Jade ware micromark detection method and device based on multi-modal data fusion

Abstract

The embodiment of the invention provides a jade device micro-mark detection method and device based on multi-modal data fusion. The method comprises the steps that image data of a to-be-detected jade device and material parameters of the to-be-detected jade device are acquired; based on the image data of the to-be-detected jade ware, the material parameters and a preset classification algorithm model, classification detection is conducted on the to-be-detected jade ware, a classification detection result is obtained, and the classification detection result comprises the micro-mark type, the machining technology, the raw material and abrasive material components, the source of the raw material and weathering degradation data of the to-be-detected jade ware; according to the micro-mark type, the processing technology, the raw material and abrasive material components, the source of the raw material and the weathering degradation data of the to-be-tested jade ware, carrying out inversion to construct the full life cycle of the to-be-tested jade ware; and outputting the classification detection result of the to-be-detected jade device and the full life cycle through a preset visualization mode. The micromark categories are distinguished in combination with multi-modal data such as image data and material data, and the recognition accuracy of the micromark categories is improved.

Description

Technical Field

[0001] The present application relates to the field of detection technology, and in particular to a method and device for detecting micro-trace of jade artifacts based on multimodal data fusion. Background Art

[0002] Micro-marks on ancient jade artifacts include traces of processing, use, and weathering, providing an objective record of the artifact's entire lifecycle, from processing and use to burial. Accurate identification and data analysis of these micro-marks are crucial for studying the craftsmanship, functional restoration, authenticity verification, and degradation mechanisms of ancient jade artifacts. These micro-marks are of great value in reflecting the landscape of the jade artifact industry since the Neolithic Age, the evolution of local productivity, and the conservation and utilization of cultural relics.

[0003] Currently, the analysis of various micro-marks at home and abroad is limited to the use of silica gel to replicate micro-marks and then observe them under a microscope. This is a contact-based test method that is not only cumbersome to operate, but also carries the risk of damaging precious organic residues (such as silk, jade sand, cinnabar, etc.) on the surface of jade or within the grooves. Related technologies have increased the viewing angle and accuracy of observation by adding optical lenses and light sources to detect various micro-marks on jade artifacts. However, these methods are limited to single-modal data and do not integrate component spectra with three-dimensional mechanical data. They are unable to distinguish between micro-mark types (such as weathering marks from natural weathering, processing marks from artificial polishing, and traces of use), resulting in a high rate of misjudgment. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide a method and device for detecting micro-trace of jade artifacts based on multimodal data fusion to solve the technical problems in the related art.

[0005] To achieve the above objectives, in a first aspect, embodiments of the present application provide a method for detecting micro-trace marks on jade artifacts based on multimodal data fusion, the method comprising:

[0006] Acquiring image data of the jade object to be tested and material parameters of the jade object to be tested;

[0007] Performing classification detection on the jade artifact to be tested based on the image data, the material parameters, and a preset classification algorithm model to obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering degradation data of the jade artifact to be tested;

[0008] The entire life cycle of the jade artifact to be tested is constructed based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0009] The classification test results and the entire life cycle of the jade artifact to be tested are output in a preset visual manner.

[0010] As an optional embodiment, the step of obtaining the image data of the jade object to be tested and the material parameters of the jade object to be tested includes:

[0011] Performing image acquisition on the jade artifact to be tested and its micro-trace features through an ultra-depth-of-field microscope to obtain first image data corresponding to the jade artifact to be tested and second image data corresponding to the micro-trace features of the jade artifact to be tested;

[0012] The material parameters of the jade artifact to be tested are obtained by performing spectral analysis on the jade artifact to be tested through a multi-spectral detection system. The material parameters of the jade artifact to be tested include the chemical element composition of the jade artifact to be tested and its corresponding mineralogical characteristics, and the element composition of the surface attachments of the jade artifact to be tested and its corresponding mineralogical characteristics.

[0013] As an optional embodiment, the performing classification detection on the jade object to be tested based on the image data of the jade object to be tested, the material parameters and a preset classification algorithm model to obtain a classification detection result includes:

[0014] Inputting the first image data, the second image data and the material parameter into the preset classification algorithm model;

[0015] Using the preset classification algorithm model, the micro-trace classification of the jade artifact to be tested is performed based on the first image data, the second image data and the material parameters to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested;

[0016] The corresponding relationship between the micro-trace type of the jade artifact to be tested and the micro-trace formation parameters is established through the preset classification algorithm model to obtain a classification detection result.

[0017] As an optional embodiment, the micro-trace classification of the jade artifact to be tested is performed based on the first image data, the second image data, and the material parameters by the preset classification algorithm model to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested, including:

[0018] Determining raw material parameters of the jade artifact to be tested using the preset classification algorithm model and the first image data, wherein the raw material parameters include raw material and abrasive composition, and the source of the raw material;

[0019] The preset classification algorithm model is used to perform coordinate conversion on the second image data, so as to perform coordinate registration processing on the second image data and the first image data to obtain image registration data of the jade tool to be tested;

[0020] The preset classification algorithm model is used to establish a spatial matching relationship between the image registration data of the jade object to be tested and the material parameters of the jade object to be tested;

[0021] The preset classification algorithm model is used to call a preset micro-trace attribute library based on the raw material parameters of the jade tool to be tested and the spatial matching relationship to determine the micro-trace type of the jade tool to be tested;

[0022] When it is determined that the micro-trace type is the first micro-trace type, the preset tool feature database is called through the preset classification algorithm model to predict the corresponding processing tool type and processing method of the micro-trace feature of the jade artifact to be tested, and the processing parameters of any micro-trace feature of the jade artifact to be tested are obtained, wherein the preset tool feature database includes physical feature data of the processing tool, and the physical feature data includes at least one of the hardness distribution parameters, blade microstructure and motion trajectory simulation data of the processing tool.

[0023] As an optional embodiment, the method further includes: performing trace classification on the micro-trace of the jade artifact to be tested based on the first image data, the second image data, and the material parameters by using the preset classification algorithm model to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested;

[0024] When it is determined that the micro-trace type is the second micro-trace type, combined with the surface attachment information data of the jade artifact to be tested in the material parameters, the preset material feature database is called through the preset classification algorithm model to predict the corresponding material environmental parameters of the micro-trace characteristics of the jade artifact to be tested, and the material environmental parameters include at least one of the pH value of the soil where the jade artifact to be tested is located and the groundwater activity data.

[0025] As an optional embodiment, the method of using the preset classification algorithm model to call a preset micro-trace attribute library based on the spatial matching relationship to determine the micro-trace type of the jade artifact to be tested includes:

[0026] Determining, from the preset micro-trace attribute library, micro-trace attribute items corresponding to the spatial matching relationship and the micro-trace features through the preset classification algorithm model;

[0027] The micro-trace type corresponding to the micro-trace attribute item is determined as the micro-trace type corresponding to any micro-trace feature in the jade artifact to be tested.

[0028] As an optional embodiment, the preset visualization method includes: at least one of: a quartz sand distribution thermal map, a stress distribution map, a machining tool motion trajectory simulation map, and a force angle and trace depth relationship curve.

[0029] As an optional embodiment, the method further includes:

[0030] According to the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials and weathering degradation data of the jade artifact to be tested, the preset classification algorithm model is used to determine and construct the processing process flow of the jade artifact to be tested, and the processing process flow includes at least one of the cutting, grinding and polishing processes of the jade artifact to be tested.

[0031] As an optional embodiment, the method further includes:

[0032] Collecting third image data, fourth image data, and material data of the jade artifact, wherein the third image data is an image of the jade artifact itself, and the fourth image data is an image of micro-trace features of micro-trace included on the jade artifact;

[0033] The third image data, the fourth image data and the material data of the jade artifact are subjected to a preset finite element analysis algorithm and a preset discrete element method algorithm to generate a particle interaction sample and a jade stress sample corresponding to the jade artifact;

[0034] The preset machine learning algorithm model is trained by the particle interaction samples and the jade stress samples to obtain the preset classification algorithm model.

[0035] In a second aspect, an embodiment of the present application provides a jade artifact micro-trace detection device based on multimodal data fusion, the device comprising:

[0036] A data acquisition module is used to acquire image data of the jade object to be tested and material parameters of the jade object to be tested;

[0037] A classification detection module is used to perform classification detection on the jade artifact to be tested based on the image data of the jade artifact to be tested, the material parameters and a preset classification algorithm model, and obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw material and weathering degradation data of the jade artifact to be tested;

[0038] An inversion construction module is used to inversely construct the entire life cycle of the jade artifact to be tested based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0039] The result output module is used to output the classification detection results and the entire life cycle of the jade artifact to be tested in a preset visual manner.

[0040] The above technical solution has the following beneficial effects: Based on multimodal data such as image data and material data of jade artifacts, jade artifacts are detected and analyzed, obtaining elemental distribution data of jade artifacts (such as raw material and abrasive composition, raw material source, and weathering and degradation data) and the types of micro-trace on the jade artifacts. This allows the full life cycle data of the jade artifacts, from mining and processing to burial, to be determined, and the factors that formed the micro-trace on the jade artifacts to be determined. The combination of multimodal data such as image data and material data can be used to distinguish the types of micro-trace, thereby improving the accuracy of micro-trace classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 This is one of the flow charts of a method for detecting micro-trace of jade artifacts based on multimodal data fusion in an embodiment of the present application.

[0043] Figure 2 This is a schematic diagram of the system architecture used in a method for detecting micro-trace on jade artifacts based on multimodal data fusion in an embodiment of the present application.

[0044] Figure 3 This is the second flow chart of a method for detecting micro-trace of jade artifacts based on multimodal data fusion in an embodiment of the present application.

[0045] Figure 4 It is a schematic diagram of the image data of the jade artifact in the embodiment of the present application.

[0046] Figure 5 Schematic diagram of the elemental composition of the samples in the embodiment of the present application.

[0047] Figure 6 This is a schematic diagram of the mineralogical characteristics of the samples in the examples of this application.

[0048] Figure 7 Schematic diagram of the stress distribution thermodynamic diagram of the embodiment of the present application.

[0049] Figure 8 It is a schematic diagram of the process inversion diagram of an embodiment of the present application.

[0050] Figure 9 This is a structural block diagram of a jade artifact micro-trace detection device based on multimodal data fusion in an embodiment of the present application.

[0051] Figure 10This is a structural block diagram of a computer-readable storage medium in an embodiment of the present application.

[0052] Figure 11 This is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] Figure 1 This is one of the flow charts of a method for detecting micro-trace of jade artifacts based on multimodal data fusion according to an embodiment of the present application. Figure 1 As shown, a method for detecting micro-trace of jade artifacts based on multimodal data fusion in an embodiment of the present application may include the following steps:

[0055] Step 101, obtaining image data of the jade artifact to be tested and material parameters of the jade artifact to be tested.

[0056] In an embodiment of the present application, an ultra-depth-of-field microscope can be used to capture images of the jade artifact to be tested and its micro-trace features to obtain first image data corresponding to the jade artifact to be tested and second image data corresponding to the micro-trace features of the jade artifact to be tested; and a multi-spectral detection system can be used to perform spectral analysis on the jade artifact to be tested to obtain material parameters of the jade artifact to be tested, wherein the material parameters of the jade artifact to be tested include the chemical element composition of the jade artifact to be tested and its corresponding mineralogical characteristics, and the element composition of the surface attachments of the jade artifact to be tested and its corresponding mineralogical characteristics.

[0057] As an example, the magnification of the super depth of field microscope can be, for example, 20 to 6000 times, and the resolution can be 12 million pixels. The first image data and the second image data can be simultaneously acquired by the super depth of field microscope, wherein the first image data can include but is not limited to the 2D (Two Dimensional, two-dimensional) morphological image, surface texture and 3D (Three Dimensional, three-dimensional) topographic image (such as height, curvature) of the jade artifact to be tested, wherein the 2D morphological image and the 3D topographic image can be in TIFF (Tag Image File Format) format, and the second image data can include micro-trace stereoscopic data of the jade artifact to be tested, and the micro-trace stereoscopic data can include but is not limited to processing traces, weathering depressions, etc. Figure 4As shown in the figure, the image data of the jade artifact to be tested is collected by the ultra-depth-of-field microscope, wherein A is the 2D morphological image of the jade artifact to be tested, B is the 3D morphological image of the jade artifact to be tested, and C is the shadow-enhanced image of the surface texture of the jade artifact to be tested.

[0058] As an example, the multispectral detection system may include but is not limited to LIBS (Laser Induced Breakdown Spectroscopy) and Raman spectroscopy. For example, ultraviolet fluorescence (wavelength less than 365nm) can be used to detect organic residues in the jade artifact to be tested (for example, burn marks can be seen as a ring-shaped distribution of carbonized organic matter under ultraviolet fluorescence), and LIBS can be used to directly scan the surface of the jade artifact to be tested to obtain its surface elemental composition, regional distribution of weathering-related elements, and inorganic residue data in cavities and depressions (specifically, LIBS can detect Na-U elements, with a spatial resolution of 10μm and a total travel range of 100×100mm). 2 ), the material parameters corresponding to the jade artifact to be tested are obtained according to LIBS and Raman spectroscopy analysis. The material parameters include but are not limited to the chemical element composition and mineralogical characteristics of the jade artifact to be tested, the element composition of the surface attachments of the jade artifact to be tested and their corresponding mineralogical characteristics, see Figure 5 and Figure 6 As shown. Among them, Figure 5 The horizontal axis represents the energy of X-rays, which corresponds to the characteristic X-ray energy excited by the chemical elements in the jade artifact to be tested, and is measured in Kev (Kilovolt Ampere Volt, kiloelectron volts). The composition of the chemical elements in the jade artifact to be tested can be determined by the position of the characteristic energy peak; the vertical axis represents the counting rate per electron volt, that is, the distribution of signal intensity with energy, cps is counts per second, reflecting the intensity of the detected electronic signal. / eV is the count normalized to the unit energy interval, which is used to eliminate the influence of energy bandwidth differences. The height (intensity) of the vertical axis peak reflects the content of the corresponding chemical element in the jade artifact to be tested. Figure 6 In the figure, the horizontal axis represents the wavelength and the vertical axis represents the reflectivity, so that the chemical elements or mineralogical characteristics of the jade artifact to be tested can be reflected or judged by the emissivity.

[0059] Step 102, classify and detect the jade artifact to be tested based on the image data, material parameters and preset classification algorithm model of the jade artifact to be tested, and obtain classification detection results, wherein the classification detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials and weathering degradation data of the jade artifact to be tested.

[0060] As an optional embodiment, the first image data, the second image data and the material parameters can be input into a preset classification algorithm model, and then the preset classification algorithm model is used to classify the micro-traces of the jade artifact to be tested based on the first image data, the second image data and the material parameters to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested. Finally, the preset classification algorithm model is used to establish a correspondence between the micro-trace type and the micro-trace formation parameters of the jade artifact to be tested to obtain a classification detection result.

[0061] Furthermore, the raw material parameters of the jade artifact to be tested are determined using a preset classification algorithm model and the first image data, the raw material parameters including the raw material and abrasive composition, and the source of the raw material; and the second image data is coordinate-converted using the preset classification algorithm model to coordinately align the second image data with the first image data to obtain image alignment data of the jade artifact to be tested; and the preset classification algorithm model is used to establish a spatial matching relationship between the image alignment data of the jade artifact to be tested and the material parameters of the jade artifact to be tested; then the preset classification algorithm model is used to call a preset micro-trace attribute library based on the raw material parameters and spatial matching relationship of the jade artifact to be tested to determine the micro-trace type of the jade artifact to be tested; when the micro-trace type is determined to be the first micro-trace type, the preset tool feature database is called through the preset classification algorithm model to predict the corresponding processing tool type and processing method of the micro-trace feature of the jade artifact to be tested, and obtain the processing parameters of any micro-trace feature of the jade artifact to be tested, wherein the preset tool feature database includes physical feature data of the processing tool, and the physical feature data includes at least one of the hardness distribution parameter, blade microstructure and motion trajectory simulation data of the processing tool.

[0062] The preset tool feature database can be, for example, a NoSQL database (e.g., MongoDB), which stores the content of various jade-dissolving sand materials (e.g., quartz SiO2, corundum Al2O3, garnet, diamond, etc.) to define the properties of the abrasive particles (particle size distribution, Mohs hardness), and stores the mechanical parameters of various processing tools (e.g., bamboo, animal hide, bronze, iron, hemp rope, etc.) to define the tool properties. The preset micro-trace attribute library can be, for example, a MySQL relational database, which is used to manage jade sample IDs, collection conditions, etc., and also stores material attribute mapping relationships, such as LIBS elemental data + Raman spectroscopy mineralogy data → jade hardness / brittleness; ultra-depth of field 3D roughness → "rough polishing / fine polishing" polishing classification or "long-term-short-term-never" usage level. The security of the database storage data is ensured through cloud storage.

[0063] For example, the coordinate registration process can be based on the SIFT (Scale-Invariant Feature Transform) algorithm or manual markers to register the micro-trace image with the image of the jade artifact to be tested, while also aligning the LIBS element distribution map with the super-depth 3D model coordinate system. The spatial matching relationship can be a semantic association, that is, establishing mapping rules such as "processing traces-element distribution of jade sand" and "weathering depressions-secondary mineral elements". For example, CaCO3 enrichment indicates the elements buried together with bronze and ivory by groundwater, and secondary mineral characteristics.

[0064] In an embodiment of the present application, feature extraction can be further performed based on the spatial matching relationship to obtain feature-level fusion data. For example, the topographic features (such as curvature, roughness) collected by the super-depth microscope and the element distribution (element concentration) of LIBS are spliced ​​into a joint feature vector for identifying and distinguishing the processing stages of the jade tool to be tested (such as wire cutting or lathe, wherein these processing links all require the participation of abrasives such as jade sand). Based on feature-level fusion data, the classification detection of the jade tool to be tested is further realized. For example, the preset classification algorithm model can judge the processing technology, jade tool raw materials and abrasive composition, the possible source and weathering degradation mechanism of jade raw materials by weighted voting (confidence 0.6:0.4), and finally obtain and output the classification detection result.

[0065] Optionally, when it is determined that the micro-trace type is the second micro-trace type, combined with the surface attachment information data of the jade artifact to be tested in the material parameters, the preset material feature database is called through the preset classification algorithm model to predict the corresponding material environmental parameters of the micro-trace characteristics of the jade artifact to be tested. The material environmental parameters include at least one of the pH value of the soil where the jade artifact to be tested is located and the groundwater activity data.

[0066] As an optional embodiment, a preset classification algorithm model is used to call a preset micro-trace attribute library based on a spatial matching relationship to determine the micro-trace type of the jade artifact to be tested. Specifically, the preset classification algorithm model can be used to determine the micro-trace attribute items corresponding to the spatial matching relationship and micro-trace characteristics from the preset micro-trace attribute library, and the micro-trace type corresponding to the micro-trace attribute item is determined as the micro-trace type corresponding to any micro-trace feature in the jade artifact to be tested.

[0067] In some embodiments, image data, material parameters, etc. may be pre-processed. For example, image data may be 3D reconstructed (MeshLab / CloudCompare), noise removed (e.g., by median filtering), and micro-trace features extracted (e.g., by edge gradient and depth distribution). Furthermore, multispectral data such as material parameters may be normalized by element matrix (Z-score), and jade sand residues (e.g., Si, Al) may be identified through cluster analysis (K-means), and the analysis results stored.

[0068] Step 103, constructing the entire life cycle of the jade artifact to be tested based on the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials and weathering degradation data of the jade artifact to be tested.

[0069] Exemplarily, the raw material (such as Mg / Si ratio) of the jade tool to be tested can be combined to trace the mining area of ​​the jade tool to be tested. Specifically, the raw material of the jade material is matched with a known mining area database (such as amphibole jade, serpentine jade, marble jade) to determine the mining area of ​​the jade tool to be tested. Further, the jade tool to be tested is subjected to processing technology inversion. Specifically, according to the micro-trace type, processing technology, raw material and abrasive composition, the source of raw material and weathering degradation data of the jade tool to be tested, a preset classification algorithm model is used to determine and construct the processing technology flow of the jade tool to be tested. The processing technology flow includes at least one of the cutting, grinding and polishing processes of the jade tool to be tested. For example, based on the micro-trace directionality (the coordinates of the super-depth microscope can be referenced), the residual elements of the processing tools (such as metal tools such as Cu, Pb, Fe) and the residual jade sand (including quartz SiO2, corundum Al2O3, garnet, diamond, etc.) are combined to reconstruct the cutting-grinding-polishing process. And / or infer the environment of the jade artifact being tested, for example, by correlating weathering traces (e.g., honeycomb structure) with secondary elements (e.g., Fe2O3 enrichment) to infer soil pH and groundwater activity. This allows for the inverse reconstruction of the entire life cycle of the jade artifact, from mining and processing to its burial environment.

[0070] Step 104: Output the classification test results and the entire life cycle of the jade artifact to be tested in a preset visualization manner.

[0071] For example, the preset visualization methods include but are not limited to at least one of a quartz sand distribution heat map, a stress distribution map, a machining tool motion trajectory simulation map, and a curve showing the relationship between the force angle and the trace depth. Figure 7 As shown. The inverse diagram of the processing process in the whole life cycle can be found in Figure 8 As shown, in Figure 8In the figure, Figure A shows the spiral distribution characteristics of the jade ring (jade artifact to be tested) surface simulated by calculation (i.e., the simulation diagram of the motion trajectory of the processing tool), which conforms to the Archimedean spiral starting from the same center. Figure B shows the jade ring (jade artifact to be tested) after the Cartesian coordinate system is converted to the polar coordinate system. The Archimedean spiral is mapped to a straight line with a slope of β (for example, a stress distribution diagram). Figure C shows a schematic diagram of the device for making surface patterns of the jade ring (jade artifact to be tested).

[0072] In some embodiments, the present application may also include model training and construction of a preset classification algorithm model. Specifically, third image data, fourth image data, and material data of the jade artifact are collected, wherein the third image data is an image of the jade artifact itself, and the fourth image data is an image of micro-trace features of tiny traces included on the jade artifact; the third image data, fourth image data, and material data of the jade artifact are subjected to a preset finite element analysis algorithm and a preset discrete element method algorithm to generate particle interaction samples and jade stress samples corresponding to the jade artifact; a preset machine learning algorithm model is trained using the particle interaction samples and the jade stress samples to obtain a preset classification algorithm model.

[0073] Specifically, the preset classification algorithm model may include but is not limited to:

[0074] Data input layer: This layer inputs third-party image data, third-party image data, and material data. For example, LIBS element distribution (e.g., in CSV (Comma-Separated Values, a plain text file format for storing tabular data) format), Raman spectral peak and intensity relationship data (CSV), ultra-depth 3D images (TIFF), and micro-trace attribute libraries (JSON (JavaScript Object Notation)).

[0075] Physics engine layer: can simulate particle interactions (such as jade sand friction) through the preset discrete element method (DEM), and simulate jade stress through the preset finite element method (FEM);

[0076] Machine learning layer: Transformer predicts tool motion trajectory and GAN generates missing mechanical parameters;

[0077] Visualization layer: WebGL real-time rendering of stress field / crack extension.

[0078] Then, the hardware configuration of the aforementioned preset classification algorithm model is performed, including but not limited to computing nodes: GPU (to accelerate DEM / FEM parallel computing), interactive terminals: touch screen workstations, supporting gesture operation tool paths, and data storage using distributed storage (Ceph) to manage TB-level simulation data.

[0079] After completing the hardware configuration, enter the dynamic modeling process of the preset classification algorithm model. For example:

[0080] ① Mining stage: Processing methods are simulated using the discrete element method (EDEM), such as hammering / splitting simulation (Python).

[0081] import edem

[0082] model=edem.Model(material="nephrite")

[0083] model.add_tool(type="stone_hammer",velocity=3m / s,angle=45°)

[0084] model.solve(steps=1000)

[0085] ②Processing stage: The contact between the coupling tool and the jade artifact is simulated by the finite element method (Abaqus / ANSYS); for example, the contact between the wire cutting and tool rotation tools and the jade artifact is simulated.

[0086] Among them, wire cutting is defined as the tangential friction between the hemp rope and the jade sand (μ = 0.3-0.6);

[0087] Tool rotation: defined as the combined effect of angular velocity ω and normal pressure P.

[0088] ③ Burial stage: Phase field method was used to simulate weathering stress (COMSOL), element diffusion (Fe 2+ →Fe 3+ ) induces volume expansion stress, fatigue cracks under cyclic temperature and humidity loads, etc.

[0089] Furthermore, a machine learning enhanced simulation is performed by using a preset classification algorithm model, exemplarily:

[0090] ① Tool path inversion: Using the Transformer network to infer the force pattern of ancient craftsmen from the directionality of micro-trace (super depth of field data):

[0091]

[0092]

[0093] ① Parameter optimization: Parallel Bayesian optimization (Hyperopt+TPE)

[0094] Hyperopt is a Python-based Bayesian optimization library that supports parallelization and asynchronous optimization. It uses TPE (Tree-structured Parzen Estimator) as the acquisition function and is suitable for high-dimensional parameter spaces.

[0095] TPE (Tree-structured Parzen Estimator) is a probability density estimation method based on a tree structure. It is suitable for processing high-dimensional parameter spaces and improves search efficiency through stratified sampling.

[0096] For example, it can be implemented through the following code:

[0097]

[0098]

[0099] Finally, the preset classification algorithm model is verified and calibrated, for example:

[0100] In the positive verification process, a jade imitation was 3D printed (Stratasys J850, material: photosensitive resin + mineral powder), processed using real tools, and the simulated / actual micro-traces were compared.

[0101] During the reverse calibration process, the residual network (ResNet50) compares the simulated traces with the actual super-depth of field images.

[0102] loss=cosine_similarity(simulated_texture,real_texture)

[0103] ifloss>threshold:

[0104] adjust_FEM_mesh_refinement()#Dynamic mesh refinement

[0105] In summary, the training modeling and optimization of the preset classification algorithm model are realized, and finally the preset classification algorithm model is obtained for the aforementioned Figure 1 In the method embodiment shown.

[0106] In order for those skilled in the art to clearly and accurately understand the technical solutions of the embodiments of the present application, Figure 2 and Figure 3 The technical solutions of the embodiments of the present application are further described in detail through examples.

[0107] in, Figure 2 This is a schematic diagram of the system architecture of a method for detecting micro-trace of jade artifacts based on multimodal data fusion according to an embodiment of the present application. Figure 3 This is the second flow chart of a method for detecting micro-trace of jade artifacts based on multimodal data fusion in an embodiment of the present application.

[0108] like Figure 2 As shown, the system used in a method for detecting micro-trace of jade artifacts based on multimodal data fusion in an embodiment of the present application includes at least: an ultra-depth-of-field microscope, a multispectral detection system (for example, including LIBS, Raman spectrometer and ultraviolet fluorescence, etc.), a dynamic mechanics simulation platform (wherein a preset classification algorithm model is configured, thus, including a data input layer, a physical engine layer, a machine learning layer and a visualization layer of the preset classification algorithm model), and configurations for the dynamic mechanics simulation platform, such as distributed storage facilities, touch screen workstations, GPUs (Graphics Processing Units, graphics processors), etc.

[0109] exist Figure 2 Based on the system shown, Figure 3 The process shown realizes the detection of jade artifacts. Specifically, the jade artifact to be tested is placed as a sample on, for example, a data acquisition console to control the ultra-depth-of-field microscope and the multispectral detection system to collect data (image data and material parameters) on the jade artifact to be tested, and the collected data is input into a preset classification algorithm model.

[0110] Furthermore, the preset classification algorithm model can process the collected data as follows:

[0111] ① Extracting data or information, such as extracting the chemical element composition of the jade artifact to be tested and its corresponding mineralogical characteristics, the element composition of the surface attachments of the jade artifact to be tested and its corresponding mineralogical characteristics, and extracting micro-traces in image data (such as surface processing marks and disease data);

[0112] ② The extracted information is then stored in an internal database. For example, a MySQL relational database is used to manage the ID of the jade sample to be tested and the collection conditions, and a NoSQL database (such as MongoDB) is used to store unstructured images and multimodal data (i.e., the image data and material parameters of the jade to be tested).

[0113] ③ Then retrieve data from various databases and analyze them. For example, retrieve parameters that match the data features from the preset micro-trace attribute library and the preset tool feature database, so as to complete the analysis of processing tools, jade material data, etc., and present the analysis results quantitatively;

[0114] ④ Based on the analysis results of processing tools, jade material and other data, further use machine learning to map the relationship between the analysis results, such as establishing the relationship between the sample (the jade artifact to be tested) and the processing method;

[0115] ⑤ Output and display analysis results, relationship mapping and other data.

[0116] For example, the micro-trace analysis of the jade artifacts unearthed from Sanxingdui was performed using the technical solution of the embodiment of the present application:

[0117] First, LIBS and Raman spectroscopy are used to analyze the material information of the target jade artifact (i.e. the jade artifact to be tested), including its chemical element composition, mineralogical characteristics, and the element composition and mineralogical characteristics of its surface attachments. These test results will be provided to Figure 2 The preset classification algorithm model in the system shown serves as the data basis for its subsequent analysis.

[0118] Secondly, based on the retrieval results of the corresponding materials in the database (for example, the jade sample ID and collection conditions stored in the MySQL relational database), the ultra-depth-of-field microscope is controlled to automatically search for polishing marks, processing marks, jade-dissolving sand and other traces related to jade processing on the surface of the target jade, as well as the disease characteristics of the surface of the target jade (such as cracks, fractures, weathering and erosion, etc.), and take pictures respectively to obtain 2D, 3D composite and shadow enhancement (Optical Shadow Effect Mode) images corresponding to the target jade in turn, including but not limited to.

[0119] Then, based on the images obtained by the ultra-depth-of-field microscope, the preset classification algorithm model can call the system's database based on its machine learning method and use a multimodal fusion method to invert any processing trace on the target jade artifact (data provided by the ultra-depth-of-field microscope) to determine which material or types of tools should have left it, as well as the specific operation method of the tool when processing the target jade artifact (such as the force and angle of the carving, the speed of the tool, etc.). The inversion results are presented in a quantitative manner, such as but not limited to quartz sand distribution thermal maps, stress distribution maps, processing tool motion trajectory simulation maps, and force angle-trace depth relationship curves.

[0120] Finally, based on the surface disease characteristics (data provided by the super-depth of field microscope), combined with the obtained surface attachment information (usually soil, data provided by LIBS) or information in the database, the preset classification algorithm model can also infer the burial environment or cause of the disease based on its machine learning method.

[0121] In summary, the embodiment of the present application is based on multimodal data such as image data and material data of jade tools, and the jade tools are detected and analyzed to obtain element distribution data (such as raw material and abrasive composition, source of raw material and weathering degradation data) of the jade tools and the micro-trace categories on the jade tools, and then determine the full life cycle data such as mining, processing and burial of the jade tools, and determine the formation factors of the micro-trace on the jade tools. Due to the combination of multimodal data such as image data and material data to distinguish the micro-trace categories, the recognition accuracy of the micro-trace categories is improved.

[0122] In addition, data collection on the jade artifacts to be tested through ultra-depth-of-field microscopy, LIBS, Raman spectrometers, etc. can meet the needs of cultural relics protection, achieve non-destructive, high-precision, and efficient data collection, and avoid the contact risks of silicone mold technology in related technologies; the high magnification and resolution of the ultra-depth-of-field microscope improve the accuracy and efficiency of micro-trace collection, and can achieve the collection and measurement of micro-trace widths of 0.01um, reducing the financial and time costs of data collection; the high spatial resolution and total travel range of LIBS enable the technical solution of this application to support micron-level cross-modal correlation, collecting not only three-dimensional morphological data, but also micro-trace regional composition and attachment data;

[0123] Secondly, based on the image collection of the ultra-depth-of-field microscope, it is compatible with the data collected by the newly added LIBS and Raman spectrometer, reducing the risk of damage to cultural relics caused by repeated replacement of detection equipment, and realizing a multimodal data fusion mode, and realizing the inversion of the entire life cycle of jade artifacts, providing an operational technical path for the systematic study of jade artifacts from mineral source determination to burial history.

[0124] Correspondingly, the embodiments of the present application also provide device embodiments corresponding to the aforementioned method embodiments. Figure 9 This is a structural block diagram of a jade artifact micro-trace detection device based on multimodal data fusion according to an embodiment of the present application. Figure 9 As shown, a jade artifact micro-trace detection device based on multimodal data fusion may include:

[0125] The data acquisition module 901 is used to obtain the image data of the jade object to be tested and the material parameters of the jade object to be tested;

[0126] A classification detection module 902 is configured to perform classification detection on the jade artifact to be tested based on the image data, the material parameters, and a preset classification algorithm model, and obtain classification detection results, wherein the classification detection results include the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0127] An inversion construction module 903 is used to inversely construct the entire life cycle of the jade artifact to be tested based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0128] The result output module 904 is used to output the classification test results and the entire life cycle of the jade artifact to be tested in a preset visual manner.

[0129] In summary, the embodiment of the present application is based on multimodal data such as image data and material data of jade tools, and the jade tools are detected and analyzed to obtain element distribution data (such as raw material and abrasive composition, source of raw materials and weathering degradation data) of the jade tools and the micro-trace categories on the jade tools, and then determine the full life cycle data such as mining, processing and burial of the jade tools, and determine the formation factors of the micro-trace on the jade tools. Due to the combination of multimodal data such as image data and material data to distinguish the micro-trace categories, the recognition accuracy of the micro-trace categories is improved.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0131] The present application also provides a computer-readable storage medium 1000. Figure 10 As shown, the computer readable storage medium 1000 stores a computer program, and when the computer program is executed by the processor, each step of the above-mentioned method and device for detecting micro-marks of jade and stone articles is implemented. For example, when the computer program is executed by the processor, the following steps are implemented:

[0132] Acquiring image data of the jade object to be tested and material parameters of the jade object to be tested;

[0133] Performing classification detection on the jade artifact to be tested based on the image data, the material parameters, and a preset classification algorithm model to obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering degradation data of the jade artifact to be tested;

[0134] The entire life cycle of the jade artifact to be tested is constructed based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0135] The classification test results and the entire life cycle of the jade artifact to be tested are output in a preset visual manner.

[0136] In some embodiments, the storage medium is further configured to store program code 1001 for performing the following steps:

[0137] Acquiring image data of the jade object to be tested and material parameters of the jade object to be tested;

[0138] Performing classification detection on the jade artifact to be tested based on the image data, the material parameters, and a preset classification algorithm model to obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering degradation data of the jade artifact to be tested;

[0139] The entire life cycle of the jade artifact to be tested is constructed based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0140] The classification test results and the entire life cycle of the jade artifact to be tested are output in a preset visual manner.

[0141] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program, when executed by the processor, can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. Of course, there are other ways of readable storage media, such as quantum memory, graphene memory, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0142] The embodiment of the present application further provides an electronic device 1100, such as Figure 11 As shown, it includes one or more processors 1101 , a communication interface 1102 , a memory 1103 and a communication bus 1104 , wherein the processor 1101 , the communication interface 1102 , and the memory 1103 communicate with each other via the communication bus 1104 .

[0143] Memory 1103, used for storing computer programs;

[0144] The processor 1101 is configured to implement the steps of the aforementioned method and device for detecting micro-trace of jade artifacts when executing the program stored in the memory 1103. For example, the processor 1101 implements the following steps when executing the program stored in the memory 1103:

[0145] Acquiring image data of the jade object to be tested and material parameters of the jade object to be tested;

[0146] Performing classification detection on the jade artifact to be tested based on the image data, the material parameters, and a preset classification algorithm model to obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering degradation data of the jade artifact to be tested;

[0147] The entire life cycle of the jade artifact to be tested is constructed based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested;

[0148] The classification test results and the entire life cycle of the jade artifact to be tested are output in a preset visual manner.

[0149] Processor 1101 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0150] Memory 1103 can include a large capacity memory for data or instructions. For example, and not limitation, memory 1103 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In appropriate cases, memory 1103 can include a removable or non-removable (or fixed) medium. In a specific embodiment, memory 1103 is a non-volatile solid-state memory. In a specific embodiment, memory 1103 includes a read-only memory (ROM). In appropriate cases, the ROM can be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0151] Communication bus 1104 comprises hardware, software or both, for above-mentioned parts are coupled together.For example, bus can comprise accelerated graphics port (AGP) or other graphics buses, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more above these combinations.In suitable cases, bus can comprise one or more buses.Although the present application embodiment describes and shows specific bus, the application considers any suitable bus or interconnection.

[0152] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0153] Although the present application provides method operation steps such as embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many steps and does not represent the only execution order. When an actual device or client product is executed, it can be executed in the order shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0154] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0155] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0157] Specific embodiments are used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for detecting micro-trace of jade artifacts based on multimodal data fusion, characterized in that: The method comprises: Acquiring image data of the jade object to be tested and material parameters of the jade object to be tested; Performing classification detection on the jade artifact to be tested based on the image data, the material parameters, and a preset classification algorithm model to obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering degradation data of the jade artifact to be tested; The entire life cycle of the jade artifact to be tested is constructed based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested; The classification test results and the entire life cycle of the jade artifact to be tested are output in a preset visual manner.

2. The method according to claim 1, characterized in that The step of obtaining image data of the jade article to be tested and material parameters of the jade article to be tested comprises: Performing image acquisition on the jade artifact to be tested and its micro-trace features through an ultra-depth-of-field microscope to obtain first image data corresponding to the jade artifact to be tested and second image data corresponding to the micro-trace features of the jade artifact to be tested; The material parameters of the jade artifact to be tested are obtained by performing spectral analysis on the jade artifact to be tested through a multi-spectral detection system. The material parameters of the jade artifact to be tested include the chemical element composition of the jade artifact to be tested and its corresponding mineralogical characteristics, and the element composition of the surface attachments of the jade artifact to be tested and its corresponding mineralogical characteristics.

3. The method according to claim 2, characterized in that The method of performing classification detection on the jade artifact to be tested based on the image data of the jade artifact to be tested, the material parameters and a preset classification algorithm model to obtain a classification detection result includes: Inputting the first image data, the second image data and the material parameter into the preset classification algorithm model; Using the preset classification algorithm model, the micro-trace classification of the jade artifact to be tested is performed based on the first image data, the second image data and the material parameters to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested; The corresponding relationship between the micro-trace type of the jade artifact to be tested and the micro-trace formation parameters is established through the preset classification algorithm model to obtain a classification detection result.

4. The method according to claim 3, characterized in that The method of performing trace classification on the micro-trace of the jade artifact to be tested based on the first image data, the second image data, and the material parameters by using the preset classification algorithm model to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested includes: Determining raw material parameters of the jade artifact to be tested using the preset classification algorithm model and the first image data, wherein the raw material parameters include raw material and abrasive composition, and the source of the raw material; The preset classification algorithm model is used to perform coordinate conversion on the second image data, so as to perform coordinate registration processing on the second image data and the first image data to obtain image registration data of the jade tool to be tested; The preset classification algorithm model is used to establish a spatial matching relationship between the image registration data of the jade object to be tested and the material parameters of the jade object to be tested; The preset classification algorithm model is used to call a preset micro-trace attribute library based on the raw material parameters of the jade tool to be tested and the spatial matching relationship to determine the micro-trace type of the jade tool to be tested; When it is determined that the micro-trace type is the first micro-trace type, the preset tool feature database is called through the preset classification algorithm model to predict the corresponding processing tool type and processing method of the micro-trace feature of the jade artifact to be tested, and the processing parameters of any micro-trace feature of the jade artifact to be tested are obtained, wherein the preset tool feature database includes physical feature data of the processing tool, and the physical feature data includes at least one of the hardness distribution parameters, blade microstructure and motion trajectory simulation data of the processing tool.

5. The method according to claim 4, characterized in that The method further comprises: performing trace classification on the micro-trace of the jade artifact to be tested based on the first image data, the second image data and the material parameters through the preset classification algorithm model to obtain the micro-trace type and micro-trace formation parameters of the jade artifact to be tested; When it is determined that the micro-trace type is the second micro-trace type, combined with the surface attachment information data of the jade artifact to be tested in the material parameters, the preset material feature database is called through the preset classification algorithm model to predict the corresponding material environmental parameters of the micro-trace characteristics of the jade artifact to be tested, and the material environmental parameters include at least one of the pH value of the soil where the jade artifact to be tested is located and the groundwater activity data.

6. The method according to claim 5, characterized in that The method of using the preset classification algorithm model to call a preset micro-trace attribute library based on the spatial matching relationship to determine the micro-trace type of the jade artifact to be tested includes: Determining, from the preset micro-trace attribute library, micro-trace attribute items corresponding to the spatial matching relationship and the micro-trace features through the preset classification algorithm model; The micro-trace type corresponding to the micro-trace attribute item is determined as the micro-trace type corresponding to any micro-trace feature in the jade artifact to be tested.

7. The method according to claim 6, characterized in that The preset visualization method includes: at least one of: a quartz sand distribution thermal map, a stress distribution map, a machining tool motion trajectory simulation map, and a force angle and trace depth relationship curve.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: According to the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials and weathering degradation data of the jade artifact to be tested, the preset classification algorithm model is used to determine and construct the processing process flow of the jade artifact to be tested, and the processing process flow includes at least one of the cutting, grinding and polishing processes of the jade artifact to be tested.

9. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Collecting third image data, fourth image data, and material data of the jade artifact, wherein the third image data is an image of the jade artifact itself, and the fourth image data is an image of micro-trace features of micro-trace included on the jade artifact; The third image data, the fourth image data and the material data of the jade artifact are subjected to a preset finite element analysis algorithm and a preset discrete element method algorithm to generate a particle interaction sample and a jade stress sample corresponding to the jade artifact; The preset machine learning algorithm model is trained by the particle interaction samples and the jade stress samples to obtain the preset classification algorithm model.

10. A jade artifact micro-trace detection device based on multimodal data fusion, characterized in that: The device comprises: A data acquisition module is used to acquire image data of the jade object to be tested and material parameters of the jade object to be tested; A classification detection module is used to perform classification detection on the jade artifact to be tested based on the image data of the jade artifact to be tested, the material parameters and a preset classification algorithm model, and obtain a classification detection result, wherein the classification detection result includes the micro-trace type, processing technology, raw material and abrasive composition, source of raw material and weathering degradation data of the jade artifact to be tested; An inversion construction module is used to inversely construct the entire life cycle of the jade artifact to be tested based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering degradation data of the jade artifact to be tested; The result output module is used to output the classification detection results and the entire life cycle of the jade artifact to be tested in a preset visual manner.

Images