Hazardous chemical operation data quality detection method and device and storage medium

Abstract

The invention discloses a quality detection method and device for hazardous chemical operation data and a storage medium. The method comprises the following steps: querying production data generated by a hazardous chemical enterprise during production in each time period; the production data comprises fire operation data and temporary power utilization operation data; preprocessing the production data of the hazardous chemical enterprises; if the preprocessing is completed, calculating the correlation between the fire operation data and the temporary power utilization operation data for the dangerous chemical enterprise; and detecting the data quality of the production data according to the correlation. According to the embodiment, the data quality of the production data is detected by using the correlation of the two data according to the coupling relationship between the fire operation and the temporary power utilization operation of the hazardous chemical enterprise, the actual business condition of the hazardous chemical enterprise is met, the accuracy of the detection data quality of the production data can be ensured, and the production efficiency is improved. Technical support is provided for effectiveness of subsequent safety commitment, daily dynamic hierarchical supervision and other models, safety production supervision of hazardous chemical enterprises is guaranteed, and production safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of safety, and particularly to a method, device, and storage medium for quality detection of hazardous chemical operation data. Background Art

[0002] In recent years, with the continuous increase in the demand for safe production of hazardous chemicals, the combination of technical means such as digitization and intelligentization with the business of hazardous chemical safe production has been gradually deepened and strengthened. Emergency management departments at all levels, chemical industrial parks, and chemical groups have successively completed the construction of a risk monitoring and early warning platform for hazardous chemical safe production, and built multiple artificial intelligence algorithm models such as instant early warning of major hazard sources, safety commitment, and daily dynamic hierarchical supervision in the platform to provide guarantee for hazardous chemical safe production.

[0003] However, the production data reported by hazardous chemical enterprises to the platform mainly relies on manual input, and there are certain data quality problems. If this part of production data is directly transmitted to the model, the results output by the model will be chaotic, affecting the safety production supervision of hazardous chemical enterprises and increasing the production risk. Summary of the Invention

[0004] In view of this, the present invention provides a method, device, and storage medium for quality detection of hazardous chemical operation data to detect the quality of production data of hazardous chemical enterprises.

[0005] The first aspect of the present invention provides a method for quality detection of hazardous chemical operation data, including:

[0006] Querying the production data generated during the production of a hazardous chemical enterprise in each time period; the production data includes hot work operation data and temporary power use operation data;

[0007] Preprocessing the production data of the hazardous chemical enterprise;

[0008] If the preprocessing is completed, calculating the correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise;

[0009] Detecting the data quality of the production data based on the correlation.

[0010] The second aspect of the present invention provides a device for quality detection of hazardous chemical operation data, including:

[0011] A production data query module for querying the production data generated during the production of a hazardous chemical enterprise in each time period; the production data includes hot work operation data and temporary power use operation data;

[0012] A preprocessing module for preprocessing the production data of the hazardous chemical enterprise;

[0013] A correlation calculation module, configured to calculate the correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise if the preprocessing is completed;

[0014] A data quality detection module, configured to detect the data quality of the production data according to the correlation.

[0015] A third aspect of the present invention provides an electronic device, which includes:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the quality detection method for hazardous chemical operation data as described in the first aspect above.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the quality detection method for hazardous chemical operation data as described in the first aspect above.

[0020] A fifth aspect of the present invention provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the quality detection method for hazardous chemical operation data as described in the first aspect above.

[0021] In this embodiment, the production data generated during the production of a hazardous chemical enterprise in each time period is queried; the production data includes hot work operation data and temporary power use operation data; the production data of the hazardous chemical enterprise is preprocessed; if the preprocessing is completed, the correlation between the hot work operation data and the temporary power use operation data is calculated for the hazardous chemical enterprise; the data quality of the production data is detected according to the correlation. This embodiment uses the correlation between the two pieces of data to detect the data quality of the production data based on the coupling relationship between the hot work operation and the temporary power use operation of the hazardous chemical enterprise, which conforms to the actual business situation of the hazardous chemical enterprise, can ensure the accuracy of detecting the data quality of the production data, provides technical support for the effectiveness of subsequent models such as safety commitment and daily dynamic hierarchical supervision, ensures the safety production supervision of the hazardous chemical enterprise, and improves the safety of production.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0024] Figure 1 It is a flowchart of a method for quality inspection of hazardous chemical operation data provided in the first embodiment of the present invention.

[0025] Figure 2 And Figure 3 It is an example diagram of outlier detection provided in the first embodiment of the present invention.

[0026] Figure 4 It is an example diagram of correlation analysis provided in the first embodiment of the present invention.

[0027] Figure 5 It is an example diagram of the proportion of hazardous chemical enterprises at each relevant level provided in the first embodiment of the present invention.

[0028] Figure 6 It is an example diagram of fitting a straight line to hazardous chemical enterprises with correlation provided in the first embodiment of the present invention.

[0029] Figure 7 It is an example diagram of fitting a straight line to hazardous chemical enterprises without correlation provided in the first embodiment of the present invention.

[0030] Figure 8 It is a schematic structural diagram of a device for quality inspection of hazardous chemical operation data provided in the second embodiment of the present invention.

[0031] Figure 9 It is a schematic structural diagram of an electronic device provided in the third embodiment of the present invention. Detailed implementation manners

[0032] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can cover implementations in sequences other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] See Figure 1 , which shows a flowchart of a method for quality detection of hazardous chemical operation data provided in Embodiment 1 of the present invention. This method can be executed by a quality detection device for hazardous chemical operation data. The quality detection device for hazardous chemical operation data can be implemented in the form of hardware and / or software, and the quality detection device for hazardous chemical operation data can be configured in an electronic device. As Figure 1 shown, the method includes:

[0036] Step 101, query the production data generated by hazardous chemical enterprises during production in each time period.

[0037] At the business level of hazardous chemical enterprises, many hot work operations (such as welding, cutting, grinding, etc.) rely on temporary power supply operations to provide high-power electrical support. Especially when using electric tools (such as electric welding machines, electric cutting machines, electric grinders, etc.), due to the large power of these electric tools, existing fixed power supplies often have difficulty supporting direct power supply. Therefore, temporary power supply equipment is used to support hot work operations. Therefore, the hot work operation data generated during hot work operations and the temporary power supply operation data generated during temporary power supply operations are usually correlated.

[0038] In practical applications, each hazardous chemical enterprise uploads various data generated during production to the hazardous chemical safety production risk monitoring and early warning platform within each relatively short time range (such as 1 day).

[0039] Considering that the fluctuations in hot work operation data and temporary power supply operation data are relatively large within a relatively short time range, multiple time ranges can be combined into a time period (such as 1 month), and the data reported by hazardous chemical enterprises are aggregated at the sampling frequency of the time period, so that a sample (i.e., production data) is formed within one time period. Among them, the production data includes hot work operation data and temporary power supply operation data.

[0040] Step 102: Preprocess the production data of hazardous chemical enterprises.

[0041] In practical applications, according to the production characteristics of hazardous chemical enterprises, one or more preprocessings can be performed on the production data of each hazardous chemical enterprise (including the hot work operation data and temporary electricity use operation data of hazardous chemical enterprises) to improve the quality of production data and meet the requirements of subsequent correlation analysis.

[0042] In an embodiment of the present invention, step 102 may include the following steps:

[0043] Step 1021: For hazardous chemical enterprises, perform content detection on individual production data to delete production data with empty content.

[0044] In this embodiment, the production data of each hazardous chemical enterprise can be traversed. Considering that some hazardous chemical enterprises actually do not have hot work operations and temporary electricity use operations, content detection can be performed on individual production data, thereby deleting production data with empty content such as hot work operation data and temporary electricity use operation data to avoid affecting the test of the correlation coefficient.

[0045] In practical applications, for individual production data, count the first operation times of hot work operation data and the second operation times of temporary electricity use operation data.

[0046] If the first operation times are 0 and the second operation times are 0, it is determined that the content of the production data is empty, and the production data is deleted.

[0047] If the first operation times are greater than 0 and / or the second operation times are greater than 0, it is determined that the content of the production data is not empty, and the production data is retained.

[0048] Step 1022: If the content detection is completed, perform anomaly detection on all production data to delete production data belonging to outliers.

[0049] When the content detection of individual production data of hazardous chemical enterprises is completed, anomaly detection can be further performed on all production data of a single hazardous chemical enterprise, thereby deleting production data belonging to outliers.

[0050] In practical applications, on the one hand, as Figure 2 and Figure 3 shown, clustering algorithms such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise) can be used to cluster all hot work operation data (mainly using the first operation times) of a single hazardous chemical enterprise. By setting parameters such as the anomaly radius and the minimum number of neighborhood points, normal points or anomaly points can be marked for the production data to which the hot work operation data belongs.

[0051] On the other hand, DBSCAN can be used to cluster all temporary electricity usage operation data (mainly using the second operation times), and by setting parameters such as the abnormal radius and the minimum number of neighborhood points, normal points or abnormal points can be marked for the production data to which the temporary electricity usage operation data belongs.

[0052] Determine that the production data marked with at least one abnormal point is an outlier, delete the production data, and eliminate the interference of individual false reports and concealed reports on subsequent analysis.

[0053] Determine that the production data marked with two normal points is normal value and retain the production data.

[0054] Step 1023: If the abnormal detection is completed, perform validity detection on all production data as a whole to retain or delete all production data.

[0055] When the abnormal detection of all production data of a single hazardous chemical enterprise is completed, the validity detection of all production data of a single hazardous chemical enterprise can be further performed as a whole, so as to decide whether to retain or delete all production data.

[0056] In a specific implementation, the sample quantity of all remaining production data (i.e., samples) of a single hazardous chemical enterprise can be counted, and the density of the first operation times and / or the second operation times can be calculated.

[0057] Exemplarily, for the first operation times, the number of different first operation times with different values can be used as the density. For the second operation times, the number of different second operation times with different values can be used as the density. For the first operation times and the second operation times, statistical values such as the sum value, average value, etc. between the number of different first operation times with different values and the number of different second operation times with different values can be used as the density, and so on.

[0058] Compare the sample quantity with a preset sample threshold, and compare the density with a density threshold.

[0059] If the sample quantity is less than the preset quantity threshold, or the density is greater than the preset density threshold, it is determined that all production data of a single hazardous chemical enterprise is invalid as a whole, and all production data of a single hazardous chemical enterprise is deleted.

[0060] Among them, the sample quantity being less than the quantity threshold means that the quantity of samples (i.e., production data) is too small, the significance of analyzing the correlation is low, and the significance of statistical analysis is lost.

[0061] In addition, a density greater than the density threshold indicates that the distribution of samples (i.e., production data) is too dense. Even if the number of samples (i.e., production data) is sufficient, it affects the common relationship between hot work operations and temporary electricity use operations, resulting in a relatively one-sided analysis and a large error.

[0062] If the number of samples is greater than or equal to the preset sample threshold and the density is less than or equal to the preset density threshold, it is determined that all the production data of a single hazardous chemical enterprise are valid as a whole, and all the production data of the single hazardous chemical enterprise are retained.

[0063] Step 103: If the preprocessing is completed, calculate the correlation between the hot work operation data and the temporary electricity use operation data for the hazardous chemical enterprise.

[0064] When the preprocessing of the production data of a hazardous chemical enterprise is completed, the correlation between the hot work operation data and the temporary electricity use operation data can be calculated for the hazardous chemical enterprise, so as to verify the correlation between the hot work operation and the temporary electricity use operation for the hazardous chemical enterprise.

[0065] In a specific implementation, as Figure 4 shown, the correlation coefficient between the hot work operation data (mainly using the first operation times) and the temporary electricity use operation data (mainly using the second operation times) can be calculated for the hazardous chemical enterprise. For example, Pearson correlation coefficient, Spearman correlation coefficient, Kendall rank correlation coefficient, and so on.

[0066] Map the correlation coefficient to a correlation level using a table or other means.

[0067] When the correlation coefficient is greater than or equal to 0, the correlation level is positively correlated with the correlation coefficient.

[0068] When the correlation coefficient is less than 0, the correlation level is negatively correlated with the correlation coefficient.

[0069] Taking the Pearson correlation coefficient as an example, the Pearson correlation coefficient can measure the strength and direction of the linear relationship between the hot work operation data and the temporary electricity use operation data. Its value ranges from -1 to +1, where +1 indicates a perfect positive correlation (the hot work operation data and the temporary electricity use operation data increase completely synchronously), -1 indicates a perfect negative correlation (when one variable increases, the other variable decreases completely); 0 indicates no linear relationship.

[0070] According to the value of the Pearson correlation coefficient, the correlation strength can be graded to obtain the correlation level.

[0071] In this example, the grading criteria for the Pearson correlation coefficient are as follows:

[0072] I. 0.0 to 0.1 or -0.1 to 0.0: Almost no correlation (very weak correlation);

[0073] II. 0.1 to 0.3 or -0.3 to -0.1: Weak correlation (weak positive or negative correlation);

[0074] III. 0.3 to 0.5 or -0.5 to -0.3: Moderate correlation (moderate positive or negative correlation);

[0075] IV. 0.5 to 0.7 or -0.7 to -0.5: Strong correlation (strong positive or negative correlation);

[0076] V. 0.7 to 1.0 or -1.0 to -0.7: Very strong correlation (very strong positive or negative correlation).

[0077] If the correlation level is less than the preset level threshold (such as level five), then there is no correlation between the hot work operation data and the temporary power use operation data for hazardous chemical enterprises.

[0078] If the correlation level is greater than or equal to the preset level threshold (such as level five), then as Figure 4 shown, perform a significance test on the hot work operation data and the temporary power use operation data of hazardous chemical enterprises, and calculate the significance coefficient between the hot work operation data and the temporary power use operation data of hazardous chemical enterprises, such as the P-value, etc.

[0079] If the significance coefficient is less than or equal to the preset significance threshold (such as 0.05), then it is determined that there is a correlation between the hot work operation data and the temporary power use operation data for hazardous chemical enterprises.

[0080] Taking the P-value as an example, the magnitude of the P-value reflects the probability of the observed hot work operation data and temporary power use operation data occurring under the hypothesis test. Among them, the hypothesis test is the null hypothesis H0, that is, it is assumed that there is no linear relationship between the hot work operation data and the temporary power use operation data (i.e., the correlation coefficient is zero), while the alternative hypothesis H1 indicates the existence of a significant linear relationship.

[0081] If the P-value is less than or equal to 0.05, it indicates that the correlation between the hot work operation data and the temporary power use operation data is significant, and the null hypothesis can be rejected, believing that there is a significant linear correlation between the hot work operation data and the temporary power use operation data; if the P-value is greater than 0.05, it indicates that there is not enough evidence to reject the null hypothesis, and it cannot be proven that there is a significant linear correlation between the hot work operation data and the temporary power use operation data.

[0082] The correlation coefficient measures the strength of the linear correlation between hot work operation data and temporary power use operation data, while the significance test evaluates whether this correlation is caused by random error. When used in combination, they can determine whether the linear relationship between two hot work operation data and temporary power use operation data is statistically significant.

[0083] In Figure 4 , the scatter plots of the significance test P-values of hazardous chemical enterprises with all very strong correlations (i.e., Pearson correlation coefficients between 0.7 and 1.0) were drawn. Among them, the P-values of most hazardous chemical enterprises were almost 0, and the maximum value was about 1×10 -5 , far less than 0.05. That is, the test results of all hazardous chemical enterprises rejected the null hypothesis, and the correlations between the hot work operation data and temporary power use operation data of all hazardous chemical enterprises with very strong correlations were not caused by random error.

[0084] Generally, situations such as false reporting and concealment are small-probability events, while normal reporting of hot work operations and temporary power use operations are large-probability events.

[0085] Therefore, the number of the first enterprises of all hazardous chemical enterprises can be counted, as well as the number of the second enterprises of hazardous chemical enterprises with correlations in hot work operation data and temporary power use operation data.

[0086] Calculate the ratio between the number of the second enterprises and the number of the first enterprises to obtain the correlation ratio, and compare the correlation ratio with a preset ratio threshold.

[0087] If the correlation ratio is greater than or equal to the preset ratio threshold, it is determined that the correlation between the hot work operation data and temporary power use operation data of the hazardous chemical enterprise is valid.

[0088] If the correlation ratio is less than the preset ratio threshold, it is determined that the correlation between the hot work operation data and temporary power use operation data of the hazardous chemical enterprise is invalid.

[0089] For example, as Figure 5 shown, when using the Pearson correlation coefficient for grading, the corresponding correlation ratios are counted for hazardous chemical enterprises under each correlation level. The proportion (i.e., the correlation ratio) of hazardous chemical enterprises with very strong correlations between hot work operations and temporary power use operations in the overall hazardous chemical enterprises is about 0.82, and the proportion is relatively high, so it can be considered that the correlation between the hot work operation data and temporary power use operation data of the hazardous chemical enterprise is valid.

[0090] Step 104: Determine the data quality of production data based on the correlation detection.

[0091] In this embodiment, the data quality of the production data of the hazardous chemical operation can be detected based on the correlation between the hot work operation data and the temporary power use operation data, and it can be determined whether the data quality of the production data of the hazardous chemical operation meets the management specifications.

[0092] In a specific implementation, as Figure 6 shown, the least squares method or other methods can be used to fit a first straight line to the correlated hot work operation data (mainly using the first number of operations) and / or temporary power use operation data (mainly using the second number of operations).

[0093] Use indicators such as residuals, average deviation, and root mean square error to calculate the degree to which the correlated hot work operation data and / or temporary power use operation data deviate from the first straight line, and obtain a first deviation degree.

[0094] As Figure 7 shown, the least squares method or other methods can be used to fit a second straight line to the uncorrelated hot work operation data and / or temporary power use operation data.

[0095] Use indicators such as residuals, average deviation, and root mean square error to calculate the degree to which the uncorrelated hot work operation data and / or temporary power use operation data deviate from the second straight line, and obtain a second deviation degree.

[0096] If the first deviation degree is less than or equal to a preset deviation threshold, it is determined that the data quality of the production data meets the management specifications.

[0097] As Figure 7 shown, for a certain hazardous chemical enterprise, the hot work operation and the temporary power use operation may be non-interfering, but this situation is rare. Therefore, the production data reported by the enterprise is relatively in line with the actual situation, and the data quality is relatively high, meeting the management specifications.

[0098] If the first deviation degree is greater than the preset deviation threshold, and / or, the second deviation degree is greater than or equal to the preset deviation threshold, it is determined that the data quality of the production data does not meet the management specifications.

[0099] As Figure 8 shown, for a certain hazardous chemical enterprise, the hot work operation and the temporary power use operation have almost no correlation, which is contrary to the actual situation of the vast majority of hazardous chemical enterprises, and there are situations such as false reporting and concealment of data.

[0100] Furthermore, initially, a fluctuation range can be constructed based on the slope of the first straight line, where the fluctuation range is the reasonable fluctuation range of the first straight line.

[0101] Generally, technicians correct the slope of the first straight line according to the actual situation of the hazardous chemical enterprise in the hot work operation and / or temporary power use operation. When the correction is completed, the step length one is added to and / or the step length two is subtracted from the slope of the first straight line to obtain the fluctuation range.

[0102] When it is not in the initial stage, the newly reported production data of hazardous chemical enterprises is fused with the historically reported production data, and quality inspection is carried out again to generate a new first straight line, and the slope and fluctuation range of the first straight line are compared.

[0103] If the slope of the first straight line is within the fluctuation range, indicating that the slope of the first straight line is within a reasonable range, it is determined that the data quality of the production data meets the management specifications.

[0104] If the slope of the first straight line is outside the fluctuation range, indicating that the slope of the first straight line is large and there is an abnormality, it is determined that the data quality of the production data does not meet the management specifications.

[0105] In this embodiment, the production data generated during the production of hazardous chemical enterprises in each time period is queried; the production data includes hot work operation data and temporary power use operation data; the production data of hazardous chemical enterprises is preprocessed; if the preprocessing is completed, the correlation between the hot work operation data and the temporary power use operation data is calculated for the hazardous chemical enterprises; the data quality of the production data is detected based on the correlation. This embodiment detects the data quality of production data using the correlation between the data of hot work operation and temporary power use operation according to the coupling relationship between hot work operation and temporary power use operation of hazardous chemical enterprises, which conforms to the actual business situation of hazardous chemical enterprises, can ensure the accuracy of detecting the data quality of production data, provides technical support for the effectiveness of subsequent models such as safety commitment and daily dynamic hierarchical supervision, ensures the safety production supervision of hazardous chemical enterprises, and improves the safety of production.

[0106] Embodiment 2

[0107] See Figure 8 , which shows a schematic structural diagram of a quality detection device for hazardous chemical operation data provided by Embodiment 2 of the present invention. As Figure 8 shown, the device includes:

[0108] A production data query module 801, configured to query the production data generated during the production of hazardous chemical enterprises in each time period; the production data includes hot work operation data and temporary power use operation data;

[0109] A preprocessing module 802, configured to preprocess the production data of the hazardous chemical enterprises;

[0110] A correlation calculation module 803, configured to calculate the correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprises if the preprocessing is completed;

[0111] A data quality detection module 804, configured to detect the data quality of the production data based on the correlation.

[0112] In an embodiment of the present invention, the preprocessing module 802 includes:

[0113] A content detection module, which is used to perform content detection on each piece of production data for the hazardous chemical enterprise to delete the production data with empty content;

[0114] An anomaly detection module, which is used to perform anomaly detection on all the production data if the content detection is completed to delete the production data belonging to outliers;

[0115] A validity detection module, which is used to perform validity detection on all the production data as a whole if the anomaly detection is completed to retain or delete all the production data.

[0116] In an embodiment of the present invention, the content detection module is further used for:

[0117] Count the first operation times of the hot work operation data and the second operation times of the temporary power use operation data for each piece of production data;

[0118] If the first operation times is 0 and the second operation times is 0, determine that the content of the production data is empty and delete the production data;

[0119] If the first operation times is greater than 0 and / or the second operation times is greater than 0, determine that the content of the production data is not empty and retain the production data;

[0120] The anomaly detection module is further used for:

[0121] Cluster all the hot work operation data to mark normal points or abnormal points for the production data to which the hot work operation data belongs;

[0122] Cluster all the temporary power use operation data to mark normal points or abnormal points for the production data to which the temporary power use operation data belongs;

[0123] Determine that the production data marked with at least one abnormal point is an outlier and delete the production data;

[0124] Determine that the production data marked with two normal points is a normal value and retain the production data;

[0125] The validity detection module is further used for:

[0126] Count the sample quantity of all the production data and calculate the density for the first operation times and / or the second operation times;

[0127] If the number of samples is less than a preset number threshold, or the density is greater than a preset density threshold, it is determined that all the production data is invalid as a whole, and all the production data is deleted;

[0128] If the number of samples is greater than or equal to a preset sample threshold and the density is less than or equal to a preset density threshold, it is determined that all the production data is valid as a whole, and all the production data is retained.

[0129] In an embodiment of the present invention, the correlation calculation module 803 includes:

[0130] A correlation coefficient calculation module, configured to calculate the correlation coefficient between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise;

[0131] A correlation level mapping module, configured to map the correlation coefficient to a correlation level;

[0132] A first correlation determination module, configured to determine that there is no correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise if the correlation level is less than a preset level threshold;

[0133] A significance coefficient calculation module, configured to calculate the significance coefficient between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise if the correlation level is greater than or equal to a preset level threshold;

[0134] A second correlation determination module, configured to determine that there is a correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise if the significance coefficient is less than or equal to a preset significance threshold.

[0135] In an embodiment of the present invention, when the correlation coefficient is greater than or equal to 0, the correlation level is positively correlated with the correlation coefficient;

[0136] When the correlation coefficient is less than 0, the correlation level is negatively correlated with the correlation coefficient.

[0137] In an embodiment of the present invention, the correlation calculation module 803 further includes:

[0138] An enterprise number statistics module, configured to count the first enterprise number of all the hazardous chemical enterprises, and the second enterprise number of the hazardous chemical enterprises where there is a correlation between the hot work operation data and the temporary power use operation data;

[0139] A correlation ratio calculation module, configured to calculate the ratio between the second enterprise number and the first enterprise number to obtain a correlation ratio;

[0140] An effective determination module, configured to determine that the correlation between the fire operation data and the temporary power use operation data of the hazardous chemical enterprise is effective if the relevant ratio is greater than or equal to a preset ratio threshold;

[0141] An ineffective determination module, configured to determine that the correlation between the fire operation data and the temporary power use operation data of the hazardous chemical enterprise is ineffective if the relevant ratio is less than the preset ratio threshold.

[0142] In an embodiment of the present invention, the data quality detection module 804 includes:

[0143] A first straight line fitting module, configured to fit a first straight line to the fire operation data and / or the temporary power use operation data having a correlation;

[0144] A first deviation degree calculation module, configured to calculate the degree to which the fire operation data and / or the temporary power use operation data having a correlation deviate from the first straight line, and obtain a first deviation degree;

[0145] A second straight line fitting module, configured to fit a second straight line to the fire operation data and / or the temporary power use operation data having no correlation;

[0146] A second deviation degree calculation module, configured to calculate the degree to which the fire operation data and / or the temporary power use operation data having no correlation deviate from the second straight line, and obtain a second deviation degree;

[0147] A first quality determination module, configured to determine that the data quality of the production data complies with the management specification if the first deviation degree is less than or equal to a preset deviation threshold;

[0148] A second quality determination module, configured to determine that the data quality of the production data does not comply with the management specification if the first deviation degree is greater than the preset deviation threshold, and / or the second deviation degree is greater than or equal to the preset deviation threshold.

[0149] In an embodiment of the present invention, the data quality detection module 804 further includes:

[0150] A fluctuation range construction module, configured to construct a fluctuation range based on the slope of the first straight line initially;

[0151] A fluctuation range comparison module, configured to compare the slope of the first straight line with the fluctuation range when it is not initial;

[0152] A third quality determination module, configured to determine that the data quality of the production data complies with the management specification if the slope of the first straight line is within the fluctuation range;

[0153] A fourth quality determination module, configured to determine that the data quality of the production data does not meet the management specification if the slope of the first straight line is outside the fluctuation range.

[0154] The quality detection device for hazardous chemical operation data provided by the embodiments of the present invention can execute the quality detection method for hazardous chemical operation data provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the quality detection method for hazardous chemical operation data.

[0155] Embodiment III

[0156] See Figure 9 , which shows a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a blade server, a mainframe computer, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0157] As Figure 9 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor, and the processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0158] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0159] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the quality detection method for hazardous chemical operation data.

[0160] In some embodiments, the quality detection method for hazardous chemical operation data may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the quality detection method for hazardous chemical operation data described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the quality detection method for hazardous chemical operation data in any other suitable manner (e.g., by means of firmware).

[0161] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs, the one or more computer programs can be executed and / or interpreted on a programmable system including at least one programmable processor, the programmable processor can be a special or general-purpose programmable processor, can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0162] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0163] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0164] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0165] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0166] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0167] Embodiment 4

[0168] The embodiment of the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the quality detection method for hazardous chemical operation data provided in any embodiment of the present invention.

[0169] In the process of implementing the computer program product, the computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0170] It should be understood that various forms of the flow shown above can be used, reordering, adding or deleting steps. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0171] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A quality inspection method for hazardous chemical operation data, characterized in that Including: Querying the production data generated during the production of hazardous chemical enterprises in each time period; The production data includes hot work operation data and temporary electricity use operation data; Preprocessing the production data of the hazardous chemical enterprise; If the preprocessing is completed, calculating the correlation between the hot work operation data and the temporary electricity use operation data for the hazardous chemical enterprise; Detecting the data quality of the production data based on the correlation; 2. The method according to claim 1, wherein The preprocessing of the production data of the hazardous chemical enterprise includes: For the hazardous chemical enterprise, performing content detection on a single piece of the production data to delete the production data with empty content; If the content detection is completed, performing anomaly detection on all the production data to delete the production data belonging to outliers; If the anomaly detection is completed, performing validity detection on all the production data as a whole to retain or delete all the production data; 3. The method according to claim 2, wherein The performing content detection on a single piece of the production data to delete the production data with empty content includes: Counting the first operation times of the hot work operation data and the second operation times of the temporary electricity use operation data for a single piece of the production data; If the first operation times is 0 and the second operation times is 0, determining that the content of the production data is empty and deleting the production data; If the first operation times is greater than 0 and / or the second operation times is greater than 0, determining that the content of the production data is not empty and retaining the production data; The performing anomaly detection on all the production data to delete the production data belonging to outliers includes: Clustering all the hot work operation data to mark normal points or abnormal points for the production data to which the hot work operation data belongs; Clustering all the temporary electricity use operation data to mark normal points or abnormal points for the production data to which the temporary electricity use operation data belongs; Determining the production data marked with at least one abnormal point as an outlier and deleting the production data; Determining the production data marked with two normal points as normal values and retaining the production data; The performing validity detection on all the production data as a whole to retain or delete all the production data includes: Counting the sample quantity of all the production data and calculating the density for the first operation times and / or the second operation times; If the sample quantity is less than a preset quantity threshold, or the density is greater than a preset density threshold, determining that all the production data is invalid as a whole and deleting all the production data; If the sample quantity is greater than or equal to a preset sample threshold and the density is less than or equal to a preset density threshold, determining that all the production data is valid as a whole and retaining all the production data; 4. The method according to claim 1, wherein The calculating the correlation between the hot work operation data and the temporary electricity use operation data for the hazardous chemical enterprise includes: Calculating the correlation coefficient between the hot work operation data and the temporary electricity use operation data for the hazardous chemical enterprise; Mapping the correlation coefficient to a correlation level; If the relevant level is less than a preset level threshold, it is determined that there is no correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise; If the relevant level is greater than or equal to the preset level threshold, the significance coefficient between the hot work operation data and the temporary power use operation data is calculated for the hazardous chemical enterprise; If the significance coefficient is less than or equal to a preset significance threshold, it is determined that there is a correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise.

5. The method according to claim 4, wherein When the correlation coefficient is greater than or equal to 0, the relevant level is positively correlated with the correlation coefficient; When the correlation coefficient is less than 0, the relevant level is negatively correlated with the correlation coefficient.

6. The method according to claim 4, characterized in that, The calculating of the correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise further includes: Counting the number of first enterprises of all the hazardous chemical enterprises, and the number of second enterprises of the hazardous chemical enterprises where there is a correlation between the hot work operation data and the temporary power use operation data; Calculating the ratio between the number of second enterprises and the number of first enterprises to obtain a correlation ratio; If the correlation ratio is greater than or equal to a preset ratio threshold, it is determined that the correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise is valid; If the correlation ratio is less than the preset ratio threshold, it is determined that the correlation between the hot work operation data and the temporary power use operation data for the hazardous chemical enterprise is invalid.

7. The method according to claim 4, characterized in that The detecting of the data quality of the production data based on the correlation includes: Fitting a first straight line to the hot work operation data and / or the temporary power use operation data where there is a correlation; Calculating the degree to which the hot work operation data and / or the temporary power use operation data where there is a correlation deviate from the first straight line to obtain a first deviation degree; Fitting a second straight line to the hot work operation data and / or the temporary power use operation data where there is no correlation; Calculating the degree to which the hot work operation data and / or the temporary power use operation data where there is no correlation deviate from the second straight line to obtain a second deviation degree; If the first deviation degree is less than or equal to a preset deviation threshold, it is determined that the data quality of the production data meets the management specifications; If the first deviation degree is greater than the preset deviation threshold, and / or the second deviation degree is greater than or equal to the preset deviation threshold, it is determined that the data quality of the production data does not meet the management specifications.

8. The method according to claim 7, wherein The detecting of the data quality of the production data based on the correlation further includes: Initially, constructing a fluctuation range based on the slope of the first straight line; At non-initial times, comparing the slope of the first straight line with the fluctuation range; If the slope of the first straight line is within the fluctuation range, it is determined that the data quality of the production data meets the management specifications; If the slope of the first straight line is outside the fluctuation range, it is determined that the data quality of the production data does not meet the management specifications.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to perform the quality detection method of hazardous chemical operation data according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the quality detection method of hazardous chemical operation data according to any one of claims 1-8 is implemented.

Images