Tracing method for production quality of sea cucumber total nutrient extract based on whole-process tracking

Abstract

The invention provides a sea cucumber total nutrient extract production quality traceability method based on whole process tracking, and relates to the technical field of production quality traceability, and the method comprises the following steps: sampling a sea cucumber total nutrient extract in a finished product stage; carrying out key quality index detection on a plurality of sample extracts; obtaining a process-index degree matrix; positioning H risk process nodes; performing optimization hierarchical classification on the H risk process nodes according to the H risk contribution degrees and the standard process; and performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and performing process parameter updating by adopting a process optimization result. According to the method and the device, the technical problem of difficulty in production quality tracing caused by difficulty in real-time tracking of quality data in the whole production process due to the fact that data of each production link is usually isolated in the prior art can be solved, and the production quality tracing efficiency is improved by tracking the whole process from the production raw materials to the final product quality. And the transparency and traceability of the production quality are improved.

Description

Technical Field

[0001] The present application relates to the technical field of production quality traceability, and in particular to a production quality traceability method for sea cucumber complete nutrition extracts based on full-process tracking. Background Art

[0002] The complete nutritional extraction of sea cucumbers includes sea cucumber peptides, sea cucumber polysaccharides, and sea cucumber saponins, and these ingredients are ground into powder. The extraction quality of these ingredients directly affects the effect of the final product. Therefore, in the production process of sea cucumber complete nutritional extracts, it is crucial to ensure quality control at each link. The process of producing sea cucumber complete nutritional extracts usually includes the procurement of sea cucumber raw materials, extraction of polysaccharides and saponins, concentration and drying of extracts, quality inspection and finished product packaging. In order to ensure the high quality of the final product, each process node must be managed in a refined manner. However, data from different links are usually managed by different departments, which makes it difficult to share and integrate data between links, making it impossible for quality traceability to fully and accurately cover the entire production process.

[0003] In summary, the prior art has a technical problem in that the data of each production link is usually isolated, making it difficult to track the quality data of the entire production process in real time, resulting in difficulty in tracing production quality. Summary of the invention

[0004] The purpose of this application is to provide a method for tracing the production quality of sea cucumber complete nutrition extract based on full-process tracking, so as to solve the technical problem in the prior art that the data of each production link is usually isolated, making it difficult to track the quality data of the entire production process in real time, resulting in difficulty in tracing production quality.

[0005] In view of the above problems, the present application provides a production quality traceability method for a sea cucumber complete nutrient extract based on full-process tracking, wherein the production quality traceability method for a sea cucumber complete nutrient extract based on full-process tracking includes: sampling sea cucumber complete nutrient extracts at the finished product stage of the sea cucumber extraction process line to obtain multiple sample extracts; performing key quality indicator detection on the multiple sample extracts to obtain multiple sample indicator deviation sets; performing process node correlation analysis based on the sea cucumber production log to obtain a process-indicator degree matrix; using the multiple sample indicator deviation sets to traverse the process-indicator degree matrix to perform production quality traceability and locate H risk process nodes, wherein the H risk process nodes have H risk contribution degree identifiers; optimizing the H risk process nodes according to the H risk contribution degrees and the standard procedures of the sea cucumber extraction process line to obtain multiple levels of nodes to be optimized; using the multiple levels of nodes to be optimized as optimization directions, performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and using the process optimization results to update the process parameters of the sea cucumber extraction process line.

[0006] The technical solution provided in this application has at least the following technical effects or advantages: The method comprises the following steps: sampling a sea cucumber full nutrient extract at the finished product stage of a sea cucumber extraction process line to obtain a plurality of sample extracts; performing key quality indicator detection on the plurality of sample extracts to obtain a plurality of sample indicator deviation sets; performing process node correlation analysis based on a sea cucumber production log to obtain a process-indicator degree matrix; using the plurality of sample indicator deviation sets to traverse the process-indicator degree matrix to perform production quality traceability, and locating H risk process nodes, wherein the H risk process nodes have H risk contribution degree identifiers; optimizing the H risk process nodes according to the H risk contribution degrees and the standard procedures of the sea cucumber extraction process line to obtain a plurality of nodes to be optimized; using the plurality of nodes to be optimized as optimization directions, performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and using the process optimization results to update the process parameters of the sea cucumber extraction process line. That is to say, by sampling at the finished product stage of the sea cucumber extraction process line and conducting key quality indicator tests, different process nodes are correlated with quality indicators based on the process-indicator degree matrix, risky process nodes are identified, and multi-level progressive optimization is performed on the risky process nodes. The standard process is updated using the process optimization results, providing full traceability from production raw materials to final product quality, and improving the transparency and traceability of production quality through detailed quality data and process node analysis.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0009] Figure 1 This is a schematic diagram of the process of the production quality traceability method of sea cucumber complete nutrition extract based on full process tracking in this application; Figure 2This is a flow chart for locating H risky process nodes in the production quality traceability method of sea cucumber complete nutrient extract based on full-process tracking in this application. DETAILED DESCRIPTION

[0010] This application solves the technical problem in the prior art that the data of each production link is usually isolated, and it is difficult to track the quality data of the entire production process in real time, which leads to difficulty in tracing the production quality by providing a production quality traceability method for sea cucumber complete nutrition extracts based on full-process tracking. By sampling at the finished product stage of the sea cucumber extraction process line and conducting key quality indicator tests, different process nodes are correlated with quality indicators according to the process-indicator degree matrix, risky process nodes are identified, and risky process nodes are progressively optimized at multiple levels. The standard process is updated using the process optimization results, providing full traceability from production raw materials to final product quality, and improving the transparency and traceability of production quality through detailed quality data and process node analysis.

[0011] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0012] For examples, please see the attached Figure 1 The present application provides a method for tracing the production quality of a sea cucumber complete nutritional extract based on full-process tracing, wherein the method for tracing the production quality of a sea cucumber complete nutritional extract based on full-process tracing specifically comprises the following steps: Step 1: Sampling the sea cucumber full nutrient extract at the finished product stage of the sea cucumber extraction process line to obtain multiple sample extracts.

[0013] Specifically, at the finished product stage of the sea cucumber extraction process line, first set a suitable sampling time window, that is, the rules for sampling within a certain time range, usually taking into account factors such as production rhythm and process fluctuations. According to the sampling time window, the sea cucumber full nutrition extract is sampled from the finished product stage of the sea cucumber extraction process line, using random sampling or stratified sampling methods to ensure that samples from all links and stages are covered. K spare extracts are obtained by smoking to ensure that the samples are representative and to avoid biased results caused by only sampling a certain part of the samples. The extract obtained from the sea cucumber contains active ingredients such as sea cucumber peptides, sea cucumber polysaccharides, and sea cucumber saponins.

[0014] Determine the sampling confidence interval based on the production scale, product quality requirements and standard operating procedures. Classify the K spare extracts into M groups of spare extracts according to the sampling time identification to ensure that the extracts in each group have a relatively similar production time. The sampling confidence threshold refers to the maximum error range allowed in the quality control process. By setting a reasonable sampling confidence threshold, the product quality can be ensured to be within an acceptable range. Screen out the sample extracts that meet the sampling confidence threshold from the M groups of spare extracts, remove the data that exceeds the range, and obtain multiple sample extracts. By sampling at the finished product stage, product quality fluctuations can be detected and potential quality problems can be discovered in a timely manner, thereby ensuring the consistency of the quality of each batch of sea cucumber extracts produced.

[0015] Step 2: Perform key quality index detection on the multiple sample extracts to obtain multiple sample index deviation sets.

[0016] Specifically, multiple sample extracts are multiple samples extracted from the finished product stage of the sea cucumber extraction process line. They are representative and can reflect the quality of sea cucumber extracts under different production batches, different time points or different process conditions. Test multiple sample extracts and select appropriate key quality indicators. In the production process of sea cucumber complete nutrition extracts, key quality indicators are important parameters reflecting product quality, including protein, fat, amino acids, Salmonella, pH, etc. Salmonella is an important microbial indicator used to detect the safety of extracts, and its content must be ensured to be zero. For example, the protein content is determined by colorimetry or UV-visible spectrophotometry, the amino acid content is determined by an amino acid analyzer, the Salmonella is detected by microbial culture, and the pH value is determined by a pH meter.

[0017] By testing the key quality indicators of multiple sample extracts, we can obtain the key quality indicator data of each sample and form a sample indicator deviation set, which reflects the differences of each sample in each quality indicator. The deviation set refers to the difference of each sample in the key quality indicator, that is, the difference between the actual measured value of each sample and the target standard value, such as the protein content of some samples is high, while the pH value of other samples is low. By comprehensively testing the key quality indicators of multiple samples, we can accurately evaluate the quality stability of the production process and find deviations in time.

[0018] Step 3: Based on the sea cucumber production log, conduct process node correlation analysis to obtain the process-indicator degree matrix.

[0019] Specifically, the sea cucumber production log records the operation, equipment status, environmental conditions, quality inspection results and other information of each link in the sea cucumber production process, including a detailed description of each process step, time, raw materials used, additives, equipment settings, operators, and quality control data. Collect operation records of each process node in the sea cucumber production log, including boiling ginseng, precipitation, concentration, cooling, freeze-drying, etc. According to key quality indicators, such as protein, heavy metals, microorganisms, etc., process node correlation analysis is performed to reveal the relationship between different process nodes and key quality indicators. Based on the results of the correlation analysis, a process-indicator degree matrix is ​​constructed. The rows of the matrix represent different process nodes, and the columns represent different quality indicators. Each element in the matrix represents the degree of influence of a certain process node on a certain quality indicator. For example, assuming there are 3 process nodes (boiling ginseng, precipitation, concentration) and 3 quality indicators (protein, heavy metals, microorganisms), the process-indicator degree matrix ,Each value represents the degree of influence of each process node on different quality indicators. For example, in multiple experiments, when the operation time of the boiling pot was extended from 30 minutes to 45 minutes, the deviation of protein content increased by 20%, indicating that the boiling operation has a greater impact on protein content. Through the process-indicator degree matrix, the degree of influence of each process node on different quality indicators is clarified, and the source of quality fluctuations is effectively identified. By analyzing the matrix, the process nodes with greater influence are optimized and adjusted to improve product quality.

[0020] Step 4: Use the multiple sample indicator deviation sets to traverse the process-indicator degree matrix to trace the production quality and locate H risk process nodes, wherein the H risk process nodes have H risk contribution degree identifiers.

[0021] Specifically, multiple sample indicator deviation sets refer to the deviation of each sample from the standard quality indicator during the production process. Each sample indicator deviation set includes N sample indicator deviations of N extraction quality indicators, that is, the percentage of deviation from the standard value. Multiple sample indicator deviation sets are used to traverse the process-indicator degree matrix to evaluate the quality deviation of each sample compared to the standard value, and then locate the process nodes that may have risks. The relationship between the indicator deviation data of all samples (such as protein deviation, amino acid deviation, etc.) and the process nodes is mapped to the process-indicator degree matrix, and the specific impact of each process node on the quality indicator is evaluated, and then the risk contribution of each process node is determined. Traverse the process-indicator degree matrix, calculate the risk contribution under the current sample indicator deviation, and add the calculated risk contribution to the cumulative risk contribution of the corresponding process node.

[0022] By analyzing multiple sample indicator deviation sets and process-indicator degree matrices, the process nodes that contribute the most to quality risk, i.e., H risk process nodes, are located, and the risk contribution of each process node in each sample indicator deviation set is determined and added together to obtain the degree of influence of each process node on the production quality indicator deviation. The number of risk process nodes is less than or equal to the total number of process nodes in the sea cucumber extraction process line. For each risk process node, by cumulatively calculating its contribution to the quality indicator, a risk contribution degree identifier is finally obtained, which reflects the risk level of each node. By traversing the sample indicator deviation set and combining the process-indicator degree matrix, the most critical risk process nodes in the production process can be effectively identified, and the process nodes can be sorted according to the risk contribution of each process node, so as to prioritize the optimization of process nodes with higher risks, reduce quality fluctuations, and improve production efficiency.

[0023] Step 5: According to the H risk contribution degrees and the standard procedures of the sea cucumber extraction process line, the H risk process nodes are optimized and graded to obtain multiple levels of nodes to be optimized.

[0024] Specifically, according to the standard procedure of the sea cucumber extraction process line, determine the execution order of each process node in the process. The standard procedure is the standard execution order in the sea cucumber extraction process, which refers to the order of execution of each process node specified in the production process to ensure the collaboration and smooth connection between each process step. Combined with the risk contribution of each process node and its position in the standard procedure, the optimization priority of each process node is calculated. At the same time, the stable control cycle, process optimization cost and process optimization complexity of each process node are considered to calculate the optimization risk quantification value of each process node, which reflects the urgency of the optimization risk of each process node. The larger the optimization risk quantification value, the higher the priority of the node optimization.

[0025] Risky process nodes are graded according to their risk contribution, optimization goals, and process execution standards. The optimization levels are usually divided into different levels according to the urgency of optimization (such as high-risk nodes, medium-risk nodes, and low-risk nodes). Nodes are sorted according to their risk contribution and divided into different levels. The execution order of process nodes will affect their optimization priority. If a high-risk node is at the front of the standard process, its optimization must be performed as soon as possible to avoid affecting subsequent processes. On the contrary, if a low-risk node is at the back of the standard process, the optimization time can be slightly delayed. By prioritizing the optimization of high-risk nodes, the production of unqualified products can be reduced, thereby improving production efficiency and stability.

[0026] Step six: taking the multi-level nodes to be optimized as the optimization direction, performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and using the process optimization results to update the process parameters of the sea cucumber extraction process line.

[0027] Specifically, the multi-level nodes to be optimized are to classify the H risk process nodes into optimization levels. Each level represents an optimization stage. Different optimization levels are gradually adjusted for different quality problems and optimization goals. The selection of multi-level nodes to be optimized means that through layer-by-layer optimization and improvement, the optimization result of each node can have the greatest impact on the quality improvement of the entire process. According to the risk analysis of the process nodes, multi-level nodes to be optimized are selected as the optimization direction. According to the H process execution order, that is, the standard execution order of the H risk process nodes, each process node to be optimized is optimized and the control parameters are determined.

[0028] According to the control parameters, the process parameters of the sea cucumber extraction process line are updated, and quality tests (such as protein, amino acid, salmonella content, etc.) are performed to detect whether the quality of the sea cucumber extract still has deviations. If the quality deviation still exists, the process optimization needs to be continued. The results of each optimization will affect the process parameters of the sea cucumber extraction process line and be used in the next production to ensure that the optimization effect continues to work. In some cases, the results after the first level of optimization are still not ideal, and the next level of optimization is entered, that is, the process parameters are adjusted more deeply. Each level of optimization is based on the feedback of the previous level, and the entire process is gradually improved until the ideal quality standard is finally reached. When the key quality indicators of the sea cucumber full nutrition extract (such as protein content, amino acid content, etc.) have met the standards after optimization at a certain level, and the deviation is zero, the optimization process stops. Through multi-level progressive optimization, the key nodes in the sea cucumber extraction process are gradually adjusted, and the quality deviation can be gradually eliminated. The update of the process parameters after each optimization provides effective guidance for subsequent production, ensuring that the product quality stably reaches the expected standards in each batch. The optimization process relies on continuous testing and feedback, so that each level of optimization is built on the previous level, thus achieving comprehensive and systematic process improvement.

[0029] Furthermore, step one of this application includes: A sampling time window, a sampling confidence interval and a sampling confidence threshold are preset; the sampling time window is used as a sampling interval constraint to sample the sea cucumber full nutrient extract in the finished product stage of the sea cucumber extraction process line to obtain K spare extracts, wherein the K spare extracts have K sampling time identifiers; the production process of the K spare extracts is traced to obtain K process parameter sequences; the sampling confidence interval is used as a grouping constraint, and the K spare extracts are classified into M groups of spare extracts according to the K sampling time identifiers, wherein M is a positive integer less than K; after the M groups of spare extracts are evaluated using the K process parameter sequences, the sampling confidence threshold is used as a screening condition to screen the M groups of spare extracts to obtain the multiple sample extracts.

[0030] Specifically, in the quality traceability process, the sampling parameters need to be set first, including the sampling time window, sampling confidence interval and sampling confidence threshold. The sampling time window refers to a set time range, which is used to determine the sampling time within the time period. The sampling time window determines the sampling time interval, that is, sampling can only be performed within this time period. The sampling confidence interval is a parameter to ensure the accuracy of the data when sampling. It refers to the allowable error interval between the sampling time points, that is, in the setting of the sampling interval, a certain confidence level is guaranteed to ensure the reliability of the sampling. The sampling confidence threshold is used to screen and evaluate the quality of the sampled data. The sampled data will only be included in the analysis if it meets certain confidence requirements. For example, if the sampling time window is set to 2 hours, it means that samples are collected every 2 hours during the production process. The sampling confidence interval is set to ±5 minutes, which means that the actual sampling time point can be carried out within ±5 minutes of the preset time point. The sampling confidence threshold is set to 0.95, which means that only when the confidence level of the sampled data reaches more than 95%, the collected data will be used as a valid sample for subsequent analysis.

[0031] The sampling time window is used as a sampling interval constraint, that is, during the sampling process, the time interval between sampling is set so that the sampling activities do not overlap and meet the sampling standards. According to the sampling time window, the sea cucumber full nutrition extract is sampled at the finished product stage of the sea cucumber extraction process line to obtain K spare extracts, each of which corresponds to a sampling time identifier, which is used to identify the specific time point of sample collection. The finished product stage of the sea cucumber extraction process line refers to the stage in the production process where the sea cucumber full nutrition extract is finally formed after extraction, concentration and other treatments. At this stage, the extract is a semi-finished product or final product. Only after necessary quality inspection can it be determined whether it meets the standards and proceed to the next step.

[0032] For each spare extract, a production process traceability analysis is conducted to review and analyze all key process nodes that the extract has experienced during the production process. The traceability analysis will review the production records of each spare extract, including all process parameters involved (such as extraction time, temperature, pressure, etc.) and equipment operating conditions. After tracing the production process of K spare extracts, a process parameter sequence is established for each extract, that is, a record of the changes in the process parameters of each sample as the production process changes, reflecting every detail of the production process and helping to analyze the relationship between these parameters and the quality of the final product. The process parameter sequence refers to the change record of all process control parameters involved (such as temperature, pressure, time, pH value, solvent concentration, etc.) throughout the production process. It consists of a set of time series process data, and each data point represents the process conditions at a specific moment or stage.

[0033] According to the sampling confidence interval, the K spare extracts are divided into M groups of spare extracts according to the sampling time identification to ensure that the extracts in each group have relatively similar production times. The classified M groups of spare extracts are subjected to process evaluation to evaluate the impact of different production conditions on the quality of the extracts. Process evaluation refers to the evaluation of the impact of different process conditions on the quality of the final product based on the collected process parameter sequence. Usually, the process similarity of each combination in each group of spare extracts is calculated to obtain the M group process similarity set corresponding to the M group process parameter sequence of the M group of spare extracts.

[0034] After the process evaluation, the extracts that meet the quality standards are screened out from the M groups of spare extracts according to the sampling confidence threshold, that is, the extracts whose process similarity meets the sampling confidence threshold are screened out from each group of process similarity sets. Only those spare extracts that meet the sampling confidence threshold requirements in the process evaluation will be finally selected as multiple sample extracts to obtain multiple sample extracts. By setting the sampling time window, confidence interval and confidence threshold, it is ensured that the collected data has high accuracy and reliability, avoiding the impact of data deviation on quality analysis, and conducting process traceability and parameter sequence analysis of K spare extracts to reveal the impact of different production conditions on product quality, ensuring that the samples finally used for quality evaluation have sufficient confidence and quality standards, and avoiding the overall analysis results affected by samples that do not meet quality standards.

[0035] Furthermore, the present application also includes the following steps: According to the mapping relationship between the M groups of spare extracts and the K spare extracts, the K process parameter sequences are classified into M groups of process parameter sequences; the process importance is assigned to the sea cucumber extraction process line to obtain W node importances of the W extraction process nodes, wherein W is a positive integer greater than or equal to H; the first process parameter sequence and the second process parameter sequence are extracted from the first group of process parameter sequences; after the W node similarities of the first process parameter sequence and the second process parameter sequence at the W extraction process nodes are obtained by using the Pearson correlation coefficient to calculate, the W node similarities are weightedly calculated using the W node importances to obtain a first process similarity; by analogy, the first group of process parameter sequences are combined and enumerated and the process similarity is calculated to obtain a first group of process similarity set of the first group of process parameter sequences; according to the first group of process similarity set, a first group of sample extracts whose process similarities all meet the sampling confidence threshold are screened in the first group of spare extracts; by analogy, the multiple sample extracts are screened from the M groups of spare extracts.

[0036] Specifically, M groups of spare extracts are formed by grouping K spare extracts, and the extracts in each group have similar sampling times or process conditions. The mapping relationship is the correspondence between K spare extracts and M groups of spare extracts. In this process, K spare extracts are classified according to similar process parameters to form M groups, and the samples in each group have certain similarities. That is, K process parameter sequences are classified into M groups of process parameter sequences.

[0037] The importance of each process node in the sea cucumber extraction process line is assigned, and a weight value is assigned to each node according to the degree of influence of each process node on the quality of the final product, thereby obtaining W node importances corresponding to W extraction process nodes. The importance of a node usually depends on its contribution to the final product, such as extraction temperature, extraction time, etc. W is a positive integer greater than or equal to H, that is, the number of process nodes in the sea cucumber extraction process line is greater than or equal to the number of located risk process nodes.

[0038] Randomly select one from the M groups of process parameter sequences as the first group of process parameter sequences, and arbitrarily select two process parameter sequences from the first group of process parameter sequences as the first process parameter sequence and the second process parameter sequence. Use the Pearson correlation coefficient to calculate the similarity of the first process parameter sequence and the second process parameter sequence at each process node. The Pearson correlation coefficient is a statistic that measures the degree of linear correlation between two variables. Its value ranges from -1 to 1. Close to 1 indicates a strong positive correlation, close to -1 indicates a strong negative correlation, and close to 0 indicates no correlation. The specific calculation process of the Pearson correlation coefficient is usually to first calculate the average value of the first process parameter sequence and the second process parameter sequence, then calculate the deviation product of the two process parameter sequences and sum them to obtain A; calculate the variance of each process parameter sequence, calculate the standard deviation of the two process parameter sequences based on the variance and multiply them to obtain B. At this time, the ratio of A and B is the Pearson correlation coefficient. After calculating the similarity of W process nodes, weighted calculation is performed in combination with the importance of W nodes, and each process node similarity is multiplied by each node importance, and all products are added to obtain the first process similarity.

[0039] By analogy, the first set of process parameter sequences are combined and enumerated, and the process similarity of each possible combination is calculated to form the first set of process similarity sets of the first set of process parameter sequences. Combination enumeration refers to the combination enumeration of the first set of process parameter sequences, that is, similarity calculation is performed on all possible process parameter sequences. According to the calculated first set of process similarity sets, the first set of sample extracts that meet the standards are screened out from the first set of spare extracts using the sampling confidence threshold. Only when the process similarity of the sample reaches or exceeds the preset sampling confidence threshold will it be extracted. By analogy, the above calculation and screening steps are repeated for the M sets of process parameter sequences of the M sets of spare extracts, and finally multiple sample extracts that meet the sampling confidence threshold are screened out from each group, and multiple samples with large differences in process parameters (the similarity of the process parameters meets the sampling confidence value) within an approximate time interval (sampling confidence interval) are obtained, thereby reducing the resource consumption problem caused by production quality traceability based on process approximation samples. By calculating the similarity and weighted analysis of different process parameter sequences, the most suitable process conditions can be accurately identified, thereby improving the quality stability of the extract.

[0040] Further, step three of this application includes: Historical risk traceability information is collected for the sea cucumber extraction process line to obtain W quality deviation information sets of W extraction process nodes in the sea cucumber extraction process line; the key quality indicators are used to deconstruct the W quality deviation information sets to obtain multiple groups of quality deviation frequencies of multiple extraction quality indicators, wherein the key quality indicators include protein content, fat content, amino acid content, Salmonella content, lead content and mercury content; risk contributions of the W extraction process nodes are quantified according to the multiple groups of quality deviation frequencies, and the process-indicator degree matrix is ​​constructed based on the risk contribution quantification results.

[0041] Specifically, the sea cucumber production log includes the entire process of extracting the full nutrition of sea cucumbers, including multiple process stages, such as boiling, precipitation, concentration, cooling, filtration, freeze-drying, etc. Through precise control of steps such as precipitation, cooling, and concentration, the concentration of nutrients in the sea cucumber extract can be effectively increased to ensure the quality of the final product. Strict quality control is required in each link, including monitoring of temperature, liquid level, and pressure, which helps to maintain the safety of the sea cucumber extract and the retention of nutrients, ensuring sterility and pollution-free.

[0042] The sea cucumber extraction process line refers to a series of process links in the entire sea cucumber extraction process, covering various stages from the initial processing of sea cucumbers, boiling, precipitation, concentration, cooling to freeze-drying, with the purpose of extracting the full nutritional components of sea cucumbers (such as sea cucumber peptides, sea cucumber polysaccharides, sea cucumber saponins, etc.). Comprehensive historical data collection of the sea cucumber extraction process line is carried out from the sea cucumber production log, and the deviation information of key quality indicators of each extraction process node in historical production is recorded. Historical risk traceability information collection refers to the collection and analysis of historical data of the sea cucumber extraction process line, analysis of regular quality inspections, production logs, operation records, etc. in the production process, and special attention is paid to factors that may cause quality fluctuations in the production process, including changes in various quality indicators in previous process nodes, adjustments to process parameters, and corresponding quality issues.

[0043] Key quality indicators were used to structure W sets of quality deviation information of W extraction process nodes, and the changes of key quality indicators were further analyzed. By summarizing the quality deviation information of each process node in different time periods, the frequency data of multiple quality deviations were obtained. Multiple sets of quality deviation frequencies of various extraction quality indicators were obtained, including the deviation frequencies of protein content, fat content, amino acid content, Salmonella content, lead content and mercury content, that is, the frequency of occurrence of quality deviations at the process node in different time periods or production conditions. For example, the number of times the protein content deviation of a certain process node exceeds the standard value. Protein content reflects the nutritional value of sea cucumber extract; fat content measures the lipid nutritional components of sea cucumber extract; amino acids are the basic building blocks of protein and affect its nutritional function; Salmonella content is a safety indicator, and the Salmonella content must be lower than a certain standard to ensure safety; lead content reflects the heavy metal pollution in sea cucumber extract; mercury content is also an indicator of heavy metal pollution.

[0044] According to multiple sets of quality deviation frequencies, the risk contribution of W extraction process nodes is quantified, and the frequency and amplitude of quality deviations generated by each process node are counted to quantify the contribution of each process node to quality fluctuations. In other words, the probability of quality indicator deviations occurring in W extraction process nodes under different process conditions is counted. A process-indicator degree matrix is ​​constructed based on the risk contribution quantification results. Each row in the matrix represents a process node, and each column represents a key quality indicator. The elements in the matrix represent the degree of influence of each process node on a certain quality indicator. For example, assuming there are 3 quality indicators and 3 process nodes, the process-indicator degree matrix is ​​obtained. The larger the value, the greater the impact of the process node on the corresponding quality indicator. By constructing a process-indicator degree matrix, we can intuitively understand the specific impact of each process link on product quality. Combined with the analysis of historical risk tracing and quality deviation frequency, we can accurately identify which process nodes have caused quality problems in history and help optimize the production process.

[0045] Further, as attached Figure 2 As shown, step 4 of this application includes: A first sample indicator deviation set is called from the multiple sample indicator deviation sets, wherein the first sample indicator deviation set includes N sample indicator deviations of N extraction quality indicators; the N extraction quality indicators are used to traverse the process-indicator degree matrix to obtain N groups of deviation contributions of N groups of related process nodes; the N sample indicator deviations are used to update the N groups of deviation contributions to obtain N groups of optimized contributions of the N groups of related process nodes; according to the mapping relationship between the N groups of optimized contributions and the N groups of related process nodes, the risk contributions of the W extraction process nodes are accumulated to obtain a first group of risk accumulation vectors, wherein the first group of risk accumulation vectors includes W risk accumulation coefficients; and so on, multiple groups of risk accumulation vectors of the multiple sample indicator deviation sets are analyzed to obtain; the multiple groups of risk accumulation vectors are subjected to superposition accumulation analysis to obtain W risk superposition coefficients; a risk superposition scale is preset, and the W risk superposition coefficients are traversed according to the risk superposition scale to trace and locate the H risk process nodes from the W extraction process nodes.

[0046] Specifically, a first sample indicator deviation set is randomly called from multiple sample indicator deviation sets, which includes N sample indicator deviations of N extraction quality indicators, and the deviation of each sample is the percentage of the actual measured value of the sample deviating from the standard value. According to the N extraction quality indicators, the process-indicator degree matrix is ​​traversed, and for each quality indicator, the process node associated with it and its deviation contribution are determined, and the deviation of the sample is multiplied by the degree of influence in the matrix to obtain the deviation contribution of each process node to the sample quality indicator. The N groups of associated process nodes refer to the process nodes related to the first sample indicator deviation set.

[0047] The deviations of N sample indicators are used to update N groups of deviation contributions, and N groups of optimization contributions of N groups of related process nodes are obtained. For each sample, data is extracted from the indicator deviation of the sample to update the deviation contribution of each process node. The indicator deviation of the sample is usually obtained by the percentage difference between the actual measurement and the standard value. For all samples, the optimization contribution of each process node is calculated in a similar way. The deviation contribution indicates the degree of influence of a process node deviating from the standard or ideal conditions during the production process on the product quality. The optimization contribution is the deviation contribution of each process node to the quality indicator of the sample obtained after adjustment.

[0048] Combine the optimized N groups of optimization contributions and the mapping relationship of N groups of associated process nodes to calculate the contribution of each process node to the overall risk. Each optimization contribution will be associated with a specific process node (for example, boiling ginseng, precipitation, concentration, etc.) to form a mapping relationship. The purpose of the mapping relationship is to clarify which process node provides the optimization contribution of each quality indicator, so that it can be evaluated in the entire production process which nodes are most important for risk control. For each process node, the optimization contribution of each quality indicator is weighted and accumulated using the mapping relationship of the optimization contribution to obtain the overall contribution of the process node to the risk, thereby evaluating the contribution of each node to the overall quality risk. Through cumulative calculation, the process node that contributes the most to the risk in the production process is identified.

[0049] The risk accumulation coefficient of each process node is actually a weighted sum of the contribution of each process node, and is ultimately presented as a vector, in which each element corresponds to the risk accumulation coefficient of a process node. The contribution of each process node to the overall risk in the production process is obtained, so that process nodes with greater risk contributions are given priority in the risk control process. The risk contribution of each process node is accumulated to form a complete set of risk accumulation vectors, which includes the risk contribution values ​​of all process nodes related to the first sample indicator deviation set, and is ultimately used to determine which process nodes have the most significant impact on product quality risks.

[0050] The above steps are performed for multiple sample index deviation sets to obtain multiple sets of risk accumulation vectors, that is, W risk accumulation vectors corresponding to the sample index deviation set of each sample extract. Multiple sets of risk accumulation vectors are superimposed, and the risk superposition coefficient is obtained by accumulating the risk contribution of multiple samples, that is, the risk impact of each process node is weighted superimposed. The superimposed coefficient represents the degree of risk that may occur in each process node in different production batches.

[0051] The risk superposition scale is pre-set to standardize or classify different risk superposition coefficients, so as to help identify which process nodes contribute the most to the quality risk in the entire process chain. According to the risk superposition scale, all risk superposition coefficients are traversed, and process nodes with high risk coefficients are identified and traced to obtain H risk process nodes, including all key process links that cause quality problems. Through detailed risk analysis and traceability, it is accurately identified which process nodes have the greatest impact on product quality, so as to carry out targeted optimization, construct risk accumulation vectors and superposition coefficients, quantify quality risks, identify and locate high-risk nodes in the sea cucumber extraction process, and take corresponding measures to reduce risks and improve product quality.

[0052] Further, step five of this application includes: Interactively obtain H stable control cycles, H process optimization costs and H process optimization complexities of the H risky process nodes; obtain H process execution orders of the H risky process nodes from the standard process call; pre-construct an optimized risk quantification function, and obtain H optimized risk quantification values ​​by loading the H stable control cycles, H process optimization costs, H process optimization complexities, H process execution orders and H risk contributions into the optimized risk quantification function; preset an optimization grading scale, and perform optimization hierarchical grading on the H risky process nodes according to the optimization grading scale and the H optimized risk quantification values ​​to obtain multiple levels of nodes to be optimized.

[0053] Specifically, in order to comprehensively evaluate the optimization potential of each risky process node, determine the time period, cost and complexity required for the optimization of each node. The stable control period of each risky process node refers to the time period within a certain period of time in which the quality indicators reach the target value and maintain a stable state by adjusting and optimizing the control parameters of the process node. The process optimization cost is the cost required to optimize each risky process node, including direct operating costs (such as equipment modification, consumables consumption) and indirect costs (such as training, time consumption, etc.). The complexity of process optimization is used to measure the complexity of the optimization process, including technical difficulty, operational complexity and the difficulty of required technical support.

[0054] The standard process refers to the execution order of a series of process nodes, that is, the processing order of different process nodes is determined according to the process requirements. The H process execution orders of H risk process nodes are retrieved from the standard process, that is, the position of each risk process node in the entire production process. An optimized risk quantification function is pre-constructed to quantify the risk size of different process nodes in the optimization process. The purpose of the optimized risk quantification function is to comprehensively consider multiple factors and measure the optimization urgency of each process node, so as to provide a basis for process optimization decisions. H stable control cycles, H process optimization costs, H process optimization complexities, H process execution orders and H risk contributions are loaded into the optimized risk quantification function to obtain H optimized risk quantification values. For each risk process node, its corresponding stable control cycle, optimization cost, optimization complexity, execution order and risk contribution are substituted into the optimized risk quantification function to calculate the optimized risk quantification value of each risk process node.

[0055] The optimization grading scale is a preset standard used to grade and sort different process nodes according to the optimization risk quantification value. The optimization grading scale can determine the urgency and priority of optimization of different process nodes, and is usually divided into several levels, such as high risk, medium risk, low risk, etc. According to specific production needs, set the range of optimization risk quantification values. Compare the calculated optimization risk quantification value of each process node with the preset grading scale to determine the optimization level of each node. According to the optimization risk quantification value of each process node and its corresponding optimization level, all nodes are divided into different groups of nodes to be optimized. By combining the optimization risk quantification value with the preset optimization grading scale, the optimization level to which each process node belongs is determined. Usually, the grading scale includes different risk thresholds to divide process nodes into multiple optimization levels.

[0056] Through grading, each process node is assigned an optimization priority, and the process nodes that need to be optimized are finally determined. High-risk nodes should be optimized first to reduce potential risks in the production process; medium-risk nodes can be optimized later; low-risk nodes can be optimized later if there are not enough resources. By considering the stable control cycle, optimization cost, complexity, and risk contribution of each process node, accurately evaluate and prioritize those process nodes that have the greatest impact on product quality. According to the optimization grading scale and optimization risk quantification value, unnecessary costs and complexity in the process of process optimization can be reduced, which can not only improve product quality, but also reduce uncertainty in the production process while ensuring quality.

[0057] Furthermore, the present application also includes the following steps: The optimized risk quantification function is as follows: ;in, F To optimize the risk quantification value, T To stabilize the control cycle, C Optimize costs for the process, O Optimize the complexity of the process, S For the process execution order, R Contribution to risk.

[0058] Specifically, the optimized risk quantification function is as follows: ; Among them, F is the optimization risk quantification value, which measures the size of the risk of a process node in the optimization process. The higher the value of F, the greater the optimization risk of the process node and the higher the urgency of optimization. Generally, when the F value is close to 0, it means that the optimization priority of the node is low, and when it is close to 1, it means that the optimization priority of the node is high. T is the stable control period, which refers to the time period during which the process node can maintain stable quality, usually in hours or minutes. A longer stable control period means that the node is more capable of maintaining quality consistency and stability. C is the process optimization cost, which is the cost or resource investment required to optimize a process node, including equipment upgrades, raw materials, technical support and human resources. O is the process optimization complexity, which is used to measure the complexity of the optimization process and is related to factors such as the technical difficulty of the process node, equipment requirements and required operating experience. S is the process execution order, that is, the execution order of the process node in the production process. Different process nodes will affect the operation of subsequent nodes, so their execution order has an impact on the urgency of optimization. R is the risk contribution, that is, the potential risk level of the process node. The larger the value, the greater the impact of the node on product quality and the higher the priority of its optimization.

[0059] T.O.e -R It represents the relationship between the stability, complexity and risk of process node optimization. The larger the product of the stable control period T and the process optimization complexity O, the more stable and difficult the optimization is. -R To adjust the risk contribution R, which represents the impact of risk on the optimization urgency. If R is large, e -R If R is smaller, the urgency of optimization increases; if R is smaller, the urgency of optimization decreases. C·S·(In(S)) 2 It indicates the inhibitory effect of process optimization cost, execution order, and nonlinear influence of execution order on optimization. The larger the optimization cost C, the greater the optimization pressure; the execution order S affects the importance of process nodes, and earlier nodes usually have a greater impact; and the square of the natural logarithm (In(S)) 2 It represents the nonlinear effect of the execution order S on the optimization - the earlier the node is executed, the greater the impact of the optimization. By calculating the optimization risk quantification value of each process node, those process nodes with high optimization risk quantification values ​​are given priority, thereby achieving higher production efficiency and product quality.

[0060] Furthermore, step six of this application includes: Extract the first-level optimization nodes from the multi-level nodes to be optimized; optimize the first-level optimization nodes one by one according to the H process execution orders to obtain the first-level optimization control parameters; if the first-level optimization control parameters are used to perform process parameters of the sea cucumber extraction process line, and the sea cucumber full nutrition extract after updating the process parameters has deviations in the key quality indicators, extract the second-level optimization nodes from the multi-level nodes to be optimized; use the first-level optimization control parameters as the optimization benchmark, optimize the second-level optimization nodes one by one, and obtain the second-level optimization control parameters; if the first-level optimization control parameters and the second-level optimization control parameters are used to perform process parameters of the sea cucumber extraction process line, If there is a deviation in the key quality indicator of the sea cucumber full nutrient extract after the process parameters of the sea cucumber extraction process line are updated, the third-level optimization node is extracted from the multi-level nodes to be optimized; conversely, if the deviation of the key quality indicator of the sea cucumber full nutrient extract after the process parameters of the sea cucumber extraction process line are restored to zero by using the first-level optimization control parameters and the second-level optimization control parameters, the progressive optimization is stopped; and so on, taking the multi-level nodes to be optimized as the optimization direction, multi-level progressive optimization of the sea cucumber extraction process is performed on the H risk process nodes until the deviation of the key quality indicator of the sea cucumber full nutrient extract after the process parameters are updated is restored to zero.

[0061] Specifically, the multi-level nodes to be optimized are process nodes extracted according to the risk assessment and optimization classification results, with different optimization priorities. The nodes to be optimized are divided into multiple levels (such as the first level, the second level, the third level, etc.), and are optimized in sequence. The first-level optimization nodes are extracted from the multi-level nodes to be optimized, and the first-level optimization nodes are optimized one by one according to the H process execution order, including adjusting process parameters, improving operation procedures, replacing equipment or materials, etc. Process optimization usually requires the use of appropriate optimization algorithms to select the most appropriate process parameters, including particle swarm optimization, genetic algorithm, simulated annealing algorithm, etc. Taking the particle swarm optimization algorithm as an example, the particle swarm is initialized, the position and speed of the particles are set, and they are usually generated randomly; the optimization target is defined (such as the deviation of quality indicators such as protein content or other quality indicators), and each particle updates its position according to its own optimal experience and the optimal experience of the group, and continuously updates the position until the stop criterion is met (such as reaching the maximum number of iterations or the objective function value converges).

[0062] After process optimization, the first-level optimization control parameters are determined to update the process parameters of the sea cucumber extraction process line to improve product quality. The first-level optimization control parameters are used to update the process parameters of the sea cucumber extraction process line, and the updated sea cucumber full nutrition extract is tested for deviations in key quality indicators (such as protein and amino acid content).

[0063] If there are still deviations, it means that the first-level optimization has not completely eliminated all quality deviations. Next, select the second-level optimization node and continue to optimize. If there are still deviations after the first-level optimization, use the first-level optimization control parameters as the optimization benchmark, and on this basis, optimize the second-level optimization nodes one by one to obtain the second optimization control parameters. Continue to update the process parameters of the sea cucumber extraction process line, and perform quality inspection on the updated sea cucumber full nutrition extract again to check the deviations of key quality indicators (such as protein, amino acid content, etc.). If there are still deviations, extract the third-level optimization node from the multi-level nodes to be optimized and continue to optimize.

[0064] On the contrary, if all indicators meet the standards and the deviation of the key quality indicators of the sea cucumber full nutrition extract after the process parameters are updated is zero, the progressive optimization process is stopped. By analogy, the multi-level nodes to be optimized are used as the optimization direction, and the process parameters of the sea cucumber extraction process line are continuously updated. Through progressive optimization layer by layer, it is ensured that the quality deviation of each process node is finally zero. In fact, it is a gradual adjustment and optimization of each process link to finally achieve the ideal quality standard. Multi-level progressive optimization means that in a process, each link is optimized and adjusted by step-by-step and step-by-step improvement until the expected goal or standard is achieved. In the sea cucumber extraction process, it aims to eliminate quality deviations by gradually adjusting key process nodes to ensure that the final product meets the quality standards. Each level of optimization is based on the optimization results of the previous level, so the optimization process is progressive. Through layer-by-layer optimization, the quality deviation of the sea cucumber full nutrition extract is gradually reduced, the optimal operating conditions of each process node are guaranteed, and each process node is optimized, and finally it is ensured that the sea cucumber full nutrition extract has no deviation in key quality indicators and the qualified rate of the product is improved.

[0065] In summary, the production quality traceability method of sea cucumber complete nutrition extract based on full process tracking provided by this application has the following technical effects: The method comprises the following steps: sampling a sea cucumber full nutrient extract at the finished product stage of a sea cucumber extraction process line to obtain a plurality of sample extracts; performing key quality indicator detection on the plurality of sample extracts to obtain a plurality of sample indicator deviation sets; performing process node correlation analysis based on a sea cucumber production log to obtain a process-indicator degree matrix; using the plurality of sample indicator deviation sets to traverse the process-indicator degree matrix to perform production quality traceability, and locating H risk process nodes, wherein the H risk process nodes have H risk contribution degree identifiers; optimizing the H risk process nodes according to the H risk contribution degrees and the standard procedures of the sea cucumber extraction process line to obtain a plurality of nodes to be optimized; using the plurality of nodes to be optimized as optimization directions, performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and using the process optimization results to update the process parameters of the sea cucumber extraction process line. That is to say, by sampling at the finished product stage of the sea cucumber extraction process line and conducting key quality indicator tests, different process nodes are correlated with quality indicators based on the process-indicator degree matrix, risky process nodes are identified, and multi-level progressive optimization is performed on the risky process nodes. The standard process is updated using the process optimization results, providing full traceability from production raw materials to final product quality, and improving the transparency and traceability of production quality through detailed quality data and process node analysis.

[0066] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for tracing the production quality of sea cucumber complete nutritional extract based on full-process tracking, characterized in that: include: Sampling the full nutritional extract of sea cucumber at the finished product stage of the sea cucumber extraction process line to obtain a plurality of sample extracts, wherein the sea cucumber extraction process line includes W extraction process nodes; Performing key quality index detection on the multiple sample extracts to obtain multiple sample index deviation sets; Based on the sea cucumber production log, the process node correlation analysis was carried out to obtain the process-index degree matrix; Using the multiple sample indicator deviation sets to traverse the process-indicator degree matrix to perform production quality traceability, and locate H risk process nodes, wherein the H risk process nodes have H risk contribution degree identifiers; According to the H risk contribution degrees and the standard procedures of the sea cucumber extraction process line, the H risk process nodes are optimized and graded to obtain multiple levels of nodes to be optimized; Taking the multi-level nodes to be optimized as optimization directions, performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and using the process optimization results to update the process parameters of the sea cucumber extraction process line; The process-index degree matrix is ​​traversed using the multiple sample index deviation sets to perform production quality traceability and locate H risky process nodes, including: Calling a first sample indicator deviation set from the plurality of sample indicator deviation sets, wherein the first sample indicator deviation set includes N sample indicator deviation amounts of N extraction quality indicators; Using the N extraction quality indicators to traverse the process-indicator degree matrix, obtain N groups of deviation contribution degrees of N groups of associated process nodes; Using the N sample index deviations to update the N groups of deviation contributions, to obtain N groups of optimized contributions of the N groups of associated process nodes; Accumulating risk contributions of the W extraction process nodes according to the mapping relationship between the N groups of optimization contributions and the N groups of associated process nodes to obtain a first group of risk accumulation vectors, wherein the first group of risk accumulation vectors includes W risk accumulation coefficients; By analogy, multiple groups of risk accumulation vectors of the multiple sample indicator deviation sets are obtained by analysis; Performing a superposition accumulation analysis on the multiple groups of risk accumulation vectors to obtain W risk superposition coefficients; A risk superposition scale is preset, and the W risk superposition coefficients are traversed according to the risk superposition scale to trace and locate the H risk process nodes from the W extraction process nodes.

2. The method for tracing the production quality of sea cucumber complete nutritional extract based on full process tracking as claimed in claim 1, characterized in that: Based on the sea cucumber production log, process node correlation analysis is performed to obtain the process-index matrix, which also includes: Collecting historical risk traceability information on the sea cucumber extraction process line to obtain W quality deviation information sets of W extraction process nodes in the sea cucumber extraction process line; Deconstructing the W quality deviation information sets using the key quality indicators to obtain multiple groups of quality deviation frequencies of multiple extracted quality indicators, wherein the key quality indicators include protein content, fat content, amino acid content, Salmonella content, lead content and mercury content; The risk contributions of the W extraction process nodes are quantified according to the multiple groups of quality deviation frequencies, and the process-index degree matrix is ​​constructed based on the risk contribution quantification results.

3. The method for tracing the production quality of sea cucumber complete nutritional extract based on full process tracking as claimed in claim 1, characterized in that: The H risk process nodes are optimized and graded according to the H risk contribution degrees and the standard procedures of the sea cucumber extraction process line to obtain multiple levels of nodes to be optimized, further comprising: Interactively obtaining H stable control cycles, H process optimization costs, and H process optimization complexities of the H risky process nodes; Obtaining H process execution orders of the H risky process nodes from the standard process call; Pre-constructing an optimization risk quantification function, and obtaining H optimization risk quantification values ​​by loading the H stable control cycles, H process optimization costs, H process optimization complexities, H process execution orders and H risk contributions into the optimization risk quantification function; An optimization grading scale is preset, and the H risk process nodes are optimized and graded according to the optimization grading scale and the H optimization risk quantification values ​​to obtain multiple levels of nodes to be optimized.

4. The method for tracing the production quality of sea cucumber complete nutritional extract based on full process tracking as claimed in claim 3, characterized in that: The optimized risk quantification function is as follows: ; in, F To optimize the risk quantification value, T To stabilize the control cycle, C Optimize costs for the process, O Optimize the complexity of the process, S For the process execution order, R Contribution to risk.

5. The method for tracing the production quality of sea cucumber complete nutritional extract based on full process tracking as claimed in claim 3, characterized in that: Taking the multi-level nodes to be optimized as optimization directions, performing multi-level progressive optimization of the sea cucumber extraction process on the H risk process nodes, and using the process optimization results to update the process parameters of the sea cucumber extraction process line, further comprising: Extracting first-level optimized nodes from the multiple levels of nodes to be optimized; Performing process optimization on the first-level optimization nodes one by one according to the H process execution orders to obtain first-level optimization control parameters; If the sea cucumber full nutrition extract after the process parameters of the sea cucumber extraction process line are updated by using the first-level optimization control parameters has deviations in the key quality indicators, extracting the second-level optimization nodes from the multi-level nodes to be optimized; Taking the first-level optimization control parameters as optimization benchmarks, process optimization is performed on the second-level optimization nodes one by one to obtain second-level optimization control parameters; If the sea cucumber full nutrition extract after the process parameters of the sea cucumber extraction process line are updated by using the first-level optimization control parameters and the second-level optimization control parameters has deviations in the key quality indicators, extracting the third-level optimization nodes from the multi-level nodes to be optimized; On the contrary, if the deviation of the key quality index of the sea cucumber full nutritional extract after the process parameters of the sea cucumber extraction process line are updated by using the first-level optimization control parameters and the second-level optimization control parameters is zero, the progressive optimization is stopped; By analogy, the multi-level nodes to be optimized are used as optimization directions, and multi-level progressive optimization of the sea cucumber extraction process is performed on the H risk process nodes until the deviation of the key quality indicator of the sea cucumber full nutrient extract after the process parameters are updated is zero.

6. The method for tracing the production quality of sea cucumber complete nutritional extract based on full process tracking as claimed in claim 2, characterized in that: The sea cucumber full nutrition extract was sampled at the finished product stage of the sea cucumber extraction process line to obtain multiple sample extracts, including: Preset sampling time window, sampling confidence interval and sampling confidence threshold; The sampling time window is used as a sampling interval constraint to sample the sea cucumber full nutrition extract at the finished product stage of the sea cucumber extraction process line to obtain K spare extracts, wherein the K spare extracts have K sampling time identifiers; Tracing the production process of the K reserve extracts to obtain K process parameter sequences; Taking the sampling confidence interval as a grouping constraint, classifying the K reserve extracts into M groups of reserve extracts according to the K sampling time identifiers, wherein M is a positive integer less than K; After the K process parameter sequences are used to perform process evaluation on the M groups of spare extracts, the sampling confidence threshold is used as a screening condition to screen the M groups of spare extracts to obtain the multiple sample extracts.

7. The method for tracing the production quality of sea cucumber complete nutritional extract based on full process tracking as claimed in claim 6, characterized in that: After the K process parameter sequences are used to perform process evaluation on the M groups of spare extracts, the sampling confidence threshold is used as a screening condition to screen the M groups of spare extracts to obtain the multiple sample extracts, further comprising: According to the mapping relationship between the M groups of spare extracts and the K spare extracts, the K process parameter sequences are classified into M groups of process parameter sequences; Assigning process importance to the sea cucumber extraction process line to obtain W node importances of the W extraction process nodes, wherein W is a positive integer greater than or equal to H; Extracting a first process parameter sequence and a second process parameter sequence from the first group of process parameter sequences; After obtaining W node similarities of the first process parameter sequence and the second process parameter sequence at the W extraction process nodes by using the Pearson correlation coefficient, weighting the W node similarities by using the W node importances to obtain a first process similarity; Similarly, the first group of process parameter sequences is combined and enumerated and the process similarity is calculated to obtain a first group of process similarity sets of the first group of process parameter sequences; According to the first group of process similarity sets, a first group of sample extracts whose process similarities all meet the sampling confidence threshold are screened in the first group of spare extracts; In this way, the multiple sample extracts are obtained by screening the M groups of spare extracts.

Images