Intelligent distinguishing and detecting system for phellinus igniarius components in different producing areas

Abstract

The invention relates to the technical field of intelligent sensors, in particular to an intelligent distinguishing and detecting system for phellinus igniarius components in different producing areas, which comprises a data acquisition module used for acquiring spectral data of a plurality of phellinus igniarius samples with unknown producing areas and representative phellinus igniarius samples with known producing areas; the similarity analysis module is used for determining the spectral shape similarity and the dissimilarity of the same component content between the spectral data of the two different phellinus igniarius samples; the clustering module is used for determining a distance index according to the similarity of the spectral shapes and the dissimilarity of the contents of the same components, and acquiring a clustering cluster of the spectral data of all the phellinus igniarius samples with unknown producing areas based on the distance index; and the producing area determination module is used for matching the spectral data in each cluster with the spectral data of the representative phellinus igniarius samples of all known producing areas based on the distance index, and determining the producing area of the phellinus igniarius samples of each cluster according to the matching result. The identification accuracy of the phellinus igniarius producing area is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent sensors, and particularly relates to an intelligent discrimination and detection system for the components of Phellinus igniarius from different origins. Background Art

[0002] As a medicinal fungus, the components of Phellinus igniarius from different origins may not only differ in types, but also, even if the component types are the same, there may be significant differences in their contents. Therefore, the intelligent discrimination and detection of the origin of Phellinus igniarius is crucial for ensuring the efficacy and quality of Phellinus igniarius.

[0003] In the prior art, using spectral detection to distinguish Phellinus igniarius from different origins is a rapid and non-destructive analysis method. However, since the main components of Phellinus igniarius, such as polysaccharides, flavonoid compounds, and triterpenoid compounds, may overlap in certain wavelength ranges, that is, the spectral signals of different components overlap, it will increase the difficulty of component discrimination and easily cause inaccurate comparative analysis between the spectral graphs of Phellinus igniarius, resulting in inaccurate discrimination of the origin of Phellinus igniarius. Summary of the Invention

[0004] In order to solve the above technical problem that inaccurate discrimination of the origin of Phellinus igniarius is caused by the overlap of spectral signals of different components, the purpose of the present invention is to provide an intelligent discrimination and detection system for the components of Phellinus igniarius from different origins, and the specific technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides an intelligent discrimination and detection system for the components of Phellinus igniarius from different origins, and the system includes:

[0006] A data acquisition module, configured to acquire spectral data of a plurality of Phellinus igniarius samples with unknown origins and representative Phellinus igniarius samples with known origins, where the spectral data includes absorbances at different wavelengths within a set wavelength range;

[0007] A similarity analysis module, configured to analyze the spectral data to determine the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples;

[0008] A clustering module, configured to determine a distance metric between the spectral data of any two different Phellinus igniarius samples based on the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap, and cluster the spectral data of all Phellinus igniarius samples with unknown origins based on the distance metric to obtain a plurality of clustering clusters;

[0009] An origin determination module, configured to match the spectral data in each clustering cluster with the spectral data of all representative Phellinus igniarius samples with known origins based on the distance metric, and determine the origin of the Phellinus igniarius samples corresponding to each clustering cluster according to the matching result.

[0010] In combination with the first aspect described above, in some possible implementation manners, the similarity analysis module includes a first analysis module, and the first analysis module includes:

[0011] A first wavelength band acquisition unit, configured to acquire a plurality of first wavelength bands corresponding to a wavelength range where the spectral shapes of the spectral data of any two different Phellinus igniarius samples are different within a set wavelength range;

[0012] A principal component analysis unit, configured to respectively acquire a first spectral data segment and a second spectral data segment of the spectral data of any two different Phellinus igniarius samples under each first wavelength band, perform principal component analysis on the first spectral data segment and the second spectral data segment, and acquire a plurality of principal components and their eigenvalues of the first spectral data segment and the second spectral data segment;

[0013] A matching analysis unit, configured to perform one-to-one matching on the principal components of the first spectral data segment and the second spectral data segment, and determine the spectral shape similarity between the spectral data of any two different Phellinus igniarius samples after reducing the influence of component overlap according to the matching result and the eigenvalues of the principal components.

[0014] In combination with the first aspect described above, in some possible implementation manners, the first wavelength band acquisition unit includes:

[0015] A difference sequence acquisition unit, configured to determine a spectral shape difference sequence of any two different Phellinus igniarius samples according to the difference in the change trend of the absorbance of the spectral data of any two different Phellinus igniarius samples at the same wavelength, and the spectral shape difference sequence reflects the difference in the change trend of the spectral data of any two different Phellinus igniarius samples at the same wavelength;

[0016] A first clustering unit, configured to cluster target elements in the spectral shape difference sequence to obtain a plurality of clusters. If the change trends of the spectral data of any two different Phellinus igniarius samples at a certain wavelength are the same, the element corresponding to the certain wavelength in the spectral shape difference sequence is used as a target element;

[0017] A first wavelength band acquisition unit, configured to use the wavelength range formed by the maximum wavelength and the minimum wavelength corresponding to the target elements in each cluster as a first wavelength band.

[0018] In combination with the first aspect described above, in some possible implementation manners, the difference sequence acquisition unit includes:

[0019] A wavelength label acquisition unit, configured to determine the wavelength label corresponding to each wavelength in the spectral data. If the absorbance at a certain wavelength in the spectral data is less than the absorbance at the next wavelength, the wavelength label corresponding to the corresponding wavelength is set to a first value. If the absorbance at a certain wavelength is equal to the absorbance at the next wavelength, the wavelength label corresponding to the corresponding wavelength is set to a second value. If the absorbance at a certain wavelength is greater than the absorbance at the next wavelength, the wavelength label corresponding to the corresponding wavelength is set to a third value;

[0020] A first sequence acquisition unit, configured to arrange all the wavelength labels in the order of wavelengths to obtain a spectral shape sequence corresponding to the spectral data;

[0021] A second sequence acquisition unit, configured to perform an AND operation on the wavelength labels at the same wavelength of the spectral shape sequences corresponding to the spectral data of any two different Phellinus igniarius samples to obtain a spectral shape difference sequence of any two different Phellinus igniarius samples.

[0022] Combined with the above first aspect, in some possible implementation manners, the matching and analyzing unit includes:

[0023] A matching unit, configured to perform one-to-one matching on the respective principal components of the first spectral data segment and the second spectral data segment to obtain a plurality of one-to-one matching pairs and their matching edge values;

[0024] A component similarity acquisition unit, configured to determine the component similarity between the first spectral data segment and the second spectral data segment according to the quantity difference between the respective principal components of the first spectral data segment and the second spectral data segment, the matching edge values of the one-to-one matching pairs, and the eigenvalue of the two principal components in the one-to-one matching pairs;

[0025] A spectral shape similarity acquisition unit, configured to determine the spectral shape similarity after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples according to the wavelength range ratio of the corresponding first wavelength segments of the respective first spectral data segments and the second spectral data segments within a set wavelength range, the component similarity between the respective first spectral data segments and the second spectral data segments, and the wavelength range ratio of the total wavelength range except all the first wavelength segments within the set wavelength range within the set wavelength range.

[0026] Combined with the above first aspect, in some possible implementation manners, the similarity analysis module further includes a second analysis module, and the second analysis module includes:

[0027] A second wavelength segment acquisition unit, configured to acquire a plurality of second wavelength segments corresponding to the wavelength range where the spectral shapes of the spectral data of any two different Phellinus igniarius samples are the same within a set wavelength range;

[0028] The first content difference obtaining unit is configured to respectively obtain a third spectral data segment and a fourth spectral data segment of spectral data of any two different Phellinus igniarius samples under each second wavelength band, and determine a first same-component content difference and a first maximum component content difference according to the absorbance difference at the same wavelength in the third spectral data segment and the fourth spectral data segment;

[0029] The second content difference obtaining unit is configured to determine a second same-component content difference and a second maximum component content difference according to the absorbance difference at the same wavelength in the one-to-one matching pairs of the first spectral data segment and the second spectral data segment;

[0030] The dissimilarity obtaining unit is configured to determine the same-component content dissimilarity between the spectral data of any two different Phellinus igniarius samples according to all the first same-component content differences and first maximum component content differences and all the second same-component content differences and second maximum component content differences corresponding to any two different Phellinus igniarius samples.

[0031] Combined with the first aspect above, in some possible implementation manners, the first content difference obtaining unit includes:

[0032] The first same-component content difference obtaining unit is configured to determine the sum value of the absolute values of the differences in absorbance at the same wavelength in the third spectral data segment and the fourth spectral data segment, so as to obtain the first same-component content difference;

[0033] The first maximum component content difference obtaining unit is configured to determine the maximum value of the absolute values of the differences in absorbance at the same wavelength in the third spectral data segment and the fourth spectral data segment, so as to obtain the first maximum component content difference.

[0034] Combined with the first aspect above, in some possible implementation manners, the dissimilarity obtaining unit includes:

[0035] The comprehensive same-component content difference determining unit is configured to determine the sum value of all the first same-component content differences and second same-component content differences corresponding to any two different Phellinus igniarius samples, so as to obtain the comprehensive same-component content difference;

[0036] The maximum component content difference variance determining unit is configured to determine the variance sum and the maximum value of all the first maximum component content differences and second maximum component content differences corresponding to any two different Phellinus igniarius samples, and correspondingly obtain the maximum component content difference variance and the maximum value of the maximum component content difference;

[0037] The dissimilarity determining unit is configured to determine the same-component content dissimilarity between the spectral data of any two different Phellinus igniarius samples according to the comprehensive same-component content difference, the maximum component content difference variance and the maximum value of the maximum component content difference.

[0038] Combined with the first aspect above, in some possible implementation manners, the clustering module includes:

[0039] A negative correlation mapping processing unit, configured to perform negative correlation mapping processing on the spectral shape similarity to obtain a spectral shape similarity processing value;

[0040] A distance index acquisition unit, configured to calculate the product of the spectral shape similarity processing value and the dissimilarity of the same component content as the distance index;

[0041] A second clustering unit, configured to perform clustering on the spectral data of all Phellinus igniarius samples with unknown origins by using the K-means clustering algorithm based on the distance index to obtain a plurality of clustering clusters.

[0042] Combined with the above first aspect, in some possible implementation manners, the origin determination module includes:

[0043] A first distance index acquisition unit, configured to determine the average value of the similarity indexes between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples of each same origin to obtain an average distance index;

[0044] A second distance index acquisition unit, configured to determine the minimum value among the average distance indexes between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples of different origins to obtain a minimum average distance index;

[0045] An origin determination unit, configured to use the origin corresponding to the minimum average distance index as the origin of the Phellinus igniarius samples corresponding to each clustering cluster.

[0046] In a second aspect, the present invention further provides an intelligent differentiation and detection method for Phellinus igniarius components from different origins, and the method includes the following steps:

[0047] Obtain the spectral data of a plurality of Phellinus igniarius samples with unknown origins and the spectral data of representative Phellinus igniarius samples with known origins, where the spectral data includes absorbances at different wavelengths within a set wavelength range;

[0048] Analyze the spectral data to determine the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples;

[0049] Determine the distance index between the spectral data of any two different Phellinus igniarius samples according to the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap, and perform clustering on the spectral data of all Phellinus igniarius samples with unknown origins based on the distance index to obtain a plurality of clustering clusters;

[0050] Based on the distance index, match the spectral data in each clustering cluster with the spectral data of all representative Phellinus igniarius samples with known origins, and determine the origin of the Phellinus igniarius samples corresponding to each clustering cluster according to the matching result.

[0051] In a third aspect, the present invention further provides an intelligent discrimination and detection device for the components of Phellinus igniarius from different origins, including a memory, a processor, and computer program code stored in the memory. The processor is configured to call and run the computer program code from the memory, so that the device executes the method in the above first aspect or any possible implementation manner of the first aspect.

[0052] In a fourth aspect, the present invention further provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer is caused to execute the method in the above first aspect or any possible implementation manner of the first aspect.

[0053] In a fifth aspect, the present invention further provides a computer-readable storage medium storing computer program code. When the computer program code runs on a computer, the computer is caused to execute the method in the above first aspect or any possible implementation manner of the first aspect.

[0054] The present invention has the following beneficial effects: By obtaining the spectral data of Phellinus igniarius samples with unknown origins and representative Phellinus igniarius samples with known origins, and analyzing the spectral data, the present invention determines the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples. Furthermore, the distance index between the spectral data of any two different Phellinus igniarius samples is accurately determined. Based on this distance index, accurate clustering of the spectral data of all Phellinus igniarius samples with unknown origins is achieved, and several clustering clusters are obtained. Then, based on this distance index, the spectral data in each clustering cluster is accurately matched with the spectral data of all representative Phellinus igniarius samples with known origins, and the origin of the Phellinus igniarius samples corresponding to each clustering cluster is determined according to the matching result. The present invention effectively reduces the influence of spectral signal overlap of different components in the spectral data of Phellinus igniarius samples, ensures the classification accuracy of the spectral data of Phellinus igniarius samples, and finally accurately matches the clustering clusters of Phellinus igniarius samples with unknown origins with the spectral data of Phellinus igniarius samples with known origins, effectively improving the accuracy of Phellinus igniarius origin discrimination. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for description in the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 It is a schematic structural diagram of an intelligent discrimination and detection system for the components of Phellinus igniarius from different origins according to an embodiment of the present invention;

[0057] Figure 2 Flow chart of steps of an intelligent discrimination and detection method for Phellinus igniarius components from different origins according to an embodiment of the present invention;

[0058] Figure 3 Schematic diagram of the absorbance of Phellinus igniarius sample 1 according to an embodiment of the present invention;

[0059] Figure 4 Schematic diagram of the absorbance of Phellinus igniarius sample 2 according to an embodiment of the present invention;

[0060] Figure 5 Schematic diagram of the structure of an intelligent discrimination and detection device for Phellinus igniarius components from different origins according to an embodiment of the present invention. Detailed implementation manners

[0061] To clearly illustrate the technical features of this solution, the present invention will be elaborated in detail below through specific implementation manners in combination with the accompanying drawings.

[0062] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0063] It should be understood that the various steps recited in the method embodiments of the present invention can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0064] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0065] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0066] In the embodiments of the present invention, although operations or steps are described in a specific order in the drawings, it should not be construed as requiring these operations or steps to be performed in the specific order shown or in a serial order, nor requiring all the operations or steps shown to obtain the desired result. In the embodiments of the present invention, these operations or steps can be performed serially; they can also be performed in parallel; or a part of these operations or steps can be performed.

[0067] Meanwhile, it can be understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs, and all parameters or indicators in the formulas involved in the present invention are numerical values after normalization that eliminate the influence of dimensions.

[0068] To solve the above technical problem that the spectral signals of different components overlap, resulting in inaccurate discrimination of the producing areas of Phellinus igniarius, the embodiments of the present invention provide an intelligent discrimination and detection system for the components of Phellinus igniarius from different producing areas. This system is essentially a software system, which is composed of modules that implement corresponding functions, and the corresponding structural schematic diagram is as Figure 1 shown. The core of this system is to implement an intelligent discrimination and detection method for the components of Phellinus igniarius from different producing areas. Each module in this system corresponds to each step in the method, and the flowchart corresponding to this method is as Figure 2 shown. The following will introduce each module of this system in detail in combination with the specific steps in this method.

[0069] The data acquisition module is used to acquire the spectral data of several Phellinus igniarius samples with unknown producing areas and representative Phellinus igniarius samples with known producing areas. The spectral data includes absorbances at different wavelengths within a set wavelength range.

[0070] Specifically, the producing areas of Phellinus igniarius are distributed in different provinces and regions. To perform intelligent discrimination and detection to distinguish the producing areas of different Phellinus igniarius, first, several Phellinus igniarius samples with unknown producing areas are acquired. For example, 30 Phellinus igniarius samples with unknown producing areas can be acquired. Among them, there are many reasons for the unknown producing areas of Phellinus igniarius. For example, some merchants may deliberately conceal or forge the producing area information in order to obtain high profits, or when the supply chain is chaotic, Phellinus igniarius may be transferred several times, and the original producing area information is lost or tampered with during the transfer process, or due to negligence or misunderstanding, the label of Phellinus igniarius may be mislabeled, resulting in inaccurate producing area information.

[0071] The specific process of obtaining several Phellinus igniarius samples with unknown origins is as follows: (1) Sample collection: Collect representative samples from all Phellinus igniarius with unknown origins. (2) Pretreatment: Appropriately pretreat the Phellinus igniarius samples, such as drying, pulverizing, sieving, etc., to ensure the consistency and representativeness of the samples.

[0072] Next, obtain the spectral data of the above-mentioned several Phellinus igniarius samples with unknown origins. The specific process of obtaining the spectral data is as follows: (1) Select a suitable spectrometer: In this embodiment, an infrared spectrometer is selected. (2) Set instrument parameters: The set wavelength range of the infrared spectrum (IR) is 4000 - 400 wavenumbers (cm^-1), which is used to detect the vibrational absorption of functional groups in Phellinus igniarius, such as hydroxyl groups, carbonyl groups, etc. (3) Sample loading: Place the pretreated Phellinus igniarius samples on the sample cell of the spectrometer. (4) Spectral scanning: Start the spectrometer to scan the Phellinus igniarius samples and record the absorbance at different wavelengths.

[0073] The spectral data of the above-mentioned several Phellinus igniarius samples with unknown origins includes infrared spectrograms of different Phellinus igniarius samples from the same origin and Phellinus igniarius samples from different origins. The horizontal axis of the infrared spectrogram is the wavelength, and the vertical axis is the absorbance.

[0074] In the same way as obtaining the spectral data of the above-mentioned several Phellinus igniarius samples with unknown origins, it is possible to obtain the spectral data of at least one representative Phellinus igniarius sample from each origin among all Phellinus igniarius origins, and at the same time mark the origin of each representative Phellinus igniarius sample.

[0075] A similarity analysis module is used to analyze the spectral data to determine the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples.

[0076] Specifically, due to the influence of factors such as geographical environment, climate conditions, soil type, cultivation techniques, etc., the components of Phellinus igniarius from different origins may not only have differences in types, but also significant differences in content even if the component types are the same. Therefore, in order to distinguish the origins of the above-mentioned several Phellinus igniarius samples with unknown origins, it is necessary to first distinguish Phellinus igniarius with different components, and further distinguish Phellinus igniarius with different contents under the same components.

[0077] For the infrared spectrogram, the magnitude of the absorbance reflects the amount of components in the sample. The larger the absorbance, the higher the content of the component in the sample. At the same time, the shape of the spectral curve can be used to identify specific components in the sample. Different chemical substances have different absorption characteristics at specific wavelengths. If the spectral curve shapes of two samples are similar, they are very likely to contain the same components.

[0078] Since the main components of Phellinus linteus, such as polysaccharides, flavonoid compounds, and triterpenoid compounds, may overlap in certain wavelength ranges, this can lead to different shapes of spectral curves in the overlapping wavelength ranges with different single-component contents in the same component, which is easily misinterpreted as different components. For ease of understanding, for example: in the overlapping wavelength range [1001, 1004] of components A and B, the content of component A in any two different Phellinus linteus samples 1 and 2 is the same, and the absorbances are {5, 10, 11, 12}, that is, the shapes of the spectral curves of component A are the same, and the absorbance magnitudes are the same. However, the contents of component B in Phellinus linteus samples 1 and 2 are different, and the absorbances are {1, 2, 1, 2} and {1, 4, 1, 4}, that is, the shapes of the spectral curves of component B are the same, but the absorbance magnitudes are different. Then the absorbances of Phellinus linteus samples 1 and 2 are {6, 12, 12, 14} and {6, 14, 12, 16} respectively. At this time, the schematic diagrams of the absorbances of Phellinus linteus samples 1 and 2 are as shown in Figure 3 and Figure 4 shown. According to Figure 3 and Figure 4 it can be seen that the shapes of the spectral curves of Phellinus linteus samples 1 and 2 with the same component but different contents are different in the overlapping wavelength range of components A and B. Therefore, it is necessary to first divide the ranges with different curve shapes in the infrared spectrogram, and further analyze whether this range is caused by different components or due to the same component, but with overlapping components and different contents.

[0079] Furthermore, the above similarity analysis module includes a first analysis module, and the first analysis module includes: a first wavelength segment acquisition unit for acquiring a plurality of first wavelength segments corresponding to the wavelength ranges with different spectral shapes of the spectral data of any two different Phellinus linteus samples within a set wavelength range; a principal component analysis unit for respectively acquiring a first spectral data segment and a second spectral data segment of the spectral data of any two different Phellinus linteus samples at each first wavelength segment, performing principal component analysis on the first spectral data segment and the second spectral data segment, and acquiring a plurality of principal components and their eigenvalues of the first spectral data segment and the second spectral data segment; a matching analysis unit for performing one-to-one matching on the principal components of the first spectral data segment and the second spectral data segment, and determining the spectral shape similarity after reducing the influence of component overlap between the spectral data of any two different Phellinus linteus samples according to the matching result and the eigenvalues of the principal components.

[0080] Specifically, for any two different Phellinus igniarius samples 1 and 2 (the Phellinus igniarius samples 1 and 2 can be Phellinus igniarius samples with unknown origin or representative Phellinus igniarius samples with known origin), by analyzing the spectral shapes between their two spectral data, several first wavelength ranges corresponding to the wavelength ranges where the spectral shapes of the two spectral data are different can be determined. Further, in some possible implementation manners, the first wavelength range obtaining unit includes: a difference sequence obtaining unit, configured to determine a spectral shape difference sequence of any two different Phellinus igniarius samples according to the difference in the change trends of the absorbances of the spectral data of any two different Phellinus igniarius samples at the same wavelength, where the spectral shape difference sequence reflects the difference in the change trends of the spectral data of any two different Phellinus igniarius samples at the same wavelength; a first clustering unit, configured to cluster the target elements in the spectral shape difference sequence to obtain several clusters, and if the change trends of the spectral data of any two different Phellinus igniarius samples are the same at a certain wavelength, then use the element corresponding to the certain wavelength in the spectral shape difference sequence as the target element; a first wavelength range obtaining unit, configured to use the wavelength range formed by the maximum wavelength and the minimum wavelength corresponding to the target elements in each cluster as a first wavelength range.

[0081] Among them, in order to obtain several first wavelength ranges corresponding to the wavelength ranges where the spectral shapes of the two spectral data of any two different Phellinus igniarius samples 1 and 2 are different, first, the change trend corresponding to each wavelength in each spectral data can be determined according to the change of the absorbance at adjacent wavelengths in each spectral data, and then the change trends corresponding to the same wavelength in the two spectral data are compared, so as to obtain the spectral shape difference sequence corresponding to the two spectral data; finally, based on the spectral shape difference sequence, band screening is performed on the set wavelength range, that is, the wavelength ranges corresponding to the wavelength ranges where the spectral shapes of the two spectral data of any two different Phellinus igniarius samples 1 and 2 are different can be determined.

[0082] Further, in some possible implementation manners, the above-mentioned difference sequence obtaining unit includes: a wavelength label obtaining unit, configured to determine the wavelength label corresponding to each wavelength in the spectral data, if the absorbance at a certain wavelength in the spectral data is less than the absorbance at the next wavelength, then set the wavelength label corresponding to the corresponding wavelength to a first value, if the absorbance at a certain wavelength is equal to the absorbance at the next wavelength, then set the wavelength label corresponding to the corresponding wavelength to a second value, if the absorbance at a certain wavelength is greater than the absorbance at the next wavelength, then set the wavelength label corresponding to the corresponding wavelength to a third value; a first sequence obtaining unit, configured to arrange all the wavelength labels in the order of wavelengths to obtain the spectral shape sequence corresponding to the spectral data; a second sequence obtaining unit, configured to perform an AND operation on the wavelength labels corresponding to the same wavelength in the spectral shape sequences corresponding to the spectral data of any two different Phellinus igniarius samples to obtain the spectral shape difference sequence of any two different Phellinus igniarius samples.

[0083] In this embodiment, for the spectral data of any Sanghuang sample, i.e., the infrared spectrogram, the absorbance S at the i-th and (i + 1)-th wavelengths is obtained. i and S i+1 ; when S i < S i+1 , a wavelength label with a value of 1 is assigned to the i-th wavelength, indicating that the shape of the spectral curve is rising; when S i = S i+1 , a wavelength label with a value of 0 is assigned to the i-th wavelength, indicating that the shape of the spectral curve remains unchanged; when S i > S i+1 , a wavelength label with a value of -1 is assigned to the i-th wavelength, indicating that the shape of the spectral curve is falling. In this way, the wavelength labels corresponding to all wavelengths in the spectral data of any Sanghuang sample can be obtained. The wavelength labels are arranged in ascending order of all wavelengths in the spectral data, and the spectral shape sequence corresponding to the spectral data of any Sanghuang sample can be obtained. It should be understood that for the last wavelength in the spectral data of the Sanghuang sample, since there is no subsequent wavelength, a wavelength label may not be assigned to the last wavelength, or the wavelength label of the penultimate wavelength may be directly assigned to the last wavelength.

[0084] The spectral data of any two different Sanghuang samples 1 and 2 are respectively denoted as A1 and A2. In the spectral shape sequences of spectral data A1 and spectral data A2, if the values at the same serial number, i.e., the element values corresponding to the same wavelength, are the same (i.e., the spectral curve shapes are the same), the marked value corresponding to this serial number is denoted as 1; if the values at the same serial number, i.e., the element values corresponding to the same wavelength, are different (i.e., the spectral curve shapes are different), the marked value corresponding to this serial number is denoted as 0. The marked values of all serial numbers are arranged in ascending order of the serial numbers, and thus the spectral shape difference sequence of the spectral data of any two different Sanghuang samples 1 and 2 can be obtained. For example, if the spectral shape sequence of spectral data A1 is {0, 0, 1} and the spectral shape sequence of spectral data A2 is {-1, 0, 1}, then the spectral shape difference sequence corresponding to spectral data A1 and A2 is {0, 1, 1}.

[0085] For the spectral shape difference sequence corresponding to spectral data A1 and A2, since the element 0 in the sequence indicates that the spectral shapes corresponding to spectral data A1 and A2 are the same, that is, the change trends at a certain wavelength are the same. Therefore, the wavelength interval between any two 0s in the sequence (the wavelength interval between adjacent 0s is 0) is used as the clustering distance, and the K-means clustering algorithm is used to perform K-means clustering on all 0s in the spectral shape difference sequence. Thus, the 0s with smaller wavelength intervals are clustered into one category, and multiple clusters are obtained. Among them, the K value in the K-means clustering algorithm can be obtained using the elbow method, and the specific obtaining process belongs to well-known technology and will not be elaborated here.

[0086] A wavelength range with different curve shapes is formed by the minimum wavelength to the maximum wavelength corresponding to all 0s in any one cluster, and thus multiple wavelength ranges with different curve shapes are obtained, and each wavelength range is used as the first wavelength segment. It should be understood that if there is only one 0 in a certain cluster, this cluster will not be analyzed. Furthermore, for each first wavelength segment, the first spectral data segment and the second spectral data segment of spectral data A1 and A2 under each first wavelength segment can be obtained, and are respectively denoted as A11 and A22.

[0087] Using the PCA principal component analysis method, principal component analysis is respectively performed on the first spectral data segment A11 and the second spectral data segment A22 to obtain multiple principal components decomposed from the first spectral data segment A11 and multiple principal components decomposed from the second spectral data segment A22, as well as the eigenvalue corresponding to each principal component. Among them, the larger the eigenvalue, the more information and data changes this principal component contains. In infrared spectral analysis, this means that this principal component may be closely related to the main chemical components or structural characteristics in the sample. For infrared spectral data with three overlapping components, after decomposition by the PCA principal component analysis method, theoretically three principal components can be obtained. Each spectral data segment has the same length as its decomposed principal components.

[0088] Perform a one-to-one matching on the principal components of the first spectral data segment A11 and the second spectral data segment A22 to obtain a matching result. Then, based on the matching result and the eigenvalues of the principal components, determine the spectral shape similarity after reducing the influence of component overlap between the spectral data of any two different Sanghuang samples. Further, in some possible implementation manners, the above-mentioned matching analysis unit includes: a matching unit, configured to perform a one-to-one matching on the principal components of the first spectral data segment and the second spectral data segment to obtain a plurality of one-to-one matching pairs and their matching edge values; a component similarity acquisition unit, configured to determine the component similarity between the first spectral data segment and the second spectral data segment according to the quantity difference between the principal components of the first spectral data segment and the second spectral data segment, the matching edge values of the one-to-one matching pairs, and the eigenvalues of the two principal components in the one-to-one matching pairs; a spectral shape similarity acquisition unit, configured to determine the spectral shape similarity after reducing the influence of component overlap between the spectral data of any two different Sanghuang samples according to the wavelength range ratio of the corresponding first wavelength segments of each first spectral data segment and the second spectral data segment within a set wavelength range, the component similarity between each first spectral data segment and the second spectral data segment, and the wavelength range ratio of the total wavelength range except all the first wavelength segments within the set wavelength range within the set wavelength range.

[0089] In the embodiment of the present invention, for the first spectral data segment A11 and the second spectral data segment A22 of the spectral data A1 and A2 at each first wavelength segment, using the KM matching algorithm (Kuhn - Munkres), with the principal components corresponding to A11 as the left nodes and the principal components corresponding to A22 as the right nodes, perform a one-to-one matching on the left nodes and the right nodes to obtain a plurality of one-to-one matching pairs and the matching edge values of each one-to-one matching pair. Each matching pair includes a left node and a right node, and each matching pair is unique, without a one-to-many situation. Among them, the KM matching algorithm is also known as the Hungarian algorithm, which is an efficient algorithm for solving the assignment problem. This is a well-known technology. Specifically: each left node is connected to all the right nodes, and the matching edge value on the connection edge is the Pearson correlation coefficient of the two principal components corresponding to the two nodes. Among them, the Pearson correlation coefficient is a well-known calculation. The larger the correlation coefficient, the more similar the change trends of the two principal components. Then, through KM matching, following the principle of maximum matching, obtain the one-to-one matching pairs of the left and right nodes. The one-to-one matching pairs indicate that the components decomposed from A11 and the components decomposed from A22 are likely to be the same.

[0090] Therefore, based on the quantitative differences between the respective principal components of the first spectral data segments A11 and the second spectral data segments A22 of the spectral data A1 and A2 in each first wavelength band, the matching edge values of the one-to-one matching pairs, and the eigenvalues of the two principal components in the one-to-one matching pairs, determine the degree of component identity between the first spectral data segments A11 and the second spectral data segments A22 of the spectral data A1 and A2 in each first wavelength band:

[0091]

[0092] In the formula: Q x is the degree of component identity between the first spectral data segments A11 and the second spectral data segments A22 of the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 at the x-th first wavelength band; B1 is the number of principal components decomposed from the first spectral data segment A11 of the spectral data A1 of Phellinus igniarius sample 1 at the x first wavelength bands, and B2 is the number of principal components decomposed from the second spectral curve segment A22 of the spectral data A2 of Phellinus igniarius sample 2 at the x first wavelength bands; exp( ) is the exponential function with the natural constant e as the base; T is the number of one-to-one matching pairs of the first spectral data segments A11 and the second spectral data segments A22 of the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 at the x-th first wavelength band; P t is the matching edge value of the t-th one-to-one matching pair, that is, the Pearson correlation coefficient between the principal components corresponding to the left and right nodes in the t-th one-to-one matching pair; C 1,t and C 2,t are the eigenvalues of the principal components corresponding to the left and right nodes in the t-th one-to-one matching pair, respectively.

[0093] In the above formula, when |B1 - B2| is 0, it indicates that the number of overlapping chemical components in the first spectral data segment A11 and the second spectral data segment A22 is the same. The larger the value of the degree of component identity corresponding to the first spectral data segment A11 and the second spectral data segment A22, so the exponential function exp(-) is used to perform negative correlation normalization processing on |B1 - B2|. At the same time, the larger the matching edge weight value between the principal components corresponding to the left and right nodes in each one-to-one matching pair of the first spectral data segment A11 and the second spectral data segment A22, the more similar the change trends of the two principal components. And the larger the eigenvalues of the two principal components, the closer the principal components are related to the main chemical components in the Phellinus igniarius sample. Therefore, is used as the weight of the matching edge weight value P t of the two principal components. Furthermore, the matching edge weight values of the two principal components in all one-to-one matching pairs are weighted and summed to obtain the cumulative value of the weighted matching edge weight values This cumulative value of the weighted matching edge weight values The larger it is, the more consistent the overlapping chemical components in the first spectral data segment A11 and the second spectral data segment A22 are.

[0094] Furthermore, for the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2, according to the wavelength range ratio of each first wavelength segment within the set wavelength range, the degree of component similarity between the first spectral data segment A11 and the second spectral data segment A22 of the spectral data A1 and A2 at each first wavelength segment, and the wavelength range ratio of the total wavelength range excluding all first wavelength segments within the set wavelength range to the set wavelength range, determine the spectral shape similarity H between the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 after reducing the influence of component overlap:

[0095]

[0096] In the formula: L is the set wavelength range of the spectral data, that is, the wavelength range size of the infrared spectrogram (4000 - 400); X is the number of first wavelength segments of the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2; L x is the wavelength range size of the x-th first wavelength segment of the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2; Q x is the degree of component similarity between the first spectral data segment A11 and the second spectral data segment A22 of the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 at the x-th first wavelength segment; L1 is the size of the total wavelength range excluding all first wavelength segments within the set wavelength range; norm( ) is the linear normalization function.

[0097] In the above formula, the degree of component similarity Q x The larger it is, the more similar the spectral data shapes of the spectral data A1 and A2 within the wavelength range of the x-th first wavelength segment are after reducing the influence of component overlap, that is, L x should be the wavelength range with the same spectral shape. Therefore, the closer the spectral shape similarity H is to 1, the more similar the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 are in shape.

[0098] The above analyzes the spectral shape similarity after reducing the influence of component overlap. However, due to the influence of factors such as geographical environment, climate conditions, soil type, and cultivation techniques, there may be significant differences in the component contents of Phellinus igniarius from different origins. In addition, even for Phellinus igniarius from the same origin, there may be certain differences in the component contents of Phellinus igniarius, but the differences in component contents are relatively small compared to those from different origins. Therefore, it is also necessary to analyze the spectral data of different Phellinus igniarius samples to determine the difference in the same component contents between the spectral data of any two different Phellinus igniarius samples.

[0099] Further, in some possible implementation manners, the above similarity analysis module further includes a second analysis module, and the second analysis module includes: a second wavelength band obtaining unit, configured to obtain a plurality of second wavelength bands corresponding to a wavelength range where spectral shapes of spectral data of any two different Phellinus igniarius samples are the same within a set wavelength range; a first content difference obtaining unit, configured to respectively obtain a third spectral data segment and a fourth spectral data segment of spectral data of any two different Phellinus igniarius samples under each second wavelength band, and determine a first same-component content difference and a first maximum component content difference according to absorbance differences at the same wavelength in the third spectral data segment and the fourth spectral data segment; a second content difference obtaining unit, configured to determine a second same-component content difference and a second maximum component content difference according to absorbance differences at the same wavelength in one-to-one matching pairs of the first spectral data segment and the second spectral data segment; a dissimilarity obtaining unit, configured to determine a same-component content dissimilarity between spectral data of any two different Phellinus igniarius samples according to all the first same-component content differences, the first maximum component content differences, the second same-component content differences, and the second maximum component content differences corresponding to any two different Phellinus igniarius samples.

[0100] Specifically, for spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2, a plurality of second wavelength bands corresponding to a wavelength range where spectral shapes of the spectral data A1 and A2 are the same within the set wavelength range are obtained, that is, continuous wavelength bands between every two adjacent first wavelength bands of the spectral data A1 and A2 within the set wavelength range, and continuous wavelength bands before the first first wavelength band and after the last first wavelength band are used as respective second wavelength bands of the spectral data A1 and A2 within the set wavelength range. It should be understood that if there are also continuous wavelength bands before the first first wavelength band and after the last first wavelength band, the continuous wavelength bands are also used as the second wavelength bands of the spectral data A1 and A2. For each second wavelength band, a third spectral data segment and a fourth spectral data segment of the spectral data A1 and A2 under each second wavelength band can be obtained, and are respectively denoted as A33 and A44.

[0101] Furthermore, according to absorbance differences at the same wavelength in the third spectral data segment A33 and the fourth spectral data segment A44 of the spectral data A1 and A2 under each second wavelength band, a first same-component content difference and a first maximum component content difference of the spectral data A1 and A2 under each second wavelength band are determined. Further, in some possible implementation manners, the above first content difference obtaining unit includes: a first same-component content difference obtaining unit, configured to determine a sum value of absolute values of differences in absorbance at the same wavelength in the third spectral data segment and the fourth spectral data segment, to obtain the first same-component content difference; a first maximum component content difference obtaining unit, configured to determine a maximum value of absolute values of differences in absorbance at the same wavelength in the third spectral data segment and the fourth spectral data segment, to obtain the first maximum component content difference.

[0102] In this embodiment, for the third spectral data segment A33 and the fourth spectral data segment A44 of the spectral data A1 and A2 in the y-th second wavelength band, the absolute value of the difference in absorbance at the same wavelength is obtained, and the sum of the absolute values of the differences in absorbance at all the same wavelengths is used as the first co-component content difference in the y-th second wavelength band, and the maximum value of the absolute values of the differences in absorbance at all the same wavelengths is used as the first maximum component content difference in the y-th second wavelength band.

[0103] Meanwhile, for the one-to-one matching pairs of the principal components decomposed from the first spectral data segment A11 and the second spectral data segment A22 of the spectral data A1 and A2 in each first wavelength band, according to the absorbance difference of the two principal components in the same wavelength in each one-to-one matching pair, in the same way, the second co-component content difference and the second maximum component content difference of each one-to-one matching pair are obtained. That is, for each one-to-one matching pair, the absolute value of the difference in the data values with the same serial number in the principal components corresponding to the left and right nodes is calculated, and the sum of the absolute values of the differences in the data values with the same serial number is used as the second co-component content difference of each one-to-one matching pair, and the maximum value of the absolute values of the differences in the data values with the same serial number is used as the second maximum component content difference of each one-to-one matching pair.

[0104] Furthermore, based on all the first co-component content differences, the first maximum component content differences, the second co-component content differences, and the second maximum component content differences corresponding to the spectral data A1 and A2, the co-component content dissimilarity between the spectral data A1 and A2 can be determined. Further, in some possible implementation manners, the above dissimilarity obtaining unit includes: a comprehensive co-component content difference determining unit, configured to determine the sum of all the first co-component content differences and the second co-component content differences corresponding to any two different Phellinus igniarius samples to obtain a comprehensive co-component content difference; a maximum component content difference variance determining unit, configured to determine the variance and the maximum value of all the first maximum component content differences and the second maximum component content differences corresponding to any two different Phellinus igniarius samples, and correspondingly obtain a maximum component content difference variance and a maximum component content difference maximum value; and a dissimilarity determining unit, configured to determine the co-component content dissimilarity between the spectral data of any two different Phellinus igniarius samples according to the comprehensive co-component content difference, the maximum component content difference variance, and the maximum component content difference maximum value.

[0105] In the embodiment of the present invention, for the spectral data A1 and A2, the first co-component content differences of all the second wavelength bands and the second co-component content differences of all the first wavelength bands form a co-component content difference set; similarly, the first maximum component content differences of all the second wavelength bands and the second maximum component content differences of all the first wavelength bands form a maximum component content difference set. At this time, based on the co-component content difference set and the maximum component content difference set, the co-component content dissimilarity R between the spectral data A1 and A2 is determined:

[0106] R = D sum × norm(F v × F max );

[0107] Where: D sum is the sum of all the same - component content differences in the set of same - component content differences, that is, the comprehensive same - component content difference; F v is the variance of all the maximum component content differences in the set of maximum component content differences, that is, the maximum component content difference variance; F max is the maximum value of all the maximum component content differences in the set of maximum component content differences, that is, the maximum component content difference maximum; norm() is a linear normalization function.

[0108] In the above formula, the larger D sum is, the greater the difference in the same - component content between the spectral data A1 and A2. At the same time, since there may also be certain differences in the component content of Phellinus igniarius from the same origin, but relatively small, that is, F max is small, and the difference between the maximum component content differences of different components is also small, that is, F v is small; while for Phellinus igniarius from different origins, there may be significant differences in the content of a certain component, resulting in F v and F max being large. Therefore, calculate the normalization of F v × F max to obtain an adjustment coefficient, and use this adjustment coefficient to adjust and correct D sum Finally, obtain the non - similarity R of the same - component content. The larger the value of the non - similarity R of the same - component content, the greater the difference between the maximum component content differences of different components in the spectral data A1 and A2, and there are components with large content differences, and the less similar the same - component content of the Phellinus igniarius corresponding to the spectral data A1 and A2.

[0109] Thus, in the above - mentioned manner, the spectral shape similarity H and the non - similarity R of the same - component content after reducing the influence of component overlap can be determined between the spectral data of any two different Phellinus igniarius samples.

[0110] A clustering module, which is used to determine the distance index between the spectral data of any two different Phellinus igniarius samples according to the spectral shape similarity and the non - similarity of the same - component content after reducing the influence of component overlap, and based on the distance index, cluster the spectral data of all Phellinus igniarius samples with unknown origins to obtain several clustering clusters.

[0111] Specifically, based on the spectral shape similarity H and the non - similarity R of the same component content after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples, the distance index between the spectral data of any two different Phellinus igniarius samples is determined. When the value of the spectral shape similarity H after reducing the influence of component overlap is smaller, and the value of the non - similarity R of the same component content is larger, it indicates that the spectral data of any two different Phellinus igniarius samples are more dissimilar, and the corresponding distance index is larger.

[0112] Further, in some possible implementation manners, the clustering module includes: a negative - correlation mapping processing unit, configured to perform negative - correlation mapping processing on the spectral shape similarity to obtain a spectral shape similarity processing value; a distance - index acquisition unit, configured to calculate the product of the spectral shape similarity processing value and the non - similarity of the same component content as the distance index; and a second clustering unit, configured to perform clustering on the spectral data of all Phellinus igniarius samples with unknown origins by using the K - means clustering algorithm based on the distance index, to obtain a plurality of clustering clusters.

[0113] In this embodiment, based on the spectral shape similarity H and the non - similarity R of the same component content after reducing the influence of component overlap between the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2, the distance index between the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 is determined:

[0114] D=(1 - H)×R;

[0115] In the formula: D is the distance index between the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2. By performing negative - correlation mapping processing on the spectral data shape similarity H of the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2 after reducing the influence of component overlap, the spectral shape similarity processing value 1 - H is obtained, and the non - similarity R of the same component content between the spectral data A1 and A2 is adjusted by using the spectral shape similarity processing value 1 - H, and finally the distance index between the spectral data A1 and A2 is obtained. When the value of the spectral data shape similarity H of the spectral data A1 and A2 after reducing the influence of component overlap is larger, the spectral data A1 and A2 are more similar, and the distance index D should be smaller; at the same time, when the value of the non - similarity R of the same component content between the spectral data A1 and A2 is larger, it indicates that the spectral data A1 and A2 are more dissimilar, and the distance index D should be larger.

[0116] Taking the distance index between the spectral data of any two Phellinus igniarius samples with unknown origins as the clustering distance, based on all clustering distances, the spectral data of all Phellinus igniarius samples with unknown origins are clustered by using the K - means clustering algorithm to obtain a plurality of clustering clusters, and each clustering cluster corresponds to one or more Phellinus igniarius samples. Among them, the value of K in the K - means clustering algorithm can be obtained by using the elbow method, and the specific obtaining process belongs to well - known technology and will not be elaborated here.

[0117] The origin determination module is used to match the spectral data in each clustering cluster with the spectral data of the representative Phellinus igniarius samples with all known origins based on the distance index, and determine the origin of the Phellinus igniarius samples corresponding to each clustering cluster according to the matching result.

[0118] Specifically, based on the distance index, the spectral data in each clustering cluster is matched with the spectral data of the representative Phellinus igniarius samples with all known origins, the spectral data of the representative Phellinus igniarius sample of a certain origin that best matches the spectral data in each clustering cluster is determined, and this certain origin is used as the origin of the Phellinus igniarius samples corresponding to each clustering cluster.

[0119] Further, in some possible implementation manners, the above-mentioned origin determination module includes: a first distance index acquisition unit, which is used to determine the average value of the similarity indexes between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples with the same origin to obtain the average distance index; a second distance index acquisition unit, which is used to determine the minimum value among the average distance indexes between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples with different origins to obtain the minimum average distance index; an origin determination unit, which is used to use the origin corresponding to the minimum average distance index as the origin of the Phellinus igniarius samples corresponding to each clustering cluster.

[0120] In this embodiment, for the spectral data of multiple representative Phellinus igniarius samples with the origin in Province A, in the above-mentioned manner of obtaining the distance index between the spectral data A1 and A2 of any two different Phellinus igniarius samples 1 and 2, the distance indexes between the spectral data of each representative Phellinus igniarius sample and the spectral data in each clustering cluster can be determined. Furthermore, the average value of all the distance indexes between the spectral data of all representative Phellinus igniarius samples and the spectral data in each clustering cluster can be determined to obtain the average distance index between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples with the same origin. Determine the minimum value among all the average similarity indexes corresponding to each clustering cluster to obtain the minimum average distance index. The origin corresponding to this minimum average distance index is the most matching origin of each clustering cluster, so the origin corresponding to the minimum average distance index is used as the origin of the Phellinus igniarius samples corresponding to each clustering cluster. Thus, the origin identification of all Phellinus igniarius samples with unknown origins can be realized.

[0121] Based on the same inventive concept, as Figure 2 shown, the embodiment of the present invention also provides an intelligent differentiation and detection method for the components of Phellinus igniarius with different origins. The method includes the following steps:

[0122] Obtain the spectral data of several Phellinus igniarius samples with unknown origins and the spectral data of the representative Phellinus igniarius samples with known origins. The spectral data includes the absorbance at different wavelengths within a set wavelength range;

[0123] Analyze the spectral data to determine the spectral shape similarity and the dissimilarity of the same component content between the spectral data of any two different Phellinus igniarius samples after reducing the influence of overlapping components.

[0124] According to the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of overlapping components, determine the distance index between the spectral data of any two different Phellinus igniarius samples, and based on the distance index, cluster the spectral data of all Phellinus igniarius samples with unknown origins to obtain several clustering clusters.

[0125] Based on the distance index, match the spectral data in each clustering cluster with the spectral data of the representative Phellinus igniarius samples of all known origins, and determine the origin of the Phellinus igniarius samples corresponding to each clustering cluster according to the matching results.

[0126] Based on the same inventive concept, an embodiment of the present invention also provides an intelligent discrimination and detection device for Phellinus igniarius components from different origins, as Figure 5 shown. The device includes: a memory 501, a processor 502, and computer program code 503 stored in the memory 501 and running on the processor 502. Among them, when the processor 502 executes the computer program code 503, the device can execute the module implementation steps in any one of the intelligent discrimination and detection systems for Phellinus igniarius components from different origins introduced above.

[0127] An embodiment of the present invention can divide the functions of the device according to the module implementation step examples in the above system. For example, it can correspond to each function module, or integrate two or more functions into one processing module. The above integrated modules can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0128] Based on the same inventive concept, an embodiment of the present invention also provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer is enabled to execute the module implementation steps in any one of the intelligent discrimination and detection systems for Phellinus igniarius components from different origins introduced above.

[0129] Based on the same inventive concept, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer is enabled to execute the module implementation steps in any one of the intelligent discrimination and detection systems for Phellinus igniarius components from different origins introduced above.

[0130] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. An intelligent discrimination and detection system for the components of Phellinus igniarius from different producing areas, characterized in that, The system includes: A data acquisition module, configured to acquire spectral data of a plurality of Phellinus igniarius samples with unknown origins and representative Phellinus igniarius samples with known origins, where the spectral data includes absorbances at different wavelengths within a set wavelength range; A similarity analysis module, configured to analyze the spectral data to determine the spectral shape similarity and the dissimilarity of the same component content between the spectral data of any two different Phellinus igniarius samples after reducing the influence of component overlap; A clustering module, configured to determine a distance metric between the spectral data of any two different Phellinus igniarius samples based on the spectral shape similarity and the dissimilarity of the same component content after reducing the influence of component overlap, and cluster the spectral data of all Phellinus igniarius samples with unknown origins based on the distance metric to obtain a plurality of clustering clusters; An origin determination module, configured to match the spectral data in each clustering cluster with the spectral data of all representative Phellinus igniarius samples with known origins based on the distance metric, and determine the origin of the Phellinus igniarius samples corresponding to each clustering cluster according to the matching result.

2. The intelligent discrimination and detection system for the components of Sanghuang from different producing areas according to claim 1, wherein The similarity analysis module includes a first analysis module, and the first analysis module includes: A first wavelength range acquisition unit, configured to acquire a plurality of first wavelength ranges corresponding to the wavelength ranges where the spectral shapes of the spectral data of any two different Phellinus igniarius samples are different within the set wavelength range; A principal component analysis unit, configured to respectively acquire a first spectral data segment and a second spectral data segment of the spectral data of any two different Phellinus igniarius samples at each first wavelength range, perform principal component analysis on the first spectral data segment and the second spectral data segment, and acquire a plurality of principal components and their eigenvalues of the first spectral data segment and the second spectral data segment; A matching analysis unit, configured to perform one-to-one matching on the principal components of the first spectral data segment and the second spectral data segment, and determine the spectral shape similarity between the spectral data of any two different Phellinus igniarius samples after reducing the influence of component overlap according to the matching result and the eigenvalues of the principal components.

3. The intelligent discrimination and detection system for Sanghuang components from different origins according to claim 2, characterized in that, The first wavelength range acquisition unit includes: A difference sequence acquisition unit, configured to determine a spectral shape difference sequence of any two different Phellinus igniarius samples according to the difference in the change trend of the absorbances of the spectral data of any two different Phellinus igniarius samples at the same wavelength, where the spectral shape difference sequence reflects the difference in the change trend of the spectral data of any two different Phellinus igniarius samples at the same wavelength; A first clustering unit, configured to cluster the target elements in the spectral shape difference sequence to obtain a plurality of clusters, and if the change trends of the spectral data of any two different Phellinus igniarius samples at a certain wavelength are the same, use the element corresponding to the certain wavelength in the spectral shape difference sequence as the target element; A first wavelength range acquisition unit, configured to use the wavelength range formed by the maximum wavelength and the minimum wavelength corresponding to the target elements in each cluster as a first wavelength range.

4. An intelligent discrimination and detection system for the components of Phellinus igniarius from different origins according to claim 3, characterized in that, The difference sequence acquisition unit includes: A wavelength label acquisition unit, configured to determine a wavelength label corresponding to each wavelength in spectral data. If the absorbance at a certain wavelength in the spectral data is less than the absorbance at the next wavelength, the wavelength label corresponding to the corresponding wavelength is set to a first value. If the absorbance at a certain wavelength is equal to the absorbance at the next wavelength, the wavelength label corresponding to the corresponding wavelength is set to a second value. If the absorbance at a certain wavelength is greater than the absorbance at the next wavelength, the wavelength label corresponding to the corresponding wavelength is set to a third value; A first sequence acquisition unit, configured to arrange all wavelength labels in the order of wavelengths to obtain a spectral shape sequence corresponding to the spectral data; A second sequence acquisition unit, configured to perform an AND operation on the wavelength labels at the same wavelength of the spectral shape sequences corresponding to the spectral data of any two different Phellinus igniarius samples to obtain a spectral shape difference sequence of any two different Phellinus igniarius samples.

5. An intelligent discrimination and detection system for Phellinus igniarius components from different origins according to claim 2, characterized in that, The matching analysis unit includes: A matching unit, configured to perform one-to-one matching on each principal component of a first spectral data segment and a second spectral data segment to obtain a plurality of one-to-one matching pairs and their matching edge values; A component similarity acquisition unit, configured to determine the component similarity between the first spectral data segment and the second spectral data segment according to the quantity difference between each principal component of the first spectral data segment and the second spectral data segment, the matching edge values of the one-to-one matching pairs, and the eigenvalues of the two principal components in the one-to-one matching pairs; A spectral shape similarity acquisition unit, configured to determine the spectral shape similarity after reducing the influence of component overlap between the spectral data of any two different Phellinus igniarius samples according to the wavelength range ratio of the corresponding first wavelength segments of each first spectral data segment and the second spectral data segment within a set wavelength range, the component similarity between each first spectral data segment and the second spectral data segment, and the wavelength range ratio of the total wavelength range except all the first wavelength segments within the set wavelength range within the set wavelength range; 6. An intelligent discrimination and detection system for Sanghuang components from different origins according to claim 5, characterized in that, The similarity analysis module further includes a second analysis module, and the second analysis module includes: A second wavelength segment acquisition unit, configured to acquire a plurality of second wavelength segments corresponding to the wavelength range where the spectral shapes of the spectral data of any two different Phellinus igniarius samples are the same within a set wavelength range; A first content difference acquisition unit, configured to respectively acquire a third spectral data segment and a fourth spectral data segment of the spectral data of any two different Phellinus igniarius samples at each second wavelength segment, and determine a first same-component content difference and a first maximum component content difference according to the absorbance difference at the same wavelength in the third spectral data segment and the fourth spectral data segment; A second content difference acquisition unit, configured to determine a second same-component content difference and a second maximum component content difference according to the absorbance difference at the same wavelength in the one-to-one matching pairs of the first spectral data segment and the second spectral data segment; A dissimilarity acquisition unit, configured to determine the same-component content dissimilarity between the spectral data of any two different Phellinus igniarius samples according to all the first same-component content differences and the first maximum component content differences and all the second same-component content differences and the second maximum component content differences corresponding to any two different Phellinus igniarius samples.

7. An intelligent discrimination and detection system for Sanghuang components from different origins according to claim 6, characterized in that, The first content difference obtaining unit includes: The first same-component content difference obtaining unit is used to determine the sum value of the absolute values of the differences in absorbance at the same wavelength in the third spectral data segment and the fourth spectral data segment, so as to obtain the first same-component content difference; The first maximum component content difference obtaining unit is used to determine the maximum value of the absolute values of the differences in absorbance at the same wavelength in the third spectral data segment and the fourth spectral data segment, so as to obtain the first maximum component content difference.

8. An intelligent discrimination and detection system for the components of Sanghuang from different origins according to claim 6, characterized in that, The dissimilarity obtaining unit includes: The comprehensive same-component content difference determining unit is used to determine the sum value of all the first same-component content differences and the second same-component content differences corresponding to any two different Phellinus igniarius samples, so as to obtain the comprehensive same-component content difference; The maximum component content difference variance determining unit is used to determine the variance sum and the maximum value of the variances of all the first maximum component content differences and the second maximum component content differences corresponding to any two different Phellinus igniarius samples, and correspondingly obtain the maximum component content difference variance and the maximum value of the maximum component content difference; The dissimilarity determining unit is used to determine the same-component content dissimilarity between the spectral data of any two different Phellinus igniarius samples according to the comprehensive same-component content difference, the maximum component content difference variance and the maximum value of the maximum component content difference.

9. The intelligent discrimination and detection system for the components of Phellinus igniarius from different origins according to claim 1, wherein The clustering module includes: The negative correlation mapping processing unit is used to perform negative correlation mapping processing on the spectral shape similarity to obtain the spectral shape similarity processing value; The distance index obtaining unit is used to calculate the product of the spectral shape similarity processing value and the same-component content dissimilarity as the distance index; The second clustering unit is used to cluster the spectral data of all Phellinus igniarius samples with unknown origins based on the distance index by using the K-means clustering algorithm to obtain several clustering clusters.

10. An intelligent discrimination and detection system for the components of Phellinus igniarius from different origins according to claim 1, characterized in that, The origin determining module includes: The first distance index obtaining unit is used to determine the average value of the similarity indexes between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples of each same origin, so as to obtain the average distance index; The second distance index obtaining unit is used to determine the minimum value among the average distance indexes between the spectral data of each clustering cluster and the spectral data of the representative Phellinus igniarius samples of different origins, so as to obtain the minimum average distance index; The origin determining unit is used to use the origin corresponding to the minimum average distance index as the origin of the Phellinus igniarius samples corresponding to each clustering cluster.

Images