Amber provenance distinguishing method and device based on amber characteristics

Abstract

The application discloses a kind of amber origin distinguishing method and device based on amber characteristics, by obtaining the infrared reflectance spectroscopy data set of multiple origins of amber sample, generate amber origin classification model, through amber origin classification model to the origin classification of distinguishing amber sample, obtain first amber origin;While through the signal peak number and signal peak position in the nuclear magnetic resonance wave pop signal of distinguishing amber sample, compare it with the standard signal peak number and standard signal peak position of each origin, obtain second amber origin;And the maturity of distinguishing amber sample obtained is compared with first standard maturity, for verifying whether the predicted amber origin is correct, to obtain the amber origin of distinguishing amber sample.Compared with prior art, the technical scheme of the present application can improve the accuracy of distinguishing the origin of amber by predicting the origin of amber twice and verifying the prediction result by the maturity of the amber sample.

Description

Technical Field

[0001] This invention relates to the technical field of amber identification, and in particular to a method and apparatus for distinguishing the origin of amber based on its characteristics. Background Technology

[0002] Amber is found all over the world, but the most common amber varieties on the market come from four main sources: the Baltic Sea, the Dominican Republic, Myanmar, and Fushun, China. Since the commercial value of amber can vary greatly depending on its origin, identifying the origin of amber is of great significance to the amber industry.

[0003] Currently, when identifying the origin of amber, a single predictive method is commonly used, such as a single spectral analysis or a single chemical composition analysis. The origin of amber is directly determined based on the analysis results. However, although there are differences between amber from different regions, there are also cases where the differences are small. In such cases, relying solely on a single predictive method can easily lead to misidentification of the amber's origin, resulting in low accuracy in identifying the origin of amber. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and apparatus for identifying the origin of amber based on amber characteristics, thereby improving the accuracy of amber origin identification by verifying the amber origin predicted in a secondary manner.

[0005] To address the aforementioned technical problems, this invention provides a method for identifying the origin of amber based on its characteristics, comprising:

[0006] Amber samples from multiple origins were collected, and infrared reflectance spectral data corresponding to each amber sample were obtained to form an infrared reflectance spectral dataset. An original classification model was constructed, and the original classification model was trained based on the infrared reflectance spectral dataset to obtain an amber origin classification model.

[0007] Obtain the infrared reflectance spectrum data of the amber sample to be identified, and input the sample infrared reflectance spectrum data into the amber origin classification model to obtain the predicted first amber origin;

[0008] The nuclear magnetic resonance (NMR) spectrum signal of the amber sample to be identified is obtained, and the number and position of the signal peaks in the NMR spectrum signal are counted. The number and position of the signal peaks are compared with the number and position of the preset standard signal peaks. Based on the comparison results, the predicted second amber origin is obtained.

[0009] Determine whether the first amber origin and the second amber origin are the same. If so, perform stable isotope testing on the amber sample to be identified, calculate the maturity of the amber sample to be identified, and set a first standard maturity of the first amber origin based on the first amber origin. Compare the maturity with the first standard maturity. If the maturity is within the range of the first standard maturity, then the first amber origin is taken as the amber origin of the amber sample to be identified.

[0010] In one possible implementation, after determining whether the origin of the first amber and the origin of the second amber are the same, the process includes:

[0011] If the first amber origin and the second amber origin are different, then a stable isotope test is performed on the amber sample to be identified, and the maturity of the amber sample to be identified is calculated.

[0012] Based on the first amber origin, a first standard maturity of the first amber origin is obtained, and based on the second amber origin, a second standard maturity of the second amber origin is obtained. The maturity is then compared with the first standard maturity and the second standard maturity, respectively.

[0013] If the maturity is within the range of the first standard maturity and the maturity is not within the range of the second standard maturity, then the first amber origin is taken as the amber origin of the amber sample to be identified.

[0014] If the maturity is within the range of the second standard maturity and the maturity is not within the range of the first standard maturity, then the second amber origin shall be taken as the amber origin of the amber sample to be identified.

[0015] If the maturity level exists within both the first standard maturity level and the second standard maturity level, then the first weight value of the first amber origin and the second weight value of the second amber origin are calculated respectively. The first weight value and the second weight value are compared, and the amber origin of the amber sample to be identified is determined based on the comparison result.

[0016] In one possible implementation, the number and position of signal peaks in the nuclear magnetic resonance spectral signal are counted, and the number and position of signal peaks are compared with preset standard number and position of signal peaks, specifically including:

[0017] The nuclear magnetic resonance (NMR) spectrum signal of the amber sample to be distinguished is obtained, and the NMR spectrum signal is divided into three signal regions, wherein the three signal regions include a saturated carbon resonance signal region, an unsaturated carbon resonance signal region, and a carbonyl carbon resonance signal region;

[0018] Standard nuclear magnetic resonance (NMR) spectral signals of amber samples from different origins were obtained, and the standard NMR spectral signals were divided into three standard signal regions. Based on the standard signal regions, the number and position of standard signal peaks were set for the standard signal regions of each origin.

[0019] The number and location of signal peaks in each signal zone are counted, and the number and location of signal peaks corresponding to each signal zone are compared with the number and location of standard signal peaks corresponding to different production areas.

[0020] In one possible implementation, the number and position of the signal peaks are compared with preset standard number and position of signal peaks, respectively. Based on the comparison results, the predicted second amber origin is obtained, specifically including:

[0021] Calculate the first similarity between the number of signal peaks and the number of standard signal peaks, and calculate the second similarity between the position of the signal peak and the position of each standard signal peak.

[0022] Statistically analyze all first and second similarities for different amber origins, and determine the predicted second amber origin based on the statistical results.

[0023] In one possible implementation, the original classification model is trained based on the infrared reflectance spectrum dataset to obtain an amber origin classification model, specifically including:

[0024] The infrared reflectance spectrum dataset is divided into a training sample set and a test sample set according to a preset ratio;

[0025] The original classification model is trained based on the training sample set, and the trained original classification model is tested based on the test sample set to obtain the accuracy value of the original classification model during the training process. Based on the accuracy value, the amber origin classification model is determined.

[0026] In one possible implementation, stable isotope testing is performed on the amber sample to be identified, and the maturity of the amber sample is calculated, specifically including:

[0027] Stable isotope testing was performed on the amber sample to be identified to obtain the isotope ratio of the amber sample to be identified, and the standard isotope ratio of amber was also obtained.

[0028] The maturity of the amber sample to be identified is obtained by substituting the isotope ratio and the standard isotope ratio into the preset maturity calculation formula.

[0029] In one possible implementation, the maturity calculation formula is as follows:

[0030] The maturity calculation formula is as follows:

[0031]

[0032] In the formula, C represents maturity, and R... T R is the standard isotope ratio. t m represents the isotopic ratio of the amber sample to be resolved. t To determine the mass of the amber sample to be identified, m T Let a be the standard mass of amber, and α be a constant.

[0033] In one possible implementation, based on the first amber origin, a first standard maturity level for the first amber origin is set, specifically including:

[0034] When the first amber origin is Fushun, China, the first standard maturity is set at -19.78% to 24.42%.

[0035] When the first amber origin is the Dominican Republic, the first standard maturity is set at -23.60% to 26.01%.

[0036] When the first amber origin is Myanmar, the first standard maturity is set at -19.38% to 22.90%.

[0037] When the first amber origin is the Baltic region, the first standard maturity is set at -22.76% to 25.76%.

[0038] The present invention also provides an amber origin identification device based on amber characteristics, comprising: an amber origin classification model generation module, a first amber origin prediction module, a second amber origin prediction module, and an amber origin determination module;

[0039] The amber origin classification model generation module is used to collect amber samples from multiple origins, obtain infrared reflectance spectral data corresponding to each amber sample, obtain an infrared reflectance spectral dataset, construct an original classification model, and train the original classification model based on the infrared reflectance spectral dataset to obtain the amber origin classification model.

[0040] The first amber origin prediction module is used to acquire the infrared reflectance spectrum data of the amber sample to be identified, and input the infrared reflectance spectrum data of the sample into the amber origin classification model to obtain the predicted first amber origin.

[0041] The second amber origin prediction module is used to acquire the nuclear magnetic resonance spectral signal of the amber sample to be identified, count the number and position of the signal peaks in the nuclear magnetic resonance spectral signal, compare the number and position of the signal peaks with the preset standard number and position of the signal peaks, and obtain the predicted second amber origin based on the comparison results.

[0042] The amber origin determination module is used to determine whether the first amber origin and the second amber origin are the same. If so, a stable isotope test is performed on the amber sample to be identified, the maturity of the amber sample to be identified is calculated, and a first standard maturity of the first amber origin is set based on the first amber origin. The maturity is compared with the first standard maturity. If the maturity is within the range of the first standard maturity, the first amber origin is taken as the amber origin of the amber sample to be identified.

[0043] In one possible implementation, the amber origin determination module, after determining whether the first amber origin and the second amber origin are the same, includes:

[0044] If the first amber origin and the second amber origin are different, then a stable isotope test is performed on the amber sample to be identified, and the maturity of the amber sample to be identified is calculated.

[0045] Based on the first amber origin, a first standard maturity of the first amber origin is obtained, and based on the second amber origin, a second standard maturity of the second amber origin is obtained. The maturity is then compared with the first standard maturity and the second standard maturity, respectively.

[0046] If the maturity is within the range of the first standard maturity and the maturity is not within the range of the second standard maturity, then the first amber origin is taken as the amber origin of the amber sample to be identified.

[0047] If the maturity is within the range of the second standard maturity and the maturity is not within the range of the first standard maturity, then the second amber origin shall be taken as the amber origin of the amber sample to be identified.

[0048] If the maturity level exists within both the first standard maturity level and the second standard maturity level, then the first weight value of the first amber origin and the second weight value of the second amber origin are calculated respectively. The first weight value and the second weight value are compared, and the amber origin of the amber sample to be identified is determined based on the comparison result.

[0049] In one possible implementation, the second amber origin prediction module is used to count the number and position of signal peaks in the nuclear magnetic resonance spectral signal, and compare the number and position of signal peaks with preset standard number and position of signal peaks, specifically including:

[0050] The nuclear magnetic resonance (NMR) spectrum signal of the amber sample to be distinguished is obtained, and the NMR spectrum signal is divided into three signal regions, wherein the three signal regions include a saturated carbon resonance signal region, an unsaturated carbon resonance signal region, and a carbonyl carbon resonance signal region;

[0051] Standard nuclear magnetic resonance (NMR) spectral signals of amber samples from different origins were obtained, and the standard NMR spectral signals were divided into three standard signal regions. Based on the standard signal regions, the number and position of standard signal peaks were set for the standard signal regions of each origin.

[0052] The number and location of signal peaks in each signal zone are counted, and the number and location of signal peaks corresponding to each signal zone are compared with the number and location of standard signal peaks corresponding to different production areas.

[0053] In one possible implementation, the second amber origin prediction module is used to compare the number of signal peaks and the position of the signal peaks with preset standard signal peak numbers and positions, and obtain the predicted second amber origin based on the comparison results, specifically including:

[0054] Calculate the first similarity between the number of signal peaks and the number of standard signal peaks, and calculate the second similarity between the position of the signal peak and the position of each standard signal peak.

[0055] Statistically analyze all first and second similarities for different amber origins, and determine the predicted second amber origin based on the statistical results.

[0056] In one possible implementation, the amber origin classification model generation module is used to train the original classification model based on the infrared reflectance spectroscopy dataset to obtain the amber origin classification model, specifically including:

[0057] The infrared reflectance spectrum dataset is divided into a training sample set and a test sample set according to a preset ratio;

[0058] The original classification model is trained based on the training sample set, and the trained original classification model is tested based on the test sample set to obtain the accuracy value of the original classification model during the training process. Based on the accuracy value, the amber origin classification model is determined.

[0059] In one possible implementation, the amber origin determination module is used to perform stable isotope testing on the amber sample to be identified and calculate the maturity of the amber sample to be identified, specifically including:

[0060] Stable isotope testing was performed on the amber sample to be identified to obtain the isotope ratio of the amber sample to be identified, and the standard isotope ratio of amber was also obtained.

[0061] The maturity of the amber sample to be identified is obtained by substituting the isotope ratio and the standard isotope ratio into the preset maturity calculation formula.

[0062] In one possible implementation, the maturity calculation formula in the amber origin determination module is as follows:

[0063]

[0064] In the formula, C represents maturity, and R... T R is the standard isotope ratio. t m represents the isotopic ratio of the amber sample to be resolved. t To determine the mass of the amber sample to be identified, m T Let a be the standard mass of amber, and α be a constant.

[0065] In one possible implementation, the amber origin determination module is used to set a first standard maturity level for the first amber origin based on the first amber origin, specifically including:

[0066] When the first amber origin is Fushun, China, the first standard maturity is set at -19.78% to 24.42%.

[0067] When the first amber origin is the Dominican Republic, the first standard maturity is set at -23.60% to 26.01%.

[0068] When the first amber origin is Myanmar, the first standard maturity is set at -19.38% to 22.90%.

[0069] When the first amber origin is the Baltic region, the first standard maturity is set at -22.76% to 25.76%.

[0070] The present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the amber origin identification method based on amber characteristics as described in any of the preceding claims.

[0071] The present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the amber origin identification method based on amber characteristics as described in any of the preceding claims.

[0072] This invention provides a method and apparatus for identifying the origin of amber based on its characteristics. Compared with existing technologies, it has the following advantages:

[0073] By acquiring infrared reflectance spectral datasets of amber samples from multiple origins, an amber origin classification model is generated. This model is then used to classify the amber sample to be identified, yielding a first amber origin. Simultaneously, the number and position of signal peaks in the nuclear magnetic resonance (NMR) spectral signal of the amber sample are obtained and compared with standard signal peak numbers and positions for each origin, resulting in a second amber origin. The maturity of the amber sample is then compared with a first standard maturity level to verify the accuracy of the predicted origin, thus confirming the correct amber origin for the sample. Compared to existing technologies, this invention improves the accuracy of amber origin identification by performing a secondary prediction of amber origin and verifying the prediction results using the maturity of the amber sample. Attached Figure Description

[0074] Figure 1 This is a flowchart illustrating an embodiment of a method for identifying the origin of amber based on amber characteristics provided by the present invention.

[0075] Figure 2 This is a schematic diagram of an embodiment of an amber origin identification device based on amber characteristics provided by the present invention. Detailed Implementation

[0076] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0077] Example 1

[0078] See Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of a method for identifying the origin of amber based on amber characteristics provided by the present invention. Figure 1 As shown, the method includes steps 101-104, as detailed below:

[0079] Step 101: Collect amber samples from multiple origins, obtain infrared reflectance spectral data for each amber sample to obtain an infrared reflectance spectral dataset, construct an original classification model, and train the original classification model based on the infrared reflectance spectral dataset to obtain an amber origin classification model.

[0080] In one embodiment, amber samples were collected from multiple origins, including Fushun in China, the Dominican Republic, Myanmar, and the Baltic Sea; specifically, 200 amber samples were collected from each amber origin.

[0081] In one embodiment, infrared reflectance spectral data corresponding to each amber sample are collected using a Fourier transform infrared spectrometer, and corresponding origin labels are set based on the origin of each amber sample to generate an infrared reflectance spectral dataset with origin labels.

[0082] In one embodiment, before acquiring infrared reflectance spectral data, relevant parameters are set for the Fourier transform infrared spectrometer, including the spectral range of 300 cm⁻¹. -1 -3500cm -1 4cm resolution -1 The number of scans was 25.

[0083] In one embodiment, the infrared reflectance spectroscopy dataset is divided into a training sample set and a test sample set according to a preset ratio; the original classification model is trained based on the training sample set, and the trained original classification model is tested based on the test sample set to obtain the accuracy value of the original classification model during the training process; based on the accuracy value, the amber origin classification model is determined.

[0084] Specifically, during model training, a combination of training and testing sample sets is used. Based on TensorBoard visualization technology, the model accuracy value obtained at each training step is recorded. By comparing the accuracy values ​​obtained before and after, it is determined whether to save the model parameters based on the accuracy value comparison. That is, if the current accuracy value is greater than the previous accuracy value, the model parameters are saved; if the current accuracy value is not greater than the previous accuracy value, the model parameters are set. Furthermore, by setting a maximum number of iterations, it is determined whether to stop training the model based on the maximum number of iterations, so as to obtain the final amber origin classification model.

[0085] Step 102: Obtain the infrared reflectance spectrum data of the amber sample to be identified, and input the sample infrared reflectance spectrum data into the amber origin classification model to obtain the predicted first amber origin.

[0086] In one embodiment, also based on a Fourier transform mid-infrared spectrometer, the infrared reflectance spectrum data of the amber sample to be identified is collected, and the infrared reflectance spectrum data of the sample is input into a trained amber origin classification model so that the amber origin classification model outputs the predicted first amber origin of the amber sample to be identified.

[0087] Step 103: Obtain the nuclear magnetic resonance (NMR) spectral signal of the amber sample to be identified, count the number and position of the signal peaks in the NMR spectral signal, compare the number and position of the signal peaks with the preset standard number and position of the signal peaks, and obtain the predicted second amber origin based on the comparison results.

[0088] In one embodiment, the nuclear magnetic resonance spectrum signal of the amber sample to be distinguished is acquired based on a Fourier solid-state nuclear magnetic resonance spectrometer, and the acquisition conditions of the Fourier solid-state nuclear magnetic resonance spectrometer are set, including setting the test frequency to 76.50MHz, the rotation speed to 9.00kHz, and grinding the amber sample to be distinguished into powder of less than 100 mesh using an agate mortar.

[0089] In one embodiment, the nuclear magnetic resonance spectral signal is divided into three signal regions, wherein the three signal regions include a saturated carbon resonance signal region, an unsaturated carbon resonance signal region, and a carbonyl carbon resonance signal region.

[0090] Specifically, the nuclear magnetic resonance spectral signal with δ = 10 × 10 -6 ~70×10 -6 Set as the saturated carbon resonance signal region; δ = 100 × 10 in the nuclear magnetic resonance spectral signal -6 ~160×10 -6 Set as the resonance signal region of unsaturated carbon; δ = 160 × 10 in the nuclear magnetic resonance spectral signal. -6 ~200×10 -6 Set as the carbon-based resonance signal region.

[0091] In one embodiment, standard nuclear magnetic resonance (NMR) spectral signals of amber samples from different origins are obtained, and the standard NMR spectral signals are divided into three standard signal regions. Based on the standard signal regions, the number and position of standard signal peaks are set for the standard signal regions of each origin.

[0092] Specifically, the first standard nuclear magnetic resonance (NMR) spectral signal of amber samples from Fushun, China, the second standard NMR spectral signal of amber samples from the Dominican Republic, the third standard NMR spectral signal of amber samples from Myanmar, and the fourth standard NMR spectral signal of amber samples from the Baltic Sea are obtained. The first, second, third, and fourth standard NMR spectral signals are divided into three standard signal regions, and based on the signal frequency characteristics of the three standard signal regions, the number and position of standard signal peaks are set for the three standard signal regions corresponding to different origins.

[0093] As an example in this embodiment, the first standard NMR spectral signal corresponding to the Fushun production area in China is divided into a first saturated carbon resonance signal region, a first unsaturated carbon resonance signal region, and a first carbonyl carbon resonance signal region. Specifically, for the first saturated carbon resonance signal region, the number of corresponding standard signal peaks is set to 5, and the corresponding standard signal peak position is set to δ = 20.1 × 10⁻⁶. -6 28×10 -6 34.2×10 -6 38.8×10 -6 47.4×10 -6 For the first unsaturated carbon resonance signal region, the number of corresponding standard signal peaks is set to 3, and the position of the corresponding standard signal peaks is set to δ = 126.2 × 10⁻⁶. -6 136.5×10 -6 140.7×10 -6 For the first carbonyl carbon resonance signal region, the number of corresponding standard signal peaks was set to 4, and the position of the corresponding standard signal peaks was set to δ = 172.5 × 10⁻⁶. -6 177.5×10 -6 181.2×10 -6 186.5×10 -6 .

[0094] For the third standard NMR spectral signal corresponding to the Dominican origin, it is divided into a third saturated carbon resonance signal region, a third unsaturated carbon resonance signal region, and a third carbonyl carbon resonance signal region. Specifically, for the third saturated carbon resonance signal region, the number of corresponding standard signal peaks is set to 4, and the corresponding standard signal peak position is set to δ = 21.3 × 10⁻⁶. -6 30.47×10 -6 38.3×10 -6 44.1×10 -6For the third unsaturated carbon resonance signal region, the number of corresponding standard signal peaks was set to 3, and the position of the corresponding standard signal peaks was set to δ = 129.3 × 10⁻⁶. -6 133.6×10 -6 139.5×10 -6 For the third carbonyl carbon resonance signal region, the number of corresponding standard signal peaks was set to 2, and the position of the corresponding standard signal peaks was set to δ = 177.3 × 10⁻⁶. -6 185.6×10 -6 .

[0095] In one embodiment, the number and position of signal peaks in each signal region of the nuclear magnetic resonance spectral signal of the amber sample to be distinguished are counted, and the number and position of signal peaks corresponding to each signal region are compared with the number and position of standard signal peaks corresponding to different origins.

[0096] Specifically, the number of signal peaks in each signal region is compared with the number of standard signal peaks from different origins. A first similarity is calculated between the number of signal peaks in each signal region and the number of standard signal peaks. The position of the signal peaks in each signal region is then compared with the position of standard signal peaks from different origins, and a second similarity is calculated between the position of the signal peaks in each signal region and the position of standard signal peaks. By statistically analyzing all first and second similarities corresponding to different origins, and based on a preset similarity calculation formula, the similarity between the amber sample to be identified and amber samples from different origins is calculated. The origin corresponding to the highest similarity is obtained, and this origin is determined as the second amber origin of the amber sample to be identified. The similarity calculation formula is as follows:

[0097]

[0098] In the formula, S represents the similarity, i represents the i-th signal region, and x... i X represents the number of signal peaks in the i-th signal region. i Y represents the number of standard peaks in the i-th signal region corresponding to a single origin. ij y represents the position of the j-th standard signal peak in the i-th signal region corresponding to a single origin. ij Let be the position of the j-th signal peak in the i-th signal region, where a and b are constants.

[0099] Step 104: Determine whether the first amber origin and the second amber origin are the same. If so, perform stable isotope testing on the amber sample to be identified, calculate the maturity of the amber sample to be identified, and set a first standard maturity of the first amber origin based on the first amber origin. Compare the maturity with the first standard maturity. If the maturity is within the range of the first standard maturity, then take the first amber origin as the amber origin of the amber sample to be identified.

[0100] In one embodiment, since there is a good correlation between the maturity of amber and the geological age in which amber was formed, the maturity of amber from different origins will vary based on the region. The maturity of amber provides a quantitative basis for the identification of the origin of amber.

[0101] In one embodiment, the amber sample to be identified is subjected to stable isotope testing using a stable isotope ratio mass spectrometer to obtain the isotope ratio of the amber sample and the standard isotope ratio of the amber. The isotope ratio and the standard isotope ratio are then substituted into a preset maturity calculation formula to obtain the maturity of the amber sample. The maturity calculation formula in the amber origin determination module is as follows:

[0102]

[0103] In the formula, C represents maturity, and R... T R is the standard isotope ratio. t m represents the isotopic ratio of the amber sample to be resolved. t To determine the mass of the amber sample to be identified, m T Let a be the standard mass of amber, and α be a constant.

[0104] In one embodiment, when the first amber origin and the second amber origin are the same, a first standard maturity of the first amber origin is set based on the first amber origin. Similarly, a second standard maturity of the second amber origin can be set based on the second amber origin, wherein the first standard maturity is equivalent to the second standard maturity.

[0105] Specifically, when the first amber originates from Fushun, China, the first standard maturity is set at -19.78% to 24.42%; when the first amber originates from the Dominican Republic, the first standard maturity is set at -23.60% to 26.01%; when the first amber originates from Myanmar, the first standard maturity is set at -19.38% to 22.90%; and when the first amber originates from the Baltic Sea, the first standard maturity is set at -22.76% to 25.76%.

[0106] In one embodiment, the maturity is compared with the first standard maturity. If the maturity is within the range of the first standard maturity, then the first amber origin or the second amber origin is taken as the amber origin of the amber sample to be identified.

[0107] In one embodiment, if the maturity is not within the first standard maturity range, the minimum error between the maturity and the first standard maturity range is calculated, and it is determined whether the minimum error meets the error threshold range. If so, the first amber origin or the second amber origin is taken as the amber origin of the amber sample to be identified. If not, the first amber origin and the second amber origin of the amber sample to be identified are obtained again.

[0108] In one embodiment, if the first amber origin and the second amber origin are different, a first standard maturity of the first amber origin is obtained based on the first amber origin, and a second standard maturity of the second amber origin is obtained based on the second amber origin. The maturity is then compared with the first standard maturity and the second standard maturity, respectively.

[0109] Specifically, if the maturity level is within the range of the first standard maturity level and the maturity level is not within the range of the second standard maturity level, then the first amber origin is taken as the amber origin of the amber sample to be identified.

[0110] Specifically, if the maturity level is within the range of the second standard maturity level and the maturity level is not within the range of the first standard maturity level, then the second amber origin is taken as the amber origin of the amber sample to be identified.

[0111] Specifically, if the maturity level exists within the range of both the first standard maturity level and the second standard maturity level, then the first weight value of the first amber origin and the second weight value of the second amber origin are calculated respectively. The first weight value and the second weight value are compared, and based on the comparison result, the amber origin corresponding to the maximum weight value is determined as the amber origin of the amber sample to be identified.

[0112] Specifically, if the maturity level is neither within the range of the first standard maturity level nor within the range of the second standard maturity level, then the first minimum error between the maturity level and the range of the first standard maturity level is calculated, and the second minimum error between the maturity level and the range of the second standard maturity level is calculated. The first minimum error and the second minimum error are compared to obtain and determine whether the minimum error value meets the error threshold range. If yes, then the amber origin corresponding to the minimum error value is taken as the amber origin of the amber sample to be identified. If not, then the first amber origin and the second amber origin of the amber sample to be identified are obtained again.

[0113] Example 2

[0114] See Figure 2 , Figure 2 This is a schematic diagram of an embodiment of an amber origin identification device based on amber characteristics provided by the present invention, as shown below. Figure 2 As shown, the device includes an amber origin classification model generation module 201, a first amber origin prediction module 202, a second amber origin prediction module 203, and an amber origin determination module 204, as detailed below:

[0115] The amber origin classification model generation module 201 is used to collect amber samples from multiple origins, obtain infrared reflectance spectral data corresponding to each amber sample, obtain an infrared reflectance spectral dataset, construct an original classification model, and train the original classification model based on the infrared reflectance spectral dataset to obtain the amber origin classification model.

[0116] The first amber origin prediction module 202 is used to acquire the infrared reflectance spectrum data of the amber sample to be identified, input the infrared reflectance spectrum data of the sample into the amber origin classification model, and obtain the predicted first amber origin.

[0117] The second amber origin prediction module 203 is used to acquire the nuclear magnetic resonance spectral signal of the amber sample to be identified, count the number and position of the signal peaks in the nuclear magnetic resonance spectral signal, compare the number and position of the signal peaks with the preset standard number and position of the signal peaks, and obtain the predicted second amber origin based on the comparison results.

[0118] The amber origin determination module 204 is used to determine whether the first amber origin and the second amber origin are the same. If so, a stable isotope test is performed on the amber sample to be identified, the maturity of the amber sample to be identified is calculated, and a first standard maturity of the first amber origin is set based on the first amber origin. The maturity is compared with the first standard maturity. If the maturity is within the range of the first standard maturity, the first amber origin is taken as the amber origin of the amber sample to be identified.

[0119] In one embodiment, the amber origin determination module 204, after determining whether the first amber origin and the second amber origin are the same, includes: if the first amber origin and the second amber origin are not the same, performing stable isotope testing on the amber sample to be identified and calculating the maturity of the amber sample; obtaining a first standard maturity based on the first amber origin, and obtaining a second standard maturity based on the second amber origin, and comparing the maturity with the first standard maturity and the second standard maturity respectively; if the maturity is within the range of the first standard maturity, and the maturity does not exist... If the maturity level falls within the range of the second standard maturity level, then the first amber origin is taken as the amber origin of the amber sample to be identified; if the maturity level falls within the range of the second standard maturity level and does not fall within the range of the first standard maturity level, then the second amber origin is taken as the amber origin of the amber sample to be identified; if the maturity level falls within both the range of the first standard maturity level and the second standard maturity level, then a first weight value for the first amber origin and a second weight value for the second amber origin are calculated respectively, the first weight value and the second weight value are compared, and the amber origin of the amber sample to be identified is determined based on the comparison result.

[0120] In one embodiment, the second amber origin prediction module 203 is used to count the number and position of signal peaks in the nuclear magnetic resonance (NMR) spectral signal, and compare the number and position of signal peaks with preset standard number and position of signal peaks. Specifically, this includes: acquiring the NMR spectral signal of the amber sample to be identified, and dividing the NMR spectral signal into three signal regions, wherein the three signal regions include a saturated carbon resonance signal region, an unsaturated carbon resonance signal region, and a carbonyl carbon resonance signal region; acquiring standard NMR spectral signals of amber samples from different origins, and dividing the standard NMR spectral signals into three standard signal regions, and setting corresponding standard number and position of signal peaks for each origin's standard signal region based on the standard signal regions; counting the number and position of signal peaks in each signal region, and comparing the number and position of signal peaks corresponding to each signal region with the number and position of standard signal peaks corresponding to different origins.

[0121] In one embodiment, the second amber origin prediction module 203 is used to compare the number of signal peaks and the position of the signal peaks with preset standard number of signal peaks and standard position of the signal peaks, and obtain the predicted second amber origin based on the comparison results. Specifically, this includes: calculating the first similarity between the number of signal peaks and each standard number of signal peaks, and calculating the second similarity between the position of the signal peaks and each standard position of the signal peaks; statistically analyzing all the first similarities and all the second similarities corresponding to different origins, and determining the predicted second amber origin based on the statistical results.

[0122] In one embodiment, the amber origin classification model generation module 201 is used to train the original classification model based on the infrared reflectance spectrum dataset to obtain an amber origin classification model. Specifically, this includes: dividing the infrared reflectance spectrum dataset into a training sample set and a test sample set according to a preset ratio; training the original classification model based on the training sample set, and testing the trained original classification model based on the test sample set to obtain the accuracy value of the original classification model during training; and determining the amber origin classification model based on the accuracy value.

[0123] In one embodiment, the amber origin determination module 204 is used to perform stable isotope testing on the amber sample to be identified and calculate the maturity of the amber sample to be identified. Specifically, it includes: performing stable isotope testing on the amber sample to be identified, obtaining the isotope ratio of the amber sample to be identified, and obtaining the standard isotope ratio of amber; substituting the isotope ratio and the standard isotope ratio into a preset maturity calculation formula to obtain the maturity of the amber sample to be identified.

[0124] In one embodiment, the maturity calculation formula in the amber origin determination module 204 is as follows:

[0125]

[0126] In the formula, C represents maturity, and R... T R is the standard isotope ratio. t m represents the isotopic ratio of the amber sample to be resolved. t To determine the mass of the amber sample to be identified, m T Let a be the standard mass of amber, and α be a constant.

[0127] In one embodiment, the amber origin determination module 204 is used to set a first standard maturity level for the first amber origin, specifically including: when the first amber origin is Fushun, China, the first standard maturity level is set to -19.78%-24.42%; when the first amber origin is Dominican Republic, the first standard maturity level is set to -23.60%-26.01%; when the first amber origin is Myanmar, the first standard maturity level is set to -19.38%-22.90%; and when the first amber origin is Baltic Sea, the first standard maturity level is set to -22.76%-25.76%.

[0128] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0129] It should be noted that the above-described embodiment of the amber origin identification device based on amber characteristics is merely illustrative. The modules described as separating components may or may not be physically separate, and the components shown as modules 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Based on the above-described embodiments of the amber origin identification method based on amber characteristics, another embodiment of the present invention provides a terminal device for amber origin identification based on amber characteristics. This terminal device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the amber origin identification method based on amber characteristics according to any embodiment of the present invention.

[0131] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the amber origin identification terminal device based on amber characteristics.

[0132] The amber origin identification terminal device based on amber characteristics can be a desktop computer, laptop, handheld computer, or cloud server, etc. The amber origin identification terminal device based on amber characteristics may include, but is not limited to, a processor and a memory.

[0133] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the amber origin identification terminal device based on amber characteristics, connecting all parts of the device via various interfaces and lines.

[0134] The memory can be used to store the computer program and / or modules. The processor, by running or executing the computer program and / or modules stored in the memory, and by calling the data stored in the memory, realizes various functions of the amber origin identification terminal device based on amber characteristics. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0135] Based on the above embodiments of the amber origin identification method based on amber characteristics, another embodiment of the present invention provides a storage medium, the storage medium including a stored computer program, wherein, when the computer program is running, the device where the storage medium is located controls the execution of the amber origin identification method based on amber characteristics of any embodiment of the present invention.

[0136] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0137] In summary, the present invention provides a method and apparatus for identifying the origin of amber based on its characteristics. This method acquires infrared reflectance spectral datasets of amber samples from multiple origins to generate an amber origin classification model. The model is then used to classify the amber sample to be identified, yielding a first amber origin. Simultaneously, the number and position of signal peaks in the nuclear magnetic resonance (NMR) spectral signal of the amber sample are obtained and compared with the standard number and position of signal peaks for each origin, yielding a second amber origin. Finally, the maturity of the amber sample is compared with a first standard maturity level to verify the accuracy of the predicted origin, thus confirming the amber origin of the sample. Compared to existing technologies, the present invention improves the accuracy of amber origin identification by performing a secondary prediction of the amber origin and verifying the prediction results using the maturity of the amber sample.

[0138] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining the origin of a piece of amber based on amber characteristics, characterized in that, The method comprises the following steps: Collecting amber samples from multiple production areas, obtaining infrared reflectance spectrum data corresponding to each amber sample, obtaining an infrared reflectance spectrum data set, constructing an original classification model, training the original classification model based on the infrared reflectance spectrum data set, and obtaining an amber production area classification model; Obtaining sample infrared reflectance spectrum data of the amber sample to be distinguished, inputting the sample infrared reflectance spectrum data into the amber production area classification model, and obtaining a predicted first amber production area; Obtaining the nuclear magnetic resonance wave signal of the amber sample to be distinguished, counting the number and position of signal peaks in the nuclear magnetic resonance wave signal, comparing the number and position of signal peaks with the preset standard number and position of signal peaks, respectively, and obtaining a predicted second amber production area according to the comparison result; Judging whether the first amber production area and the second amber production area are the same, if yes, performing stable isotope testing on the amber sample to be distinguished, calculating the maturity of the amber sample to be distinguished, and based on the first amber production area, setting a first standard maturity of the first amber production area, comparing the maturity with the first standard maturity, and if the maturity is within the range of the first standard maturity, taking the first amber production area as the amber production area of the amber sample to be distinguished; If the first amber production area and the second amber production area are not the same, performing stable isotope testing on the amber sample to be distinguished, and calculating the maturity of the distinguished amber sample; Based on the first amber production area, obtaining a first standard maturity of the first amber production area, and based on the second amber production area, obtaining a second standard maturity of the second amber production area, comparing the maturity with the first standard maturity and the second standard maturity, respectively; If the maturity exists within the range of the first standard maturity and does not exist within the range of the second standard maturity, taking the first amber production area as the amber production area of the amber sample to be distinguished; If the maturity exists within the range of the second standard maturity and does not exist within the range of the first standard maturity, taking the second amber production area as the amber production area of the amber sample to be distinguished; If the maturity exists within the range of the first standard maturity and the second standard maturity, respectively calculating a first weight value of the first amber production area and a second weight value of the second amber production area, comparing the first weight value and the second weight value, and determining the amber production area of the amber sample to be distinguished according to the comparison result.

2. The method of determining the provenance of a sample based on amber characteristics as claimed in claim 1, wherein, Counting the number and position of signal peaks in the nuclear magnetic resonance wave signal, and comparing the number and position of signal peaks with the preset standard number and position of signal peaks, respectively, specifically comprising: Acquire the nuclear magnetic resonance wave pop signal of the amber sample to be distinguished, and divide the nuclear magnetic resonance wave pop signal into three signal regions, wherein the three signal regions include a saturated carbon resonance signal region, an unsaturated carbon resonance signal region, and a carbonyl carbon resonance signal region; Acquire the standard nuclear magnetic resonance wave pop signal of the amber sample of different origins, and divide the standard nuclear magnetic resonance wave pop signal into three standard signal regions, and set the corresponding standard signal peak number and standard signal peak position for each standard signal region of each origin based on the standard signal region; Statistically count the signal peak number and signal peak position in each signal region, and compare the signal peak number and signal peak position corresponding to each signal region with the standard signal peak number and standard signal peak position corresponding to different origins, respectively.

3. The method of provenance determination of a Baltic amber based on amber characteristics as claimed in claim 2, characterized in that, Compare the signal peak number and signal peak position with the preset standard signal peak number and standard signal peak position, respectively, and obtain the predicted second amber origin according to the comparison result, specifically including: Respectively calculate the first similarity of the signal peak number and each standard signal peak number, and simultaneously calculate the second similarity of the signal peak position and each standard signal peak position; Statistically count all first similarities and all second similarities corresponding to different origins, and determine the predicted second amber origin according to the statistical result.

4. The method of determining the origin of a sample based on amber characteristics as claimed in claim 1, wherein, Based on the infrared reflection spectrum data set, the original classification model is trained to obtain an amber origin classification model, specifically including: Divide the infrared reflection spectrum data set into a training sample set and a test sample set according to a preset proportion; Based on the training sample set, the original classification model is trained, and based on the test sample set, the trained original classification model is tested to obtain the accuracy value of the original classification model in the training process, and based on the accuracy value, an amber origin classification model is determined.

5. The method of determining the origin of a sample based on amber characteristics as claimed in claim 1, wherein, Stable isotope testing is performed on the amber sample to be distinguished to calculate the maturity of the amber sample to be distinguished, specifically including: Stable isotope testing is performed on the amber sample to be distinguished to obtain the isotope ratio of the amber sample to be distinguished, and the standard isotope ratio of the amber is obtained; The isotope ratio and the standard isotope ratio are substituted into a preset maturity calculation formula to obtain the maturity of the amber sample to be distinguished.

6. The method of determining the origin of a sample based on amber characteristics as claimed in claim 1, wherein, Based on the first amber origin, a first standard maturity of the first amber origin is set, specifically including: When the first amber origin is the China Fushun origin, the first standard maturity is set to -19.78%-24.42%; When the first amber origin is the Dominican origin, the first standard maturity is set to -23.60%-26.01% When the first amber origin is the Myanmar origin, the first standard maturity is set to -19.38%-22.90%; When the first amber origin is the Baltic origin, the first standard maturity is set to -22.76%-25.76%.

7. A device for identifying the origin of amber based on its characteristics, characterized in that, Including: An amber origin classification model generation module, a first amber origin prediction module, a second amber origin prediction module, and an amber origin determination module; The amber origin classification model generation module is used to collect amber samples from multiple origins, obtain infrared reflectance spectral data corresponding to each amber sample, obtain an infrared reflectance spectral dataset, construct an original classification model, and train the original classification model based on the infrared reflectance spectral dataset to obtain the amber origin classification model. The first amber origin prediction module is used to acquire the infrared reflectance spectrum data of the amber sample to be identified, and input the infrared reflectance spectrum data of the sample into the amber origin classification model to obtain the predicted first amber origin. The second amber origin prediction module is used to acquire the nuclear magnetic resonance spectral signal of the amber sample to be identified, count the number and position of the signal peaks in the nuclear magnetic resonance spectral signal, compare the number and position of the signal peaks with the preset standard number and position of the signal peaks, and obtain the predicted second amber origin based on the comparison results. The amber origin determination module is used to determine whether the first amber origin and the second amber origin are the same. If so, a stable isotope test is performed on the amber sample to be identified, the maturity of the amber sample to be identified is calculated, and a first standard maturity of the first amber origin is set based on the first amber origin. The maturity is compared with the first standard maturity. If the maturity is within the range of the first standard maturity, the first amber origin is taken as the amber origin of the amber sample to be identified. If the first amber origin and the second amber origin are different, then a stable isotope test is performed on the amber sample to be identified, and the maturity of the amber sample to be identified is calculated. Based on the first amber origin, a first standard maturity of the first amber origin is obtained, and based on the second amber origin, a second standard maturity of the second amber origin is obtained. The maturity is then compared with the first standard maturity and the second standard maturity, respectively. If the maturity is within the range of the first standard maturity and the maturity is not within the range of the second standard maturity, then the first amber origin is taken as the amber origin of the amber sample to be identified. If the maturity is within the range of the second standard maturity and the maturity is not within the range of the first standard maturity, then the second amber origin shall be taken as the amber origin of the amber sample to be identified. If the maturity level exists within both the first standard maturity level and the second standard maturity level, then the first weight value of the first amber origin and the second weight value of the second amber origin are calculated respectively. The first weight value and the second weight value are compared, and the amber origin of the amber sample to be identified is determined based on the comparison result.

8. A terminal device, characterized by comprising: The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the amber origin identification method based on amber characteristics as described in any one of claims 1 to 6.

9. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the amber feature-based determination of the origin of the amber according to any one of claims 1 to 6 when the computer program is running.

Images