Traditional Chinese medicinal material rapid detection system based on artificial intelligence model

Abstract

The invention relates to the technical field of traditional Chinese medicinal material detection, and particularly discloses a traditional Chinese medicinal material rapid detection system based on an artificial intelligence model, and the system comprises a conveying module which is used for conveying and transporting traditional Chinese medicinal materials; the image acquisition module is used for acquiring the image information of the traditional Chinese medicinal materials on the transmission module; the smell collection module is used for collecting smell information of the traditional Chinese medicinal materials on the transmission module; the sorting module is used for sorting, removing, sorting and preparing the traditional Chinese medicinal materials on the conveying module and sorting, removing, sorting and returning the traditional Chinese medicinal materials on the sorting and temporary storage module; according to the method, the traditional Chinese medicinal materials are rapidly screened according to the characteristic similarity coefficients of the traditional Chinese medicinal materials, and then the traditional Chinese medicinal materials with medium similarity coefficients of the traditional Chinese medicinal materials are further fully detected through the near-infrared spectrometer, so that the purpose of rapidly detecting the traditional Chinese medicinal materials is achieved, and the detection quantity of the near-infrared spectrometer is effectively reduced; and the detection accuracy of the traditional Chinese medicinal materials is also ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of Chinese medicinal material detection, and in particular to a Chinese medicinal material rapid detection system based on an artificial intelligence model. Background Art

[0002] For a long time, most of the Chinese medicinal materials in my country have been processed in a decentralized manner. After being initially processed into raw medicinal materials at the place of origin, different regions and enterprises perform secondary processing due to differences in production implementation conditions and lack of standardized production in different places. In particular, sulfur fumigation in some places has been repeatedly banned, resulting in uneven quality of processed medicinal pieces and common adulteration in the market, which affects the clinical efficacy of traditional Chinese medicine. In order to ensure the quality of Chinese medicinal materials, many companies need to test the quality of Chinese medicinal materials when purchasing or processing them.

[0003] Traditional detection methods for Chinese medicinal materials are mostly to detect the components of Chinese medicinal materials through liquid chromatography. Although this detection method can effectively detect Chinese medicinal materials, its detection process is complicated, including medicinal material crushing, drying, physical and chemical analysis, and detection through liquid chromatography; the data generation cycle is long, which may take several days or even longer. In the application process, most of the purchased Chinese medicinal materials can only be sampled and tested, and it is difficult to achieve the purpose of fully detecting the quality of Chinese medicinal materials. With the development of technology, there is also a method of detecting Chinese medicinal materials through near-infrared spectrometer. The detection time of a single sample of Chinese medicinal materials by near-infrared spectrometer detection method can be completed within 1 minute, which is greatly improved compared with the detection efficiency of liquid chromatography (more than 99.9% of the time is saved). Compared with the detection results of liquid chromatography, the correlation coefficient reaches more than 0.95, which can ensure the reliability of the detection results and effectively improve the detection efficiency of Chinese medicinal materials. However, when it is actually used for the detection of Chinese medicinal materials in the process of Chinese medicinal materials processing, its detection speed still cannot meet the purpose of rapid and sufficient detection of Chinese medicinal materials. Summary of the invention

[0004] The purpose of the present invention is to provide a rapid detection system for Chinese herbal medicines based on an artificial intelligence model to solve the following technical problems:

[0005] How to achieve the goal of rapid detection of Chinese medicinal materials based on artificial intelligence.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A rapid detection system for Chinese medicinal materials based on an artificial intelligence model, the system comprising:

[0008] A conveying module, used for conveying and transporting Chinese medicinal materials;

[0009] An image acquisition module, used for acquiring image information of the Chinese medicinal materials on the transmission module;

[0010] An odor collection module is used to collect odor information of the Chinese medicinal materials on the transmission module;

[0011] The sorting module is used to sort, remove and prepare the Chinese medicinal materials on the conveying module, and to sort, remove and return the Chinese medicinal materials on the sorting temporary storage module;

[0012] A sorting and temporary storage module is used to temporarily store the sorted and prepared Chinese medicinal materials to be tested by near-infrared spectrometer and the remaining medicinal materials;

[0013] Near infrared spectrometer, used to perform infrared spectrum analysis on prepared Chinese medicinal materials and generate similarity coefficients of Chinese medicinal materials components;

[0014] The analysis control module generates signals for the sorting module to sort and prepare the Chinese medicinal materials at a preset frequency; processes and analyzes the image information and the odor information to obtain the similarity coefficient of the Chinese medicinal materials characteristics, and generates signals for the sorting module to sort, reject and prepare the Chinese medicinal materials; generates signals for the sorting module to sort, reject and sort and return the Chinese medicinal materials according to the similarity coefficient of the Chinese medicinal materials components.

[0015] Furthermore, the process of obtaining the similarity coefficient of Chinese medicinal material characteristics includes:

[0016] S1, pre-process the image information by denoising, enhancing, and resizing, and extract the color, texture, and shape features of Chinese medicinal materials;

[0017] S2, filtering and amplifying the odor information to extract the odor characteristics of Chinese medicinal materials;

[0018] S3. Generate a similarity coefficient of Chinese medicinal material characteristics by comparing the color, texture, shape and gas characteristics of Chinese medicinal materials with the data in the Chinese medicinal material database.

[0019] Furthermore, in step S3, the process of generating the similarity coefficient of Chinese medicinal material characteristics includes:

[0020]

[0021] The similarity coefficient Q of Chinese medicinal materials characteristics is obtained by calculation and analysis through formula (1)-(2) s ;

[0022] Among them, E i is the similarity evaluation parameter of the i-th feature, E i,stdis the i-th feature standard evaluation parameter. When i=1, E1 is the comprehensive similarity evaluation parameter of the texture feature of Chinese medicinal materials. When i=2, E2 is the similarity evaluation parameter of the color feature of Chinese medicinal materials. When i=3, E3 is the similarity evaluation parameter of the shape feature of Chinese medicinal materials. When i=4, E4 is the similarity evaluation parameter of the smell feature of Chinese medicinal materials. When i=5, E5 is the similarity evaluation parameter of other features of Chinese medicinal materials. ω i is the influence coefficient of the i-th feature on the detection of Chinese medicinal materials, R1 is the number of textures on the Chinese medicinal materials whose texture similarity reaches the first preset coefficient, R2 is the number of textures on the Chinese medicinal materials whose texture similarity does not reach the second preset coefficient, is the weight coefficient corresponding to different texture numbers.

[0023] Furthermore, the process of generating a signal for the sorting module to sort, reject and prepare the Chinese medicinal materials includes:

[0024] The similarity coefficient of Chinese medicinal materials characteristics Q s Compare with the preset threshold range of Chinese medicinal material characteristics [Q1, Q2];

[0025] If Q s >Q2, no sorting signal is generated, and the analysis and control module generates a signal for the sorting module to sort and prepare the Chinese medicinal materials at a preset frequency;

[0026] If Q s ∈[Q1,Q2], the analysis and control module marks the detected Chinese medicinal materials and generates corresponding sorting and preparation signals;

[0027] If Q s <Q1, the analysis and control module marks the detected Chinese medicinal materials and generates corresponding sorting and rejection signals.

[0028] Furthermore, the process of generating the similarity coefficient of Chinese medicinal material components includes:

[0029] The spectrum of the prepared Chinese medicinal materials is collected by a near-infrared spectrometer to obtain the spectrum data of the corresponding Chinese medicinal materials;

[0030] Preprocess the spectral data and input it into the constructed artificial intelligence big data model to compare it with the chemical component content in the preset Chinese herbal medicine samples;

[0031] The similarity coefficient of the Chinese medicinal materials components of the corresponding Chinese medicinal materials is calculated based on the comparison results.

[0032] Furthermore, the process of generating a signal for the sorting module to sort and reject the Chinese medicinal materials and sort and return them to their original positions includes:

[0033] Compare the similarity coefficient of Chinese medicinal materials ingredients with the preset standard similarity coefficient of Chinese medicinal materials ingredients;

[0034] If the similarity coefficient of the Chinese medicinal material components is greater than or equal to the preset similarity coefficient of the Chinese medicinal material components standard, the analysis and control module marks the remaining Chinese medicinal materials after sorting and preparation and generates a corresponding sorting homing signal;

[0035] If the similarity coefficient of the Chinese medicinal material ingredients is less than the preset standard similarity coefficient of the Chinese medicinal material ingredients, the analysis and control module marks the remaining Chinese medicinal materials after sorting and preparation and generates a corresponding sorting and rejection signal.

[0036] Furthermore, the system further comprises:

[0037] The statistical adjustment module performs statistical analysis on the result data of Chinese medicinal materials detected by the near-infrared spectrometer and adjusts the preset threshold range of Chinese medicinal materials characteristics; the sorting module performs statistical analysis on the data of sorting, rejection, sorting preparation and unsorted Chinese medicinal materials on the transmission module and adjusts the preset frequency.

[0038] Furthermore, the process of adjusting the preset threshold range of Chinese medicinal material characteristics includes:

[0039] Conduct statistical analysis on the number of signals generated by the near infrared spectrometer after testing a preset number of Chinese medicinal materials in the near future;

[0040]

[0041] The defect rate Z1 of the preset number of Chinese medicinal materials is obtained by calculation and analysis through formula (3);

[0042] The preset number of Chinese medicinal materials defect rate Z1 and the preset defect rate threshold range [Z a , Z b ] for comparison;

[0043] If Z1>Z b , then update the left endpoint Q1 of the threshold range [Q1, Q2] to Q 1，re , Q 1，re =Q1+ΔQ;

[0044] If Z1<Z a , then update the left endpoint Q1 of the threshold range [Q1, Q2] to Q 1，re , Q 1，re =Q1-ΔQ;

[0045] Among them, Q 1，re is the lowest threshold of the updated preset threshold range of Chinese herbal medicine characteristics, ΔQ is the adjustment coefficient of the threshold range of Chinese herbal medicine characteristics, and A risk The number of sorting rejection signals generated for the NIR spectrometer, A all The total number of signals generated for the near infrared spectrometer;

[0046] Conduct statistical analysis on the number of signals generated by the near infrared spectrometer after the near infrared spectrometer has recently detected a preset number of Chinese medicinal materials and the corresponding number of signals generated after a certain number of Chinese medicinal materials have been sorted and prepared at a preset frequency;

[0047]

[0048] The abnormal rate Z2 of the preset number of Chinese medicinal materials is obtained through timely analysis through formula (4);

[0049] The abnormal rate Z2 of the preset number of Chinese medicinal materials is compared with the preset abnormal rate threshold range [Z c , Z d ] for comparison;

[0050] If Z2>Z d , then update the right endpoint Q2 of the threshold range [Q1, Q2] to Q 2，re , Q 2，re =Q2+ΔQ;

[0051] If Z2<Z c , then update the right endpoint Q2 of the threshold range [Q1, Q2] to Q 2，re , Q 2，re =Q2-ΔQ;

[0052] Among them, Q 2，re is the highest threshold of the updated preset TCM characteristic threshold range, A no The number of Chinese medicinal materials that are sorted and discarded in a certain amount of Chinese medicinal materials prepared by sorting at a preset frequency, τ no It is the adjustment coefficient of abnormal rate of Chinese medicinal materials.

[0053] Furthermore, the process of adjusting the preset frequency includes:

[0054]

[0055] The sorting rate F of the sorting module is obtained by calculation and analysis through formula (5): s ;

[0056] Among them, D f is the number of Chinese medicinal materials sorted by the sorting module within a preset positive integer multiple sorting cycle, D all The number of Chinese medicinal materials determined by the analysis and control module according to the similarity coefficient of Chinese medicinal materials characteristics within a preset positive integer multiple sorting cycle, and the sorting cycle is the number of Chinese medicinal materials detected in the process of generating adjacent sorting preparation signals at a preset frequency;

[0057] The sorting rate F of the sorting module s With the preset sorting rate F std Make a comparison;

[0058] If Fs ≥F std , then P s =P std *(1+F s );

[0059] If F s <F std , then P s =P std ;

[0060] Among them, P s is the preset frequency, P std is the basic frequency.

[0061] Beneficial effects of the present invention:

[0062] (1) The present invention uses a trained artificial intelligence model to perform a rapid identification analysis on all Chinese medicinal materials, quickly screens the Chinese medicinal materials according to the similarity coefficients of the Chinese medicinal materials characteristics, and then further fully detects the Chinese medicinal materials with medium similarity coefficients through a near-infrared spectrometer, thereby achieving the purpose of rapid detection of Chinese medicinal materials. Compared with the method of only detecting by a near-infrared spectrometer in the prior art, the detection amount of the near-infrared spectrometer is effectively reduced, the purpose of rapid detection of Chinese medicinal materials is achieved, and the accuracy of the detection of Chinese medicinal materials is also guaranteed.

[0063] (2) The present invention intelligently adjusts the testing standards and sampling frequency in the Chinese medicinal materials testing process according to the feedback of the test results in the Chinese medicinal materials testing process. This intelligent adjustment method can perform adaptive adjustment for Chinese medicinal materials of different qualities, further improving the efficiency of the Chinese medicinal materials testing process and the accuracy of Chinese medicinal materials testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The present invention will be further described below in conjunction with the accompanying drawings.

[0065] Figure 1 It is a schematic block diagram of a rapid detection system for Chinese medicinal materials based on an artificial intelligence model proposed by the present invention;

[0066] Figure 2 It is a flow chart of the steps of the process of obtaining the similarity coefficient of Chinese medicinal material characteristics proposed by the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] See also Figure 1-Figure 2 As shown, in one embodiment, a rapid detection system for Chinese medicinal materials based on an artificial intelligence model is provided, the system comprising:

[0069] A conveying module is used to convey and transport Chinese medicinal materials;

[0070] An image acquisition module, used for acquiring image information of the Chinese medicinal materials on the transmission module;

[0071] An odor collection module is used to collect odor information of the Chinese medicinal materials on the transmission module;

[0072] The sorting module is used to sort, remove and prepare the Chinese medicinal materials on the conveying module, and to sort, remove and return the Chinese medicinal materials on the sorting temporary storage module;

[0073] A sorting and temporary storage module is used to temporarily store the sorted and prepared Chinese medicinal materials to be tested by near-infrared spectrometer and the remaining medicinal materials;

[0074] Near infrared spectrometer, used to perform infrared spectrum analysis on prepared Chinese medicinal materials and generate similarity coefficients of Chinese medicinal materials components;

[0075] The analysis control module generates signals for the sorting module to sort and prepare the Chinese medicinal materials at a preset frequency; processes and analyzes the image information and the odor information to obtain the similarity coefficient of the Chinese medicinal materials characteristics, and generates signals for the sorting module to sort, reject and prepare the Chinese medicinal materials; generates signals for the sorting module to sort, reject and sort and return the Chinese medicinal materials according to the similarity coefficient of the Chinese medicinal materials components.

[0076] Through the above technical scheme, this embodiment provides a rapid detection system for Chinese medicinal materials based on an artificial intelligence model. During the detection process of Chinese medicinal materials by the enterprise, the Chinese medicinal materials are transported through a transmission module. The transmission module can be a conveyor belt. An image acquisition module, an odor acquisition module and a sorting module are installed in sequence on one side of the transmission module. The image acquisition module can be a high-definition camera for taking pictures of the Chinese medicinal materials during the transportation process and collecting image information of the Chinese medicinal materials. The odor acquisition module can be a Chinese medicine odor analyzer for collecting odor information emitted by the Chinese medicinal materials during the transportation process. The sorting module can be a robotic arm and a preparation platform. The preparation platform is mainly used It is used to take a small portion of Chinese medicinal materials and prepare them through processes such as grinding, mixing, and tableting, so as to facilitate the subsequent component detection of the samples through a near-infrared spectrometer. The preparation platform can be an automatic sample processing machine or a manual preparation machine. The robotic arm is used to clamp the Chinese medicinal materials on the conveying module and place them in the unqualified area for removal, or to clamp the Chinese medicinal materials on the conveying module and place them on the preparation platform for preparation, as well as to sort, remove, and sort and return the Chinese medicinal materials on the sorting and temporary placement module. During the detection process, the analysis and control module can process and analyze the image information and odor information based on the artificial intelligence model to obtain the Chinese medicinal materials feature similarity coefficient. The feature similarity coefficient determines the possibility that each Chinese medicinal material is the target Chinese medicinal material. If the feature similarity coefficient of the detected Chinese medicinal material is high, the Chinese medicinal material will not be sorted. If the feature similarity coefficient of the detected Chinese medicinal material is medium, a signal for sorting and preparing the Chinese medicinal material is generated, and the Chinese medicinal material is sorted and prepared through the sorting module. If the feature similarity coefficient of the detected Chinese medicinal material is low, a signal for sorting and rejecting the Chinese medicinal material is generated, and the Chinese medicinal material is sorted and rejected through the sorting module. The sorted and prepared samples and the remaining Chinese medicinal materials are placed on the sorting temporary storage module and arranged in sequence, waiting for the analysis of the near-infrared spectrometer in sequence, and then the prepared Chinese medicinal materials are analyzed by the near-infrared spectrometer. The samples are subjected to infrared spectral analysis to generate a similarity coefficient of Chinese medicinal materials components. Finally, the analysis and control module determines the possibility of each prepared Chinese medicinal material being the target Chinese medicinal material based on the similarity coefficient of Chinese medicinal materials components. If the detected similarity coefficient of Chinese medicinal materials components is high, a signal is generated to sort and return the Chinese medicinal materials. The remaining part of the Chinese medicinal materials placed in the sorting and temporary placement module is clamped and placed back on the transmission module through the sorting module. If the detected similarity coefficient of Chinese medicinal materials components is low, a signal is generated to sort and remove the Chinese medicinal materials. The remaining part of the Chinese medicinal materials placed in the sorting and temporary placement module is clamped and placed in the incompatible area through the sorting module for removal. In this way, the process of rapid detection of Chinese medicinal materials can be completed.

[0077] It should be noted that the training process of the artificial intelligence model for identifying Chinese medicinal materials can be obtained through multi-step training such as data collection, data cleaning, data labeling, and model training. This is a prior art and will not be elaborated here. In order to improve the accuracy of Chinese medicinal materials detection, the analysis and control module will generate a signal for the sorting module to sort and prepare Chinese medicinal materials at a preset frequency, thereby achieving the purpose of random inspection of Chinese medicinal materials that do not need to be sorted on the transmission module. According to the results of the random inspection, the standard for generating the sorting signal can be intelligently adjusted.

[0078] In the process of detecting Chinese medicinal materials through this system, a database for identifying medicinal material properties is established using machine vision and odor collection methods. A preliminary identification analysis is performed on all Chinese medicinal materials through the constructed database. The identification characteristics include but are not limited to the shape of the medicinal materials, odor, sheet diameter size, thickness, color, etc. The Chinese medicinal materials characteristic similarity coefficient is obtained based on the calculation and analysis of the identification characteristics. The Chinese medicinal materials are quickly screened based on the Chinese medicinal materials characteristic similarity coefficient, and then the Chinese medicinal materials with the Chinese medicinal materials characteristic similarity coefficient within a certain threshold are further fully detected by the near-infrared spectrometer, thereby achieving the purpose of rapid detection of Chinese medicinal materials. Compared with the method of only detecting by near-infrared spectrometer in the prior art, the detection amount of near-infrared spectrometer is effectively reduced, the purpose of rapid detection of Chinese medicinal materials is achieved, and the accuracy of detection of Chinese medicinal materials is also guaranteed. The operation process is simple and standardized, and the operator does not need to have a professional background or receive special training. Although the modeling process is time-consuming, once completed, efficient and accurate detection can be achieved.

[0079] In one embodiment, the process of obtaining the similarity coefficient of Chinese medicinal material characteristics includes:

[0080] S1, pre-process the image information by denoising, enhancing, and resizing, and extract the characteristics of the Chinese medicinal materials such as color, texture, and shape;

[0081] S2, filtering and amplifying the odor information to extract the odor characteristics of Chinese medicinal materials;

[0082] S3. Generate a similarity coefficient of Chinese medicinal material characteristics by comparing the color, texture, shape, smell and other characteristics of Chinese medicinal materials with the data in the Chinese medicinal material database.

[0083] In step S3, the process of generating the similarity coefficient of Chinese medicinal material characteristics includes:

[0084]

[0085] The similarity coefficient Q of Chinese medicinal materials characteristics is obtained by calculation and analysis through formula (1)-(2) s ;

[0086] Among them, E i is the similarity evaluation parameter of the i-th feature, Ei,std is the i-th feature standard evaluation parameter, which can be used to preset the feature data of the target Chinese medicinal materials in the artificial intelligence model. When i = 1, E1 is the comprehensive similarity evaluation parameter of the texture feature of the Chinese medicinal materials, and E 1，std is the standard evaluation parameter of the target Chinese medicinal material texture feature, which can be set according to multiple factors such as texture distribution, shape, and type on the target Chinese medicinal material. When i=2, E2 is the similarity evaluation parameter of the color feature of the Chinese medicinal material, which can be obtained according to the recognition and evaluation of the artificial intelligence model. 2,std is the standard evaluation parameter of the target Chinese medicinal material color feature, which can be preset according to multiple factors such as the color distribution, chromaticity and color corresponding wavelength of the Chinese medicinal material. For example, it can be set according to the wavelength corresponding to the color feature. For example, if the target Chinese medicinal material color is red and corresponds to a wavelength of 700 nanometers, the standard evaluation parameter of the target Chinese medicinal material color feature can be set to 700. The similarity evaluation parameter of the Chinese medicinal material color feature is the wavelength value corresponding to the detected color feature minus the wavelength value of 700. When i=3, E3 is the similarity evaluation parameter of the shape feature of the Chinese medicinal material, which can be obtained according to the recognition and evaluation of the artificial intelligence model. E 3,std is the standard evaluation parameter for the target Chinese medicinal material shape feature, which can be set based on multiple factors such as the similarity of the contour of the Chinese medicinal material, the similarity of the contour of the part, and the similarity of the shape of the same part. When i=4, E4 is the similarity evaluation parameter for the smell feature of the Chinese medicinal material, which can be obtained based on the recognition and evaluation of the artificial intelligence model. 4,std is the standard evaluation parameter for the odor characteristics of the target Chinese medicinal materials, which can be set according to multiple factors such as the volatile oil, odor, taste, and concentration of the target Chinese medicinal materials. When i=5, E5 is the similarity evaluation parameter for other characteristics of Chinese medicinal materials, which can be obtained according to the recognition and evaluation of the artificial intelligence model. 5,std Other characteristic standard evaluation parameters of the target Chinese medicinal materials can be set according to the cross-sectional characteristics, gloss, special marks and other characteristics of the target Chinese medicinal materials. i is the influence coefficient of the i-th feature on the detection of Chinese medicinal materials, which is obtained according to experience. R1 is the number of textures on the Chinese medicinal materials whose texture similarity reaches the first preset coefficient, and R2 is the number of textures on the Chinese medicinal materials whose texture similarity does not reach the second preset coefficient. The first preset coefficient and the second preset coefficient are both obtained according to experience. For example, the first preset coefficient can be set to 80% similarity, and the second preset coefficient can be preset to 20% similarity. The texture similarity can be obtained through artificial intelligence model recognition and evaluation. is the weight coefficient corresponding to different numbers of textures, which is preset based on experience.

[0087] The process of generating a signal for the sorting module to sort, reject and prepare the Chinese medicinal materials includes:

[0088] The similarity coefficient of Chinese medicinal materials characteristics Q sCompare with the preset Chinese medicinal material characteristic threshold range [Q1, Q2], wherein the preset Chinese medicinal material characteristic threshold range [Q1, Q2] can be preliminarily preset based on experience;

[0089] If Q s >Q2, indicating that the corresponding Chinese medicinal materials are qualified Chinese medicinal materials, no sorting signal is generated, the analysis and control module generates a signal for the sorting module to sort and prepare the Chinese medicinal materials at a preset frequency, and controls the sorting module to perform random inspections on qualified Chinese medicinal materials at a preset frequency;

[0090] If Q s ∈[Q1, Q2], indicating that the corresponding Chinese medicinal materials are Chinese medicinal materials that need further testing, and the analysis and control module marks the tested Chinese medicinal materials and generates corresponding sorting and preparation signals;

[0091] If Q s <Q1, indicating that the corresponding Chinese medicinal materials are unqualified Chinese medicinal materials. The analysis and control module marks the detected Chinese medicinal materials and generates corresponding sorting and rejection signals.

[0092] The process of generating the similarity coefficient of Chinese medicinal material components includes:

[0093] The spectrum of the prepared Chinese medicinal materials is collected by a near-infrared spectrometer to obtain the spectrum data of the corresponding Chinese medicinal materials;

[0094] Preprocess the spectral data and input it into the constructed artificial intelligence big data model to compare it with the chemical component content in the preset Chinese herbal medicine samples;

[0095] The similarity coefficient of the Chinese medicinal material components of the corresponding Chinese medicinal materials is calculated based on the comparison results. The similarity coefficient of the Chinese medicinal material components can be calculated by a variety of methods, such as Euclidean distance, cosine similarity, Pearson correlation coefficient, etc. According to the generated similarity coefficient of the Chinese medicinal material components, the similarity of the components between the tested Chinese medicinal materials and the Chinese medicinal material samples is analyzed. The higher the similarity coefficient, the more similar the components between the tested Chinese medicinal materials and the Chinese medicinal material samples are; the lower the similarity coefficient, the greater the difference in components between the tested Chinese medicinal materials and the Chinese medicinal material samples.

[0096] The process of generating a signal for the sorting module to sort, reject and return the Chinese medicinal materials includes:

[0097] Compare the similarity coefficient of Chinese medicinal material ingredients with the preset similarity coefficient of Chinese medicinal material ingredient standards, where the similarity coefficient of Chinese medicinal material ingredient standards can be preset according to the Chinese medicinal material demand standards of the enterprise;

[0098] If the similarity coefficient of the Chinese medicinal material components is greater than or equal to the preset similarity coefficient of the Chinese medicinal material components standard, it means that the corresponding Chinese medicinal material is a qualified Chinese medicinal material, and the analysis and control module marks the remaining Chinese medicinal materials after sorting and preparation and generates a corresponding sorting return signal;

[0099] If the similarity coefficient of the Chinese medicinal material ingredients is less than the preset standard similarity coefficient of the Chinese medicinal material ingredients, it means that the corresponding Chinese medicinal material is unqualified. The analysis and control module marks the remaining Chinese medicinal materials after sorting and preparation and generates corresponding sorting and rejection signals.

[0100] Through the above technical scheme, this embodiment provides a method for fully detecting and identifying Chinese medicinal materials based on an artificial intelligence model. First, the characteristics of Chinese medicinal materials are identified and analyzed by the artificial intelligence model to obtain the characteristic similarity coefficient of the Chinese medicinal materials. According to the characteristic similarity coefficient of the Chinese medicinal materials, the Chinese medicinal materials are classified into three types: sorting and rejection, sorting and preparation, and non-sorting. The sorted and rejected ones are judged as unqualified Chinese medicinal materials, and the non-sorted ones are judged as qualified Chinese medicinal materials. The sorted and prepared Chinese medicinal materials are then analyzed for their components by a near-infrared spectrometer to generate corresponding Chinese medicinal material component similarity coefficients. According to the Chinese medicinal material component similarity coefficients, the sorted and prepared Chinese medicinal materials are further sorted and sorted and rejected. The sorted and rejected ones are judged as unqualified Chinese medicinal materials, and the sorted and returned ones are judged as qualified Chinese medicinal materials. In this way, the artificial intelligence model and the near-infrared spectrometer can cooperate with each other to quickly and fully detect the Chinese medicinal materials, which not only provides the detection speed of Chinese medicinal materials, but also ensures the accuracy of the Chinese medicinal materials detection process.

[0101] The application of this Chinese herbal medicine detection system can effectively reduce personnel costs, reducing the original process of Chinese herbal medicine detection that requires at least 5 to 10 people to be involved to only one person, reducing labor costs by more than 80%; the detection cycle is greatly shortened, shortening the traditional detection cycle from dozens of hours to several days to minutes, and the detection efficiency is improved by more than 99.9%; the sample size covers a comprehensive range, and can effectively detect more than 1,000 common Chinese herbal medicines, covering various types such as rhizomes and fruits; the model has high adaptability, and the accuracy of the established big data model in the detection of Chinese herbal medicines from different origins and batches remains above 90%, which is actually In application, it can effectively help enterprises improve their product quality control capabilities and production efficiency. At the same time, the test results are not affected by human factors and have high repeatability, providing efficient, accurate and stable new methods and new approaches for the detection of Chinese medicinal materials industry. The present invention is expected to produce many benefits in the field of Chinese medicine preparation piece detection. Economically, it can significantly reduce the cost of detection and improve corporate benefits. Socially, it can alleviate the shortage of skilled inspectors, improve the quality of Chinese medicine preparation pieces, ensure the safety of public drug use, and enhance the reputation of the industry. Ecologically, efficient detection can promote the standardized development of the Chinese medicine industry, rationally utilize Chinese medicinal materials resources, reduce waste, and promote the modernization of the Chinese medicine industry.

[0102] Furthermore, the system further comprises:

[0103] The statistical adjustment module performs statistical analysis on the result data of Chinese medicinal materials detected by the near-infrared spectrometer and adjusts the preset threshold range of Chinese medicinal materials characteristics; the sorting module performs statistical analysis on the data of sorting, rejection, sorting preparation and unsorted Chinese medicinal materials on the transmission module and adjusts the preset frequency.

[0104] The process of adjusting the preset threshold range of Chinese medicinal material characteristics includes:

[0105] After the near-infrared spectrometer has recently detected a preset number of Chinese medicinal materials, the preset number can be obtained by preset according to experience, and the number of generated signals is statistically analyzed;

[0106]

[0107] The defect rate Z1 of the preset number of Chinese medicinal materials is obtained by calculation and analysis through formula (3);

[0108] The preset number of Chinese medicinal materials defect rate Z1 and the preset defect rate threshold range [Z a , Z b ] for comparison, the preset defect rate threshold range [Z a , Z b ]According to experience preset;

[0109] If Z1>Z b , indicating that the defective rate of Chinese medicinal materials detected by the near-infrared spectrometer is too high. The detection volume detected by the near-infrared spectrometer is large, which affects the detection efficiency. It is necessary to improve the minimum threshold of unqualified Chinese medicinal materials determined by the similarity coefficient of Chinese medicinal materials characteristics in the analysis and control module. Then, the left endpoint Q1 of the threshold range [Q1, Q2] is updated to Q 1，re , Q 1，re =Q1+ΔQ;

[0110] If Z1<Z a , indicating that the defective rate of Chinese medicinal materials detected by the near-infrared spectrometer is low. The Chinese medicinal materials that are judged as unqualified according to the similarity coefficient of Chinese medicinal materials characteristics in the analysis and control module may contain some qualified Chinese medicinal materials. It is necessary to lower the minimum threshold of unqualified Chinese medicinal materials judged in the analysis and control module. Then, the left endpoint Q1 of the threshold range [Q1, Q2] is updated to Q 1，re , Q 1，re =Q1-ΔQ;

[0111] Among them, Q 1，re is the lowest threshold of the updated preset threshold range of Chinese medicinal materials characteristics, ΔQ is the adjustment coefficient of the threshold range of Chinese medicinal materials characteristics, which is obtained based on experience, ΔQ<<Q2-Q1, A risk is the number of sorting and rejecting signals generated by the near-infrared spectrometer, which can be obtained by counting the number of sorting and rejecting signals generated by the near-infrared spectrometer. allis the total number of signals generated by the near-infrared spectrometer, obtained by counting the number of signals generated by the near-infrared spectrometer;

[0112] Conduct statistical analysis on the number of signals generated by the near-infrared spectrometer after the near-infrared spectrometer has recently detected a preset number of Chinese medicinal materials and the number of corresponding sorting and rejection signals generated after a certain number of Chinese medicinal materials are sorted and prepared at a preset frequency;

[0113]

[0114] The abnormal rate Z2 of the preset number of Chinese medicinal materials is obtained through timely analysis through formula (4);

[0115] The abnormal rate Z2 of the preset number of Chinese medicinal materials is compared with the preset abnormal rate threshold range [Z c , Z d ] for comparison, the preset abnormality rate threshold range [Z c , Z d ]According to experience preset;

[0116] If Z2>Z d , indicating that the defective rate of Chinese medicinal materials detected by the near-infrared spectrometer is too high or the probability of unqualified Chinese medicinal materials in the sampled Chinese medicinal materials is too high. The qualified Chinese medicinal materials determined by the similarity coefficient of Chinese medicinal materials characteristics in the analysis and control module may contain some unqualified Chinese medicinal materials. It is necessary to increase the highest threshold of qualified Chinese medicinal materials determined by the similarity coefficient of Chinese medicinal materials characteristics in the analysis and control module. Then, the right endpoint Q2 of the threshold range [Q1, Q2] is updated to Q 2.re , Q 2，re =Q2+ΔQ;

[0117] If Z2<Z c , indicating that the defective rate of Chinese medicinal materials detected by the near-infrared spectrometer is low or the probability of unqualified Chinese medicinal materials in the sampled Chinese medicinal materials is low. The analysis and control module determines that there are more qualified Chinese medicinal materials for further testing based on the similarity coefficient of Chinese medicinal materials characteristics, and the qualified rate of Chinese medicinal materials determined by the similarity coefficient of Chinese medicinal materials characteristics meets the standard. The detection amount detected by the near-infrared spectrometer is large, which affects the detection efficiency. It is necessary to reduce the highest threshold of qualified Chinese medicinal materials determined by the similarity coefficient of Chinese medicinal materials characteristics in the analysis and control module, then update the right endpoint Q2 of the threshold range [Q1, Q2] to Q 2，re , Q 2，re =Q2-ΔQ;

[0118] Among them, Q 2，re is the highest threshold of the updated preset TCM characteristic threshold range, A noThe number of Chinese medicinal materials that are sorted and rejected in a certain number of Chinese medicinal materials prepared by sorting at a preset frequency is obtained by statistically analyzing the number of Chinese medicinal materials rejected in the sampled Chinese medicinal materials analyzed by a near-infrared spectrometer. The certain number of Chinese medicinal materials is a preset number of Chinese medicinal materials sampled recently, which is preset based on experience. For example, the certain number is preset to 100, A no That is, the number of unqualified Chinese medicinal materials detected in the recent 100 sampled Chinese medicinal materials tested by near-infrared spectrometer, τ no It is the adjustment coefficient of abnormal rate of Chinese medicinal materials, which is preset based on experience.

[0119] The process of adjusting the preset frequency includes:

[0120]

[0121] The sorting rate F of the sorting module is obtained by calculation and analysis through formula (5): s ;

[0122] Among them, D f is the number of Chinese medicinal materials sorted by the sorting module within a preset positive integer multiple of the sorting cycle, the number of sorted Chinese medicinal materials includes the number of Chinese medicinal materials that are sorted and rejected and prepared, which can be obtained by statistically analyzing the sorting signals generated by the analysis and control module according to the similarity coefficient of Chinese medicinal materials characteristics through the statistical adjustment module, D all D is the number of Chinese medicinal materials determined by the analysis and control module according to the similarity coefficient of Chinese medicinal materials characteristics within a sorting cycle that is a preset positive integer multiple. The sorting cycle is the number of Chinese medicinal materials detected in the process of generating adjacent sorting preparation signals at a preset frequency. The preset positive integer is obtained based on experience. For example, if the preset positive integer is 1, the preset frequency is 100 Chinese medicinal materials and one Chinese medicinal material is sampled for preparation. These 100 Chinese medicinal materials are qualified Chinese medicinal materials determined by the analysis and control module according to the similarity coefficient of Chinese medicinal materials characteristics. In the process of the analysis and control module determining the 100 Chinese medicinal materials, 10 unqualified Chinese medicinal materials and 20 Chinese medicinal materials that need further detection may be determined. Therefore, at this time, D f The value of D is 30. all The value of 130, D f and D all All of them can be obtained through statistics of the statistical adjustment module;

[0123] The sorting rate F of the sorting module s With the preset sorting rate F std Compare, the preset sorting rate F std It can be obtained based on experience.

[0124] If F s ≥F std , then P s =P std *(1+F s);

[0125] If F s <F std , then P s =P std ;

[0126] Among them, P s is the preset frequency, P std is the basic frequency, which can be preset based on experience.

[0127] Through the above technical scheme, this embodiment provides a method for intelligently adjusting the preset Chinese medicinal material characteristic threshold range and the preset frequency. Through the above analysis and adjustment process, the detection standard and sampling frequency in the Chinese medicine detection process can be intelligently adjusted according to the feedback of the detection results in the Chinese medicinal material detection process. This intelligent adjustment method can perform adaptive adjustment for Chinese medicinal materials of different qualities, further improving the efficiency of the Chinese medicinal material detection process and the accuracy of Chinese medicinal material detection.

[0128] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A rapid detection system for Chinese herbal medicine based on an artificial intelligence model, characterized in that: The system comprises: A conveying module, used for conveying and transporting Chinese medicinal materials; An image acquisition module, used for acquiring image information of the Chinese medicinal materials on the transmission module; An odor collection module is used to collect odor information of the Chinese medicinal materials on the transmission module; The sorting module is used to sort, remove and prepare the Chinese medicinal materials on the conveying module, and to sort, remove and return the Chinese medicinal materials on the sorting temporary storage module; A sorting and temporary storage module is used to temporarily store the sorted and prepared Chinese medicinal materials to be tested by near-infrared spectrometer and the remaining medicinal materials; Near infrared spectrometer, used to perform infrared spectrum analysis on prepared Chinese medicinal materials and generate similarity coefficients of Chinese medicinal materials components; The analysis control module generates signals for the sorting module to sort and prepare the Chinese medicinal materials at a preset frequency; processes and analyzes the image information and the odor information to obtain the similarity coefficient of the Chinese medicinal materials characteristics, and generates signals for the sorting module to sort, reject and prepare the Chinese medicinal materials; generates signals for the sorting module to sort, reject and sort and return the Chinese medicinal materials according to the similarity coefficient of the Chinese medicinal materials components.

2. According to claim 1, a rapid detection system for Chinese medicinal materials based on an artificial intelligence model is characterized in that: The process of obtaining the similarity coefficient of Chinese medicinal material characteristics includes: S1, pre-process the image information by denoising, enhancing, and resizing, and extract the color, texture, and shape features of Chinese medicinal materials; S2, filtering and amplifying the odor information to extract the odor characteristics of Chinese medicinal materials; S3. Generate a similarity coefficient of Chinese medicinal material characteristics by comparing the color, texture, shape and gas characteristics of Chinese medicinal materials with the data in the Chinese medicinal material database.

3. A rapid detection system for Chinese medicinal materials based on an artificial intelligence model according to claim 2, characterized in that: In step S3, the process of generating the similarity coefficient of Chinese medicinal material characteristics includes: The similarity coefficient Q of Chinese medicinal materials characteristics is obtained by calculation and analysis through formula (1)-(2) s ; Among them, E i is the similarity evaluation parameter of the i-th feature, E i,std is the i-th feature standard evaluation parameter. When i=1, E1 is the comprehensive similarity evaluation parameter of the texture feature of Chinese medicinal materials. When i=2, E2 is the similarity evaluation parameter of the color feature of Chinese medicinal materials. When i=3, E3 is the similarity evaluation parameter of the shape feature of Chinese medicinal materials. When i=4, E4 is the similarity evaluation parameter of the smell feature of Chinese medicinal materials. When i=5, E5 is the similarity evaluation parameter of other features of Chinese medicinal materials. ω i is the influence coefficient of the i-th feature on the detection of Chinese medicinal materials, R1 is the number of textures on the Chinese medicinal materials whose texture similarity reaches the first preset coefficient, R2 is the number of textures on the Chinese medicinal materials whose texture similarity does not reach the second preset coefficient, is the weight coefficient corresponding to different texture numbers.

4. A rapid detection system for Chinese medicinal materials based on an artificial intelligence model according to claim 3, characterized in that: The process of generating a signal for the sorting module to sort, reject and prepare the Chinese medicinal materials includes: The similarity coefficient of Chinese medicinal materials characteristics Q s Compare with the preset threshold range of Chinese medicinal material characteristics [Q1, Q2]; If Q s >Q2, no sorting signal is generated, and the analysis and control module generates a signal for the sorting module to sort and prepare the Chinese medicinal materials at a preset frequency; If Q s ∈[Q1,Q2], the analysis and control module marks the detected Chinese medicinal materials and generates corresponding sorting and preparation signals; If Q s <Q1, the analysis and control module marks the detected Chinese medicinal materials and generates corresponding sorting and rejection signals.

5. A rapid detection system for Chinese medicinal materials based on an artificial intelligence model according to claim 4, characterized in that: The process of generating the similarity coefficient of Chinese medicinal material components includes: The spectrum of the prepared Chinese medicinal materials is collected by a near-infrared spectrometer to obtain the spectrum data of the corresponding Chinese medicinal materials; Preprocess the spectral data and input it into the constructed artificial intelligence big data model to compare it with the chemical component content in the preset Chinese herbal medicine samples; The similarity coefficient of the Chinese medicinal materials components of the corresponding Chinese medicinal materials is calculated based on the comparison results.

6. The rapid detection system for Chinese medicinal materials based on artificial intelligence model according to claim 5 is characterized in that: The process of generating a signal for the sorting module to sort and reject the Chinese medicinal materials and sort and return them to their original positions includes: Compare the similarity coefficient of Chinese medicinal materials ingredients with the preset standard similarity coefficient of Chinese medicinal materials ingredients; If the similarity coefficient of the Chinese medicinal material components is greater than or equal to the preset similarity coefficient of the Chinese medicinal material components standard, the analysis and control module marks the remaining Chinese medicinal materials after sorting and preparation and generates a corresponding sorting homing signal; If the similarity coefficient of the Chinese medicinal material ingredients is less than the preset standard similarity coefficient of the Chinese medicinal material ingredients, the analysis and control module marks the remaining Chinese medicinal materials after sorting and preparation and generates a corresponding sorting and rejection signal.

7. The rapid detection system for Chinese medicinal materials based on artificial intelligence model according to claim 6 is characterized in that: The system further comprises: The statistical adjustment module performs statistical analysis on the result data of Chinese medicinal materials detected by the near-infrared spectrometer and adjusts the preset threshold range of Chinese medicinal materials characteristics; the sorting module performs statistical analysis on the data of sorting, rejection, sorting preparation and unsorted Chinese medicinal materials on the transmission module and adjusts the preset frequency.

8. The rapid detection system for Chinese medicinal materials based on artificial intelligence model according to claim 7 is characterized in that: The process of adjusting the preset threshold range of Chinese medicinal material characteristics includes: Conduct statistical analysis on the number of signals generated by the near infrared spectrometer after testing a preset number of Chinese medicinal materials in the near future; The defect rate Z1 of the preset number of Chinese medicinal materials is obtained by calculation and analysis through formula (3); The preset number of Chinese medicinal materials defect rate Z1 and the preset defect rate threshold range [Z a ,Z b ] for comparison; If Z1>Z b , then update the left endpoint Q1 of the threshold range [Q1,Q2] to Q 1,re , Q 1,re =Q1+ΔQ; If Z1 <Z a , then update the left endpoint Q1 of the threshold range [Q1,Q2] to Q 1,re , Q 1,re =Q1-ΔQ; Among them, Q 1,re is the lowest threshold of the updated preset threshold range of Chinese herbal medicine characteristics, ΔQ is the adjustment coefficient of the threshold range of Chinese herbal medicine characteristics, and A risk The number of sorting rejection signals generated for the NIR spectrometer, A all The total number of signals generated for the near infrared spectrometer; Conduct statistical analysis on the number of signals generated by the near infrared spectrometer after the near infrared spectrometer has recently detected a preset number of Chinese medicinal materials and the corresponding number of signals generated after a certain number of Chinese medicinal materials have been sorted and prepared at a preset frequency; The abnormal rate Z2 of the preset number of Chinese medicinal materials is obtained through timely analysis through formula (4); The abnormal rate Z2 of the preset number of Chinese medicinal materials is compared with the preset abnormal rate threshold range [Z c ,Z d ] for comparison; If Z2>Z d , then update the right endpoint Q2 of the threshold range [Q1,Q2] to Q 2,re , Q 2,re =Q2+ΔQ; If Z2 <Z c , then update the right endpoint Q2 of the threshold range [Q1,Q2] to Q 2,re , Q 2,re =Q2-ΔQ; Among them, Q 2,re is the highest threshold of the updated preset TCM characteristic threshold range, A no The number of Chinese medicinal materials that are sorted and discarded in a certain amount of Chinese medicinal materials prepared by sorting at a preset frequency, τ no It is the adjustment coefficient of abnormal rate of Chinese medicinal materials.

9. The rapid detection system for Chinese medicinal materials based on artificial intelligence model according to claim 8, characterized in that: The process of adjusting the preset frequency includes: The sorting rate F of the sorting module is obtained by calculation and analysis through formula (5): s ; Among them, D f is the number of Chinese medicinal materials sorted by the sorting module within a preset positive integer multiple sorting cycle, D all The number of Chinese medicinal materials determined by the analysis and control module according to the similarity coefficient of Chinese medicinal materials characteristics within a preset positive integer multiple sorting cycle, and the sorting cycle is the number of Chinese medicinal materials detected in the process of generating adjacent sorting preparation signals at a preset frequency; The sorting rate F of the sorting module s With the preset sorting rate F std Make a comparison; If F s ≥F std , then P s =P std *(1+F s ); If F s <F std , then P s =P std ; Among them, P s is the preset frequency, P std is the basic frequency.

Images