A method, system, device, and medium for tea quality detection based on big data

Abstract

A method, system, device and medium for detecting the quality of tea based on big data provided by the present invention relate to the technical field of tea quality detection. The method obtains a captured image of tea; uses a variational autoencoder based on the captured image of the tea to generate tea images under different color illuminations and the similarity of tea images under different color illuminations; constructs a light map structure, which includes multiple tea nodes of different color illuminations and multiple edges between the tea nodes of different color illuminations. The node feature of each tea node of a color illumination includes the illumination image of the tea under this color illumination, and the feature of the edge between the tea nodes is the similarity of the tea images under different color illuminations; based on the first graph convolutional network, processes the light map structure to determine whether the tea quality detection is qualified. This method can quickly and accurately detect the quality of tea.

Description

Technical Field

[0001] The present invention relates to the technical field of tea quality detection, and in particular to a tea quality detection method, system, device and medium based on big data. Background Art

[0002] With the continuous expansion of the global tea market, consumers have higher and higher requirements for tea quality. Currently, the commonly used tea quality detection methods in the market mainly include sensory evaluation, laboratory analysis and instrument measurement. Sensory evaluation relies on the expert's experience judgment and is easily affected by personal preferences; although laboratory analysis is relatively accurate, it is complex and time-consuming to operate; while the existing instrument measurement equipment mostly focuses on the determination of basic components, and there is less research on the change of tea appearance color and its internal structure characteristics. These traditional methods have problems such as strong subjectivity, low efficiency and insufficient accuracy, and it is difficult to meet the requirements of tea quality standardization in modern industrial production and international trade.

[0003] Therefore, how to quickly and accurately detect the quality of tea is an urgent problem to be solved at present. Summary of the Invention

[0004] The main technical problem to be solved by the present invention is how to quickly and accurately detect the quality of tea.

[0005] According to a first aspect, the present invention provides a tea quality detection method based on big data, including: obtaining a captured image of tea; using a variational autoencoder based on the captured image of the tea to generate tea images under different color illuminations and similarities of the tea images under different color illuminations; constructing a light map structure, the light map structure includes a plurality of tea nodes under different color illuminations and a plurality of edges between the tea nodes under different color illuminations, the node feature of each tea node under a color illumination includes the light image of the tea under this color illumination, and the feature of the edge between the tea nodes is the similarity of the tea images under different color illuminations; processing the light map structure based on a first graph convolutional network to determine whether the tea quality detection is qualified.

[0006] In a possible implementation manner, the method further includes:

[0007] Determine multiple vibration frequencies of the tea leaves using a deep neural network model based on the captured images of the tea leaves; control a vibration device to vibrate based on the multiple vibration frequencies of the tea leaves, and obtain vibration videos of the tea leaves at each vibration frequency; determine the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies by processing the vibration videos of the tea leaves at each vibration frequency based on a frequency information determination model; construct a tea leaf vibration graph structure, where the tea leaf vibration graph structure includes multiple tea leaf nodes at different frequencies and multiple edges between the tea leaf nodes at different frequencies, the node feature of each tea leaf node at a frequency includes the vibration information of the tea leaves at each vibration frequency, and the feature of the edge between tea leaf nodes at different frequencies is the similarity of the vibration information of the tea leaves at different vibration frequencies; determine whether the tea leaf vibration detection is qualified by processing the tea leaf vibration graph structure based on a second graph convolutional network.

[0008] In a possible implementation, the frequency information determination model is a long short-term neural network model. The input of the frequency information determination model is the vibration videos of the tea leaves at each vibration frequency, and the output of the frequency information determination model is the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies. The vibration information of the tea leaves at each vibration frequency includes the average amplitude of the tea leaves and the amplitude of each tea leaf.

[0009] In a possible implementation, the input of the variational autoencoder is the captured image of the tea leaves, and the output of the variational autoencoder is the tea leaf images of the tea leaves under different color lights and the similarity of the tea leaf images under different color lights.

[0010] According to a second aspect, the present invention provides a tea leaf quality detection system based on big data, including:

[0011] An acquisition module for acquiring the captured images of the tea leaves;

[0012] A generation module for generating the tea leaf images of the tea leaves under different color lights and the similarity of the tea leaf images under different color lights using a variational autoencoder based on the captured images of the tea leaves;

[0013] A construction module for constructing a lighting graph structure, where the lighting graph structure includes multiple tea leaf nodes under different color lights and multiple edges between the multiple tea leaf nodes under different color lights. The node feature of each tea leaf node under a color light includes the lighting image of the tea leaves under this color light, and the feature of the edge between the tea leaf nodes is the similarity of the tea leaf images under different color lights;

[0014] A detection module for determining whether the tea leaf quality detection is qualified by processing the lighting graph structure based on a first graph convolutional network.

[0015] In a possible implementation, the system is further configured to:

[0016] Determine multiple vibration frequencies of the tea leaves using a deep neural network model based on the captured image of the tea leaves; control a vibration device to vibrate based on the multiple vibration frequencies of the tea leaves, and obtain vibration videos of the tea leaves at each vibration frequency; determine vibration information of the tea leaves at each vibration frequency and similarity of the vibration information of the tea leaves at different vibration frequencies by processing the vibration videos of the tea leaves at each vibration frequency based on a frequency information determination model; construct a tea leaf vibration graph structure, where the tea leaf vibration graph structure includes multiple tea leaf nodes at different frequencies and multiple edges between the tea leaf nodes at different frequencies, the node feature of each tea leaf node at a frequency includes the vibration information of the tea leaves at each vibration frequency, and the feature of the edge between the tea leaf nodes at different frequencies is the similarity of the vibration information of the tea leaves at different vibration frequencies; determine whether the tea leaf vibration detection is qualified by processing the tea leaf vibration graph structure based on a second graph convolutional network.

[0017] In a possible implementation, the frequency information determination model is a long short-term neural network model, the input of the frequency information determination model is the vibration video of the tea leaves at each vibration frequency, the output of the frequency information determination model is the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies, and the vibration information of the tea leaves at each vibration frequency includes the average amplitude of the tea leaves and the amplitude of each tea leaf.

[0018] In a possible implementation, the input of the variational autoencoder is the captured image of the tea leaves, and the output of the variational autoencoder is the tea leaf images of the tea leaves under different color lights and the similarity of the tea leaf images under different color lights.

[0019] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a processor; a 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 method as described above, and the method includes: obtaining a captured image of the tea leaves; generating tea leaf images of the tea leaves under different color lights and the similarity of the tea leaf images under different color lights using a variational autoencoder based on the captured image of the tea leaves; constructing a lighting graph structure, where the lighting graph structure includes multiple tea leaf nodes under different color lights and multiple edges between the multiple tea leaf nodes under different color lights, the node feature of each tea leaf node under a color light includes the lighting image of the tea leaves under this color light, and the feature of the edge between the tea leaf nodes is the similarity of the tea leaf images under different color lights; determining whether the tea leaf quality detection is qualified by processing the lighting graph structure based on a first graph convolutional network.

[0020] According to a fourth aspect, the present embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the aforementioned method for detecting the quality of tea based on big data. The method includes: acquiring a captured image of the tea; generating, based on the captured image of the tea, tea images under different color illuminations and the similarity of the tea images under different color illuminations using a variational autoencoder; constructing an illumination graph structure, where the illumination graph structure includes multiple tea nodes under different color illuminations and multiple edges between the tea nodes under different color illuminations. The node feature of each tea node under a color illumination includes the illumination image of the tea under this color illumination, and the feature of the edge between the tea nodes is the similarity of the tea images under different color illuminations; determining whether the tea quality detection is qualified by processing the illumination graph structure based on a first graph convolutional network.

[0021] A method and system for detecting the quality of tea based on big data provided by the present invention. The method includes acquiring a captured image of the tea; generating, based on the captured image of the tea, tea images under different color illuminations and the similarity of the tea images under different color illuminations using a variational autoencoder; constructing an illumination graph structure, where the illumination graph structure includes multiple tea nodes under different color illuminations and multiple edges between the tea nodes under different color illuminations. The node feature of each tea node under a color illumination includes the illumination image of the tea under this color illumination, and the feature of the edge between the tea nodes is the similarity of the tea images under different color illuminations; determining whether the tea quality detection is qualified by processing the illumination graph structure based on a first graph convolutional network. This method can quickly and accurately detect the quality of tea. Description of the Drawings

[0022] Figure 1 It is a schematic diagram of an application scenario of a method for detecting the quality of tea based on big data provided by an embodiment of the present invention;

[0023] Figure 2 It is a schematic flowchart of a method for detecting the quality of tea based on big data provided by an embodiment of the present invention;

[0024] Figure 3 It is a schematic flowchart of determining whether the tea vibration detection is qualified provided by an embodiment of the present invention;

[0025] Figure 4 It is a schematic diagram of a system for detecting the quality of tea based on big data provided by an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of an electronic device provided by an embodiment of the present invention;

[0027] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings through specific implementation manners. Similar elements in different implementation manners are labeled with related similar element numbers. In the following implementation manners, many detailed descriptions are provided to enable a better understanding of the present invention. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present invention are not shown or described in the specification to avoid the core part of the present invention being overwhelmed by excessive descriptions. 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 based on the descriptions in the specification and the general technical knowledge in the art.

[0029] Figure 2 It is a schematic diagram of the application scenario of a tea quality detection method based on big data provided by an embodiment of the present invention. Figure 2 The application scenario of the tea quality detection method based on big data can include a server 11, a network 12, a terminal 13, and a storage device 14.

[0030] In some embodiments, the server 11 can be a single server or a server group. The server 11 can access the information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 can be used to execute Figure 2 the tea quality detection method based on big data shown in

[0031] The network 12 can facilitate the exchange of information and / or data. In some embodiments, the network 12 can be any form of wired or wireless network, or any combination thereof.

[0032] The terminal 13 can refer to one or more terminal devices used by a user. In some embodiments, the terminal 13 can include one or more combinations of mobile devices, tablet computers, laptop computers, etc.

[0033] The storage device 14 can store data and / or instructions. For example, the storage device 14 can store the data instructions of the tea quality detection method based on big data.

[0034] In an embodiment of the present invention, there is provided a tea quality detection method based on big data as shown in Figure 1 The tea quality detection method based on big data includes steps S1 to S4:

[0035] Step S1, obtain a captured image of the tea.

[0036] The captured image of tea leaves refers to the two-dimensional visual representation of tea leaf samples captured by a camera or video recording device. The captured image of tea leaves is the basic data for subsequent processing.

[0037] Step S2: Based on the captured image of the tea leaves, use a variational autoencoder to generate tea leaf images under different color illuminations and the similarities of the tea leaf images under different color illuminations.

[0038] The input of the variational autoencoder is the captured image of the tea leaves, and the output of the variational autoencoder is the tea leaf images under different color illuminations and the similarities of the tea leaf images under different color illuminations.

[0039] A variational autoencoder (VAE) is a deep generative model. The variational autoencoder generates new samples by learning the probability distribution of the data and can perform a compressed representation of the input data.

[0040] Different illumination conditions can reveal the surface characteristics of tea leaves, while the similarity reflects the consistency of tea leaves under various illuminations, which is very important for evaluating the quality of tea leaves. The surface characteristics of tea leaves include glossiness, color change information, etc. By analyzing the images of tea leaves under different illumination conditions, the quality of tea leaves can be evaluated more comprehensively, and potential problems can be discovered.

[0041] The variational autoencoder encodes the input image into a low-dimensional representation in a latent space, then samples different points from this latent space, corresponding to different color illumination conditions. Finally, these sampled points are decoded to generate the corresponding tea leaf images under different colors of illumination. The variational autoencoder not only generates tea leaf images under different color illuminations but also calculates the similarities between these images.

[0042] Step S3: Construct an illumination graph structure, which includes multiple tea leaf nodes under different color illuminations and multiple edges between the tea leaf nodes under different color illuminations. The node feature of each tea leaf node under a color illumination includes the illumination image of the tea leaves under this color illumination, and the feature of the edge between the tea leaf nodes is the similarity of the tea leaf images under different color illuminations.

[0043] The illumination graph structure is a graph data structure, where the nodes represent the tea leaf images under specific illumination conditions, and the edges represent the relationships between the nodes (i.e., similarities). This structure can be used to capture the associations between tea leaf images under different illumination conditions.

[0044] As an example, if there are three different color illumination conditions (red light, blue light, green light), then the illumination graph structure will contain three nodes, and each node corresponds to the tea leaf image under one illumination condition. The edges between the nodes represent the similarities between these images.

[0045] As an example, the image of green tea under red light irradiation can be used as a tea leaf node, and the images of green tea under blue light and green light irradiation can also be used as the other two tea leaf nodes.

[0046] Step S4: Based on the first graph convolutional network, process the illumination graph structure to determine whether the tea leaf quality inspection is qualified.

[0047] The input of the first graph convolutional network is the illumination graph structure, and the output of the first graph convolutional network is that the tea leaf quality inspection is qualified or the tea leaf quality inspection is unqualified.

[0048] A graph convolutional network is a neural network specifically designed to process graph-structured data. It can perform feature extraction and classification tasks by aggregating information from neighboring nodes. In this step, the first graph convolutional network is used to analyze the illumination graph structure and determine the result of the tea leaf quality inspection.

[0049] The graph structure can effectively organize and express complex association relationships, facilitating subsequent comprehensive analysis using the graph convolutional network. By constructing the illumination graph structure, the performance of tea leaves under different illumination conditions and their interrelationships can be systematically displayed and analyzed, which helps to discover potential quality problems.

[0050] Lights of different colors can reveal different gloss characteristics on the surface of tea leaves. For example, certain types of tea leaves may exhibit higher reflectivity or glossiness under light of specific wavelengths, which may be a sign of high-quality tea. The color performance under different illumination conditions can help identify features such as the color uniformity and color depth of tea leaves, which are important factors in evaluating the appearance quality of tea. Some tea varieties may show different light transmittance under specific color illumination, which is related to the thickness and cell structure of the leaves. By analyzing these characteristics, the internal structure of the tea can be indirectly understood. Different color illuminations help observe the distribution of pigments in tea leaves, which is very important for judging the processing technology and preservation status of tea. Pigments include chlorophyll, thearubigins, etc. High-resolution images can more clearly show the texture characteristics on the surface of tea leaves under different illumination conditions, such as wrinkles, hairs, etc. These fine details often reflect the freshness and processing fineness of tea. Different illumination conditions can also help discover minor damages or defects on the surface of tea leaves, such as spots, mildew, etc., which directly affect the quality of tea.

[0051] Constructing the illumination graph structure enables the systematic presentation of the characteristics of tea leaves under different illumination conditions, and the graph convolutional network improves the speed and accuracy of detection.

[0052] In some embodiments, Figure 3A schematic flowchart for determining whether tea leaf vibration detection is qualified provided by an embodiment of the present invention. The determination of whether tea leaf vibration detection is qualified includes steps S21 to S25:

[0053] Step S21, using a deep neural network model based on the captured image of the tea leaves to determine multiple vibration frequencies of the tea leaves.

[0054] The input of the deep neural network model is the captured image of the tea leaves, and the output of the deep neural network model is multiple vibration frequencies of the tea leaves.

[0055] In some embodiments, the deep neural network model includes a tea leaf information determination layer, a target frequency determination layer, and multiple vibration frequency determination layers. The tea leaf information determination layer, the target frequency determination layer, and the multiple vibration frequency determination layers all include deep neural networks. The input of the tea leaf information determination layer is the captured image of the tea leaves, and the output of the tea leaf information determination layer is the color information, size information, and quantity of each tea leaf. The input of the target frequency determination layer is the color information, size information, and quantity of each tea leaf, and the output of the target frequency determination layer is the optimal vibration frequency of the tea leaves. The input of the multiple vibration frequency determination layers is the optimal vibration frequency of the tea leaves, and the output of the multiple vibration frequency determination layers is multiple vibration frequencies of the tea leaves.

[0056] Step S22, controlling a vibration device to vibrate based on the multiple vibration frequencies of the tea leaves, and obtaining vibration videos of the tea leaves at each vibration frequency.

[0057] Start the vibration device and record the video of the vibration process of the tea leaves at each frequency to obtain the vibration videos of the tea leaves at each vibration frequency. For example, the vibration video is a high-definition video showing the movement of the tea leaves at a vibration frequency of 50 Hz. In the video, the displacement and morphological changes of each tea leaf can be clearly seen.

[0058] Step S23, using a frequency information determination model to process the vibration videos of the tea leaves at each vibration frequency to determine the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies.

[0059] The frequency information determination model is a long short-term neural network model. The input of the frequency information determination model is the vibration videos of the tea leaves at each vibration frequency. The output of the frequency information determination model is the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies. The vibration information of the tea leaves at each vibration frequency includes the average amplitude of the tea leaves and the amplitude of each tea leaf.

[0060] The long short-term neural network model includes a long short-term neural network (LSTM, Long Short-Term Memory). Through the long short-term neural network model, the relationship in the vibration video time series of the tea leaves at each vibration frequency for consecutive time periods can be processed, and the characteristics of the vibration videos of the tea leaves at each vibration frequency considering each time point can be output, making the output characteristics more accurate and comprehensive.

[0061] The average amplitude is the average value of the amplitudes of all tea leaves at the same vibration frequency. For example, the average amplitude is 22 mm.

[0062] The amplitude of each tea leaf refers to the maximum displacement of each tea leaf at a certain vibration frequency. For example, the maximum displacement of a certain tea leaf is 15 mm.

[0063] Step S24: Construct a tea leaf vibration graph structure. The tea leaf vibration graph structure includes tea leaf nodes of multiple frequencies and multiple edges between the tea leaf nodes of multiple frequencies. The node features of each frequency's tea leaf node include the vibration information of the tea leaves at each vibration frequency, and the feature of the edge between the tea leaf nodes of different frequencies is the similarity of the vibration information of the tea leaves at different vibration frequencies.

[0064] The tea leaf vibration graph structure is a type of graph structure, where the nodes represent the vibration information of the tea leaves at different vibration frequencies, and the edges represent the similarity between this information. The tea leaf vibration graph structure is used to capture the associations of the dynamic behavior of the tea leaves under different vibration conditions. As an example, if there are three vibration frequencies (40 Hz, 60 Hz, 80 Hz), then the tea leaf vibration graph structure will contain three nodes, with each node corresponding to the vibration information at one vibration frequency. The edges between the nodes represent the similarity between this information. Each node in the tea leaf vibration graph structure represents the vibration information of the tea leaves at a specific vibration frequency. The tea leaf vibration graph structure can systematically organize and present the tea leaf vibration information and its interrelationships, facilitating further analysis and promoting comprehensive evaluation. By constructing the tea leaf vibration graph structure, the dynamic characteristics of the tea leaves at different vibration frequencies can be fully displayed, which helps to identify potential quality problems.

[0065] Step S25: Based on the second graph convolutional network, process the tea leaf vibration graph structure to determine whether the tea leaf vibration detection is qualified.

[0066] The input of the second graph convolutional network is the tea leaf vibration graph structure, and the output of the second graph convolutional network is whether the tea leaf vibration detection is qualified or unqualified. The response of tea leaves at different vibration frequencies reflects the elastic properties of their internal structures. High-quality tea leaves usually have specific elastic moduli and damping coefficients, and these physical properties affect the vibration modes of tea leaves at different frequencies. Tea leaves with higher compactness may exhibit smaller amplitudes during low-frequency vibration and greater energy dissipation during high-frequency vibration. These relationships can be effectively represented by the tea leaf vibration graph structure and processed by the second graph convolutional network to determine whether the tea leaf vibration detection is qualified.

[0067] Based on the same inventive concept, Figure 4 FIG. is a schematic diagram of a tea quality detection system based on big data provided by an embodiment of the present invention. The tea quality detection system based on big data includes:

[0068] An acquisition module 41, configured to acquire a captured image of a tea leaf;

[0069] A generation module 42, configured to generate tea leaf images under different color illuminations and the similarity of tea leaf images under different color illuminations based on the captured image of the tea leaf by using a variational autoencoder;

[0070] A construction module 43, configured to construct an illumination graph structure, where the illumination graph structure includes multiple tea leaf nodes of different color illuminations and multiple edges between the multiple tea leaf nodes of different color illuminations. The node feature of each tea leaf node of a color illumination includes the illumination image of the tea leaf under this color illumination, and the feature of the edge between the tea leaf nodes is the similarity of the tea leaf images under different color illuminations;

[0071] A detection module 44, configured to determine whether the tea quality detection is qualified by processing the illumination graph structure based on a first graph convolutional network.

[0072] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, as Figure 5 shown, including:

[0073] Including: 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 big data-based tea quality detection method provided as described above. The method includes: acquiring a captured image of tea; using a variational autoencoder based on the captured image of tea to generate tea images under different color illuminations and the similarity of tea images under different color illuminations; constructing an illumination graph structure, the illumination graph structure including multiple tea nodes under different color illuminations and multiple edges between the multiple tea nodes under different color illuminations, the node feature of each tea node under a color illumination including the illumination image of the tea under this color illumination, and the feature of the edge between tea nodes being the similarity of tea images under different color illuminations; and determining whether the tea quality detection is qualified by processing the illumination graph structure based on a first graph convolutional network.

[0074] Based on the same inventive concept, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by the processor 51, it implements the big data-based tea quality detection method provided as described above. The method includes: acquiring a captured image of tea; using a variational autoencoder based on the captured image of tea to generate tea images under different color illuminations and the similarity of tea images under different color illuminations; constructing an illumination graph structure, the illumination graph structure including multiple tea nodes under different color illuminations and multiple edges between the multiple tea nodes under different color illuminations, the node feature of each tea node under a color illumination including the illumination image of the tea under this color illumination, and the feature of the edge between tea nodes being the similarity of tea images under different color illuminations; and determining whether the tea quality detection is qualified by processing the illumination graph structure based on a first graph convolutional network.

[0075] The big data-based tea quality detection method provided in the embodiments of the present application can be applied to electronic devices such as terminal devices (such as mobile phones), tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, etc. The embodiments of the present application do not make any restrictions on this.

[0076] Taking the mobile phone 100 as an example of the above-mentioned electronic device, Figure 6 shows a schematic structural diagram of the mobile phone 100.

[0077] AsFigure 6 As shown in the figure, 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 interface 170D, a sensor module 180, a button 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. For example, the processing module 110 may include 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), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0079] Among them, the controller may be the nerve center and command center of the mobile phone 100, and is the decision maker that commands each component of the mobile phone 100 to work in coordination according to instructions. The controller may generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching instructions and executing instructions.

[0080] The operating system of the mobile phone 100 may be installed on the application processor to manage the hardware and software resources of the mobile phone 100. For example, manage and configure the memory, determine the priority order of system resource supply and demand, manage the file system, manage the driver, etc. The operating system may also be used to provide an operation interface for users to interact with the system. Among them, various software may be installed in the operating system, such as drivers, applications (Apps), etc. Exemplarily, the operating system of the mobile phone 100 may be an Android system, a Linux system, etc.

[0081] A memory may also be provided in the processing module 110 for storing instructions and data. In some embodiments, the memory in the processing module 110 is a cache memory. This memory can store the instructions or data that the processing module 110 has just used or recycled. If the processing module 110 needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces the waiting time of the processing module 110, and thus improves the efficiency of the system.

[0082] In some embodiments, the processing module 110 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0083] The processing module 110 can be used to: obtain a captured image of tea leaves; generate images of tea leaves under different color lights and the similarity of the images of tea leaves under different color lights based on the captured image of the tea leaves using a variational autoencoder; construct a light map structure, where the light map structure includes multiple tea leaf nodes of different color lights and multiple edges between the tea leaf nodes of different color lights, and the node feature of each tea leaf node of a color light includes the light image of the tea leaves under this color light, and the feature of the edge between the tea leaf nodes is the similarity of the images of the tea leaves under different color lights; determine whether the tea leaf quality inspection is qualified based on a first graph convolutional network for processing the light map structure.

[0084] The charging management module 140 is configured to receive a charging input from a charger. The charger can be a wireless charger or a wired charger. In some embodiments of wired charging, the charging management module 140 can receive the charging input from the wired charger through the USB interface 130. In some embodiments of wireless charging, the charging management module 140 can receive the wireless charging input through the wireless charging coil of the mobile phone 100. While charging the battery 142, the charging management module 140 can also supply power to the electronic device through the power management module 141.

[0085] The power management module 141 is used to connect the battery 142, the charging management module 140, and the processing module 110. The power management module 141 receives inputs from the battery 142 and / or the charging management module 140 and supplies power to the processing module 110, the internal memory 121, the external memory, the display screen 194, the camera 193, the wireless communication module 160, etc. The power management module 141 can also be used to monitor parameters such as the battery capacity, the number of battery cycles, and the battery health status (leakage, impedance). In some other embodiments, the power management module 141 can also be disposed in the processing module 110. In some other embodiments, the power management module 141 and the charging management module 140 can also be disposed in the same device.

[0086] The wireless communication function of the mobile phone 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modulation and demodulation processor, and the baseband processor, etc.

[0087] The antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the mobile phone 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization rate of the antennas. For example, the antenna 1 can be multiplexed as the diversity antenna of the wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0088] The mobile communication module 150 may provide solutions for wireless communications such as 2G / 3G / 4G / 5G applied to the mobile phone 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 may receive electromagnetic waves through the antenna 1, filter, amplify, and perform other processing on the received electromagnetic waves, and then transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 may also amplify the signal modulated by the modulation and demodulation processor and convert it into electromagnetic waves through the antenna 1 for radiation. In some embodiments, at least some functional modules of the mobile communication module 150 may be disposed in the processing module 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processing module 110 may be disposed in the same device.

[0089] The modulation and demodulation processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. Subsequently, the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 170A, receiver 170B, etc.), or displays an image or video through the display screen 194. In some embodiments, the modulation and demodulation processor may be an independent device. In other embodiments, the modulation and demodulation processor may be independent of the processing module 110 and disposed in the same device as the mobile communication module 150 or other functional modules.

[0090] The wireless communication module 160 may provide solutions for wireless communications applied to the mobile phone 100, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite systems (GNSSs), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, performs frequency modulation and filtering processing on the electromagnetic wave signals, and sends the processed signals to the processing module 110. The wireless communication module 160 may also receive signals to be sent from the processing module 110, perform frequency modulation and amplification on them, and convert them into electromagnetic waves through the antenna 2 for radiation.

[0091] In some embodiments, the antenna 1 of the mobile phone 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the mobile phone 100 can communicate with the network and other devices through wireless communication technologies. The wireless communication technologies may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technologies, etc. The GNSS may include global positioning system (GPS), global navigation satellite system (GLONASS), beidou navigation satellite system (BDS), quasi-zenith satellite system (QZSS), and / or satellite based augmentation systems (SBAS).

[0092] The mobile phone 100 realizes the display function through the GPU, the display screen 194, and the application processor, etc. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. The GPU is used to execute mathematical and geometric calculations for graphics rendering. The processing module 110 may include one or more GPUs, which execute program instructions to generate or change the display information.

[0093] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the mobile phone 100 may include one or N display screens 194, where N is a positive integer greater than 1.

[0094] The mobile phone 100 can implement the shooting function through the ISP, the camera 193, the video codec, the GPU, the display screen 194, and the application processor, etc. In some embodiments, the mobile phone 100 can implement the video communication function through the ISP, the camera 193, the video codec, the GPU, and the application processor.

[0095] The ISP is used to process the data fed back by the camera 193. For example, when taking a photo, the shutter is opened, and the light passes through the lens and is transmitted to the camera photosensitive element. The optical signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye. The ISP can also perform algorithm optimization on the noise, brightness, and skin color of the image. The ISP can also optimize parameters such as the exposure and color temperature of the shooting scene. In some embodiments, the ISP can be set in the camera 193.

[0096] The camera 193 is used to capture static images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in standard RGB, YUV, etc. formats. In some embodiments, the mobile phone 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0097] The digital signal processor is used to process digital signals. Besides being able to process digital image signals, it can also process other digital signals. For example, when the mobile phone 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy, etc.

[0098] The video codec is used to compress or decompress digital videos. The mobile phone 100 can support one or more video codecs. In this way, the mobile phone 100 can play or record videos in multiple coding formats, such as: Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0099] The NPU is a neural-network (NN) computing processor. By drawing on the structure of the biological neural network, such as the transmission mode between human brain neurons, it can quickly process the input information and can also continuously self-learn. Through the NPU, applications such as intelligent cognition of the mobile phone 100 can be realized, such as: image recognition, face recognition, speech recognition, text understanding, etc.

[0100] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the mobile phone 100. The external memory card communicates with the processing module 110 through the external memory interface 120 to achieve the data storage function. For example, files such as music and videos are saved in the external memory card.

[0101] The internal memory 121 can be used to store computer-executable program code, and the executable program code includes instructions. The processing module 110 executes various functional applications and data processing of the mobile phone 100 by running the instructions stored in the internal memory 121. The internal memory 121 can include a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, image playback function, etc.). The data storage area can store the data created during the use of the mobile phone 100 (such as audio data, phone book, etc.). In addition, the internal memory 121 can include high-speed random access memory and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0102] The mobile phone 100 can implement audio functions through the audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and the application processor, etc. For example, music playback, recording, etc.

[0103] The audio module 170 is used to convert digital audio information into an analog audio signal for output, and is also used to convert an analog audio input into a digital audio signal. The audio module 170 can also be used for encoding and decoding audio signals. In some embodiments, the audio module 170 can be disposed in the processing module 110, or some functional modules of the audio module 170 can be disposed in the processing module 110.

[0104] The speaker 170A, also known as the "loudspeaker", is used to convert an audio electrical signal into a sound signal. The mobile phone 100 can listen to music or hands-free calls through the speaker 170A.

[0105] The receiver 170B, also known as the "earpiece", is used to convert an audio electrical signal into a sound signal. When the mobile phone 100 answers a call or a voice message, the user can listen to the voice by bringing the receiver 170B close to the ear.

[0106] The microphone 170C, also known as the "microphone" or "transmitter", is used to convert a sound signal into an electrical signal. When making a call or sending a voice message, the user can speak by bringing the mouth close to the microphone 170C to input the sound signal into the microphone 170C. The mobile phone 100 can be provided with at least one microphone 170C. In some other embodiments, the mobile phone 100 can be provided with two microphones 170C, which can not only collect sound signals but also implement a noise reduction function. In some other embodiments, the mobile phone 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify the sound source, and implement functions such as directional recording.

[0107] The headphone jack 170D is used to connect a wired headphone. The headphone jack 170D can be a USB interface 130, or a 3.5 mm open mobile terminal platform (OMTP) standard interface, or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0108] The keys 190 include a power-on key, volume keys, etc. The keys 190 can be mechanical keys or touch keys. The mobile phone 100 can receive key inputs to generate key signal inputs related to the user settings and function controls of the mobile phone 100.

[0109] The motor 191 can generate vibration prompts. The motor 191 can be used for incoming call vibration prompts and also for touch vibration feedback. For example, touch operations for different applications (such as taking pictures, audio playing, etc.) can correspond to different vibration feedback effects. For touch operations on different areas of the display screen 194, the motor 191 can also correspond to different vibration feedback effects. Different application scenarios (such as time reminder, receiving messages, alarm clock, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0110] The indicator 192 can be an indicator light and can be used to indicate the charging state, power change, and can also be used to indicate messages, missed calls, notifications, etc.

[0111] The SIM card interface 195 is used to connect the SIM card. The SIM card can be inserted into or pulled out from the SIM card interface 195 to achieve contact and separation from the mobile phone 100. The mobile phone 100 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, etc. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the multiple cards can be the same or different. The SIM card interface 195 can also be compatible with different types of SIM cards. The SIM card interface 195 can also be compatible with external memory cards. The mobile phone 100 interacts with the network through the SIM card to achieve functions such as calls and data communication. In some embodiments, the mobile phone 100 uses an eSIM, that is, an embedded SIM card. The eSIM card can be embedded in the mobile phone 100 and cannot be separated from the mobile phone 100.

[0112] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to 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 fall within the spirit and scope of the exemplary embodiments of this specification.

[0113] At the same time, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at 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.

[0114] Moreover, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numerical and alphabetical characters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments of the invention have been discussed through various examples in the above disclosure, it should be understood that such details are for illustrative purposes only. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to 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 through software solutions, such as installing the described system on existing servers or mobile devices.

[0115] Similarly, it should be noted that, in order to simplify the presentation of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are combined into one embodiment, drawing, or description thereof. However, this method of disclosure does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0116] 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, by way of example and not limitation, alternative configurations of the embodiments of this specification can be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments clearly introduced and described in this specification.

Claims

1. A tea quality detection method based on big data, characterized in that: include: Acquire a photographed image of tea leaves; Based on the photographed images of the tea leaves, a variational autoencoder is used to generate tea leaves images under different colors of light and similarities of tea leaves images under different colors of light; Constructing a lighting graph structure, wherein the lighting graph structure includes tea leaves nodes illuminated by multiple colors and multiple edges between the tea leaves nodes illuminated by multiple colors, wherein the node feature of each tea leaves node illuminated by the color includes a lighting image of the tea leaves under the lighting of the color, and the feature of the edges between the tea leaves nodes is the similarity of the tea leaves images under lighting of different colors; Processing the illumination map structure based on the first graph convolutional network to determine whether the tea quality test is qualified; The method further comprises: Determining multiple vibration frequencies of the tea leaves using a deep neural network model based on the photographed image of the tea leaves; Controlling the vibration device to vibrate based on the multiple vibration frequencies of the tea leaves, and obtaining a vibration video of the tea leaves at each vibration frequency; Based on the frequency information determination model, the vibration video of the tea leaves at each vibration frequency is processed to determine the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies; Constructing a tea vibration graph structure, the tea vibration graph structure comprising tea nodes of multiple frequencies and multiple edges between the tea nodes of multiple frequencies, the node feature of each tea node of each frequency comprising vibration information of the tea at each vibration frequency, and the edge feature between tea nodes of different frequencies being the similarity of vibration information of the tea at different vibration frequencies; The tea vibration graph structure is processed based on the second graph convolutional network to determine whether the tea vibration detection is qualified.

2. The tea quality detection method based on big data according to claim 1, characterized in that: The frequency information determination model is a long-term and short-term neural network model, the input of the frequency information determination model is the vibration video of the tea leaves at each vibration frequency, the output of the frequency information determination model is the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies, and the vibration information of the tea leaves at each vibration frequency includes the average amplitude of the tea leaves and the amplitude of each piece of tea leaves.

3. The tea quality detection method based on big data according to claim 1, characterized in that: The input of the variational autoencoder is the photographed image of the tea leaves, and the output of the variational autoencoder is the images of the tea leaves under different colors of light and the similarities of the images of the tea leaves under different colors of light.

4. A tea quality detection system based on big data, characterized in that: include: An acquisition module is used to acquire the photographed image of tea leaves; A generation module, used for generating tea images under different colors of light and similarities of tea images under different colors of light by using a variational autoencoder based on the photographed images of the tea leaves; A construction module is used to construct a light map structure, wherein the light map structure includes tea leaves nodes illuminated by multiple colors and multiple edges between the tea leaves nodes illuminated by multiple colors, the node feature of each tea leaf node illuminated by the color includes the illumination image of the tea leaves under the illumination of the color, and the feature of the edge between the tea leaves nodes is the similarity of the tea leaves images under illumination of different colors; A detection module, used to process the illumination map structure based on a first graph convolutional network to determine whether the tea quality test is qualified; The system is also used to: Determining multiple vibration frequencies of the tea leaves using a deep neural network model based on the photographed image of the tea leaves; Controlling the vibration device to vibrate based on the multiple vibration frequencies of the tea leaves, and obtaining a vibration video of the tea leaves at each vibration frequency; Based on the frequency information determination model, the vibration video of the tea leaves at each vibration frequency is processed to determine the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies; Constructing a tea vibration graph structure, the tea vibration graph structure comprising tea nodes of multiple frequencies and multiple edges between the tea nodes of multiple frequencies, the node feature of each tea node of each frequency comprising vibration information of the tea at each vibration frequency, and the edge feature between tea nodes of different frequencies being the similarity of vibration information of the tea at different vibration frequencies; The tea vibration graph structure is processed based on the second graph convolutional network to determine whether the tea vibration detection is qualified.

5. The tea quality detection system based on big data according to claim 4, characterized in that: The frequency information determination model is a long-term and short-term neural network model, the input of the frequency information determination model is the vibration video of the tea leaves at each vibration frequency, the output of the frequency information determination model is the vibration information of the tea leaves at each vibration frequency and the similarity of the vibration information of the tea leaves at different vibration frequencies, and the vibration information of the tea leaves at each vibration frequency includes the average amplitude of the tea leaves and the amplitude of each piece of tea leaves.

6. The tea quality detection system based on big data according to claim 4, characterized in that: The input of the variational autoencoder is the photographed image of the tea leaves, and the output of the variational autoencoder is the images of the tea leaves under different colors of light and the similarities of the images of the tea leaves under different colors of light.

7. 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 tea quality detection method based on big data as described in any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the big data-based tea quality detection method as described in any one of claims 1 to 3 is implemented.

Images