Confidence sorting method and system for salt iodine content detection data

Abstract

The present invention relates to the field of food safety monitoring, and in particular to a confidence sorting method and system for salt iodine content detection data. The method comprises: performing correlation analysis on a preset influencing indicator set according to the detection process type to obtain an associated influencing indicator set; receiving an associated influencing indicator constraint interval; when detecting a salt sample, collecting the associated influencing indicator monitoring value time series information and comparing the constraint interval to obtain deviation vector time series information; counting the error mode value of the detection sample set that meets the deviation vector time series information; when the error mode value is less than the error threshold, the detection value is credibly identified; the detection value set with the credible identification is counted to obtain an iodine content confidence value and send it to the user end. The present application establishes a systematic data confidence sorting mechanism by comprehensively considering multi-dimensional associated influencing indicators, thereby effectively improving the reliability and accuracy of the salt iodine content detection results.

Description

Technical Field

[0001] The present invention relates to the field of food safety monitoring, and in particular to a confidence sorting method and system for salt iodine content detection data. Background Art

[0002] Currently, the iodine content of table salt is mainly tested using spectrophotometry, which measures the sample's absorbance at a specific wavelength and uses a standard curve to determine the iodine content. However, in actual testing, due to the influence of various factors such as the spectrophotometer's instrument performance, sample characteristics, environmental conditions, and operating procedures, the results of table salt iodine content tests often fluctuate and contain errors, resulting in low reliability and accuracy of the test results. Summary of the Invention

[0003] The present invention addresses the technical problem of low reliability and accuracy of iodine content detection results in table salt in the prior art, achieves the technical effect of improving the reliability and accuracy of iodine content detection results in table salt, and provides a confidence sorting method and system for iodine content detection data to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides a confidence sorting method for salt iodine content detection data, comprising: performing correlation analysis on a preset influencing indicator set according to the type of salt iodine content detection process to obtain an associated influencing indicator set; receiving an associated influencing indicator constraint interval of the associated influencing indicator set; when a salt sample is detected, collecting associated influencing indicator monitoring value time series information, comparing it with the associated influencing indicator constraint interval, and obtaining associated influencing indicator deviation vector time series information; counting the iodine content detection error mode value of the iodine content detection sample set that meets the associated influencing indicator deviation vector time series information; when the iodine content detection error mode value is less than the error threshold, the iodine content detection value of the salt sample is credibly identified; counting the iodine content detection value set of the salt sample with the credible identification, obtaining the salt iodine content confidence value and sending it to the user end.

[0006] In a second aspect, the present invention provides a confidence sorting system for salt iodine content detection data, comprising: a correlation analysis module, used to perform correlation analysis on a preset influencing indicator set according to the salt iodine content detection process type to obtain an associated influencing indicator set; a constraint interval receiving module, used to receive the associated influencing indicator constraint interval of the associated influencing indicator set; a deviation vector analysis module, used to collect the associated influencing indicator monitoring value time series information when the salt sample is detected, and compare it with the associated influencing indicator constraint interval to obtain the associated influencing indicator deviation vector time series information; an error mode statistics module, used to count the iodine content detection error mode value of the iodine content detection sample set that meets the associated influencing indicator deviation vector time series information; a detection value identification module, used to credibly identify the iodine content detection value of the salt sample when the iodine content detection error mode value is less than the error threshold; a confidence value statistics module, used to count the iodine content detection value set of the salt sample with a credible identification, obtain the salt iodine content confidence value and send it to the user end.

[0007] The beneficial effects of the present invention are:

[0008] Based on the type of salt iodine content testing process, a correlation analysis is performed on the preset influencing indicator set to obtain an associated influencing indicator set. For a specific testing process type, various factors that may affect the test results are analyzed, such as instrument factors (light source stability, detector performance, monochromator performance, wavelength accuracy), sample factors (uniformity, stability, concentration range), environmental factors (temperature stability, humidity stability, electromagnetic interference), and operational factors (measurement parameter settings, sample placement and operating specifications, data processing methods). Through correlation analysis, indicators with significant correlation with the test results are screened out to form an associated influencing indicator set, laying the foundation for subsequent data processing. The associated influencing indicator constraint intervals of the associated influencing indicator set are received. After determining the associated influencing indicator set, constraint intervals are set for each associated influencing indicator. These constraint intervals represent the reasonable fluctuation range of each indicator under normal testing conditions. The setting of the constraint interval can be based on theoretical analysis, historical data statistics, or expert experience, providing a basis for subsequent judgment of whether the testing process is stable. During the actual salt sample testing process, the values ​​of each associated influencing indicator are monitored in real time, and their time series information changing over time is recorded to obtain the time series information of the associated influencing indicator monitoring values. The time series information of the associated influencing indicator monitoring values ​​is compared with the associated influencing indicator constraint interval, and the deviation degree and direction of each indicator are calculated to form the deviation vector time series information, which reflects the stability of each influencing factor in the testing process.

[0009] Based on the obtained deviation vector time series information, a set of detection samples under a specific pattern of the deviation vector time series information of the associated influencing index is screened out, and the detection errors of these samples are statistically analyzed to obtain the mode value of the error distribution, thereby identifying the typical error pattern under specific disturbance conditions and providing a quantitative indicator for evaluating the reliability of the detection results. According to the obtained iodine content detection error mode value, it is compared with the preset error threshold to determine whether the detection result is reliable. When the iodine content detection error mode value is less than the error threshold, it indicates that under the current detection conditions, despite the fluctuations of various influencing factors, the detection result still has sufficient accuracy, so the detection value is marked as reliable data. The iodine content detection value set of salt samples that have passed the credibility assessment is statistically processed to calculate the iodine content confidence value of salt with high reliability, and the result is transmitted to the user end. This statistical method based on confidence sorting effectively eliminates the interference of unreliable data and improves the accuracy and reliability of the final result.

[0010] Through the above technical solution, confidence sorting of salt iodine content detection data is achieved, which effectively solves the problem of insufficient detection accuracy and reliability caused by neglecting the quality assessment of the detection process in traditional methods, and improves the reliability and accuracy of salt iodine content detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of a confidence sorting method for salt iodine content detection data provided by the present invention;

[0012] Figure 2 This is a schematic structural diagram of the confidence sorting system for salt iodine content detection data provided by the present invention.

[0013] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0014] Correlation analysis module 11, constraint interval receiving module 12, deviation vector analysis module 13, error mode statistics module 14, detection value identification module 15, confidence value statistics module 16. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0016] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0017] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0018] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a confidence sorting method for salt iodine content detection data, comprising:

[0019] S1. According to the type of salt iodine content detection process, perform correlation analysis on the preset influencing indicator set to obtain the associated influencing indicator set.

[0020] Specifically, during the salt iodine content detection process, the test results will be affected by a variety of factors. The preset influencing indicator set includes indicators that may affect the salt iodine content test results. These indicators can be divided into four categories: instrument factors, sample factors, environmental factors and operational factors. Instrument factors include light source stability, detector performance, monochromator performance and instrument wavelength accuracy; sample factors include sample uniformity, sample stability and sample concentration range; environmental factors include temperature stability, humidity stability and electromagnetic interference; operational factors include measurement parameter settings, sample placement and operation specifications, and data processing methods. Different salt iodine content detection process types (such as spectrophotometry, potentiometric titration, etc.) are affected to different degrees by different influencing indicators. Therefore, for specific salt iodine content detection process types, a correlation analysis is performed on the preset influencing indicator set to screen out indicators that are highly correlated with the test results of this specific process type, forming a set of associated influencing indicators.

[0021] Correlation analysis uses statistical methods to assess the correlation between each pre-defined influencing indicator and the test results, retaining only those indicators whose correlations meet a certain threshold as correlation influencing indicators. This screening method can effectively reduce the complexity of subsequent analysis, avoid interference introduced by irrelevant indicators, and improve analytical efficiency and accuracy. The specific correlation analysis method will be described in detail later to enable a comprehensive and systematic assessment of the impact of each indicator, ensuring the reliability of the resulting set of correlation influencing indicators.

[0022] By obtaining a set of associated influencing indicators, the foundation is laid for the subsequent confidence sorting process of salt iodine content detection data, the influencing factors that need to be monitored are clarified, and the accuracy and reliability of salt iodine content detection are effectively improved.

[0023] S2. Receive the associated impact indicator constraint interval of the associated impact indicator set.

[0024] Specifically, the constraint ranges for the impact indicators were determined by an expert panel based on standards, industry specifications, instrumentation specifications, and statistical analysis of extensive historical testing data. The panel, comprised of senior experts in food testing, analytical instrumentation specialists, and statistical experts, ensured the authoritative and scientific nature of the constraint ranges. The process for determining the impact indicator constraint ranges involved the following: first, reference was made to the relevant standards regarding the testing environment, instrumentation, and sample handling; second, the technical parameters and stability of testing equipment, such as the spectrophotometer, were considered; third, the normal distribution ranges for each impact indicator were determined through statistical analysis of extensive historical testing data; and finally, the expert panel comprehensively assessed the appropriate constraint ranges for each indicator, taking into account actual laboratory operating conditions and technical feasibility. For example, for the impact indicator of light source stability, the panel determined a constraint range of no more than ±2% for light intensity fluctuation based on spectrophotometer specifications and historical data analysis. For the impact indicator of temperature stability, the panel determined a constraint range of 20±2°C based on the laboratory's environmental control capabilities and testing method requirements.

[0025] The received constraint intervals for the associated impact indicators are a key criterion for confidence sorting of salt iodine content test data. The proper setting of these constraint intervals influences the ability to identify abnormal conditions, and thus the credibility assessment of the test data. By receiving the constraint intervals for the associated impact indicators within the set of associated impact indicators determined by the expert panel, we obtain a scientific basis for determining whether the indicators are in a normal state, providing a reliable reference standard for subsequent deviation analysis.

[0026] By accepting the constraint range of the associated impact indicators determined by the expert group, the definition of the normal state of the associated impact indicators was established, laying the foundation for the subsequent confidence sorting process of salt iodine content detection data.

[0027] S3. When the salt sample is tested, the time series information of the monitoring value of the correlation influencing indicator is collected and compared with the constraint interval of the correlation influencing indicator to obtain the time series information of the deviation vector of the correlation influencing indicator.

[0028] Specifically, based on obtaining the set of associated influencing indicators and their constraint intervals, the status of each associated influencing indicator in the actual detection process is monitored and evaluated in real time to quantify the degree to which the indicator deviates from the normal state.

[0029] During the salt iodine content testing process, each associated influencing indicator within the identified set of associated influencing indicators is monitored in real time via a sensor network. The monitored values ​​are recorded over time to form time series information of the associated influencing indicator monitoring values. The frequency of collecting this time series information is set based on the characteristics of the testing equipment and the testing process requirements to ensure that the dynamic changes of the associated influencing indicators are captured. After obtaining this time series information, it is compared and analyzed with the received constraint intervals of the associated influencing indicators. For each associated influencing indicator, the deviation between the monitored value and the constraint interval is calculated at each monitoring moment, generating a deviation vector. The deviation vector not only contains the direction of the deviation (above the upper constraint limit or below the lower constraint limit) but also quantifies the degree of deviation, providing richer information for subsequent analysis. For example, assuming the temperature stability constraint is 20±2°C, if the monitored value at a certain moment is 23.5°C, the deviation vector at that moment is +1.5°C, indicating that it exceeds the upper limit of the constraint by 1.5°C. If the monitored value is 17.8°C, the deviation vector is -0.2°C, indicating that it falls below the lower limit by 0.2°C. If the monitored value is 21°C, it is within the constraint, and the deviation vector is 0. Arranging the deviation vectors at each moment in chronological order creates a time series of deviation vectors for the associated influencing indicators. This time series information not only reflects whether each associated influencing indicator deviates from the constraint, but also reveals the temporal pattern and dynamic trend of the deviation, providing an important basis for subsequent evaluation of the credibility of the test results.

[0030] By obtaining the time series information of the deviation vector of the associated influencing indicators, we can fully grasp the actual status of each associated influencing indicator during the detection of iodine content in salt, laying the foundation for subsequent result analysis and credibility assessment based on similar detection conditions, and effectively improving the accuracy and reliability of confidence sorting of salt iodine content detection data.

[0031] S4. Counting the iodine content detection error mode value of the iodine content detection sample set that satisfies the correlation influence indicator deviation vector time series information.

[0032] Specifically, based on the time series information of the deviation vector of the associated influencing indicators, iodine content detection samples under similar influencing factors are screened out, and the detection error distribution characteristics of these samples are analyzed to provide a basis for evaluating the credibility of the current detection results.

[0033] First, based on the obtained time series information of the deviation vectors of the associated influencing indicators, a set of iodine content test samples that meet this time series information are screened from the historical test database. Samples meeting this time series information are those whose deviation states of the associated influencing indicators during historical testing are highly similar to the deviation states of the current test samples (i.e., the time series information of the deviation vectors of the associated influencing indicators). This similarity considers not only the direction and degree of deviation of each associated influencing indicator, but also the temporal pattern and dynamic characteristics of the deviations.

[0034] For the screened set of iodine content test samples, the iodine content test error of each iodine content test sample is calculated, that is, the difference between the actual test value of the sample and the true value. These error values ​​are then statistically analyzed to determine their distribution characteristics, especially to find the mode of the error values, that is, the error value with the highest frequency, which is defined as the mode value of the iodine content test error. The mode value of the iodine content test error reflects the most likely systematic error in the test result under the deviation state of a specific associated influencing indicator (that is, the deviation of the associated influencing indicator from the vector time series information). This systematic error is mainly caused by the deviation of the associated influencing indicator and has a certain regularity and predictability. By statistically analyzing the central trend of this error, the reliability of the results under the current test conditions can be evaluated, and a quantitative basis can be provided for the subsequent credibility judgment of the test value.

[0035] The statistically analyzed error mode of iodine content testing reflects the error characteristics of the testing system under specific influencing factors, providing a reference for subsequent evaluation of the credibility of test results. This method, based on historical data and analysis of similar conditions, improves the scientific nature and accuracy of confidence sorting of salt iodine content testing data.

[0036] S5. When the iodine content detection error mode value is less than the error threshold, the iodine content detection value of the salt sample is marked as credible.

[0037] Specifically, based on the obtained mode value of the iodine content detection error, the credibility of the iodine content detection value of the current salt sample is judged and marked, providing a basis for achieving confidence sorting of salt iodine content detection data.

[0038] First, the statistically derived mode of iodine content test errors is compared with a preset error threshold. The error threshold is a pre-set maximum acceptable error limit, determined based on factors such as the standard requirements for salt iodine content testing, quality control requirements, and the accuracy requirements of the actual application scenario. When the mode of iodine content test errors is less than the error threshold, it indicates that the systematic error generated by the detection system is within an acceptable range given the current deviation of the associated influencing indicators, and the test result has a high degree of reliability. At this point, the system assigns a trustworthy mark to the iodine content test value of the salt sample, marking it as a trustworthy result. This trustworthy mark can take the form of a data flag, quality grade, or credibility score, allowing for differentiation between test results of varying degrees of credibility in subsequent data processing and applications. Conversely, if the mode of iodine content test errors is greater than or equal to the error threshold, it indicates that the detection system may generate large systematic errors given the current deviation of the associated influencing indicators, compromising the reliability of the test result. In this case, the iodine content test value of the salt sample is not assigned a trustworthy mark and may be marked as a pending verification result or a low-confidence result, indicating that retesting or other corrective measures may be necessary.

[0039] The credibility judgment method based on error analysis can effectively identify and screen test results with high reliability under various testing conditions, avoiding the impact of test errors caused by deviations from related influencing indicators on the final results. Unlike the traditional method of directly statistically analyzing multiple test results, this method takes into account the actual impact of various disturbance factors during the testing process and can more accurately assess the reliability of the test results. Through the credibility identification process, effective screening and grading of salt iodine content test results are achieved, providing support for obtaining more accurate and reliable test results, and effectively improving the accuracy and reliability of salt iodine content testing.

[0040] S6. Count the set of iodine content detection values ​​of salt samples with a credible identifier, obtain a confidence value of the iodine content of the salt, and send it to the user end.

[0041] Specifically, first, salt samples marked with a trusted identifier are screened from all iodine content test samples to form a set of iodine content test values ​​for the salt samples. The iodine content test values ​​in this set of salt samples meet error control requirements and are highly reliable, making them suitable as the basis for calculating the final result. This screening effectively eliminates test results that are subject to excessive perturbations and produce large errors, thereby improving the accuracy of the final result. The iodine content test values ​​of the salt samples in the screened set are averaged, and the result of this average calculation is used as the confidence value for the iodine content of the salt. This confidence value is then transmitted to a user via a communication network. The user can be a data management system of a testing laboratory, a quality control system of a salt production enterprise, or a supervisory platform of a regulatory agency. The user receives the confidence value for the iodine content of the salt, obtaining a highly reliable test result, which provides a basis for subsequent quality evaluation, production adjustments, or regulatory decisions.

[0042] Through statistical analysis and result feedback, the entire process of confidence sorting of salt iodine content test data was completed, achieving the transformation from raw test data to highly reliable final results. Compared with the traditional method of directly counting multiple test results, this method considers multiple influencing factors in the detection process. Through analysis and screening, it effectively improves the accuracy and reliability of salt iodine content test results, providing support for the strengthened supervision and management of salt iodine.

[0043] Furthermore, according to the type of salt iodine content detection process, a correlation analysis is performed on the preset influencing indicator set to obtain a set of associated influencing indicators, including:

[0044] S11, sending the salt iodine content detection process type and the preset impact indicator set to a first distributed node, performing correlation analysis, and obtaining a first correlation impact indicator set;

[0045] S12, until the salt iodine content detection process type and the preset impact indicator set are sent to the Nth distributed node, correlation analysis is performed, and the Nth correlation impact indicator set is obtained;

[0046] S13: Perform trigger frequency sorting based on the first association impact indicator set to the Nth association impact indicator set to obtain the association impact indicator set.

[0047] In a feasible implementation, a correlation analysis method based on distributed computing is proposed to improve the accuracy and reliability of correlation analysis through multi-node collaborative analysis.

[0048] First, the salt iodine content detection process type and the preset influencing indicator set are sent to the first distributed node, where a correlation analysis is performed to obtain a first set of associated influencing indicators. Distributed nodes are processing units dispersed across different geographical locations or computing resources, each with independent computing power and data resources. The first distributed node is any one of the N distributed nodes. After receiving the salt iodine content detection process type and the preset influencing indicator set, the first distributed node performs a correlation analysis based on its locally stored historical test data and analysis model, assessing the degree of correlation between each preset influencing indicator and the test results, screening out indicators with significant correlation, and forming a first set of associated influencing indicators.

[0049] Similarly, in a similar manner, the salt iodine content detection process type and the preset influencing indicator set are sent to the second distributed node up to the Nth distributed node, and each node independently performs correlation analysis to obtain the second correlation influencing indicator set up to the Nth correlation influencing indicator set. Wherein, N represents the total number of nodes involved in the calculation in the distributed system, and the specific value can be configured according to the data scale and computing requirements. Through parallel calculation of multiple distributed nodes, the analysis efficiency is effectively improved, and the data resources and analysis perspectives of different nodes are utilized to enhance the comprehensiveness and representativeness of the analysis results. Afterwards, trigger frequency sorting is performed based on the first correlation influencing indicator set up to the Nth correlation influencing indicator set to obtain the correlation influencing indicator set. Trigger frequency sorting refers to counting the frequency of occurrence of each preset influencing indicator in the N correlation influencing indicator sets, and screening out the indicators with higher occurrence frequency as the final correlation influencing indicators. This analysis method based on multi-node collaboration and trigger frequency makes full use of the data and computing advantages of the distributed system, and can more comprehensively and accurately identify indicators that have a significant impact on the specific salt iodine content detection process.

[0050] Through distributed correlation analysis, the accuracy and reliability of identifying associated influencing indicators are effectively improved, laying a solid foundation for the subsequent confidence sorting of salt iodine content detection data. It is suitable for the analysis and processing of large-scale detection data, and can fully explore the regular information contained in historical data, thereby improving the accuracy and stability of salt iodine content detection.

[0051] Furthermore, performing trigger frequency sorting based on the first association impact indicator set to the Nth association impact indicator set to obtain the association impact indicator set includes:

[0052] S131: Perform same-attribute trigger frequency statistics on the first correlation impact indicator set to the Nth correlation impact indicator set to obtain first indicator trigger frequencies to Qth indicator trigger frequencies;

[0053] S132. Calculate the ratio of the first indicator trigger frequency to N, and set it as the first indicator correlation degree;

[0054] S133, until the ratio of the Qth indicator trigger frequency to N is calculated and set as the Qth indicator correlation degree;

[0055] S134: Extract the indicators whose correlation degrees from the first indicator to the Qth indicator are greater than or equal to the correlation threshold, and add them into the correlation impact indicator set.

[0056] In a preferred embodiment, first, a same-attribute trigger frequency count is performed for the first through Nth sets of related influence indicators, obtaining the first through Qth indicator trigger frequencies. This same-attribute trigger frequency count refers to counting the number of times each indicator in a preset influence indicator set appears in the set of related influence indicators generated by N distributed nodes. Q represents the total number of indicators in the preset influence indicator set. Each indicator has a corresponding trigger frequency, reflecting the degree of consistency in the relevance judgments of that indicator across distributed nodes. For example, if a preset influence indicator, "light source stability," appears m times in N sets of related influence indicators, its trigger frequency is m; if another preset influence indicator, "sample uniformity," appears n times in N sets of related influence indicators, its trigger frequency is n. This statistical analysis yields the first through Qth indicator trigger frequencies, comprehensively reflecting the selection of each indicator in the multi-node analysis. Next, the ratio of the first indicator trigger frequency to N is calculated, defining this as the first indicator relevance. The relevance is a value between 0 and 1 that represents the probability or confidence that the indicator is considered a related indicator. For example, if the trigger frequency of the first indicator is m and the total number of distributed nodes is N, the correlation of the first indicator is m / N. A higher correlation indicates that more distributed nodes believe that the indicator has a significant correlation with the detection result, and the credibility of the judgment is higher.

[0057] Subsequently, in a similar manner, the ratios of the triggering frequencies of the second indicator up to the Qth indicator to N are calculated in sequence, and are set as the second indicator correlation degree up to the Qth indicator correlation degree respectively. Through this calculation, the correlation degrees of all indicators in the preset impact indicator set are obtained, providing a quantitative basis for subsequent screening. Afterwards, the indicators from the first indicator correlation degree up to the Qth indicator correlation degree that are greater than or equal to the correlation threshold are extracted and added to the correlation impact indicator set. The correlation threshold is a preset judgment criterion, which indicates the minimum correlation required to accept an indicator as an association impact indicator. The setting of the correlation threshold needs to balance the analysis accuracy and screening strictness, and can be adjusted according to actual application requirements and system performance. For example, if the correlation threshold is set to 0.7, only indicators whose triggering frequency exceeds 70% of the total number of nodes will be included in the final correlation impact indicator set.

[0058] Through a quantitative screening method based on trigger frequency and correlation, highly consistent and recognized correlation influencing indicators can be extracted from multi-node analysis results, effectively avoiding the bias and limitations that may be introduced by single-node analysis. This method fully leverages the advantages of distributed computing and can more reliably identify factors that significantly influence salt iodine content test results, providing a basis for subsequent confidence sorting of test data.

[0059] Furthermore, the salt iodine content detection process type and the preset impact indicator set are sent to the first distributed node, and correlation analysis is performed to obtain a first correlation impact indicator set, including:

[0060] S111, sending the salt iodine content detection process type and the preset influencing indicator set to a first distributed node, and collecting salt iodine content detection historical data, wherein the salt iodine content detection historical data includes salt production record parameters, preset influencing indicator record characteristic values, and salt iodine content detection record values;

[0061] S112. Performing cluster analysis on the historical data of iodine content detection of salt based on the salt production record parameters to obtain multiple clusters of historical data of iodine content detection of salt;

[0062] S113. Based on the preset influencing indicator record characteristic values ​​and the salt iodine content detection record values, traverse the multiple clusters of salt iodine content detection historical data to perform grey correlation analysis, perform correlation analysis, obtain multiple initial correlation influencing indicator sets, take the union of the sets, and add them to the first correlation influencing indicator set.

[0063] In a preferred embodiment, first, the salt iodine content detection process type and the preset influencing indicator set are sent to the first distributed node, and the salt iodine content detection historical data are collected, wherein the salt iodine content detection historical data include salt production record parameters, preset influencing indicator record characteristic values ​​and salt iodine content detection record values. Salt production record parameters include information such as production batch, production date, raw material source, process parameters, etc., which are used to identify sample characteristics under different production conditions; preset influencing indicator record characteristic values ​​refer to the actual monitoring values ​​of each preset influencing indicator during the historical detection process, such as the specific values ​​of factors such as light source stability, temperature, and humidity; salt iodine content detection record values ​​are the salt iodine content measurement results obtained in the historical detection. The first distributed node obtains relevant historical detection data from its local database or from the central database through the data interface based on the received salt iodine content detection process type and preset influencing indicator set, providing data support for subsequent analysis.

[0064] Then, based on the salt production record parameters, cluster analysis was performed on the historical data of salt iodine content testing to obtain multiple clusters of historical data of salt iodine content testing. Cluster analysis is an unsupervised learning method that aims to group data samples with similar characteristics into one category. Based on the key features in the salt production record parameters, such as raw material sources, production processes, and production equipment, algorithms such as K-means, hierarchical clustering, or density clustering were used to divide the historical data of salt iodine content testing into multiple clusters. The samples within each cluster have a high degree of similarity in salt production conditions. This classification method helps to identify the key factors that affect the test results under specific production conditions and improve the pertinence and accuracy of correlation analysis.

[0065] Subsequently, based on the preset influencing indicator record characteristic values ​​and the salt iodine content detection record values, multiple clusters of salt iodine content detection historical data are traversed to perform grey correlation analysis, and correlation analysis is performed to obtain multiple initial correlation influencing indicator sets, take the union, and add them into the first correlation influencing indicator set. Grey correlation analysis is an effective method for dealing with uncertainty problems, and is particularly suitable for situations where the sample size is small and the information is incomplete. Specifically, for each cluster of salt iodine content detection historical data, the preset influencing indicator record characteristic values ​​are extracted as the comparison sequence, and the salt iodine content detection record values ​​are used as the reference sequence. The grey correlation between each preset influencing indicator and the test result is calculated, and the indicators with a correlation higher than the threshold are screened out to form an initial correlation influencing indicator set. After traversing all data clusters, multiple initial correlation influencing indicator sets are obtained, and then the union of these sets is taken to form the first correlation influencing indicator set of the first distributed node.

[0066] This method, based on data clustering and grey correlation analysis, can fully tap into the regular information contained in historical test data and identify factors that significantly influence the iodine content of salt under different production conditions. This method comprehensively considers the diversity of production conditions and the complexity of influencing factors, and can more comprehensively and accurately determine the associated influencing indicators, providing a basis for subsequent confidence sorting of salt iodine content test data. Using this historical data analysis method, the precise identification of associated influencing indicators is achieved on a distributed computing architecture, improving the accuracy and adaptability of confidence sorting of salt iodine content test data and providing technical support for obtaining high-quality test results.

[0067] Furthermore, based on the preset influencing indicator record characteristic value and the salt iodine content detection record value, the multiple clusters of salt iodine content detection historical data are traversed to perform grey correlation analysis, and correlation analysis is performed to obtain multiple initial correlation influencing indicator sets, including:

[0068] S1131, extracting a first cluster of table salt iodine content detection historical data from the multiple clusters of table salt iodine content detection historical data;

[0069] S1132: extracting a first cluster of preset influencing indicator record feature value sets from the first cluster of table salt iodine content detection historical data, de-dimensionalizing the data, and setting the result as a comparison sequence;

[0070] S1133: extracting a first cluster of table salt iodine content detection record value sets from the first cluster of table salt iodine content detection historical data, de-dimensionalizing the sets, and setting the sets as a reference sequence;

[0071] S1134. Perform grey relational analysis based on the comparison sequence and the reference sequence to obtain a first cluster relational degree set;

[0072] S1135: extracting preset influence indicators greater than or equal to the correlation threshold from the first cluster correlation set, and adding them to the first initial correlation influence indicator set;

[0073] S1136: Add the first initial correlation influence indicator set to the multiple initial correlation influence indicator sets.

[0074] In a preferred embodiment, first, a first cluster of table salt iodine content detection historical data is extracted from multiple clusters of table salt iodine content detection historical data. The first cluster refers to one of the multiple data clusters formed after the cluster analysis in step S112. Each cluster of data represents a set of detection records under specific table salt production conditions, with similar production backgrounds and process characteristics. The first cluster of table salt iodine content detection historical data is processed first, and the other clusters of data will be processed in sequence subsequently to ensure a comprehensive analysis of the influencing factors under different production conditions.

[0075] Then, the first cluster of recorded characteristic values ​​for pre-set influencing indicators is extracted from the first cluster of historical data on iodine content testing of salt. After dimensioning, this is set as the comparison sequence. The first cluster of recorded characteristic values ​​for pre-set influencing indicators contains the actual values ​​of each pre-set influencing indicator recorded during the historical testing process, such as the specific measured values ​​of factors such as light source stability, temperature, and humidity. Because the dimensions and orders of magnitude of different indicators may vary significantly, these characteristic values ​​are subjected to dimensioning, such as initialization, averaging, or intervalization, to eliminate the impact of dimensional differences on the analysis results. The dimensioned data serves as the comparison sequence for grey relational analysis, used for comparison with the benchmark sequence to assess its correlation. Simultaneously, the first cluster of recorded values ​​for iodine content detection of salt is extracted from the first cluster of historical data on iodine content testing of salt. After dimensioning, this is set as the benchmark sequence. The first cluster of recorded values ​​for iodine content detection of salt contains the iodine content measurement results of salt obtained during the historical testing process. These detection values ​​are also dimensioned to ensure comparability with the comparison sequence. The processed data serves as the benchmark sequence for grey relational analysis and is the reference standard for evaluating the correlation of each preset influencing indicator. Subsequently, grey relational analysis is performed based on the comparison sequence and the benchmark sequence to obtain the first cluster of correlation sets. Specifically, the difference sequence between the benchmark sequence and each comparison sequence is first calculated, and then the correlation coefficient at each moment is calculated based on the minimum difference, maximum difference and resolution coefficient, and finally the average value is calculated to obtain the grey relational degree. Through this calculation, the similarity and correlation between each preset influencing indicator and the iodine content test result of table salt are quantified, forming the first cluster of correlation sets containing the correlations of all preset influencing indicators.

[0076] Afterwards, the preset influencing indicators in the first cluster correlation set that are greater than or equal to the correlation threshold are extracted and added to the first initial correlation influencing indicator set. The correlation threshold is a preset judgment standard, which indicates the minimum correlation required to accept an indicator as a correlation influencing indicator. The preset influencing indicators with a correlation higher than the correlation threshold are screened out. These indicators have a significant correlation with the iodine content test results of table salt and are included in the first initial correlation influencing indicator set. Subsequently, the first initial correlation influencing indicator set is added to multiple initial correlation influencing indicator sets, so that the results of the analysis of the historical data of the first cluster of table salt iodine content test are saved in the overall result set, in preparation for the subsequent integration of the analysis results of each cluster. In a similar manner, the second cluster until the last cluster of data is processed in sequence to obtain multiple initial correlation influencing indicator sets, and finally their union is taken to form the correlation influencing indicator set of the distributed node.

[0077] Using a method based on grey correlation analysis, it is possible to accurately assess the correlation between each preset influencing indicator and the iodine content test results of table salt, even under conditions of limited data and incomplete information. This provides a basis for determining the associated influencing indicators and offers technical support for improving the reliability and accuracy of test data. Using grey correlation analysis, the precise identification of associated influencing indicators is achieved. While fully considering different production conditions, the impact of each preset influencing indicator is comprehensively assessed, providing a reliable technical means for confidence sorting of table salt iodine content test data.

[0078] Furthermore, the iodine content detection sample set that satisfies the correlation impact index deviation vector time series information is counted, including:

[0079] S41. Based on the time series information of the deviation vector of the correlation impact indicator, a deviation state similarity evaluation function is constructed:

[0080] ,

[0081] ,

[0082] in, Characterizes the deviation vector similarity of the i-th attribute association impact index, represents the total number of monitoring moments of the i-th attribute-related impact indicator, t represents the t-th moment of the monitoring time, Characterizes the time series information of the deviation vector of the impact index of the i-th attribute association, Characterizes the time series information of the deviation vector of the impact index of the i-th attribute of the sample, Characterizes the deviation vector of the impact index of the i-th attribute association at the t-th moment, Characterizes the deviation vector of the sample's attribute-i correlation impact index at time t, Characterizes the time series information of the deviation vector of all attribute association impact indicators, Represents the deviation vector time series information of all attribute correlation impact indicators of the sample, M represents the total number of attributes, , Characterize small constants;

[0083] S42, evaluating the deviation state similarity between the time series information of the deviation vector of the correlation influence indicator of the selected salt sample and the time series information of the deviation vector of the correlation influence indicator according to the deviation state similarity evaluation function;

[0084] S43. When the deviation state similarity is greater than or equal to the similarity threshold, the salt sample to be selected is added to the iodine content detection sample set.

[0085] Specifically, a sample screening method based on deviation state similarity evaluation is proposed. By quantitatively evaluating the deviation state similarity between samples, a set of iodine content detection samples with similar detection conditions is screened out, providing a reliable data basis for subsequent error analysis.

[0086] First, based on the time series information of the deviation vector of the associated impact indicator, the deviation state similarity evaluation function is constructed as follows:

[0087] , .

[0088] This evaluation function uses a structured similarity metric design concept to effectively quantify the degree of similarity between different samples in terms of the deviation states of the associated influence indicators. The function is divided into two levels: first, the deviation vector similarity of the associated influence indicators of each attribute is calculated, and then the overall similarity is determined based on the similarity of each attribute.

[0089] At the attribute level, the improved cosine similarity formula is used to calculate the deviation vector similarity of the i-th attribute association influence index This formula takes into account the dynamic characteristics of time series information and quantifies the directional consistency and amplitude similarity of two time series information by the ratio of the product and sum of squares of the deviation vectors at each moment. The deviation vector time series information representing the impact index of the i-th attribute of the current detection sample is a vector sequence that changes over time; The time series information of the deviation vector of the i-th attribute correlation impact index of the candidate sample in the historical database is also a time series vector sequence. These two sequences record the changes in the deviation status of different samples on the same correlation impact index over time. Represents the total number of monitoring moments of the i-th attribute-related impact indicator, that is, the number of time points at which the indicator is monitored during the entire detection process; t represents the specific moment in the monitoring process, with a value range of 1 to T, representing different points in the time series. For each moment t, Represents the deviation vector of the attribute-related impact index of the current detection sample at the tth moment, that is, the degree of deviation between the monitoring value at that moment and the constraint interval; similarly, The deviation vector representing the impact index of the i-th attribute of the candidate sample at time t. These deviation vectors are the basic units for calculating similarity and reflect the deviation state of the index at each moment. is a small constant used to avoid the denominator being zero and to improve the stability of the algorithm. By averaging the similarities at each moment, the overall similarity of the entire time series is obtained.

[0090] At the overall level, the minimum value of the similarity of each attribute is taken as the overall similarity .in, The deviation vector time series information that represents all attribute correlation impact indicators of the current detection sample is a collection of all attribute deviation information; similarly, Represents the time series information of the deviation vector of all attribute correlation impact indicators of the candidate sample. M represents the total number of attributes, that is, the number of correlation impact indicators. Find the value with the lowest similarity among all M attributes as the overall evaluation result. This shows that the deviation vector at each moment is a component of the corresponding time series information, and the time series information of each attribute is a component of the overall deviation information, which clearly describes the hierarchical relationship between the data.

[0091] Subsequently, based on the deviation state similarity evaluation function, the deviation state similarity between the time series information of the deviation vector of the associated influence indicator of the candidate salt sample and the time series information of the deviation vector of the associated influence indicator is evaluated. Specifically, the time series information of the deviation vector of the associated influence indicator of the current test sample is used as a reference and compared with the time series information of the deviation vector of the associated influence indicator of the candidate salt sample to calculate the deviation state similarity between the two. This comparison not only takes into account the direction and magnitude of the deviation, but also takes into account the dynamic change characteristics of the time series, which can comprehensively evaluate the comparability of the test conditions between samples. When the deviation state similarity is greater than or equal to the similarity threshold, the candidate salt sample is added to the iodine content test sample set. The similarity threshold is a preset judgment standard that represents the minimum similarity required to accept a sample as a reference sample. Through this screening, a sample set with a high degree of similarity in the deviation state of the associated influence indicator is formed. These samples are comparable to the current test sample in terms of interference from influencing factors and are suitable as a reference basis for evaluating system errors.

[0092] By using a sample screening method based on deviation state similarity assessment, samples similar to the current test conditions can be accurately screened from historical data, providing effective data support for subsequent error analysis. This method fully considers the temporal and multi-attribute characteristics of the deviation of the associated influencing indicators, and can more comprehensively and accurately assess the similarity between samples, improving the accuracy and reliability of the confidence sorting of salt iodine content test data. This deviation state similarity assessment method achieves accurate screening of test samples, ensuring that the data basis for error analysis is highly comparable and representative, providing a guarantee for obtaining an accurate mode value of iodine content test errors, and further improving the accuracy and reliability of salt iodine content testing.

[0093] Furthermore, statistics are collected on the iodine content detection value set of the salt samples with the trustworthy identification to obtain the confidence value of the iodine content of the salt and send it to the user end, including:

[0094] S61, performing box plot analysis on the set of iodine content detection values ​​of the salt samples to obtain a set of iodine content detection values ​​of the box salt samples;

[0095] S62. Perform a central tendency assessment on the set of iodine content detection values ​​of the salt samples in the box to obtain a distribution interval of the iodine content of the salt, set it as the confidence value of the iodine content of the salt, and send it to the user end.

[0096] In a preferred embodiment, a box plot analysis is first performed on the set of iodine content test values ​​of the salt samples to obtain a set of iodine content test values ​​of the salt samples in the box. Specifically, the quartiles of the set of iodine content test values ​​of the salt samples are first calculated, including the first quartile Q1 (25% quantile), the second quartile Q2 (median, 50% quantile), and the third quartile Q3 (75% quantile), and the interquartile range (IQR) (i.e., Q3-Q1) is determined. Based on the quartiles and interquartile range, upper and lower boundaries are defined: the upper boundary is Q3+1.5*IQR, and the lower boundary is Q1-1.5*IQR. Samples with iodine content test values ​​of salt samples outside these boundaries are considered potential outliers or outliers and are excluded from subsequent analysis. The test values ​​between the upper and lower boundaries constitute the set of iodine content test values ​​of the salt samples in the box, which is suitable for subsequent central tendency analysis. Through box plot analysis, extreme values ​​that may be affected by unknown factors or measurement errors can be effectively identified and excluded, improving the accuracy and reliability of subsequent statistical analysis.

[0097] Subsequently, a central tendency assessment is performed on the set of iodine content test values ​​of the box salt samples to obtain the distribution range of the iodine content of the salt, which is set as the confidence value of the iodine content of the salt and sent to the user end. The central tendency assessment aims to extract statistics that can represent the overall characteristics from the set of iodine content test values ​​of the screened box salt samples, providing a basis for determining the final test results. First, the basic statistics of the set of iodine content test values ​​of the box salt samples, such as the mean, median, standard deviation or variance, are calculated to fully grasp the distribution characteristics of the data. On this basis, a statistical method is selected based on the distribution type of the data to determine the distribution range of the iodine content of the salt. If the data approximately obeys a normal distribution, the distribution range can be defined in the form of mean ± K times the standard deviation, where K is a coefficient determined according to the confidence level; if the data distribution does not meet the normal assumption, a quantile-based method can be used, such as taking the median as the center point and expanding to specific quantiles on both sides to form a non-parametric distribution range. The determined distribution range of the iodine content of the salt is used as the confidence value of the iodine content of the salt and sent to the user end via the communication network.

[0098] Through the above steps, outliers were effectively eliminated from the set of test values ​​with credible identification, representative central tendency characteristics were extracted, and a highly reliable confidence value for the iodine content of table salt was formed. This method, based on box plot analysis and central tendency assessment, fully considers the distribution characteristics and possible uncertainties of the data, providing users with accurate and reliable test results and effectively supporting the quality control and supervision and management of the iodine content of table salt. Using this method, a scientific transformation from credible test results to final confidence values ​​is achieved, improving the accuracy and reliability of salt iodine content testing and providing users with high-quality test results.

[0099] Example 2, as Figure 2 As shown, based on the same inventive concept as the confidence sorting method for salt iodine content detection data provided in Example 1, an embodiment of the present invention also provides a confidence sorting system for salt iodine content detection data, comprising:

[0100] A correlation analysis module 11 is used to perform correlation analysis on a preset influencing indicator set according to the type of salt iodine content detection process to obtain a related influencing indicator set;

[0101] The constraint interval receiving module 12 is used to receive the associated impact indicator constraint interval of the associated impact indicator set;

[0102] The deviation vector analysis module 13 is used to collect the time series information of the monitoring value of the correlation influence indicator when the salt sample is tested, compare it with the constraint interval of the correlation influence indicator, and obtain the time series information of the deviation vector of the correlation influence indicator;

[0103] An error mode statistics module 14 is configured to count the iodine content detection error mode values ​​of the iodine content detection sample set that satisfies the correlation impact indicator deviation vector time series information;

[0104] A detection value identification module 15 is used to identify the iodine content detection value of the salt sample as credible when the iodine content detection error mode value is less than an error threshold;

[0105] The confidence value statistics module 16 is used to collect statistics on the iodine content detection value set of the salt samples with the trustworthy identification, obtain the confidence value of the iodine content of the salt and send it to the user end.

[0106] Furthermore, the correlation analysis module 11 includes the following execution steps:

[0107] Sending the salt iodine content detection process type and the preset impact indicator set to a first distributed node, performing correlation analysis, and obtaining a first correlation impact indicator set;

[0108] Until the salt iodine content detection process type and the preset impact indicator set are sent to the Nth distributed node, correlation analysis is performed, and the Nth correlation impact indicator set is obtained;

[0109] Trigger frequency sorting is performed based on the first association impact indicator set to the Nth association impact indicator set to obtain the association impact indicator set.

[0110] Furthermore, the correlation analysis module 11 further includes the following execution steps:

[0111] Performing same-attribute trigger frequency statistics on the first associated impact indicator set to the Nth associated impact indicator set to obtain first indicator trigger frequencies to Qth indicator trigger frequencies;

[0112] Calculate the ratio of the first indicator trigger frequency to N, and set it as the first indicator correlation degree;

[0113] Until the ratio of the trigger frequency of the Qth indicator to N is calculated and set as the Qth indicator correlation degree;

[0114] Indicators from the first indicator correlation degree to the Qth indicator correlation degree that are greater than or equal to a correlation degree threshold are extracted and added into the correlation impact indicator set.

[0115] Furthermore, the correlation analysis module 11 further includes the following execution steps:

[0116] Sending the salt iodine content detection process type and the preset influencing indicator set to a first distributed node, and collecting salt iodine content detection history data, wherein the salt iodine content detection history data includes salt production record parameters, preset influencing indicator record characteristic values, and salt iodine content detection record values;

[0117] performing cluster analysis on the historical data of iodine content detection of salt according to the salt production record parameters to obtain multiple clusters of historical data of iodine content detection of salt;

[0118] Based on the preset influencing indicator record characteristic values ​​and the salt iodine content detection record values, the multiple clusters of salt iodine content detection historical data are traversed to perform grey correlation analysis, and correlation analysis is performed to obtain multiple initial correlation influencing indicator sets, take the union set, and add it to the first correlation influencing indicator set.

[0119] Furthermore, the correlation analysis module 11 further includes the following execution steps:

[0120] Extracting a first cluster of table salt iodine content detection historical data from the multiple clusters of table salt iodine content detection historical data;

[0121] Extracting a first cluster of preset influencing indicator record feature value sets from the first cluster of table salt iodine content detection historical data, de-dimensionalizing the sets and setting them as a comparison sequence;

[0122] Extracting a first cluster of table salt iodine content detection record value sets from the first cluster of table salt iodine content detection historical data, de-dimensionalizing the sets, and setting the sets as a reference sequence;

[0123] Performing grey relational analysis on the comparison sequence and the reference sequence to obtain a first cluster relational degree set;

[0124] Extracting preset impact indicators greater than or equal to a correlation threshold from the first cluster correlation set, and adding them to a first initial correlation impact indicator set;

[0125] The first initial correlation impact indicator set is added to the multiple initial correlation impact indicator sets.

[0126] Furthermore, the error mode statistics module 14 includes the following execution steps:

[0127] Based on the time series information of the deviation vector of the correlation impact indicator, a deviation state similarity evaluation function is constructed:

[0128] ,

[0129] ,

[0130] in, Characterizes the deviation vector similarity of the i-th attribute association impact index, represents the total number of monitoring moments of the i-th attribute-related impact indicator, t represents the t-th moment of the monitoring time, Characterizes the time series information of the deviation vector of the impact index of the i-th attribute association, Characterizes the time series information of the deviation vector of the impact index of the i-th attribute of the sample, Characterizes the deviation vector of the impact index of the i-th attribute association at the t-th moment, Characterizes the deviation vector of the sample's attribute-i correlation impact index at time t, Characterizes the time series information of the deviation vector of all attribute association impact indicators, Represents the deviation vector time series information of all attribute correlation impact indicators of the sample, M represents the total number of attributes, , Characterize small constants;

[0131] According to the deviation state similarity evaluation function, the deviation state similarity between the time series information of the deviation vector of the correlation influence indicator of the selected salt sample and the time series information of the deviation vector of the correlation influence indicator is evaluated;

[0132] When the deviation state similarity is greater than or equal to the similarity threshold, the salt sample to be selected is added to the iodine content detection sample set.

[0133] Furthermore, the confidence value statistics module 16 includes the following execution steps:

[0134] Performing a box plot analysis on the set of iodine content detection values ​​of the salt samples to obtain a set of iodine content detection values ​​of the box salt samples;

[0135] A central tendency assessment is performed on the set of iodine content detection values ​​of the box salt samples to obtain a distribution interval of the iodine content of the salt, which is set as the confidence value of the iodine content of the salt and sent to the user end.

[0136] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0137] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0141] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A confidence sorting method for salt iodine content detection data, characterized in that: include: According to the type of salt iodine content detection process, correlation analysis is performed on the preset influencing indicator set to obtain the associated influencing indicator set; receiving an associated impact indicator constraint interval of the associated impact indicator set; When the salt sample is tested, the time series information of the monitoring value of the correlation influence indicator is collected and compared with the constraint interval of the correlation influence indicator to obtain the time series information of the deviation vector of the correlation influence indicator; Counting the iodine content detection error mode value of the iodine content detection sample set that satisfies the correlation influence indicator deviation vector time series information; When the iodine content detection error mode value is less than the error threshold, the iodine content detection value of the salt sample is marked as credible; Collect statistics on the iodine content test values ​​of salt samples with trustworthy identification, obtain the confidence value of the iodine content of salt and send it to the user end; Among them, according to the type of salt iodine content detection process, a correlation analysis is performed on the preset influencing indicator set to obtain a set of associated influencing indicators, including: Sending the salt iodine content detection process type and the preset impact indicator set to a first distributed node, performing correlation analysis, and obtaining a first correlation impact indicator set; Until the salt iodine content detection process type and the preset impact indicator set are sent to the Nth distributed node, correlation analysis is performed, and the Nth correlation impact indicator set is obtained; Trigger frequency sorting is performed based on the first association impact indicator set to the Nth association impact indicator set to obtain the association impact indicator set.

2. The confidence sorting method for salt iodine content detection data according to claim 1, wherein: Performing trigger frequency sorting based on the first association impact indicator set to the Nth association impact indicator set to obtain the association impact indicator set includes: Performing same-attribute trigger frequency statistics on the first associated impact indicator set to the Nth associated impact indicator set to obtain first indicator trigger frequencies to Qth indicator trigger frequencies; Calculate the ratio of the first indicator trigger frequency to N, and set it as the first indicator correlation degree; Until the ratio of the trigger frequency of the Qth indicator to N is calculated and set as the Qth indicator correlation degree; Indicators from the first indicator correlation degree to the Qth indicator correlation degree that are greater than or equal to a correlation degree threshold are extracted and added into the correlation impact indicator set.

3. The confidence sorting method for salt iodine content detection data according to claim 1, wherein: The salt iodine content detection process type and the preset impact indicator set are sent to a first distributed node, and a correlation analysis is performed to obtain a first correlation impact indicator set, including: Sending the salt iodine content detection process type and the preset influencing indicator set to a first distributed node, and collecting salt iodine content detection history data, wherein the salt iodine content detection history data includes salt production record parameters, preset influencing indicator record characteristic values, and salt iodine content detection record values; performing cluster analysis on the historical data of iodine content detection of salt according to the salt production record parameters to obtain multiple clusters of historical data of iodine content detection of salt; Based on the preset influencing indicator record characteristic values ​​and the salt iodine content detection record values, the multiple clusters of salt iodine content detection historical data are traversed to perform grey correlation analysis, and correlation analysis is performed to obtain multiple initial correlation influencing indicator sets, take the union set, and add it to the first correlation influencing indicator set.

4. The confidence sorting method for salt iodine content detection data according to claim 3, characterized in that: Based on the preset influencing indicator record characteristic values ​​and the salt iodine content detection record values, the multiple clusters of salt iodine content detection historical data are traversed to perform grey correlation analysis and correlation analysis to obtain multiple initial correlation influencing indicator sets, including: Extracting a first cluster of table salt iodine content detection historical data from the multiple clusters of table salt iodine content detection historical data; Extracting a first cluster of preset influencing indicator record feature value sets from the first cluster of table salt iodine content detection historical data, de-dimensionalizing the sets and setting them as a comparison sequence; Extracting a first cluster of table salt iodine content detection record value sets from the first cluster of table salt iodine content detection historical data, de-dimensionalizing the sets, and setting the sets as a reference sequence; Performing grey relational analysis on the comparison sequence and the reference sequence to obtain a first cluster relational degree set; Extracting preset impact indicators greater than or equal to a correlation threshold from the first cluster correlation set, and adding them to a first initial correlation impact indicator set; The first initial correlation impact indicator set is added to the multiple initial correlation impact indicator sets.

5. The confidence sorting method for salt iodine content detection data according to claim 1, characterized in that: The iodine content detection sample set that satisfies the correlation impact indicator deviation vector time series information is counted, including: Based on the time series information of the deviation vector of the correlation impact indicator, a deviation state similarity evaluation function is constructed: ， , in, Characterizes the deviation vector similarity of the i-th attribute association impact index, represents the total number of monitoring moments of the i-th attribute-related impact indicator, t represents the t-th moment of the monitoring time, Characterizes the time series information of the deviation vector of the impact index of the i-th attribute association, Characterizes the time series information of the deviation vector of the impact index of the i-th attribute of the sample, Characterizes the deviation vector of the impact index of the i-th attribute association at the t-th moment, Characterizes the deviation vector of the sample's attribute-i correlation impact index at time t, Characterizes the time series information of the deviation vector of all attribute association impact indicators, Represents the deviation vector time series information of all attribute correlation impact indicators of the sample, M represents the total number of attributes, , Characterize small constants; According to the deviation state similarity evaluation function, the deviation state similarity between the time series information of the deviation vector of the correlation influence indicator of the selected salt sample and the time series information of the deviation vector of the correlation influence indicator is evaluated; When the deviation state similarity is greater than or equal to the similarity threshold, the salt sample to be selected is added to the iodine content detection sample set.

6. The confidence sorting method for salt iodine content detection data according to claim 1, characterized in that: The iodine content detection value set of salt samples with a trustworthy identifier is counted to obtain the confidence value of the iodine content of the salt and sent to the user end, including: Performing a box plot analysis on the set of iodine content detection values ​​of the salt samples to obtain a set of iodine content detection values ​​of the box salt samples; A central tendency assessment is performed on the set of iodine content detection values ​​of the box salt samples to obtain a distribution interval of the iodine content of the salt, which is set as the confidence value of the iodine content of the salt and sent to the user end.

7. A confidence sorting system for salt iodine content detection data, characterized in that: For implementing the method according to any one of claims 1 to 6, the system comprises: A correlation analysis module is used to perform correlation analysis on a preset influencing indicator set according to the type of salt iodine content detection process to obtain a related influencing indicator set; A constraint interval receiving module, configured to receive the associated impact indicator constraint interval of the associated impact indicator set; The deviation vector analysis module is used to collect the time series information of the monitoring value of the correlation influence indicator when the salt sample is tested, compare it with the constraint interval of the correlation influence indicator, and obtain the time series information of the deviation vector of the correlation influence indicator; An error mode statistics module, configured to count the iodine content detection error mode values ​​of the iodine content detection sample set that satisfies the correlation influence index deviation vector time series information; A detection value identification module, configured to identify the iodine content detection value of the salt sample as credible when the iodine content detection error mode value is less than an error threshold; The confidence value statistics module is used to collect statistics on the iodine content detection value set of salt samples with a trustworthy identifier, obtain the confidence value of the iodine content of the salt and send it to the user end.

Images