Intelligent Evaluation Method and System for Jade Quality Based on Deep Learning Reinforced Feature Extraction

Abstract

The present invention discloses an intelligent evaluation method and system for jade quality based on deep learning enhanced feature extraction, which relates to the field of artificial intelligence. The method includes: first, obtaining jade appearance data, importing the obtained data into a target feature distiller in a target enhanced feature extraction path corresponding to each jade type to obtain target appearance distillation information, and then obtaining target jade appearance features through a target feature extractor. The target jade quality grading model is obtained by optimizing a preset jade quality association unit with feature difference degree constraints. Finally, the jade quality level is determined based on the target jade appearance features and the target quality grading path, realizing the intelligent evaluation of jade quality.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and in particular, to an intelligent jade quality evaluation method and system based on deep learning enhanced feature extraction. Background Art

[0002] Currently, the evaluation of jade quality mostly relies on manual experience, with low efficiency and being easily affected by subjective factors. The evaluation results of different appraisers may vary, making it difficult to ensure the accuracy and consistency of the evaluation. With the development of deep learning technology, although it has been applied in some fields, in the aspect of jade quality evaluation, how to effectively use deep learning to extract jade features and accurately evaluate the quality remains a difficult problem. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent jade quality evaluation method and system based on deep learning enhanced feature extraction.

[0004] In the first aspect, an embodiment of the present invention provides an intelligent jade quality evaluation method based on deep learning enhanced feature extraction, including:

[0005] Obtain jade appearance data;

[0006] Import the jade appearance data into the target feature distiller in the target enhanced feature extraction path corresponding to each jade type for feature distillation operation to obtain the target appearance distillation information corresponding to each jade type;

[0007] Import the target appearance distillation information corresponding to each jade type into the target feature extractor in the target enhanced feature extraction path corresponding to each jade type for feature extraction to obtain the target jade appearance features corresponding to each jade type; the target jade quality grading model is obtained by optimizing the preset jade quality association unit in the preset enhanced feature extraction path according to the feature difference degree constraint, and the feature difference degree constraint is used to quantify the relevance of the target jade quality association features, and the target jade quality association features are the jade quality association features generated by the preset jade quality association units corresponding to different jade types;

[0008] Determine the target jade quality grade corresponding to the jade appearance data according to the target jade appearance features corresponding to each jade type and the target quality grading path corresponding to each jade type.

[0009] In the second aspect, an embodiment of the present invention provides a server system, including a server, and the server is used to execute the method in the first aspect.

[0010] Compared with the prior art, the beneficial effects provided by the present invention include: adopting an intelligent jade quality evaluation method and system based on deep learning enhanced feature extraction disclosed by the present invention, obtaining jade appearance data, importing the obtained target appearance distillation information into the target feature distiller in the target enhanced feature extraction path corresponding to each jade type, and then obtaining the target jade appearance features through the target feature extractor. The target jade quality grading model is obtained by optimizing the preset jade quality correlation unit with the feature difference degree constraint. Finally, the jade quality grade is determined according to the target jade appearance features and the target quality grading path, realizing the intelligent evaluation of jade quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic flow chart of the steps of the intelligent jade quality evaluation method based on deep learning enhanced feature extraction provided by the embodiment of the present invention;

[0013] Figure 2 It is a schematic block diagram of the structure of the computer device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0015] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings.

[0016] To solve the technical problems in the foregoing background art, Figure 1 It is a schematic flow chart of the intelligent jade quality evaluation method based on deep learning enhanced feature extraction provided by the embodiment of the present disclosure. The intelligent jade quality evaluation method based on deep learning enhanced feature extraction will be introduced in detail below.

[0017] Step S201, obtain jade appearance data;

[0018] Step S202: Import the jade appearance data into the target feature distiller in the target enhanced feature extraction path corresponding to each jade type for feature distillation operation to obtain the target appearance distillation information corresponding to each jade type;

[0019] Step S203: Import the target appearance distillation information corresponding to each jade type into the target feature extractor in the target enhanced feature extraction path corresponding to each jade type for feature extraction to obtain the target jade appearance features corresponding to each jade type; the target jade quality grading model is obtained by optimizing the preset jade quality association unit in the preset enhanced feature extraction path according to the feature difference degree constraint, the feature difference degree constraint is used to quantify the relevance of the target jade quality association features, and the target jade quality association features are the jade quality association features generated by the preset jade quality association units corresponding to different jade types;

[0020] Step S204: Determine the target jade quality grade corresponding to the jade appearance data according to the target jade appearance features corresponding to each jade type and the target quality grading path corresponding to each jade type.

[0021] In an embodiment of the present invention, exemplarily, the server is connected to high-definition camera devices in the market. When a merchant places a piece of jade on a specific shooting area, the camera will take an all-round shot of the jade according to preset parameters, such as appropriate lighting conditions, shooting angles, and resolutions. After the shooting is completed, the image data containing the appearance information of the jade, such as color, texture, and shape, is transmitted to the server in the form of digital signals. For example, a Hetian jade is placed in the shooting area, and the camera takes multiple clear pictures from different sides. These picture data are quickly transmitted to the server and become the jade appearance data to be processed. The server has pre-stored the extraction paths of target enhanced features corresponding to various jade types. Taking jadeite as an example, the server will accurately import the just-obtained jade appearance data into the target feature distiller in the target enhanced feature extraction path corresponding to jadeite. This target feature distiller is like a knowledge refining factory. It will perform complex mathematical operations and feature screening on the input jade appearance data. It will extract key and representative feature information from the jade appearance data, integrate and refine this information, and remove redundant parts. After a series of operations, the target appearance distillation information corresponding to the jade type of jadeite is obtained. For example, the target feature distiller extracts key features related to the vividness of the jadeite color and the uniqueness of the texture from the jade appearance data to form the target appearance distillation information. For jadeite, the server then imports its target appearance distillation information into the target feature extractor in the target enhanced feature extraction path corresponding to this jade type. Multiple functional units inside the target feature extractor work together. Suppose the first feature focusing unit in the target feature extractor. It will focus on some key features of the target appearance distillation information like a magnifying glass, perform feature focusing operations, highlight the features closely related to the quality of jadeite, and obtain the first focused feature map. Then, the first focused feature map and the target appearance distillation information are imported into the first feature recombination unit. This recombination unit will recombine these features in a more reasonable way like a puzzle master to obtain the first intermediate feature data. At the same time, the first focused feature map and the target appearance distillation information are also imported into the preset jade quality association unit for feature calibration operations to obtain the first jade quality association feature. Finally, the first intermediate feature data, the first jade quality association feature, the first focused feature map, and the target appearance distillation information are all sent to the first feature aggregation node, where feature aggregation operations are performed to aggregate all relevant features together, and finally the target jade appearance features corresponding to jadeite are obtained. These target jade appearance features contain various key information that can accurately reflect the quality of jadeite. The target jade quality grading model here is obtained by the server previously optimizing the preset jade quality association unit in the preset enhanced feature extraction path according to the feature difference degree constraint.For example, during the training phase, the server compared the jade quality correlation features generated by the preset jade quality correlation units corresponding to two types of jade, namely jadeite and Hetian jade, quantified the correlation between them, and obtained the feature difference degree constraint. Through this constraint, the preset jade quality correlation unit was adjusted and optimized to obtain the target jade quality grading model. The server imported the target jade appearance features corresponding to jadeite into the target quality grading path corresponding to jadeite. This target quality grading path is like an experienced appraiser. It will make a quality inference based on the input target jade appearance features. Through the internally preset algorithms and models, these features are analyzed and judged to obtain the first jade quality inference value of jadeite. Similarly, for other types of jade, the server will perform similar operations to obtain their respective first jade quality inference values. Then, the server will comprehensively determine the target jade quality level corresponding to the jade appearance data based on the first jade quality inference values respectively configured for multiple types of jade. For example, for a piece of jade appearance data, the server analyzes it under the paths of different types of jade (such as jadeite, Hetian jade, Xiu jade, etc.) and obtains the first jade quality inference values corresponding to each type. Then, the server will determine the target jade quality level of this piece of jade according to the comprehensive situation of these inference values, such as high quality, medium quality, or low quality. In addition, the server will also import the jade appearance data into the target dynamic weight allocator in the target jade quality grading model for weight optimization allocation to obtain the target feature contribution degree parameter. According to this target feature contribution degree parameter, the server performs an adaptive synthesis operation on the first jade quality inference values respectively configured for multiple types of jade to obtain the second jade quality inference value corresponding to the jade appearance data. Finally, based on this second jade quality inference value, the server more accurately determines the target jade quality level. For example, if the target feature contribution degree parameter indicates that the jadeite feature is more important for the evaluation of this jade quality, the server will assign a higher weight to the first jade quality inference value corresponding to jadeite during the synthesis operation, so as to obtain a more accurate second jade quality inference value, and then determine a more accurate target jade quality level.

[0022] In the embodiment of the present invention, the target jade quality grading model is trained through the following process and can be implemented through the following examples.

[0023] Obtain the first preset jade appearance data set;

[0024] Import the first preset jade appearance data set into the preset enhanced feature extraction paths respectively configured for multiple types of jade in the initial integration model for feature extraction operations to obtain the preset jade quality correlation features corresponding to each type of jade;

[0025] Combining the corresponding preset jade quality correlation features according to the target jade type combination, determining the feature difference degree constraint corresponding to the target jade type combination; the target jade type combination is any two types among the multiple jade types;

[0026] Training the preset jade quality correlation unit corresponding to the target jade type combination according to the feature difference degree constraint corresponding to the target jade type combination to obtain the target jade quality grading model.

[0027] In an embodiment of the present invention, illustratively, the server establishes connections with multiple data sources such as jade identification institutions, major jade trading markets and jade processing plants. These data sources collect and organize a large amount of jade appearance data of different types and qualities, covering jade images under various shooting angles and lighting conditions. For example, the data source provides Hetian jade appearance images from place A, jadeite raw stones and finished products from place B, Xiuyan jade pictures from place C, etc. The server integrates these jade appearance data to form a first preset jade appearance data set, providing a rich data basis for subsequent model training. The initial integrated model in the server sets respective preset enhanced feature extraction paths for different types of jade. Taking jadeite and Hetian jade as examples, the server imports the relevant data in the first preset jade appearance data set into the preset enhanced feature extraction paths corresponding to jadeite and Hetian jade, respectively. Assuming that the preset feature distiller in the preset enhanced feature extraction path of jadeite will perform feature extraction on the input jadeite appearance data to obtain preset appearance distillation information. Then, this information enters the first feature focusing unit, focusing on key features to generate a first focused feature map. The graph and the preset appearance distillation information are reorganized in the first feature reorganizer to obtain the first intermediate feature data. At the same time, they are subjected to feature calibration calculation in the preset jade quality association unit to generate the first jade quality association feature. Finally, the preset jade quality association feature corresponding to jadeite is obtained through the first feature aggregation node calculation. Hetian jade also obtains its corresponding preset jade quality association feature according to this process. The server selects any two types from multiple jade types as the target jade type combination, such as jadeite and Hetian jade. It compares the preset jade quality association features corresponding to the two jades, such as the color brightness and crystal structure characteristics of jadeite with the warmth and texture fineness characteristics of Hetian jade. The degree of difference between these features is calculated through a complex algorithm, and their correlation is quantified, so as to determine the feature difference constraint corresponding to the target jade type combination of jadeite and Hetian jade. This constraint value reflects the difference between the two in quality association features. According to the feature difference constraint corresponding to the target jade type combination of jadeite and Hetian jade, the server adjusts and optimizes the preset jade quality association unit in the preset enhanced feature extraction path of each of the two jades. During the training process, the server continuously adjusts the parameters of the preset jade quality association unit so that the model can better distinguish and understand the differences in quality association characteristics of different jade types. After multiple rounds of training, when the model is able to accurately reflect these differences when processing the characteristics of different jade types, the server obtains the target jade quality grading model, which will be used to accurately assess the quality grade of jade in the future.

[0028] In an embodiment of the present invention, the preset enhanced feature extraction path corresponding to each jade type includes a preset feature distiller and a preset feature extractor. The preset feature extractor includes a first feature focusing unit, a first feature reorganizer, a preset jade quality association unit, and a first feature aggregation node; the operation of importing the first preset jade appearance dataset into the preset enhanced feature extraction paths respectively configured for the multiple jade types in the initial integrated model to extract features, so as to obtain the preset jade quality association features corresponding to each jade type, can be implemented through the following examples.

[0029] Import the first preset jade appearance dataset into the preset feature distiller corresponding to each jade type to perform feature distillation operation, so as to obtain the preset appearance distillation information corresponding to each jade type;

[0030] Import the preset appearance distillation information corresponding to each jade type into the first feature focusing unit corresponding to each jade type to perform feature focusing operation, so as to obtain the first focused feature map corresponding to each jade type;

[0031] Import the first focused feature map corresponding to each jade type and the preset appearance distillation information corresponding to each jade type into the first feature reorganizer corresponding to each jade type to perform feature reorganization operation, so as to obtain the first intermediate feature data corresponding to each jade type;

[0032] Import the first focused feature map corresponding to each jade type and the preset appearance distillation information corresponding to each jade type into the preset jade quality association unit corresponding to each jade type to perform feature calibration operation, so as to obtain the first jade quality association feature corresponding to each jade type;

[0033] Import the first intermediate feature data corresponding to each jade type, the first jade quality association feature corresponding to each jade type, the first focused feature map corresponding to each jade type, and the preset appearance distillation information corresponding to each jade type into the first feature aggregation node corresponding to each jade type to perform feature aggregation operation, so as to obtain the second intermediate feature data corresponding to each jade type.

[0034] In an embodiment of the present invention, exemplarily, the server obtains a first preset jade appearance data set containing multiple jade appearance data, which contains appearance images of jades such as jadeite and Hetian jade. Taking jadeite as an example, the server imports the jadeite appearance data in the data set into the preset feature distiller corresponding to jadeite. This preset feature distiller is like a filter, which screens and refines a large amount of jadeite appearance data. It identifies key features closely related to the quality of jadeite, such as the unique emerald green tone, fiber interweaving structure, etc., removes irrelevant information, such as minor flaws in the shooting background, and finally generates the preset appearance distillation information corresponding to jadeite. Similarly, for the Hetian jade appearance data in the data set, the server will also import it into the preset feature distiller corresponding to Hetian jade, extract the key features of Hetian jade, such as mutton-like whiteness, delicate texture, etc., to form the preset appearance distillation information of Hetian jade. The server imports the preset appearance distillation information of jadeite into the first feature focusing unit corresponding to jadeite. This unit is like a magnifying glass, which further focuses on the key features in the preset appearance distillation information. For example, it focuses on the core features of jadeite, such as the brightness of its color and the change of its transparency, and presents it in a visual atlas form to generate the first focused feature atlas of jadeite, making the key quality features of jadeite clearer and more specific. For Hetian jade, the first feature focusing unit focuses on the subtle differences in its warmth and moisture, the density of its texture, and other features to form the first focused feature atlas of Hetian jade, highlighting the unique quality characteristics of Hetian jade. The server inputs the first focused feature atlas of jadeite and the preset appearance distillation information into the first feature reorganizer corresponding to jadeite. The first feature reorganizer is like a puzzle master. It recombines these two types of information in a new and more logical way according to preset rules and algorithms. For example, the color features and structural features of jadeite are rearranged and combined according to the weights of their impact on quality to obtain the first intermediate feature data of jadeite. This data form is more conducive to the subsequent in-depth analysis of jadeite quality. Similarly, the first focused feature atlas of Hetian jade and the preset appearance distillation information are reorganized in the first feature reorganizer corresponding to Hetian jade to generate the first intermediate feature data of Hetian jade. For jadeite, the server imports its first focused feature atlas and preset appearance distillation information into the preset jade quality association unit. This unit is like a calibrator, which performs calibration operations on these two types of information. It calibrates the characteristics of jadeite based on the existing jadeite quality standards and a large amount of sample data, such as calibrating the correspondence between jadeite color and quality grade, to ensure the accuracy and reliability of the characteristics, thereby obtaining the first jade quality-related characteristics of jadeite, accurately reflecting the quality-related information of jadeite. Hetian jade also calibrates the characteristics in its preset jade quality-related unit through the same operation to generate the first jade quality-related characteristics of Hetian jade. The server inputs all the first intermediate feature data, first jade quality-related features, first focused feature maps, and preset appearance distillation information of jadeite into the first feature aggregation node corresponding to jadeite.This node acts as a fusion center, comprehensively integrating the feature information obtained from these different stages. Through complex aggregation operations, the quality characteristics of various aspects of jadeite are fused together to form a comprehensive and more representative second intermediate feature data, laying a foundation for accurately evaluating the quality of jadeite subsequently. Similarly, the relevant feature information of Hetian jade is aggregated in the first feature aggregation node corresponding to Hetian jade to obtain the second intermediate feature data of Hetian jade.

[0035] In the embodiments of the present invention, the following implementation manners are also provided.

[0036] Obtain the first jade quality target value corresponding to each preset jade appearance data in the first preset jade appearance data set;

[0037] Import the second intermediate feature data corresponding to each jade type into the preset quality grading path corresponding to each jade type in the initial integration model for quality inference, and obtain the third jade quality inference value corresponding to each jade type;

[0038] Import the first preset jade appearance data set into the preset dynamic weight allocator in the initial integration model for weight optimization and allocation, and obtain the preset feature contribution degree parameter corresponding to each preset jade appearance data in the first preset jade appearance data set;

[0039] According to the preset feature contribution degree parameter, perform an adaptive synthesis operation on the third jade quality inference values respectively configured for the multiple jade types to obtain the fourth jade quality inference value corresponding to each preset jade appearance data in the first preset jade appearance data set;

[0040] Determine the first fusion consistency error according to the fourth jade quality inference value and the first jade quality target value;

[0041] The training of the preset jade quality association unit corresponding to the target jade type combination according to the feature difference degree constraint corresponding to the target jade type combination to obtain the target jade quality grading model includes:

[0042] Train the preset jade quality association unit corresponding to the target jade type combination according to the feature difference degree constraint corresponding to the target jade type combination, and train the preset dynamic weight allocator according to the first fusion consistency error to obtain the target jade quality grading model.

[0043] In an embodiment of the present invention, exemplarily, the server obtains the accurate quality evaluation result corresponding to each piece of jade in the first preset jade appearance dataset from an authoritative jade appraisal institution, that is, the first jade quality target value. For example, there is the appearance data of a piece of jadeite in the dataset. According to industry standards, the appraisal institution evaluates this jadeite as "high-grade quality", and this "high-grade quality" is the first jade quality target value corresponding to the appearance data of this piece of jadeite. For the appearance data of other jades such as Hetian jade and Xiuyu in the dataset, there are also corresponding quality target values appraised by the authority, and these values provide an accurate reference basis for subsequent model training. The server inputs the second intermediate feature data of the jadeite obtained through the previous steps into the preset quality grading path corresponding to the jadeite in the initial integrated model. This preset quality grading path is like a "simulated appraiser", which analyzes and judges the second intermediate feature data of the jadeite according to the internally set algorithms and rules, so as to infer the quality grade of this piece of jadeite and obtain the third jade quality inference value. For example, it is inferred that this jadeite is "medium-high grade". Similarly, the server imports the second intermediate feature data of Hetian jade into the preset quality grading path corresponding to Hetian jade, and obtains the third jade quality inference value of Hetian jade, such as "medium quality". The server inputs the entire first preset jade appearance dataset into the preset dynamic weight allocator in the initial integrated model. This allocator will analyze the importance of different jade types and different features in the dataset for quality evaluation. For example, for jadeite, the color feature has a greater impact on quality, followed by the transparency feature, and then the texture feature. The preset dynamic weight allocator assigns different weights to each feature of each piece of jade according to this difference in importance, and obtains the preset feature contribution degree parameter corresponding to each piece of preset jade appearance data. For a specific piece of jadeite appearance data, the color feature may be assigned a weight of 0.5, the transparency feature is assigned a weight of 0.3, and the texture feature is assigned a weight of 0.2. These weight values are part of the preset feature contribution degree parameter of this jadeite. The server comprehensively considers the third jade quality inference values of different jade types according to the preset feature contribution degree parameter obtained above. For example, for a piece of jade appearance data that involves the characteristics of both jadeite and Hetian jade, the third jade quality inference value of jadeite is "medium-high grade", and that of Hetian jade is "medium quality". Combining their respective preset feature contribution degree parameters, such as the higher weight of jadeite features, the server performs an adaptive synthesis operation through a specific algorithm to fuse the inference values of the two, and obtains a more comprehensive fourth jade quality inference value, such as "medium-high grade tending to high-grade", which more comprehensively reflects the quality of this piece of jade. The server compares the fourth jade quality inference value of each piece of preset jade appearance data with the first jade quality target value obtained from the appraisal institution. For example, the fourth jade quality inference value of a certain piece of jade is "medium-high grade tending to high-grade", while its first jade quality target value is "high-grade quality". The server determines the first fusion consistency error by calculating the difference degree between the two.This error reflects the deviation magnitude between the current model inference result and the actual quality target value. Taking the target jade type combination of jadeite and Hetian jade as an example, the server adjusts the parameters and optimizes the training of the preset jade quality association units in the preset enhanced feature extraction paths respectively configured for jadeite and Hetian jade according to the previously determined constraint of their corresponding feature difference degrees, so that the model can better capture the differences in the quality features of the two. At the same time, the preset dynamic weight allocator is also trained according to the first fusion consistency error. For example, if it is found that the weight allocation of a certain feature is unreasonable and causes a large error, the weight of this feature is adjusted. After repeated training, when the error between the model inference result and the actual quality target value is within an acceptable range, the server obtains the target jade quality grading model, which is more accurate and reliable in jade quality assessment.

[0044] In the embodiment of the present invention, the preset enhanced feature extraction path corresponding to each jade type includes a preset feature distiller and a preset feature extractor. The preset feature extractor includes a second feature focusing unit, a second feature reorganizer, a preset jade quality association unit, and a second feature aggregation node. The preset jade quality association unit includes a first preset quality association subunit and a second preset quality association subunit; The operation of extracting features from the first preset jade appearance dataset by importing it into the preset enhanced feature extraction paths respectively configured for the multiple jade types in the initial integration model to obtain the preset jade quality association features corresponding to each jade type can be implemented through the following examples.

[0045] Import the first preset jade appearance dataset into the preset feature distiller corresponding to each jade type for feature distillation operation to obtain the preset appearance distillation information corresponding to each jade type;

[0046] Import the preset appearance distillation information corresponding to each jade type into the second feature focusing unit corresponding to each jade type for feature focusing operation to obtain the second focusing feature map corresponding to each jade type;

[0047] Import the second focusing feature map corresponding to each jade type into the first preset quality association subunit corresponding to each jade type for feature calibration operation to obtain the second jade quality association feature corresponding to each jade type;

[0048] Import the second jade quality association feature corresponding to each jade type and the preset appearance distillation information corresponding to each jade type into the second feature reorganizer corresponding to each jade type for feature reorganization operation to obtain the third intermediate feature data corresponding to each jade type;

[0049] Import the third intermediate feature data corresponding to each jade type into the second preset quality correlation subunit corresponding to each jade type for feature calibration operation to obtain the third jade quality correlation feature corresponding to each jade type;

[0050] Import the third jade quality correlation feature corresponding to each jade type, the second jade quality correlation feature corresponding to each jade type, and the preset appearance distillation information corresponding to each jade type into the second feature aggregation node corresponding to each jade type for feature aggregation operation to obtain the fourth intermediate feature data corresponding to each jade type.

[0051] In an embodiment of the present invention, exemplarily, the server has a first preset jade appearance data set containing multiple jade appearance data, which includes various types of jade such as jadeite and Xiuyan jade. Taking Xiuyan jade as an example, the server imports the appearance data of Xiuyan jade in the data set into the preset feature distiller corresponding to Xiuyan jade. The preset feature distiller is like an information screening refinery, which carefully combs the appearance data of Xiuyan jade. It identifies and extracts the unique color features of Xiuyan jade, such as common green and yellow tones, and key information such as unique texture features, while removing some interference information generated during the shooting process, such as tiny light spots, visual deviations caused by shooting angles, etc., and finally generates the preset appearance distillation information corresponding to Xiuyan jade. Similarly, for the jadeite appearance data in the data set, the server also imports it into the preset feature distiller corresponding to jadeite, extracts the key features of jadeite's unique jadeite and glass luster, and forms the preset appearance distillation information of jadeite. The server transmits the preset appearance distillation information of Xiuyan jade to the second feature focusing unit corresponding to Xiuyan jade. This unit is like a precise magnifying glass, which further focuses and strengthens the key features in the preset appearance distillation information. For example, it emphasizes the core features of Xiuyu jade, such as the uniformity of color and the direction of texture, and presents them in the form of a map, generating the second focused feature map of Xiuyu jade, making the key features related to quality of Xiuyu jade more intuitive and prominent. For jadeite, the second feature focusing unit focuses on the hierarchical changes in the transparency of jadeite, the distribution characteristics of crystal particles, etc., forming the second focused feature map of jadeite, and clearly showing the key characteristics of jadeite that affect quality. The server inputs the second focused feature map of Xiuyu jade into the first preset quality association subunit corresponding to Xiuyu jade. This subunit is similar to a calibration instrument, which calibrates the characteristics of Xiuyu jade according to the relevant standards of Xiuyu jade quality and a large amount of sample data. For example, it calibrates the correspondence between the color of Xiuyu jade and the quality grade, ensures the accuracy of the association between the feature and the actual quality, and thus obtains the second jade quality association feature of Xiuyu jade, which can accurately reflect the characteristics of Xiuyu jade related to quality. Similarly, for jadeite, the first preset quality association subunit calibrates the jadeite features according to the jadeite quality standard, and generates the second jadeite quality association feature of jadeite. The server sends the second jade quality-related features and preset appearance distillation information of Xiuyu jade to the second feature recombiner corresponding to Xiuyu jade. The second feature recombiner is like an experienced jigsaw puzzle master, recombining the two types of information according to specific rules and algorithms. It may rearrange and integrate the color features, texture features and calibrated quality-related features of Xiuyu jade according to the weights of the factors affecting the quality of Xiuyu jade to obtain the third intermediate feature data of Xiuyu jade. This data form is more conducive to the subsequent in-depth analysis of the quality of Xiuyu jade. Similarly, the relevant information of jadeite is reorganized in the second feature recombiner corresponding to jadeite to generate the third intermediate feature data of jadeite. The server inputs the third intermediate feature data of Xiuyu jade into the second preset quality-related subunit corresponding to Xiuyu jade.This sub-unit calibrates the features again. From another perspective or a more detailed level, according to the quality standard of Xiuyu jade, it calibrates the features of Xiuyu jade again. For example, it further calibrates the subtle relationship between the texture of Xiuyu jade and its quality, making the correlation between the obtained features and the actual quality more accurate, so as to obtain the third jade quality correlation feature of Xiuyu jade. Similarly, the third intermediate feature data of jadeite is calibrated and calculated in the second preset quality correlation sub-unit corresponding to jadeite to generate the third jade quality correlation feature of jadeite. The server inputs all the third jade quality correlation feature of Xiuyu jade, the second jade quality correlation feature, and the preset appearance distillation information into the second feature aggregation node corresponding to Xiuyu jade. This node is like a fusion center. Through complex aggregation operations, it comprehensively integrates various quality-related features obtained in different stages of Xiuyu jade. It fuses features such as the color, texture, and calibrated quality correlation of Xiuyu jade together to form a more comprehensive and representative fourth intermediate feature data, providing more powerful data support for accurately evaluating the quality of Xiuyu jade. Similarly, the relevant features of jadeite are aggregated and calculated in the second feature aggregation node corresponding to jadeite to obtain the fourth intermediate feature data of jadeite.

[0052] In the embodiments of the present invention, the following implementation manners are also provided.

[0053] Obtain the first jade quality target value corresponding to each preset jade appearance data in the first preset jade appearance data set;

[0054] Import the fourth intermediate feature data corresponding to each jade type into the preset quality grading path corresponding to each jade type in the initial integration model for quality inference to obtain the fifth jade quality inference value corresponding to each jade type;

[0055] Import the first preset jade appearance data set into the preset dynamic weight allocator in the initial integration model for weight optimization and allocation to obtain the preset feature contribution degree parameter corresponding to each preset jade appearance data in the first preset jade appearance data set;

[0056] According to the preset feature contribution degree parameter, perform an adaptive synthesis operation on the fifth jade quality inference values respectively configured for the multiple jade types to obtain the sixth jade quality inference value corresponding to each preset jade appearance data in the first preset jade appearance data set;

[0057] Determine the second fusion consistency error according to the sixth jade quality inference value and the first jade quality target value;

[0058] The training of the preset jade quality correlation unit corresponding to the target jade type combination according to the feature difference degree constraint corresponding to the target jade type combination to obtain the target jade quality grading model includes:

[0059] According to the corresponding characteristic difference degree constraint of the target jade species combination, train the preset jade quality correlation unit corresponding to the target jade species combination, and train the preset dynamic weight allocator according to the second fusion consistency error to obtain the target jade quality grading model.

[0060] In an embodiment of the present invention, exemplarily, the server cooperates with a professional jade appraisal laboratory to obtain the authoritative quality evaluation results of each piece of jade in the first preset jade appearance dataset, that is, the first jade quality target value. For example, there is an appearance data of a jadeite raw stone from place B in the dataset. The appraisal laboratory comprehensively considers various aspects such as color, transparency, and texture according to the unified quality appraisal standard in the industry, and appraises this jadeite raw stone as "superior quality". This "superior quality" is the first jade quality target value corresponding to the appearance data of this jadeite raw stone. For the appearance data of many different types of jade in the dataset, such as Hetian jade and Xiu jade, there are also corresponding accurate quality appraisals as the first jade quality target values, providing a reliable reference benchmark for subsequent model training. The server inputs the fourth intermediate feature data of the jadeite obtained through the previous complex process into the preset quality grading path corresponding to the jadeite in the initial integrated model. This preset quality grading path is like an experienced "virtual appraiser", which deeply analyzes the fourth intermediate feature data of the jadeite according to the internally set algorithms and rules. It will consider various features such as the richness of the color and the density of the crystal structure in the fourth intermediate feature data of the jadeite, and then infer the quality grade of this jadeite, obtaining the fifth jade quality inference value. For example, it is inferred that this jadeite is "first-class quality". Similarly, the server imports the fourth intermediate feature data of Xiu jade into the preset quality grading path corresponding to Xiu jade, and combines the unique features of Xiu jade, such as the softness of the color and the fineness of the texture, to obtain the fifth jade quality inference value of Xiu jade, such as "second-class quality". The server transports the entire first preset jade appearance dataset to the preset dynamic weight allocator in the initial integrated model. This allocator will carefully analyze the importance of various features of different types of jade in the dataset for quality evaluation. For example, for jadeite, color occupies a relatively large proportion in quality evaluation, followed by transparency, and then the impurity content. The preset dynamic weight allocator assigns corresponding weights to each feature of the preset jade appearance data of each piece of jadeite according to this difference in importance, obtaining the preset feature contribution degree parameter corresponding to each piece of jadeite. Suppose for a certain piece of jadeite appearance data, the color feature is assigned a weight of 0.6, the transparency feature is assigned a weight of 0.3, and the impurity content feature is assigned a weight of 0.1. These weight values constitute the preset feature contribution degree parameter of this jadeite. For other types of jade, such as Hetian jade and Xiu jade, the preset dynamic weight allocator will also assign corresponding preset feature contribution degree parameters according to the influence degree of their respective features on quality. The server comprehensively processes the fifth jade quality inference values of different types of jade according to the preset feature contribution degree parameters obtained previously. For example, for an appearance data of a jade that combines some features of jadeite and Xiu jade, the fifth jade quality inference value of jadeite is "first-class quality", and that of Xiu jade is "second-class quality".Combined with their respective preset feature contribution degree parameters, since the jadeite features have a relatively high weight in the quality evaluation of this piece of jade, the server performs an adaptive synthesis operation through a specific algorithm to organically fuse the inference values of the two, obtaining a sixth jade quality inference value that is more in line with the actual situation, such as "first-class quality tending towards special-class quality". This value more comprehensively and accurately reflects the quality status of the jade. The server carefully compares the sixth jade quality inference value of each preset jade appearance data with the first jade quality target value obtained from the appraisal laboratory. For example, the sixth jade quality inference value of a certain piece of jade is "first-class quality tending towards special-class quality", while its first jade quality target value is "special-class quality". The server uses a special calculation method to measure the degree of difference between the two, thereby determining the second fusion consistency error. This error intuitively reflects the deviation between the current model inference result and the actual quality target value, providing a key basis for subsequent model optimization. Taking the target jade type combination of jadeite and serpentine jade as an example, based on the previously determined characteristic difference degree constraints corresponding to them, the server conducts targeted parameter adjustment and optimization training on the preset jade quality association units in the preset enhanced feature extraction paths of jadeite and serpentine jade respectively. This enables the model to more sensitively capture the differences in quality characteristics between jadeite and serpentine jade. At the same time, according to the second fusion consistency error, the preset dynamic weight allocator is also trained. For example, if it is found that the weight allocation of a certain feature is unreasonable, resulting in a large error between the inference value and the target value, the server will adjust the weight of this feature. After repeated training and optimization, when the error between the model's inference result and the actual quality target value is reduced to an acceptable range, the server successfully obtains the target jade quality grading model, which will be more accurate and reliable in jade quality evaluation.

[0061] In the embodiments of the present invention, the following implementation manners are also provided.

[0062] Obtain a second preset jade appearance data set and the second jade quality target value corresponding to each preset jade appearance data in the second preset jade appearance data set;

[0063] Import the second preset jade appearance data set into the preset enhanced feature extraction paths respectively configured for the multiple jade types in the initial integration model to perform feature extraction operations, and obtain the fifth intermediate feature data corresponding to each jade type;

[0064] Import the fifth intermediate feature data corresponding to each jade type into the preset quality grading path corresponding to each jade type to perform quality inference, and obtain the seventh jade quality inference value corresponding to each jade type;

[0065] Determine the sub-item quality error corresponding to each jade type according to the seventh jade quality inference value corresponding to each jade type and the second jade quality target value;

[0066] Training the preset jade quality correlation unit corresponding to the target jade type combination according to the corresponding characteristic difference degree constraint to obtain the target jade quality grading model includes:

[0067] Training the preset jade quality correlation unit corresponding to the target jade type combination according to the corresponding characteristic difference degree constraint, and training the preset model core component corresponding to each jade type in the initial integrated model according to the sub-quality error corresponding to each jade type to obtain the target jade quality grading model; the preset model core component corresponding to each jade type is the feature processing architecture in the preset enhanced feature extraction path corresponding to each jade type except the preset jade quality correlation unit corresponding to each jade type.

[0068] In an embodiment of the present invention, exemplarily, the server collects data from detection institutions in multiple jade-producing areas to form a second preset jade appearance dataset. This data includes jade appearance information of different origins and qualities, such as Huanglong jade from place D, jasper from place E, etc. At the same time, the detection institution will conduct a professional assessment on each piece of jade and give the corresponding second jade quality target value. For example, a piece of Huanglong jade is rated as "high quality", and this "high quality" is the second jade quality target value corresponding to the preset jade appearance data of this Huanglong jade. Each piece of jade has such a quality target value based on professional standards, providing a reference for subsequent model training. Taking Huanglong jade as an example, the server imports the relevant data of Huanglong jade in the second preset jade appearance dataset into the preset enhanced feature extraction path corresponding to Huanglong jade. The preset feature distiller first screens and refines the Huanglong jade appearance data, extracts key information such as unique yellow hues and stone pattern distributions, and obtains the preset appearance distilled information. Then, this information enters the second feature focusing unit to further highlight features such as the saturation of the Huanglong jade color and the clarity of the texture, generating the second focused feature map. The map enters the first preset quality association sub-unit to calibrate the features, obtaining the second jade quality association features. These features are recombined with the preset appearance distilled information in the second feature recombinator to form the third intermediate feature data. The third intermediate feature data is further calibrated by the second preset quality association sub-unit to obtain the third jade quality association features. Finally, the third jade quality association features, the second jade quality association features, and the preset appearance distilled information are aggregated at the second feature aggregation node to obtain the fifth intermediate feature data corresponding to Huanglong jade. Other jade types such as jasper from place E also obtain their respective fifth intermediate feature data according to a similar process. The server inputs the fifth intermediate feature data of Huanglong jade into the preset quality grading path corresponding to Huanglong jade. This path comprehensively analyzes features such as color, texture, and transparency in the fifth intermediate feature data of Huanglong jade according to internal algorithms, infers the quality grade of Huanglong jade, and obtains the seventh jade quality inference value, such as "medium to high quality". Similarly, for jasper from place E, the server imports its fifth intermediate feature data into the corresponding preset quality grading path, combines the characteristics of jasper, such as color uniformity and black dot distribution, and obtains the seventh jade quality inference value of jasper from place E, such as "medium quality". For Huanglong jade, the server compares its seventh jade quality inference value "medium to high quality" with the second jade quality target value "high quality". By calculating the difference between the two through a specific algorithm, the sub-item quality error of Huanglong jade is determined, and this error reflects the deviation degree between the model's inference of Huanglong jade quality and the actual quality. Similarly, for jasper from place E, its seventh jade quality inference value "medium quality" is compared with the corresponding second jade quality target value to obtain the sub-item quality error of jasper from place E, thereby measuring the accuracy of the model's inference of different jade qualities.Taking the combination of Huanglong jade and Jasper from Location E as an example of the target jade types, the server trains the respective pre-set jade quality correlation units for Huanglong jade and Jasper from Location E according to the corresponding characteristic difference constraints. At the same time, referring to the respective sub-quality errors of Huanglong jade and Jasper from Location E, the server trains the corresponding pre-set model core components for Huanglong jade and Jasper from Location E in the initial integrated model (i.e., other parts in the pre-set enhanced feature extraction path except the pre-set jade quality correlation unit, such as the pre-set feature distiller, the second feature focusing unit, etc.). For example, if it is found that the extraction of the color feature of Huanglong jade is inaccurate, resulting in a large sub-quality error, the components such as the pre-set feature distiller and the second feature focusing unit of Huanglong jade are adjusted to optimize the extraction of the color feature. After multiple trainings and adjustments, when the accuracy of the model's inference of various jade qualities reaches a satisfactory level, the server obtains the target jade quality grading model.

[0069] In the embodiment of the present invention, the step of determining the target jade quality level corresponding to the jade appearance data according to the target jade appearance feature corresponding to each jade type and the target quality grading path corresponding to each jade type may be implemented through the following examples.

[0070] Import the target jade appearance feature corresponding to each jade type into the target quality grading path corresponding to each jade type for quality inference to obtain the first jade quality inference value corresponding to each jade type;

[0071] Determine the target jade quality level corresponding to the jade appearance data according to the first jade quality inference values respectively configured for the multiple jade types.

[0072] In an embodiment of the present invention, illustratively, the server stores target enhanced feature extraction paths and target quality grading paths corresponding to a variety of jade types. For the jade type of jadeite, the corresponding target jade appearance features have been extracted from the jade appearance data. These features include key information such as the brightness of the jade color, transparency, and fineness of the texture. The server imports these target jade appearance features of jadeite into the target quality grading path corresponding to jadeite. The target quality grading path is like an expert system specifically for jadeite quality assessment, with a series of complex algorithms and rules preset inside. It will conduct a comprehensive and in-depth analysis of the input target jade appearance features. For example, according to the quality assessment standards of the jadeite industry, jadeite with bright and uniform color, high transparency, and fine and flawless texture is usually of higher quality. The target quality grading path quantitatively evaluates and comprehensively considers the various features of jade based on these standards, and finally obtains the first jade quality inference value corresponding to jadeite, such as inferring that if the jade is jadeite, its quality is "medium and high-end". Similarly, for Hetian jade, the server imports the corresponding target jade appearance features, such as the whiteness, warmth, and density of the jade, into the target quality grading path corresponding to Hetian jade. This path gives a higher quality evaluation to Hetian jade with whiteness reaching mutton-fat white, excellent warmth, and dense texture according to the quality assessment rules of Hetian jade, thereby obtaining the first jade quality inference value corresponding to Hetian jade, which is assumed to be "superior quality". For other types of jade such as Xiuyan jade and Dushan jade, the server also follows this process to import their respective target jade appearance features into the corresponding target quality grading path, and obtain the corresponding first jade quality inference value. The server has collected multiple first jade quality inference values ​​for this piece of jade under different types of jade, such as "medium-high-end" for jadeite, "superior quality" for Hetian jade, and "medium quality" for Xiuyan jade. Next, the server needs to combine these inference values ​​to determine the target jade quality grade that the appearance data of this piece of jade ultimately corresponds to. The server will first consider factors such as the general value and recognition of different jade types in the market, and assign a certain weight to the inferred value of each jade type. For example, jadeite and Hetian jade have a higher status in the jade market, and their inferred value weights are relatively large; while Xiuyan jade, Dushan jade, etc. have relatively small weights. Then, the server multiplies the first jade quality inference value of each jade type by its corresponding weight through a specific algorithm and adds them together to obtain a comprehensive value. Finally, the server maps this comprehensive value to the corresponding target jade quality grade according to the pre-set quality grade classification standard. For example, if the comprehensive value falls within a certain range and the corresponding quality grade is "high quality", then the server determines that the target jade quality grade corresponding to the appearance data of this piece of jade is "high quality". In this way, by comprehensively considering the inference results of multiple jade types, the server can more comprehensively and accurately assess the quality grade of jade.

[0073] In an embodiment of the present invention, the following implementation manners are further provided.

[0074] Import the jade appearance data into the target dynamic weight allocator in the target jade quality grading model for weight optimization allocation to obtain target feature contribution degree parameters;

[0075] Determining the target jade quality grade corresponding to the jade appearance data according to the first jade quality inference values respectively configured for the multiple jade types includes:

[0076] Perform an adaptive synthesis operation on the first jade quality inference values respectively configured for the multiple jade types according to the target feature contribution degree parameters to obtain a second jade quality inference value corresponding to the jade appearance data;

[0077] Determine the target jade quality grade according to the second jade quality inference value.

[0078] In an embodiment of the present invention, exemplarily, the server inputs the appearance data of the jade into the target dynamic weight allocator in the target jade quality grading model. This allocator is like an intelligent analysis master, which will deeply analyze the degree of correlation between each feature in the jade appearance data and the quality of different jade types. For example, the unique green color presented by the appearance of jade is highly similar to the emerald green feature of jadeite after analysis, which has a great influence on whether it is high-quality jadeite; and the fineness of the texture of jade not only plays an important role in judging whether it is high-quality Hetian jade, but also has a certain influence on the quality judgment of other types of jade, but the influence is relatively small. Based on this analysis of the correlation between features and the quality of jade types, the target dynamic weight allocator will assign different weights to each feature for different types of jade, so as to obtain the target feature contribution parameter. For example, for jadeite, the color feature weight may be set to 0.6, the texture feature weight to 0.3, and the transparency weight to 0.1; for Hetian jade, the whiteness weight is 0.5, the warmth weight is 0.3, and the texture fineness weight is 0.2, etc. These weight values ​​are the specific embodiment of the target feature contribution parameters, which reflect the relative importance of each feature in the quality assessment of different jade types. The server obtains the first jade quality inference value for this jade under multiple jade types, such as jadeite is inferred as "medium-high", Hetian jade is inferred as "superior quality", Xiuyan jade is inferred as "medium quality", etc. At the same time, the server has obtained the target feature contribution parameters. Next, the server performs adaptive synthesis operations on the first jade quality inference value based on these parameters. Taking jadeite and Hetian jade as examples, since the color feature weight of jadeite is relatively high, it is assumed that the value corresponding to its first jade quality inference value "medium-high" is 80 (setting a value is convenient for calculation and explanation), and the whiteness weight of Hetian jade is relatively high, and the value corresponding to its first jade quality inference value "superior quality" is 90. The server calculates according to the target feature contribution parameter. The weighted value of jadeite is \(80×0.6=48\), the weighted value of Hetian jade is \(90×0.5=45\), and then the weighted values ​​of all jade types are added together. At the same time, the weighted values ​​of other jade types such as Xiuyan jade are considered to obtain a comprehensive weighted value. Then, this comprehensive weighted value is converted into a new value through a specific algorithm. This new value is the second jade quality inference value. For example, after a series of calculations and conversions, the value corresponding to the obtained second jade quality inference value is 85 (this value is only an example). The server pre-sets a set of clear quality grade classification standards. According to this standard, different value ranges correspond to different quality grades. For example, a value of 90-100 corresponds to "special quality", 80-89 corresponds to "high quality", 70-79 corresponds to "intermediate quality", etc.The server compares the obtained second jade quality inference value (such as the numerical value 85) with these standards and finds that this numerical value falls within the range of 80 - 89, thereby determining that the target jade quality level corresponding to the appearance data of this piece of jade is "high quality". In this way, the server synthesizes the inference values of multiple jade types using the target feature contribution degree parameter, and further accurately determines the quality level of the jade.

[0079] In the embodiment of the present invention, the target feature extractor corresponding to each jade type includes a third feature focusing unit, a third feature recombination unit, a target jade quality association unit, and a third feature aggregation node; the step of importing the target appearance distillation information corresponding to each jade type into the target feature extractor in the target enhanced feature extraction path corresponding to each jade type for feature extraction to obtain the target jade appearance feature corresponding to each jade type can be implemented through the following examples.

[0080] Import the target appearance distillation information corresponding to each jade type into the third feature focusing unit corresponding to each jade type for feature focusing operation to obtain the third focused feature map corresponding to each jade type;

[0081] Import the target appearance distillation information corresponding to each jade type and the third focused feature map corresponding to each jade type into the third feature recombination unit corresponding to each jade type for feature recombination operation to obtain the first target quality key feature corresponding to each jade type;

[0082] Import the target appearance distillation information corresponding to each jade type and the third focused feature map corresponding to each jade type into the target jade quality association unit corresponding to each jade type for feature calibration operation to obtain the fourth jade quality association feature corresponding to each jade type;

[0083] Import the fourth jade quality association feature corresponding to each jade type, the first target quality key feature corresponding to each jade type, the target appearance distillation information corresponding to each jade type, and the third focused feature map corresponding to each jade type into the third feature aggregation node corresponding to each jade type for feature aggregation operation to obtain the target jade appearance feature corresponding to each jade type.

[0084] In the embodiment of the present invention, illustratively, taking jade as an example, the server has obtained the target appearance distillation information corresponding to jade, which is the key features after being refined by the target feature distiller, such as the key information of the color, transparency, crystal structure, etc. of jade. The server inputs the target appearance distillation information of jade into the third feature focusing unit corresponding to jade. The third feature focusing unit is like a high-precision microscope, which will further focus and refine the input target appearance distillation information. It will focus on the core features such as the hue, saturation and distribution uniformity of the color of jade, the specific value and level change of transparency, and the arrangement of the crystal structure. By focusing and strengthening these features, they are presented in the form of a spectrum to generate the third focused feature spectrum of jade. This spectrum can more clearly and intuitively show the key features closely related to the quality of jade. Similarly, for Hetian jade, the server inputs its target appearance distillation information into the third feature focusing unit corresponding to Hetian jade, highlighting the whiteness, warm texture, and the direction and density of the texture of Hetian jade, forming the third focused feature spectrum of Hetian jade. The server inputs the target appearance distillation information of jade and the third focused feature spectrum into the third feature recombiner corresponding to jade. The third feature reorganizer is like a skilled jigsaw puzzler. It will reorganize the two sets of information according to preset rules and algorithms. It will take into account the relationship and importance of each feature in the jade quality assessment, such as color has a greater impact on quality, followed by crystal structure. The first target quality key feature of jade is obtained by rearranging and combining the features of jade such as color, transparency, and crystal structure according to certain weights and logic. For example, it may combine the bright and uniform color features of jade with the tightly ordered crystal structure features to form a key feature combination that better represents high-quality jade. For Hetian jade, the third feature reorganizer will combine the characteristics of Hetian jade to reasonably reorganize the whiteness, warmth and texture features to obtain the first target quality key feature of Hetian jade. The server inputs the target appearance distillation information of jade and the third focus feature map into the target jade quality association unit corresponding to jade. This unit is like a strict calibration expert. It performs calibration operations on the input features based on the industry standards of jade quality and a large amount of sample data. It checks whether the color characteristics of jade are consistent with the known high-quality jade color standards, whether the transparency meets the requirements of the corresponding quality grade, and whether the crystal structure meets the normal physical properties. By calibrating and adjusting these features, more accurate and reliable features directly related to jade quality are obtained, namely the fourth jade quality-related features. For example, if the color feature of jade is found to deviate slightly from the standard in some aspects, the target jade quality-related unit will fine-tune it to make it more consistent with the color feature of high-quality jade.Similarly, for Hetian jade, the target jade quality association unit will calibrate its whiteness, warmth and texture characteristics according to the quality standard of Hetian jade, and obtain the fourth jade quality association feature of Hetian jade. The server inputs the fourth jade quality association feature of jadeite, the first target quality key feature, the target appearance distillation information and the third focus feature map into the third feature aggregation node corresponding to jadeite. The third feature aggregation node is like a powerful fusion center, which will perform comprehensive and in-depth aggregation operations on the feature information obtained at different stages. It will comprehensively consider the characteristics of various aspects of jadeite, and fuse the quality-related features accurately calibrated in the fourth jade quality association feature, the key feature combination that has been reasonably reorganized in the first target quality key feature, and the target appearance distillation information and the basic key features contained in the third focus feature map. Through complex algorithms, these features are organically integrated to form a comprehensive, comprehensive and accurate target jade appearance feature that can accurately reflect the quality of jadeite. Similarly, for Hetian jade, the third feature aggregation node will also aggregate the corresponding information to obtain the target jade appearance features of Hetian jade. These target jade appearance features will provide a key basis for the subsequent accurate assessment of jade quality grades.

[0085] In an embodiment of the present invention, the target feature extractor corresponding to each jade type includes a fourth feature focusing unit, a fourth feature recombiner, a target jade quality association unit and a fourth feature aggregation node, and the target jade quality association unit corresponding to each jade type includes a first target quality association subunit and a second target quality association subunit; the target feature extractor that imports the target appearance distillation information corresponding to each jade type into the target enhanced feature extraction path corresponding to each jade type performs feature extraction to obtain the target jade appearance features corresponding to each jade type, which can be implemented through the following examples.

[0086] Importing the target appearance distillation information corresponding to each jade type into the fourth feature focusing unit corresponding to each jade type to perform feature focusing operation, so as to obtain the fourth focusing feature map corresponding to each jade type;

[0087] Importing the fourth focused feature map corresponding to each jade type into the first target quality association subunit corresponding to each jade type to perform feature calibration calculation, so as to obtain the fifth jade quality association feature corresponding to each jade type;

[0088] Importing the fifth jade quality-related feature corresponding to each jade type and the target appearance distillation information corresponding to each jade type into the fourth feature recombiner corresponding to each jade type to perform feature recombining operation, so as to obtain the second target quality key feature corresponding to each jade type;

[0089] Import the second target quality key features corresponding to each jade type into the second target quality association sub-unit corresponding to each jade type for feature calibration operation, and obtain the sixth jade quality association features corresponding to each jade type;

[0090] Import the sixth jade quality association features corresponding to each jade type, the fifth jade quality association features corresponding to each jade type, and the target appearance distillation information corresponding to each jade type into the fourth feature aggregation node corresponding to each jade type for feature aggregation operation, and obtain the target jade appearance features corresponding to each jade type.

[0091] In an embodiment of the present invention, by way of example, taking Xiuyu as an example, the server has obtained the target appearance distillation information of Xiuyu refined by the target feature distiller, which covers key features such as the color, texture, and texture of Xiuyu. The server inputs the target appearance distillation information of these Xiuyu into the fourth feature focusing unit corresponding to Xiuyu. This unit is like a precise magnifying glass, deeply analyzing the target appearance distillation information of Xiuyu, and focusing on the core features closely related to quality, such as the unique tone of the Xiuyu color, the fineness and distribution pattern of the texture, and the tightness of the texture. By strengthening and organizing these features and presenting them in the form of a map, the fourth focusing feature map of Xiuyu is generated. This map can more clearly and intuitively highlight the key information related to the quality of Xiuyu. Similarly, for Dushan jade, the server inputs its target appearance distillation information into the corresponding fourth feature focusing unit, focusing on features such as the richness of the Dushan jade color and the characteristics of the massive structure, and forming the fourth focusing feature map of Dushan jade. The server inputs the fourth focusing feature map of Xiuyu into the first target quality correlation subunit corresponding to Xiuyu. This subunit is similar to a professional calibration instrument, and calibrates the features of Xiuyu according to the industry standards of Xiuyu quality and a large amount of Xiuyu sample data. For example, referring to the standards of high-quality Xiuyu with bright and uniform colors and delicate and coherent textures, the color and texture features in the fourth focusing feature map are calibrated to remove possible deviations or inaccurate information, and more accurate features related to the quality of Xiuyu are obtained, that is, the fifth jade quality correlation feature. For Dushan jade, the first target quality correlation subunit calibrates the color, structure and other features in its fourth focusing feature map according to the quality standards of Dushan jade, and obtains the fifth jade quality correlation feature of Dushan jade. The server inputs the fifth jade quality correlation feature and the target appearance distillation information of Xiuyu into the fourth feature reorganizer corresponding to Xiuyu. This reorganizer is like a skilled jigsaw master, and recombines this information according to preset rules and algorithms, combining the importance and mutual relationship of each feature in the quality assessment of Xiuyu. For example, the calibrated color and texture features are arranged and combined with features such as texture in the target appearance distillation information with specific weights and logic to obtain the second target quality key feature of Xiuyu, making it more accurately reflect the quality of Xiuyu. Similarly, for Dushan jade, the fourth feature reorganizer will recombine its fifth jade quality correlation feature and target appearance distillation information according to the characteristics of Dushan jade to obtain the second target quality key feature of Dushan jade. The server inputs the second target quality key feature of Xiuyu into the second target quality correlation subunit corresponding to Xiuyu. This subunit calibrates the features again, and from another angle or a more refined level, calibrates the Xiuyu features according to the Xiuyu quality standards. For example, further calibrate the coordination and matching degree between the texture of Xiuyu and its color and texture, so that the obtained features are more precisely related to the actual quality, and thus the sixth jade quality correlation feature of Xiuyu is obtained.Similarly, for Dushan jade, the second target quality correlation subunit performs secondary calibration on its second target quality key features to obtain the sixth jade quality correlation feature of Dushan jade. The server inputs the sixth jade quality correlation feature, the fifth jade quality correlation feature, and the target appearance distillation information of Xiuyu into the fourth feature aggregation node corresponding to Xiuyu. This node is like an efficient fusion center that comprehensively integrates various quality-related features obtained during different stages of Xiuyu through complex aggregation operations. It comprehensively considers various features such as the color, texture, and texture of Xiuyu, and organically combines the features that have been calibrated twice and reorganized once to form a more comprehensive, representative, and accurate target jade appearance feature that reflects the quality of Xiuyu. Similarly, for Dushan jade, the fourth feature aggregation node performs aggregation operations on the corresponding information to obtain the target jade appearance feature of Dushan jade. These target jade appearance features will provide a key basis for accurately evaluating the quality grade of jade in the subsequent process.

[0092] An embodiment of the present invention provides a computer device 100. The computer device 100 includes a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device 100 executes the aforementioned intelligent evaluation method for jade quality based on deep learning enhanced feature extraction. As Figure 2 shown, Figure 2 is a structural block diagram of the computer device 100 provided by an embodiment of the present invention. The computer device 100 includes a memory 111, a processor 112, and a communication unit 113. To achieve data transmission or interaction, each element of the memory 111, the processor 112, and the communication unit 113 is directly or indirectly electrically connected to each other.

[0093] For illustrative purposes, the foregoing description has been made with reference to specific embodiments. However, the above illustrative discussion is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Numerous modifications and variations are possible in light of the above teachings. The embodiments are selected and described to best illustrate the principles of the disclosure and its practical applications, so that those skilled in the art can best utilize the disclosure and use various embodiments with different modifications to suit the particular applications contemplated.

Claims

1. An intelligent jade quality assessment method based on deep learning enhanced feature extraction, characterized in that: include: Get jade appearance data; Importing the jade appearance data into a target feature distiller in a target enhancement feature extraction path corresponding to each jade type to perform a feature distillation operation, and obtaining target appearance distillation information corresponding to each jade type; Importing the target appearance distillation information corresponding to each jade type into the target feature extractor in the target enhanced feature extraction path corresponding to each jade type to perform feature extraction, so as to obtain the target jade appearance feature corresponding to each jade type; The target jade quality grading model is obtained by tuning the preset jade quality association unit in the preset enhanced feature extraction path according to the feature difference constraint, and the feature difference constraint is used to quantify the correlation of the target jade quality association feature, and the target jade quality association feature is the jade quality association feature generated by the preset jade quality association unit corresponding to different jade types; Determine the target jade quality grade corresponding to the jade appearance data according to the target jade appearance features corresponding to each jade type and the target quality grading path corresponding to each jade type; Determining the target jade quality grade corresponding to the jade appearance data according to the target jade appearance features corresponding to each jade type and the target quality grading path corresponding to each jade type includes: Importing the target jade appearance features corresponding to each jade type into the target quality grading path corresponding to each jade type to perform quality inference, and obtaining a first jade quality inference value corresponding to each jade type; Determine a target jade quality grade corresponding to the jade appearance data according to first jade quality inference values ​​respectively configured for a plurality of jade types; The method further comprises: Importing the jade appearance data into the target dynamic weight allocator in the target jade quality grading model for weight optimization allocation to obtain a target feature contribution parameter; The first jade quality inference values ​​respectively configured according to the plurality of jade types determine the target jade quality grade corresponding to the jade appearance data, including: According to the target feature contribution parameter, an adaptive synthesis operation is performed on the first jade quality inference values ​​respectively configured for the plurality of jade types to obtain a second jade quality inference value corresponding to the jade appearance data; The target jade quality grade is determined according to the second jade quality inference value.

2. The method according to claim 1, characterized in that The target jade quality grading model is trained through the following process, including: Obtaining a first preset jade appearance data set; Importing the first preset jade appearance data set into the preset enhanced feature extraction paths respectively configured for the multiple jade types in the initial integrated model to perform feature extraction operations, and obtaining the preset jade quality associated features corresponding to each jade type; Determine the characteristic difference constraint corresponding to the target jade type combination according to the preset jade quality associated characteristics corresponding to the target jade type combination; the target jade type combination is any two types of the multiple jade types; According to the characteristic difference constraint corresponding to the target jade type combination, the preset jade quality association unit corresponding to the target jade type combination is trained to obtain the target jade quality grading model.

3. The method according to claim 2, characterized in that The preset enhanced feature extraction path corresponding to each jade type includes a preset feature distiller and a preset feature extractor, and the preset feature extractor includes a first feature focusing unit, a first feature recombiner, a preset jade quality association unit and a first feature aggregation node; The first preset jade appearance data set is imported into the preset enhanced feature extraction paths respectively configured for the multiple jade types in the initial integrated model to perform feature extraction operations to obtain preset jade quality associated features corresponding to each jade type, including: Importing the first preset jade appearance data set into a preset feature distiller corresponding to each jade type to perform a feature distillation operation, so as to obtain preset appearance distillation information corresponding to each jade type; Importing the preset appearance distillation information corresponding to each jade type into the first feature focusing unit corresponding to each jade type to perform feature focusing operation, so as to obtain the first focusing feature map corresponding to each jade type; Importing the first focused feature map corresponding to each jade type and the preset appearance distillation information corresponding to each jade type into the first feature recombiner corresponding to each jade type to perform feature recombination operation, so as to obtain the first intermediate feature data corresponding to each jade type; Importing the first focused feature map corresponding to each jade type and the preset appearance distillation information corresponding to each jade type into the preset jade quality association unit corresponding to each jade type to perform feature calibration calculation, so as to obtain the first jade quality association feature corresponding to each jade type; The first intermediate feature data corresponding to each jade type, the first jade quality-related feature corresponding to each jade type, the first focused feature map corresponding to each jade type and the preset appearance distillation information corresponding to each jade type are imported into the first feature aggregation node corresponding to each jade type to perform feature aggregation operation to obtain the second intermediate feature data corresponding to each jade type.

4. The method according to claim 3, characterized in that The method further comprises: Obtaining a first jade quality target value corresponding to each preset jade appearance data in the first preset jade appearance data set; Importing the second intermediate feature data corresponding to each jade type into the preset quality grading path corresponding to each jade type in the initial integrated model to perform quality inference, and obtaining a third jade quality inference value corresponding to each jade type; Importing the first preset jade appearance data set into the preset dynamic weight allocator in the initial integrated model for weight optimization allocation, and obtaining a preset feature contribution parameter corresponding to each preset jade appearance data in the first preset jade appearance data set; According to the preset feature contribution parameter, an adaptive synthesis operation is performed on the third jade quality inference values ​​respectively configured for the plurality of jade types to obtain a fourth jade quality inference value corresponding to each preset jade appearance data in the first preset jade appearance data set; Determining a first fusion consistency error according to the fourth jade quality inference value and the first jade quality target value; The method of training the preset jade quality association unit corresponding to the target jade type combination according to the characteristic difference constraint corresponding to the target jade type combination to obtain the target jade quality grading model includes: According to the feature difference constraint corresponding to the target jade type combination, the preset jade quality association unit corresponding to the target jade type combination is trained, and according to the first fusion consistency error, the preset dynamic weight allocator is trained to obtain the target jade quality grading model.

5. The method according to claim 2, characterized in that: The preset enhanced feature extraction path corresponding to each jade type includes a preset feature distiller and a preset feature extractor, the preset feature extractor includes a second feature focusing unit, a second feature recombiner, a preset jade quality association unit and a second feature aggregation node, and the preset jade quality association unit includes a first preset quality association subunit and a second preset quality association subunit; the first preset jade appearance data set is imported into the preset enhanced feature extraction path respectively configured for the multiple jade types in the initial integrated model to perform feature extraction operations, and the preset jade quality association features corresponding to each jade type are obtained, including: Importing the first preset jade appearance data set into a preset feature distiller corresponding to each jade type to perform a feature distillation operation, so as to obtain preset appearance distillation information corresponding to each jade type; Importing the preset appearance distillation information corresponding to each jade type into the second feature focusing unit corresponding to each jade type to perform feature focusing operation, so as to obtain the second focusing feature map corresponding to each jade type; Importing the second focused feature map corresponding to each jade type into the first preset quality association subunit corresponding to each jade type to perform feature calibration calculation, so as to obtain the second jade quality association feature corresponding to each jade type; Importing the second jade quality-related feature corresponding to each jade type and the preset appearance distillation information corresponding to each jade type into the second feature recombiner corresponding to each jade type to perform feature recombining operation, so as to obtain third intermediate feature data corresponding to each jade type; Importing the third intermediate feature data corresponding to each jade type into the second preset quality association subunit corresponding to each jade type to perform feature calibration calculation, so as to obtain the third jade quality association feature corresponding to each jade type; The third jade quality-related feature corresponding to each jade type, the second jade quality-related feature corresponding to each jade type, and the preset appearance distillation information corresponding to each jade type are imported into the second feature aggregation node corresponding to each jade type to perform feature aggregation operation to obtain the fourth intermediate feature data corresponding to each jade type.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining a first jade quality target value corresponding to each preset jade appearance data in the first preset jade appearance data set; Importing the fourth intermediate feature data corresponding to each jade type into the preset quality grading path corresponding to each jade type in the initial integrated model to perform quality inference, and obtaining a fifth jade quality inference value corresponding to each jade type; Importing the first preset jade appearance data set into the preset dynamic weight allocator in the initial integrated model for weight optimization allocation, and obtaining a preset feature contribution parameter corresponding to each preset jade appearance data in the first preset jade appearance data set; According to the preset feature contribution parameter, an adaptive synthesis operation is performed on the fifth jade quality inference values ​​respectively configured for the plurality of jade types to obtain a sixth jade quality inference value corresponding to each preset jade appearance data in the first preset jade appearance data set; Determining a second fusion consistency error according to the sixth jade quality inference value and the first jade quality target value; The method of training the preset jade quality association unit corresponding to the target jade type combination according to the characteristic difference constraint corresponding to the target jade type combination to obtain the target jade quality grading model includes: According to the feature difference constraint corresponding to the target jade type combination, the preset jade quality association unit corresponding to the target jade type combination is trained, and according to the second fusion consistency error, the preset dynamic weight allocator is trained to obtain the target jade quality grading model.

7. The method according to claim 2, characterized in that The method further comprises: Acquire a second preset jade appearance data set and a second jade quality target value corresponding to each preset jade appearance data in the second preset jade appearance data set; Importing the second preset jade appearance data set into the preset enhanced feature extraction paths respectively configured for the multiple jade types in the initial integrated model to perform feature extraction operations, and obtaining fifth intermediate feature data corresponding to each jade type; Importing the fifth intermediate characteristic data corresponding to each jade type into the preset quality grading path corresponding to each jade type to perform quality inference, and obtaining the seventh jade quality inference value corresponding to each jade type; Determine the sub-item quality error corresponding to each jade type according to the seventh jade quality inference value corresponding to each jade type and the second jade quality target value; The method of training the preset jade quality association unit corresponding to the target jade type combination according to the characteristic difference constraint corresponding to the target jade type combination to obtain the target jade quality grading model includes: According to the feature difference constraints corresponding to the target jade type combination, the preset jade quality association units corresponding to the target jade type combination are trained, and according to the sub-item quality errors corresponding to each jade type, the preset model core components corresponding to each jade type in the initial integrated model are trained to obtain the target jade quality grading model; the preset model core components corresponding to each jade type are the feature processing architectures in the preset enhanced feature extraction paths corresponding to each jade type except the preset jade quality association units corresponding to each jade type.

8. A server system, characterized in that: The method comprises a server, wherein the server is used to execute the method described in any one of claims 1 to 7.

Images