Breeding aquatic product quality tracking method and system based on lipidome fingerprint spectrum

Abstract

The invention belongs to the technical field of data processing, and provides a cultured aquatic product quality tracking method and system based on a lipidome fingerprint spectrum, and the method specifically comprises the steps: firstly, recognizing the circulation process of cultured aquatic products, selecting sampling points in the circulation process of the aquatic products, carrying out the HS-SPME-based processing of the cultured aquatic products at each sampling point to obtain aquatic product volatile matter samples, collecting GC-MS total ion chromatogram information of the aquatic product volatile matter samples, constructing peak area vectors, calculating quality attenuation density according to the peak area vectors of the sampling points, and feeding back quality attenuation risks to an administrator or a management system through the quality attenuation density. The method can effectively quantify the inducible existence degree of the aquatic product quality variation risk in the subsequent circulation stage between different sampling points, and finally locates the circulation step of the aquatic product with quality variation in the circulation process. The quality attenuation density calculation unit not only significantly improves the reliability of abnormal change detection, but also has good scene adaptability.

Description

Technical Field

[0001] The present invention belongs to the technical field of data collection and aquatic product quality tracking, and specifically relates to a method and system for tracking the quality of aquacultured aquatic products based on lipidome fingerprints. Background Art

[0002] In the circulation process of farmed aquatic products, the guarantee of farmed aquatic product quality is the key to circulation management. The actual steps involved in circulation management mainly include fishing, storage, transportation and display, and there are still many branch steps in these main steps according to the types of farmed aquatic products. The quality of farmed aquatic products described in these steps usually refers to the important sensory perception of aquatic products such as taste, flavor or smell. Since these sensory perceptions directly affect consumers' consumption choices, aquaculture management often conducts high-precision analysis of the quality of farmed aquatic products in the circulation process of farmed aquatic products, thereby reducing the risk of quality loss of farmed aquatic products.

[0003] Currently, the methods for detecting the taste, flavor or smell of farmed aquatic products vary. Often, one method only detects one quality characteristic of aquatic products, such as using gas chromatography-mass spectrometry to detect the impact of fishy substances produced by oxidation and microbial metabolism on the smell of aquatic products, using texture analysis to detect the impact of the elasticity and moisture retention capacity of muscle fibers of texture-sensitive species such as shrimp and cod on the taste, and using DHS dynamic headspace analysis to detect the concentration and type of volatile flavor compounds released into the air by aquatic products.

[0004] However, the quality tracking of farmed aquatic products is often highly targeted, which makes the quality analysis of different varieties of farmed aquatic products in the circulation process have high development costs and inefficient development processes. Therefore, there is an urgent need for a method and system for tracking the quality of farmed aquatic products based on lipidome fingerprints.

[0005] The reason for using lipidome fingerprints is that lipidomics covers a variety of lipid components in aquatic products. Lipidomes are prone to change during the aquatic product processing process and directly affect the taste of aquatic products, including fatty acids represented by AA (arachidonic acid), DHA and EPA, as well as components in lipidomes such as phospholipids and triglycerides, which can cause bad odor and taste changes. Aldehydes produced during the peroxidation of lipidome substances, including hexanal and heptanal, and ketones, often increase fishy or peculiar smells, and therefore significantly affect the edible quality. They are often considered to be directly related to changes in farmed aquatic products. In addition, the degradation of phospholipids will also affect the texture and flavor of the product. Different components show different metabolic or degradation characteristics during the circulation of farmed aquatic products, so the quality of farmed aquatic products based on lipidome fingerprints can be tracked based on lipidome fingerprints. Summary of the invention

[0006] The purpose of the present invention is to propose a method and system for tracking the quality of aquaculture products based on lipidome fingerprints to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0007] In order to achieve the above object, according to one aspect of the present invention, a method for tracking the quality of aquaculture products based on lipidome fingerprint is provided, the method comprising the following steps: S100, identifying the aquaculture flow process and selecting sampling points in the aquaculture flow process; S200, HS-SPME-based processing of aquaculture aquatic products at various sampling points to obtain aquatic volatile samples; S300, collecting GC-MS total ion current information of aquatic volatile samples and constructing peak area vectors; S400, quality attenuation density calculated based on the peak area vector of each sampling point; S500, feeding back the circulation steps where the risk of quality degradation occurs to the administrator or management system through the quality degradation density.

[0008] Further, in step S100, the circulation process of aquaculture is identified, and the method for selecting sampling points in the circulation process of aquaculture is as follows: the circulation process of aquaculture includes an environmental detection device, and the environmental detection device is composed of a humidity sensor and a temperature sensor; if the temperature value measured by the temperature sensor in real time is not in the temperature range of 0~4°C, or if the humidity value measured by the humidity sensor in real time is not in the humidity range of 85~95%, it is defined that the temperature and humidity abnormality occurs at this moment; the time interval GTT of the preset collection points is 10-30 minutes, if the temperature and humidity abnormality does not occur within the GTT interval, the end moment of the GTT interval is used as the sampling point, otherwise the time point when the temperature and humidity abnormality occurs is recorded as the sampling point of the time period. That is, the time point when the temperature and humidity abnormality occurs replaces the end moment of the GTT interval as a sampling point in a GTT interval, and there is one and only one sampling point in each GTT interval. When there are multiple such moments when the temperature and humidity abnormality occurs, the first moment is selected as the sampling point, that is, the moment when the temperature and humidity abnormality is obtained by the first monitoring is selected.

[0009] The humidity sensor is any one of a capacitive humidity sensor or a resistive humidity sensor, and the temperature sensor is any one of a thermistor sensor or a semiconductor temperature sensor; During the fishing and initial storage stages, temperature sensors and humidity sensors should be placed on the top, middle and bottom of the fishing vessel's refrigerated compartment; in the transportation and cold chain links, temperature and humidity sensors should be placed on the top, middle and bottom of the refrigerated compartment respectively; in the display refrigerator stage, temperature and humidity sensors are installed on the top, middle and bottom near the operating table in the processing area; when there are multiple readings of the same type of sensors, the average value is taken as the real-time reading of this type of sensor; the environmental detection equipment sends the sampling points to the server in real time, and the server stores or applies the environmental data.

[0010] Further, in step S200, the method for obtaining aquatic volatile samples by processing aquaculture products based on HS-SPME at each sampling point is: Aquacultured aquatic products are selected at the sampling point for sampling to obtain original samples; aquatic volatile samples are collected from the original samples by the HS-SPME solid phase microextraction method; wherein the extraction temperature in the HS-SPME technical application is set between 30-60°C, and the extraction time is set between 10-30 minutes.

[0011] Farmed aquatic products are generally fish products; the HS-SPME technology utilizes the principle of solid phase microextraction to extract volatile organic compounds from the head space of aquatic products, specifically: select the SPME fiber of the target compound, the target compound is fatty acid, and one or more of phospholipids, triglycerides, etc., the SPME fiber includes PDMS, CAR / PDMS or PDMS / DVB, the fiber captures volatile substances in the head space of aquatic products, the volatile substances include fatty acids, aldehydes, ketones, amino acids and their derivatives, etc., the captured volatile substances are the volatile organic compounds as aquatic volatile samples.

[0012] Furthermore, in step S300, the method for collecting GC-MS total ion current information of aquatic volatile samples and constructing a peak area vector is: introducing the aquatic volatile sample into a GC-MS gas chromatography-mass spectrometer to obtain a total ion current diagram, reading each aquatic volatile in the total ion current diagram and recording it as a test object, and reading the peak area of ​​each test object, and constructing the peak area of ​​each test object in the sampling point into a vector recorded as a peak area vector.

[0013] The total ion current is a spectrum obtained by accumulating the ion intensities of all mass-to-charge ratios detected by the mass spectrometer at each time point. The working process of the GC-MS equipment can accurately separate and identify different volatile compounds in the sample. In the GC-MS process, the chemical components in the sample will be separated in the chromatographic column according to their molecular weight, polarity and other characteristics, forming a series of peaks; the mass spectrometer ionizes the separated components and performs qualitative and quantitative analysis based on the mass spectrum information after ionization.

[0014] The total ion current obtained by GC-MS provides detailed information on the various chemical components in the sample, including the location of each peak, i.e., retention time and peak area. Each peak represents a specific chemical component or class of compounds, and the peak area vector is obtained by quantifying the area of ​​each peak in the total ion current.

[0015] Further, in step S400, the method for calculating the quality attenuation density according to the peak area vector of each sampling point is as follows: the time interval formed by all sampling points is a sampling period, and the sampling points of a sampling point in the reverse time direction and along the time direction are defined as its tracing point and extending point respectively; the cosine distance between the peak area vector of a sampling point and each of its extending points is calculated, and the extending point with a maximum cosine distance is the first marking point; the average value of the cosine distance of each extending point is the extending cosine distance; the first distance condition is set as the cosine distance being greater than the extending cosine distance, and the second distance condition is set as the cosine distance of at least one intermediate extending point between the sampling point and the extending point being less than the extending cosine distance; the first marking point satisfying the first distance condition and the second distance condition is searched in reverse time order from the sampling point and recorded as the second marking point; the number of tracing points in the reverse time direction of the sampling point having the same second marking point as the current sampling point is counted and recorded as the reverse filling number, and the reverse filling coefficient Rc.idx is preset, Rc.idx∈[0.3,1]; the product of the number of reverse charging and the reverse charging coefficient is rounded upward as the reverse charging value Rc.vl, the third marking point of the sampling point is defined as the Rc.vlth extension point of the second marking point in the time direction, and the time interval between the sampling point and the third marking point is recorded as the reference domain of the sampling point; the ratio of the cosine distance between the second marking point and the third marking point is recorded as the reverse charging regression ratio Rc.rvt of the sampling point; The intermediate extension points refer to the extension points between the sampling point and the extension points participating in the judgment of the second distance condition. The preset backfill coefficient has a default value of 0.5, which is used to adjust the calculation model of the quality attenuation. When the frequency of the added class object is high in most of the sampling points, the value is increased, otherwise it is reduced, thereby enhancing the exclusivity of the calculated quality attenuation density and preventing overfitting problems.

[0016] For any sampling point, the peak area vector of the sampling point is subtracted from the first sampling point in the reverse time direction to obtain the step difference vector. The test objects corresponding to the step difference elements with values ​​greater than zero in the step difference vector are classified as enhancement objects. Each enhancement object is written into a sequence and recorded as an enhancement sequence. Otherwise, it is a loss object. The step difference element refers to any element in the step difference vector. The percentile value of the step difference element of the enhancement object in the set of step difference elements corresponding to each identical enhancement object in the reference domain is recorded as the enhancement order value. The cumulative value of the enhancement order values ​​corresponding to all enhancement objects at the sampling point is the enhancement cumulative value Icv. The extension point in the reference domain where the enhancement cumulative value is less than the enhancement cumulative value is recorded as the adaptation extension point. The quality attenuation density Pdt is calculated by the enhancement cumulative value and the back-charge regression ratio: ; Where i0 is the serial number of the sampling point, Pdt(i0) represents the quality attenuation density of the i0th sampling point, i1 is the cumulative variable, len is the number of adaptive extension points corresponding to the sampling point, exp() is an exponential function with the natural constant e as the base, and Icv i0 and Icv i1 is the cumulative value of the i0th sampling point and the i1th adaptation extension point; diff{} is the Euclidean distance function, which returns the Euclidean distance between two call sequences, Pmks i0 and Pmks i1 The increasing class read sequence represents the i0th sampling point and the i1th adaption extension point respectively, and the increasing class read sequence is composed of the increasing class sequence corresponding to each step difference element at the i0th sampling point and the i1th adaption extension point. The increasing class sequence of the i1th adaption extension point is the same as the increasing class sequence of the i0th sampling point.

[0017] Beneficial effects: Since the quality decay density is an analysis result constructed based on a dynamically screened reference domain, it can effectively quantify the degree of induction of the risk of quality variation of aquatic products in subsequent circulation stages between different sampling points. This analysis method can not only clearly reflect the time points when lipid group substances change significantly during the circulation of aquatic products, but also accurately quantify the ability of these inductions to respond continuously to subsequent changes, thereby providing a solid mathematical basis for further identifying the key steps of the risk of sudden quality decline of aquatic products.

[0018] Furthermore, in step S500, the method of feeding back the circulation steps with quality decay risk to the administrator or management system through the quality decay density is: setting a risk management time period RMT, RMT∈[60,120] minutes; taking any sampling point as the current sampling point, and the RMT period in the reverse time direction of the current sampling point as the current risk management time period; recording the quality decay density of the current sampling point as Pdt, and recording the average value of each quality decay density in the current risk management time period as EPdt; presetting the variable risk identification threshold RPRt, and its value range is RPRt∈[1.1,2); when Pdt≥RPRt×EPdt, it is defined that the current sampling point is at risk of quality decay, and the flavor of the aquatic product is deteriorated or lost, and each sampling point at risk of quality decay is constructed into a sequence and sent to the administrator client.

[0019] Preferably, all undefined variables in the present invention, if not clearly defined, can be manually set thresholds.

[0020] The present invention also provides a system for tracking the quality of aquatic products based on lipidome fingerprints. The system for tracking the quality of aquatic products based on lipidome fingerprints comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the method for tracking the quality of aquatic products based on lipidome fingerprints are implemented. The system for tracking the quality of aquatic products based on lipidome fingerprints can be run on computing devices such as desktop computers, notebook computers, PDAs, and cloud data centers. The executable system may include, but is not limited to, a processor, a memory, and a server cluster. The processor executes the computer program and runs it in the following system units: Aquatic sampling point collection unit is used to identify the flow process of aquaculture aquatic products and select sampling points in the flow process of aquatic products; Aquatic volatiles extraction unit, used to process farmed aquatic products based on HS-SPME at various sampling points to obtain aquatic volatile samples; A peak area vector construction unit is used to collect GC-MS total ion current information of aquatic volatile samples and construct a peak area vector; An attenuation density calculation unit, used for calculating the quality attenuation density according to the peak area vector of each sampling point; The quality decay feedback unit is used to feed back the circulation steps where the quality decay risk occurs to the administrator or management system through the quality decay density.

[0021] The beneficial effects of the present invention are as follows: since the quality decay density is an analysis result constructed based on a dynamically screened reference domain, it can effectively quantify the degree of induced existence of the risk of quality variation of aquatic products in the subsequent circulation stage between different sampling points, and accurately quantify the quality change dynamics of farmed aquatic products in the circulation process by extracting the quality decay density, providing a highly targeted means of identifying the deterioration stage, and finally locating the circulation steps where the quality of aquatic products varies in the circulation process. The quality decay density calculation unit not only significantly improves the reliability of abnormal change detection, but also can quickly locate the problem links in a variety of aquatic products, and has good scene adaptability. At the same time, it supports the construction of an intelligent quality monitoring system, providing scientific support for the digitization and efficiency of farmed aquatic product circulation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1Shown is a flow chart of a method for tracking the quality of aquacultured aquatic products based on lipidome fingerprints; Figure 2 Shown is the structural diagram of the aquaculture product quality tracking system based on lipidome fingerprint. DETAILED DESCRIPTION

[0023] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0024] like Figure 1 The flowchart of the method for tracking the quality of aquatic products based on lipid group fingerprint is shown below. Figure 1 To illustrate a method for tracking the quality of aquaculture products based on lipidome fingerprints according to an embodiment of the present invention, the method comprises the following steps: S100, identifying the aquaculture flow process and selecting sampling points in the aquaculture flow process; S200, HS-SPME-based processing of aquaculture aquatic products at various sampling points to obtain aquatic volatile samples; S300, collecting GC-MS total ion current information of aquatic volatile samples and constructing peak area vectors; S400, quality attenuation density calculated based on the peak area vector of each sampling point; S500, feeding back the circulation steps where the risk of quality degradation occurs to the administrator or management system through the quality degradation density.

[0025] Further, in step S100, the circulation process of aquaculture aquatic products is identified, and the method for selecting sampling points in the circulation process of aquatic products is: the circulation process of aquaculture aquatic products includes environmental detection equipment, and the environmental detection equipment is composed of a humidity sensor and a temperature sensor; if the temperature value measured in real time by the temperature sensor is not in the temperature range of 0~4°C, or if the humidity value measured in real time by the humidity sensor is not in the humidity range of 85~95%, it is defined that temperature and humidity abnormalities occur at this moment; the time interval GTT of the preset collection points is 15 minutes, if no temperature and humidity abnormalities occur within the GTT interval, the end moment of the GTT interval is used as the sampling point, otherwise the time point when the temperature and humidity abnormalities occur is recorded as the sampling point of this time period.

[0026] Further, in step S200, the method for obtaining aquatic volatile samples by processing aquaculture products based on HS-SPME at each sampling point is: Farmed aquatic products were selected at the sampling point for sampling to obtain original samples; aquatic volatile samples were collected from the original samples by the HS-SPME solid phase microextraction method; the extraction temperature in the HS-SPME technical application was set at 40°C, and the extraction time was set at 30 minutes.

[0027] Furthermore, in step S300, the method for collecting GC-MS total ion current information of aquatic volatile samples and constructing a peak area vector is: introducing the aquatic volatile sample into a GC-MS gas chromatography-mass spectrometer to obtain a total ion current diagram, reading each aquatic volatile in the total ion current diagram and recording it as a test object, and reading the peak area of ​​each test object, and constructing the peak area of ​​each test object in the sampling point into a vector recorded as a peak area vector.

[0028] Further, in step S400, the method for calculating the quality attenuation density according to the peak area vector of each sampling point is as follows: the time interval formed by all sampling points is a sampling period, and the sampling points of a sampling point in the reverse time direction and along the time direction are defined as its tracing point and extending point respectively; the cosine distance between the peak area vector of a sampling point and each of its extending points is calculated, and the extending point with a maximum cosine distance is the first marking point; the average value of the cosine distance of each extending point is the extending cosine distance; the first distance condition is set as the cosine distance being greater than the extending cosine distance, and the second distance condition is set as the cosine distance of at least one intermediate extending point between the sampling point and the extending point being less than the extending cosine distance; the first marking point satisfying the first distance condition and the second distance condition is searched in reverse time order from the sampling point and recorded as the second marking point; the number of tracing points in the reverse time direction of the sampling point having the same second marking point as the current sampling point is counted and recorded as the reverse filling number, and the reverse filling coefficient Rc.idx is preset, The value of Rc.idx is 0.5; the product of the number of reverse charging and the reverse charging coefficient is rounded upward to the reverse charging value Rc.vl; the third marking point of the sampling point is defined as the Rc.vlth extension point of the second marking point in the time direction; the time interval between the sampling point and the third marking point is recorded as the reference domain of the sampling point; the ratio of the cosine distance between the second marking point and the third marking point is recorded as the reverse charging regression ratio Rc.rvt of the sampling point; For any sampling point, the peak area vector of the sampling point is subtracted from the first sampling point in the reverse time direction to obtain the step difference vector. The test objects corresponding to the step difference elements with values ​​greater than zero in the step difference vector are classified as enhancement objects. Each enhancement object is written into a sequence and recorded as an enhancement sequence. Otherwise, it is a loss object. The step difference element refers to any element in the step difference vector. The percentile value of the step difference element of the enhancement object in the set of step difference elements corresponding to each identical enhancement object in the reference domain is recorded as the enhancement order value. The cumulative value of the enhancement order values ​​corresponding to all enhancement objects at the sampling point is the enhancement cumulative value Icv. The extension point in the reference domain where the enhancement cumulative value is less than the enhancement cumulative value is recorded as the adaptation extension point. The quality attenuation density Pdt is calculated by the enhancement cumulative value and the back-charge regression ratio: ; Where i0 is the serial number of the sampling point, Pdt(i0) represents the quality attenuation density of the i0th sampling point, i1 is the cumulative variable, len is the number of adaptive extension points corresponding to the sampling point, exp() is an exponential function with the natural constant e as the base, and Icv i0 and Icv i1 is the cumulative value of the i0th sampling point and the i1th adaptation extension point; diff{} is the Euclidean distance function, which returns the Euclidean distance between two call sequences, Pmks i0 and Pmks i1 Respectively represent the augmented reading sequences of the i0th sampling point and the i1th adapting extension point, and the augmented reading sequence is composed of the step difference elements corresponding to the augmented sequence at the i0th sampling point and the i1th adapting extension point.

[0029] Furthermore, in step S500, the method of feeding back the circulation steps with quality decay risk to the administrator or management system through the quality decay density is: setting a risk management time period RMT, the RMT value is 60 minutes; taking any sampling point as the current sampling point, and the RMT period in the reverse time direction of the current sampling point as the current risk management time period; recording the quality decay density of the current sampling point as Pdt, and recording the average value of each quality decay density in the current risk management time period as EPdt; presetting the variable risk identification threshold RPRt, the value is 1.5; when Pdt≥RPRt×EPdt, it is defined that the current sampling point is at risk of quality decay, and the flavor of the aquatic product is deteriorated or lost, and each sampling point at risk of quality decay is constructed into a sequence and sent to the administrator client.

[0030] The embodiment of the present invention provides a system for tracking the quality of aquaculture products based on lipid group fingerprints, such as Figure 2The structure diagram of the aquaculture product quality tracking system based on lipidome fingerprint of the present invention is shown. The aquaculture product quality tracking system based on lipidome fingerprint of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned aquaculture product quality tracking method embodiment based on lipidome fingerprint are implemented.

[0031] The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system: Aquatic sampling point collection unit is used to identify the flow process of aquaculture aquatic products and select sampling points in the flow process of aquatic products; Aquatic volatiles extraction unit, used to process farmed aquatic products based on HS-SPME at various sampling points to obtain aquatic volatile samples; A peak area vector construction unit is used to collect GC-MS total ion current information of aquatic volatile samples and construct a peak area vector; An attenuation density calculation unit, used for calculating the quality attenuation density according to the peak area vector of each sampling point; The quality decay feedback unit is used to feed back the circulation steps where the quality decay risk occurs to the administrator or management system through the quality decay density.

[0032] The aquaculture product quality tracking system based on lipidome fingerprint can be run on computing devices such as desktop computers, laptops, PDAs and cloud servers. The aquaculture product quality tracking system based on lipidome fingerprint can be operated on systems including, but not limited to, processors and memories. Those skilled in the art will appreciate that the examples are merely examples of aquaculture product quality tracking systems based on lipidome fingerprints, and do not constitute limitations on aquaculture product quality tracking systems based on lipidome fingerprints. The examples may include more or fewer components than the examples, or a combination of certain components, or different components. For example, the aquaculture product quality tracking system based on lipidome fingerprints may also include input and output devices, network access devices, buses, and the like.

[0033] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the operation system of the aquaculture product quality tracking system based on lipidome fingerprint, and uses various interfaces and lines to connect various parts of the entire aquaculture product quality tracking system based on lipidome fingerprint.

[0034] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the aquaculture product quality tracking system based on lipid group fingerprint by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0035] Although the description of the present invention has been quite detailed and specifically described several embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present invention. In addition, the above description of the present invention with foreseeable embodiments is intended to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes to the present invention.

Claims

1. A method for tracking the quality of aquaculture products based on lipidome fingerprints, characterized in that: The method comprises the following steps: S100, identifying the aquaculture flow process and selecting sampling points in the aquaculture flow process; S200, HS-SPME-based processing of aquaculture aquatic products at various sampling points to obtain aquatic volatile samples; S300, collecting GC-MS total ion current information of aquatic volatile samples and constructing peak area vectors; S400, quality attenuation density calculated based on the peak area vector of each sampling point; S500, feeding back the circulation steps that have the risk of quality degradation to the administrator or management system through the quality degradation density; Among them, in step S400, the method for calculating the quality attenuation density according to the peak area vector of each sampling point is: calculate the cosine distance between the collection points according to the peak area vector, calculate the extended cosine distance according to the cosine distance, locate the second marking point by horizontal comparison of the extended cosine distance and calculate the back-charging number, locate the third marking point by the back-charging number, calculate the back-charging regression ratio according to the second marking point and the third marking point, obtain the added class object and the added class sequence through the peak area vector, calculate the added class cumulative value using the added class object and identify the adapted extended point, and obtain the quality attenuation density through the added class sequence and the back-charging regression ratio of the adapted extended point.

2. The method for tracking the quality of aquaculture products based on lipidome fingerprint according to claim 1, characterized in that: In step S100, the circulation process of aquaculture aquatic products is identified, and the method for selecting sampling points in the circulation process of aquatic products is as follows: the circulation process of aquaculture aquatic products includes environmental detection equipment, and the environmental detection equipment is composed of a humidity sensor and a temperature sensor; if the temperature value measured in real time by the temperature sensor is not in the temperature range of 0~4°C, or if the humidity value measured in real time by the humidity sensor is not in the humidity range of 85~95%, it is defined that temperature and humidity abnormalities occur at this moment; the time interval GTT of the preset collection points is 10-30 minutes, if no temperature and humidity abnormalities occur within the GTT interval, the end moment of the GTT interval is used as the sampling point, otherwise the time point when the temperature and humidity abnormalities occur is recorded as the sampling point of this time period.

3. The method for tracking the quality of aquaculture products based on lipidome fingerprint according to claim 1, characterized in that: In step S200, the method for obtaining aquatic volatile samples by HS-SPME treatment of aquaculture products at various sampling points is: Aquacultured aquatic products are selected at the sampling point for sampling to obtain original samples; aquatic volatile samples are collected from the original samples by the HS-SPME solid phase microextraction method; wherein the extraction temperature in the HS-SPME technical application is set between 30-60°C, and the extraction time is set between 10-30 minutes.

4. The method for tracking the quality of aquaculture products based on lipidome fingerprint according to claim 1, characterized in that: In step S300, the method for collecting GC-MS total ion current information of aquatic volatile samples and constructing a peak area vector is: introducing the aquatic volatile sample into a GC-MS gas chromatography-mass spectrometer to obtain a total ion current diagram, reading each aquatic volatile in the total ion current diagram and recording it as a test object, and reading the peak area of ​​each test object, and constructing the peak area of ​​each test object in the sampling point into a vector recorded as a peak area vector.

5. The method for tracking the quality of aquaculture products based on lipidome fingerprint according to claim 1, characterized in that: In step S400, the method for calculating the quality attenuation density based on the peak area vector of each sampling point is as follows: the time interval formed by all sampling points is a sampling period, and the sampling points of a sampling point in the reverse time direction and along the time direction are defined as its traceback point and extension point respectively; the cosine distance between the peak area vector of a sampling point and each of its extension points is calculated, and the extension point with the maximum cosine distance is the first marking point; the average value of the cosine distance of each extension point is the extension cosine distance; the first distance condition is set as the cosine distance is greater than the extension cosine distance, and the second distance condition is set as the cosine distance of at least one intermediate extension point between the sampling point and the extension point is less than the extension cosine distance; Search the first first mark point that meets the first distance condition and the second distance condition in reverse time order from the sampling point and record it as the second mark point; count the number of traceable points in the reverse time direction of the sampling point that have the same second mark point as the current sampling point and record it as the reverse filling number, and preset the reverse filling coefficient Rc.idx, Rc.idx∈[0.3,1]; the product of the reverse filling number and the reverse filling coefficient is rounded upward as the reverse filling value Rc.vl, and the third mark point of the sampling point is defined as the Rc.vlth extended point of the second mark point in the forward time direction, and the time interval between the sampling point and the third mark point is recorded as the reference domain of the sampling point; the ratio of the cosine distance between the second mark point and the third mark point is recorded as the reverse filling regression ratio Rc.rvt of the sampling point; For any sampling point, the peak area vector of the sampling point is subtracted from the first sampling point in the reverse time direction to obtain the step difference vector. The test objects corresponding to the step difference elements with values ​​greater than zero in the step difference vector are classified as enhancement objects. Each enhancement object is written into a sequence and recorded as an enhancement sequence. Otherwise, it is a loss object. The step difference element refers to any element in the step difference vector. The percentile value of the step difference element of the enhancement object in the set of step difference elements corresponding to each identical enhancement object in the reference domain is recorded as the enhancement order value. The cumulative value of the enhancement order values ​​corresponding to all enhancement objects at the sampling point is the enhancement cumulative value Icv. The extension point in the reference domain where the enhancement cumulative value is less than the enhancement cumulative value is recorded as the adaptation extension point. The quality attenuation density Pdt is calculated by the enhancement cumulative value and the back-charge regression ratio: ； Where i0 is the serial number of the sampling point, Pdt(i0) represents the quality attenuation density of the i0th sampling point, i1 is the cumulative variable, len is the number of adaptive extension points corresponding to the sampling point, exp() is an exponential function with the natural constant e as the base, and Icv i0 and Icv i1 is the cumulative value of the i0th sampling point and the i1th adaptation extension point; diff{} is the Euclidean distance function, which returns the Euclidean distance between two call sequences. i0 and Pmks i1 Respectively represent the augmented reading sequences of the i0th sampling point and the i1th adapting extension point, and the augmented reading sequence is composed of the step difference elements corresponding to the augmented sequence at the i0th sampling point and the i1th adapting extension point.

6. The method for tracking the quality of aquaculture products based on lipidome fingerprint according to claim 1, characterized in that: In step S500, the method of feeding back the circulation step of the quality decay risk to the administrator or management system through the quality decay density is: setting a risk management time period RMT, RMT∈[60,120] minutes; taking any sampling point as the current sampling point, and the RMT period in the reverse time direction of the current sampling point as the current risk management time period; recording the quality decay density of the current sampling point as Pdt, and recording the average value of each quality decay density in the current risk management time period as EPdt; The variable risk identification threshold RPRt is preset, and its value range is RPRt∈[1.1,2); when Pdt≥RPRt×EPdt, it is defined that the current sampling point is at risk of quality degradation, and the flavor of the aquatic product is deteriorated or lost. The sampling points at risk of quality degradation are constructed into a sequence and sent to the administrator client.

7. Aquaculture product quality tracking system based on lipidome fingerprint, characterized in that: The aquaculture product quality tracking system based on lipidome fingerprint includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the aquaculture product quality tracking method based on lipidome fingerprint described in any one of claims 1 to 6 are implemented. The aquaculture product quality tracking system based on lipidome fingerprint runs on a desktop computer, a laptop computer, a PDA, and a computing device in a cloud data center.

Images