Group standard spot check optimization method and system based on big data analysis

Abstract

The application discloses a group standard spot check optimization method and system based on big data analysis, and relates to the technical field of group spot check optimization management.The group standard spot check optimization method based on big data analysis comprises the following steps: quality inspection data quality analysis, spot check visual analysis and visual optimization judgment.The application evaluates the data quality of food quality inspection data to determine whether to perform spot check visualization, then evaluates the effect of spot check visualization to obtain a spot check visualization evaluation value, judges whether to perform visual optimization based on the spot check visualization evaluation value, and finally evaluates the effect of visual optimization to determine whether to perform spot check storage, thereby improving the visualization quality of spot check data in the process of group spot check of food quality, and solving the problem of low visualization quality of spot check data in the process of group spot check of food quality in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of group sampling optimization management, and particularly relates to a group standard sampling optimization method and system based on big data analysis. BACKGROUND

[0002] Group standards play a very important role in many industries (such as manufacturing, food safety, etc.). They are usually developed by industry associations, academic organizations, expert groups or joint enterprises, aiming to improve the quality and safety of industry products or services, and regulate market behavior. Sampling as a supervision means can screen and detect a large number of production or service samples to determine whether they meet the predetermined standards. Sampling usually checks the quality, compliance, etc. of a part of samples through random sampling or directional sampling in the case that it is not possible to conduct a comprehensive inspection of all samples. In recent years, with the rapid development of information technology, big data analysis has become an important tool and is widely used in various industries. Big data integrates and analyzes information from different channels (such as enterprise production data, market feedback, historical sampling data, etc.), thereby accurately revealing the nature of the problem and optimizing sampling accordingly.

[0003] The existing group standard sampling based on big data analysis integrates data from different sources to establish a unified data platform, and uses big data technology for data cleaning, storage and management. Random sampling is performed using big data technology, and directional sampling can also be performed based on specific rules. Based on historical data and standard requirements, data mining techniques (such as clustering analysis, regression analysis, machine learning, etc.) are used to identify possible abnormal behaviors, and real-time data is combined to perform intelligent and automated sampling processes. Through data collection, intelligent analysis, predictive modeling and real-time monitoring, the efficiency and accuracy of sampling are improved, the sampling strategy is dynamically adjusted, the sampling cost is reduced, and the comprehensiveness and effectiveness of supervision are improved.

[0004] For example, the food risk prediction method, device, equipment and storage medium disclosed in the invention patent announcement with the announcement number CN112101819B include: based on the multidimensional feature vectors of each food as the input of the food risk preset model, the next month prediction sampling unqualified rate of each food is obtained, and then the food subcategory name with a next month prediction sampling unqualified rate higher than the unqualified rate threshold is further screened to form a next month sampling food subcategory name list, thereby improving the efficiency of the screening list.

[0005] For example, the invention patent announcement No. CN112749888B announces a multi-element random sampling method, system and device based on RANSAC algorithm, including: step S10: obtaining original enterprise standard data, and setting threshold for sampling model in the original enterprise standard data; Step S20: select M standards, calculate the correlation of the standards and each sampling condition, and the error within the set threshold is the inlier, that is, the matching is successful; Step S30: repeat step S20, step S30, after the iteration number reaches the preset value, save the model parameters corresponding to the maximum number of inliers as the final sampling model.

[0006] But in the process of implementing the technical scheme of the embodiments of the present application, it is found that the above-mentioned technology at least has the following technical problems:

[0007] The group standard sampling is usually completed by random sampling or specific range sampling. Among them, the equipment detection plays a crucial role in the sampling process of food quality detection, but due to the influence of various factors, the equipment detection may have inaccuracy problems.

[0008] In the prior art, data visualization as a powerful tool to help understand, analyze and present complex data also plays an important role in the sampling process of food quality detection. However, in actual operation, there are still some challenges, for example, if the amount of detection data is too large, it may lead to overcrowded charts that are difficult to interpret, and there is a problem of low quality of sampling data visualization in the group sampling process of food quality. SUMMARY

[0009] The embodiments of the present application provide a group standard sampling optimization method and system based on big data analysis, which solves the problem of low quality of sampling data visualization in the group sampling process of food quality in the prior art, and improves the quality of sampling data visualization in the group sampling process of food quality.

[0010] The embodiments of the present application provide a group standard sampling optimization method based on big data analysis, including the following steps: S1, obtaining food quality detection data of food to be sampled, and evaluating the data quality of the food quality detection data to determine whether to perform sampling visualization; S2, if the sampling visualization is performed, the effect of the sampling visualization is evaluated to obtain a sampling visualization evaluation value, and the sampling visualization evaluation value is used to evaluate the effect of the sampling visualization; S3, if the visualization optimization is performed, the effect of the visualization optimization is evaluated to determine whether to perform sampling storage.

[0011] Further, the food quality inspection data includes food biomass inspection data, food chemical quality inspection data, and food physical quality inspection data; the food biomass inspection data is used to reflect the microorganism detection situation of the food to be randomly inspected, and specifically includes bacterial detection content and pathogenic bacteria detection content; the food chemical quality inspection data is used to reflect the chemical property detection situation of the food to be randomly inspected, and specifically includes pH detection data and heavy metal detection content; the food physical quality inspection data is used to reflect the physical property detection situation of the food to be randomly inspected, and specifically includes moisture detection data and hardness detection data.

[0012] Further, the specific process of evaluating the data quality of the food quality inspection data to determine whether to perform random inspection visualization is: evaluating the data quality of the food quality inspection data to obtain a quality inspection data evaluation value, the quality inspection data evaluation value is used to quantitatively evaluate the data quality of the food quality inspection data; comparing the obtained quality inspection data evaluation value with a preset quality inspection quality threshold range obtained from a preset database; if the quality inspection data evaluation value is within the preset quality inspection quality threshold range obtained from the preset database, random inspection visualization is performed, and the effect of random inspection visualization is evaluated to obtain a random inspection visualization evaluation value; if the quality inspection data evaluation value is not within the preset quality inspection quality threshold range obtained from the preset database, random inspection visualization is not performed, and a preset personnel is reminded to calibrate the collection equipment and reacquire the food quality inspection data.

[0013] Further, the specific steps of evaluating the data quality of the food quality inspection data to obtain a quality inspection data evaluation value are as follows: performing statistical analysis on the obtained quality inspection data measurement values in the preset random inspection quality inspection time period to obtain quality inspection data correlation values, the quality inspection data correlation values including a quality inspection amount average value, a quality inspection amount maximum value, and a quality inspection amount minimum value, thereby obtaining a collection accuracy evaluation value and a data consistency evaluation value; obtaining environmental correction data in the preset random inspection quality inspection time period, combining the environmental correction data with environmental correction reference data obtained from the preset database to obtain a quality inspection environmental correction factor, the environmental correction data including an environmental electromagnetic interference average intensity, an environmental average air pressure, and an environmental average light intensity; the environmental correction reference data including a reference electromagnetic interference intensity, a reference environmental air pressure, a reference environmental light intensity, and an environmental correction weight, the environmental correction weight including an environmental electromagnetic correction weight, an environmental air pressure correction weight, and an environmental light intensity correction weight; obtaining quality inspection data quality correlation values in the preset random inspection quality inspection time period, the quality inspection data quality correlation values including a quality inspection collection missing data amount, a quality inspection collection total data amount, and a quality inspection collection delay; judging whether the ratio of the obtained quality inspection collection missing data amount to the quality inspection collection total data amount is less than a reference maximum collection missing ratio obtained from the preset database, if yes, combining quality inspection evaluation data with quality inspection evaluation reference data obtained from the preset database to obtain the quality inspection data evaluation value, otherwise, recording the quality inspection data evaluation value as 0; the quality inspection evaluation data including the quality inspection environmental correction factor, the collection accuracy evaluation value, the data consistency evaluation value, the quality inspection collection missing data amount, and the quality inspection collection delay; the quality inspection evaluation reference data including a reference collection maximum missing amount, a reference maximum collection delay, and a quality inspection evaluation weight; the quality inspection evaluation weight including a collection accuracy evaluation weight, a data consistency evaluation weight, a data missing evaluation weight, and a collection delay evaluation weight.

[0014] Further, the specific steps of evaluating the effect of the random inspection visualization to obtain a random inspection visualization evaluation value are as follows: obtaining quality inspection data measurement values before the random inspection visualization is performed and quality inspection data visualization values after the random inspection visualization is performed, processing the obtained data to obtain a visualization accuracy evaluation value; obtaining visualization evaluation data after the random inspection visualization is performed, the visualization evaluation data including an interaction success rate, a visualization information density, and a visualization interaction response time; judging whether the obtained interaction success rate is greater than an interaction success rate threshold value obtained from the preset database, if yes, combining the visualization evaluation data with visualization evaluation reference data obtained from the preset database to obtain the random inspection visualization evaluation value, otherwise, recording the random inspection visualization evaluation value as 0; the visualization evaluation reference data including a reference visualization maximum information density, a reference visualization maximum response time, and a visualization evaluation weight; the visualization evaluation weight including a visualization accuracy evaluation weight, a visualization information density evaluation weight, and a visualization interaction evaluation weight.

[0015] Further, the specific process for determining whether to perform the visualization optimization based on the spot check visualization evaluation value is: comparing the obtained spot check visualization evaluation value with a preset spot check visualization threshold range obtained from a preset database; if the spot check visualization evaluation value is within the preset spot check visualization threshold range obtained from the preset database, the visualization optimization is not performed, and it is continuously monitored whether the spot check visualization evaluation value is within the preset spot check visualization threshold range; if the spot check visualization evaluation value is not within the preset spot check visualization threshold range obtained from the preset database, the visualization optimization is performed.

[0016] Further, the specific process for the visualization optimization is: S21, determining whether the spot check visualization evaluation value is within the preset spot check visualization threshold range after performing the visualization interface adaptive optimization, if yes, stopping the visualization optimization, otherwise performing S22; S22, determining whether the spot check visualization evaluation value is within the preset spot check visualization threshold range after performing the visualization data optimization, if yes, stopping the visualization optimization, otherwise performing S23; S23, evaluating the effect of the visualization optimization to obtain a visualization optimization evaluation value, which is used for quantitatively evaluating the effect of the visualization optimization.

[0017] Further, the specific process for evaluating the effect of the visualization optimization to determine whether to perform the spot check storage is: evaluating the effect of the visualization optimization to obtain a visualization optimization evaluation value, which is used for quantitatively evaluating the effect of the visualization optimization; comparing the obtained visualization optimization evaluation value with a preset visualization optimization threshold range obtained from a preset database; if the visualization optimization evaluation value is within the preset visualization optimization threshold range obtained from the preset database, the spot check storage is performed; if the visualization optimization evaluation value is not within the preset visualization optimization threshold range obtained from the preset database, the spot check storage is not performed, and a preset personnel is reminded to replace the visualization tool.

[0018] Further, the specific steps for evaluating the effect of the visualization optimization to obtain a visualization optimization evaluation value are: obtaining optimization evaluation related data before and after performing the visualization optimization, the optimization evaluation related data including a visualization information density, an optimization response average speed, an optimization spot check visualization evaluation value, an optimization memory maximum usage, and an optimization visualization information density; combining the optimization evaluation related data with optimization evaluation reference data obtained from a preset database to perform a weighted summation operation with corresponding optimization evaluation weights to obtain the visualization optimization evaluation value; the optimization evaluation reference data including a reference maximum response speed, a spot check visualization evaluation value threshold, a reference maximum memory usage, and a reference visualization maximum information density; the optimization evaluation weights including a response speed optimization weight, an effect optimization weight, a resource consumption optimization weight, and an information density optimization weight.

[0019] The embodiment of the application provides a group standard spot check optimization system based on big data analysis, comprising: a quality inspection data quality analysis module, a spot check visualization analysis module and a visualization optimization judgment module; the quality inspection data quality analysis module is used for acquiring food quality inspection data of food to be spot checked, and evaluating data quality of the food quality inspection data to determine whether to perform spot check visualization; the spot check visualization analysis module is used for, if the spot check visualization is performed, evaluating an effect of the spot check visualization to obtain a spot check visualization evaluation value, and judging whether to perform visualization optimization based on the spot check visualization evaluation value, the spot check visualization evaluation value being used for quantifying the effect of the spot check visualization comprehensively; and the visualization optimization judgment module is used for, if the visualization optimization is performed, evaluating an effect of the visualization optimization to determine whether to perform spot check storage.

[0020] The one or more technical solutions provided in the embodiment of the application have at least the following technical effects or advantages:

[0021] 1. By evaluating data quality of food quality inspection data to determine whether to perform spot check visualization, then evaluating an effect of the spot check visualization to obtain a spot check visualization evaluation value, judging whether to perform visualization optimization based on the spot check visualization evaluation value, and finally evaluating an effect of the visualization optimization to determine whether to perform spot check storage, the analysis and judgment of spot check data visualization quality are realized, and the improvement of spot check data visualization quality in the group spot check process of food quality is realized, thereby effectively solving the problem of low spot check data visualization quality in the group spot check process of food quality in the prior art.

[0022] 2. By processing the acquired quality inspection data measurement value and quality inspection data visualization value to obtain a visualization accuracy evaluation value, and simultaneously acquiring visualization evaluation data after performing spot check visualization, then judging whether the obtained interaction success rate is greater than an interaction success rate threshold value acquired from a preset database, if yes, combining the visualization evaluation data with visualization evaluation reference data acquired from the preset database to obtain a spot check visualization evaluation value, otherwise, setting the spot check visualization evaluation value as 0, the numerical evaluation of the spot check visualization effect is realized, and more accurate evaluation of the spot check visualization effect is realized.

[0023] 3. By acquiring optimization evaluation related data before and after performing visualization optimization, then combining the optimization evaluation related data with optimization evaluation reference data acquired from a preset database, and performing weighted summation operation on the corresponding optimization evaluation weight to obtain a visualization optimization evaluation value, the numerical evaluation of the visualization optimization effect is realized, and more accurate evaluation of the visualization optimization effect is realized. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1A flowchart illustrating the group standard spot check optimization method based on big data analysis provided in this application embodiment;

[0025] Figure 2 A schematic diagram of the structure of the group standard spot check optimization system based on big data analysis provided in the embodiments of this application. Detailed Implementation

[0026] This application provides a group standard sampling inspection optimization method and system based on big data analysis, which solves the problem of low visualization quality of sampling data in the existing technology during group sampling inspections of food quality. It obtains food quality inspection data of the food to be inspected and evaluates the data quality to determine whether to perform sampling inspection visualization. If sampling inspection visualization is performed, the effect of the visualization is evaluated to obtain a sampling inspection visualization evaluation value. Based on the evaluation value, it is determined whether to perform visualization optimization. Finally, if visualization optimization is performed, the effect of the optimization is evaluated to determine whether to perform sampling inspection storage. This improves the visualization quality of sampling data during group sampling inspections of food quality.

[0027] The technical solution in this application embodiment aims to address the problem of low data visualization quality during group sampling inspections of food quality. The overall approach is as follows:

[0028] By evaluating the data quality of food quality inspection data to determine whether to perform random inspection visualization, then determining whether to perform visualization optimization based on the random inspection visualization evaluation value, and finally evaluating the effect of visualization optimization to determine whether to perform random inspection storage, the effect of improving the visualization quality of random inspection data during group random inspections of food quality is achieved.

[0029] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0030] like Figure 1 The diagram shows a flowchart of a group standard sampling optimization method based on big data analysis provided in this application embodiment. The method includes the following steps: S1, obtaining food quality inspection data of the food to be sampled, and evaluating the data quality of the food quality inspection data to determine whether to perform sampling visualization; S2, if sampling visualization is performed, evaluating the effect of sampling visualization to obtain a sampling visualization evaluation value, and determining whether to perform visualization optimization based on the sampling visualization evaluation value, the sampling visualization evaluation value being used to comprehensively quantify the effect of sampling visualization; S3, if visualization optimization is performed, evaluating the effect of visualization optimization to determine whether to perform sampling storage.

[0031] In this embodiment, the food to be sampled includes perishable food, such as fruits, vegetables, seafood, dairy products, etc., which are prone to spoilage, decay, and loss of nutritional value; after food processing is completed, the government or industry regulatory department conducts food quality detection through regular or random sampling to ensure food safety and compliance, and obtains food quality detection data to more clearly view the quality detection of the food to be sampled, so as to realize timely intervention. Food quality detection data often has the characteristics of multi-dimensionality and unstructuredness, and as the amount of food quality detection data increases, food quality sampling detection results can be submerged in a large amount of numerical data, making it difficult for industry regulators to quickly identify food quality problems. The method of the present application not only helps to improve the accuracy of group sampling of food quality and reduce resource waste, but also provides support for decision-making in terms of compliance and trend analysis.

[0032] It should be noted that the food quality detection data includes food biological quality detection data, food chemical quality detection data, and food physical quality detection data; wherein the food biological quality detection data is used to reflect the microbial detection of the food to be sampled, and specifically includes bacterial detection content and pathogenic bacteria detection content; specifically, the bacterial detection content is obtained by an automatic bacterial counter (such as a microbial culture counter or a fluorescent bacterial counter), and the pathogenic bacteria detection content is obtained by a polymerase chain reaction instrument.

[0033] The food chemical quality detection data is used to reflect the chemical property detection of the food to be sampled, and specifically includes pH detection data and heavy metal detection content; specifically, the pH detection data is obtained by a pH meter, and the heavy metal detection content is obtained by an atomic absorption spectrometer.

[0034] The food physical quality detection data is used to reflect the physical property detection of the food to be sampled, and specifically includes moisture detection data and hardness detection data; specifically, the moisture detection data is obtained by a Karl Fischer moisture titrator, and the hardness detection data is obtained by a texture analyzer.

[0035] By obtaining the food quality detection data of the food to be sampled, the data quality analysis of the food quality detection data is realized, and based on the data quality analysis result, it is judged whether to perform sampling visualization and visualization optimization, thereby realizing the improvement of the reliability of the sampling data in the group sampling process of the food quality.

[0036] Further, the specific process for evaluating the data quality of the food quality inspection data to determine whether to perform spot check visualization is as follows: evaluating the data quality of the food quality inspection data to obtain a quality inspection data evaluation value, the quality inspection data evaluation value being used to quantitatively evaluate the data quality of the food quality inspection data; comparing the obtained quality inspection data evaluation value with a preset quality inspection quality threshold range obtained from a preset database; if the quality inspection data evaluation value is within the preset quality inspection quality threshold range obtained from the preset database, performing spot check visualization and evaluating the effect of the spot check visualization to obtain a spot check visualization evaluation value; if the quality inspection data evaluation value is not within the preset quality inspection quality threshold range obtained from the preset database, not performing spot check visualization and reminding a preset person to calibrate a collection device and reacquire food quality inspection data.

[0037] In the present embodiment, the preset quality inspection quality threshold range is set by a professional according to a standard in the field, for example, the preset quality inspection quality threshold range is set to 0.70 to 1; wherein the spot check visualization is realized by a visualization tool (such as Power BI, Python (Matplotlib, Seaborn, Plotly, Altair), etc.), for example, a visualization chart such as a column chart, a line chart, etc. is drawn by using Matplotlib in Python; by combining the preset quality inspection quality threshold range for judgment and performing spot check visualization, more accurate judgment of the data quality in the food quality group spot check process is realized, and the accuracy of the spot check data visualization in the food quality group spot check process is improved.

[0038] Further, the specific steps for evaluating the data quality of the food quality inspection data to obtain a quality inspection data evaluation value are as follows: statistically analyzing the obtained quality inspection data measurement values in the preset spot check inspection time period to obtain quality inspection data related values, the quality inspection data related values including a quality inspection quantity average value, a quality inspection quantity maximum value and a quality inspection quantity minimum value, thereby obtaining a collection accuracy evaluation value (i.e. the ) in the quality inspection data evaluation value and a data consistency evaluation value (i.e. the ) in the quality inspection data evaluation value; obtaining environmental correction data in the preset spot check inspection time period, combining the environmental correction data with environmental correction reference data obtained from a preset database to obtain a quality inspection environmental correction factor (i.e. the ), the environmental correction data includes environmental electromagnetic interference average intensity, environmental average air pressure, and environmental average light intensity; the environmental correction reference data includes reference electromagnetic interference intensity, reference environmental air pressure, reference environmental light intensity, and environmental correction weight, the environmental correction weight includes environmental electromagnetic correction weight, environmental air pressure correction weight, and environmental light intensity correction weight; the quality inspection data quality related value in the preset spot check quality inspection time period is acquired, the quality inspection data quality related value includes quality inspection acquisition missing data quantity, quality inspection acquisition total data quantity, and quality inspection acquisition delay; whether the ratio of the acquired quality inspection acquisition missing data quantity and the quality inspection acquisition total data quantity is smaller than the reference maximum acquisition missing ratio acquired from the preset database is judged, if yes, the quality inspection evaluation data is combined with the quality inspection evaluation reference data acquired from the preset database to obtain the quality inspection data evaluation value, otherwise, the quality inspection data evaluation value is recorded as 0; the quality inspection evaluation data includes quality inspection environmental correction factor, acquisition accuracy evaluation value, data consistency evaluation value, quality inspection acquisition missing data quantity, and quality inspection acquisition delay; the quality inspection evaluation reference data includes reference acquisition maximum missing quantity, reference maximum acquisition delay, and quality inspection evaluation weight; the quality inspection evaluation weight includes acquisition accuracy evaluation weight, data consistency evaluation weight, data missing evaluation weight, and acquisition delay evaluation weight.

[0039] The method for obtaining the quality inspection data evaluation value is as follows:

[0040] ,

[0041] ,

[0042] ,

[0043] ;

[0044] In the formula, CCJ represents the quality inspection data evaluation value, represents the quality inspection environmental correction factor, represents the environmental electromagnetic correction weight, represents the environmental air pressure correction weight, represents the environmental light intensity correction weight, represents the acquisition accuracy evaluation weight, represents the data consistency evaluation weight, represents the data missing evaluation weight, represents the acquisition delay evaluation weight, SQ represents the quality inspection acquisition missing data quantity, and SA represents the quality inspection acquisition total data quantity, represents the reference maximum acquisition missing ratio, represents the acquisition accuracy evaluation value, represents the data consistency evaluation value, represents the reference acquisition maximum missing quantity, and ST represents the quality inspection acquisition delay, represents the reference maximum acquisition delay, n represents the number of types of food quality inspection data, N represents the total number of food quality inspection data types, N = 6, m represents the number of acquisition times of food quality inspection data in the preset sampling inspection time period, M represents the total number of acquisition times of food quality inspection data in the preset sampling inspection time period, represents the quality inspection data measurement value of the nth type of food quality inspection data acquired for the mth time in the preset sampling inspection time period, represents the average value of the quality inspection data of the nth type of food quality inspection data, represents the maximum value of the quality inspection data of the nth type of food quality inspection data, represents the minimum value of the quality inspection data of the nth type of food quality inspection data, represents the average intensity of environmental electromagnetic interference in the preset sampling inspection time period, represents the reference electromagnetic interference intensity, represents the average atmospheric pressure in the preset sampling inspection time period, represents the reference atmospheric pressure, represents the average light intensity in the preset sampling inspection time period, represents the reference light intensity.

[0045] In this embodiment, the preset sampling inspection time period is a preset time period for acquiring food quality inspection data of a food to be sampled, and the quality inspection data measurement value is a measurement value of the food quality inspection data in the preset sampling inspection time period; the average value of the quality inspection data is obtained by statistical analysis of the quality inspection data measurement value by the np.mean function of the numpy library in Python; the maximum value and the minimum value of the quality inspection data are obtained by statistical analysis of the quality inspection data measurement value by the MAX function and the MIN function of Google Sheets.

[0046] The environmental electromagnetic interference intensity is obtained by an electromagnetic field strength meter, the environmental atmospheric pressure is obtained by a barometer, and the environmental light intensity is obtained by a light meter; the environmental correction data is obtained by statistical analysis of the environmental electromagnetic interference intensity, the environmental atmospheric pressure, and the environmental light intensity by the np.mean function of the numpy library in Python, the units of the average intensity of environmental electromagnetic interference and the reference electromagnetic interference intensity are consistent, both are microtesla; the units of the average atmospheric pressure and the reference atmospheric pressure are consistent, both are pascals; the units of the average light intensity and the reference light intensity are consistent, both are lux.

[0047] The reference electromagnetic interference intensity is represented by the sum and average of the collected historical environmental electromagnetic interference intensity, the reference atmospheric pressure is represented by the sum and average of the collected historical environmental atmospheric pressure, and the reference light intensity is represented by the sum and average of the collected historical environmental light intensity.

[0048] The environmental electromagnetic interference correction weight, environmental air pressure correction weight, and environmental light intensity correction weight are used to describe the influence of the average intensity of environmental electromagnetic interference, the average environmental air pressure, and the average environmental light intensity on the quality inspection environment correction factor, respectively. They can be directly obtained from the preset database. For example, the real-time average intensity of environmental electromagnetic interference, the average environmental air pressure, and the average environmental light intensity can be input into the preset mapping set in the database to obtain the corresponding weights. The mapping relationship is one-to-one. In this example, the values ​​are all in the range of [0, 1], and the sum of the environmental electromagnetic interference correction weight, the environmental air pressure correction weight, and the environmental light intensity correction weight is 1.

[0049] The SCADA (Supervisory Control and Data Acquisition) system is used to obtain the amount of missing data, the total amount of data collected, and the data acquisition delay during quality inspection. The SCADA system provides an API (Application Programming Interface) to retrieve the amount of missing data and the total amount of data collected. The data acquisition delay is calculated by recording the start and end timestamps of the data acquisition. The units for the amount of missing data, the total amount of data collected, and the maximum reference missing data are all the same: items. The units for the data acquisition delay and the maximum reference acquisition delay are also the same: milliseconds. The maximum reference missing data is represented by the maximum historical missing data, and the maximum historical acquisition delay is represented by the maximum reference acquisition delay. The maximum reference missing data ratio is set by professionals according to industry standards; for example, it might be set to 5%.

[0050] The weights for accurate collection assessment, data consistency assessment, data missing assessment, and collection delay assessment are all within the range of [0, 1] and their sum is 1. The real-time accurate collection assessment value, data consistency assessment value, the amount of missing data in quality inspection collection, and the quality inspection collection delay are input into a preset mapping set in the database to obtain the corresponding weights. These weights describe the degree of influence of the accurate collection assessment value, data consistency assessment value, the amount of missing data in quality inspection collection, and the quality inspection collection delay on the quality inspection data assessment value. The mapping relationship can be one-to-one or many-to-one.

[0051] The quality inspection data evaluation value is used for quantitatively evaluating the data quality of the food quality inspection data, wherein the collection precision evaluation value, the data consistency evaluation value, the quality inspection collection missing data amount and the quality inspection collection delay all have an influence on the quality inspection data evaluation value, specifically, when the ratio of the quality inspection collection missing data amount to the total quality inspection collection data amount is greater than or equal to the reference maximum collection missing ratio, the quality inspection data evaluation value is 0; when the ratio of the quality inspection collection missing data amount to the total quality inspection collection data amount is less than the reference maximum collection missing ratio, with the decrease of the collection precision evaluation value, the data consistency evaluation value, the quality inspection collection missing data amount and the quality inspection collection delay, the quality inspection data evaluation value increases accordingly.

[0052] In addition, the quality inspection data evaluation value contains multiple parameters, and each parameter is related to each other and not independent. For example, the environmental average air pressure has an influence on the gas flow and some chemical reactions (such as the gas injection process in ICP-MS), thereby having an influence on the heavy metal analysis and other detection processes, resulting in an increase in the deviation of the heavy metal detection content, i.e. the quality inspection data measurement value, from the average value of the quality inspection amount, and further causing the quality inspection data evaluation value to decrease; in addition, with the increase of the quality inspection collection delay, the quality inspection collection missing data amount increases, and further causes the quality inspection data evaluation value to decrease; at the same time, the environmental electromagnetic interference average intensity, the environmental average air pressure, the environmental average light intensity and the quality inspection collection delay are also related, for example, the fluctuations of the environmental average air pressure and the environmental average light intensity can cause the response time of the data collection equipment to become longer, thereby causing the quality inspection collection delay to increase, and further causing the quality inspection data evaluation value to decrease.

[0053] Therefore, considering the correlation and mutual influence between various factors, the quality inspection data evaluation value is obtained through quantitative analysis, the data quality numerical evaluation of the food quality inspection data is realized, the data quality in the food quality group sampling process is judged through numerical evaluation, and the accuracy of the data in the sampling visualization in the group sampling process of the food quality is improved.

[0054] Further, the specific steps of evaluating the effect of the sampling visualization to obtain the sampling visualization evaluation value are as follows: obtaining the quality inspection data measurement value before the sampling visualization is performed and the quality inspection data visualization value after the sampling visualization is performed, processing the obtained data to obtain the visualization accuracy evaluation value (i.e. the sampling visualization evaluation value in the sampling visualization evaluation value), and obtaining the sampling visualization evaluation value by combining the visualization accuracy evaluation value and the quality inspection data evaluation value. ); obtaining the visualization evaluation data after performing the spot check visualization, the visualization evaluation data including an interaction success rate, a visualization information density, and a visualization interaction response time; determining whether the obtained interaction success rate is greater than an interaction success rate threshold value obtained from a preset database, and if yes, combining the visualization evaluation data with visualization evaluation reference data obtained from the preset database to obtain a spot check visualization evaluation value, otherwise, recording the spot check visualization evaluation value as 0; the visualization evaluation reference data including a reference visualization maximum information density, a reference visualization maximum response time, and a visualization evaluation weight; the visualization evaluation weight including a visualization accuracy evaluation weight, a visualization information density evaluation weight, and a visualization interaction evaluation weight.

[0055] The method for obtaining the spot check visualization evaluation value is as follows:

[0056] ,

[0057] ,

[0058] In the formula, CCK represents the spot check visualization evaluation value, represents the visualization accuracy evaluation weight, represents the visualization information density evaluation weight, represents the visualization interaction evaluation weight, represents the visualization accuracy evaluation value, represents the visualization information density, represents the reference visualization maximum information density, represents the visualization interaction response time, represents the reference visualization maximum response time, represents the interaction success rate, represents the interaction success rate threshold value, n represents the number of types of food quality inspection data, N represents the total number of types of food quality inspection data, N = 6, and m represents the number of times of collecting food quality inspection data in a preset spot check quality inspection time period, M represents the total number of times of collecting food quality inspection data in the preset spot check quality inspection time period, represents the quality inspection data measurement value of the nth type of food quality inspection data collected for the mth time in the preset spot check quality inspection time period, represents the quality inspection data visualization value of the nth type of food quality inspection data collected for the mth time in the preset spot check quality inspection time period.

[0059] In the embodiment, the quality inspection data visualization value, i.e., the quality inspection data measurement value after performing the sampling visualization, the interaction success rate (i.e., the ratio of the number of successful interactions of the user with the data in the visualization interface to the total number of interactions) is obtained through a user behavior analysis tool (such as Google Analytics), the visualization information density (i.e., the amount of information displayed in a unit area in the visualization interface) is obtained through a data density analysis tool (such as Tableau or D3.js), the visualization interaction response time (i.e., the difference between the end time and the start time after the user triggers the interaction) is obtained through a front-end performance monitoring tool (such as Google Lighthouse, WebPageTest, etc.), and the interaction success rate threshold is set by a professional according to the standard in the field, for example, the interaction success rate threshold is set to 95%.

[0060] The maximum value of the collected historical visualization information density represents the reference visualization maximum information density, and the maximum value of the collected historical visualization interaction response time represents the reference visualization maximum response time.

[0061] In the example, the visualization accuracy evaluation weight, the visualization information density evaluation weight, and the visualization interaction evaluation weight all have a value range of [0, 1], and the sum is 1. Specifically, when used, the corresponding weights can be directly obtained from a preset database, for example, by inputting the real-time visualization accuracy evaluation value, the visualization information density, and the visualization interaction response time into the preset mapping set in the database to obtain the corresponding weights. The mapping relationship therein can be a one-to-one correspondence or a many-to-one relationship. The visualization accuracy evaluation weight, the visualization information density evaluation weight, and the visualization interaction evaluation weight are respectively used to reflect the influence degree of the visualization accuracy evaluation value, the visualization information density, and the visualization interaction response time on the sampling visualization evaluation value.

[0062] The sampling visualization evaluation value is used to comprehensively quantify the effect of the sampling visualization. The sampling visualization evaluation value contains multiple parameters, specifically, the visualization accuracy evaluation value (wherein the quality inspection data measurement value and the quality inspection data visualization value), the visualization information density, the visualization interaction response time, and the interaction success rate all affect the sampling visualization evaluation value. For example, when the interaction success rate is less than or equal to the interaction success rate threshold, the sampling visualization evaluation value is 0; when the interaction success rate is greater than the interaction success rate threshold, as the visualization accuracy evaluation value decreases, the sampling visualization evaluation value increases, and as the visualization information density and the visualization interaction response time increase, the sampling visualization evaluation value also increases.

[0063] It should be added that the various parameters in the spot check visualization evaluation value are related, not independent, for example, as the visualization information density increases (not more than the maximum information density of the reference visualization), the correlation between different dimensions increases, and the user can view multiple data levels and dimensions at the same time, for example, the quality inspector can view the food quality inspection data of heavy metal detection content and hardness detection data at the same time. In addition, as the visualization information density increases, the interaction success rate increases, and as the interaction success rate increases, the visualization interaction response time decreases, thereby increasing the spot check visualization evaluation value. At the same time, as the deviation between the quality inspection data measurement value and the quality inspection data visualization value decreases, the visualization accuracy evaluation value decreases, thereby increasing the spot check visualization evaluation value.

[0064] In summary, the algorithm considers the correlation and mutual influence between various factors, and obtains the spot check visualization evaluation value through comprehensive analysis, realizes the numerical evaluation of the spot check visualization effect, judges the spot check visualization effect through numerical evaluation, and further realizes more accurate evaluation of the spot check data visualization effect in the food quality group spot check process.

[0065] Further, the specific process of judging whether to perform visualization optimization based on the spot check visualization evaluation value is: comparing the obtained spot check visualization evaluation value with the preset spot check visualization threshold range obtained from the preset database; if the spot check visualization evaluation value is within the preset spot check visualization threshold range obtained from the preset database, no visualization optimization is performed, and whether the spot check visualization evaluation value is within the preset spot check visualization threshold range is continuously monitored; if the spot check visualization evaluation value is not within the preset spot check visualization threshold range obtained from the preset database, visualization optimization is performed.

[0066] In the embodiment, the preset spot check visualization threshold range is set by professionals according to the standards in the field, for example, the preset spot check visualization threshold range is set to 2.0 to 3.0; by combining the preset spot check visualization threshold range for judgment, more accurate judgment of the spot check visualization effect in the food quality group spot check process is realized.

[0067] It should be added that the specific process of visualization optimization is: S21, judging whether the spot check visualization evaluation value is within the preset spot check visualization threshold range after performing the visualization interface adaptive optimization, if yes, stopping the visualization optimization, otherwise performing S22; S22, judging whether the spot check visualization evaluation value is within the preset spot check visualization threshold range after performing the visualization data optimization, if yes, stopping the visualization optimization, otherwise performing S23; S23, evaluating the effect of the visualization optimization to obtain a visualization optimization evaluation value, which is used for quantitative evaluation of the effect of the visualization optimization.

[0068] In the embodiment, the self-adaptive optimization of the visual interface is realized by CSS3 (Cascading Style Sheets Level 3 Media Queries) media query or Bootstrap to create a responsive layout. Specifically, the CSS3 media query can automatically adjust the layout of charts, graphics and interface elements according to the screen size. By using a distributed computing framework such as Dask or Apache Spark, batch processing and loading of big data are performed to avoid loading all data at once, reduce memory occupation and realize visual data optimization. By using the debouncing technology and data lazy loading, the visual interaction optimization is realized. By performing the visual optimization, the improvement of the visual quality in the case of abnormal visual effect in the group sampling process of food quality sampling is realized.

[0069] Further, the effect of the visual optimization is evaluated to determine whether to perform the specific process of sampling storage, which comprises: evaluating the effect of the visual optimization, obtaining a visual optimization evaluation value, and using the visual optimization evaluation value to quantitatively evaluate the effect of the visual optimization; comparing the obtained visual optimization evaluation value with a preset visual optimization threshold range obtained from a preset database; if the visual optimization evaluation value is within the preset visual optimization threshold range obtained from the preset database, performing the sampling storage; and if the visual optimization evaluation value is not within the preset visual optimization threshold range obtained from the preset database, not performing the sampling storage and reminding the preset personnel to replace the visual tool.

[0070] In the embodiment, the preset visual optimization threshold range is set by the professional personnel according to the standards in the field, for example, the preset visual optimization threshold range is set to 3.0 to 4.0. The food quality inspection data is stored by using a database (such as MySQL, PostgreSQL, MongoDB, etc.) to realize the sampling storage. By combining the preset visual optimization threshold range for judgment, the more accurate judgment of the visual optimization effect in the case of visual abnormality in the group sampling process of food quality is realized.

[0071] Further, the effect of the visualization optimization is evaluated to obtain a visualization optimization evaluation value, and the specific steps are as follows: obtaining optimization evaluation related data before and after the visualization optimization is performed, the optimization evaluation related data including visualization information density, optimization response average speed, optimization spot check visualization evaluation value, optimization maximum memory usage, and optimization visualization information density; combining the optimization evaluation related data with optimization evaluation reference data obtained from a preset database, and performing weighted summation operation on the corresponding optimization evaluation weights to obtain the visualization optimization evaluation value; the optimization evaluation reference data including reference maximum response speed, spot check visualization evaluation value threshold, reference maximum memory usage, and reference maximum visualization information density; the optimization evaluation weights including response speed optimization weight, effect optimization weight, resource consumption optimization weight, and information density optimization weight.

[0072] The method for obtaining the visualization optimization evaluation value is as follows:

[0073] ;

[0074] In the formula, CCY represents the visualization optimization evaluation value, represents the response speed optimization weight, represents the effect optimization weight, represents the resource consumption optimization weight, represents the information density optimization weight, represents the optimization response average speed, represents the reference maximum response speed, represents the optimization spot check visualization evaluation value, represents the spot check visualization evaluation value threshold, represents the reference maximum memory usage, represents the optimization maximum memory usage, represents the visualization information density, represents the reference maximum visualization information density, j represents the number of preset time points in a preset visualization optimization time period, J represents the total number of preset time points in the preset visualization optimization time period, represents the optimization visualization information density of the jth preset time point in the preset visualization optimization time period.

[0075] In the embodiment, the optimized response average speed is the average value of the response speed after the execution of the visual optimization, the response speed is obtained by a Web performance test tool (such as Google Lighthouse), the optimized response average speed is obtained by statistical analysis of the response speed by the np.mean function of the numpy library in Python, the optimized spot check visual evaluation value is the spot check visual evaluation value after the execution of the visual optimization, the optimized maximum memory usage is the maximum memory usage after the execution of the visual optimization, the maximum memory usage is obtained by the New Relic tool, and the optimized visual information density is the visual information density after the execution of the visual optimization.

[0076] The reference maximum response speed is represented by the maximum value of the collected historical response speed, the spot check visual evaluation value threshold is generally the maximum value of the preset spot check visual threshold range, and the reference maximum memory usage is represented by the sum and average of the collected historical optimized maximum memory usage.

[0077] The response speed optimization weight, the effect optimization weight, the resource consumption optimization weight, and the information density optimization weight are respectively used to describe the influence degree of the optimized response average speed, the optimized spot check visual evaluation value, the optimized maximum memory usage, and the optimized visual information density on the visual optimization evaluation value, and can be directly obtained from the preset database during use, for example, the real-time optimized response average speed, the optimized spot check visual evaluation value, the optimized maximum memory usage, and the optimized visual information density are input into the preset mapping set in the database to obtain the corresponding weights, the mapping relationship therein is one-to-one, the value range in the example is [0, 1], and the sum of the response speed optimization weight, the effect optimization weight, the resource consumption optimization weight, and the information density optimization weight is 1 in the example.

[0078] The visual optimization evaluation value is used to quantitatively evaluate the effect of the visual optimization, wherein the visual optimization evaluation value contains multiple parameters, and the parameters are related to each other and not independent, for example, as the deviation degree between the optimized visual information density and the reference maximum visual information density decreases, the optimized spot check visual evaluation value increases, and then the visual optimization evaluation value increases; in addition, as the optimized response average speed increases, the optimized spot check visual evaluation value also increases, and then the visual optimization evaluation value increases, and at the same time, as the optimized maximum memory usage decreases, the optimized response average speed increases, and then the visual optimization evaluation value also increases.

[0079] The algorithm considers the correlation and mutual influence between various factors through quantization, and obtains a visual optimization evaluation value through comprehensive analysis, realizes numerical evaluation of the visual optimization effect, judges the visual optimization effect through numerical evaluation, and realizes more accurate evaluation of the visual optimization effect of the food quality group sampling data.

[0080] As shown in Figure 2 The group standard sampling optimization system based on big data analysis provided by the embodiment of the application has the structure as shown in the figure. The group standard sampling optimization system based on big data analysis provided by the embodiment of the application comprises a quality inspection data quality analysis module, a sampling visualization analysis module, and a visual optimization judgment module. The quality inspection data quality analysis module is used to obtain food quality inspection data of food to be sampled, and evaluate the data quality of the food quality inspection data to determine whether to perform sampling visualization. The sampling visualization analysis module is used to evaluate the effect of sampling visualization to obtain a sampling visualization evaluation value if sampling visualization is performed, and determine whether to perform visual optimization based on the sampling visualization evaluation value. The sampling visualization evaluation value is used to quantitatively evaluate the effect of sampling visualization. The visual optimization judgment module is used to evaluate the effect of visual optimization to determine whether to perform sampling storage if visual optimization is performed.

[0081] In the embodiment, the food quality inspection data of food to be sampled is obtained, thereby realizing data quality analysis of the food quality inspection data. Whether to perform sampling visualization is determined based on the data quality analysis result, and whether to perform visual optimization and sampling storage is determined based on the sampling visualization evaluation value, thereby realizing improvement of the sampling data visualization quality in the group sampling process of food quality.

[0082] In summary, the embodiment of the application evaluates the data quality of the food quality inspection data to determine whether to perform sampling visualization, then evaluates the effect of sampling visualization to obtain a sampling visualization evaluation value, determines whether to perform visual optimization based on the sampling visualization evaluation value, and finally evaluates the effect of visual optimization to determine whether to perform sampling storage, thereby realizing analysis and judgment of the sampling data visualization quality, and further realizing improvement of the sampling data visualization quality in the group sampling process of food quality, and effectively solving the problem of low sampling data visualization quality in the group sampling process of food quality in the prior art.

[0083] Those skilled in the art will appreciate that embodiments of the present application can be devised for a variety of applications. It is intended that the present application be limited only by the scope of the appended claims, and it is intended that various modifications and alterations made by those skilled in the art be considered as within the scope of the present application. The embodiments of the present application will be described with reference to the attached drawings, wherein:

[0084] The present application is described in reference to the drawings using a flowchart and / or a block diagram of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0085] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0087] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to cover all such modifications and variations as fall within the scope of the present application.

[0088] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A group standard spot check optimization method based on big data analysis, characterized in that, The method comprises the following steps: S1, obtaining food quality inspection data of food to be sampled, and evaluating data quality of the food quality inspection data to determine whether to perform sampling visualization; S2, if sampling visualization is performed, evaluating an effect of the sampling visualization to obtain a sampling visualization evaluation value, and determining whether to perform visualization optimization based on the sampling visualization evaluation value, wherein the sampling visualization evaluation value is used to comprehensively quantify the effect of the sampling visualization; The specific steps of evaluating the effect of the sampling visualization to obtain the sampling visualization evaluation value are as follows: obtaining quality inspection data measurement values before the sampling visualization is performed and quality inspection data visualization values after the sampling visualization is performed, processing the obtained data to obtain a visualization accuracy evaluation value; obtaining visualization evaluation data after the sampling visualization is performed, wherein the visualization evaluation data comprises an interaction success rate, a visualization information density, and a visualization interaction response time; determining whether the obtained interaction success rate is greater than an interaction success rate threshold value obtained from a preset database, if yes, combining the visualization evaluation data with visualization evaluation reference data obtained from the preset database to obtain the sampling visualization evaluation value, and if no, recording the sampling visualization evaluation value as 0; the visualization evaluation reference data comprises a reference visualization maximum information density, a reference visualization maximum response time, and a visualization evaluation weight; the visualization evaluation weight comprises a visualization accuracy evaluation weight, a visualization information density evaluation weight, and a visualization interaction evaluation weight; S3, if visualization optimization is performed, evaluating an effect of the visualization optimization to determine whether to perform sampling storage.

2. The method of claim 1, wherein the method is based on big data analysis. The food quality inspection data comprises food biological quality inspection data, food chemical quality inspection data, and food physical quality inspection data; the food biological quality inspection data is used to reflect a microorganism detection situation of the food to be sampled, and specifically comprises a bacterial detection content and a pathogenic bacteria detection content; the food chemical quality inspection data is used to reflect a chemical property detection situation of the food to be sampled, and specifically comprises pH detection data and heavy metal detection content; the food physical quality inspection data is used to reflect a physical property detection situation of the food to be sampled, and specifically comprises moisture detection data and hardness detection data.

3. The method of claim 2, wherein the method further comprises: The specific process of evaluating the data quality of the food quality inspection data to determine whether to perform sampling visualization is as follows: evaluating the data quality of the food quality inspection data to obtain a quality inspection data evaluation value, wherein the quality inspection data evaluation value is used to quantitatively evaluate the data quality of the food quality inspection data; comparing the obtained quality inspection data evaluation value with a preset quality inspection quality threshold value range obtained from a preset database; if the quality inspection data evaluation value is within the preset quality inspection quality threshold value range obtained from the preset database, performing sampling visualization, and evaluating an effect of the sampling visualization to obtain a sampling visualization evaluation value; if the quality inspection data evaluation value is not within the preset quality inspection quality threshold value range obtained from the preset database, not performing sampling visualization, and reminding a preset person to calibrate a collection device and reacquire food quality inspection data.

4. The method of claim 3, wherein the group standard is optimized based on big data analysis. The specific steps of evaluating the data quality of the food quality inspection data to obtain the quality inspection data evaluation value are as follows: The statistical analysis of the measured values of the quality inspection data in the preset sampling inspection time period is performed to obtain quality inspection data correlation values, including quality inspection amount average value, quality inspection amount maximum value, and quality inspection amount minimum value, from which the collection accuracy evaluation value and the data consistency evaluation value are obtained; The environmental correction data in the preset sampling inspection time period is obtained, and the environmental correction data is combined with the environmental correction reference data obtained from the preset database to obtain a quality inspection environmental correction factor, the environmental correction data including environmental electromagnetic interference average intensity, environmental average air pressure, and environmental average light intensity; The environmental correction reference data includes reference electromagnetic interference intensity, reference environmental air pressure, reference environmental light intensity, and environmental correction weight, the environmental correction weight including environmental electromagnetic correction weight, environmental air pressure correction weight, and environmental light intensity correction weight; The quality inspection data quality correlation values in the preset sampling inspection time period are obtained, including quality inspection collection missing data amount, quality inspection collection total data amount, and quality inspection collection delay; It is judged whether the ratio of the obtained quality inspection collection missing data amount to the quality inspection collection total data amount is less than the reference maximum collection missing ratio obtained from the preset database, if yes, the quality inspection evaluation data is combined with the quality inspection evaluation reference data obtained from the preset database to obtain the quality inspection data evaluation value, otherwise, the quality inspection data evaluation value is recorded as 0; The quality inspection evaluation data includes quality inspection environmental correction factor, collection accuracy evaluation value, data consistency evaluation value, quality inspection collection missing data amount, and quality inspection collection delay; The quality inspection evaluation reference data includes reference collection maximum missing amount, reference maximum collection delay, and quality inspection evaluation weight; The quality inspection evaluation weight includes collection accuracy evaluation weight, data consistency evaluation weight, data missing evaluation weight, and collection delay evaluation weight.

5. The method of claim 1, wherein the method further comprises: The specific process of judging whether to perform visual optimization based on the sampling visualization evaluation value is as follows: The obtained sampling visualization evaluation value is compared with the preset sampling visualization threshold range obtained from the preset database; If the sampling visualization evaluation value is within the preset sampling visualization threshold range obtained from the preset database, no visual optimization is performed, and it is continuously monitored whether the sampling visualization evaluation value is within the preset sampling visualization threshold range; If the sampling visualization evaluation value is not within the preset sampling visualization threshold range obtained from the preset database, visual optimization is performed.

6. The group standard spot check optimization method based on big data analysis of claim 5, wherein, The specific process of visual optimization is as follows: S21, it is judged whether the sampling visualization evaluation value is within the preset sampling visualization threshold range after performing visual interface adaptive optimization, if yes, the visual optimization is stopped, otherwise, S22 is performed; S22, it is judged whether the sampling visualization evaluation value is within the preset sampling visualization threshold range after performing visual data optimization, if yes, the visual optimization is stopped, otherwise, S23 is performed; S23, the effect of visual optimization is evaluated to obtain a visual optimization evaluation value, which is used for quantitative evaluation of the effect of visual optimization.

7. The method of claim 1, wherein the method further comprises: determining a group standard based on the big data analysis; and determining a group standard deviation based on the big data analysis. The specific process of evaluating the effect of visual optimization to judge whether to perform sampling storage is as follows: The effect of the visualization optimization is evaluated to obtain a visualization optimization evaluation value, which is used for quantitatively evaluating the effect of the visualization optimization. The obtained visualization optimization evaluation value is compared with a preset visualization optimization threshold range obtained from a preset database. If the visualization optimization evaluation value is within the preset visualization optimization threshold range obtained from the preset database, spot check storage is performed. If the visualization optimization evaluation value is not within the preset visualization optimization threshold range obtained from the preset database, the spot check storage is not performed, and a preset personnel is reminded to replace the visualization tool.

8. The method of claim 7, wherein the method further comprises: The effect of the visualization optimization is evaluated to obtain a visualization optimization evaluation value, and the specific steps are as follows: Optimization evaluation related data before and after the visualization optimization is performed is obtained, and the optimization evaluation related data includes visualization information density, optimization response average speed, optimization spot check visualization evaluation value, optimization memory maximum usage, and optimization visualization information density. The optimization evaluation related data is combined with optimization evaluation reference data obtained from a preset database, and weighted summation operation is performed on the corresponding optimization evaluation weights to obtain the visualization optimization evaluation value. The optimization evaluation reference data includes reference maximum response speed, spot check visualization evaluation value threshold, reference maximum memory usage, and reference visualization maximum information density. The optimization evaluation weights include response speed optimization weight, effect optimization weight, resource consumption optimization weight, and information density optimization weight.

9. A group standard spot check optimization system based on big data analysis, characterized in that, It includes: A quality inspection data quality analysis module, a spot check visualization analysis module, and a visualization optimization judgment module. The quality inspection data quality analysis module is used to obtain food quality inspection data of food to be spot checked, evaluate the data quality of the food quality inspection data, and judge whether to perform spot check visualization. The spot check visualization analysis module is used to evaluate the effect of the spot check visualization to obtain a spot check visualization evaluation value if the spot check visualization is performed, and judge whether to perform visualization optimization based on the spot check visualization evaluation value, which is used for comprehensively quantifying the effect of the spot check visualization. The effect of the spot check visualization is evaluated to obtain a spot check visualization evaluation value, and the specific steps are as follows: The quality inspection data measurement value before the spot check visualization is performed and the quality inspection data visualization value after the spot check visualization is performed are obtained, and the obtained data is processed to obtain a visualization accuracy evaluation value. Visualization evaluation data after the spot check visualization is performed is obtained, and the visualization evaluation data includes an interaction success rate, visualization information density, and visualization interaction response time. It is judged whether the obtained interaction success rate is greater than an interaction success rate threshold value obtained from a preset database, and if so, the visualization evaluation data is combined with visualization evaluation reference data obtained from the preset database to obtain the spot check visualization evaluation value, otherwise, the spot check visualization evaluation value is recorded as 0. The visualization evaluation reference data includes reference visualization maximum information density, reference visualization maximum response time, and visualization evaluation weight. The visualization evaluation weight includes visualization accuracy evaluation weight, visualization information density evaluation weight, and visualization interaction evaluation weight. The visual optimization judgment module is configured to evaluate the effect of the visual optimization to determine whether to perform the spot check storage if the visual optimization is performed.

Images