A method and system for processing pre-prepared vegetables

Abstract

This invention provides a method and system for processing pre-prepared vegetables. The invention relates to the field of pre-prepared vegetable processing technology. The method includes: acquiring CT scan images of packaging bags at the initial injection speed of the pre-prepared vegetables to be filled; determining multiple test injection speeds for the pre-prepared vegetables using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed; controlling a filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds, and acquiring CT scan images of the packaging bags at each test injection speed; determining a preferred injection speed range for the pre-prepared vegetables using an interval determination model based on the CT scan images of the packaging bags at each test injection speed; determining a target injection speed for the pre-prepared vegetables based on the preferred injection speed range; and injecting the pre-prepared vegetables to be filled based on the target injection speed. This method can accurately determine a suitable pre-prepared vegetable filling speed.

Description

Technical Field

[0001] This invention relates to the field of pre-prepared food processing technology, specifically to a pre-prepared food processing method and system. Background Technology

[0002] Pre-prepared meals refer to dishes that have been pre-processed, treated, and packaged, offering convenience, speed, and ease of storage and transportation. In recent years, they have gained widespread attention and application globally. With the rapid growth in demand for pre-prepared meals, processing efficiency and product quality have become important research directions in the food processing industry. In the production process of pre-prepared meals, the filling stage is a crucial step, directly affecting packaging efficiency, packaging quality, and the final product quality. The filling speed is a vital parameter in this stage; excessively fast filling may lead to packaging bag breakage, uneven filling, or the formation of numerous air bubbles, while excessively slow filling will reduce production efficiency.

[0003] Therefore, accurately determining the appropriate filling speed for pre-prepared vegetables is an urgent problem to be solved. Summary of the Invention

[0004] The main technical problem this invention addresses is how to accurately determine the appropriate filling speed for pre-prepared vegetables.

[0005] According to a first aspect, the present invention provides a method for processing pre-prepared food, comprising: acquiring CT scan images of packaging bags at an initial injection speed of the pre-prepared food to be filled; determining multiple test injection speeds of the pre-prepared food using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed of the pre-prepared food to be filled; controlling a filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds of the pre-prepared food, and acquiring CT scan images of packaging bags at each test injection speed of the pre-prepared food; processing the CT scan images of packaging bags at each test injection speed of the pre-prepared food using an interval determination model to determine a preferred injection speed range for the pre-prepared food; determining a target injection speed for the pre-prepared food based on the preferred injection speed range of the pre-prepared food; and injecting the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0006] In one possible implementation, determining the target injection speed of the pre-prepared food based on the preferred injection speed range includes: Based on the CT scan images of the packaging bags at each pre-prepared food test injection speed and the preferred injection speed range of the pre-prepared food, a simulated image generation model is used to generate multiple simulated CT scan images of the packaging bags at multiple simulated injection speeds within the preferred injection speed range; A knowledge graph is constructed, which includes multiple nodes and multiple edges between the nodes. The multiple nodes include multiple simulated injection speed nodes. The node features of each simulated injection speed node include simulated CT scan images of packaging bags under each simulated injection speed. The edges between nodes represent the similarity of simulated CT scan images of packaging bags under different simulated injection speeds. The knowledge graph is processed using a graph convolutional network to determine the injection speed of the pre-prepared dish target.

[0007] In one possible implementation, the interval determination model is a Transformer model.

[0008] In one possible implementation, the speed determination model is a deep neural network model.

[0009] According to a second aspect, the present invention provides a pre-prepared food processing system, comprising: The acquisition module is used to acquire CT scan images of the packaging bag at the initial injection rate of the pre-prepared food to be filled; The test injection speed determination module is used to determine the test injection speed of multiple pre-prepared vegetables using a speed determination model based on the CT scan image of the packaging bag at the initial injection speed of the pre-prepared vegetables to be filled. The first control module is used to control the filling machine to fill multiple packaging bags sequentially based on the injection speed of the multiple pre-prepared food test, and to acquire CT scan images of the packaging bags at each pre-prepared food test injection speed; The interval determination module is used to determine the preferred injection speed interval for the pre-prepared food by processing the CT scan images of the packaging bags at each pre-prepared food test injection speed using the interval determination model. The target injection speed determination module is used to determine the target injection speed of the pre-prepared food based on the preferred injection speed range of the pre-prepared food. The second control module is used to inject the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0010] In one possible implementation, the target injection speed determination module is further configured to: Based on the CT scan images of the packaging bags at each pre-prepared food test injection speed and the preferred injection speed range of the pre-prepared food, a simulated image generation model is used to generate multiple simulated CT scan images of the packaging bags at multiple simulated injection speeds within the preferred injection speed range; A knowledge graph is constructed, which includes multiple nodes and multiple edges between the nodes. The multiple nodes include multiple simulated injection speed nodes. The node features of each simulated injection speed node include simulated CT scan images of packaging bags under each simulated injection speed. The edges between nodes represent the similarity of simulated CT scan images of packaging bags under different simulated injection speeds. The knowledge graph is processed using a graph convolutional network to determine the injection speed of the pre-prepared dish target.

[0011] In one possible implementation, the interval determination model is a Transformer model.

[0012] In one possible implementation, the speed determination model is a deep neural network model.

[0013] According to a third aspect, embodiments of the present invention provide an electronic device, including: 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: acquiring CT scan images of packaging bags at an initial injection speed of pre-prepared food to be filled; determining a plurality of test injection speeds for pre-prepared food using a speed determination model based on the CT scan images of packaging bags at the initial injection speed of pre-prepared food to be filled; controlling a filling machine to sequentially fill a plurality of packaging bags based on the plurality of test injection speeds for pre-prepared food, and acquiring CT scan images of packaging bags at each test injection speed for pre-prepared food; processing the CT scan images of packaging bags at each test injection speed for pre-prepared food using an interval determination model to determine a preferred injection speed range for pre-prepared food; determining a target injection speed for pre-prepared food based on the preferred injection speed range for pre-prepared food; and injecting pre-prepared food to be filled based on the target injection speed for pre-prepared food.

[0014] According to a fourth aspect, this embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned pre-prepared food processing method. The method includes: acquiring CT scan images of packaging bags at an initial injection speed of the pre-prepared food to be filled; determining multiple test injection speeds for the pre-prepared food using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed of the pre-prepared food to be filled; controlling a filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds of the pre-prepared food, and acquiring CT scan images of packaging bags at each test injection speed of the pre-prepared food; processing the CT scan images of the packaging bags at each test injection speed of the pre-prepared food using an interval determination model to determine a preferred injection speed range for the pre-prepared food; determining a target injection speed for the pre-prepared food based on the preferred injection speed range of the pre-prepared food; and injecting the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0015] This invention provides a method and system for processing pre-prepared vegetables. The method includes acquiring CT scan images of packaging bags at an initial injection speed of the pre-prepared vegetables to be filled; determining multiple test injection speeds for the pre-prepared vegetables using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed; controlling a filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds of the pre-prepared vegetables, and acquiring CT scan images of the packaging bags at each test injection speed; determining a preferred injection speed range for the pre-prepared vegetables using an interval determination model based on the CT scan images of the packaging bags at each test injection speed; determining a target injection speed for the pre-prepared vegetables based on the preferred injection speed range; and injecting the pre-prepared vegetables to be filled based on the target injection speed. This method can accurately determine a suitable filling speed for pre-prepared vegetables. Attached Figure Description

[0016] Figure 1 This is a schematic diagram illustrating an application scenario of a pre-prepared food processing method provided in an embodiment of the present invention; Figure 2 A schematic flowchart of a pre-prepared food processing method provided in an embodiment of the present invention; Figure 3 A schematic diagram of a process for determining the target injection speed of pre-prepared vegetables, provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of a pre-prepared food processing system provided in an embodiment of the present invention; Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of a pre-prepared food processing method provided in an embodiment of the present invention. Figure 1 The application scenarios for pre-prepared food processing methods can include servers 11, networks 12, terminals 13, and storage devices 14.

[0019] In some embodiments, server 11 may be a single server or a group of servers. Server 11 can access information and / or data stored in terminal 13 or storage device 14 via network 12. In some embodiments, server 11 may be used to perform... Figure 2 The pre-prepared food processing method shown in the figure.

[0020] Network 12 can facilitate the exchange of information and / or data. In some embodiments, network 12 can be any form of wired or wireless network, or any combination thereof.

[0021] 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 mobile devices, tablet computers, laptop computers, etc.

[0022] Storage device 14 can store data and / or instructions, for example, storage device 14 can store data instructions for pre-prepared food processing methods.

[0023] In this embodiment of the invention, the following are provided: Figure 2 The method for processing pre-prepared dishes, as shown, includes steps S1 to S6: Step S1: Obtain a CT scan image of the packaging bag at the initial injection speed of the pre-prepared food to be filled.

[0024] The initial injection speed is the speed at which the filling machine begins filling pre-prepared food, and it is usually set to a low reference value.

[0025] The CT scan image of the packaging bag at the initial injection speed of the pre-prepared food to be filled is a CT scan image of the packaging bag being filled with the pre-prepared food at the initial injection speed.

[0026] Step S2: Based on the CT scan image of the packaging bag at the initial injection speed of the pre-prepared food to be filled, a speed determination model is used to determine the test injection speed of multiple pre-prepared foods.

[0027] The velocity determination model is a deep neural network model. The input to the velocity determination model is a CT scan image of the packaging bag at the initial injection velocity of the pre-prepared food to be filled, and the output of the velocity determination model is the injection velocity of multiple pre-prepared foods for testing.

[0028] Deep neural network models include deep neural networks (DNNs). A deep neural network can include multiple processing layers, each consisting of multiple neurons, and each neuron performs matrix transformations on the data. Features from CT scan images of the packaging bag at the initial injection speed of the pre-prepared food to be filled are extracted using a deep neural network model. Through a multi-layered structure and activation functions, complex nonlinear relationships are captured, ultimately predicting the injection speed of multiple pre-prepared food samples.

[0029] By using a velocity determination model to predict multiple test injection velocities, multiple test injection velocities can be quickly selected during the experimental phase, improving experimental efficiency and reducing experimental costs.

[0030] In some embodiments, determining the test injection speed of multiple pre-prepared vegetables using a velocity determination model based on the CT scan images of the packaging bag at the initial injection speed of the pre-prepared vegetables to be filled includes steps S11 to S13: Step S11: Based on the CT scan image of the packaging bag at the initial injection speed of the pre-prepared food to be filled, determine the local wall thickness deviation matrix of the packaging bag and the compressive stress distribution map of the inner wall of the packaging bag.

[0031] In some embodiments, deep neural networks can be used to determine the local wall thickness deviation matrix of the packaging bag and the compressive stress distribution map of the inner wall of the packaging bag.

[0032] The local wall thickness deviation matrix of a packaging bag is a set of data representing the difference between the actual thickness of the packaging bag at various locations and the standard design thickness.

[0033] The stress distribution diagram of the inner wall of a packaging bag refers to the distribution diagram of the stress intensity and spatial distribution on the inner surface of the packaging bag under the initial injection impact.

[0034] The compressive stress distribution diagram of the inner wall of the packaging bag uses different color levels and contour lines to distinguish the magnitude of instantaneous pressure on different parts of the packaging bag. The compressive stress distribution diagram of the inner wall of the packaging bag can reflect the degree of stress balance of the bag structure in the initial injection state.

[0035] Deep neural networks can extract features and model CT scan images of pre-filled food packaging bags at their initial injection speed using multi-layer nonlinear transformations. The deep neural network can identify the microscopic deformation texture of the packaging bag's outline in the CT scan image at the initial injection speed. By combining the spatial relationships of pixels, the model can deduce the stress distribution field. Simultaneously, utilizing the mapping relationship between image grayscale and material density, the deep neural network can accurately locate microscopic fluctuations in wall thickness, thereby determining the local wall thickness deviation matrix and the compressive stress distribution map of the inner wall of the packaging bag.

[0036] Step S12: Based on the local wall thickness deviation matrix of the packaging bag and the compressive stress distribution map of the inner wall of the packaging bag, determine the local estimated rupture pressure threshold sequence of the packaging bag and the fatigue damage score of the packaging material.

[0037] In some embodiments, deep neural networks can be used to determine the local estimated burst pressure threshold sequence of the packaging bag and the fatigue damage score of the packaging material.

[0038] The local estimated burst pressure threshold sequence of a packaging bag is a set of values ​​arranged spatially to represent the maximum pressure limit that each local area of ​​the packaging bag can withstand.

[0039] Each value in the sequence of estimated local burst pressure thresholds for packaging bags represents the critical pressure point that can be tolerated at the corresponding coordinate point without physical rupture.

[0040] The fatigue damage score of packaging materials is a numerical indicator that quantifies the degree of structural strength loss of packaging bag materials under current pressure and accumulated past deformation.

[0041] The fatigue damage score of packaging materials can reflect the degree of embrittlement and fatigue resistance of the materials. The lower the fatigue damage score of the packaging materials, the better the structural integrity of the materials.

[0042] Deep neural networks possess powerful capabilities for multi-dimensional data fusion and state evolution inference. They can deeply couple and analyze the input local wall thickness deviation matrix of a packaging bag with the compressive stress distribution map of the bag's inner wall, simulating the failure process of the bag under complex stress conditions. By learning material damage logic, deep neural networks can determine the strength decay law of different thickness regions under specific stresses, thereby calculating the pressure bearing limit at each location and determining the local estimated rupture pressure threshold sequence and fatigue damage score of the packaging material.

[0043] Step S13: Determine multiple pre-prepared food test injection speeds based on the local estimated rupture pressure threshold sequence of the packaging bag and the fatigue damage score of the packaging material.

[0044] In some embodiments, a deep neural network can be used to determine the injection rate of multiple pre-prepared food tests.

[0045] Deep neural networks can use the locally estimated burst pressure threshold sequence of the packaging bag as a constraint and refer to the material toughness reflected by the fatigue damage score of the packaging material. Through extensive numerical simulations and strategy mapping within the safety boundary, deep neural networks can identify multiple dynamic equilibrium points that can overcome injection port resistance without triggering the local burst threshold. By globally scanning the pressure threshold distribution, deep neural networks can ensure that the selected values ​​cover different process ranges from conservative filling to extreme filling, ultimately determining multiple pre-prepared food test injection rates.

[0046] Step S3: Based on the multiple pre-prepared food test injection speed control filling machine, multiple packaging bags are sequentially filled, and CT scan images of the packaging bags at each pre-prepared food test injection speed are obtained.

[0047] Once multiple pre-prepared food test injection speeds are determined, the filling machine is controlled to sequentially fill multiple packaging bags based on these multiple pre-prepared food test injection speeds, and CT scan images of the packaging bags at each pre-prepared food test injection speed are obtained.

[0048] Step S4: Based on the CT scan images of the packaging bags at each pre-prepared food test injection speed, the preferred injection speed range for the pre-prepared food is determined using an interval determination model.

[0049] The interval determination model is a Transformer model. The input to the interval determination model is the CT scan image of the packaging bag at each pre-prepared food test injection speed, and the output is the optimal injection speed range for the pre-prepared food. The Transformer model is an implementation method of artificial intelligence.

[0050] The optimal injection speed range for pre-prepared dishes is a range selected from multiple tested injection speeds, within which the injection speed can achieve a better filling effect.

[0051] The Transformer model consists of an encoder and a decoder. The encoder learns representations from the input sequence, incorporating a self-attention mechanism and a feed-forward network. The decoder, building upon the encoder, introduces an additional multi-head attention mechanism to decode the encoder output and generate the target sequence. The Transformer model can process CT scan images of packaged bags at different injection speeds in pre-prepared food testing, better capturing the relationships within the sequences of these images.

[0052] In some embodiments, the interval determination model includes a packaging bag analysis layer, an optimal test injection speed determination layer, and an interval determination layer. Each of these layers comprises a Transformer structure. The input to the packaging bag analysis layer is a CT scan image of the packaging bag at each pre-prepared food test injection speed, and the output is the CT scan information of the packaging bag at each pre-prepared food test injection speed. The input to the optimal test injection speed determination layer is the CT scan information of the packaging bag at each pre-prepared food test injection speed, and the output is the optimal pre-prepared food test injection speed. The input to the interval determination layer is the CT scan information of the packaging bag at the optimal pre-prepared food test injection speed and the CT scan information of the packaging bag at each pre-prepared food test injection speed, and the output is the preferred injection speed interval for the pre-prepared food.

[0053] The CT scan information of the packaging bag at each pre-prepared food test injection rate includes the degree of rupture of the packaging bag, the density distribution of the pre-prepared food, and the degree of air bubbles in the pre-prepared food.

[0054] The greater the degree of tear in the packaging bag, the more serious the tear.

[0055] The density distribution information of pre-prepared food can be used to show the spatial distribution of pre-prepared food within the packaging bag. The density distribution information of pre-prepared food includes whether it is evenly distributed and whether there are local accumulations or gaps.

[0056] The greater the number of bubbles in the pre-cooked food, the more bubbles will be present after filling.

[0057] The packaging bag analysis layer extracts features from CT scan images, including the degree of rupture, density distribution, and the degree of air bubbles. The optimal test injection speed determination layer selects the optimal test injection speed for pre-prepared dishes based on these features. The interval determination layer integrates information from all speeds to determine the optimal injection speed range for pre-prepared dishes. This hierarchical structure, through layer-by-layer abstraction and transformation, better captures the complex relationships within the data. Each layer can process data in parallel, further improving computational speed.

[0058] Step S5: Determine the target injection speed of the pre-prepared food based on the preferred injection speed range of the pre-prepared food.

[0059] In some embodiments, Figure 3 This is a schematic flowchart illustrating a method for determining the target injection speed of pre-prepared vegetables according to an embodiment of the present invention. The determination of the target injection speed includes steps S21 to S23: Step S21: Based on the CT scan image of the packaging bag at each pre-prepared food test injection speed and the preferred injection speed range of the pre-prepared food, use a simulation image generation model to generate multiple simulated CT scan images of the packaging bag at multiple simulated injection speeds within the preferred injection speed range.

[0060] In some embodiments, the simulated image generation model includes a deep neural network model and a generative adversarial network (GAN). The input to the deep neural network model is the preferred injection speed range of the pre-prepared food and the CT scan image of the packaging bag at each tested injection speed of the pre-prepared food. The output of the deep neural network model is multiple simulated injection speeds within the preferred injection speed range. The input to the GAN is multiple simulated injection speeds within the preferred injection speed range and the CT scan image of the packaging bag at each tested injection speed of the pre-prepared food. The output of the GAN is multiple simulated CT scan images of the packaging bag at multiple simulated injection speeds within the preferred injection speed range.

[0061] Generative Adversarial Networks (GANs) consist of a generator and a discriminator. The generator and discriminator engage in a game-like interaction, continuously optimizing their performance to generate realistic data. Through training, GANs learn feature representations of data.

[0062] The generator's input includes a preferred injection rate range and CT scan images of the packaging bag at each test injection rate for the pre-prepared food. Based on the conditional input, the generator uses random noise to generate simulated images. The generator's goal is to produce simulated images that resemble the distribution of real CT scan images while conforming to the characteristics of the preferred injection rate range. The generator outputs simulated CT scan images of the packaging bag at multiple simulated injection rates within the preferred injection rate range. These simulated images reflect the distribution, fill density, and porosity of the pre-prepared food within the packaging bag at different injection rates.

[0063] Step S22: Construct a knowledge graph, which includes multiple nodes and multiple edges between the nodes. The multiple nodes include multiple simulated injection speed nodes. The node features of each simulated injection speed node include simulated CT scan images of packaging bags under each simulated injection speed. The edges between nodes represent the similarity of simulated CT scan images of packaging bags under different simulated injection speeds.

[0064] The knowledge graph consists of multiple nodes and multiple edges between them. The multiple nodes include multiple simulated injection velocity nodes. The node features of each simulated injection velocity node include simulated CT scan images of packaging bags under each simulated injection velocity. The edges between nodes represent the similarity of simulated CT scan images of packaging bags under different simulated injection velocities.

[0065] In some embodiments, the similarity between simulated CT scan images of packaging bags at different simulated injection velocities can be calculated using image similarity calculation methods. In some embodiments, image similarity calculation methods include convolutional neural network model methods, cosine similarity calculation methods, etc.

[0066] Step S23: Process the knowledge graph based on the graph convolutional network to determine the injection speed of the pre-made dish target.

[0067] In the knowledge graph, each node represents a simulated injection rate, and the node features include a simulated CT scan image of the packaging bag at each simulated injection rate. Each edge connecting two nodes represents the similarity between the simulated CT scan images of the packaging bag at the two simulated injection rates. Nodes and edges together constitute a knowledge graph representing the relationship between simulated injection rates and their corresponding simulated images.

[0068] The knowledge graph organizes simulated injection speeds and corresponding CT scan simulation image information into a graph structure, facilitating subsequent analysis and processing by the graph convolutional network. Through the relationships between nodes and edges, the knowledge graph can capture the correlation between simulated injection speeds and simulated images. By calculating the similarity of CT scan simulation images at different injection speeds, the knowledge graph can capture the similarities and differences between different speeds, enabling the graph convolutional network to extract global features and determine the target injection speed for the pre-prepared solution.

[0069] Graph Convolutional Network (GCN) is a deep learning model used to process graph-structured data. The input to the GCN is the knowledge graph, and the output is the pre-defined target injection speed.

[0070] Step S6: Inject the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0071] In some embodiments, the pre-prepared food injection device can be remotely controlled via mobile phone to inject the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0072] Based on the same inventive concept Figure 4 This is a schematic diagram of a pre-prepared food processing system provided in an embodiment of the present invention. The pre-prepared food processing system includes: The acquisition module 41 is used to acquire CT scan images of the packaging bag at the initial injection speed of the pre-prepared food to be filled; The test injection speed determination module 42 is used to determine the test injection speed of multiple pre-prepared vegetables using a speed determination model based on the CT scan image of the packaging bag under the initial injection speed of the pre-prepared vegetables to be filled. The first control module 43 is used to control the filling machine to fill multiple packaging bags sequentially based on the multiple pre-prepared food test injection speeds, and to acquire CT scan images of the packaging bags at each pre-prepared food test injection speed. The interval determination module 44 is used to determine the preferred injection speed interval for the pre-prepared food by processing the CT scan image of the packaging bag under the test injection speed of each pre-prepared food using the interval determination model. The target injection speed determination module 45 is used to determine the target injection speed of the pre-prepared food based on the preferred injection speed range of the pre-prepared food. The second control module 46 is used to inject the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0073] Based on the same inventive concept, embodiments of the present invention provide an electronic device, such as... Figure 5 As shown, it includes: The system includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and configured to be executed by the processor 51 to implement the pre-prepared food processing method provided above, the method comprising: acquiring CT scan images of packaging bags at an initial injection speed of the pre-prepared food to be filled; determining multiple test injection speeds of the pre-prepared food using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed of the pre-prepared food to be filled; controlling a filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds of the pre-prepared food, and acquiring CT scan images of packaging bags at each test injection speed of the pre-prepared food; processing the CT scan images of the packaging bags at each test injection speed of the pre-prepared food using an interval determination model to determine a preferred injection speed range for the pre-prepared food; determining a target injection speed for the pre-prepared food based on the preferred injection speed range of the pre-prepared food; and injecting the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0074] Based on the same inventive concept, this embodiment provides a computer-readable storage medium storing a computer program that, when executed by processor 51, implements the aforementioned pre-prepared food processing method. The method includes: acquiring CT scan images of packaging bags at an initial injection speed of the pre-prepared food to be filled; determining multiple test injection speeds for the pre-prepared food using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed of the pre-prepared food to be filled; controlling a filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds of the pre-prepared food, and acquiring CT scan images of packaging bags at each test injection speed of the pre-prepared food; processing the CT scan images of the packaging bags at each test injection speed of the pre-prepared food using an interval determination model to determine a preferred injection speed range for the pre-prepared food; determining a target injection speed for the pre-prepared food based on the preferred injection speed range of the pre-prepared food; and injecting the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0075] The pre-cooked food processing method provided in this application can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smartwatches, smart glasses, or smart helmets), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, and other electronic devices. This application does not impose any limitations on this.

[0076] Taking mobile phone 100 as an example of the aforementioned electronic devices, Figure 6 A structural schematic diagram of mobile phone 100 is shown.

[0077] like Figure 6 As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0078] The processing module 110 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0079] The processing module 110 can be used to: acquire CT scan images of packaging bags at the initial injection speed of the pre-prepared food to be filled; determine multiple test injection speeds of the pre-prepared food using a speed determination model based on the CT scan images of the packaging bags at the initial injection speed of the pre-prepared food to be filled; control the filling machine to sequentially fill multiple packaging bags based on the multiple test injection speeds of the pre-prepared food, and acquire CT scan images of packaging bags at each test injection speed of the pre-prepared food; process the CT scan images of packaging bags at each test injection speed of the pre-prepared food using an interval determination model to determine a preferred injection speed range for the pre-prepared food; determine a target injection speed for the pre-prepared food based on the preferred injection speed range of the pre-prepared food; and inject the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

[0080] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, 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 and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0081] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0082] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0083] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0084] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for processing pre-prepared dishes, characterized in that, include: Acquire CT scan images of the packaging bag at the initial injection velocity of the pre-prepared food to be filled; Based on the CT scan images of the packaging bags at the initial injection speed of the pre-prepared food to be filled, a speed determination model was used to determine the injection speed of multiple pre-prepared food test samples. The filling machine is controlled by the injection speed of the multiple pre-prepared food test to fill multiple packaging bags sequentially, and CT scan images of the packaging bags at each pre-prepared food test injection speed are obtained. Based on the CT scan images of the packaging bags at each pre-prepared food test injection speed, an interval determination model is used to process and determine the preferred injection speed range for the pre-prepared food. The target injection speed for pre-prepared vegetables is determined based on the preferred injection speed range. The pre-prepared food is injected based on the target injection speed.

2. The pre-prepared food processing method as described in claim 1, characterized in that, The step of determining the target injection speed of pre-prepared vegetables based on the preferred injection speed range includes: Based on the CT scan images of the packaging bags at each pre-prepared food test injection speed and the preferred injection speed range of the pre-prepared food, a simulated image generation model is used to generate multiple simulated CT scan images of the packaging bags at multiple simulated injection speeds within the preferred injection speed range; A knowledge graph is constructed, which includes multiple nodes and multiple edges between the nodes. The multiple nodes include multiple simulated injection speed nodes. The node features of each simulated injection speed node include simulated CT scan images of packaging bags under each simulated injection speed. The edges between nodes represent the similarity of simulated CT scan images of packaging bags under different simulated injection speeds. The knowledge graph is processed using a graph convolutional network to determine the injection speed of the pre-prepared dish target.

3. The pre-prepared food processing method as described in claim 1, characterized in that, The interval determination model is the Transformer model.

4. The pre-prepared food processing method as described in claim 1, characterized in that, The speed determination model is a deep neural network model.

5. A pre-prepared food processing system, characterized in that, include: The acquisition module is used to acquire CT scan images of the packaging bag at the initial injection rate of the pre-prepared food to be filled; The test injection speed determination module is used to determine the test injection speed of multiple pre-prepared vegetables using a speed determination model based on the CT scan image of the packaging bag at the initial injection speed of the pre-prepared vegetables to be filled. The first control module is used to control the filling machine to fill multiple packaging bags sequentially based on the injection speed of the multiple pre-prepared food test, and to acquire CT scan images of the packaging bags at each pre-prepared food test injection speed; The interval determination module is used to determine the preferred injection speed interval for the pre-prepared food by processing the CT scan images of the packaging bags at each pre-prepared food test injection speed using the interval determination model. The target injection speed determination module is used to determine the target injection speed of the pre-prepared food based on the preferred injection speed range of the pre-prepared food. The second control module is used to inject the pre-prepared food to be filled based on the target injection speed of the pre-prepared food.

6. The pre-prepared food processing system as described in claim 5, characterized in that, The target injection speed determination module is also used for: Based on the CT scan images of the packaging bags at each pre-prepared food test injection speed and the preferred injection speed range of the pre-prepared food, a simulated image generation model is used to generate multiple simulated CT scan images of the packaging bags at multiple simulated injection speeds within the preferred injection speed range; A knowledge graph is constructed, which includes multiple nodes and multiple edges between the nodes. The multiple nodes include multiple simulated injection speed nodes. The node features of each simulated injection speed node include simulated CT scan images of packaging bags under each simulated injection speed. The edges between nodes represent the similarity of simulated CT scan images of packaging bags under different simulated injection speeds. The knowledge graph is processed using a graph convolutional network to determine the injection speed of the pre-prepared dish target.

7. The pre-prepared food processing system as described in claim 5, characterized in that, The interval determination model is the Transformer model.

8. The pre-prepared food processing system as described in claim 5, characterized in that, The speed determination model is a deep neural network model.

9. An electronic device, characterized in that, include: processor; 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 pre-prepared food processing method as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the pre-prepared food processing method as described in any one of claims 1 to 4.

Images