Agricultural product quality grade grading method and system and electronic equipment

Abstract

The invention relates to the technical field of agricultural product intelligence, in particular to an agricultural product quality grade grading method and system and electronic equipment. The method comprises the steps of determining appearance grade data of agricultural products according to appearance image data of the agricultural products; quality fingerprint data of the agricultural products are obtained, the quality fingerprint data represent physicochemical indexes of the agricultural products, and the physicochemical indexes comprise at least one of sugar degree, acidity, pesticide residue degree and production place characteristics; and quality grade information of the agricultural product is determined according to the appearance grade data and the quality fingerprint data, and the quality grade information represents the quality grade of the agricultural product. According to the technical scheme, the accuracy of agricultural product quality grading is improved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent agricultural product technology, and in particular to a method, system and electronic equipment for grading agricultural product quality. Background Technology

[0002] Current technologies primarily rely on deep learning algorithms such as Convolutional Neural Networks (CNN) and YOLO object detection to grade agricultural products based on surface features. However, this approach is prone to misjudging quality and is ineffective for grading agricultural products with inherently poor appearance. Summary of the Invention

[0003] This disclosure provides a method, system, and electronic device for grading agricultural product quality to solve or alleviate one or more technical problems in the prior art.

[0004] As a first aspect of the present disclosure, the present disclosure provides a method for grading the quality of agricultural products, including: Based on the appearance image data of agricultural products, determine the appearance grade data of agricultural products; Obtain quality fingerprint data of agricultural products. Quality fingerprint data characterizes the physicochemical indicators of agricultural products, including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics. Based on appearance grade data and quality fingerprint data, the quality grade information of agricultural products is determined, and the quality grade information represents the quality grade level of agricultural products.

[0005] In some embodiments, obtaining quality fingerprint data of agricultural products includes: Obtain the labeling information of agricultural products; Based on the identification information, the quality fingerprint data is determined, and the quality fingerprint data corresponds to the identification information.

[0006] In some embodiments, obtaining quality fingerprint data of agricultural products includes: Based on the appearance image data, identify the category information of agricultural products, which includes the type and variety information of agricultural products; Based on the product category information, quality fingerprint data is retrieved from a pre-set quality database. The pre-set quality database stores different categories of agricultural products and their corresponding quality fingerprint data.

[0007] In some embodiments, determining the quality grade information of agricultural products based on appearance grade data and quality fingerprint data includes: Based on the category information of agricultural products, determine the appearance weight and quality fingerprint weight of agricultural products. Category information includes the type information and variety information of agricultural products. The first quality score is determined based on the appearance grade data and appearance weight; The second quality score is determined based on the quality fingerprint data and quality fingerprint weights. The quality grade information of agricultural products is determined based on the first quality score and the second quality score.

[0008] In some embodiments, determining the appearance weight of agricultural products based on category information includes: Determine the initial weights of the appearance of agricultural products based on their type information; Based on the variety information of agricultural products, determine the confidence level fluctuation coefficient of agricultural products; The appearance weights of agricultural products are determined based on the initial appearance weights and the confidence level fluctuation coefficient.

[0009] In some embodiments, determining the quality fingerprint weight of agricultural products based on the type information of the agricultural products includes: Determine the initial quality weights of agricultural products based on their type information; Based on the time information of the quality fingerprint data, the timeliness coefficient of the quality fingerprint data is determined. The time information is used to characterize the data storage time of the quality fingerprint data and the change information of the origin characteristics of agricultural products. The quality fingerprint weight is determined based on the initial quality weight and the timeliness coefficient.

[0010] In some embodiments, applied to the server side, the method further includes: The system receives appearance image data sent by the client. The appearance image data is acquired by the client based on the type of agricultural product, through the image acquisition module, and under the guidance of the image acquisition guidance instructions. The image acquisition guidance instructions include an image frame used to represent the image area and lighting prompts. The image frame is adapted to the appearance shape of the agricultural product. The image acquisition guidance instructions are generated by the client based on the type of agricultural product. The quality grade information of agricultural products is sent to the client so that the client can generate a quality grading result for the agricultural products based on the quality grade information.

[0011] As a second aspect of this disclosure, this disclosure provides a method for grading the quality of agricultural products, applied to a client, the method comprising: Based on the type of agricultural product, the image acquisition module is activated and an image acquisition guidance instruction is generated to acquire the appearance image data of the agricultural product. The image acquisition guidance instruction is used to guide the acquisition of the appearance image data of the agricultural product. The image acquisition guidance instruction includes an image frame for representing the image area and lighting prompt information. The image frame is adapted to the appearance shape of the agricultural product. The appearance image data is judged to be qualified using a preset image evaluation standard. If the appearance image data does not meet the preset image evaluation criteria, the image acquisition module will be restarted and an image acquisition guidance command will be generated to re-acquire the appearance image data of agricultural products. If the appearance image data meets the preset image evaluation criteria, the appearance image data is sent to the server so that the server executes any of the methods in this disclosure; Receive the quality grade information of agricultural products returned by the server, and generate the quality grading results of agricultural products based on the quality grade information.

[0012] In some embodiments, before activating the image acquisition module and generating image acquisition guidance instructions based on the type of agricultural product, the method further includes: In response to the identification command, the image acquisition module is activated to acquire images of the physical identification marks on agricultural products; Based on the physical identification image, obtain the identification information of agricultural products, including the type of agricultural product.

[0013] In some embodiments, the method further includes: While sending the appearance image data to the server, the identification information is also sent to the server so that the server can determine the quality fingerprint data of the agricultural product based on the identification information.

[0014] In some embodiments, before activating the image acquisition module and generating image acquisition guidance instructions based on the type of agricultural product, the method further includes: Based on the keywords of agricultural products entered by the user, obtain information about the types of agricultural products.

[0015] As a third aspect of this disclosure, this embodiment provides an agricultural product quality grading device, comprising: The appearance grade determination module allows users to determine the appearance grade data of agricultural products based on the appearance image data. The acquisition module is used to acquire quality fingerprint data of agricultural products. The quality fingerprint data characterizes the physicochemical indicators of agricultural products, including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics. The quality grade determination module is used to determine the quality grade information of agricultural products based on appearance grade data and quality fingerprint data.

[0016] As a fourth aspect of the present disclosure, this disclosure provides an agricultural product quality grading device, applied to a client, the device comprising: The guided acquisition module is used to start the image acquisition module and generate image acquisition guidance instructions based on the type information of agricultural products, so as to acquire the appearance image data of agricultural products. The image acquisition guidance instructions are used to guide the acquisition of appearance image data of agricultural products. The image acquisition guidance instructions include image frames for representing image areas and lighting prompts. The image frames are adapted to the appearance shape of agricultural products. The image evaluation module is used to determine whether the appearance image data is qualified by using preset image evaluation standards. If the appearance image data does not meet the preset image evaluation criteria, an instruction to re-acquire the image will be generated. If the appearance image data meets the preset image evaluation criteria, the appearance image data is sent to the server so that the server executes any of the methods disclosed herein. The generation module is used to receive the quality grade information of agricultural products returned by the server and generate the quality grading results of agricultural products based on the quality grade information.

[0017] As a fifth aspect of this disclosure, this disclosure provides an agricultural product quality grading system, including: The client is used to activate the image acquisition module and generate image acquisition guidance instructions based on the type of agricultural product, in order to acquire the appearance image data of the agricultural product. The image acquisition guidance instructions guide the acquisition of the appearance image data of the agricultural product and include an image frame representing the image area and lighting prompts. The image frame is adapted to the appearance shape of the agricultural product. A preset image evaluation standard is used to determine whether the appearance image data is qualified. If the appearance image data does not meet the preset image evaluation standard, the image acquisition module is restarted and an image acquisition guidance instruction is generated to re-acquire the appearance image data of the agricultural product. If the appearance image data meets the preset image evaluation standard, the appearance image data is sent to the server. The server is used to determine the appearance grade data of agricultural products based on the appearance image data; to obtain the quality fingerprint data of agricultural products, which characterizes the physicochemical indicators of agricultural products, including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics; and to determine the quality grade information of agricultural products based on the appearance grade data and the quality fingerprint data, and send the quality grade information to the client. The client is also used to receive the quality grade information of agricultural products returned by the server, and generate the quality grading results of agricultural products based on the quality grade information.

[0018] As a sixth aspect of this disclosure, this disclosure provides an electronic device, including: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform any of the methods of this disclosure.

[0019] As a seventh aspect of the present disclosure, the present disclosure provides a readable storage medium that, when executed by a processor, implements the methods as described in any of the present disclosure.

[0020] The technical solution of this disclosure determines the appearance grade data of agricultural products based on their appearance image data; acquires the quality fingerprint data of the agricultural products; and then comprehensively determines the quality grade of the agricultural products based on both the appearance grade data and the quality fingerprint data. This approach no longer relies solely on a single visual indicator (i.e., appearance image) to evaluate the quality grade of agricultural products. Instead, it combines both appearance grade data and quality fingerprint data, integrating internal and external quality indicators to comprehensively determine the quality grade of the agricultural products. This significantly reduces the grading error compared to schemes that rely solely on appearance, thus improving the accuracy of agricultural product quality grading.

[0021] The above overview is for illustrative purposes only and is not intended to be limiting in any way. Further aspects, embodiments, and features of this disclosure will become readily apparent from the accompanying drawings and the following detailed description, in addition to the illustrative aspects, embodiments, and features described above. Attached Figure Description

[0022] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments according to this disclosure and should not be construed as limiting the scope of this disclosure.

[0023] Figure 1 This is a flowchart illustrating a method for grading agricultural product quality grades in one embodiment of the present disclosure; Figure 2 This is a schematic diagram of the process of grading agricultural product quality grades in one embodiment of the present disclosure; Figure 3 This is a structural block diagram of an agricultural product quality grading device according to an embodiment of the present disclosure; Figure 4 This is a structural block diagram of an agricultural product quality grading device according to another embodiment of the present disclosure; Figure 5 This is a structural block diagram of an agricultural product quality grading system in one embodiment of the present disclosure. Detailed Implementation

[0024] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of this disclosure, and different embodiments can be combined arbitrarily without conflict. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0025] In related technologies, agricultural product appearance image data and self-learning neural network models are used to classify agricultural products according to their quality by analyzing surface characteristics (such as color, morphology, and surface defects). However, this classification method does not consider agricultural product quality data (such as physicochemical indicators like sugar content, acidity, and hardness), which can easily lead to inaccurate quality grading. Furthermore, this method also fails to consider the impact of agricultural product growth environment data (such as accumulated temperature, precipitation, and soil conditions) on agricultural product quality, resulting in biased quality grading results, large errors, and inaccurate grading outcomes.

[0026] While related technologies use physical identifiers (such as QR codes and RFID tags) to record agricultural product supply chain information, their main functions include origin traceability verification, variety information recording, and circulation tracking, but they do not establish a link between physical identifiers and the quality of agricultural products.

[0027] To further improve the accuracy of agricultural product quality grading, this disclosure proposes a method for grading agricultural product quality grades. Using this method to grade agricultural products can reduce grading errors and improve the accuracy of the grading results. The technical solution of this disclosure is described in detail below through specific embodiments.

[0028] Figure 1 This is a flowchart illustrating a method for grading agricultural product quality levels according to an embodiment of this disclosure. Figure 1 As shown, the grading method includes steps S11 to S13.

[0029] In step S11, the appearance grade data of the agricultural products are determined based on the appearance image data of the agricultural products.

[0030] Agricultural products can be photographed using an image acquisition module to obtain their appearance image data. This appearance image data can be obtained through photographs of the agricultural product's appearance, videos of its appearance, or multiple photographs of the agricultural product from different angles. This disclosure does not limit the method of obtaining appearance image data.

[0031] The appearance image data can be preprocessed. Preprocessing methods may include using the CLAHE algorithm to enhance the contrast of the appearance image and using YOLOv5 to locate target regions in the image. The preprocessed appearance image data is then normalized and input into a preset appearance grading model to obtain the appearance features of the agricultural product, such as the color HSV histogram and the proportion of defect area. Alternatively, AI visual analysis can be used, for example, using a high-precision model (ResNet50) to analyze the color, texture, and defects (such as the proportion of mold area) of the agricultural product's appearance, extracting the appearance features. Based on the appearance features and preset thresholds, the agricultural product is graded according to its appearance, resulting in appearance grade data.

[0032] In step S12, quality fingerprint data of agricultural products is obtained. The quality fingerprint data characterizes the physicochemical indicators of agricultural products, including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics.

[0033] Different agricultural products have different physicochemical indicators, which significantly influence their quality grade. For example, for fruits, these indicators may include sugar content, acidity, firmness, moisture content, and geographical origin. Vegetables, on the other hand, typically have indicators such as moisture content, pesticide residues, firmness, and geographical origin. Geographical origin characteristics can include natural attributes of the production area, such as climate and soil characteristics (e.g., pH level). The specific physicochemical indicators for different agricultural products can be determined based on actual needs.

[0034] Quality fingerprint data corresponds to agricultural products; different types of agricultural products have different quality fingerprint data, which characterizes the physicochemical indicators of the agricultural products. In practical applications, physicochemical indicators of various types of agricultural products can be tested to obtain their quality fingerprint data. Furthermore, a quality database can be established, storing quality fingerprint data for different types of agricultural products.

[0035] In step S13, the quality grade information of agricultural products is determined based on the appearance grade data and quality fingerprint data. The quality grade information represents the quality grade level of agricultural products.

[0036] Understandably, quality fingerprint data has a significant impact on the quality of agricultural products. When an agricultural product has a high appearance grade, a poor quality fingerprint will result in a lower quality grade. Therefore, both appearance grade data and quality fingerprint data are used to comprehensively determine the quality grade information of agricultural products. This quality grade information can characterize the quality level of the agricultural product.

[0037] The technical solution disclosed herein determines the appearance grade data of agricultural products based on their appearance image data; obtains the quality fingerprint data of agricultural products; and then comprehensively determines the quality grade of agricultural products based on both appearance grade data and quality fingerprint data. This approach no longer relies solely on a single visual indicator (i.e., appearance image) to evaluate the quality grade of agricultural products, but combines both appearance grade data and quality fingerprint data, integrating internal and external quality indicators to comprehensively determine the quality grade of agricultural products. This significantly reduces grading errors compared to solutions that rely solely on appearance, thus improving the accuracy of agricultural product quality grading.

[0038] The quality grading method of this disclosure can be executed on the client side or the server side. When the quality grading method is executed on the server side, the client can collect appearance image data of agricultural products and send the corresponding appearance image data to the server side, which can then process the appearance image data. Alternatively, the client can collect appearance image data, process it, and then send the processed appearance image data to the server side.

[0039] The server can be a physical server or a cloud server.

[0040] In one embodiment, obtaining quality fingerprint data of agricultural products may include: obtaining identification information of agricultural products; determining quality fingerprint data based on the identification information, wherein the quality fingerprint data corresponds to the identification information.

[0041] Agricultural products can have physical identifiers, such as QR codes, barcodes, or RFID tags, that can identify the product. These physical identifiers can be identified using corresponding identifier recognition modules to obtain the product's identification information. Each type of identifier corresponds to quality fingerprint data; for example, a quality database stores different identifiers and their corresponding quality fingerprint data. After obtaining the product's identifier information, the corresponding quality fingerprint data can be retrieved from the quality database.

[0042] When the grading method of this embodiment is executed on the server, the client can identify the physical identifier of the agricultural product through the corresponding identifier recognition module, and then send the identified identifier information to the server, so that the server can obtain the identifier information of the agricultural product.

[0043] To improve the accuracy of quality fingerprint data, the quality fingerprint data in the quality database can be updated periodically.

[0044] In another embodiment, obtaining quality fingerprint data of agricultural products includes: identifying the category information of agricultural products based on appearance image data, the category information including the type information and variety information of agricultural products; and querying quality fingerprint data from a preset quality database based on the category information, the preset quality database storing different categories of agricultural products and their corresponding quality fingerprint data.

[0045] Agricultural product category information can be identified through appearance image data. For example, appearance image data can be input into a pre-trained category recognition model, which outputs the category information of the agricultural product, including type and variety information. For instance, if the appearance image data of a Fuji apple is input into a pre-trained category recognition model, the model will output the category information of the agricultural product: type is apple, variety is Fuji. It is understandable that variety information can reflect the regional characteristics of agricultural products.

[0046] The category recognition model can be trained using conventional techniques disclosed herein. For example, multiple sets of appearance image data of agricultural products can be used as input to the category recognition model, and the types and varieties of agricultural products can be used as the actual output to train the category recognition model. The parameter values ​​of the category recognition model are continuously adjusted until the output of the category recognition model converges, thus obtaining a pre-trained category recognition model. The category recognition model can use a neural network model commonly used in this field, such as a CNN model, etc., and no specific model type is limited here.

[0047] The quality database stores quality fingerprint data for different categories of agricultural products. Based on the category information of the agricultural product, the quality fingerprint data of that category of agricultural product can be obtained by querying the preset quality database.

[0048] In one embodiment, determining the quality grade information of an agricultural product based on appearance grade data and quality fingerprint data may include: determining the appearance weight and quality fingerprint weight of the agricultural product based on the category information of the agricultural product, wherein the category information includes the type information and variety information of the agricultural product; determining a first quality score based on the appearance grade data and appearance weight; determining a second quality score based on the quality fingerprint data and quality fingerprint weight; and determining the quality grade information of the agricultural product based on the first quality score and the second quality score.

[0049] In this embodiment, appearance grade data and quality fingerprint data are respectively assigned weights. Appearance grade data has a corresponding appearance weight, and quality fingerprint data has a corresponding quality fingerprint weight.

[0050] Category information includes the types and varieties of agricultural products. Different types of agricultural products can have different appearance weights. For example, appearance has a greater impact on the quality of apples, while its impact on the quality of onions is relatively smaller; therefore, the appearance weights for apples and onions can be different. The quality fingerprint weights for different types of agricultural products can also be different. Therefore, based on the category information of agricultural products, the appearance weights and quality fingerprint weights can be determined.

[0051] The first quality score can be determined based on the appearance rating data and appearance weight. For example, the first quality score is obtained by calculating the product of the appearance rating data and the appearance weight.

[0052] A second quality score is determined based on the quality fingerprint data and its weights. For example, the second quality score is obtained by multiplying the quality fingerprint data by its weights.

[0053] For example, the first quality score and the second quality score can be summed to obtain the quality grade information of the agricultural product. For instance, the quality grade information of the agricultural product can be a quality grade score. Quality grade information can characterize the quality grade of the agricultural product; for example, the higher the quality grade score, the higher its quality grade. For example, the quality grade score can be expressed as: Quality grade score = (Appearance grade data × Appearance weight) + (Quality fingerprint data × Variety fingerprint weight) Formula (1) In this embodiment, different agricultural products have corresponding appearance weights and quality fingerprint weights. By weighting the appearance grade data and quality fingerprint data separately, and combining the appearance weighted score and the quality weighted score, the quality grade information of the agricultural products is determined. This method adjusts the proportion of appearance grade data by appearance weight and the proportion of quality fingerprint data by quality fingerprint weight according to the category of agricultural products, thereby further improving the accuracy of the determined quality grade and reducing the quality grade error.

[0054] Quality grade information can characterize the quality level of agricultural products. For example, the higher the quality grade score, the higher the quality level of the agricultural product. For example, a quality score of 90-100 corresponds to a five-star quality level; a quality score of 80-89 corresponds to a four-star quality level; a quality score of 70-79 corresponds to a three-star quality level; and a quality score of 60-69 corresponds to a two-star quality level.

[0055] To further improve the accuracy of quality grades, the appearance weights can be dynamically adjusted.

[0056] In one embodiment, determining the appearance weight of agricultural products based on the category information of agricultural products may include: determining the initial appearance weight of agricultural products based on the type information of agricultural products; determining the confidence level fluctuation coefficient of agricultural products based on the variety information of agricultural products; and determining the appearance weight of agricultural products based on the initial appearance weight and the confidence level fluctuation coefficient.

[0057] Agricultural products can include different kinds of fruits and vegetables, and fruits can include different kinds of fruits such as apples, pears, bananas, lychees, and tomatoes. Different kinds of fruits can have the same initial appearance weight or different initial appearance weights. The initial appearance weight can be determined based on the variety information. For example, different kinds of fruits may have the same initial appearance weight. For instance, the initial appearance weight of a fruit may be 0.6.

[0058] The same type of fruit can be divided into different varieties. For example, apples can be divided into varieties such as Fuji and Guoguang, and pears can be divided into different varieties such as Ya pear, Xuehua pear, and Korla fragrant pear. For agricultural products of the same type but different varieties, the impact of appearance on quality fluctuations varies. This impact can be called the confidence level fluctuation coefficient. For example, for fruits like lychee and longan, the appearance has a relatively small impact on quality fluctuations, and their corresponding confidence level fluctuation coefficients are small; for grapes, the appearance has a relatively large impact on quality fluctuations, and their corresponding confidence level fluctuation coefficients are large.

[0059] The confidence level fluctuation coefficient of agricultural products can be determined based on their variety information. The appearance weights of agricultural products are dynamically determined based on the initial appearance weights and the confidence level fluctuation coefficient. This dynamic adjustment of appearance weights using the confidence level fluctuation coefficient ensures that the appearance weights are matched to different varieties of agricultural products, improving the accuracy of appearance quality scores. For example, the appearance weights can be expressed as... Appearance weight = initial appearance weight × (1 - confidence level fluctuation coefficient), formula (2) The larger the confidence level fluctuation coefficient, the greater its impact on appearance weight; therefore, the larger the confidence level fluctuation coefficient, the smaller the appearance weight.

[0060] To further improve the accuracy of quality grades, the weight of the quality fingerprint can be dynamically adjusted.

[0061] In one embodiment, determining the quality fingerprint weight of agricultural products based on the type information of agricultural products includes: determining the initial quality weight of agricultural products based on the type information of agricultural products; determining the timeliness coefficient of quality fingerprint data based on the time information of quality fingerprint data, wherein the time information is used to characterize the data storage time of quality fingerprint data and the change information of the origin characteristics of agricultural products; and determining the quality fingerprint weight based on the initial quality weight and the timeliness coefficient.

[0062] Different types of fruit can have the same initial quality weight or different initial quality weights. The initial quality weights can be determined based on the type information. For example, different types of fruit may have the same initial quality weight. For instance, the initial appearance weight of the fruit might be 0.4.

[0063] It is understandable that the quality fingerprint data of agricultural products is obtained by testing samples. Because the process of testing samples is relatively complicated and costly, the update frequency of quality fingerprint data of different types of agricultural products is different, which leads to the fact that the time information of different quality fingerprint data can be the same.

[0064] The geographical origin characteristics of agricultural products have a significant impact on their quality. These characteristics can include natural attributes such as climate and soil features. Over time, these geographical origin characteristics may change, leading to variations in the quality of the agricultural products. Information on these changes reflects how these characteristics have evolved over time. Because geographical origin characteristics influence quality, the temporal information in quality fingerprint data has varying impacts on the current quality of the agricultural product. Therefore, changes in geographical origin characteristics affect the reliability of quality fingerprint data. The magnitude of this impact can be termed the timeliness coefficient of the quality fingerprint data. This time information characterizes both the data storage time of the quality fingerprint data and the changes in the geographical origin characteristics of the agricultural product.

[0065] For example, the shorter the data storage time of quality fingerprint data, the larger the timeliness coefficient; the stronger the regional variation characteristics of agricultural products, the smaller the timeliness coefficient. The larger the timeliness coefficient, the greater the weight of the quality fingerprint.

[0066] For example, a table can be pre-established to correspond to data storage time, changes in origin characteristics, and timeliness coefficients. Based on the time information of the quality fingerprint data, this table can be queried to determine the timeliness coefficients.

[0067] Based on the initial quality weight and the timeliness coefficient, the quality fingerprint weight of agricultural products is dynamically determined. This allows for dynamic adjustment of the initial quality weight using the timeliness coefficient, ensuring that the initial quality weight matches the quality fingerprint data of the agricultural products and improving the accuracy of the quality score. For example, the quality fingerprint weight can be expressed as: Quality fingerprint weight = initial quality weight × timeliness coefficient, formula (3) The higher the timeliness coefficient, the greater the weight of the quality fingerprint.

[0068] In one embodiment, the quality grading method of this disclosure is executed on a server. The server and client are connected in communication. The client can collect appearance image data of agricultural products and send the corresponding appearance image data to the server. The server receives the appearance image data sent by the client.

[0069] For example, the client can activate the image acquisition module and generate image acquisition guidance instructions based on the type of agricultural product. The image acquisition module then acquires appearance image data under the guidance of these instructions. The image acquisition guidance instructions include an image frame representing the image area, lighting cues, and shooting background information. The image frame is adapted to the shape of the agricultural product, and the instructions are generated by the client based on the type of agricultural product.

[0070] After determining the quality grade information of agricultural products, the server sends the quality grade information to the client so that the client can generate the quality grading result of agricultural products based on the quality grade information. The client can also display the quality grading result of agricultural products.

[0071] The specific execution process on the client side can be found below.

[0072] Another embodiment of this disclosure provides a method for grading the quality of agricultural products, applied to a client, the grading method including steps S21 and S22.

[0073] In step S21, the client starts the image acquisition module and generates an image acquisition guidance instruction based on the type information of the agricultural products, so as to acquire the appearance image data of the agricultural products.

[0074] The client can be an application installed on a terminal device or a dedicated terminal device. After receiving the type information of agricultural products, the client can identify the types of agricultural products that require quality grading. Then, it activates the image acquisition module, allowing the user to collect visual image data of the agricultural products.

[0075] It is understandable that different users have varying image-capturing abilities, which may lead to differences in the quality of the acquired appearance image data. To reduce the requirements on users' image-capturing abilities, the client can generate image acquisition guidance instructions based on the type of agricultural product. These instructions guide the capture of appearance image data of the agricultural product and include an image frame representing the image area and lighting cues. The image frame is adapted to the shape of the agricultural product. For example, the image acquisition guidance instructions can be voice commands. For instance, after activating the image acquisition module, users can adjust the shooting angle, shooting position, shooting background, lighting, etc., under the guidance of the image acquisition guidance instructions, so that they can acquire high-quality appearance image data.

[0076] For example, image acquisition guidance instructions can be integrated into the image acquisition module using augmented reality (AR) technology. For instance, the background automatically adapts to the shape of the corresponding agricultural product, displaying an image frame. For example, when the agricultural product is an apple, the image frame is a circular frame resembling an apple; when the agricultural product is a banana, the image frame is an arc-shaped frame. This ensures that the image captured by the user is within the image frame, improving image quality. Lighting prompts can remind the user whether to turn on the flash to increase brightness, thereby improving image quality.

[0077] Image acquisition guidance instructions are not limited to image frames and lighting cues; they can also include other guidance instructions to improve the quality of images captured by the user. For example, AR technology can be used to overlay shooting elements such as lighting, angle, and background onto the shooting screen to guide users in photographing agricultural products. In practice, different image acquisition guidance instructions can be set according to different types of agricultural products. AR-based guidance instructions can be implemented using ARKit / ARCore, dynamically marking the outline of agricultural products against the standard shooting area in the shooting screen.

[0078] In step S22, a preset image evaluation standard is used to determine whether the appearance image data is qualified.

[0079] To ensure the server can efficiently acquire high-quality appearance image data, the client has preset image evaluation standards. After the user acquires appearance image data through the image acquisition module, the client evaluates the data using these preset standards to determine whether it is qualified or meets the standards. These preset standards can be set as needed; different agricultural product types can have the same or different standards. For example, OpenCV can be used to detect image brightness and blurriness. The captured image brightness must meet the brightness standard in the preset image evaluation standards, and the captured image blurriness must also meet the blurriness standard in the preset image evaluation standards.

[0080] If the appearance image data does not meet the preset image evaluation criteria, the image acquisition module is restarted and an image acquisition guidance instruction is generated to re-acquire the appearance image data of the agricultural product. If the appearance image data meets the preset image evaluation criteria, the appearance image data is sent to the server so that the server can determine the quality grade of the agricultural product using the method described in the above embodiment. After the server determines the quality grade information of the agricultural product, the server sends the quality grade information to the client. The client receives the quality grade information of the agricultural product returned by the server and generates a quality grading result of the agricultural product based on the quality grade information. The client can also display the quality grading result of the agricultural product.

[0081] The client can display the quality grading results of agricultural products through voice, images, or reports, or by outputting visual reports. The specific display format can be set according to actual needs.

[0082] This embodiment of the agricultural product quality grading method allows users to acquire appearance images of agricultural products via an image acquisition module under the guidance of image acquisition instructions through a client. This reduces the requirements for users' shooting capabilities, enabling ordinary users to easily acquire high-quality appearance images through the client. This expands the application scope of this technical solution; for example, the disclosed technical solution can be applied not only to professional agricultural product quality grading scenarios but also to small farms or rural agricultural scenarios. Furthermore, in this embodiment, the client can automatically evaluate the received appearance image data, sending images that meet preset image evaluation standards to the server; otherwise, the user is prompted to retake the image. This setup improves the efficiency of acquiring high-quality appearance image data. Moreover, the server completes the quality grading and then returns the grading results (i.e., quality grade information) to the client. This reduces the processing power requirements of the client, and the server can more quickly determine the quality grade information of agricultural products and return it to the client. The client then generates the quality grading result based on the quality grade information and displays the result to the user, allowing the user to quickly understand the quality grading results of the agricultural products.

[0083] In one embodiment, agricultural products have corresponding physical identifiers, such as QR codes, RFID tags, or barcodes. The type of agricultural product can be obtained by identifying its physical identifier.

[0084] Users can activate the client's identification recognition function. In response to the identification recognition command, the client initiates an image acquisition module to capture images of the physical identification marks on agricultural products. For example, if a user triggers the client's "scan" function, initiating the identification recognition function, the client receives the identification recognition command. Then, based on the physical identification image, the client obtains the identification information of the agricultural product, including its type. Based on this type information, the client reactivates the image acquisition module and generates an image acquisition guidance command, allowing the user to collect the appearance image data of the agricultural product through the image acquisition module. In this embodiment, the client obtains the type information of the agricultural product through its physical identification. To improve the efficiency of the server in obtaining this information, the client sends the identification information to the server simultaneously with the appearance image data, enabling the server to determine the quality fingerprint data of the agricultural product based on its identification information.

[0085] In small-scale farms or rural agricultural settings, agricultural products are not labeled. If users want to learn about the quality grade of agricultural products through the client, the client's user interface can have an input box for the type of agricultural product. Users can enter keywords for the type of agricultural product in the input box, for example, "Red Fuji". After receiving the type keywords entered by the user, the client will retrieve the type information of the agricultural product based on the keywords entered by the user.

[0086] Figure 2 This is a schematic diagram of the process of grading agricultural product quality grades in one embodiment of the present disclosure. The grading process of the technical solution of the present disclosure is explained below using the grading of Fuji apples as an example.

[0087] refer to Figure 2 When a user triggers the "Scan" function on the client, the client initiates image acquisition on the device. The user scans the apple's QR code using the image acquisition module. The client obtains the type information from the identification information, then restarts the image acquisition module and generates image acquisition guidance instructions, such as initiating AR shooting guidance. Guided by these instructions, the user adjusts to a preset angle and acquires an image of the Fuji apple's appearance using the image acquisition module. The client determines if the image quality meets the standards. If not, the user is prompted to retake the photo; if it does, the client uploads the apple's appearance image data to the server. The server uses AI visual analysis to extract the apple's appearance features and obtain appearance grade data. Based on the apple's type information, the server queries the quality database.

[0088] During the dynamic data fusion process, the server obtains appearance grade data based on the apple's appearance characteristics. For example, if the server detects localized browning (3% defect area), it determines the appearance grade to be "Level 1," and the appearance grade data represents an appearance score of 85 points. It also obtains quality fingerprint data by querying the quality database. For example, the quality fingerprint data shows that the production area has recently experienced heavy rainfall, resulting in a general increase in sugar content of 1°. Therefore, the quality fingerprint data reflects a sugar content score of 15 points for the apple. The server determines the confidence fluctuation coefficient using the method of this embodiment, and then calculates the appearance weight, for example, 0.55. Based on the timeliness coefficient, it determines the quality fingerprint weight, for example, 0.45. The server uses formula (1) to calculate the quality grade score = 85 × 0.55 + 15 × 0.45 = 82.5. The final grade of the apple is upgraded from "Level 1" to "Special Grade," meaning that the quality grade increases due to the higher sugar content of the apple. It is understood that the quality grade corresponding to the appearance score is different from the grade corresponding to the quality score of this disclosure.

[0089] The server sends the quality grade score to the client, which can then generate a quality grading result for the agricultural product based on the quality grade information and output a visual report. If the client is deployed in a local lightweight mode, it can display the quality grading result. If the client is not deployed in a local lightweight mode, it can send the quality grading result to the server, which will then generate a report on the quality grade of the agricultural product.

[0090] One embodiment of this disclosure also provides a device for grading the quality of agricultural products, such as... Figure 3 As shown, this grading device can be applied to a server. The grading device may include an appearance grade determination module 31, an acquisition module 32, and a quality grade determination module 33.

[0091] The appearance grade determination module 31 allows users to determine the appearance grade data of agricultural products based on the appearance image data of the agricultural products.

[0092] The acquisition module 32 is used to acquire quality fingerprint data of agricultural products. The quality fingerprint data characterizes the physicochemical indicators of agricultural products, including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics.

[0093] The quality grade determination module 33 is used to determine the quality grade information of agricultural products based on appearance grade data and quality fingerprint data.

[0094] For example, the acquisition module can be used to: acquire the identification information of agricultural products; determine the quality fingerprint data based on the identification information, wherein the quality fingerprint data corresponds to the identification information.

[0095] For example, the acquisition module can be used to: identify the category information of agricultural products based on appearance image data, the category information including the type information and variety information of agricultural products; and query quality fingerprint data from a preset quality database based on the category information, the preset quality database storing different categories of agricultural products and their corresponding quality fingerprint data.

[0096] For example, the quality grade determination module can be used to: determine the appearance weight and quality fingerprint weight of the agricultural product based on the category information of the agricultural product, wherein the category information includes the type information and variety information of the agricultural product; determine a first quality score based on the appearance grade data and appearance weight; determine a second quality score based on the quality fingerprint data and quality fingerprint weight; and determine the quality grade information of the agricultural product based on the first quality score and the second quality score.

[0097] For example, the quality grade determination module can be used to: determine the initial appearance weight of agricultural products based on the type information of agricultural products; determine the confidence level fluctuation coefficient of agricultural products based on the variety information of agricultural products; and determine the appearance weight of agricultural products based on the initial appearance weight and the confidence level fluctuation coefficient.

[0098] For example, the quality grade determination module can be used to: determine the initial quality weight of agricultural products based on the type information of agricultural products; determine the timeliness coefficient of quality fingerprint data based on the time information of quality fingerprint data, where the time information is used to characterize the data storage time of quality fingerprint data and the change information of the origin characteristics of agricultural products; and determine the quality fingerprint weight based on the initial quality weight and the timeliness coefficient.

[0099] For example, the grading device may further include a receiving module 34 and a sending module 35. The receiving module 34 is used to receive appearance image data sent by the client; the sending module 35 is used to send the quality grade information of the agricultural product to the client so that the client can generate the quality grading result of the agricultural product based on the quality grade information.

[0100] Another embodiment of this disclosure provides a device for grading the quality of agricultural products, such as... Figure 4 As shown, this grading device can be applied to a client. The grading device includes a guided acquisition module 41, an image evaluation module 42, and a generation module 43.

[0101] The guided acquisition module 41 is used to start the image acquisition module and generate image acquisition guidance instructions based on the type information of agricultural products, so as to acquire the appearance image data of agricultural products. The image acquisition guidance instructions are used to guide the acquisition of appearance image data of agricultural products. The image acquisition guidance instructions include an image frame for representing the image area and lighting prompt information. The image frame is adapted to the appearance shape of the agricultural product.

[0102] The image evaluation module 42 is used to determine whether the appearance image data is qualified by using a preset image evaluation standard; if the appearance image data does not meet the preset image evaluation standard, the image acquisition module is restarted and an image acquisition guidance instruction is generated to re-acquire the appearance image data of the agricultural product; if the appearance image data meets the preset image evaluation standard, the appearance image data is sent to the server so that the server can use the grading method of this embodiment to determine the quality grade information of the agricultural product.

[0103] The generation module 43 is used to receive the quality grade information of agricultural products returned by the server and generate the quality grading result of agricultural products based on the quality grade information.

[0104] For example, the guided acquisition module can be used to: in response to an identification instruction, activate the image acquisition module to acquire physical identification images of agricultural products; and obtain identification information of agricultural products based on the physical identification images, the identification information including the type information of agricultural products.

[0105] For example, the image evaluation module is also used to: send identification information to the server at the same time as sending the appearance image data, so that the server can determine the quality fingerprint data of the agricultural product based on the identification information.

[0106] For example, the guided data collection module is also used to: obtain information about the types of agricultural products based on keywords of agricultural product types input by the user.

[0107] One embodiment of this disclosure also provides a grading system for agricultural product quality, such as... Figure 5 As shown, the system includes a client and a server.

[0108] The client, in response to receiving information about the type of agricultural product, initiates the image acquisition module to collect appearance image data of the agricultural product and generates image acquisition guidance instructions. These instructions guide the capturing of appearance image data and include an image frame representing the image area and lighting cues. The image frame is adapted to the shape of the agricultural product. Upon receiving the appearance image data, a preset image evaluation standard is used to determine whether the data is acceptable. If the appearance image data does not meet the preset standard, an instruction to retake the image is generated. If the appearance image data meets the preset standard, it is sent to the server.

[0109] The server is used to determine the appearance grade data of agricultural products based on the appearance image data; obtain the quality fingerprint data of agricultural products, which characterizes the physicochemical indicators of agricultural products, including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics; determine the quality grade information of agricultural products based on the appearance grade data and the quality fingerprint data, and send the quality grade information to the client.

[0110] The client is also used to receive the quality grade information of agricultural products returned by the server, and generate the quality grading results of agricultural products based on the quality grade information.

[0111] refer to Figure 5The client can include an image acquisition module. Image acquisition guidance instructions are integrated into the image acquisition module via AR functionality. Users acquire agricultural product appearance image data through the image acquisition module, guided by these instructions. After evaluation by the image evaluation module, the appearance image data is sent to the server's appearance grade determination module via an HTTP / HTTPS interface. The appearance grade determination module determines the appearance grade of the agricultural product based on the image data. The server's acquisition module acquires the quality fingerprint data of the agricultural product. The data fusion engine (including the quality grade determination module) fuses the appearance grade data and quality fingerprint data to determine the quality grade information of the agricultural product. This quality grade information is then sent to the client's generation module. After generating the quality grading result, the generation module can display the quality grading result on the client's user interface. The server can also output a quality grading report via a RESTful API interface. The quality grading report can be a visual report including quality grade, key indicators, and data traceability.

[0112] In one embodiment, a lightweight model (such as MobileNet Quantized Version) can be deployed on the client side to determine the appearance grade data of agricultural products. The client then sends the appearance grade data to the server. This setup reduces the computational burden on the server.

[0113] According to embodiments of this disclosure, an electronic device is also provided. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the hierarchical method in any embodiment of this disclosure.

[0114] This disclosure also provides a readable storage medium storing a computer program that, when executed by a processor, implements the hierarchical method as described in any embodiment of this disclosure.

[0115] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0119] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0120] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0121] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

Claims

1. A method for grading the quality of agricultural products, characterized in that, include: Based on the appearance image data of the agricultural products, determine the appearance grade data of the agricultural products; Obtain quality fingerprint data of the agricultural product, wherein the quality fingerprint data characterizes the physicochemical indicators of the agricultural product, and the physicochemical indicators include at least one of sugar content, acidity, pesticide residue, and place of origin characteristics; Based on the appearance grade data and the quality fingerprint data, the quality grade information of the agricultural product is determined, and the quality grade information represents the quality grade level of the agricultural product.

2. The method according to claim 1, characterized in that, The acquisition of the quality fingerprint data of the agricultural product includes: Obtain the identification information of the agricultural product; determine the quality fingerprint data based on the identification information, wherein the quality fingerprint data corresponds to the identification information; Alternatively, based on the appearance image data, the category information of the agricultural product can be identified, including the type and variety information of the agricultural product; based on the category information, the quality fingerprint data can be obtained from a preset quality database, which stores different categories of agricultural products and their corresponding quality fingerprint data.

3. The method according to claim 1, characterized in that, The step of determining the quality grade information of the agricultural product based on the appearance grade data and the quality fingerprint data includes: Based on the category information of the agricultural products, the appearance weight and quality fingerprint weight of the agricultural products are determined, wherein the category information includes the type information and variety information of the agricultural products; A first quality score is determined based on the appearance grade data and the appearance weight; A second quality score is determined based on the quality fingerprint data and the quality fingerprint weight; The quality grade information of the agricultural product is determined based on the first quality score and the second quality score.

4. The method according to claim 3, characterized in that, The step of determining the appearance weight of the agricultural product based on its category information includes: Based on the type information of the agricultural products, determine the initial weight of the appearance of the agricultural products; Based on the variety information of the agricultural product, determine the confidence level fluctuation coefficient of the agricultural product; The appearance weight of the agricultural product is determined based on the initial appearance weight and the confidence fluctuation coefficient.

5. The method according to claim 3, characterized in that, The step of determining the quality fingerprint weight of the agricultural product based on its type information includes: Based on the type information of the agricultural products, determine the initial quality weight of the agricultural products; Based on the time information of the quality fingerprint data, the timeliness coefficient of the quality fingerprint data is determined, wherein the time information is used to characterize the data storage time of the quality fingerprint data and the change information of the place of origin characteristics of the agricultural product; The quality fingerprint weight is determined based on the initial quality weight and the timeliness coefficient.

6. The method according to any one of claims 1-5, characterized in that, When applied to the server side, the method further includes: The client receives the appearance image data sent by the client. The appearance image data is acquired by the client through the image acquisition module based on the type information of the agricultural product, and under the guidance of the image acquisition guidance instruction. The image acquisition guidance instruction includes an image frame for representing the image area and lighting prompt information. The image frame is adapted to the appearance shape of the agricultural product. The image acquisition guidance instruction is generated by the client based on the type information of the agricultural product. The quality grade information of the agricultural product is sent to the client so that the client can generate a quality grading result of the agricultural product based on the quality grade information.

7. A method for grading the quality of agricultural products, characterized in that, Applied to a client, the method includes: Based on the type information of the agricultural products, the image acquisition module is activated and an image acquisition guidance instruction is generated to acquire the appearance image data of the agricultural products. The image acquisition guidance instruction is used to guide the acquisition of the appearance image data of the agricultural products. The image acquisition guidance instruction includes an image frame for representing the image area and lighting prompt information. The image frame is adapted to the appearance shape of the agricultural products. The appearance image data is judged to be qualified using a preset image evaluation standard. If the appearance image data does not meet the preset image evaluation standard, the image acquisition module is restarted and an image acquisition guidance instruction is generated to re-acquire the appearance image data of the agricultural product; If the appearance image data meets the preset image evaluation criteria, the appearance image data is sent to the server so that the server executes the method of any one of claims 1-6; The system receives the quality grade information of the agricultural product returned by the server and generates a quality grading result of the agricultural product based on the quality grade information.

8. The method according to claim 7, characterized in that, Before activating the image acquisition module and generating image acquisition guidance instructions based on the type information of the agricultural product, the method further includes: In response to an identification command, the image acquisition module is activated to acquire a physical identification image of the agricultural product; based on the physical identification image, the identification information of the agricultural product is obtained, including the type information of the agricultural product; Alternatively, the type information of the agricultural product can be obtained based on the keywords of the agricultural product type entered by the user.

9. A grading system for agricultural product quality, characterized in that, include: The client is used to activate the image acquisition module and generate image acquisition guidance instructions based on the type information of the agricultural product, so as to acquire the appearance image data of the agricultural product. The image acquisition guidance instructions are used to guide the acquisition of the appearance image data of the agricultural product. The image acquisition guidance instructions include an image frame for representing the image area and lighting prompt information. The image frame is adapted to the appearance shape of the agricultural product. A preset image evaluation standard is used to determine whether the appearance image data is qualified. If the appearance image data does not meet the preset image evaluation standard, the image acquisition module is restarted and an image acquisition guidance instruction is generated to re-acquire the appearance image data of the agricultural product. If the appearance image data meets the preset image evaluation standard, the appearance image data is sent to the server. The server is used to determine the appearance grade data of the agricultural product based on the appearance image data; obtain the quality fingerprint data of the agricultural product, the quality fingerprint data representing the physicochemical indicators of the agricultural product, the physicochemical indicators including at least one of sugar content, acidity, pesticide residue, and place of origin characteristics; determine the quality grade information of the agricultural product based on the appearance grade data and the quality fingerprint data, and send the quality grade information to the client. The client is also configured to receive the quality grade information of the agricultural product returned by the server, and generate the quality grading result of the agricultural product based on the quality grade information.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images