Medical supply chain data mining method and system based on artificial intelligence
Through artificial intelligence-based methods, preprocessing, classifying and matching the data of medical supply chains, the problem of low efficiency and quality of medical supply chain data mining in the existing technology is solved, and efficient and accurate data mining effects are achieved.
Patent Information
- Application Number
- CN202510145738.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-10
- Publication Date
- 2025-05-13
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing medical supply chain data mining methods are not efficient and of high quality, and the data availability is insufficient, so improvement is urgently needed.
Using an artificial intelligence-based method, the data is preprocessed, vectorized, classified identification and similarity matching are performed by acquiring and analyzing the initial capture information packets uploaded by the data acquisition end, and the data is preprocessed, vectorized, classified identification and similarity matching are performed, and the data classification number is determined, and the data is entered into the data file.
Accurate medical supply chain data mining in the digital medical supply chain is realized, improving the efficiency and quality of data mining, and ensuring the availability and ease of use of data.
Smart Images
Figure CN119989099A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of data mining, and in particular relates to a medical supply chain data mining method and system based on artificial intelligence. Background Art
[0002] Digital medical supply chain refers to the use of digital technology and information technology to manage the logistics, procurement, inventory, distribution and other information of the medical industry, so as to achieve an efficient, fast, safe and traceable supply chain management model for medical products and services. With the development of medical informatization, medical supply chain data mining has become an important means to improve the quality and efficiency of medical product services. Medical supply chain data mining refers to the process of searching for useful information hidden in a large amount of data in the medical supply chain through algorithms. Medical supply chain data mining has the benefits of improving the accuracy of medical product supply decision-making, optimizing medical product inventory management, and reducing management costs. However, the existing medical supply chain data mining methods generally have problems such as low efficiency and quality of data mining, and low availability of mined medical supply chain data, which urgently need to be improved. Summary of the invention
[0003] The purpose of the present invention is to provide a medical supply chain data mining method and system based on artificial intelligence to solve the above-mentioned problems existing in the prior art.
[0004] In order to achieve the above object, the present invention adopts the following technical solutions:
[0005] In a first aspect, a medical supply chain data mining method based on artificial intelligence is provided, comprising:
[0006] Obtain the initialization capture information package uploaded by each data acquisition terminal, and parse the initialization capture information package to obtain the corresponding initialization capture information;
[0007] Perform data preprocessing on the initialization crawling information to obtain the corresponding node crawling data, and perform data conversion processing on the node crawling data to obtain the corresponding structured crawling data;
[0008] Vectorize the structured crawled data to obtain the corresponding data feature vector;
[0009] Input the data feature vector into a preset data classification and recognition model for classification and recognition, and obtain the corresponding data classification and recognition result;
[0010] When the node captured data is determined to be medical supply chain data according to the data classification and recognition result, the corresponding data feature vector is matched with each template vector pre-stored in the template library for similarity to obtain a similarity matching result;
[0011] Determine the medical supply chain data classification number of the node captured data based on the similarity matching result, and annotate the node captured data with the corresponding medical supply chain data classification number and enter it into the medical digital supply chain mining data file;
[0012] Output the entered medical digital supply chain mining data file.
[0013] In a possible design, when the initialization crawling information includes text data, the initialization crawling information is preprocessed to obtain corresponding node crawling data, and the node crawling data is converted to obtain corresponding structured crawling data, including:
[0014] Perform data cleaning on text data to obtain corresponding node crawling data;
[0015] The node captured data is processed by slicing to obtain a number of node captured data blocks, and the base conversion process is performed on each node captured data block to obtain the corresponding block conversion data;
[0016] The converted data of each block are associated and combined according to the fragmentation order of the corresponding node captured data block to obtain structured captured data.
[0017] In a possible design, when the initialization crawling information includes image data, the initialization crawling information is preprocessed to obtain corresponding node crawling data, and the node crawling data is converted to obtain corresponding structured crawling data, including:
[0018] Perform image enhancement and image encoding processing on the image data to obtain the corresponding node capture data;
[0019] The node captured data is processed by slicing to obtain a number of node captured data blocks, and the base conversion process is performed on each node captured data block to obtain the corresponding block conversion data;
[0020] The converted data of each block are associated and combined according to the fragmentation order of the corresponding node captured data block to obtain structured captured data.
[0021] In a possible design, when the initialization crawling information includes audio data, the initialization crawling information is preprocessed to obtain corresponding node crawling data, and the node crawling data is converted to obtain corresponding structured crawling data, including:
[0022] Perform speech recognition on the audio data to obtain the recognized text data, and then perform data cleaning on the text data to obtain the corresponding node crawling data;
[0023] The node captured data is processed by slicing to obtain a number of node captured data blocks, and the base conversion process is performed on each node captured data block to obtain the corresponding block conversion data;
[0024] The converted data of each block are associated and combined according to the fragmentation order of the corresponding node captured data block to obtain structured captured data.
[0025] In a possible design, the structured crawled data is vectorized to obtain a corresponding data feature vector, including:
[0026] Perform one-hot encoding on the structured crawled data to obtain the corresponding data feature vector.
[0027] In a possible design, before inputting the data feature vector into a preset data classification and recognition model for classification and recognition, the method further includes:
[0028] An initialized convolutional neural network model is constructed, and classification training is performed on the convolutional neural network model using a preset training set to obtain a corresponding data classification recognition model, wherein the training set includes a number of data feature vector samples marked with corresponding data classification labels.
[0029] In a possible design, the similarity matching of the corresponding data feature vector with each template vector pre-stored in the template library to obtain a similarity matching result includes:
[0030] Substitute the data feature vector and each template vector pre-stored in the template library into the preset similarity operator for calculation to obtain the similarity parameters between the data feature vector and each template vector. The similarity operator is
[0031]
[0032] Among them, S represents the similarity parameter, x represents the data feature vector, y represents the template vector, ||·|| 2 Characterizes the vector bi-norm operation, and δ is the set similarity calculation coefficient.
[0033] In a possible design, determining the medical supply chain data classification number of the node captured data according to the similarity matching result includes:
[0034] According to the similarity parameters between the data feature vector and each template vector, several template vectors with the highest similarity parameters with the data feature vector are selected, and they are sorted and combined in descending order according to the corresponding similarity parameters to obtain a template vector sequence;
[0035] Assigning points to each template vector according to the order of each template vector in the template vector sequence, and determining the medical supply chain data classification number associated with each template vector in the template vector sequence;
[0036] Add the scores corresponding to the template vectors associated with the same medical supply chain data classification number in the template vector sequence to obtain the total classification score of the corresponding medical supply chain data classification number;
[0037] The medical supply chain data classification number with the highest total classification score is used as the medical supply chain data classification number for node crawling data.
[0038] In a second aspect, a medical supply chain data mining system based on artificial intelligence is provided, comprising an information collection unit, a data processing unit, a feature extraction unit, a data classification unit, a feature matching unit, a data entry unit and a mining output unit, wherein:
[0039] The information collection unit is used to obtain the initialization capture information package uploaded by each data collection terminal, and parse the initialization capture information package to obtain the corresponding initialization capture information;
[0040] A data processing unit is used to perform data preprocessing on the initialization crawling information to obtain corresponding node crawling data, and perform data conversion processing on the node crawling data to obtain corresponding structured crawling data;
[0041] A feature extraction unit is used to vectorize the structured captured data to obtain the corresponding data feature vector;
[0042] A data classification unit, used to input the data feature vector into a preset data classification and recognition model for classification and recognition, and obtain a corresponding data classification and recognition result;
[0043] A feature matching unit is used to perform similarity matching between the corresponding data feature vector and each template vector pre-stored in the template library when the node captured data is determined to be medical supply chain data according to the data classification recognition result, so as to obtain a similarity matching result;
[0044] A data entry unit, used to determine the medical supply chain data classification number of the node captured data according to the similarity matching result, and to mark the node captured data with the corresponding medical supply chain data classification number and then enter it into the medical digital supply chain mining data file;
[0045] The mining output unit is used to output the entered medical digital supply chain mining data file.
[0046] In a third aspect, a medical supply chain data mining system based on artificial intelligence is provided, including:
[0047] A memory for storing instructions;
[0048] A processor is used to read the instructions stored in the memory and execute any one of the methods described in the first aspect according to the instructions.
[0049] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored on the computer-readable storage medium, and when the instructions are executed on a computer, the computer executes any one of the methods described in the first aspect. In addition, a computer program product is provided, and when the computer program product is executed on a computer, the computer executes any one of the methods described in the first aspect.
[0050] Beneficial effects: The present invention obtains the information packets captured by the data acquisition end at the corresponding medical supply chain node for parsing and data processing to obtain the node captured data, then extracts features from the node captured data, uses data feature vectors to identify data types to determine that the node captured data is medical supply chain data, and then uses data feature vectors for classification and matching to determine the medical supply chain data classification number of the node captured data, and finally records the node captured data according to the classification number, and outputs the mined data file to realize intelligent medical supply chain data mining. The present invention can realize accurate medical supply chain data mining in the digital medical supply chain, can effectively improve the mining efficiency and quality of medical supply chain data, ensure the availability of mined medical supply chain data, and improve the usability of mined medical supply chain data. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0052] Figure 1 This is a schematic diagram of the steps of the method in Example 1 of the present invention;
[0053] Figure 2 This is a schematic diagram of the structure of the system in Example 2 of the present invention;
[0054] Figure 3 Schematic diagram of the system structure in Example 3 of the present invention. DETAILED DESCRIPTION
[0055] It should be noted that the description of these embodiments is intended to help understand the present invention, but does not constitute a limitation of the present invention. The specific structures and functional details disclosed herein are only intended to describe exemplary embodiments of the present invention. However, the present invention can be embodied in a number of alternative forms, and should not be construed as being limited to the embodiments set forth herein.
[0056] It should be understood that unless otherwise clearly specified and limited, the corresponding terms should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be an electrical connection, a direct connection, an indirect connection through an intermediate medium, or the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments can be understood according to specific circumstances.
[0057] In the following description, certain details are provided to facilitate a complete understanding of the example embodiments. However, it will be appreciated by those of ordinary skill in the art that the example embodiments may be implemented without these certain details. For example, devices may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other embodiments, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the embodiments.
[0058] Embodiment 1:
[0059] This embodiment provides a medical supply chain data mining method based on artificial intelligence, which can be applied to corresponding data analysis terminals, such as Figure 1 As shown, the method comprises the following steps:
[0060] S1. Obtain the initialization capture information package uploaded by each data acquisition terminal, and parse the initialization capture information package to obtain the corresponding initialization capture information.
[0061] In specific implementation, a data collection terminal can be set up in advance at the corresponding node of the digital medical supply chain, and the online interactive information of the corresponding node can be collected through the data collection terminal, and then the collected initialization capture information is packaged into an initialization capture information package, and then the initialization capture information package is uploaded to the data analysis terminal through the corresponding data transmission channel, such as a separate encrypted transmission channel. The data analysis terminal then parses and processes the initialization capture information package uploaded by each data collection terminal to obtain the corresponding initialization capture information.
[0062] S2. Perform data preprocessing on the initialization crawling information to obtain corresponding node crawling data, and perform data conversion processing on the node crawling data to obtain corresponding structured crawling data.
[0063] In specific implementation, if the initialization crawling information includes text data, the data analysis terminal can perform data cleaning on the text data, including checking the consistency of the text data, deleting invalid values, filling missing values, etc., to obtain corresponding node crawling data; then the node crawling data is fragmented, that is, the node crawling data is split to obtain several node crawling data blocks, and each node crawling data block is subjected to base conversion processing to obtain corresponding block conversion data; then each block conversion data is associated and combined according to the fragmentation order of the corresponding node crawling data block to obtain structured crawling data.
[0064] If the initialization capture information includes image data, the data analysis terminal can perform image enhancement and image encoding processing on the image data to obtain corresponding node capture data; then, the node capture data is fragmented to obtain a number of node capture data blocks, and each node capture data block is subjected to base conversion processing to obtain corresponding block conversion data; each block conversion data is then associated and combined according to the fragmentation order of the corresponding node capture data block to obtain structured capture data.
[0065] If the initialization capture information includes audio data, the data analysis terminal can perform speech recognition on the audio data, that is, audio-to-text processing, to obtain recognized text data, and perform data cleaning on the text data to obtain corresponding node capture data; then the node capture data is segmented to obtain a number of node capture data blocks, and each node capture data block is subjected to base conversion processing to obtain corresponding block conversion data; each block conversion data is then associated and combined according to the segmentation order of the corresponding node capture data block to obtain structured capture data
[0066] S3. Perform vectorization processing on the structured crawled data to obtain the corresponding data feature vector.
[0067] During specific implementation, the data analysis terminal can perform one-hot encoding on the structured captured data to obtain the corresponding data feature vector, or, according to actual needs, other vectorization processing methods can be used to vectorize the structured captured data, such as vectorizing the structured captured data through an autoencoder.
[0068] S4. Input the data feature vector into a preset data classification and recognition model for classification and recognition to obtain the corresponding data classification and recognition result.
[0069] In specific implementation, the data analysis terminal can pre-build an initialized convolutional neural network model, and use a preset training set to classify and train the convolutional neural network model to obtain a corresponding data classification and recognition model, wherein the training set contains a number of data feature vector samples marked with corresponding data classification labels. Then, the data feature vector can be input into the data classification and recognition model for classification and recognition to obtain the corresponding data classification and recognition result, which is the classification identifier corresponding to the node captured data. If the classification identifier corresponding to the node captured data is a medical supply chain data identifier, the node captured data is determined to be medical supply chain data.
[0070] S5. When the node captured data is determined to be medical supply chain data based on the data classification and recognition result, the corresponding data feature vector is matched with each template vector pre-stored in the template library for similarity to obtain a similarity matching result.
[0071] In specific implementation, when the node capture data is determined to be medical supply chain data based on the data classification and recognition results, the data analysis terminal substitutes the data feature vector and each template vector pre-stored in the template library into the preset similarity operator for calculation to obtain the similarity parameters between the data feature vector and each template vector. A number of template vectors are pre-stored in the template library, and each template vector is associated with a corresponding medical supply chain data classification number.
[0072] The similarity operator is
[0073]
[0074] Among them, S represents the similarity parameter, x represents the data feature vector, y represents the template vector, ||·|| 2 Characterize the vector bi-norm operation, δ is the set similarity calculation coefficient. Alternatively, other similarity calculation rules can be set according to actual needs to determine the similarity index between the data feature vector and each template vector in the template library.
[0075] S6. Determine the medical supply chain data classification number of the node captured data based on the similarity matching result, and mark the node captured data with the corresponding medical supply chain data classification number and enter it into the medical digital supply chain mining data file.
[0076] In the specific implementation, the data analysis terminal first selects several template vectors with the highest similarity parameters with the data feature vector according to the similarity parameters between the data feature vector and each template vector, and sorts and combines them in order from high to low according to the corresponding similarity parameters to obtain a template vector sequence. Then, each template vector is scored according to the sorting of each template vector in the template vector sequence, such as 10 points for the first sorting, 9 points for the second sorting, and so on, and the medical supply chain data classification number associated with each template vector in the template vector sequence is determined. Then, the scores corresponding to the template vectors associated with the same medical supply chain data classification number in the template vector sequence are added to obtain the total classification score of the corresponding medical supply chain data classification number. Finally, the medical supply chain data classification number with the highest total classification score is used as the medical supply chain data classification number for the node to capture data.
[0077] After determining the medical supply chain data classification number of the node captured data, the data analysis terminal marks the node captured data with the corresponding medical supply chain data classification number and enters it into the medical digital supply chain mining data file. The medical digital supply chain mining data file can be a JSON format file or other format file.
[0078] S7. Output the entered medical digital supply chain mining data file.
[0079] In specific implementation, after all the captured data from all nodes have been classified and entered, the data analysis terminal can output, display and store the medical digital supply chain mining data files so that data management personnel can directly obtain the mined medical digital supply chain mining data.
[0080] This method can realize accurate medical supply chain data mining in the digital medical supply chain, effectively improve the mining efficiency and quality of medical supply chain data, ensure the availability of the mined medical supply chain data, and improve the usability of the mined medical supply chain data.
[0081] Embodiment 2:
[0082] This embodiment provides a medical supply chain data mining system based on artificial intelligence, such as Figure 2 As shown, it includes an information collection unit, a data processing unit, a feature extraction unit, a data classification unit, a feature matching unit, a data entry unit and a mining output unit, wherein:
[0083] The information collection unit is used to obtain the initialization capture information package uploaded by each data collection terminal, and parse the initialization capture information package to obtain the corresponding initialization capture information;
[0084] A data processing unit is used to perform data preprocessing on the initialization crawling information to obtain corresponding node crawling data, and perform data conversion processing on the node crawling data to obtain corresponding structured crawling data;
[0085] A feature extraction unit is used to vectorize the structured captured data to obtain the corresponding data feature vector;
[0086] A data classification unit, used to input the data feature vector into a preset data classification and recognition model for classification and recognition, and obtain a corresponding data classification and recognition result;
[0087] A feature matching unit is used to perform similarity matching between the corresponding data feature vector and each template vector pre-stored in the template library when the node captured data is determined to be medical supply chain data according to the data classification recognition result, so as to obtain a similarity matching result;
[0088] A data entry unit, used to determine the medical supply chain data classification number of the node captured data according to the similarity matching result, and to mark the node captured data with the corresponding medical supply chain data classification number and then enter it into the medical digital supply chain mining data file;
[0089] The mining output unit is used to output the entered medical digital supply chain mining data file.
[0090] Embodiment 3:
[0091] This embodiment provides a medical supply chain data mining system based on artificial intelligence, such as Figure 3 As shown, at the hardware level, it includes:
[0092] Data interface, used to establish data connection between the processor and the data acquisition terminal;
[0093] A memory for storing instructions;
[0094] A processor is used to read the instructions stored in the memory and execute the artificial intelligence-based medical supply chain data mining method in Example 1 according to the instructions.
[0095] Optionally, the system further includes an internal bus, through which the processor, the memory and the data interface can be interconnected, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.
[0096] The memory may include, but is not limited to, random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO) memory, etc. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0097] Embodiment 4:
[0098] This embodiment provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the medical supply chain data mining method based on artificial intelligence in Embodiment 1. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
[0099] This embodiment also provides a computer program product, which, when running on a computer, executes the medical supply chain data mining method based on artificial intelligence in Embodiment 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device.
[0100] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A medical supply chain data mining method based on artificial intelligence, characterized in that: include: Obtain the initialization capture information package uploaded by each data acquisition terminal, and parse the initialization capture information package to obtain the corresponding initialization capture information; Perform data preprocessing on the initialization crawling information to obtain the corresponding node crawling data, and perform data conversion processing on the node crawling data to obtain the corresponding structured crawling data; Vectorize the structured crawled data to obtain the corresponding data feature vector; Input the data feature vector into a preset data classification and recognition model for classification and recognition, and obtain the corresponding data classification and recognition result; When the node captured data is determined to be medical supply chain data according to the data classification and recognition result, the corresponding data feature vector is matched with each template vector pre-stored in the template library for similarity to obtain a similarity matching result; Determine the medical supply chain data classification number of the node captured data based on the similarity matching result, and annotate the node captured data with the corresponding medical supply chain data classification number and enter it into the medical digital supply chain mining data file; Output the entered medical digital supply chain mining data file.
2. According to claim 1, a medical supply chain data mining method based on artificial intelligence is characterized in that: When the initialization crawling information includes text data, the data preprocessing is performed on the initialization crawling information to obtain corresponding node crawling data, and the node crawling data is converted to obtain corresponding structured crawling data, including: Perform data cleaning on text data to obtain corresponding node crawling data; The node captured data is processed by slicing to obtain a number of node captured data blocks, and the base conversion process is performed on each node captured data block to obtain the corresponding block conversion data; The converted data of each block are associated and combined according to the fragmentation order of the corresponding node captured data block to obtain structured captured data.
3. The medical supply chain data mining method based on artificial intelligence according to claim 1 is characterized in that: When the initialization crawling information includes image data, the data preprocessing is performed on the initialization crawling information to obtain corresponding node crawling data, and the node crawling data is converted to obtain corresponding structured crawling data, including: Perform image enhancement and image encoding processing on the image data to obtain the corresponding node capture data; The node captured data is processed by slicing to obtain a number of node captured data blocks, and the base conversion process is performed on each node captured data block to obtain the corresponding block conversion data; The converted data of each block are associated and combined according to the fragmentation order of the corresponding node captured data block to obtain structured captured data.
4. The medical supply chain data mining method based on artificial intelligence according to claim 1 is characterized in that: When the initialization crawling information includes audio data, the data preprocessing is performed on the initialization crawling information to obtain corresponding node crawling data, and the node crawling data is converted to obtain corresponding structured crawling data, including: Perform speech recognition on the audio data to obtain the recognized text data, and then perform data cleaning on the text data to obtain the corresponding node crawling data; The node captured data is processed by slicing to obtain a number of node captured data blocks, and the base conversion process is performed on each node captured data block to obtain the corresponding block conversion data; The converted data of each block are associated and combined according to the fragmentation order of the corresponding node captured data block to obtain structured captured data.
5. The medical supply chain data mining method based on artificial intelligence according to claim 1 is characterized in that: The vectorization processing of the structured crawled data to obtain the corresponding data feature vector includes: Perform one-hot encoding on the structured crawled data to obtain the corresponding data feature vector.
6. The medical supply chain data mining method based on artificial intelligence according to claim 1 is characterized in that: Before inputting the data feature vector into a preset data classification and recognition model for classification and recognition, the method further includes: An initialized convolutional neural network model is constructed, and classification training is performed on the convolutional neural network model using a preset training set to obtain a corresponding data classification recognition model, wherein the training set includes a number of data feature vector samples marked with corresponding data classification labels.
7. The medical supply chain data mining method based on artificial intelligence according to claim 1 is characterized in that: The method of performing similarity matching between the corresponding data feature vector and each template vector pre-stored in the template library to obtain a similarity matching result includes: Substitute the data feature vector and each template vector pre-stored in the template library into the preset similarity operator for calculation to obtain the similarity parameters between the data feature vector and each template vector. The similarity operator is Among them, S represents the similarity parameter, x represents the data feature vector, y represents the template vector, ||·||2 represents the vector bi-norm operation, and δ is the set similarity calculation coefficient.
8. The medical supply chain data mining method based on artificial intelligence according to claim 7 is characterized in that: The method of determining the medical supply chain data classification number of the node captured data according to the similarity matching result includes: According to the similarity parameters between the data feature vector and each template vector, several template vectors with the highest similarity parameters with the data feature vector are selected, and they are sorted and combined in descending order according to the corresponding similarity parameters to obtain a template vector sequence; Assigning points to each template vector according to the order of each template vector in the template vector sequence, and determining the medical supply chain data classification number associated with each template vector in the template vector sequence; Add the scores corresponding to the template vectors associated with the same medical supply chain data classification number in the template vector sequence to obtain the total classification score of the corresponding medical supply chain data classification number; The medical supply chain data classification number with the highest total classification score is used as the medical supply chain data classification number for node crawling data.
9. A medical supply chain data mining system based on artificial intelligence, characterized in that: It includes an information collection unit, a data processing unit, a feature extraction unit, a data classification unit, a feature matching unit, a data entry unit and a mining output unit, wherein: The information collection unit is used to obtain the initialization capture information package uploaded by each data collection terminal, and parse the initialization capture information package to obtain the corresponding initialization capture information; A data processing unit is used to perform data preprocessing on the initialization crawling information to obtain corresponding node crawling data, and perform data conversion processing on the node crawling data to obtain corresponding structured crawling data; A feature extraction unit is used to vectorize the structured captured data to obtain the corresponding data feature vector; A data classification unit is used to input the data feature vector into a preset data classification and recognition model for classification and recognition to obtain a corresponding data classification and recognition result; A feature matching unit is used to perform similarity matching between the corresponding data feature vector and each template vector pre-stored in the template library when the node captured data is determined to be medical supply chain data according to the data classification recognition result, so as to obtain a similarity matching result; A data entry unit, used to determine the medical supply chain data classification number of the node captured data according to the similarity matching result, and to mark the node captured data with the corresponding medical supply chain data classification number and then enter it into the medical digital supply chain mining data file; The mining output unit is used to output the entered medical digital supply chain mining data file.
10. A medical supply chain data mining system based on artificial intelligence, characterized in that: include: A memory for storing instructions; A processor is used to read the instructions stored in the memory and execute the artificial intelligence-based medical supply chain data mining method described in any one of claims 1-8 according to the instructions.