A method and system for detecting active components of plant protein meat
Through multi-stage sample collection and detection, combined with preset synthetic reaction routes and reaction mechanisms, the proportion coefficient of active components of plant protein meat is identified and verified, which solves the problem of inaccurate detection results in the existing technology and improves the accuracy of detection Sex and reliability.
Patent Information
- Application Number
- CN202410300364.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-15
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-03-15
AI Technical Summary
The existing methods for detecting active components of plant protein meat have faults between sample collection and active components analysis, and lack of multi-stage evaluation, resulting in low accuracy and reliability of the detection results, and the inability to correct the verification deviation in time and accurately.
By obtaining the predetermined activity detection component information of the target plant protein meat, identifying multiple synthesis process nodes, performing multi-stage sample collection and detection, using preset synthesis reaction routes and reaction mechanisms to identify component content proportional coefficients, verify and correct the detection Results for improved accuracy.
The accuracy and reliability of the detection of active components of plant protein meat are improved, the accuracy and stability of the detection results are ensured, and the problem of inaccurate detection results in the prior art is solved.
Smart Images

Figure CN118258967B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of food detection, and in particular to a method and system for detecting active components of plant protein meat. Background Art
[0002] As healthy eating is increasingly valued, plant protein meat, as a new type of food that is nutritious, healthy and environmentally friendly, is gradually gaining favor among consumers. Plant protein meat not only has a similar taste and texture to animal meat, but is also rich in a variety of essential amino acids and trace elements, which is of great significance for improving people's dietary structure and promoting sustainable development. However, in order to ensure the quality and safety of plant protein meat, accurate detection of its active components is crucial. The existing detection methods for active components of plant protein meat have a gap between sample collection and active ingredient analysis, and lack a comprehensive multi-stage evaluation, resulting in low accuracy and reliability of the results. In addition, the existing methods lack effective means for verification deviation and feedback correction, and cannot make timely and accurate corrections to the test results, affecting the accuracy of the final active component detection results. Summary of the invention
[0003] The embodiments of the present application provide a method and system for detecting active components of plant protein meat, which solves the technical problem of inaccurate active component detection results in the prior art.
[0004] In view of the above problems, the embodiments of the present application provide a method and system for detecting active components of plant protein meat.
[0005] In a first aspect of an embodiment of the present application, a method for detecting active components of plant protein meat is provided, the method comprising:
[0006] Obtaining information on predetermined active detection components of target plant protein meat;
[0007] Acquire multiple synthesis processes of the target plant protein meat, and identify the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes;
[0008] Establishing connections between the multiple key process nodes and a sampling module, and performing sample collection on the multiple key process nodes through the sampling module to obtain multi-stage sample collection results;
[0009] Based on the predetermined active detection component information, the active component detection platform is matched, and the active component detection is performed on the multi-stage sample collection results to obtain a multi-stage detection result;
[0010] Obtaining the preset synthesis reaction routes and preset reaction mechanisms of the multiple key process nodes, identifying the content relationship of the active components of the multiple key process nodes, and obtaining the multi-stage component content ratio coefficients;
[0011] Verifying the multi-stage detection results based on the multi-stage component content ratio coefficient to obtain a verification deviation;
[0012] If the verification deviation value is within a predetermined deviation range, the multi-stage detection result is fed back and corrected using the verification deviation value to obtain an active component detection result.
[0013] A second aspect of the embodiment of the present application provides a plant protein meat active component detection system, the system comprising:
[0014] An information acquisition module, the information acquisition module is used to obtain predetermined active detection component information of the target plant protein meat;
[0015] A first identification module, wherein the first identification module is used to obtain multiple synthesis processes of the target plant protein meat, and identify the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes;
[0016] A collection module, the collection module is used to establish a connection between the multiple key process nodes and the sampling module, and perform sample collection on the multiple key process nodes through the sampling module to obtain multi-stage sample collection results;
[0017] A detection module, the detection module is used to match an active component detection platform based on the predetermined active detection component information, perform active component detection on the multi-stage sample collection results, and obtain a multi-stage detection result;
[0018] A second identification module, the second identification module is used to obtain the preset synthesis reaction routes and preset reaction mechanisms of the multiple key process nodes, identify the content relationship of the active components of the multiple key process nodes, and obtain the multi-stage component content ratio coefficient;
[0019] A verification module, the verification module is used to verify the multi-stage detection results based on the multi-stage component content ratio coefficient to obtain a verification deviation;
[0020] A correction module is used to feedback and correct the multi-stage detection result with the verification deviation value if the verification deviation value is within a predetermined deviation range, so as to obtain an active component detection result.
[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0022] First, the predetermined active detection component information of the target plant protein meat is obtained. Then, multiple synthesis processes of the target plant protein meat are obtained, and the active component influence is identified for these processes to obtain multiple key process nodes. Then, the connection between these key process nodes and the sampling module is established, and sample collection is performed on these key process nodes through the sampling module to obtain multi-stage sample collection results. The active component detection platform is matched with the predetermined active detection component information, and the multi-stage sample collection results are tested for active components to obtain multi-stage test results. Then, the preset synthesis reaction routes and preset reaction mechanisms of these key process nodes are obtained, and the content relationship of the active components of these nodes is identified to obtain the multi-stage component content ratio coefficient. Finally, the multi-stage test results are verified based on the multi-stage component content ratio coefficient to obtain the verification deviation. If the verification deviation value is within the predetermined deviation range, the verification deviation value is used to feedback and correct the multi-stage test results, thereby obtaining the active component test results. The technical problem of inaccurate active component test results in the prior art is solved, and the technical effect of improving the detection accuracy is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0024] Figure 1 A schematic diagram of a process for detecting active components of plant protein meat provided in an embodiment of the present application;
[0025] Figure 2 A schematic diagram of the structure of a plant protein meat active component detection system provided in an embodiment of the present application.
[0026] Explanation of the reference numerals: information acquisition module 11 , first recognition module 12 , acquisition module 13 , detection module 14 , second recognition module 15 , verification module 16 , correction module 17 . DETAILED DESCRIPTION
[0027] The embodiments of the present application solve the technical problem of inaccurate active component detection results in the prior art by providing a method and system for detecting active components in plant protein meat.
[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0029] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices. Embodiment 1
[0030] like Figure 1 As shown, the embodiment of the present application provides a method for detecting active components of plant protein meat, wherein the method comprises:
[0031] Obtaining information on predetermined active detection components of target plant protein meat;
[0032] The predetermined active detection component information includes active ingredients such as proteins, peptides, amino acids, minerals, vitamins, etc. Obtaining the predetermined active detection component information of the target plant protein meat can provide a clear target and basis for subsequent detection of active components of the plant protein meat.
[0033] Acquire multiple synthesis processes of the target plant protein meat, and identify the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes;
[0034] The production process of plant protein meat includes multiple synthesis steps. Plant protein is processed by chemical separation, heating, extrusion, cooling, shaping and other processes to produce plant protein meat. Each synthesis process has different degrees of influence on the active ingredients. By identifying the impact of each synthesis process on the active ingredients, the contribution and potential impact of each step on the active components can be evaluated.
[0035] Furthermore, the method of obtaining multiple synthesis processes of the target plant protein meat and identifying the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes includes:
[0036] Obtaining a first synthesis process from the plurality of synthesis processes, and performing historical synthesis data mining on the first synthesis process to obtain a first component content record data set and a second component content record data set;
[0037] The first component content record data set is the active component record data before the first synthesis process is performed, and the second component content record data set is the active component record data after the first synthesis process is performed;
[0038] Comparing the component contents before and after the process is performed based on the first component content record data set and the second component content record data set to obtain a first component content deviation data set;
[0039] Performing a discrete value evaluation on the first component content deviation data set, and performing data trimming based on the discrete value evaluation result to obtain a first component calibration content deviation;
[0040] If the deviation of the calibrated content of the first component is greater than or equal to a predetermined deviation threshold, the first synthesis process is added to the multiple key process nodes.
[0041] A process is selected from multiple synthesis processes as the first synthesis process, and historical synthesis data mining is performed on the first synthesis process to obtain a first component content record data set and a second component content record data set. These two data sets provide a direct comparison basis for the active component content before and after the process is executed. Among them, the first component content record data set reflects the active component content before the first synthesis process is executed, while the second component content record data set records the active component content after the process is executed. By comparing the first component content record data set and the second component content record data set, a first component content deviation data set can be obtained, which reflects the change in the active component content before and after the first synthesis process is executed. In order to ensure the accuracy and reliability of the data, it is necessary to perform a discrete value evaluation on the first component content deviation data set to identify and exclude possible abnormal values or erroneous data. Based on the results of the discrete value evaluation, data trimming can be performed to obtain a more accurate first component calibration content deviation. Finally, the first component calibration content deviation is compared with a predetermined deviation threshold. If the first component calibration content deviation is greater than or equal to the predetermined deviation threshold, the first synthesis process is added to multiple key process nodes.
[0042] Further, the performing discrete value evaluation on the first component content deviation data set, and performing data trimming based on the discrete value evaluation result to obtain the first component calibration content deviation includes:
[0043] Performing data cluster fitting on the first component content deviation data set to obtain a first fitting data cluster;
[0044] calculating a first anomaly probability of the first fitted data cluster;
[0045] If the first abnormal probability is less than a predetermined abnormal probability, a mean calculation is performed on the data in the first fitting data cluster to obtain the first component calibration content deviation.
[0046] A certain number of sample points are randomly selected from the first component content deviation data set for preliminary fitting of a model, and the distance from all points in the data set to the fitting model is calculated to evaluate the fitness of the model. At the same time, a threshold is set, and only points with a distance less than the threshold are considered to be inliers of the model (i.e., data points that conform to the model). The number of inliers considered by the current model is counted. Repeat the iteration and select the model with the largest number of inliers as the final optimal model. After the optimal model is determined, all data points identified as inliers by the model constitute the first fitting data cluster. The first abnormal probability is obtained by calculating the first fitting data cluster. Compare the first abnormal probability with the predetermined abnormal probability. If the first abnormal probability is less than the predetermined abnormal probability, the data in the first fitting data cluster are averaged to obtain the first component calibration content deviation.
[0047] Furthermore, the calculating of the first abnormal probability of the first fitting data cluster includes:
[0048] Obtaining a first difference set between the first fitting data cluster and the first component content deviation data set;
[0049] Counting the amount of first difference set data in the first difference set;
[0050] Counting the total amount of first data in the first component content deviation data set;
[0051] The ratio of the first difference set data volume to the first total data volume is used as the first abnormality probability.
[0052] The first difference set is the data points that belong to the first component content deviation data set but are not in the first fitting data cluster. These points represent outliers that do not conform to the main distribution pattern of the cluster. The number of data points included in the first difference set is counted, and the total amount of data in the first component content deviation data set is counted. The amount of data in the first difference set is divided by the total amount of the first data, and the result is the first anomaly probability.
[0053] Establishing connections between the multiple key process nodes and a sampling module, and performing sample collection on the multiple key process nodes through the sampling module to obtain multi-stage sample collection results;
[0054] The sampling module is used to accurately collect samples from key process nodes. By connecting the sampling module with multiple key process nodes, sample collection can be performed on multiple key process nodes to obtain multi-stage sample collection results.
[0055] Based on the predetermined active detection component information, the active component detection platform is matched, and the active component detection is performed on the multi-stage sample collection results to obtain a multi-stage detection result;
[0056] The active ingredient detection platform is used to perform qualitative and quantitative analysis on the active ingredients in the sample. The appropriate active ingredient detection platform is matched by the predetermined active detection ingredient information, and the multi-stage sample collection results are used for active component detection, including analyzing the samples collected at each stage one by one to obtain information such as the content, distribution and state of the active ingredients, thereby obtaining multi-stage detection results.
[0057] Obtaining the preset synthesis reaction routes and preset reaction mechanisms of the multiple key process nodes, identifying the content relationship of the active components of the multiple key process nodes, and obtaining the multi-stage component content ratio coefficients;
[0058] By obtaining the preset synthesis reaction route and reaction mechanism and identifying the content relationship of the active components at multiple key process nodes, the multi-stage component content ratio coefficient can be obtained. The multi-stage component content ratio coefficient reflects the relative content change of the active components between different process nodes.
[0059] Furthermore, the multi-stage component content ratio coefficient is obtained, including:
[0060] Based on the preset synthesis reaction route, the plurality of key process nodes are subjected to serialization processing to obtain a process node sequence;
[0061] Extracting a first node and a second node in the process node sequence, wherein the first node and the second node are two adjacent process nodes;
[0062] Based on the preset reaction mechanism, the first node and the second node are identified with the same active component content ratio to obtain a first component content ratio coefficient;
[0063] The first component content proportional coefficient is added to the multi-stage component content proportional coefficients.
[0064] In order to obtain the multi-stage component content proportional coefficient, specifically, according to the preset synthesis reaction route, multiple key process nodes are serialized. In the process node sequence, two adjacent process nodes are extracted as the first node and the second node respectively. Based on the preset reaction mechanism, the first node and the second node are identified for the same active component content ratio, and the content proportional relationship of the active component from the first node to the second node can be determined. According to the identified same active component content proportional relationship, the first component content proportional coefficient can be calculated. The first component content proportional coefficient indicates how the content of the active component changes from the first node to the second node. Finally, the calculated first component content proportional coefficient is added to the multi-stage component content proportional coefficient.
[0065] Verifying the multi-stage detection results based on the multi-stage component content ratio coefficient to obtain a verification deviation;
[0066] After obtaining the multi-stage component content proportional coefficients, these coefficients need to be verified to ensure their accuracy and reliability. Specifically, the multi-stage component content proportional coefficients can be compared with the multi-stage test results, and the deviation between them can be calculated to obtain the accuracy verification deviation for evaluating the multi-stage component content proportional coefficients.
[0067] Furthermore, after obtaining the calibration deviation, it also includes:
[0068] If the verification deviation value is not within the predetermined deviation range, abnormal node positioning is performed on the multiple key process nodes to obtain a first abnormal node and a first abnormally active component;
[0069] Acquiring process execution environment information of the first abnormal node;
[0070] Performing component variation identification on the process execution environment information and the first abnormally active component to obtain a first variation probability;
[0071] If the first mutation probability is greater than or equal to a predetermined mutation probability, a synthetic environment warning is issued to the first abnormal node.
[0072] When the verification deviation value is not within the predetermined deviation range, it is necessary to locate abnormal nodes for multiple key process nodes. By comparing the actual test results with the theoretical values, it is possible to identify which nodes have large deviations in the content of active components. These nodes are marked as first abnormal nodes, and the corresponding active components are called first abnormal active components. Next, obtain the process execution environment information of the first abnormal node, such as excessive temperature may cause variation. Then, component variation identification is performed on the process execution environment information and the first abnormal active component. By analyzing the relationship between environmental information and the content of active components, the degree of influence of environmental factors on the variation of active components can be evaluated to obtain the first variation probability. If the first variation probability is greater than or equal to the predetermined variation probability, the system will issue a synthetic environmental warning for the first abnormal node.
[0073] Furthermore, obtaining the first mutation probability includes:
[0074] Acquire a first stable temperature range of the first abnormally active component;
[0075] A deviation comparison is performed between the process execution environment information and the first stable temperature range, and the first variation probability is generated based on the comparison result.
[0076] The stable temperature range refers to the range within which the chemical properties and activity of the active component can remain stable and are not prone to mutation. By obtaining the first stable temperature range of the first abnormal active component, the actual temperature in the process execution environment information can be compared with the first stable temperature range for deviation, and based on the comparison result, the first mutation probability can be generated.
[0077] If the verification deviation value is within a predetermined deviation range, the multi-stage detection result is fed back and corrected using the verification deviation value to obtain an active component detection result.
[0078] When the verification deviation value is within the predetermined deviation range, it indicates that the deviation between the multi-stage test result and the theoretical value is acceptable and the production process is relatively stable. In order to improve the accuracy of the active component test results, the verification deviation value can be used to feedback and correct the multi-stage test results.
[0079] In summary, the embodiments of the present application have at least the following technical effects:
[0080] First, the predetermined active detection component information of the target plant protein meat is obtained. Then, multiple synthesis processes of the target plant protein meat are obtained, and the active component influence is identified for these processes to obtain multiple key process nodes. Then, the connection between these key process nodes and the sampling module is established, and sample collection is performed on these key process nodes through the sampling module to obtain multi-stage sample collection results. The active component detection platform is matched with the predetermined active detection component information, and the multi-stage sample collection results are tested for active components to obtain multi-stage test results. Then, the preset synthesis reaction routes and preset reaction mechanisms of these key process nodes are obtained, and the content relationship of the active components of these nodes is identified to obtain the multi-stage component content ratio coefficient. Finally, the multi-stage test results are verified based on the multi-stage component content ratio coefficient to obtain the verification deviation. If the verification deviation value is within the predetermined deviation range, the verification deviation value is used to feedback and correct the multi-stage test results, thereby obtaining the active component test results. The technical problem of inaccurate active component test results in the prior art is solved, and the technical effect of improving the detection accuracy is achieved. Embodiment 2
[0081] Based on the same inventive concept as the method for detecting active components of plant protein meat in the aforementioned embodiment, Figure 2 As shown, the present application provides a plant protein meat active component detection system, and the system and method embodiments in the present application embodiment are based on the same inventive concept. Among them, the system includes:
[0082] An information acquisition module 11, wherein the information acquisition module 11 is used to obtain predetermined active detection component information of the target plant protein meat;
[0083] A first identification module 12, the first identification module 12 is used to obtain multiple synthesis processes of the target plant protein meat, and identify the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes;
[0084] A collection module 13, the collection module 13 is used to establish a connection between the multiple key process nodes and the sampling module, and perform sample collection on the multiple key process nodes through the sampling module to obtain multi-stage sample collection results;
[0085] A detection module 14, wherein the detection module 14 is used to match an active component detection platform based on the predetermined active component detection information, perform active component detection on the multi-stage sample collection results, and obtain a multi-stage detection result;
[0086] The second identification module 15 is used to obtain the preset synthesis reaction routes and preset reaction mechanisms of the multiple key process nodes, identify the content relationship of the active components of the multiple key process nodes, and obtain the multi-stage component content ratio coefficient;
[0087] A verification module 16, the verification module 16 is used to verify the multi-stage detection results based on the multi-stage component content ratio coefficient to obtain a verification deviation;
[0088] The correction module 17 is used to feedback and correct the multi-stage detection result with the verification deviation value if the verification deviation value is within a predetermined deviation range, so as to obtain the active component detection result.
[0089] Furthermore, the first identification module 12 is used to execute the following method:
[0090] Obtaining a first synthesis process from the plurality of synthesis processes, and performing historical synthesis data mining on the first synthesis process to obtain a first component content record data set and a second component content record data set;
[0091] The first component content record data set is the active component record data before the first synthesis process is performed, and the second component content record data set is the active component record data after the first synthesis process is performed;
[0092] Comparing the component contents before and after the process is performed based on the first component content record data set and the second component content record data set to obtain a first component content deviation data set;
[0093] Performing a discrete value evaluation on the first component content deviation data set, and performing data trimming based on the discrete value evaluation result to obtain a first component calibration content deviation;
[0094] If the deviation of the calibrated content of the first component is greater than or equal to a predetermined deviation threshold, the first synthesis process is added to the multiple key process nodes.
[0095] Furthermore, the first identification module 12 is used to execute the following method:
[0096] Performing data cluster fitting on the first component content deviation data set to obtain a first fitting data cluster;
[0097] calculating a first anomaly probability of the first fitted data cluster;
[0098] If the first abnormal probability is less than a predetermined abnormal probability, a mean calculation is performed on the data in the first fitting data cluster to obtain the first component calibration content deviation.
[0099] Furthermore, the first identification module 12 is used to execute the following method:
[0100] Obtaining a first difference set between the first fitting data cluster and the first component content deviation data set;
[0101] Counting the amount of first difference set data in the first difference set;
[0102] Counting the total amount of first data in the first component content deviation data set;
[0103] The ratio of the first difference set data volume to the first total data volume is used as the first abnormality probability.
[0104] Furthermore, the second identification module 15 is used to execute the following method:
[0105] Based on the preset synthesis reaction route, the plurality of key process nodes are subjected to serialization processing to obtain a process node sequence;
[0106] Extracting a first node and a second node in the process node sequence, wherein the first node and the second node are two adjacent process nodes;
[0107] Based on the preset reaction mechanism, the first node and the second node are identified with the same active component content ratio to obtain a first component content ratio coefficient;
[0108] The first component content proportional coefficient is added to the multi-stage component content proportional coefficients.
[0109] Furthermore, the correction module 17 is used to execute the following method:
[0110] If the verification deviation value is not within the predetermined deviation range, abnormal node positioning is performed on the multiple key process nodes to obtain a first abnormal node and a first abnormally active component;
[0111] Acquiring process execution environment information of the first abnormal node;
[0112] Performing component variation identification on the process execution environment information and the first abnormally active component to obtain a first variation probability;
[0113] If the first mutation probability is greater than or equal to a predetermined mutation probability, a synthetic environment warning is issued to the first abnormal node.
[0114] Furthermore, the correction module 17 is used to execute the following method:
[0115] Acquire a first stable temperature range of the first abnormally active component;
[0116] A deviation comparison is performed between the process execution environment information and the first stable temperature range, and the first variation probability is generated based on the comparison result.
[0117] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0118] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
[0119] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.
Claims
1. A method for detecting active components of plant protein meat, characterized in that: The method comprises: Obtaining information on predetermined active detection components of target plant protein meat; Acquire multiple synthesis processes of the target plant protein meat, and identify the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes; Establishing connections between the multiple key process nodes and a sampling module, and performing sample collection on the multiple key process nodes through the sampling module to obtain multi-stage sample collection results; Based on the predetermined active detection component information, the active component detection platform is matched, and the active component detection is performed on the multi-stage sample collection results to obtain a multi-stage detection result; Obtaining the preset synthesis reaction routes and preset reaction mechanisms of the multiple key process nodes, identifying the content relationship of the active components of the multiple key process nodes, and obtaining the multi-stage component content ratio coefficients; Verifying the multi-stage detection results based on the multi-stage component content ratio coefficient to obtain a verification deviation; If the verification deviation value is within a predetermined deviation range, the multi-stage detection result is fed back and corrected using the verification deviation value to obtain an active component detection result; The method of obtaining multiple synthesis processes of the target plant protein meat and identifying the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes includes: Obtaining a first synthesis process from the plurality of synthesis processes, and performing historical synthesis data mining on the first synthesis process to obtain a first component content record data set and a second component content record data set; The first component content record data set is the active component record data before the first synthesis process is performed, and the second component content record data set is the active component record data after the first synthesis process is performed; Comparing the component contents before and after the process is performed based on the first component content record data set and the second component content record data set to obtain a first component content deviation data set; Performing a discrete value evaluation on the first component content deviation data set, and performing data trimming based on the discrete value evaluation result to obtain a first component calibration content deviation; If the deviation of the calibrated content of the first component is greater than or equal to a predetermined deviation threshold, adding the first synthesis process to the multiple key process nodes; The method of obtaining the multi-stage component content ratio coefficient comprises: Based on the preset synthesis reaction route, the plurality of key process nodes are subjected to serialization processing to obtain a process node sequence; Extracting a first node and a second node in the process node sequence, wherein the first node and the second node are two adjacent process nodes; Based on the preset reaction mechanism, the first node and the second node are identified with the same active component content ratio to obtain a first component content ratio coefficient; The first component content proportional coefficient is added to the multi-stage component content proportional coefficients.
2. The method according to claim 1, characterized in that The step of performing discrete value evaluation on the first component content deviation data set and performing data trimming based on the discrete value evaluation result to obtain the first component calibrated content deviation includes: Performing data cluster fitting on the first component content deviation data set to obtain a first fitting data cluster; calculating a first anomaly probability of the first fitted data cluster; If the first abnormal probability is less than a predetermined abnormal probability, a mean calculation is performed on the data in the first fitting data cluster to obtain the first component calibration content deviation.
3. The method according to claim 2, characterized in that The calculating a first abnormal probability of the first fitting data cluster comprises: Obtaining a first difference set between the first fitting data cluster and the first component content deviation data set; Counting the amount of first difference set data in the first difference set; Counting the total amount of first data in the first component content deviation data set; The ratio of the first difference set data volume to the first total data volume is used as the first abnormality probability.
4. The method according to claim 1, characterized in that After obtaining the calibration deviation, it also includes: If the verification deviation value is not within the predetermined deviation range, abnormal node positioning is performed on the multiple key process nodes to obtain a first abnormal node and a first abnormally active component; Acquiring process execution environment information of the first abnormal node; Performing component variation identification on the process execution environment information and the first abnormally active component to obtain a first variation probability; If the first mutation probability is greater than or equal to a predetermined mutation probability, a synthetic environment warning is issued to the first abnormal node.
5. The method according to claim 4, characterized in that The obtaining of the first mutation probability comprises: Acquire a first stable temperature range of the first abnormally active component; A deviation comparison is performed between the process execution environment information and the first stable temperature range, and the first variation probability is generated based on the comparison result.
6. A plant protein meat active component detection system, characterized in that: A method for detecting active components of plant protein meat according to any one of claims 1 to 5, the system comprising: An information acquisition module, the information acquisition module is used to obtain predetermined active detection component information of the target plant protein meat; A first identification module, wherein the first identification module is used to obtain multiple synthesis processes of the target plant protein meat, and identify the influence of active ingredients on the multiple synthesis processes to obtain multiple key process nodes; A collection module, the collection module is used to establish a connection between the multiple key process nodes and the sampling module, and perform sample collection on the multiple key process nodes through the sampling module to obtain multi-stage sample collection results; A detection module, the detection module is used to match an active component detection platform based on the predetermined active detection component information, perform active component detection on the multi-stage sample collection results, and obtain a multi-stage detection result; A second identification module, the second identification module is used to obtain the preset synthesis reaction routes and preset reaction mechanisms of the multiple key process nodes, identify the content relationship of the active components of the multiple key process nodes, and obtain the multi-stage component content ratio coefficient; A verification module, wherein the verification module is used to verify the multi-stage detection result based on the multi-stage component content proportional coefficient to obtain a verification deviation; a correction module, wherein if the verification deviation value is within a predetermined deviation range, the correction module is used to feedback and correct the multi-stage detection result with the verification deviation value to obtain an active component detection result.
