Cinnabar quality identification method and device, electronic equipment and storage medium

Abstract

The invention provides a cinnabar quality identification method and device, electronic equipment and a storage medium, and relates to the technical field of jewelry detection. According to the method, the cinnabar sample is comprehensively identified from at least two dimensions of the composition, the filler and the surface structure, so that the accuracy and the reliability of an identification result can be improved, and accurate evaluation on the quality of the cinnabar sample can be realized.

Description

Technical Field

[0001] The present application relates to the field of jewelry testing technology, and more specifically, to a cinnabar quality identification method, device, electronic device, and storage medium. Background Art

[0002] Cinnabar, also known as cinnabar, is an important red mineral primarily composed of mercury sulfide (HgS). However, natural high-purity cinnabar resources are relatively limited, making it difficult to meet the enormous demand for this red mineral in the jewelry market. Furthermore, cinnabar is relatively low in hardness (2-2.5 on the Mohs scale) and brittle, making it difficult to directly use in jewelry for everyday wear. To address this issue, powdered pressed cinnabar (powdered pressed cinnabar) has gradually emerged in the jewelry market. This involves crushing cinnabar into a powder, then adding a binder such as resin (such as epoxy) to form jewelry.

[0003] However, the resulting confusion between genuine and counterfeit cinnabar jewelry and the sale of inferior products as genuine products has become increasingly prevalent in the jewelry market. In addition to pressed cinnabar, a large number of imitation cinnabar jewelry has also flooded the market. These imitations are typically made from cheap materials such as dyed barite (BaSO4), calcite (CaCO3), or red lead (Pb3O4) powder, using a powder pressing process. While their appearance closely resembles pressed cinnabar, their composition and value differ significantly.

[0004] There are obvious differences in the production processes of powdered cinnabar and imitation cinnabar. This difference in production process leads to differences in composition, structure and physical properties between the two, but it is difficult to distinguish them only through visual observation or simple physical tests. Moreover, the quality of powdered cinnabar is also difficult to evaluate through visual observation or simple physical tests.

[0005] Physical tests, such as infrared spectroscopy, can detect the presence of organic matter in a sample and provide a preliminary assessment of resin content, but they cannot accurately quantify the resin content, making it impossible to further assess the quality of cinnabar jewelry. Therefore, existing cinnabar jewelry testing technology has significant shortcomings and cannot meet market demands for accurate identification of pressed cinnabar and imitation cinnabar, as well as for scientific quality grading of pressed cinnabar. Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide a cinnabar quality identification method, device, electronic device and storage medium to improve the existing detection technology that is difficult to meet the market demand for accurately identifying powdered cinnabar and imitation cinnabar and scientifically grading the quality of powdered cinnabar.

[0007] In a first aspect, the present invention provides a method for identifying the quality of cinnabar, the method comprising: Obtain sample data for the cinnabar sample; According to the sample data, the quality of the cinnabar sample is identified from a target dimension to obtain an identification result, wherein the target dimension includes at least two dimensions of composition, filler and surface structure.

[0008] In the above implementation process, by comprehensively identifying the cinnabar sample from at least two dimensions of composition, filling material and surface structure, the accuracy and reliability of the identification result can be improved, thereby achieving an accurate assessment of the quality of the cinnabar sample.

[0009] Optionally, identifying the quality of the cinnabar sample from a target dimension based on the sample data to obtain an identification result includes: According to the sample data, the quality of the cinnabar sample is identified from various dimensions, and an identification result corresponding to each dimension is determined; The final identification result is determined based on the individual identification results.

[0010] In this implementation, the quality of cinnabar samples is identified across multiple dimensions, and the final conclusion is drawn based on the combined results from each dimension, effectively improving the comprehensiveness and accuracy of the identification. This identification method allows for a more detailed analysis of the different characteristics of cinnabar samples, avoiding details that might be overlooked in single-dimensional testing, and thus enabling a more accurate assessment of their quality.

[0011] Optionally, the identifying the quality of the cinnabar sample from various dimensions based on the sample data and determining the identification result corresponding to each dimension includes: According to the determined identification order rule and based on the sample data, the quality of the cinnabar sample is identified from the corresponding dimension to determine the identification result corresponding to the dimension.

[0012] In this implementation, identifying samples from different dimensions in a predetermined order effectively avoids omissions or duplications during testing, making the test results for each dimension more accurate and reliable. Furthermore, this orderly identification process helps quickly screen out samples that don't meet basic requirements, saving testing resources and time. It also provides a clear basis for subsequent comprehensive judgment, significantly improving the efficiency of the entire identification process.

[0013] Optionally, the identification order rules include: When the identification result corresponding to the component dimension meets the first set requirement, the quality of the cinnabar sample is further identified from the filler dimension to determine the corresponding identification result; when the identification result corresponding to the filler dimension meets the second set requirement, the quality of the cinnabar sample is further identified from the surface structure dimension to determine the corresponding identification result.

[0014] In the above implementation process, this hierarchical screening method can quickly exclude samples that do not meet the basic requirements and avoid unnecessary subsequent testing, thereby improving detection efficiency and saving resources.

[0015] Optionally, the sample data includes component detection data, and the first set requirement is that the cinnabar content in the component detection data is greater than or equal to a first set content and the heavy metal content is less than a second set content; And / or, the sample data includes filler detection data, and the second setting requirement is that the filler content in the filler detection data is less than a third set content.

[0016] In the above implementation process, by clearly setting specific requirements for composition and filler content, a quantitative standard is provided for the quality identification of cinnabar samples.

[0017] Optionally, the sample data includes a fluorescent image of the cinnabar sample, the target dimension includes a filler dimension, and the quality of the cinnabar sample is identified from each dimension based on the sample data to determine an identification result corresponding to each dimension, including: acquiring a fluorescence image of the cinnabar sample; Comparing the fluorescent image with standard fluorescent images of different filler contents to determine a target standard fluorescent image having the highest similarity to the fluorescent image, wherein each standard fluorescent image is marked with a corresponding identification result; Determine that the identification result corresponding to the target standard fluorescent image is the identification result corresponding to the filler dimension.

[0018] In this implementation, the fluorescence image can intuitively reflect the sample's fluorescence characteristics. Since fluorescence intensity is closely related to filler content, comparison with a standard fluorescence image allows for rapid and accurate determination of the filler content range, enabling quantitative identification of filler dimensions. This method, which eliminates the need for complex chemical analysis or destructive testing, is simple and efficient. It also provides an intuitive and reliable basis for evaluating the quality of cinnabar samples, effectively improving identification accuracy and efficiency.

[0019] Optionally, the sample data includes a surface structure image of the cinnabar sample, the target dimension includes a surface structure dimension, and the quality of the cinnabar sample is identified from each dimension based on the sample data to determine an identification result corresponding to each dimension, including: obtaining a surface structure image of the cinnabar sample; Comparing the surface structure image with standard surface structure images of different surface structures to determine a target standard surface structure image having the highest similarity to the surface structure image, wherein each standard surface structure image is marked with a corresponding identification result; Determine the identification result corresponding to the target standard surface structure image as the identification result corresponding to the surface structure dimension.

[0020] In this implementation, image comparison technology enables intuitive assessment of sample characteristics such as structural density and particle distribution, allowing for rapid determination of quality. This method, which requires no complex physical or chemical analysis, is simple and efficient. It also provides an intuitive and reliable basis for evaluating the quality of cinnabar jewelry, effectively improving identification accuracy and efficiency.

[0021] Optionally, the sample data includes component detection data, the target dimension includes a component dimension, and obtaining the sample data of the cinnabar sample includes: The components of the cinnabar sample are detected by energy dispersive X-ray fluorescence spectrometer to obtain component detection data.

[0022] In the above implementation process, the energy dispersive X-ray fluorescence spectrometer is used to detect the components of the cinnabar sample, which can quickly and non-destructively obtain the chemical composition data of the sample with simple operation and high detection efficiency.

[0023] In a second aspect, an embodiment of the present application provides a cinnabar quality identification device, the device comprising: A data acquisition module, used for acquiring sample data of cinnabar samples; An identification module is used to identify the quality of the cinnabar sample from a target dimension based on the sample data to obtain an identification result, wherein the target dimension includes at least two dimensions of composition, filler and surface structure.

[0024] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect above are executed.

[0025] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are executed.

[0026] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising computer program instructions, which, when read and executed by a processor, execute the steps in the method provided in the first aspect above.

[0027] Other features and advantages of the present application will be described in the following description and, in part, will become apparent from the description or be understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 A flow chart of a cinnabar quality identification method provided in an embodiment of the present application; Figure 2 A schematic diagram of a calibration curve between element content and fluorescence intensity provided in an embodiment of the present application; Figure 3 A schematic diagram of a standard fluorescent image of different filler content ranges provided in an embodiment of the present application; Figure 4 A schematic diagram of a standard surface structure image of different surface structures provided in an embodiment of the present application; Figure 5 This is a structural block diagram of a cinnabar quality identification device provided in an embodiment of the present application; Figure 6 A schematic structural diagram of an electronic device for executing a cinnabar quality identification method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application.

[0031] It should be noted that the terms "system" and "network" in the embodiments of the present invention are used interchangeably. "Multiple" refers to two or more. In view of this, in the embodiments of the present invention, "multiple" can also be understood as "at least two." "And / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the related objects are in an "or" relationship.

[0032] It should also be noted that all actions of obtaining signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0033] An embodiment of the present application provides a cinnabar quality identification method, which obtains sample data of the cinnabar sample and then identifies the quality of the cinnabar sample from a target dimension based on the sample data to obtain an identification result. The target dimension may include at least two dimensions of composition, filler and surface structure. In this way, the quality of the cinnabar sample can be combined and judged from multiple dimensions, which can improve the accuracy and reliability of the identification result, thereby achieving an accurate evaluation of the quality of the cinnabar sample.

[0034] Please refer to Figure 1 , Figure 1 A flow chart of a cinnabar quality identification method provided in an embodiment of the present application, the method comprising the following steps: Step S110: Acquire sample data of the cinnabar sample.

[0035] The cinnabar sample can refer to the cinnabar jewelry to be identified, or can also be referred to as powdered cinnabar jewelry. This solution can identify the quality of the cinnabar sample and distinguish between powdered cinnabar and imitation cinnabar.

[0036] In some embodiments, the sample data may refer to relevant attribute information of the cinnabar sample, such as the sample data may include at least two of component detection data, filler detection data, and surface structure feature detection data.

[0037] Composition data refers to the composition of the cinnabar sample, such as the various elements and their content, for example, heavy metals and cinnabar elements. Filler data refers to the organic matter filling the cinnabar sample, such as the resin filler content. Surface structure data refers to the surface structure of the cinnabar sample, such as the presence of mineral particles.

[0038] In order to make a more comprehensive and accurate assessment of the quality of the cinnabar sample, at least two types of sample data mentioned above may be obtained for assessment.

[0039] The cinnabar quality identification method of this solution can be executed by a server or a terminal device, and the sample data can be sent to the server or the terminal device by an external device, or can also be uploaded manually.

[0040] Step S120: According to the sample data, the quality of the cinnabar sample is identified from the target dimension to obtain an identification result.

[0041] The target dimensions can include at least two of the following: composition, filler, and surface structure. This sample data can reflect the quality of the cinnabar sample, such as the presence and degree of defects. This allows for a multi-dimensional assessment of the quality of the cinnabar sample, helping consumers or merchants accurately judge the quality of cinnabar jewelry and providing data reference for sales strategies.

[0042] In some embodiments, if the sample data includes component detection data, filler detection data, and surface structure feature detection data, the quality of the cinnabar sample can be identified based on these three dimensions: component, filler, and surface structure. Regarding the component dimension, the quality of the cinnabar sample can be identified based on the component detection data; regarding the filler dimension, the quality of the cinnabar sample can be identified based on the filler detection data; and regarding the surface structure dimension, the quality of the cinnabar sample can be identified based on the surface structure feature detection data. In other words, identification can be performed using at least one sample data point corresponding to each dimension.

[0043] The identification result may include the quality level of the cinnabar sample, for example, a higher quality level indicates a better quality cinnabar sample, and conversely, a lower quality level indicates a worse quality cinnabar sample, such as imitation cinnabar. Alternatively, the identification result may include whether the quality of the cinnabar sample is qualified, that is, qualified or unqualified, where qualified indicates a good quality cinnabar sample and unqualified indicates a poor quality cinnabar sample, such as imitation cinnabar.

[0044] In the above implementation process, by comprehensively identifying the cinnabar sample from at least two dimensions of composition, filling material and surface structure, the accuracy and reliability of the identification result can be improved, thereby achieving an accurate assessment of the quality of the cinnabar sample.

[0045] On the basis of the above embodiment, in order to comprehensively detect the quality of cinnabar samples, the quality of cinnabar samples can be identified from various dimensions according to the sample data, the identification results corresponding to each dimension can be determined, and then the final identification result can be determined based on the various identification results.

[0046] For example, in the component dimension, when identifying cinnabar samples based on component detection data, if the component detection data includes heavy metal content (such as lead (Pb), arsenic (As), etc.) and cinnabar (mercury (Hg)) content, if the heavy metal content is greater than or equal to the set content, the identification result is determined to be unqualified, otherwise it is qualified.

[0047] In the filler dimension, when identifying cinnabar samples based on filler detection data, it can be determined whether the filler content or filler degree meets the requirements. If the filler content is greater than or equal to the set threshold, the identification result is determined to be unqualified, otherwise it is qualified.

[0048] In the surface structure dimension, when identifying cinnabar samples based on surface structure feature detection data, it can be determined whether the surface structure features are obvious mineral particles. If there are obvious mineral particles on the surface of the cinnabar sample, the identification result is determined to be unqualified, otherwise it is qualified.

[0049] When determining the final identification result of the cinnabar sample by combining various identification results, if any one identification result is unqualified, the final identification result can be determined to be unqualified; if all identification results are qualified, the final identification result can be determined to be qualified.

[0050] In this implementation, the quality of cinnabar samples is identified across multiple dimensions, and the final conclusion is drawn based on the combined results from each dimension, effectively improving the comprehensiveness and accuracy of the identification. This identification method allows for a more detailed analysis of the different characteristics of cinnabar samples, avoiding details that might be overlooked in single-dimensional testing, and thus enabling a more accurate assessment of their quality.

[0051] On the basis of the above embodiment, if the detection data includes three types of detection data: component detection data, filler detection data and surface structure feature detection data, when identifying the quality of cinnabar samples, the three types of detection data can be sorted according to the degree of influence on the quality. For example, if the component detection data has a greater impact on the quality of the cinnabar sample, the quality of the cinnabar sample can be identified first based on the component detection data. If the identification is unqualified, there is no need to use other detection data for identification. If it is qualified, other detection data can be used for identification.

[0052] In practical applications, it has been found that component testing primarily reflects the internal chemical properties of cinnabar samples and is the fundamental factor affecting product quality. Filler testing focuses on the impact of fillers such as resin within the sample's internal structure on quality. Surface structure testing assesses the sample's external physical characteristics. Composition is fundamental to determining cinnabar sample quality. If the composition does not meet requirements, other aspects of testing become meaningless. Fillers and surface structure, on top of qualified ingredients, further influence the product's texture and durability.

[0053] Therefore, when performing identification, the quality of the cinnabar sample can be identified from the corresponding dimension according to the determined identification order rules and the sample data to determine the identification result corresponding to the dimension.

[0054] The identification order rules may be pre-set and stored, or determined based on the characteristics of the cinnabar sample, or determined by analyzing the degree of influence of each dimension in the target dimension on the quality of the cinnabar.

[0055] For example, the identification order is to proceed from component to filler to surface structure. Only when the component identification results meet the requirements can the filler identification be performed. Only when the filler identification results meet the requirements can the surface structure identification be performed. This testing sequence can be performed from the inside out, following the hierarchy of quality influences, enabling a more systematic and comprehensive quality assessment of cinnabar samples.

[0056] In the implementation described above, by following the identification sequence rules, jewelry with excessive heavy metal content and low cinnabar content can be eliminated first, avoiding wasted resources in subsequent testing. Filler testing is then used to further eliminate counterfeits. Finally, surface structure testing is performed to complete the quality rating. This three-step process is based on the degree of destructiveness, efficiency, cost, and purpose of the test, ensuring the entire testing process is efficient, accurate, and cost-effective.

[0057] Based on the above embodiment, the identification order rules may include: when the identification result corresponding to the component dimension meets the first set requirement, the quality of the cinnabar sample is continued to be identified from the filler dimension to determine the corresponding identification result; when the identification result corresponding to the filler dimension meets the second set requirement, the quality of the cinnabar sample is continued to be identified from the surface structure dimension to determine the corresponding identification result.

[0058] For example, a cinnabar sample can be identified based on component testing data. For example, if the component testing data includes heavy metal content (such as Pb and As) as well as cinnabar content, if the heavy metal content is less than the set content, the cinnabar sample is considered to meet the first set requirement and is considered qualified. If the heavy metal content is greater than or equal to the set content, the cinnabar sample is considered to fail the first set requirement and is considered unqualified. At this point, identification can be performed based on filler testing data. If the component testing data determines that the sample is unqualified, the identification process ends, and the final identification result is unqualified.

[0059] The filler test data may include the resin filler content. If the resin filler content is less than a set threshold, the cinnabar sample is considered to meet the second set requirement and be qualified. If the resin filler content is greater than or equal to the set threshold, the cinnabar sample is considered to fail the second set requirement and be unqualified. At this point, further identification can be performed based on the surface structure feature test data. If the filler test data determines that the quality is unqualified, the identification process ends, and the final identification result is unqualified.

[0060] Surface structural feature detection data may include mineral particle detection on the surface of the cinnabar sample. If fine mineral particles are present, the identification result is unqualified; otherwise, the quality is qualified. If the surface structural feature detection data determines that the quality is unqualified, the final identification result will be unqualified. If the quality is qualified, the final identification result will be qualified.

[0061] In the above implementation process, this hierarchical screening method can quickly exclude samples that do not meet the basic requirements and avoid unnecessary subsequent testing, thereby improving detection efficiency and saving resources.

[0062] Based on the above embodiment, the sample data may include component testing data, in which case the first set requirement may be that the cinnabar content in the component testing data is greater than or equal to a first set content and the heavy metal content is less than a second set content; and / or, if the sample data includes filler testing data, the second set requirement may be that the filler content in the filler testing data is less than a third set content. For example, the values ​​of the first set content, the second set content, and the third set content can be determined based on the level of stringency required in actual practice. For example, the first set content may be 50%, the second set content may be 0.1%, and the third set content may be 50%.

[0063] Among them, HgS powder can be added to imitation cinnabar (such as "cinnabar content 10% + barite 90%"). If the component analysis test still shows that it contains Hg, the "fake cinnabar" will be misjudged as powdered cinnabar. Therefore, comprehensive identification can be carried out based on the heavy metal content and HgS content.

[0064] Specifically, when the heavy metal content in the component test data is greater than or equal to 0.1%, the corresponding identification result is unqualified. When the heavy metal content is less than 0.1%, the corresponding identification result can be determined based on the cinnabar (HgS) content. The rules are as follows: When the HgS content is ≥ 90%, the identification level is A; When 90% > HgS content ≥ 70%, the identification level is B; When 70% > HgS content ≥ 50%, the identification level is C; When the HgS content is less than 50%, the identification grade is D, and it is judged as "imitation cinnabar", and the identification process ends.

[0065] An identification grade of D is the lowest grade. In some embodiments, the identification result may be qualified when the identification grade is A, B, or C, and may be unqualified when the identification grade is D. If the identification result determined based on the component test data is qualified, that is, the first set requirement is met, then subsequent testing can be continued.

[0066] For identification based on filler test data, the rules for determining the identification results are as follows: No or low-filled resin (filler content <10%), fluorescence intensity: none-weak, then the identification level is A; For resins with a medium filling content (30%> filler content ≥ 10%), the fluorescence intensity is medium, and the identification grade is B; High resin content (filler content ≥30%), fluorescence intensity: strong, the identification grade is C; Heavily filled resin (e.g. filler content ≥50%), with abnormal fluorescence, such as strong red fluorescence (due to the presence of organic dyes), is judged as "imitation cinnabar", and the identification level is D, ending the identification process.

[0067] An identification grade of D is the lowest grade. In some embodiments, the identification result may be qualified when the identification grade is A, B, or C, and unqualified when the identification grade is D. If the identification grade determined based on the filling material test data is not D, the identification result is qualified, i.e., the second set requirement is met, and subsequent testing can be continued.

[0068] When identifying based on surface structure feature detection data, a 3D super-depth-of-field digital microscope can be used to photograph the surface of the sample with a fixed magnification of 200×. Each sample can be photographed from multiple different angles to obtain the surface structure image of the cinnabar sample. The surface structure image is then tested, such as extracting image features from the surface structure image and judging the mineral particle condition on the sample surface based on the image features.

[0069] The rules for determining the identification results based on the mineral particles are as follows: At 200×, if the mineral particles are almost invisible in the image and there are no obvious boundaries, the identification grade is A; At 200×, if mineral particles are visible in the image and fuzzy boundaries are visible, the identification grade is B; At 200×, if obvious mineral particles and clear boundaries are visible in the image, the identification grade is C.

[0070] In some embodiments, when the identification level is C, it may indicate that the quality is unqualified, and other identification levels indicate that the quality is qualified. In this way, the final identification result can be determined based on the identification results corresponding to each test data. For example, when the identification result determined based on the surface structure feature test data is qualified, the final identification result is qualified. When the identification result determined based on the surface structure feature test data is unqualified, the final identification result is unqualified. Because the surface structure feature test data will be used for identification only when the identification results determined based on the component test data and the filler test data are both qualified, it is only necessary to judge the last identification result.

[0071] In some embodiments, when determining the identification result based on the mineral particle condition, if the identification grade is C, the identification result can also be considered qualified. That is, when the identification is carried out according to the above identification sequence and the identification is carried out based on the mineral particle condition, it means that the identification results of the previous two dimensions are qualified, and the mineral particles do not significantly affect the quality of cinnabar. Therefore, even if the identification grade is C, it can be considered a qualified cinnabar sample and classified as powdered cinnabar. The distinction of identification grades here can provide a reference basis for the subsequent evaluation of the grade of cinnabar samples.

[0072] In some embodiments, the final identification result can also be determined by the identification level determined by each test data. For example, the final identification result can also be characterized by a level, and the levels are from high to low, namely, collection level, boutique level, priority level, and ordinary level. The specific determination can be made according to the following rules:

[0073] In addition, when the identification grade determined by the component detection data and / or the filling material detection data is D, the final identification result may be an unqualified grade.

[0074] Of course, the specific identification level determination rules and the final identification result determination rules can be flexibly set according to actual conditions. The above method is only an example. In actual application, different identification rules can be flexibly selected according to identification requirements.

[0075] In the above implementation process, by clearly setting specific requirements for composition and filler content, a quantitative standard is provided for the quality identification of cinnabar samples.

[0076] Based on the above embodiments, the above-mentioned component detection data, filling detection data and surface structure feature detection data can all be obtained from the cinnabar sample. If the sample data includes component detection data, the target dimension includes the component dimension. At this time, an energy dispersive X-ray fluorescence spectrometer can be used to detect the components of the cinnabar sample and obtain the component detection data.

[0077] In practice, the instrument should be turned on and preheated according to the instrument's operating manual. This typically takes 30 minutes to an hour to ensure stable instrument parameters and improve the accuracy and repeatability of test results. The instrument's excitation conditions, such as X-ray tube voltage and current, as well as detector parameters, should be set based on the characteristics of the cinnabar jewelry and the testing requirements. Generally speaking, for elements commonly found in cinnabar, such as mercury / cinnabar (Hg), sulfur (S), lead (Pb), and arsenic (As), appropriate excitation voltage and current ranges are required to achieve sufficient fluorescence signal intensity and good energy resolution.

[0078] Before testing, the instrument can be calibrated using standard samples of known composition. These standard samples should contain components similar to the elements and their content ranges that may be present in cinnabar jewelry. By measuring the standard samples, a calibration curve between element content and fluorescence intensity can be established, such as Figure 2 As shown, this ensures that the instrument can accurately and quantitatively analyze the chemical components in the sample.

[0079] During testing, a cinnabar sample is placed on the instrument's sample test platform, ensuring the test site is flatly in contact with the test window and the sample surface is perpendicular to the instrument's optical path to ensure optimal X-ray excitation and fluorescence signal reception. The instrument's test program is then activated, and X-ray fluorescence excitation and signal acquisition are performed on the test site according to pre-set parameters. During the test, the instrument automatically records the energy and intensity of the fluorescent X-rays and converts them into corresponding data signals.

[0080] Multiple test sites can be selected for testing. The test time for each site is generally set according to the specific situation, usually several minutes to more than ten minutes, to ensure sufficient signal strength and statistical accuracy. After the test is completed, the instrument automatically performs preliminary processing and analysis on the collected data, stores the results in the computer, and generates a corresponding energy spectrum or composition analysis report.

[0081] The collected X-ray fluorescence spectrum data can then be subjected to background subtraction to remove background signals caused by instrument noise, scattering, and other factors, thereby improving spectrum quality and analytical accuracy. Peak identification is then performed on the background-subtracted spectrum using the instrument's accompanying analysis software or specialized spectrum analysis software. Based on the characteristic X-ray energies of known elements, the elements present in the sample and their corresponding fluorescence peak positions are determined. Subsequently, by comparing the concentrations of each element with the calibration curve, quantitative analysis is performed to determine the concentrations of elements such as Hg, S, Pb, and As in the sample.

[0082] Finally, the chemical composition data from multiple test sites can be integrated to calculate statistical parameters such as the mean and standard deviation of each element's content to assess the stability and reliability of the test results. If there are significant discrepancies between the test results of multiple sites, further analysis is required. This may be due to uneven sample composition or interference factors during the test. Appropriate measures can be taken based on the actual situation, such as adding test sites or recalibrating the instrument.

[0083] In other embodiments, the purity can also be semi-quantitatively analyzed by the HgS characteristic peak (250 cm⁻¹), so that the composition detection data can also be obtained.

[0084] In the above implementation process, the energy dispersive X-ray fluorescence spectrometer is used to detect the components of the cinnabar sample, which can quickly and non-destructively obtain the chemical composition data of the sample with simple operation and high detection efficiency.

[0085] On the basis of the above embodiment, the filling material detection data and the surface structure feature detection data can be directly detected on the cinnabar sample.

[0086] For example, in the implementation method of obtaining filler detection data, a sample image of a cinnabar sample can be taken under ultraviolet light, and then fluorescent features can be identified from the sample image. Because ultraviolet light can stimulate the fluorescent reaction of organic matter, the filling degree of the filler can be identified through the fluorescent features, that is, the filler detection data can include the filling degree, and then the identification result or identification level can be determined based on the filling degree.

[0087] For example, the fluorescence characteristics can reflect the distribution of organic matter on gemstone samples, such as the distribution area, distribution position, distribution shape, etc. Therefore, the distribution of organic matter can be determined based on the fluorescence characteristics, and then the degree of organic matter filling can be determined based on the distribution of organic matter. Of course, the filler content can also be determined based on the distribution of organic matter. For example, different distribution areas correspond to different filler contents, and the filler content is positively correlated with the filling degree.

[0088] For example, the degree of organic matter filling can be determined based on the distribution area of ​​the fluorescence feature. If the distribution area is less than a set threshold, the organic matter filling is determined to be lightly filled, and the corresponding filler content is less than a set content (e.g., 50%). In this case, the corresponding identification result is qualified. If the distribution area is greater than or equal to the set threshold, the organic matter filling is determined to be heavily filled, and the corresponding filler content is greater than or equal to the set content (e.g., 50%). The corresponding identification result is unqualified. The judgment of the distribution position or distribution shape can also be similar. For example, if the distribution position is at the edge of the cinnabar sample, the organic matter filling is determined to be lightly filled, and the corresponding identification result is qualified. If the distribution position is in the middle of the cinnabar sample, the organic matter filling is determined to be heavily filled, and the corresponding identification result is unqualified. Alternatively, if the distribution shape is a specific shape (e.g., dotted, short line, etc.), the organic matter filling is determined to be lightly filled, and the corresponding identification result is qualified. Otherwise, it is heavily filled, and the corresponding identification result is unqualified.

[0089] In some embodiments, the obtained fluorescence signature can also be input into a neural network model, which can then be used to identify the degree of organic matter filling. For example, a convolutional neural network model or a long short-term memory network model can be used to identify the correlation between the fluorescence signature and the degree of organic matter filling or filler content. This allows the neural network model to accurately predict the degree of organic matter filling or filler content. The degree of organic matter filling output by the neural network model can be represented by a numerical value, such as a value between 0 and 1, where 0 represents no filling and 1 represents complete filling, with larger values ​​indicating greater filling.

[0090] In some embodiments, the filling degree can also be determined based on the area ratio of the fluorescent region where the fluorescent feature is located in the cinnabar sample. If the area ratio is greater than the set ratio, it can be determined that the organic matter filling degree of the cinnabar sample is heavily filled, and the corresponding identification result is unqualified. Otherwise, it is lightly filled, and the corresponding identification result is qualified.

[0091] Of course, the specific filling degree distinction can be flexibly set according to the actual situation. In addition, different filling degrees can correspond to different identification levels, which can be set according to actual needs.

[0092] In an implementation method for obtaining surface structural feature detection data, an image of the cinnabar sample can be obtained, and then the surface structural features can be extracted from the image. For example, a neural network model, such as a convolutional neural network model, can be used to extract the surface structural features from the image. Based on the surface structural features, corresponding surface structural feature detection data can be determined, such as the detection data including the size of the mineral particles and the visibility of the corresponding particles. The corresponding identification result can then be determined based on the detection data according to the aforementioned identification rules.

[0093] In some other embodiments, in order to quickly obtain the identification results corresponding to the filler dimension, the sample data at this time may include a fluorescence image of the cinnabar sample, and the target dimension includes the filler dimension. When determining the identification result, the fluorescence image of the cinnabar sample can be obtained, and then the fluorescence image is compared with the standard fluorescence images of different filler contents to determine the target standard fluorescence image with the highest similarity to the fluorescence image, wherein each standard fluorescence image is marked with a corresponding identification result, and then the identification result corresponding to the target standard fluorescence image is determined as the identification result corresponding to the filler dimension.

[0094] For example, a 365nm ultraviolet light source can be used to capture images of cinnabar samples from different angles under the uniform environment of a standard light box to obtain fluorescence images. The standard fluorescence image library contains standard fluorescence images of different filler contents, such as standard fluorescence images with filler contents less than 10%, with no or weak fluorescence intensity; standard fluorescence images with filler contents less than 30% and greater than or equal to 10%, with medium fluorescence intensity; standard fluorescence images with filler contents greater than or equal to 30%, with strong fluorescence intensity; and standard fluorescence images with strong red fluorescence, with abnormal fluorescence, corresponding to imitation cinnabar. Of course, the filler content of this standard fluorescence image may be greater than or equal to 50% (the specific value can be determined based on experiments).

[0095] In the standard fluorescence image library, there are multiple standard fluorescence images for different filler content ranges. These standard fluorescence images are all obtained under the uniform environment of a standard light box, using a 365nm ultraviolet light source and the same shooting parameters. Figure 3 As shown, the standard fluorescence images of different filler content ranges are marked with corresponding identification results, such as identification grades. For example, the standard fluorescence image with a filler content of less than 10% has an identification grade of A.

[0096] Therefore, the fluorescence image of the cinnabar sample can be directly compared with the standard fluorescence image one by one, and the filling detection data and identification level can be determined based on the comparison results.

[0097] During the comparison, the fluorescence image can be compared with various standard fluorescence images for similarity, such as by using an image hash algorithm, or by using a neural network model. For example, the fluorescence image and all standard fluorescence images are input into the neural network model, and the neural network model predicts the target standard fluorescence image with the highest similarity to the fluorescence image. In this way, the target standard fluorescence image with the highest similarity to the fluorescence image can be determined, and the filler content of the target standard fluorescence image can be determined. The filler content can be used as the filler detection data of the cinnabar sample, and the identification level of the target standard fluorescence image can also be determined. In this way, the identification level obtained from the filler dimension can be directly determined, that is, the corresponding filler detection data and identification level can be determined through image comparison.

[0098] For example, the target standard fluorescent image with the highest similarity to the fluorescent image is a standard fluorescent image with a filler content of less than 10%. The identification level of this image mark is A, so it can be determined that the filler detection data is a filler content of less than 10%, and the identification result corresponding to the filler dimension is identification level A.

[0099] In this implementation, the fluorescence image can intuitively reflect the sample's fluorescence characteristics. Since fluorescence intensity is closely related to filler content, comparison with a standard fluorescence image allows for rapid and accurate determination of the filler content range, enabling quantitative identification of filler dimensions. This method, which eliminates the need for complex chemical analysis or destructive testing, is simple and efficient. It also provides an intuitive and reliable basis for evaluating the quality of cinnabar samples, effectively improving identification accuracy and efficiency.

[0100] In some other embodiments, in order to quickly obtain the identification result corresponding to the surface result dimension, the sample data at this time may include the surface structure image of the cinnabar sample, and the target dimension includes the surface structure dimension. When determining the identification result, the surface structure image of the cinnabar sample can be obtained first, and then the surface structure image can be compared with the standard surface structure image of different surface structures to determine the target standard surface structure image with the highest similarity to the surface structure image, wherein each standard surface structure image is marked with a corresponding identification result, and then the identification result corresponding to the target standard surface structure image is determined as the identification result corresponding to the surface structure dimension.

[0101] Surface structure images of cinnabar samples can be acquired from different angles using a 3D ultra-depth-of-field digital microscope under uniform parameters. These images are then stored in a standard structure image library. This library contains standard surface structure images of varying surface structures, including images with virtually no visible mineral grains and no distinct boundaries, images with visible mineral grains and fuzzy boundaries, and images with distinct mineral grains and clear boundaries.

[0102] There are multiple standard surface structure images for different surface structures in the standard structure image library. These standard surface structure images are all obtained by shooting with the same shooting parameters under the same environment, such as Figure 4 As shown, the standard surface structure images of different surface structures are marked with corresponding identification results, such as identification levels. For example, in the above image, the standard surface structure image with almost no visible mineral particles and no obvious boundaries has an identification level of A.

[0103] Therefore, the surface structure image of the cinnabar sample can be directly compared with the standard surface structure image one by one, and the surface structure detection data and identification level can be determined based on the comparison results.

[0104] When comparing here, the surface structure image can be compared with each standard surface structure image for similarity, such as using an image hash algorithm for similarity comparison, or determined through a neural network model, such as inputting the surface structure image and all standard surface structure images into the neural network model, and using the neural network model to predict the target standard surface structure image with the highest similarity to the surface structure image. In this way, the target standard surface structure image with the highest similarity to the surface structure image can be determined, and the mineral particle situation of the target standard surface structure image can be determined. The mineral particle situation can be used as the surface structure feature detection data of the cinnabar sample, and the identification level to which the target standard surface structure image belongs can also be determined. In this way, the identification level obtained from the surface structure dimension can be directly determined, that is, the corresponding surface structure feature detection data and identification level can be determined by image comparison.

[0105] For example, the target standard surface structure image with the highest similarity to the surface structure image is a standard surface structure image with almost no visible mineral particles and no obvious boundaries in the image. The identification level of this image mark is A, so it can be determined that the surface structure feature detection data is almost no visible mineral particles and no obvious boundaries, and the identification result corresponding to the surface structure dimension is identification level A.

[0106] In this implementation, image comparison technology enables intuitive assessment of sample characteristics such as structural density and particle distribution, allowing for rapid determination of quality. This method, which requires no complex physical or chemical analysis, is simple and efficient. It also provides an intuitive and reliable basis for evaluating the quality of cinnabar jewelry, effectively improving identification accuracy and efficiency.

[0107] During the above identification, the component detection data, the filling detection data and the surface structure feature detection data can also be fused into multi-dimensional data to construct a composite discrimination model.

[0108] For example, analyzing the correlation between composition and surface structure. For example, if the cinnabar content in the composition is high (for example, the identification grade is A) but the mineral particles in the surface structure are obvious (for example, the identification grade is C), this may also indicate a processing defect and require downgrading.

[0109] Correlation analysis is performed between the components and fillers. For example, if the cinnabar content in the components is high (for example, the identification grade is A) but the filler content is high (for example, the identification grade is D), it will trigger the judgment of imitation products to avoid adulteration and missed detection.

[0110] Through data cross-validation, the problem of single technology being susceptible to interference (such as imitations adding trace amounts of HgS powder to deceive identification results) is solved, and the robustness of identification is significantly improved.

[0111] In some implementations, to improve analysis accuracy, subsequent testing parameters and processes can be dynamically adjusted based on the results of previous steps, creating a closed-loop optimization loop. For example, if the compositional testing data indicates that the cinnabar content is close to a threshold (e.g., 50%), the intensity of the fluorescence test light source (i.e., the light source intensity during filler testing) is automatically increased to more sensitively detect abnormal filler content. If surface structure analysis reveals visible mineral particles in the image and the identification grade is C, redundant steps are skipped and the sample is directly classified as normal, improving efficiency.

[0112] This can make the detection process intelligent and efficient, avoid the waste of resources in traditional linear processes, and is particularly suitable for large-scale detection scenarios.

[0113] Please refer to Figure 5 , Figure 5 This is a structural block diagram of a cinnabar quality identification device 200 provided in an embodiment of the present application. The device 200 may be a module, program segment or code on an electronic device. It should be understood that the device 200 is similar to the above-mentioned Figure 1 The method embodiment corresponds to the embodiment that can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device 200 can be found in the description above. To avoid repetition, detailed description is appropriately omitted here.

[0114] Optionally, the apparatus 200 includes: The data acquisition module 210 is used to acquire sample data of the cinnabar sample; The identification module 220 is used to identify the quality of the cinnabar sample from a target dimension based on the sample data to obtain an identification result, wherein the target dimension includes at least two dimensions of composition, filler and surface structure.

[0115] Optionally, the identification module 220 is configured to identify the quality of the cinnabar sample from various dimensions based on the sample data, determine an identification result corresponding to each dimension, and determine a final identification result based on each identification result.

[0116] Optionally, the identification module 220 is configured to identify the quality of the cinnabar sample from a corresponding dimension according to the sample data in accordance with a determined identification sequence rule, and determine an identification result corresponding to the dimension.

[0117] Optionally, the identification order rules include: When the identification result corresponding to the component dimension meets the first set requirement, the quality of the cinnabar sample is further identified from the filler dimension to determine the corresponding identification result; when the identification result corresponding to the filler dimension meets the second set requirement, the quality of the cinnabar sample is further identified from the surface structure dimension to determine the corresponding identification result.

[0118] Optionally, the sample data includes component detection data, and the first set requirement is that the cinnabar content in the component detection data is greater than or equal to a first set content and the heavy metal content is less than a second set content; And / or, the sample data includes filler detection data, and the second setting requirement is that the filler content in the filler detection data is less than a third set content.

[0119] Optionally, the sample data includes a fluorescence image of the cinnabar sample, the target dimension includes a filler dimension, and the identification module 220 is used to obtain a fluorescence image of the cinnabar sample; compare the fluorescence image with standard fluorescence images of different filler contents, and determine a target standard fluorescence image with the highest similarity to the fluorescence image, wherein each standard fluorescence image is marked with a corresponding identification result; and determine that the identification result corresponding to the target standard fluorescence image is the identification result corresponding to the filler dimension.

[0120] Optionally, the sample data includes a surface structure image of the cinnabar sample, the target dimension includes a surface structure dimension, and the identification module 220 is used to obtain the surface structure image of the cinnabar sample; compare the surface structure image with standard surface structure images of different surface structures, and determine the target standard surface structure image with the highest similarity to the surface structure image, wherein each standard surface structure image is marked with a corresponding identification result; and determine that the identification result corresponding to the target standard surface structure image is the identification result corresponding to the surface structure dimension.

[0121] Optionally, the sample data includes component detection data, the target dimension includes component dimension, and the data acquisition module is used to use an energy dispersive X-ray fluorescence spectrometer to detect the components of the cinnabar sample and obtain the component detection data.

[0122] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0123] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device for performing a cinnabar quality identification method provided in an embodiment of the present application. The electronic device may include: at least one processor 310, such as a CPU, at least one communication interface 320, at least one memory 330, and at least one communication bus 340. The communication bus 340 is used to enable communication between these components. The communication interface 320 of the device in this embodiment of the present application is used to communicate signaling or data with other node devices. The memory 330 may be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The memory 330 may optionally be at least one storage device located remotely from the processor. The memory 330 stores computer-readable instructions. When the processor 310 executes these computer-readable instructions, the electronic device performs the method described above.

[0124] I understand. Figure 6 The structure shown is only for illustration, and the electronic device may also include Figure 6 More or fewer components than shown, or with Figure 6 Different configurations shown. Figure 6 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0125] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method process executed by the electronic device in the method embodiment shown above is executed.

[0126] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the methods provided in the above method embodiments, for example, including: Obtain sample data for the cinnabar sample; According to the sample data, the quality of the cinnabar sample is identified from a target dimension to obtain an identification result, wherein the target dimension includes at least two dimensions of composition, filler and surface structure.

[0127] In summary, the embodiments of the present application provide a cinnabar quality identification method, device, electronic device and storage medium. This method can improve the accuracy and reliability of the identification results by comprehensively identifying cinnabar samples from at least two dimensions: composition, filler and surface structure, thereby achieving accurate evaluation of the quality of cinnabar samples.

[0128] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0129] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0131] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0132] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for identifying the quality of cinnabar, characterized in that: The method comprises: Obtain sample data for the cinnabar sample; According to the sample data, the quality of the cinnabar sample is identified from a target dimension to obtain an identification result, wherein the target dimension includes at least two dimensions of composition, filler and surface structure.

2. The method according to claim 1, characterized in that The method of identifying the quality of the cinnabar sample from a target dimension based on the sample data to obtain an identification result includes: According to the sample data, the quality of the cinnabar sample is identified from various dimensions, and an identification result corresponding to each dimension is determined; The final identification result is determined based on the individual identification results.

3. The method according to claim 2, characterized in that The method of identifying the quality of the cinnabar sample from various dimensions based on the sample data and determining the identification result corresponding to each dimension includes: According to the determined identification order rule and based on the sample data, the quality of the cinnabar sample is identified from the corresponding dimension to determine the identification result corresponding to the dimension.

4. The method according to claim 3, characterized in that The identification order rules include: When the identification result corresponding to the component dimension meets the first set requirement, the quality of the cinnabar sample is further identified from the filler dimension to determine the corresponding identification result; when the identification result corresponding to the filler dimension meets the second set requirement, the quality of the cinnabar sample is further identified from the surface structure dimension to determine the corresponding identification result.

5. The method according to claim 4, characterized in that The sample data includes component detection data, and the first setting requirement is that the cinnabar content in the component detection data is greater than or equal to a first set content and the heavy metal content is less than a second set content; And / or, the sample data includes filler detection data, and the second setting requirement is that the filler content in the filler detection data is less than a third set content.

6. The method according to claim 2, characterized in that The sample data includes a fluorescent image of the cinnabar sample, the target dimension includes a filler dimension, and the quality of the cinnabar sample is identified from each dimension based on the sample data to determine an identification result corresponding to each dimension, including: acquiring a fluorescence image of the cinnabar sample; Comparing the fluorescent image with standard fluorescent images of different filler contents to determine a target standard fluorescent image having the highest similarity to the fluorescent image, wherein each standard fluorescent image is marked with a corresponding identification result; Determine the identification result corresponding to the target standard fluorescent image as the identification result corresponding to the filler dimension.

7. The method according to claim 2, characterized in that The sample data includes a surface structure image of the cinnabar sample, the target dimension includes a surface structure dimension, and the quality of the cinnabar sample is identified from each dimension based on the sample data to determine an identification result corresponding to each dimension, including: Acquiring a surface structure image of the cinnabar sample; Comparing the surface structure image with standard surface structure images of different surface structures to determine a target standard surface structure image having the highest similarity to the surface structure image, wherein each standard surface structure image is marked with a corresponding identification result; Determine the identification result corresponding to the target standard surface structure image as the identification result corresponding to the surface structure dimension.

8. The method according to claim 1, characterized in that The sample data includes component detection data, the target dimension includes a component dimension, and obtaining the sample data of the cinnabar sample includes: The components of the cinnabar sample are detected by energy dispersive X-ray fluorescence spectrometer to obtain component detection data.

9. A cinnabar quality identification device, characterized in that: The device comprises: A data acquisition module, used for acquiring sample data of cinnabar samples; An identification module is used to identify the quality of the cinnabar sample from a target dimension based on the sample data to obtain an identification result, wherein the target dimension includes at least two dimensions of composition, filler and surface structure.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 8 is executed.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is executed.

12. A computer program product, characterized in that The method comprises computer program instructions, and when the computer program instructions are read and executed by a processor, the method according to any one of claims 1 to 8 is executed.

Images