A food processing control method and system based on big data processing

Abstract

The present invention provides a food processing control method and system based on big data processing, which relate to the technical field of food processing. The method comprises: based on an infrared video of food processing, using a variational autoencoder to generate a subsequent simulated infrared video of food processing; based on the subsequent simulated infrared video of food processing, using an information determination model to determine a simulated infrared video of a high temperature area and a simulated infrared video of each low temperature area; based on the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme. The method can quickly and accurately determine the target heating scheme for food processing.

Description

Technical Field

[0001] The present invention relates to the technical field of food processing control, and in particular to a food processing control method and system based on big data processing. Background Art

[0002] In the food processing industry, precise control of the heating process is key to ensuring food quality and safety. Traditional heating control methods usually rely on fixed heating time and temperature settings, lacking real-time monitoring and dynamic adjustment of temperature distribution during food processing. This fixed heating strategy is difficult to cope with the differences in different food ingredients and processing environments, and can easily lead to uneven food heating, affecting the taste and nutritional value of the food. In most cases, the heating process requires operators to monitor in real time and manually adjust the heating parameters according to actual conditions. This is not only time-consuming and labor-intensive, but also easily affected by personal experience and skill level.

[0003] Therefore, how to accurately control the temperature during food processing is an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present invention is how to accurately control the temperature during food processing.

[0005] According to a first aspect, the present invention provides a food processing control method based on big data processing, comprising: obtaining a constant heating temperature of food and an infrared video of food being processed at the constant heating temperature; based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared video of subsequent food processing; based on the infrared video of the food being processed at the constant heating temperature, using an information determination model to determine a simulated infrared video of a high temperature area and a simulated infrared video of each low temperature area; based on the constant heating temperature of the food, the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and the similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme.

[0006] In a possible implementation, each of the multiple preliminary heating schemes includes high temperature heating time, high temperature heating temperature, medium temperature slow boiling time, medium temperature slow boiling temperature, low temperature insulation time, and low temperature insulation temperature.

[0007] In one possible implementation, the similarities between the multiple preliminary heating plans and different preliminary heating plans, and determining the target heating plan using a graph convolutional network include: constructing a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, each node representing a preliminary heating plan, and the node features of each node including a high temperature heating time, a high temperature heating temperature, a medium temperature slow boiling time, a medium temperature slow boiling temperature, a low temperature insulation time, a low temperature insulation temperature, a constant heating temperature of food, a high temperature area simulated infrared shooting video, and each low temperature area simulated infrared shooting video in a preliminary heating plan, and an edge between two nodes represents the similarity of the two preliminary heating plans; and processing the graph structure based on the graph convolutional network to determine the target heating plan.

[0008] In a possible implementation, the information determination model is a long-term and short-term neural network model. The input of the information determination model is the simulated infrared video of the subsequent food processing, and the output of the information determination model is the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area.

[0009] According to a second aspect, the present invention provides a food processing control system based on big data processing, comprising: an acquisition module for acquiring a constant heating temperature of a food and an infrared video of the food being processed at the constant heating temperature; a simulation generation module for generating a subsequent simulated infrared video of the food processing based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature using a variational autoencoder; an information determination module for determining a simulated infrared video of a high temperature area and a simulated infrared video of each low temperature area based on the infrared video of the food being processed at the constant heating temperature using an information determination model; a heating scheme generation module for generating multiple preliminary heating schemes and the similarities of different preliminary heating schemes based on the constant heating temperature of the food, the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area using a generative adversarial network; a target scheme determination module for determining a target heating scheme based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes using a graph convolutional network.

[0010] In a possible implementation, each of the multiple preliminary heating schemes includes high temperature heating time, high temperature heating temperature, medium temperature slow boiling time, medium temperature slow boiling temperature, low temperature insulation time, and low temperature insulation temperature.

[0011] In a possible implementation, the target scheme determination module is also used to: construct a graph structure, the graph structure includes multiple nodes and multiple edges between the multiple nodes, each node represents a preliminary heating scheme, and the node features of each node include high temperature heating time, high temperature heating temperature, medium temperature slow boiling time, medium temperature slow boiling temperature, low temperature insulation time, low temperature insulation temperature, food constant heating temperature, high temperature area simulated infrared shooting video, each low temperature area simulated infrared shooting video in a preliminary heating scheme, and the edge between two nodes represents the similarity of two preliminary heating schemes; the graph structure is processed based on a graph convolutional network to determine the target heating scheme.

[0012] In a possible implementation, the information determination model is a long-term and short-term neural network model. The input of the information determination model is the simulated infrared video of the subsequent food processing, and the output of the information determination model is the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area.

[0013] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method comprising: obtaining a constant heating temperature of a food and an infrared video of the food being processed at the constant heating temperature; based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared video of subsequent food processing; based on the infrared video of the food being processed at the constant heating temperature, using an information determination model to determine a simulated infrared video of a high temperature area and a simulated infrared video of each low temperature area; based on the constant heating temperature of the food, the simulated infrared video of the high temperature area, and the simulated infrared video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and the similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme.

[0014] According to the fourth aspect, the present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned food processing control method based on big data processing, the method comprising: obtaining a constant heating temperature of the food and an infrared shot video of the food being processed at the constant heating temperature; based on the constant heating temperature of the food and the infrared shot video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared shot video of subsequent food processing; based on the infrared shot video of the food being processed at the constant heating temperature, using an information determination model to determine a simulated infrared shot video of a high temperature area and a simulated infrared shot video of each low temperature area; based on the constant heating temperature of the food, the simulated infrared shot video of the high temperature area, and the simulated infrared shot video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and the similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme.

[0015] The present invention provides a food processing control method and system based on big data processing, the method comprising obtaining a constant heating temperature of a food and an infrared video of the food being processed at the constant heating temperature; based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared video of subsequent food processing; based on the infrared video of the food being processed at the constant heating temperature, using an information determination model to determine a simulated infrared video of a high temperature area and a simulated infrared video of each low temperature area; based on the constant heating temperature of the food, the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme, the method can accurately control the temperature during food processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an application scenario of a food processing control method based on big data processing provided by an embodiment of the present invention;

[0017] Figure 2 A schematic flow chart of a food processing control method based on big data processing provided by an embodiment of the present invention;

[0018] Figure 3 A schematic diagram of a process for determining a target heating scheme provided by an embodiment of the present invention;

[0019] Figure 4 A schematic diagram of a food processing control system based on big data processing provided by an embodiment of the present invention;

[0020] Figure 5 A schematic diagram of an electronic device provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0021] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0022] Figure 1 A schematic diagram of an application scenario of a food processing control method based on big data processing provided in an embodiment of the present invention. Figure 1 The application scenario of the food processing control method based on big data processing may include a server 11, a network 12, a terminal 13 and a storage device 14.

[0023] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 The food processing control method based on big data processing is shown in.

[0024] The network 12 may facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0025] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, and the like.

[0026] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of a food processing control method based on big data processing.

[0027] In an embodiment of the present invention, there is provided Figure 2A food processing control method based on big data processing is shown, and the food processing control method based on big data processing includes steps S1 to S5:

[0028] Step S1, obtaining a constant heating temperature of food and an infrared video of the food being processed at the constant heating temperature;

[0029] Constant heating temperature is a fixed heating temperature value set during the food processing process. Constant heating temperature is the basic parameter of the food heating process and is used to ensure that the food is evenly heated under specific processing conditions.

[0030] Infrared video is a video obtained by shooting the food processing process with an infrared camera. Food processing is carried out at a constant temperature.

[0031] The infrared camera can capture the temperature distribution of food during processing and generate infrared thermal imaging video. The infrared video of food processing can be captured by an infrared camera set on the video processing equipment. An infrared camera can be installed on the top or side of the food processing equipment, and the camera is started to record the process of food processing. The infrared video of food processing includes information such as food surface temperature distribution, heating uniformity, and temperature change trend.

[0032] As an example, infrared cameras are installed on food processing production lines to capture temperature changes during food processing in real time. Through analysis and processing, infrared video can determine the temperature change patterns at different stages of food processing, help analyze the heating and cooling process of the video, provide basic data for subsequent heating control, and ensure the accuracy and controllability of the heating process.

[0033] Step S2, based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared video of subsequent food processing;

[0034] The input of the variational autoencoder is the infrared video of the food processing and the constant heating temperature of the food, and the output of the variational autoencoder is the simulated infrared video of the subsequent food processing.

[0035] Infrared video is the core data source for generating subsequent simulated videos. Infrared video can comprehensively and intuitively record the temperature distribution and dynamic changes during food processing. The high-resolution temperature data captured by the infrared camera covers the entire surface of the food, which can accurately reflect the heating uniformity and local temperature anomalies, providing an important basis for optimizing food processing technology, and can provide rich training samples for the variational autoencoder (VAE) to generate simulated infrared video of subsequent food processing. The variational autoencoder calculates the temperature distribution in subsequent processing by analyzing historical infrared videos, thereby generating high-precision simulated infrared video of subsequent food processing.

[0036] Variational Autoencoder (VAE) is a generative model that combines deep learning and probabilistic graphical models. The variational autoencoder contains a latent space, which is mainly composed of an encoder and a decoder. The encoder maps the input data infrared video to a latent space and extracts the latent features of the data, such as temperature distribution, heating trend, food shape change, etc. The decoder samples from the latent space and reconstructs the latent features into new data, namely the simulated infrared video.

[0037] The simulated infrared video generated by the variational autoencoder (VAE) can learn and generate videos with similar temperature distribution characteristics based on real infrared data, which can accurately reflect the temperature changes during food processing and be used to predict the temperature distribution changes of food during subsequent heating. The simulated infrared video retains the key temperature features of the real infrared video, such as the distribution of high-temperature and low-temperature areas. The high-temperature area usually corresponds to the concentrated heating part, while the low-temperature area may be an area with insufficient heating or fast heat dissipation. The information determination model can accurately divide the simulated infrared video into high-temperature areas and low-temperature areas by analyzing the simulated infrared video, providing a reliable basis for temperature monitoring and optimization of the food processing process.

[0038] Step S3, based on the infrared video of the food being processed at a constant heating temperature, using an information determination model to determine a high temperature area simulated infrared video and each low temperature area simulated infrared video;

[0039] The information determination model is a long-term and short-term neural network model. The input of the information determination model is the simulated infrared video of the subsequent food processing, and the output of the information determination model is the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area.

[0040] The LSTN model is a special type of recurrent neural network (RNN) designed specifically for processing time series data. By introducing memory units and gating mechanisms (input gate, forget gate, and output gate), the LSTN model can effectively capture long-term dependencies in time series data, which makes the LSTN model perform well in processing data with temporal continuity, such as video, voice, sensor data, etc.

[0041] In some embodiments, the information determination model includes a temperature point recognition layer, a region division layer, and a video generation layer. The input of the temperature point recognition layer is an infrared video of food processed at a constant heating temperature, and the output of the temperature point recognition layer is a high temperature point, a plurality of low temperature points, a temperature change trend sequence, and a regional temperature distribution map. The input of the regional division layer is a high temperature point, a plurality of low temperature points, and a temperature change trend sequence, and the output of the regional division layer is a high temperature region outline, a plurality of low temperature region outlines, and a temperature abnormal region mark. The input of the video generation layer is a regional temperature distribution map, a high temperature region outline, a plurality of low temperature region outlines, and a temperature abnormal region mark, and the output of the video generation layer is a high temperature region simulated infrared shooting video and each low temperature region simulated infrared shooting video.

[0042] The temperature point recognition layer is responsible for extracting key temperature point information from the infrared video. The temperature point information includes coordinates, temperature values, and the average temperature of the neighborhood of each point and the timestamp. Identify areas with higher and lower temperatures on the food surface, and generate temperature change trend sequences and regional temperature distribution maps. The regional division layer further divides the contours of high-temperature and low-temperature areas, and marks areas with abnormal temperatures. The video generation layer generates simulated infrared videos of high-temperature and low-temperature areas based on the output of the regional division layer. By dividing the information determination model into multiple levels, the temperature information in the infrared video can be gradually refined, improving the accuracy of the model and the interpretability of the system, thereby improving processing efficiency.

[0043] The high temperature area simulated infrared shooting video and each low temperature area simulated infrared shooting video are predicted video clips generated from the original infrared shooting video through the information determination model. The simulated video shows the temperature change trend of the high temperature area and the low temperature area of ​​the food during the heating process, helping to accurately identify the heating status of each area, ensuring that the food is heated evenly, and improving the control accuracy and effect of the heating process.

[0044] Step S4, based on the constant heating temperature of the food, the simulated infrared shooting video of the high temperature area, and the simulated infrared shooting video of each low temperature area, a generative adversarial network is used to generate multiple preliminary heating schemes and similarities between different preliminary heating schemes;

[0045] Each of the multiple preliminary heating schemes includes high temperature heating time, high temperature heating temperature, medium temperature slow boiling time, medium temperature slow boiling temperature, low temperature insulation time, and low temperature insulation temperature.

[0046] The simulated infrared video of the high temperature area reflects the area where heating is concentrated during food processing, which can help the generative adversarial network identify heating hotspots; the simulated infrared video of the low temperature area shows the area where heating is insufficient or heat dissipation is fast. The combination of the two can comprehensively extract the temperature distribution data during food processing, providing key data support for the generative adversarial network to generate heating solutions.

[0047] The Generative Adversarial Network (GAN) consists of two parts: a generator and a discriminator. The Generative Adversarial Network can generate multiple preliminary heating schemes and the similarity of each scheme through adversarial learning. The generator is responsible for generating data, and the discriminator judges the authenticity and similarity of the generated data. The two compete with each other for adversarial training. In some embodiments, the Generative Adversarial Network can generate multiple preliminary heating schemes based on simulated infrared shooting videos of high temperature areas and low temperature areas. The generator uses temperature distribution data to generate different heating schemes, and the discriminator evaluates the rationality and feasibility of these preliminary heating schemes. Through adversarial learning, the Generative Adversarial Network can generate a variety of heating schemes and calculate the similarity of each scheme to help select the optimal scheme.

[0048] Similarity is the degree of similarity between different heating schemes. Analyzing the similarity helps to identify heating schemes with similar effects, thus providing a basis for the subsequent selection of the optimal heating scheme, ensuring that the efficiency and consistency of the heating process are improved while meeting the heating needs. Similarity analysis can improve the overall reliability and adaptability of the system.

[0049] Step S5: Based on the multiple preliminary heating schemes and the similarities between different preliminary heating schemes, a target heating scheme is determined using a graph convolutional network.

[0050] In some embodiments, Figure 3 A schematic diagram of a process for determining a target heating scheme provided by an embodiment of the present invention, wherein determining the target heating scheme includes steps S21-S22:

[0051] Step S21, constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, each node representing a preliminary heating scheme, node features of each node comprising a high temperature heating time, a high temperature heating temperature, a medium temperature slow boiling time, a medium temperature slow boiling temperature, a low temperature insulation time, a low temperature insulation temperature, a high temperature area simulated infrared shooting video, and each low temperature area simulated infrared shooting video in a preliminary heating scheme, and an edge between two nodes represents the similarity of the two preliminary heating schemes;

[0052] A graph structure is a data structure consisting of nodes (vertices) and edges (edges) that is used to represent the relationship between nodes. Each node represents a preliminary heating plan, and the node features include the high temperature heating time, high temperature heating temperature, medium temperature slow boiling time, medium temperature slow boiling temperature, low temperature insulation time, low temperature insulation temperature, and simulated infrared video of high temperature area and low temperature area. These features provide the heating strategy and temperature distribution of each heating plan.

[0053] The edge between two nodes represents the similarity between two preliminary heating schemes. By constructing such a graph structure, the relationship between various heating schemes can be intuitively represented, and the node and edge features in the graph structure can be used for further analysis and optimization.

[0054] Step S22, processing the graph structure based on a graph convolutional network to determine a target heating scheme;

[0055] The graph structure provides a systematic way to represent and compare multiple preliminary heating schemes. The node features record the heating parameters and temperature distribution of each scheme; the edges can quantify the similarities between different schemes and help select the optimal heating scheme. This structured representation method provides strong support for the selection and optimization of heating schemes.

[0056] Graph convolutional network (GCN) is a neural network model specially designed for processing graph structure data, which can effectively capture the relationship between nodes and their neighbor nodes. In the graph structure, each node represents a preliminary heating plan. The node features include information such as heating time, temperature setting, and temperature zone distribution, and the edges represent the similarity between the plans. The graph convolutional network gradually updates the representation of the node by aggregating node features and neighbor node information, and finally captures local and global graph structure information. This feature enables the graph convolutional network to make full use of the similarity between heating plans. Without manually designing rules, the graph convolutional network can calculate the relationship between all heating plans and determine the optimal target heating plan.

[0057] Based on the same inventive concept, Figure 4 A schematic diagram of a food processing control system based on big data processing provided by an embodiment of the present invention, the food processing control system based on big data processing includes:

[0058] An acquisition module 41 is used to acquire a constant heating temperature of food and an infrared video of food being processed at the constant heating temperature;

[0059] A simulation generation module 42, configured to generate a simulated infrared video of subsequent food processing using a variational autoencoder based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature;

[0060] An information determination module 43 is used to determine, based on the infrared video of the food being processed at a constant heating temperature, a simulated infrared video of a high temperature area and a simulated infrared video of each low temperature area using an information determination model;

[0061] A heating scheme generating module 44 is used to generate a plurality of preliminary heating schemes and similarities of different preliminary heating schemes using a generative adversarial network based on the constant heating temperature of the food, the simulated infrared shooting video of the high temperature area, and the simulated infrared shooting video of each low temperature area;

[0062] The target scheme determination module 45 is used to determine the target heating scheme using a graph convolutional network based on the multiple preliminary heating schemes and the similarities between different preliminary heating schemes.

[0063] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, such as Figure 5 As shown, it includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and is configured to be executed by the processor 51 to implement the food processing control method based on big data processing as provided above, the method comprising: obtaining a constant heating temperature of the food and an infrared shooting video of the food being processed at the constant heating temperature; based on the constant heating temperature of the food and the infrared shooting video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared shooting video of subsequent food processing; based on the infrared shooting video of the food being processed at the constant heating temperature, using an information determination model to determine a simulated infrared shooting video of a high temperature area and a simulated infrared shooting video of each low temperature area; based on the constant heating temperature of the food, the simulated infrared shooting video of the high temperature area, and the simulated infrared shooting video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and the similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme.

[0064] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by the processor 51, implements the aforementioned food processing control method based on big data processing, the method comprising: obtaining a constant heating temperature of the food and an infrared shot video of the food being processed at the constant heating temperature; based on the constant heating temperature of the food and the infrared shot video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared shot video of subsequent food processing; based on the infrared shot video of the food being processed at the constant heating temperature, using an information determination model to determine a simulated infrared shot video of a high temperature area and a simulated infrared shot video of each low temperature area; based on the constant heating temperature of the food, the simulated infrared shot video of the high temperature area and the simulated infrared shot video of each low temperature area, using a generative adversarial network to generate multiple preliminary heating schemes and the similarities of different preliminary heating schemes; based on the multiple preliminary heating schemes and the similarities of different preliminary heating schemes, using a graph convolutional network to determine a target heating scheme.

[0065] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0066] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0067] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0068] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0069] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A food processing control method based on big data processing, characterized in that: include: Obtaining a constant heating temperature for food and infrared video of food being processed at a constant heating temperature. The infrared video includes information on food surface temperature distribution, heating uniformity, and temperature change trend; Based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature, using a variational autoencoder to generate a simulated infrared video of subsequent food processing; Based on the simulated infrared video of the subsequent food processing, the information determination model is used to determine the simulated infrared video of the high temperature area and the simulated infrared video of each low temperature area; Based on the constant heating temperature of the food, the simulated infrared shooting video of the high temperature area, and the simulated infrared shooting video of each low temperature area, a generative adversarial network is used to generate multiple preliminary heating schemes and similarities of different preliminary heating schemes, each of the multiple preliminary heating schemes including high temperature heating time, high temperature heating temperature, medium temperature slow boiling time, medium temperature slow boiling temperature, low temperature insulation time, and low temperature insulation temperature; Based on the similarities between the multiple preliminary heating schemes and different preliminary heating schemes, determining a target heating scheme using a graph convolutional network, wherein based on the similarities between the multiple preliminary heating schemes and different preliminary heating schemes, determining a target heating scheme using a graph convolutional network comprises: Constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, each node representing a preliminary heating scheme, node features of each node comprising a high temperature heating time, a high temperature heating temperature, a medium temperature slow boiling time, a medium temperature slow boiling temperature, a low temperature insulation time, a low temperature insulation temperature, a food constant heating temperature, a high temperature area simulated infrared shooting video, and each low temperature area simulated infrared shooting video in a preliminary heating scheme, and an edge between two nodes representing the similarity of the two preliminary heating schemes; The graph structure is processed based on a graph convolutional network to determine a target heating scheme.

2. The food processing control method based on big data processing according to claim 1, characterized in that: The information determination model is a long-short term neural network model, the input of the information determination model is the simulated infrared shooting video of the subsequent food processing, and the output of the information determination model is the simulated infrared shooting video of the high temperature area and the simulated infrared shooting video of each low temperature area.

3. A food processing control system based on big data processing, characterized in that: include: An acquisition module is used to acquire the constant heating temperature of food and infrared video of food being processed at the constant heating temperature. The infrared video includes information on food surface temperature distribution, heating uniformity, and temperature change trend. a simulation generation module, for generating a simulated infrared video of subsequent food processing using a variational autoencoder based on the constant heating temperature of the food and the infrared video of the food being processed at the constant heating temperature; An information determination module, for determining the simulated infrared shooting video of the high temperature area and each simulated infrared shooting video of the low temperature area using an information determination model based on the simulated infrared shooting video of the subsequent food processing; A heating scheme generating module, for generating a plurality of preliminary heating schemes and similarities of different preliminary heating schemes using a generative adversarial network based on the constant heating temperature of the food, the simulated infrared shooting video of the high temperature area, and the simulated infrared shooting video of each low temperature area, wherein each of the plurality of preliminary heating schemes includes a high temperature heating time, a high temperature heating temperature, a medium temperature slow boiling time, a medium temperature slow boiling temperature, a low temperature insulation time, and a low temperature insulation temperature; A target solution determination module is used to determine a target heating solution using a graph convolutional network based on the multiple preliminary heating solutions and similarities between different preliminary heating solutions. The target solution determination module is also used to: Constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, each node representing a preliminary heating scheme, node features of each node comprising a high temperature heating time, a high temperature heating temperature, a medium temperature slow boiling time, a medium temperature slow boiling temperature, a low temperature insulation time, a low temperature insulation temperature, a food constant heating temperature, a high temperature area simulated infrared shooting video, and each low temperature area simulated infrared shooting video in a preliminary heating scheme, and an edge between two nodes representing the similarity of the two preliminary heating schemes; The graph structure is processed based on a graph convolutional network to determine a target heating scheme.

4. The food processing control system based on big data processing as claimed in claim 3, characterized in that: The information determination model is a long-short term neural network model, the input of the information determination model is the simulated infrared shooting video of the subsequent food processing, and the output of the information determination model is the simulated infrared shooting video of the high temperature area and the simulated infrared shooting video of each low temperature area.

5. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the food processing control method based on big data processing as described in any one of claims 1 to 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the food processing control method based on big data processing as described in any one of claims 1 to 2 is implemented.

Images