rationality of the monitoring data is judged through historical monitoring data, historical upstream monitoring data of upstream monitoring points, historical downstream monitoring data of target downstream monitoring points, and meteorological parameters and other monitoring data of the target monitoring point to obtain a rationality judgment result, that is, the rationality of the monitoring data is inferred by combining the historical monitoring data of the upstream monitoring points and downstream monitoring points of the target monitoring point, and the rationality of the monitoring data is inferred by combining the weather conditions when the monitoring data is measured and other measured monitoring data, thereby improving the accuracy of the rationality judgment result.

[0109] In one embodiment, as shown in FIG9 , based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, the rationality of the monitoring data is judged to obtain a first judgment result, including:

[0110] Step 902 , based on a first difference vector between an upstream vector corresponding to historical upstream monitoring data of an upstream monitoring point and a target vector corresponding to historical monitoring data of a target monitoring point, determine a first mean and a first standard deviation corresponding to the first difference vector.

[0111] The upstream vector refers to the vector representing the historical upstream monitoring data. The target vector refers to the vector representing the historical monitoring data. The first difference vector refers to the vector obtained by subtracting the upstream vector from the target vector. The first mean refers to the average value of the values ​​in the first difference vector. The first standard deviation refers to the value representing the degree of dispersion of the values ​​in the first difference vector.

[0112] Exemplarily, the computer device subtracts the upstream vector corresponding to the historical upstream monitoring data of the upstream monitoring point from the target vector corresponding to the historical monitoring data of the target monitoring point to obtain a first difference vector, and then calculates the first mean and first standard deviation corresponding to the first difference vector.

[0113] Step 904 : Based on the second difference vector between the downstream vector corresponding to the historical downstream monitoring data of the downstream monitoring point and the target vector, determine the second mean and the second standard deviation corresponding to the second difference vector.

[0114] The downstream vector refers to a vector representing historical downstream monitoring data. The second difference vector refers to a vector obtained by subtracting the downstream vector from the target vector. The second mean refers to the average value of the values ​​in the second difference vector. The second standard deviation refers to a value representing the degree of dispersion of the values ​​in the second difference vector.

[0115] Exemplarily, the computer device subtracts the downstream vector corresponding to the historical downstream monitoring data of the downstream monitoring point from the target vector to obtain a second difference vector, and then calculates a second mean and a second standard deviation corresponding to the second difference vector.

[0116] In one embodiment, a computer device obtains historical monitoring data of a preset number of days for a target monitoring point, historical upstream monitoring data of a preset number of days for an upstream monitoring point, and historical downstream monitoring data of a preset number of days for a downstream monitoring point, and converts the historical monitoring data of the preset number of days into a target vector c1 (x11, x12, …, x1n), converts the historical upstream monitoring data into an upstream vector c2 (x21, x22, …, x2n), and converts the historical downstream monitoring data into a downstream vector c3 (x31, x32, …, x3n), then the first difference vector b1=c2-c1, the first difference vector b2=c3-c1, n represents the preset number of days, for example, if the preset number of days is 30 days, then n=30.

[0117] Step 906, determining the upstream difference between the upstream monitoring data and the monitoring data corresponding to the upstream monitoring point; the measurement time of the upstream monitoring data and the monitoring data is the same.

[0118] Among them, the upstream monitoring data refers to the monitoring value measured at the upstream monitoring point while measuring the monitoring data at the target monitoring point.

[0119] Exemplarily, the computer device obtains upstream monitoring data corresponding to the upstream monitoring point, subtracts the monitoring data from the upstream monitoring data, and obtains the upstream difference.

[0120] Step 908, determining the downstream difference between the downstream monitoring data and the monitoring data corresponding to the downstream monitoring point; the measurement time of the downstream monitoring data and the monitoring data is the same.

[0121] Among them, the downstream monitoring data refers to the monitoring values ​​measured at the downstream monitoring point while the monitoring data is measured at the target monitoring point.

[0122] Exemplarily, the computer device obtains downstream monitoring data corresponding to the downstream monitoring point, subtracts the monitoring data from the downstream monitoring data, and obtains a downstream difference.

[0123] Step 910, obtaining a first judgment result based on the upstream difference, the downstream difference, the first mean, the first standard deviation, the second mean and the second standard deviation.

[0124] Exemplarily, the computer device determines the first judgment result based on the upstream difference, the downstream difference, the first mean, the first standard deviation, the second mean, and the second standard deviation.

[0125] In one embodiment, based on the upstream difference, the downstream difference and the first mean, the first standard deviation, the second mean and the second standard deviation, a first judgment result is obtained, including: determining the first threshold based on the first standard deviation and the preset multiple; obtaining the upstream judgment result based on the difference between the upstream difference and the first mean and the size relationship between the first threshold; determining the second threshold based on the second standard deviation and the preset multiple; obtaining the downstream judgment result based on the difference between the downstream difference and the second mean and the size relationship between the second threshold; obtaining the first judgment result based on the upstream judgment result and the downstream judgment result. Among them, the preset multiple refers to a preset multiple, which can be set according to actual needs, and is not limited here. The preset multiple can be 1.5 or 2.0. For example, as shown in Figure 10, the upstream and downstream data schematic diagram includes a monitoring value straight line, a median value straight line and a mean value straight line. The monitoring value straight line characterizes the changes in the monitoring values ​​between the upstream monitoring point, the target monitoring point and the downstream monitoring point.

[0126] In this embodiment, the rationality of the monitoring data is judged through historical monitoring data, historical upstream monitoring data of the upstream monitoring point, and historical downstream monitoring data of the current downstream monitoring point to obtain a first judgment result, providing basic data for subsequent determination of the rationality judgment result of the monitoring data.

[0127] In one embodiment, based on the meteorological parameters and other monitoring data of the target monitoring point, the monitoring data is judged for rationality to obtain a second judgment result, including:

[0128] The meteorological parameters and other monitoring data of the target monitoring point are input into the first model to obtain multiple first prediction confidences and first confidence intervals corresponding to each first prediction confidence; the first model is a linear neural network model; the first prediction confidence corresponding to the first confidence interval in which the monitoring data is located is determined as the first confidence of the monitoring data; the meteorological parameters and other monitoring data of the target monitoring point are input into the second model to obtain multiple second prediction confidences and second confidence intervals corresponding to each second prediction confidence; the second model is a nonlinear neural network model; the second prediction confidence corresponding to the second confidence interval in which the monitoring data is located is determined as the second confidence of the monitoring data; based on the first confidence and the second confidence, a second judgment result is obtained.

[0129] Among them, a linear neural network refers to a neural network model in which the transformations between each layer in the network are linear transformations. A nonlinear neural network refers to a neural network model that introduces a nonlinear activation function. Linear neural network models and nonlinear neural network models are two major types of neural networks. The main difference between them is whether the network contains a nonlinear activation function. Prediction confidence refers to a numerical value that characterizes the accuracy of the confidence interval. Prediction confidence is usually expressed in percentage or decimal form, ranging from 0 to 1. The confidence interval refers to the possible range of the predicted value.

[0130] Exemplarily, the computer device inputs the meteorological parameters and other monitoring data of the target monitoring point into the first model, obtains multiple first prediction confidences and a first confidence interval corresponding to each first prediction confidence, and determines the first prediction confidence corresponding to the first confidence interval in which the monitoring data is located as the first confidence of the monitoring data; inputs the meteorological parameters and other monitoring data of the target monitoring point into the second model, obtains multiple second prediction confidences and a second confidence interval corresponding to each second prediction confidence, and determines the second prediction confidence corresponding to the second confidence interval in which the monitoring data is located as the second confidence of the monitoring data; and obtains a second judgment result based on the first confidence and the first confidence.

[0131] In one embodiment, based on the first confidence level and the second confidence level, a second judgment result is obtained, including: comparing the first confidence level with an abnormal threshold, and comparing the second confidence level with the abnormal threshold. If the first confidence level is greater than the abnormal threshold, and the second confidence level is greater than the abnormal threshold, the second judgment result is determined to be abnormal.

[0132] In one embodiment, a schematic diagram of the training and use of the first model and the second model is shown in Figure 11. First, the initial first model is trained using historical meteorological parameters and other historical monitoring data to obtain a trained first model, and the meteorological parameters and other monitoring data of the target monitoring point are input into the trained first model to obtain multiple first prediction confidences and a first confidence interval corresponding to each first prediction confidence; first, the initial second model is trained using historical meteorological parameters and other historical monitoring data to obtain a trained second model, and the meteorological parameters and other monitoring data of the target monitoring point are input into the trained second model to obtain multiple first prediction confidences and a first confidence interval corresponding to each first prediction confidence.

[0133] In this embodiment, the prediction confidence and confidence interval are predicted respectively by a linear neural network model and a nonlinear neural network model, that is, prediction is performed by two neural network models, and the second judgment result is determined according to the prediction results of the two neural network models, thereby improving the accuracy of the second judgment result.

[0134] In an exemplary embodiment, the monitoring data checking flow chart is shown in FIG12 , including:

[0135] The computer device obtains the monitoring data, and then obtains the measurement parameters and quality control parameters of the monitoring device corresponding to the monitoring data. When the quality control parameters include the measurement value of the first standard solution, the measurement span value of the first standard solution, the measurement value of the second standard solution, and the measurement span value of the second standard solution, and the quality control threshold includes the measurement threshold of the first standard solution, the measurement span threshold of the first standard solution, the measurement threshold of the second standard solution, and the measurement span threshold of the second standard solution, the absolute error between the measurement value of the first standard solution and the value of the first standard solution is compared with the measurement threshold of the first standard solution. If the absolute error between the measurement value of the first standard solution and the value of the first standard solution is greater than the measurement threshold of the first standard solution, the quality control validity result is determined to be invalid; the measurement span value of the first standard solution is compared with the measurement span value of the first standard solution. The solution measurement span threshold is compared. If the measurement span value of the first standard solution is greater than the measurement span threshold of the first standard solution, the quality control validity result is determined to be invalid; the absolute error between the measurement value of the second standard solution and the second standard solution value is compared with the second standard solution measurement threshold. If the absolute error between the measurement value of the second standard solution and the second standard solution value is greater than the second standard solution measurement threshold, the quality control validity result is determined to be invalid; the measurement span value of the second standard solution is compared with the measurement span threshold of the second standard solution. If the measurement span value of the second standard solution is greater than the measurement span threshold of the second standard solution, the quality control validity result is determined to be invalid.

[0136] The computer device substitutes the measurement parameters of the monitoring device into the inverse calculation formula to obtain the calculation reference data corresponding to the monitoring data, and compares the monitoring data with the calculation reference data. According to the comparison result of the monitoring data and the calculation reference data, if the monitoring data and the calculation reference data are different, the measurement validity result is determined to be invalid; if the monitoring data and the calculation reference data are the same, the measurement validity result is determined to be valid.

[0137] The computer device obtains the monitoring log and inspection record of the monitoring device. The computer device obtains the abnormal level mapping relationship and the device status parameters from the monitoring log, and determines the device abnormal level of the monitoring device based on the abnormal level mapping relationship and the device status parameters; the information in the inspection record is digitally encoded to obtain the inspection feature vector, and the inspection feature vector is input into the random forest model. Each decision tree in the random forest model outputs an abnormal prediction result, and multiple abnormal prediction results are classified to obtain the device prediction result, or multiple abnormal prediction results are averaged to obtain the device prediction result. According to the device abnormal level and the device prediction result, the detection result of the monitoring device is obtained.

[0138] The computer device obtains the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point. The historical monitoring data of the target monitoring point corresponding to the monitoring data is converted into a target vector, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point is converted into an upstream vector, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point is converted into a downstream vector; the upstream vector corresponding to the historical upstream monitoring data of the upstream monitoring point is subtracted from the target vector corresponding to the historical monitoring data of the target monitoring point to obtain a first difference vector, and then the first mean and first standard deviation corresponding to the first difference vector are calculated; the downstream vector corresponding to the historical downstream monitoring data of the downstream monitoring point is subtracted from the target vector to obtain a second difference vector, and then the second mean and second standard deviation corresponding to the second difference vector are calculated. Standard deviation; obtain the upstream monitoring data corresponding to the upstream monitoring point, subtract the monitoring data from the upstream monitoring data, and obtain the upstream difference; obtain the downstream monitoring data corresponding to the downstream monitoring point, subtract the monitoring data from the downstream monitoring data, and obtain the downstream difference; determine the first threshold value based on the first standard deviation and the preset multiplier; obtain the upstream judgment result based on the difference between the upstream difference and the first mean, and the size relationship between the first threshold value; determine the second threshold value based on the second standard deviation and the preset multiplier; obtain the downstream judgment result based on the difference between the downstream difference and the second mean, and the size relationship between the second threshold value; obtain the first judgment result based on the upstream judgment result and the downstream judgment result.

[0139] The computer device inputs the meteorological parameters and other monitoring data of the target monitoring point into the first model, obtains multiple first prediction confidences and a first confidence interval corresponding to each first prediction confidence, and determines the first prediction confidence corresponding to the first confidence interval in which the monitoring data is located as the first confidence of the monitoring data; inputs the meteorological parameters and other monitoring data of the target monitoring point into the second model, obtains multiple second prediction confidences and a second confidence interval corresponding to each second prediction confidence, and determines the second prediction confidence corresponding to the second confidence interval in which the monitoring data is located as the second confidence of the monitoring data; compares the first confidence with the abnormal threshold, and compares the second confidence with the abnormal threshold, if the first confidence is greater than the abnormal threshold, and the second confidence is greater than the abnormal threshold, then the second judgment result is determined to be abnormal.

[0140] The computer equipment determines whether the monitoring data is abnormal based on the effectiveness judgment results, the detection results and the rationality judgment results, and obtains the inspection results of the monitoring data.

[0141] In the above-mentioned monitoring data inspection method, the validity of the monitoring data is judged by the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data to obtain the validity judgment result of the monitoring data, the monitoring equipment is inspected by the monitoring log and inspection record of the monitoring equipment to obtain the inspection result of the monitoring equipment, the rationality of the monitoring data is judged by the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point to obtain the rationality judgment result of the monitoring data, that is, the validity judgment result of the comprehensive monitoring data, whether the monitoring equipment measuring the monitoring data is abnormal and the rationality judgment result of the monitoring data are judged whether the monitoring data is abnormal, which improves the accuracy of monitoring data inspection compared with only comparing the monitoring data with national standard data.

[0142] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0143] Based on the same inventive concept, the embodiment of the present application also provides a monitoring data inspection device for implementing the monitoring data inspection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more monitoring data inspection device embodiments provided below can refer to the limitations of the monitoring data inspection method above, and will not be repeated here.

[0144] In one embodiment, as shown in FIG. 13 , a monitoring data inspection device is provided, including: a validity judgment module 1302, an equipment detection module 1304, a rationality judgment module 1306 and an anomaly detection module 1308, wherein:

[0145] The validity judgment module 1302 is used to judge the validity of the monitoring data based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, and obtain the validity judgment result;

[0146] The device detection module 1304 is used to detect the monitoring device based on the monitoring log and inspection record of the monitoring device to obtain the detection result of the monitoring device;

[0147] The rationality judgment module 1306 is used to judge the rationality of the monitoring data based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, and obtain a rationality judgment result; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point excluding the monitoring data;

[0148] The anomaly detection module 1308 is used to obtain the inspection results of the monitoring data based on the effectiveness judgment results, the detection results and the rationality judgment results.

[0149] In one embodiment, the validity judgment module 1302 is also used to: determine the calculation reference data corresponding to the monitoring data based on the measurement parameters of the monitoring equipment; obtain the measurement validity result based on the size relationship between the monitoring data and the calculation reference data; obtain the quality control validity result based on the size relationship between the quality control parameter and the quality control threshold; obtain the validity judgment result based on the measurement validity result and the quality control validity result.

[0150] In one embodiment, the equipment detection module 1304 is also used to: determine the equipment abnormality level of the monitoring equipment based on the equipment status parameters in the monitoring log; determine the inspection feature vector corresponding to the inspection record; for each decision tree, determine the abnormality prediction result corresponding to the inspection feature vector based on the decision tree; determine the equipment prediction result of the monitoring equipment based on multiple abnormality prediction results; and obtain the detection result of the monitoring equipment based on the equipment abnormality level and the equipment prediction result.

[0151] In one embodiment, the rationality judgment module 1306 is also used to: perform rationality judgment on the monitoring data based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point to obtain a first judgment result; perform rationality judgment on the monitoring data based on the meteorological parameters and other monitoring data of the target monitoring point to obtain a second judgment result; obtain a rationality judgment result based on the first judgment result and the second judgment result.

[0152] In one embodiment, the rationality judgment module 1306 is also used to: determine the first mean and the first standard deviation corresponding to the first difference vector based on the first difference vector between the upstream vector corresponding to the historical upstream monitoring data of the upstream monitoring point and the target vector corresponding to the historical monitoring data of the target monitoring point; determine the second mean and the second standard deviation corresponding to the second difference vector based on the second difference vector between the downstream vector corresponding to the historical downstream monitoring data of the downstream monitoring point and the target vector; determine the upstream difference between the upstream monitoring data corresponding to the upstream monitoring point and the monitoring data; the measurement time of the upstream monitoring data and the monitoring data is the same; determine the downstream difference between the downstream monitoring data corresponding to the downstream monitoring point and the monitoring data; the measurement time of the downstream monitoring data and the monitoring data is the same; obtain the first judgment result based on the upstream difference, the downstream difference, the first mean, the first standard deviation, the second mean and the second standard deviation.

[0153] In one embodiment, the rationality judgment module 1306 is also used to: input the meteorological parameters and other monitoring data of the target monitoring point into the first model to obtain multiple first prediction confidences and first confidence intervals corresponding to each first prediction confidence; the first model is a linear neural network model; the first prediction confidence corresponding to the first confidence interval in which the monitoring data is located is determined as the first confidence of the monitoring data; the meteorological parameters and other monitoring data of the target monitoring point are input into the second model to obtain multiple second prediction confidences and second confidence intervals corresponding to each second prediction confidence; the second model is a nonlinear neural network model; the second prediction confidence corresponding to the second confidence interval in which the monitoring data is located is determined as the second confidence of the monitoring data; based on the first confidence and the second confidence, a second judgment result is obtained.

[0154] Each module in the above monitoring data inspection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0155] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG14. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a monitoring data inspection method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0156] Those skilled in the art will understand that the structure shown in FIG. 14 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0157] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0158] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0159] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0162] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A monitoring data checking method, characterized in that: The method comprises: Based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, the effectiveness of the monitoring data is judged to obtain a validity judgment result; Based on the monitoring log and inspection record of the monitoring device, the monitoring device is tested to obtain the test result of the monitoring device; Based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point, the rationality of the monitoring data is judged to obtain a rationality judgment result; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point excluding the monitoring data; Based on the validity judgment result, the detection result and the rationality judgment result, the inspection result of the monitoring data is obtained.

2. The method according to claim 1, characterized in that The validity judgment of the monitoring data is performed based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data to obtain the validity judgment result, including: Determining computational reference data corresponding to the monitoring data based on measurement parameters of the monitoring device; Based on the magnitude relationship between the monitoring data and the calculation reference data, a measurement validity result is obtained; Based on the magnitude relationship between the quality control parameter and the quality control threshold, a quality control effectiveness result is obtained; Based on the measurement validity result and the quality control validity result, a validity judgment result is obtained.

3. The method according to claim 1, characterized in that The detecting of the monitoring device based on the monitoring log and the inspection record of the monitoring device to obtain the detection result of the monitoring device includes: Determining a device abnormality level of the monitoring device based on the device status parameters in the monitoring log; Determine an inspection feature vector corresponding to the inspection record; For each decision tree, determining an abnormality prediction result corresponding to the inspection feature vector based on the decision tree; Determining a device prediction result of the monitoring device based on the plurality of abnormal prediction results; Based on the device abnormality level and the device prediction result, a detection result of the monitoring device is obtained.

4. The method according to claim 1, characterized in that The rationality judgment of the monitoring data is performed based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point to obtain a rationality judgment result, including: Based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, the rationality of the monitoring data is judged to obtain a first judgment result; Based on the meteorological parameters and other monitoring data of the target monitoring point, a rationality judgment is performed on the monitoring data to obtain a second judgment result; Based on the first judgment result and the second judgment result, a rationality judgment result is obtained.

5. The method according to claim 4, characterized in that The rationality judgment of the monitoring data based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, and the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point to obtain a first judgment result includes: Determine a first mean and a first standard deviation corresponding to the first difference vector based on a first difference vector between an upstream vector corresponding to the historical upstream monitoring data of the upstream monitoring point and a target vector corresponding to the historical monitoring data of the target monitoring point; Determine a second mean and a second standard deviation corresponding to the second difference vector based on a second difference vector between a downstream vector corresponding to the historical downstream monitoring data of the downstream monitoring point and the target vector; Determine an upstream difference between the upstream monitoring data corresponding to the upstream monitoring point and the monitoring data; the upstream monitoring data and the monitoring data are measured at the same time; Determine a downstream difference between the downstream monitoring data corresponding to the downstream monitoring point and the monitoring data; the downstream monitoring data and the monitoring data are measured at the same time; A first judgment result is obtained based on the upstream difference, the downstream difference, the first mean, the first standard deviation, the second mean and the second standard deviation.

6. The method according to claim 4, characterized in that The rationality judgment of the monitoring data based on the meteorological parameters and other monitoring data of the target monitoring point to obtain a second judgment result includes: Inputting the meteorological parameters and other monitoring data of the target monitoring point into a first model to obtain a plurality of first prediction confidences and a first confidence interval corresponding to each of the first prediction confidences; the first model is a linear neural network model; Determine the first prediction confidence corresponding to the first confidence interval in which the monitoring data is located as the first confidence of the monitoring data; Inputting the meteorological parameters and other monitoring data of the target monitoring point into a second model to obtain a plurality of second prediction confidences and a second confidence interval corresponding to each second prediction confidence; the second model is a nonlinear neural network model; Determine the second prediction confidence corresponding to the second confidence interval in which the monitoring data is located as the second confidence of the monitoring data; A second judgment result is obtained based on the first confidence level and the second confidence level.

7. A monitoring data checking device, characterized in that: The device comprises: The validity judgment module is used to judge the validity of the monitoring data based on the measurement parameters and quality control parameters of the monitoring equipment corresponding to the monitoring data, and obtain the validity judgment result; An equipment detection module, used to detect the monitoring equipment based on the monitoring log and inspection record of the monitoring equipment, and obtain the detection result of the monitoring equipment; A rationality judgment module is used to judge the rationality of the monitoring data based on the historical monitoring data of the target monitoring point corresponding to the monitoring data, the historical upstream monitoring data of the upstream monitoring point corresponding to the target monitoring point, the historical downstream monitoring data of the downstream monitoring point corresponding to the target monitoring point, and the meteorological parameters and other monitoring data of the target monitoring point to obtain a rationality judgment result; the other monitoring data is the monitoring value of the monitoring data set corresponding to the target monitoring point excluding the monitoring data; The anomaly detection module is used to obtain the inspection result of the monitoring data based on the effectiveness judgment result, the detection result and the rationality judgment result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images