Production control method and system of fish flavor chili sauce

Through in-depth analysis technology, the correlation between the raw material ratio of fish-flavored chili sauce and product parameters was solved, and the problems of multiple regulation in the existing technology were reduced, achieving the reduction of production costs and the maintenance of product flavor.

CN118782188BActive Publication Date: 2024-11-29SICHUAN WANGJIADU FOOD CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411242166.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-11-29
Estimated Expiration
2044-09-05

AI Technical Summary

Technical Problem

The existing production methods of fish-flavored chili sauce cannot determine the production parameters from the perspective of product parameter indicators, resulting in multiple adjustments during the production process to achieve the expected product parameter indicators and increase production costs.

Method used

In-depth analysis technology is used to analyze the relationship between the spicyness and acidity of each raw material in the formula and the produced fish-flavored chili sauce, determine the most suitable raw material ratio under the corresponding fermentation conditions, and reduce the number of artificial regulation in the later stage.

Benefits of technology

The actual spicy and acidity of the fish-flavored chili sauce produced is achieved to the expected target value, reducing production costs, and maintaining the natural flavor of the product.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118782188B_ABST
    Figure CN118782188B_ABST
Patent Text Reader

Abstract

The present invention belongs to the technical field of production management, and provides a production control method and system for fish-flavored chili sauce. The method comprises: receiving the formula, target spiciness and target acidity of the fish-flavored chili sauce; using a deep analysis model to process the main formula raw materials, auxiliary formula raw materials, and fermentation parameters that affect the spiciness and acidity in the formula to obtain a spiciness correlation relationship and an acidity correlation relationship, and thereby determining the ratio of the main formula raw materials and auxiliary formula raw materials that affect the spiciness and acidity; regulating the amount of the formula raw materials according to the determined ratio, and pre-treating, pickling, and fermenting the formula raw materials in turn, and producing a fish-flavored chili sauce that meets the target spiciness and target acidity. The present invention uses deep analysis technology to analyze the correlation between each raw material in the formula and the spiciness and acidity of the produced fish-flavored chili sauce, and thereby determines the most suitable raw material ratio under the corresponding fermentation conditions, which can reduce production costs and maintain the natural flavor of the product.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of production management, and in particular to a production control method and system for fish-flavored chili sauce. Background Art

[0002] Fish-flavored chili sauce is a condiment, usually made by mixing chili peppers, fish or fish sauce, salt, sugar and other spices, and can be used as a dipping sauce or seasoning for cooking. The existing production of fish-flavored chili sauce determines the production parameters from the perspective of raw material ratio, but cannot determine the production parameters from the perspective of product parameter indicators, such as spiciness, acidity, etc. However, it is generally difficult to accurately correspond between the raw material ratio at the front end and the parameter indicators of the product produced at the back end, which is interfered by various factors in the production process (such as fermentation environment, duration, etc.), resulting in the fish-flavored chili sauce produced needing to be adjusted multiple times to achieve the expected product parameter indicators, which will undoubtedly increase the production cost of fish-flavored chili sauce manufacturers. The present invention aims to provide a solution to the above-mentioned technical problems. Summary of the invention

[0003] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a production control method, system, electronic device, storage medium and computer program product of fish flavor chili sauce.

[0004] The present invention provides a production control method of fish flavor chili sauce, comprising the following steps:

[0005] Receive a formula, target spiciness, and target acidity of a fish-flavored chili sauce; wherein the formula includes fresh erjingtiao, fresh chili pepper, red pepper, star anise, galangal, fresh green peppercorns, patchouli, garlic, young ginger, celery, salt, crucian carp, white wine, fermented glutinous rice, and rapeseed oil;

[0006] Analyze and process the formula to obtain a first main formula raw material and a first auxiliary formula raw material that affect the spiciness, and a second main formula raw material and a second auxiliary formula raw material that affect the acidity;

[0007] The first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity are deeply processed using a deep analysis model to obtain a spiciness correlation relationship and an acidity correlation relationship; wherein the spiciness correlation relationship is used to indicate the correspondence between the actual spiciness of the produced fish-flavored chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, and the acidity correlation relationship is used to indicate the correspondence between the actual acidity of the produced fish-flavored chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material; the first fermentation temperature and the first fermentation humidity are preset;

[0008] Determine a first ratio of the first main formula raw material and the first auxiliary formula raw material that affects the spiciness based on the target spiciness and the spiciness correlation relationship, and determine a second ratio of the second main formula raw material and the second auxiliary formula raw material that affects the acidity based on the target acidity and the acidity correlation relationship;

[0009] The amount of the formula raw materials is regulated according to the first ratio and the second ratio, and the formula raw materials are pretreated, pickled and fermented in sequence to produce a fish flavor chili sauce that meets the target spiciness and the target acidity.

[0010] In some embodiments, the method further comprises:

[0011] Acquire several pieces of real production data of fish-flavored chili sauce, each piece of the real production data comprising: a ratio of a third main formula raw material and a third auxiliary formula raw material affecting spiciness, a ratio of a fourth main formula raw material and a fourth auxiliary formula raw material affecting acidity, fermentation parameters, a first actual spiciness, and a first actual acidity; wherein the fermentation parameters comprise a second fermentation temperature and a second fermentation humidity;

[0012] A training data set is formed according to the real production data, and the deep analysis model is trained using the training data in the training data set until a training termination condition is reached.

[0013] In some embodiments, forming a training data set according to the real production data includes:

[0014] Forming a first set of training data according to the real production data;

[0015] Regulating a third ratio of the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, and the second auxiliary formula raw material in the formula, and regulating the fermentation parameters, arranging and combining the third ratio and the fermentation parameters to obtain simulation input data, inputting the simulation input data into simulation software, and simulating to obtain simulation output data, wherein the simulation output data includes a second actual spiciness and a second actual acidity;

[0016] A second set of training data is constructed based on the simulation input data and the simulation output data, and the training data set is obtained by fusing the first set of training data and the second set of training data.

[0017] In some embodiments, the obtaining the training data set by fusing the first set of training data and the second set of training data includes:

[0018] The real production data also includes data on the number of manual adjustments, and the average number of manual adjustments is calculated based on the data on the number of manual adjustments;

[0019] Calculate a first proportion of the first group of training data according to the average number of manual controls and a corresponding negative correlation function, and determine a second proportion of the second group of training data according to the first proportion;

[0020] Determine a first data amount in the first set of training data and a second data amount in the second set of training data according to a preset amount of training data and the first proportion and the second proportion;

[0021] The training data set is composed of training data of the first data volume randomly selected from the first group of training data and training data of the second data volume randomly selected from the second group of training data.

[0022] In some embodiments, the negative correlation function is expressed as follows:

[0023] ;

[0024] In the formula, Perc1 represents the first proportion, Perc is the basic value of the first proportion, n is the average number of manual controls, n1 is the median value of the number of manual controls in each of the control number record data, and n2 is the maximum value of the number of manual controls in each of the control number record data.

[0025] In some embodiments, the deep analysis model is constructed based on a convolutional neural network or a generative adversarial network.

[0026] The present invention also provides a production control system for fish-flavored chili sauce, comprising a receiving module, a first processing module, a second processing module, a third processing module, and a control module; the characteristics are:

[0027] The receiving module is used to receive the formula, target spiciness and target acidity of the fish-flavored chili sauce; wherein the formula includes fresh er jing tiao, fresh chili pepper, red pepper, star anise, galangal, fresh green peppercorns, patchouli, garlic, young ginger, celery, salt, crucian carp, white wine, fermented glutinous rice and rapeseed oil;

[0028] The first processing module is used to analyze and process the formula to obtain a first main formula raw material and a first auxiliary formula raw material that affect the spiciness, and a second main formula raw material and a second auxiliary formula raw material that affect the acidity;

[0029] The second processing module is used to use the deep analysis model to perform deep processing on the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity to obtain a spiciness correlation relationship and an acidity correlation relationship; wherein the spiciness correlation relationship is used to indicate the correspondence between the actual spiciness of the produced fish flavor chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, and the acidity correlation relationship is used to indicate the correspondence between the actual acidity of the produced fish flavor chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material; the first fermentation temperature and the first fermentation humidity are preset;

[0030] The third processing module is used to determine a first ratio of the first main formula raw material and the first auxiliary formula raw material that affects the spiciness based on the target spiciness and the spiciness correlation relationship, and to determine a second ratio of the second main formula raw material and the second auxiliary formula raw material that affects the acidity based on the target acidity and the acidity correlation relationship;

[0031] The control module is used to regulate the amount of the formula raw materials according to the first ratio and the second ratio, and to pretreat, marinate and ferment the formula raw materials in sequence to produce a fish flavor chili sauce that meets the target spiciness and the target acidity.

[0032] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method as described in any of the preceding items.

[0033] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0034] The present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor of an electronic device, it implements any of the methods described above.

[0035] The invention uses deep analysis technology to analyze the correlation between each raw material in the formula and the spiciness and acidity of the produced fish-flavored chili sauce, and accordingly determines the most suitable raw material ratio under corresponding fermentation conditions, so that the actual spiciness and actual acidity of the produced fish-flavored chili sauce are closest to the expected target spiciness and target acidity, reducing the number of times of artificially adjusting the acidity and spiciness in the later stage, thereby reducing the production cost and maintaining the natural flavor of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0037] Figure 1 It is a flow chart of a production control method of a fish flavor chili sauce disclosed in an embodiment of the present invention;

[0038] Figure 2 The invention discloses a structural schematic diagram of a production control system for fish-flavored chili sauce disclosed in an embodiment of the invention. DETAILED DESCRIPTION

[0039] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0040] See also Figure 1 The embodiment of the present invention discloses a production control method of fish flavor chili sauce, comprising the following steps:

[0041] Receive a formula, target spiciness, and target acidity of a fish-flavored chili sauce; wherein the formula includes fresh erjingtiao, fresh chili pepper, red pepper, star anise, galangal, fresh green peppercorns, patchouli, garlic, young ginger, celery, salt, crucian carp, white wine, fermented glutinous rice, and rapeseed oil;

[0042] Analyze and process the formula to obtain a first main formula raw material and a first auxiliary formula raw material that affect the spiciness, and a second main formula raw material and a second auxiliary formula raw material that affect the acidity;

[0043] The first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity are deeply processed using a deep analysis model to obtain a spiciness correlation relationship and an acidity correlation relationship; wherein the spiciness correlation relationship is used to indicate the correspondence between the actual spiciness of the produced fish-flavored chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, and the acidity correlation relationship is used to indicate the correspondence between the actual acidity of the produced fish-flavored chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material; the first fermentation temperature and the first fermentation humidity are preset;

[0044] Determine a first ratio of the first main formula raw material and the first auxiliary formula raw material that affects the spiciness based on the target spiciness and the spiciness correlation relationship, and determine a second ratio of the second main formula raw material and the second auxiliary formula raw material that affects the acidity based on the target acidity and the acidity correlation relationship;

[0045] The amount of the formula raw materials is regulated according to the first ratio and the second ratio, and the formula raw materials are pretreated, pickled and fermented in sequence to produce a fish flavor chili sauce that meets the target spiciness and target acidity.

[0046] Referring to the background technology, the existing fish-flavored chili sauce production line only determines the ratio of the raw materials used for production according to the formula. However, various factors in the production process (such as fermentation environment, duration, etc.) will affect the spiciness and acidity of the final fish-flavored chili sauce produced, that is, it is easy to have the raw material ratio at the front end and the parameter indicators of the product produced at the back end. It is generally difficult to accurately correspond, which requires multiple manual adjustments to achieve the expected product spiciness and acidity. In this way, on the one hand, the production cost of the fish-flavored chili sauce manufacturer will increase, and on the other hand, it will also cause the flavor of the fish-flavored chili sauce to be less natural.

[0047] In view of the above technical problems, the present invention adopts a scheme for determining the ratio of each raw material used for production from the perspective of product parameter indicators. First, the formula determined for this production is analyzed and processed to obtain the first main formula raw material and the first auxiliary formula raw material that affect the spiciness, and the second main formula raw material and the second auxiliary formula raw material that affect the acidity.

[0048] Referring to the above formula table, both fresh erjingtiao and fresh chili pepper contain capsaicin, which is a key factor in determining the spiciness of the chili sauce. The higher the capsaicin content, the greater the spiciness of the chili sauce. Therefore, the first main formula raw materials in the present invention include fresh erjingtiao, fresh chili pepper, and fresh green peppercorns (when some spicy green pepper varieties are selected). Garlic, young ginger, and celery may produce some bioactive substances such as sulfides and volatile organic compounds during the fermentation process, which will affect the release of capsaicin or the human body's perception of it; the alcohol in the white wine can extract capsaicin from the pepper, so the use of white wine during the fermentation process will increase the spiciness of the chili sauce; the microorganisms and enzymes contained in the fermented glutinous rice will affect the conversion or degradation of capsaicin, thereby indirectly affecting the spiciness. Therefore, the first auxiliary formula raw materials in the present invention include garlic, young ginger, celery, white wine, and fermented glutinous rice.

[0049] Laozao is a fermented food, usually containing lactic acid and other organic acids, which directly provide sour taste for chili sauce; although liquor itself is not sour, the alcohol in it will be converted into acid during the fermentation process, thereby increasing the acidity. Therefore, the second main formula raw materials in the present invention include Laozao and liquor. Vegetables such as garlic, young ginger, and celery produce acidic substances due to the action of enzymes during the fermentation process, such as alliinase in garlic can catalyze alliin to produce acid; the protein in crucian carp meat can be decomposed to produce amino acids during the fermentation process, and some amino acids such as glutamic acid are converted into acidic substances under certain conditions; fresh Erjingtiao and fresh millet pepper, these two peppers, may produce a small amount of acidic substances during the fermentation process, especially if the fermentation conditions cause microbial activity to produce lactic acid or other organic acids. Therefore, the second auxiliary formula raw materials in the present invention include garlic, young ginger, celery, crucian carp, fresh Erjingtiao, and fresh millet pepper.

[0050] The production parameters (fermentation temperature and fermentation humidity) of the production line can be preset. At this time, the constructed deep analysis model is used to deeply process the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity. When the fermentation conditions of the production line, i.e., the fermentation temperature and the fermentation humidity, are known, the deep analysis model analyzes the correspondence between the actual spiciness of the produced fish-flavored chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, i.e., the spiciness correlation relationship, and the correspondence between the actual acidity of the produced fish-flavored chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material, i.e., the acidity correlation relationship. The trained deep analysis model stores multiple sets of spiciness correlation relationships and acidity correlation relationships. This step of the deep analysis model is actually to screen out matching spiciness correlation relationships and acidity correlation relationships.

[0051] Since the target spiciness and target acidity are also known in advance, the first ratio of the first main formula raw material and the first auxiliary formula raw material that affect the spiciness can be determined based on the above target spiciness and the correlation between spiciness, and the second ratio of the second main formula raw material and the second auxiliary formula raw material that affect the acidity can be determined according to the correlation between the target acidity and the acidity. According to the first ratio and the second ratio, the amount of each raw material in the formula is determined, and then the determined raw materials are pre-treated (including cleaning, evisceration, cutting, mincing, etc.), pickled, and fermented (regularly open the pot to check the fermentation of the materials, check the fermentation of the materials, check whether there is mildew, rancidity, etc.; after the inspection is qualified, use a stirring rod to stir the materials in the pot again to make them uniform), and the actual spiciness and actual acidity of the fish flavor chili sauce produced are closest to the expected target spiciness and target acidity, so that the number of artificial later adjustments can be reduced, which can not only reduce the production cost of the fish flavor chili sauce manufacturer, but also can keep the natural flavor of the fish flavor chili sauce as much as possible.

[0052] The following table is the formula and raw material ratio determined under a certain set of fermentation temperature and fermentation humidity conditions using the above scheme of the present invention.

[0053] Raw material name Weight (kg) Raw material name Weight (kg) Fresh Vitex truncatula 100 Young Ginger 8 Fresh chili 10 celery 3.5 Red peppercorns 0.2 Salt 22 star anise 0.3 Crucian carp 12 Shannai 0.2 Liquor 5 Fresh green peppercorns 1 Laozao 2.6 Patchouli 1.2 Rapeseed Oil 15 garlic 5

[0054] In some embodiments, the method further comprises:

[0055] Acquire several pieces of real production data of fish-flavored chili sauce, each piece of the real production data comprising: a ratio of a third main formula raw material and a third auxiliary formula raw material affecting spiciness, a ratio of a fourth main formula raw material and a fourth auxiliary formula raw material affecting acidity, fermentation parameters, a first actual spiciness, and a first actual acidity; wherein the fermentation parameters comprise a second fermentation temperature and a second fermentation humidity;

[0056] A training data set is formed according to the real production data, and the deep analysis model is trained using the training data in the training data set until a training termination condition is reached.

[0057] In this embodiment, the deep analysis model of the present invention needs to be trained sufficiently in advance before the spiciness correlation and acidity correlation corresponding to various fermentation parameters can be established therein. Subsequently, based on the spiciness correlation and acidity correlation, the first ratio of the first main formula raw material and the first auxiliary formula raw material affecting the spiciness and the second ratio of the second main formula raw material and the second auxiliary formula raw material affecting the acidity can be accurately determined.

[0058] The present invention is mainly based on the real production data of fish flavor chili sauce, that is, collecting multiple (no less than 500) production data of the chili sauce production line, wherein the production data includes formula data, that is, the third main formula raw material and the third auxiliary formula raw material that affect the spiciness, the fourth main formula raw material and the fourth auxiliary formula raw material that affect the acidity, and the fermentation parameters actually taken, such as the fermentation temperature and the fermentation humidity, and the actually measured first actual spiciness and the first actual acidity.

[0059] The format of the training data formed by the real production data can be: spiciness formula matrix, acidity formula matrix, fermentation parameter matrix, spiciness-acidity matrix. The spiciness formula matrix is ​​[the ratio of the third main formula raw material, the ratio of the third auxiliary formula raw material], and the acidity formula matrix is ​​[the ratio of the fourth main formula raw material, the ratio of the fourth auxiliary formula raw material]. The ratio of the formula raw materials that affect the spiciness and acidity after the above matrix processing and the fermentation parameters are associated with the corresponding spiciness-acidity matrix to characterize the actual spiciness (predicted value) and actual acidity (predicted value) of the fish-flavored chili sauce produced by the corresponding ratio of the formula raw materials that affect the spiciness and acidity under the set fermentation parameters. After sufficient training, the deep analysis model establishes multiple groups of spiciness correlation relationships and acidity correlation relationships corresponding to different formula ratios and different fermentation parameters.

[0060] In some embodiments, forming a training data set according to the real production data includes:

[0061] Forming a first set of training data according to the real production data;

[0062] Regulating a third ratio of the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, and the second auxiliary formula raw material in the formula, and regulating the fermentation parameters, arranging and combining the third ratio and the fermentation parameters to obtain simulation input data, inputting the simulation input data into simulation software, and simulating to obtain simulation output data, wherein the simulation output data includes a second actual spiciness and a second actual acidity;

[0063] A second set of training data is constructed based on the simulation input data and the simulation output data, and the training data set is obtained by fusing the first set of training data and the second set of training data.

[0064] In this embodiment, the training data in the present invention includes real production data and simulation data. The collected pieces of real production data of fish flavor chili sauce are sorted according to the aforementioned data format to obtain a first set of training data.

[0065] At the same time, the third ratio of the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, and the second auxiliary formula raw material in the above formula is regulated, and the fermentation temperature and fermentation humidity in the fermentation parameters are regulated, and then the third ratio and the fermentation parameters are arranged and combined, so as to obtain formulas with different ratios and different fermentation parameters, which are input as simulation input data into simulation software such as COMSOL Multiphysics or Pensim for simulation processing. The above simulation software can simulate the physical and chemical reactions in the fermentation process, so as to obtain the simulation prediction values ​​of the characteristics of the fish-flavored chili sauce including acidity and spiciness. The simulation software outputs the corresponding second actual spiciness and second actual acidity based on the simulation input data as simulation output data. The simulation input data and the simulation output data are constructed according to the above data format to obtain the second set of training data. The first set of training data and the second set of training data are then fused to obtain the final training data set.

[0066] The present invention uses a combination of real data and simulated data to construct a training data set, wherein the real data actually contains a lot of distorted data, that is, the spiciness and acidity of the produced fish-flavored chili sauce have a certain degree of deviation from the expected spiciness and acidity; while the simulated data is ideal data, which is difficult to achieve in real production. By combining the real and the virtual training data, the deep analysis model trained by the present invention can establish a spiciness correlation relationship and an acidity correlation relationship that are more in line with the actual production situation.

[0067] In some embodiments, the obtaining the training data set by fusing the first set of training data and the second set of training data includes:

[0068] The real production data also includes data on the number of manual adjustments, and the average number of manual adjustments is calculated based on the data on the number of manual adjustments;

[0069] Calculate a first proportion of the first group of training data according to the average number of manual controls and a corresponding negative correlation function, and determine a second proportion of the second group of training data according to the first proportion;

[0070] Determine a first data amount in the first set of training data and a second data amount in the second set of training data according to a preset amount of training data and the first proportion and the second proportion;

[0071] The training data set is composed of training data of the first data volume randomly selected from the first group of training data and training data of the second data volume randomly selected from the second group of training data.

[0072] In this embodiment, the amount of data in the training data set is preset, for example, 800. At this time, it is necessary to determine the amount of data selected from the first set of training data and the second set of training data. The above-mentioned real production data obtained also includes the record data of the number of manual adjustments. After the fish flavor chili sauce is produced, the staff will use the test equipment to measure the spiciness and acidity of the batch of fish flavor chili sauce. When the spiciness and acidity are greatly deviated from the expected values, it is necessary to fine-tune by manual adjustment. The fine-tuning may require multiple times, and there are also multiple corresponding records. The average number of manual adjustments is calculated based on the record data of the number of manual adjustments in each real production data. The larger the average number of manual adjustments, the more difficult it is to grasp the fermentation process in the actual production process (the larger the deviation, the more times of adjustment are required), resulting in the inevitable deviation between the spiciness and acidity of the fish flavor chili sauce produced and the expected values. At this time, the proportion of the first set of training data can be appropriately lowered and the proportion of the second set of training data can be increased. That is, by using more second set of training data that is more in line with the theoretical value to train the deep analysis model, it is conducive to improving the deep analysis model to analyze more reasonable spiciness correlation and acidity correlation. The sum of the first proportion and the second proportion is 1.

[0073] Among them, the first proportion and the average number of manual adjustments are in a negative correlation. When the average number of manual adjustments increases, the first proportion should decrease, that is, the amount of data from the first group of training data in the training data set should be reduced; when the average number of manual adjustments decreases, the first proportion should increase, that is, the amount of data from the first group of training data in the training data set should be increased.

[0074] In some embodiments, the negative correlation function is expressed as follows:

[0075] ;

[0076] In the formula, Perc1 represents the first proportion, Perc is the basic value of the first proportion, n is the average number of manual controls, n1 is the median value of the number of manual controls in each of the control number record data, and n2 is the maximum value of the number of manual controls in each of the control number record data.

[0077] In this embodiment, the first proportion and the average number of manual controls conform to the aforementioned negative correlation function relationship, which is implemented by the above negative correlation function. In the above formula, the present invention further considers the median and maximum values ​​of the number of manual controls in each control number record data, and decides the degree of expansion of the basic value Perc based on the ratio of the difference between the average value and the median value, and the average value and the maximum value. The settings can be Maintain it within a reasonable range so that the first proportion is not too large.

[0078] In some embodiments, the deep analysis model is constructed based on a convolutional neural network or a generative adversarial network.

[0079] In this embodiment, the deep analysis model in the present invention is preferably constructed based on a convolutional neural network (CNN) or a generative adversarial network (GANs). The model building process belongs to the mature existing technology and will not be repeated here.

[0080] See also Figure 2 , the embodiment of the present invention discloses a production control system of fish flavor chili sauce, including a receiving module, a first processing module, a second processing module, a third processing module, and a control module;

[0081] The receiving module is used to receive the formula, target spiciness and target acidity of the fish-flavored chili sauce; wherein the formula includes fresh er jing tiao, fresh chili pepper, red pepper, star anise, galangal, fresh green peppercorns, patchouli, garlic, young ginger, celery, salt, crucian carp, white wine, fermented glutinous rice and rapeseed oil;

[0082] The first processing module is used to analyze and process the formula to obtain a first main formula raw material and a first auxiliary formula raw material that affect the spiciness, and a second main formula raw material and a second auxiliary formula raw material that affect the acidity;

[0083] The second processing module is used to use the deep analysis model to perform deep processing on the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity to obtain a spiciness correlation relationship and an acidity correlation relationship; wherein the spiciness correlation relationship is used to indicate the correspondence between the actual spiciness of the produced fish flavor chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, and the acidity correlation relationship is used to indicate the correspondence between the actual acidity of the produced fish flavor chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material; the first fermentation temperature and the first fermentation humidity are preset;

[0084] The third processing module is used to determine a first ratio of the first main formula raw material and the first auxiliary formula raw material that affects the spiciness based on the target spiciness and the spiciness correlation relationship, and to determine a second ratio of the second main formula raw material and the second auxiliary formula raw material that affects the acidity based on the target acidity and the acidity correlation relationship;

[0085] The control module is used to regulate the amount of the formula raw materials according to the first ratio and the second ratio, and to pretreat, marinate and ferment the formula raw materials in sequence to produce a fish flavor chili sauce that meets the target spiciness and the target acidity.

[0086] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method as described in any of the preceding items.

[0087] The processor may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0088] The memory may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media\other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0089] The memory is used to store the computer program for executing the embodiment of the present application, and the execution is controlled by the processor. The processor is used to execute the computer program stored in the memory to implement the steps shown in the above method embodiment.

[0090] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any of the above items is executed.

[0091] An embodiment of the present invention further discloses a computer program product, which includes a computer program. When the computer program is executed by a processor of an electronic device, the method described in any of the preceding items is implemented.

[0092] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0093] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0094] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A production control method for fish flavor chili sauce, characterized in that: The steps include: Receive a formula, target spiciness, and target acidity of a fish-flavored chili sauce; wherein the formula includes fresh erjingtiao, fresh chili pepper, red pepper, star anise, galangal, fresh green peppercorns, patchouli, garlic, young ginger, celery, salt, crucian carp, white wine, fermented glutinous rice, and rapeseed oil; Analyze and process the formula to obtain a first main formula raw material and a first auxiliary formula raw material that affect the spiciness, and a second main formula raw material and a second auxiliary formula raw material that affect the acidity; The first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity are deeply processed using a deep analysis model to obtain a spiciness correlation relationship and an acidity correlation relationship; wherein the spiciness correlation relationship is used to indicate the correspondence between the actual spiciness of the produced fish-flavored chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, and the acidity correlation relationship is used to indicate the correspondence between the actual acidity of the produced fish-flavored chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material; the first fermentation temperature and the first fermentation humidity are preset; Determine a first ratio of the first main formula raw material and the first auxiliary formula raw material that affects the spiciness based on the target spiciness and the spiciness correlation relationship, and determine a second ratio of the second main formula raw material and the second auxiliary formula raw material that affects the acidity based on the target acidity and the acidity correlation relationship; The amount of the formula raw materials is regulated according to the first ratio and the second ratio, and the formula raw materials are pretreated, pickled, and fermented in sequence to produce a fish-flavored chili sauce that meets the target spiciness and the target acidity; The method further comprises: Acquire several pieces of real production data of fish-flavored chili sauce, each piece of the real production data comprising: a ratio of a third main formula raw material and a third auxiliary formula raw material affecting spiciness, a ratio of a fourth main formula raw material and a fourth auxiliary formula raw material affecting acidity, fermentation parameters, a first actual spiciness, and a first actual acidity; wherein the fermentation parameters comprise a second fermentation temperature and a second fermentation humidity; Constructing a training data set according to the real production data, and training the deep analysis model using the training data in the training data set until a training termination condition is reached; The forming of a training data set according to the real production data comprises: Forming a first set of training data according to the real production data; Regulating a third ratio of the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, and the second auxiliary formula raw material in the formula, and regulating the fermentation parameters, arranging and combining the third ratio and the fermentation parameters to obtain simulation input data, inputting the simulation input data into simulation software, and simulating to obtain simulation output data, wherein the simulation output data includes a second actual spiciness and a second actual acidity; Constructing a second set of training data according to the simulation input data and the simulation output data, and obtaining the training data set by fusing the first set of training data and the second set of training data; The step of obtaining the training data set by fusing the first set of training data and the second set of training data comprises: The real production data also includes data on the number of manual adjustments, and the average number of manual adjustments is calculated based on the data on the number of manual adjustments; Calculate a first proportion of the first group of training data according to the average number of manual controls and a corresponding negative correlation function, and determine a second proportion of the second group of training data according to the first proportion; Determine a first data amount in the first set of training data and a second data amount in the second set of training data according to a preset amount of training data and the first proportion and the second proportion; The training data set is composed of training data of the first data volume randomly selected from the first group of training data and training data of the second data volume randomly selected from the second group of training data.

2. The production control method of a fish flavor chili sauce according to claim 1, characterized in that: The expression of the negative correlation function is as follows: ; In the formula, Perc1 represents the first proportion, Perc is the basic value of the first proportion, n is the average number of manual controls, n1 is the median value of the number of manual controls in each of the control number record data, and n2 is the maximum value of the number of manual controls in each of the control number record data.

3. The production control method of a fish flavor chili sauce according to claim 1, characterized in that: The deep analysis model is constructed based on a convolutional neural network or a generative adversarial network.

4. A production control system based on the production control method of claim 1, comprising a receiving module, a first processing module, a second processing module, a third processing module, and a control module; characterized in that: The receiving module is used to receive the formula, target spiciness and target acidity of the fish-flavored chili sauce; wherein the formula includes fresh er jing tiao, fresh chili pepper, red pepper, star anise, galangal, fresh green peppercorns, patchouli, garlic, young ginger, celery, salt, crucian carp, white wine, fermented glutinous rice and rapeseed oil; The first processing module is used to analyze and process the formula to obtain a first main formula raw material and a first auxiliary formula raw material that affect the spiciness, and a second main formula raw material and a second auxiliary formula raw material that affect the acidity; The second processing module is used to use the deep analysis model to perform deep processing on the first main formula raw material, the first auxiliary formula raw material, the second main formula raw material, the second auxiliary formula raw material, the first fermentation temperature and the first fermentation humidity to obtain a spiciness correlation relationship and an acidity correlation relationship; wherein the spiciness correlation relationship is used to indicate the correspondence between the actual spiciness of the produced fish flavor chili sauce and the ratio of the first main formula raw material and the first auxiliary formula raw material, and the acidity correlation relationship is used to indicate the correspondence between the actual acidity of the produced fish flavor chili sauce and the ratio of the second main formula raw material and the second auxiliary formula raw material; the first fermentation temperature and the first fermentation humidity are preset; The third processing module is used to determine a first ratio of the first main formula raw material and the first auxiliary formula raw material that affects the spiciness based on the target spiciness and the spiciness correlation relationship, and to determine a second ratio of the second main formula raw material and the second auxiliary formula raw material that affects the acidity based on the target acidity and the acidity correlation relationship; The control module is used to regulate the amount of the formula raw materials according to the first ratio and the second ratio, and to pretreat, marinate and ferment the formula raw materials in sequence to produce a fish flavor chili sauce that meets the target spiciness and the target acidity.

Citation Information

Patent Citations

  • Fish-flavored chili sauce and preparation method thereof

    CN109363136A

  • Explosive safety prediction method based on digital twinborn model

    CN117610278A

  • Food taste adjusting method and device and cooking equipment

    CN118303763A