Method for extracting protein from mealworm

By optimizing the extraction of yellow mealworm protein using supercritical CO2 extraction, electrostatic precipitation-salting-out combined method, small molecule bioactive peptide separation and spray drying, and combining it with intelligent control of pH value and hydrolysis temperature, the problems of low protein extraction efficiency and environmental pollution in traditional methods have been solved, achieving efficient and environmentally friendly protein extraction.

CN118272476BActive Publication Date: 2024-11-19QINGDAO SINO CROWN BIOLOGICAL ENG CO
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410439818.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-12
Publication Date
2024-11-19
Estimated Expiration
2044-04-12

AI Technical Summary

Technical Problem

Traditional methods for extracting protein from yellow mealworms suffer from problems such as nutrient loss, environmental pollution, and alteration of protein structure under high alkaline conditions, which affect extraction efficiency and sustainability.

Method used

The protein extraction process of yellow mealworms was optimized by using supercritical CO2 extraction for defatting, electrostatic precipitation-salting precipitation, small molecule bioactive peptide separation technology, and spray drying, combined with enzymatic hydrolysis and intelligent control of pH and hydrolysis temperature.

Benefits of technology

It improves hydrolysis efficiency, avoids excessive protein degradation, ensures protein solubility and bioavailability, and achieves more efficient and environmentally friendly protein extraction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118272476B_ABST
    Figure CN118272476B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method for extracting protein from yellow mealworms. The method includes: washing and sterilizing the yellow mealworm body, then drying and crushing it into insect body powder; then, using an organic solvent to make the crushed insect body into insect pulp, and defatting it by supercritical CO2 fluid extraction; after that, adding water to the defatted insect pulp and slurrying it to remove impurities; enzymatically treating the purified homogenate to produce a hydrolyzate, and then enriching and precipitating it by an electro-point-salting-out method to obtain a precipitate; after the precipitate is treated by centrifugation and desalting, adding water to the homogenate and precipitating and draining it; finally, using a small molecule bioactive peptide separation technology to remove insoluble proteins, and obtaining high-purity yellow mealworm protein by spray drying. In this way, the hydrolysis efficiency can be improved, and excessive protein degradation can be avoided, while ensuring the solubility and bioavailability of the protein.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of mealworm protein, and in particular, to a method for extracting mealworm protein. Background Art

[0002] Tenebrio molitor is a common edible insect rich in nutrients such as protein, fat, vitamins and minerals, and is therefore widely studied for protein extraction. Traditional methods for extracting insect protein mainly include alkaline method and salt method, but these two methods have some disadvantages. Although alkaline extraction has a high extraction rate, is simple and easy to operate, and has a low production cost, it is easy to produce toxic lysine under high alkaline conditions, resulting in nutrient loss. In addition, high alkaline conditions will also cause protein hydrolysis and Maillard reaction to accelerate, produce black-brown substances, and cause the color of the extract to deepen, the non-protein content to increase, and reduce the separation effect. A large amount of salt solution is often used in the salt extraction process, and these salts may cause environmental pollution, especially when treating wastewater, which may cause environmental problems. At the same time, salts have an impact on the structure and function of proteins, which may cause partial protein inactivation or structural changes, affecting the biological activity and bioavailability of proteins. These shortcomings limit the efficiency and sustainability of traditional insect protein extraction methods in practical applications.

[0003] Therefore, an optimized protein extraction protocol for Tenebrio molitor is desired. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a method for extracting protein from yellow mealworms, the method comprising:

[0006] The yellow mealworm bodies are cleaned and sterilized and dried to obtain dried mealworm bodies;

[0007] The dried insect bodies are crushed and sieved to obtain crushed insect bodies;

[0008] After the crushed insect bodies are passed through an organic solvent to prepare an insect pulp, the insect pulp is extracted and defatted by supercritical fluid CO2 extraction to obtain an extracted defatted product;

[0009] The extracted defatted product is homogenized by adding water, and the resulting homogenate is filtered to remove epidermal substances to obtain a purified homogenate;

[0010] enzymatically hydrolyzing the purified homogenate to obtain a hydrolyzed slurry;

[0011] Decolorizing the slurry using activated carbon to obtain an adsorption product;

[0012] Using an electrochemical-salting-out method to enrich and precipitate the adsorbed product to obtain a precipitate;

[0013] The precipitate is subjected to centrifugal desalting treatment to obtain a desalted product;

[0014] adding water to the desalted product to homogenize to obtain a homogenate, and subjecting the homogenate to a precipitation and drainage treatment to obtain a homogenate precipitate;

[0015] The homogenate precipitate is treated using a small molecule bioactive peptide separation technology to remove insoluble proteins to obtain a separation product;

[0016] The separated product is treated by a spray drying method to obtain yellow mealworm protein.

[0017] Optionally, the purified homogenate is subjected to enzymatic hydrolysis to obtain a hydrolyzed slurry, including: obtaining a time series of pH values ​​and a time series of hydrolysis temperatures; performing sequence segmentation and data regularization on the time series of pH values ​​and the time series of hydrolysis temperatures at a predetermined time scale to obtain a sequence of local time series input vectors of pH values ​​and a sequence of local time series input vectors of hydrolysis temperatures; using a gamma responsiveness analysis module to perform vector pair analysis on the sequence of local time series input vectors of pH values ​​and the sequence of local time series input vectors of hydrolysis temperatures to obtain a sequence of local time series response interaction feature vectors of pH values ​​and hydrolysis temperatures; performing autocorrelation feature significant fusion on the sequence of local time series response interaction feature vectors of pH values ​​and hydrolysis temperatures to obtain a full-time domain interaction feature of pH values ​​and hydrolysis temperatures; and determining whether the hydrolysis temperature value at the current time point should increase, decrease, or remain unchanged based on the full-time domain interaction feature of pH values ​​and hydrolysis temperatures.

[0018] Optionally, using a gamma responsiveness analysis module to perform vector pair analysis on the sequence of the pH value local timing input vectors and the sequence of the hydrolysis temperature local timing input vectors to obtain a sequence of pH value-hydrolysis temperature local timing response interaction feature vectors, including: using the gamma responsiveness analysis module to perform vector pair analysis on the sequence of the pH value local timing input vectors and the sequence of the hydrolysis temperature local timing input vectors using the following gamma response formula to obtain a sequence of pH value-hydrolysis temperature local timing response interaction feature vectors; wherein the gamma response formula is:

[0019]

[0020] in, and are the eigenvalues ​​of the ith position of the corresponding PH value local time series input vector and the hydrolysis temperature local time series input vector in the sequence of the PH value local time series input vector and the sequence of the hydrolysis temperature local time series input vector, respectively. A, B, C and D are adjustment hyperparameters. v i It is the characteristic value of the i-th position of each pH value-hydrolysis temperature local time series response interaction characteristic vector in the sequence of the pH value-hydrolysis temperature local time series response interaction characteristic vector.

[0021] Optionally, the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors is subjected to autocorrelation feature significant fusion to obtain the pH value-hydrolysis temperature full time domain interaction feature, including: passing the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors through an autocorrelation signal feature significant fusion network to obtain the pH value-hydrolysis temperature full time domain interaction feature vector as the pH value-hydrolysis temperature full time domain interaction feature.

[0022] Optionally, the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors is passed through an autocorrelation signal feature saliency fusion network to obtain a pH value-hydrolysis temperature full time domain interaction feature vector as the pH value-hydrolysis temperature full time domain interaction feature, including: passing the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors through the autocorrelation signal feature saliency fusion network to process the sequence with the following autocorrelation saliency fusion formula to obtain the pH value-hydrolysis temperature full time domain interaction feature vector; wherein the autocorrelation saliency fusion formula is:

[0023]

[0024]

[0025]

[0026] Among them, h i is the i-th pH value-hydrolysis temperature local time series response interaction feature vector in the sequence of pH value-hydrolysis temperature local time series response interaction feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score of the ith pH value-hydrolysis temperature local temporal response interaction feature vector, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the sequence of the pH value-hydrolysis temperature local temporal response interaction feature vector, and V is the pH value-hydrolysis temperature full time domain interaction feature vector.

[0027] Optionally, based on the pH value-hydrolysis temperature full time domain interaction characteristics, it is determined whether the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged, including: passing the pH value-hydrolysis temperature full time domain interaction feature vector through a classifier-based hydrolysis temperature controller to obtain a temperature control instruction, wherein the temperature control instruction is used to indicate that the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged.

[0028] Optionally, the method further includes a training step for training the gamma responsiveness analysis module, the autocorrelation signal feature saliency fusion network and the classifier-based hydrolysis temperature controller.

[0029] Optionally, the training step includes: obtaining a time series of training pH values ​​and a time series of training hydrolysis temperatures; performing sequence segmentation and data regularization on the time series of training pH values ​​and the time series of training hydrolysis temperatures at a predetermined time scale to obtain a sequence of training pH value local time series input vectors and a sequence of training hydrolysis temperature local time series input vectors; using the gamma responsiveness analysis module to perform vector pair analysis on the sequence of training pH value local time series input vectors and the sequence of training hydrolysis temperature local time series input vectors to obtain a sequence of training pH value-hydrolysis temperature local time series response interaction feature vectors; and converting the training pH value local time series input vectors and the training hydrolysis temperature local time series input vectors into a vector pair analysis. The sequence of the local time-series response interaction feature vectors of the training pH value-hydrolysis temperature is processed by the autocorrelation signal feature saliency fusion network to obtain the full-time-domain interaction feature vector of the training pH value-hydrolysis temperature; the full-time-domain interaction feature vector of the training pH value-hydrolysis temperature is passed through the classifier-based hydrolysis temperature controller to obtain the classification loss function value; the gamma responsiveness analysis module, the autocorrelation signal feature saliency fusion network and the classifier-based hydrolysis temperature controller are trained based on the classification loss function value, and the full-time-domain interaction feature vector of the training pH value-hydrolysis temperature is corrected in each iteration.

[0030] The above technical scheme is adopted, the yellow mealworm body is cleaned and sterilized, then dried and crushed into insect body powder; then, the crushed insect body is made into insect pulp using an organic solvent, and defatted by supercritical CO2 fluid extraction; then, the defatted insect pulp is homogenized with water and filtered to remove impurities; the purified homogenate is enzymatically treated to produce a hydrolyzate, and then enriched and precipitated by an electrophoresis-salting out method to obtain a precipitate; after the precipitate is centrifuged and desalted, it is homogenized with water and precipitated and drained; finally, the insoluble protein is removed by using a small molecule bioactive peptide separation technology, and a high-purity yellow mealworm protein is obtained by spray drying. In this way, the hydrolysis efficiency can be improved, and excessive protein degradation can be avoided, while ensuring the solubility and bioavailability of the protein.

[0031] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0033] Figure 1 The present invention is a flow chart showing a method for extracting protein from yellow mealworms according to an exemplary embodiment.

[0034] Figure 2 is based on Figure 1 The illustrated embodiment shows a flow chart of step 105 of a method for extracting protein from yellow mealworms.

[0035] Figure 3 The invention is a block diagram of a system for extracting protein from mealworms according to an exemplary embodiment.

[0036] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment.

[0037] Figure 5 It is an application scenario diagram of a method for extracting protein from mealworms according to an exemplary embodiment. DETAILED DESCRIPTION

[0038] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0039] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0040] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0041] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0042] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0043] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0044] In order to solve the above problems, the present disclosure provides a method for extracting yellow mealworm protein, which includes washing and sterilizing the yellow mealworm body, drying and crushing it into insect body powder; then, using an organic solvent to make the crushed insect body into insect pulp, and performing defatting by supercritical CO2 fluid extraction; then, adding water to the defatted insect pulp for homogenization and filtering to remove impurities; performing enzymatic hydrolysis on the purified homogenate to produce a hydrolyzate, and then enriching and precipitating by an electrophoresis-salting out method to obtain a precipitate; after the precipitate is subjected to centrifugal desalting treatment, adding water to homogenize and precipitating and draining; finally, using a small molecule bioactive peptide separation technology to remove insoluble proteins, and obtaining high-purity yellow mealworm protein by spray drying. In this way, the hydrolysis efficiency can be improved, and excessive protein degradation can be avoided, while ensuring the solubility and bioavailability of the protein.

[0045] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0046] Figure 1 is a flow chart of a method for extracting protein from mealworms according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0047] Step 101, removing impurities and washing the mealworm bodies, and then sterilizing and drying them to obtain dried mealworm bodies;

[0048] Step 102, crushing and sieving the dried insect bodies to obtain crushed insect bodies;

[0049] Step 103, after the crushed insect bodies are passed through an organic solvent to prepare an insect pulp, the insect pulp is extracted and defatted by supercritical fluid CO2 extraction to obtain an extracted defatted product;

[0050] Step 104, adding water to the extracted defatted product for homogenization, and filtering the resulting homogenate to remove epidermal substances to obtain a purified homogenate;

[0051] Step 105, enzymatically hydrolyzing the purified homogenate to obtain a hydrolyzed slurry;

[0052] Step 106, decolorizing the slurry using activated carbon to obtain an adsorption product;

[0053] Step 107, using an electrochemical-salting-out method to enrich and precipitate the adsorbed product to obtain a precipitate;

[0054] Step 108, performing centrifugal desalting treatment on the precipitate to obtain a desalted product;

[0055] Step 109, adding water to the desalted product to obtain a homogenate, and subjecting the homogenate to a precipitation and drainage treatment to obtain a homogenate precipitate;

[0056] Step 1010, using a small molecule bioactive peptide separation technology to treat the homogenate precipitate to remove insoluble proteins to obtain a separation product;

[0057] Step 1011, treating the separated product by spray drying to obtain mealworm protein.

[0058] In the above-mentioned yellow mealworm protein extraction scheme, the process of enzymatic hydrolysis of the purified homogenate is crucial. By hydrolysis, the protein can be decomposed into smaller peptides, thereby improving the solubility and bioavailability of the protein. The efficiency of hydrolysis is often affected by multiple factors, including changes in hydrolysis temperature and pH value. Adjusting the hydrolysis temperature can affect the activity and reaction rate of the enzyme, thereby affecting the hydrolysis efficiency. According to different protein properties and enzyme properties, appropriately adjusting the hydrolysis temperature can improve the hydrolysis efficiency while avoiding excessive degradation of the protein. In addition, the pH value plays a vital role in the hydrolysis process because the activity and stability of the enzyme are affected by the pH value. Different enzymes show optimal activity in different pH ranges, and when exceeding this range, the activity of the enzyme will decrease or even inactivate.

[0059] Not only that, but also considering that pH and temperature usually affect each other. Under different pH and temperature conditions, the activity and stability of the enzyme will change. Therefore, adaptively adjusting the hydrolysis temperature based on the change of pH value is an effective strategy. For different pH values, choosing the appropriate hydrolysis temperature can better adapt to the changes in enzyme activity and stability, so as to maximize the catalytic effect of the enzyme and improve the hydrolysis efficiency.

[0060] Based on this, the technical concept of the present application is to monitor and collect the pH value and hydrolysis temperature of the purified homogenate in real time through sensors during the hydrolysis process, and use artificial intelligence-based data processing and analysis algorithms at the back end to perform time-series coordinated analysis of the pH value and the hydrolysis temperature, so as to capture the time-series coordinated change pattern and correlation between the pH value and the hydrolysis temperature. In this way, the hydrolysis temperature can be adaptively adjusted based on the change of the pH value during the hydrolysis process, thereby realizing intelligent control of the hydrolysis process and the extraction of yellow mealworm protein, so as to improve the hydrolysis efficiency, avoid excessive protein degradation, and ensure the solubility and bioavailability of the protein.

[0061] In one embodiment of the present disclosure, Figure 2 is based on Figure 1 The embodiment shown is a flow chart of step 105 of a method for extracting protein from mealworms. Figure 2 As shown, the purified homogenate is subjected to enzymatic hydrolysis to obtain a hydrolyzed slurry, comprising:

[0062] Step 1051, obtaining a time series of pH value and a time series of hydrolysis temperature;

[0063] Step 1052: performing sequence segmentation and data regularization on the time series of the pH value and the time series of the hydrolysis temperature at a predetermined time scale to obtain a sequence of local time series input vectors of the pH value and a sequence of local time series input vectors of the hydrolysis temperature;

[0064] Step 1053: Use a gamma responsiveness analysis module to perform vector pair analysis on the sequence of the pH value local time series input vectors and the sequence of the hydrolysis temperature local time series input vectors to obtain a sequence of pH value-hydrolysis temperature local time series response interaction feature vectors;

[0065] Step 1054, performing autocorrelation feature saliency fusion on the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors to obtain the pH value-hydrolysis temperature full time domain interaction feature;

[0066] Step 1055: Based on the full-time interaction characteristics of the pH value-hydrolysis temperature, determine whether the hydrolysis temperature value at the current time point should increase, decrease, or remain unchanged.

[0067] Specifically, in the technical solution of the present application, first, the time series of pH value and the time series of hydrolysis temperature are obtained. Then, considering that both pH value and hydrolysis temperature will continue to change over time, that is, both pH value and hydrolysis temperature have a dynamic change law of time series in the time dimension. Therefore, in order to better understand the change law and time series correlation of these two parameters in the hydrolysis process, so as to carry out effective control and regulation, in the technical solution of the present application, the time series of pH value and the time series of hydrolysis temperature are sequence segmented and data regularized at a predetermined time scale to obtain a sequence of local time series input vectors of pH value and a sequence of local time series input vectors of hydrolysis temperature. By segmenting and data regularizing the time series data of pH value and hydrolysis temperature, it can help to better understand the changing trend of these two parameters over time, including periodic changes, trend changes, etc., so as to capture the time series correlation and interactive correlation between pH value and hydrolysis temperature, thereby optimizing the control strategy of hydrolysis process.

[0068] Then, considering that the pH value and the hydrolysis temperature not only have their own time series dynamic change rules in the time dimension, but also there is a time series correlation between the two data, this correlation can affect the activity of the hydrolysis process enzyme, which is very important for the control and optimization of the hydrolysis process. Therefore, in order to further study the interaction between the pH value and the hydrolysis temperature and its influence on the hydrolysis process, in the technical scheme of the present application, the gamma responsiveness analysis module is further used to analyze the sequence of the local time series input vector of the pH value and the sequence of the local time series input vector of the hydrolysis temperature by vector to obtain the sequence of the local time series response interaction feature vector of the pH value-hydrolysis temperature. The gamma responsiveness analysis module can help reveal the interaction between the pH value and the hydrolysis temperature in the hydrolysis process in each local time period. That is to say, by vector-by-vector analysis, the time series correlation degree between the pH value and the hydrolysis temperature in different time periods can be understood, and how they affect each other. In this way, the laws and patterns that may exist between the pH value and the hydrolysis temperature under different conditions can be found, providing a deeper understanding for the optimization of the hydrolysis process.

[0069] In one embodiment of the present disclosure, a gamma responsiveness analysis module is used to perform vector pair analysis on the sequence of the local timing input vectors of the pH value and the sequence of the local timing input vectors of the hydrolysis temperature to obtain a sequence of the local timing response interaction feature vectors of the pH value-hydrolysis temperature, including: using the gamma responsiveness analysis module to perform vector pair analysis on the sequence of the local timing input vectors of the pH value and the sequence of the local timing input vectors of the hydrolysis temperature using the following gamma response formula to obtain a sequence of the local timing response interaction feature vectors of the pH value-hydrolysis temperature; wherein the gamma response formula is:

[0070]

[0071] in, and are the eigenvalues ​​of the ith position of the corresponding PH value local time series input vector and the hydrolysis temperature local time series input vector in the sequence of the PH value local time series input vector and the sequence of the hydrolysis temperature local time series input vector, respectively. A, B, C and D are adjustment hyperparameters. v i It is the characteristic value of the i-th position of each pH value-hydrolysis temperature local time series response interaction characteristic vector in the sequence of the pH value-hydrolysis temperature local time series response interaction characteristic vector.

[0072] It should be understood that the gamma responsiveness correlation characteristics between pH value and hydrolysis temperature in different local time periods have a time-series correlation relationship in the entire time domain. In order to comprehensively consider the hydrolysis parameter time-series correlation characteristic information in different time periods, so as to more comprehensively and comprehensively perform the time-series collaborative analysis between pH value and hydrolysis temperature in the hydrolysis process, in the technical solution of the present application, the sequence of the local time-series response interaction characteristic vector of pH value-hydrolysis temperature is further passed through the autocorrelation signal feature significant fusion network to obtain the pH value-hydrolysis temperature full time domain interaction characteristic vector. In particular, the autocorrelation signal feature significant fusion network can adaptively allocate weights according to the importance of the time-series correlation characteristics between pH value and hydrolysis temperature in different local time periods, and perform weighted fusion. Through the processing of the autocorrelation signal feature significant fusion network, the interaction relationship and change law of pH value and hydrolysis temperature in the entire time series can be better captured and reflected, which is helpful to deeply understand the dynamic interaction mechanism between them, improve the richness of feature expression, and provide a basis for subsequent hydrolysis parameter control and hydrolysis process optimization.

[0073] In one embodiment of the present disclosure, the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors is subjected to autocorrelation feature significant fusion to obtain the pH value-hydrolysis temperature full time domain interaction feature, including: passing the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors through an autocorrelation signal feature significant fusion network to obtain the pH value-hydrolysis temperature full time domain interaction feature vector as the pH value-hydrolysis temperature full time domain interaction feature.

[0074] Furthermore, the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors is passed through an autocorrelation signal feature saliency fusion network to obtain a pH value-hydrolysis temperature full time domain interaction feature vector as the pH value-hydrolysis temperature full time domain interaction feature, including: passing the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors through the autocorrelation signal feature saliency fusion network to process the sequence with the following autocorrelation saliency fusion formula to obtain the pH value-hydrolysis temperature full time domain interaction feature vector; wherein the autocorrelation saliency fusion formula is:

[0075]

[0076]

[0077]

[0078] Among them, h i is the i-th pH value-hydrolysis temperature local time series response interaction feature vector in the sequence of pH value-hydrolysis temperature local time series response interaction feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score of the ith pH value-hydrolysis temperature local temporal response interaction feature vector, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the sequence of the pH value-hydrolysis temperature local temporal response interaction feature vector, and V is the pH value-hydrolysis temperature full time domain interaction feature vector.

[0079] Furthermore, the pH value-hydrolysis temperature full time domain interactive feature vector is passed through a hydrolysis temperature controller based on a classifier to obtain a temperature control instruction, and the temperature control instruction is used to indicate whether the hydrolysis temperature value at the current time point should be increased, decreased, or kept unchanged. In other words, the interactive feature information based on the full time domain between the local time series features between each pH value and the hydrolysis temperature is used for classification processing, so as to utilize the time series coordinated change pattern and correlation relationship between the pH value and the hydrolysis temperature, and adaptively adjust the hydrolysis temperature based on the change of the pH value in the actual hydrolysis process, thereby realizing intelligent control of the hydrolysis process and the extraction of protein from yellow mealworms.

[0080] In one embodiment of the present disclosure, based on the pH value-hydrolysis temperature full time domain interaction characteristics, it is determined whether the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged, including: passing the pH value-hydrolysis temperature full time domain interaction feature vector through a classifier-based hydrolysis temperature controller to obtain a temperature control instruction, wherein the temperature control instruction is used to indicate that the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged.

[0081] In one embodiment of the present disclosure, the yellow mealworm protein extraction method further includes a training step: for training the gamma responsiveness analysis module, the autocorrelation signal feature saliency fusion network and the classifier-based hydrolysis temperature controller. The training step includes: obtaining a time series of training pH values ​​and a time series of training hydrolysis temperatures; performing sequence segmentation and data regularization on the time series of training pH values ​​and the time series of training hydrolysis temperatures at a predetermined time scale to obtain a sequence of training pH value local time series input vectors and a sequence of training hydrolysis temperature local time series input vectors; using the gamma responsiveness analysis module to perform vector pair analysis on the sequence of training pH value local time series input vectors and the sequence of training hydrolysis temperature local time series input vectors to obtain a sequence of training pH value-hydrolysis temperature local time series response interaction feature vectors; and converting the training pH value and the time series of training hydrolysis temperature into a vector pair analysis. The sequence of H value-hydrolysis temperature local time series response interaction feature vectors is processed by the autocorrelation signal feature significant fusion network to obtain the training pH value-hydrolysis temperature full time domain interaction feature vector; the training pH value-hydrolysis temperature full time domain interaction feature vector is passed through the classifier-based hydrolysis temperature controller to obtain the classification loss function value; based on the classification loss function value, the gamma responsiveness analysis module, the autocorrelation signal feature significant fusion network and the classifier-based hydrolysis temperature controller are trained, and in each iteration, the training pH value-hydrolysis temperature full time domain interaction feature vector is corrected.

[0082] In the technical scheme described above, each training pH value-hydrolysis temperature local time series response interaction feature vector in the sequence of training pH value-hydrolysis temperature local time series response interaction feature vectors expresses the local time domain source time series interaction distribution of the training pH value and the training hydrolysis temperature. Therefore, after the sequence of the training pH value-hydrolysis temperature local time series response interaction feature vectors is fused through an autocorrelation signal feature saliency network, the autocorrelation distribution can be enhanced based on the overall distribution of the pH value-hydrolysis temperature source time series interaction in each local time domain, so as to obtain the time series interaction feature expression of the training pH value-hydrolysis temperature full time domain interaction feature vector in the local-global time domain.

[0083] In this way, considering the complexity of the expression of multi-parameter source time series interaction correlation features of the training pH value-hydrolysis temperature full time domain interaction feature vector in the local-global time domain temporal series feature domain, the training pH value-hydrolysis temperature full time domain interaction feature vector will have rich geometric shape details in the high-dimensional feature space, so that there will be category representation distortion when classified by the classifier to map to the class probability domain, that is, it affects the category representation of the training pH value-hydrolysis temperature full time domain interaction feature vector for the classifier's predetermined category, thereby reducing the accuracy of the classification result.

[0084] Based on this, the applicant of the present application corrects the training pH value-hydrolysis temperature full time domain interactive feature vector each time the training pH value-hydrolysis temperature full time domain interactive feature vector is classified and iterated by the classifier, which is expressed as follows: In each iteration, the training pH value-hydrolysis temperature full time domain interactive feature vector is corrected by the following optimization formula to obtain the corrected training pH value-hydrolysis temperature full time domain interactive feature vector; wherein the optimization formula is:

[0085]

[0086] Wherein, p is the class probability value obtained by the classifier of the training pH value-hydrolysis temperature full time domain interaction feature vector V, and v i is the ith eigenvalue of the pH-hydrolysis temperature full-time domain interactive eigenvector V, is the mean of all eigenvalues ​​of the training pH value-hydrolysis temperature full-time domain interactive feature vector V, ‖V‖1 represents the norm of the training pH value-hydrolysis temperature full-time domain interactive feature vector V, and α is a weight hyperparameter, V is the training pH value-hydrolysis temperature full-time domain interactive feature vector, v i ′ is the ith eigenvalue of the corrected training pH-hydrolysis temperature full-time domain interaction eigenvector, and exp(·) represents the calculation of the natural exponential function value with the value as the power.

[0087] Specifically, while maintaining the geometric shape details of the high-dimensional feature manifold under the class probability mapping of the training pH value-hydrolysis temperature full-time domain interactive feature vector V, the shape attribute editing is performed on the feature value details relative to the variational representation of the feature set of the training pH value-hydrolysis temperature full-time domain interactive feature vector V by means of class probability distortion consultation, so that the class probability distortion of the training pH value-hydrolysis temperature full-time domain interactive feature vector V is mapped to the latent class space feature representation, and then the consultation fusion is performed by supplementing the basic low-rank constrained latent inversion representation to bridge the gap between the edited consultation representation and the original geometric shape details, thereby improving the class representation of the high-dimensional features of the training pH value-hydrolysis temperature full-time domain interactive feature vector V, thereby improving the accuracy of the classification results. In this way, the hydrolysis temperature can be adaptively adjusted based on the change of pH value during the hydrolysis process, thereby realizing intelligent control of the hydrolysis process and the extraction of yellow mealworm protein, so as to improve the hydrolysis efficiency, avoid excessive protein degradation, and ensure the solubility and bioavailability of the protein.

[0088] In summary, the above scheme is adopted to collect the pH value and hydrolysis temperature of the purified homogenate in real time through sensors during the hydrolysis process, and to perform a time-series coordinated analysis of the pH value and the hydrolysis temperature using an artificial intelligence-based data processing and analysis algorithm at the back end, so as to capture the time-series coordinated change pattern and correlation between the pH value and the hydrolysis temperature. In this way, the hydrolysis temperature can be adaptively adjusted based on the change of the pH value during the hydrolysis process, thereby realizing intelligent control of the hydrolysis process and the extraction of Tenebrio molitor protein, so as to improve the hydrolysis efficiency, avoid excessive protein degradation, and ensure the solubility and bioavailability of the protein.

[0089] Figure 3 FIG. 1 is a block diagram of a system for extracting protein from mealworms according to an exemplary embodiment. Figure 3 As shown, the system 200 includes:

[0090] The sterilization and drying module 201 is used to remove impurities and wash the mealworm bodies and then sterilize and dry them to obtain dried mealworm bodies;

[0091] A crushing and screening processing module 202 is used to crush and screen the dried insect bodies to obtain crushed insect bodies;

[0092] An extraction and degreasing module 203 is used to extract and degrease the pulverized insect bodies through an organic solvent to obtain an insect pulp, and then extract and degrease the insect pulp through a supercritical fluid CO2 extraction method to obtain an extracted degreased product;

[0093] A water addition and homogenization processing module 204 is used to add water and homogenize the extracted defatted material, and filter the generated homogenate to remove epidermal substances to obtain a purified homogenate;

[0094] An enzyme hydrolysis module 205 is used to perform enzyme hydrolysis on the purified homogenate to obtain a hydrolyzed slurry;

[0095] A decolorization treatment module 206 is used to decolorize the slurry using activated carbon to obtain an adsorption product;

[0096] An enrichment and precipitation module 207 is used to enrich and precipitate the adsorption product using an electrochemical-salting-out method to obtain a precipitate;

[0097] A centrifugal desalination treatment module 208 is used to perform a centrifugal desalination treatment on the precipitate to obtain a desalted product;

[0098] The sedimentation and drainage treatment module 209 is used to add water to the desalination product to homogenize to obtain a homogenate, and to perform sedimentation and drainage treatment on the homogenate to obtain a homogenate precipitate;

[0099] A removal processing module 210 is used to use a small molecule bioactive peptide separation technology to process the homogenate precipitate to remove the insoluble protein to obtain a separation product;

[0100] The spray drying module 2011 is used to process the separation product by spray drying to obtain mealworm protein.

[0101] Reference below Figure 4 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0102] like Figure 4 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0103] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0104] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0105] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0106] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0107] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0108] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

[0111] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0112] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] Figure 5 is an application scenario diagram of a method for extracting protein from mealworms according to an exemplary embodiment. Figure 5 As shown, in this application scenario, first, the time series of pH values ​​is obtained (for example, Figure 5 C1) and the time series of hydrolysis temperature (e.g., Figure 5 Then, the obtained time series of pH value and time series of hydrolysis temperature are input to a server (for example, Figure 5 In the S) shown in FIG. 1 , the server is capable of processing the time series of the pH value and the time series of the hydrolysis temperature based on the mealworm protein extraction algorithm to determine whether the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged.

[0114] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0115] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0116] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A method for extracting protein from yellow mealworms, characterized in that: include: The yellow mealworm bodies are cleaned and sterilized and dried to obtain dried mealworm bodies; The dried insect bodies are crushed and sieved to obtain crushed insect bodies; After the crushed insect bodies are passed through an organic solvent to prepare an insect pulp, the insect pulp is extracted and defatted by supercritical fluid CO2 extraction to obtain an extracted defatted product; The extracted defatted product is homogenized by adding water, and the resulting homogenate is filtered to remove epidermal substances to obtain a purified homogenate; enzymatically hydrolyzing the purified homogenate to obtain a hydrolyzed slurry; Decolorizing the slurry using activated carbon to obtain an adsorption product; Using an electrochemical-salting-out method to enrich and precipitate the adsorbed product to obtain a precipitate; The precipitate is subjected to centrifugal desalting treatment to obtain a desalted product; adding water to the desalted product to homogenize to obtain a homogenate, and subjecting the homogenate to a precipitation and drainage treatment to obtain a homogenate precipitate; The homogenate precipitate is treated using a small molecule bioactive peptide separation technology to remove insoluble proteins to obtain a separation product; The separated product is treated by a spray drying method to obtain yellow mealworm protein; The purified homogenate is subjected to enzymatic hydrolysis to obtain a hydrolyzed slurry, comprising: Obtain the time series of pH value and hydrolysis temperature; Performing sequence segmentation and data regularization on the time series of the pH value and the time series of the hydrolysis temperature at a predetermined time scale to obtain a sequence of local time series input vectors of the pH value and a sequence of local time series input vectors of the hydrolysis temperature; Using a gamma responsiveness analysis module, performing vector pair analysis on the sequence of the pH value local time series input vectors and the sequence of the hydrolysis temperature local time series input vectors to obtain a sequence of pH value-hydrolysis temperature local time series response interaction feature vectors; Performing autocorrelation feature saliency fusion on the sequence of the pH value-hydrolysis temperature local time series response interaction feature vectors to obtain the pH value-hydrolysis temperature full time domain interaction feature; Based on the pH value-hydrolysis temperature full time domain interaction characteristics, determining whether the hydrolysis temperature value at the current time point should increase, decrease, or remain unchanged; Using a gamma responsiveness analysis module to perform vector pair analysis on the sequence of the local timing input vectors of the pH value and the sequence of the local timing input vectors of the hydrolysis temperature to obtain a sequence of the local timing response interaction characteristic vectors of the pH value and the hydrolysis temperature, including: using the gamma responsiveness analysis module to perform vector pair analysis on the sequence of the local timing input vectors of the pH value and the sequence of the local timing input vectors of the hydrolysis temperature using the following gamma response formula to obtain a sequence of the local timing response interaction characteristic vectors of the pH value and the hydrolysis temperature; Wherein, the gamma response formula is: in, and are the eigenvalues ​​of the ith position of the corresponding PH value local time series input vector and the hydrolysis temperature local time series input vector in the sequence of the PH value local time series input vector and the sequence of the hydrolysis temperature local time series input vector, respectively. A, B, C and D are adjustment hyperparameters. v i is the characteristic value of the i-th position of each pH value-hydrolysis temperature local time series response interaction characteristic vector in the sequence of the pH value-hydrolysis temperature local time series response interaction characteristic vector; The sequence of the local time series response interaction feature vectors of the pH value and the hydrolysis temperature is subjected to autocorrelation feature saliency fusion to obtain the full time domain interaction feature of the pH value and the hydrolysis temperature, including: the sequence of the local time series response interaction feature vectors of the pH value and the hydrolysis temperature is subjected to the autocorrelation signal feature saliency fusion network to obtain the full time domain interaction feature vector of the pH value and the hydrolysis temperature as the full time domain interaction feature of the pH value and the hydrolysis temperature; The sequence of the local time series response interaction feature vectors of the pH value and the hydrolysis temperature is passed through an autocorrelation signal feature saliency fusion network to obtain a pH value-hydrolysis temperature full time domain interaction feature vector as the pH value-hydrolysis temperature full time domain interaction feature, including: the sequence of the local time series response interaction feature vectors of the pH value and the hydrolysis temperature is passed through the autocorrelation signal feature saliency fusion network to be processed by the following autocorrelation saliency fusion formula to obtain the pH value-hydrolysis temperature full time domain interaction feature vector; The autocorrelation saliency fusion formula is: Among them, h i is the i-th pH value-hydrolysis temperature local time series response interaction feature vector in the sequence of pH value-hydrolysis temperature local time series response interaction feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score of the ith pH value-hydrolysis temperature local temporal response interaction feature vector, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the sequence of the pH value-hydrolysis temperature local temporal response interaction feature vector, and V is the pH value-hydrolysis temperature full time domain interaction feature vector.

2. The method for extracting protein from yellow mealworm according to claim 1, characterized in that: Based on the pH value-hydrolysis temperature full time domain interaction characteristics, determine whether the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged, including: passing the pH value-hydrolysis temperature full time domain interaction feature vector through a classifier-based hydrolysis temperature controller to obtain a temperature control instruction, and the temperature control instruction is used to indicate that the hydrolysis temperature value at the current time point should increase, decrease or remain unchanged.

3. The method for extracting protein from yellow mealworm according to claim 2, characterized in that: The method also includes a training step for training the gamma responsiveness analysis module, the autocorrelation signal feature saliency fusion network and the classifier-based hydrolysis temperature controller.

4. The method for extracting protein from yellow mealworm according to claim 3, characterized in that: The training step comprises: Obtain the time series of the training pH value and the time series of the training hydrolysis temperature; Performing sequence segmentation and data regularization on the time series of the training pH value and the time series of the training hydrolysis temperature at a predetermined time scale to obtain a sequence of local time series input vectors of the training pH value and a sequence of local time series input vectors of the training hydrolysis temperature; Using the gamma responsiveness analysis module, performing vector pair analysis on the sequence of the training pH value local time series input vectors and the sequence of the training hydrolysis temperature local time series input vectors to obtain a sequence of training pH value-hydrolysis temperature local time series response interaction feature vectors; Processing the sequence of the training pH value-hydrolysis temperature local time series response interaction feature vectors through the autocorrelation signal feature saliency fusion network to obtain the training pH value-hydrolysis temperature full time domain interaction feature vector; Passing the training pH value-hydrolysis temperature full time domain interactive feature vector through the classifier-based hydrolysis temperature controller to obtain a classification loss function value; The gamma responsiveness analysis module, the autocorrelation signal feature saliency fusion network and the classifier-based hydrolysis temperature controller are trained based on the classification loss function value, and in each iteration, the training pH value-hydrolysis temperature full time domain interaction feature vector is corrected.

Citation Information

Patent Citations

  • Method for preparing tenebrio molitor protein powder by enzymolysis

    CN102422974A

  • Method for extracting insect protein

    CN107034258A

  • Preparation method of cytidine 5 '-phosphate

    CN117126220A