Intelligent RFID medicine cabinet system and method based on intelligent medical treatment

Abstract

The invention provides an intelligent RFID medicine cabinet system and method based on intelligent medical treatment, relates to the field of medicine management, and aims to understand medicine date information and medicine inventory information in an intelligent RFID medicine cabinet based on RFID tags and understand medicine use conditions based on historical medicine application records of different departments in a hospital information system. And comprehensively considering the drug use condition, the inventory information and the date information to obtain the drug name and the drug quantity with the expiration risk at the current time point. Therefore, intelligent management of the medicine cabinet can be realized, medicines with expiration risks can be accurately identified through efficient and accurate data semantic analysis, and the safety and effectiveness of the medicines can be ensured.

Description

Technical Field

[0001] The present application relates to the field of drug management, and more specifically, to an intelligent RFID medicine cabinet system and method based on smart healthcare. Background Art

[0002] In the current booming medical industry, the management of medical office consumables has long faced prominent problems such as low efficiency and poor intelligence. Taking traditional medicine cabinet management as an example, the inventory of medicines and other consumables usually relies entirely on manual operations. The staff has to spend a lot of energy to regularly and carefully check the key information such as the name, specification and quantity of the medicines in the medicine cabinet. In large hospitals, there are many medicine cabinets and the types of medicines are even more complicated. As a result, manual inventory often requires a lot of time and cost. This not only causes a serious waste of human resources, but also during the inventory period, the medicine cabinet cannot provide services for medical work normally, which greatly affects the efficient development of medical work.

[0003] Furthermore, regarding the issue of expired medicines in medicine cabinets, the determination of medicines at risk of expiration basically relies on regular manual inspections by staff. However, due to the limitations of human factors, this method is prone to omissions. Once expired medicines are accidentally misused by patients, they will pose an immeasurable threat to the patient's health, and may even cause medical disputes and have a negative impact on the hospital's reputation and image. At the same time, with the continuous growth of medical needs and the rapid advancement of medical technology, the traditional manual management model has been unable to meet the requirements of the modern medical system for efficiency, accuracy, and safety.

[0004] Therefore, an intelligent RFID medicine cabinet solution based on smart medical care is needed. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent RFID medicine cabinet system and method based on smart medical care, which uses RFID tags to understand the drug date information and drug inventory information in the intelligent RFID medicine cabinet, and at the same time understands the drug usage based on the historical drug application records of different departments in the hospital information system, and comprehensively considers the drug usage, inventory information and date information to obtain the name and quantity of drugs that are at risk of expiration at the current time point. In this way, intelligent management of medicine cabinets can be achieved, and through efficient and accurate data semantic analysis, drugs that are at risk of expiration can be accurately identified, which is conducive to ensuring the safety and effectiveness of drugs.

[0006] According to one aspect of the present application, there is provided an intelligent RFID medicine cabinet system based on smart medical care, which includes:

[0007] Drug-related data collection module, used to obtain historical drug application records of different departments in the hospital information system and obtain production date, shelf life and quantity information of different drugs in the smart RFID medicine cabinet based on RFID tags;

[0008] A drug-related data processing module is used to process the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain a drug usage semantic feature vector and a medicine cabinet inventory drug semantic feature vector;

[0009] A drug inventory status-drug usage status matching module, used to obtain a drug inventory status-drug usage status matching feature vector based on the drug usage semantic feature vector and the drug inventory semantic feature vector of the medicine cabinet;

[0010] The expired risk drug result generation module is used to obtain the name and quantity of drugs with expiration risk at the current time point based on the inventory drug situation-drug usage matching feature vector.

[0011] According to another aspect of the present application, a smart RFID medicine cabinet method based on smart medical care is provided, which includes:

[0012] Obtain historical drug application records from different departments in the hospital information system and obtain production date, shelf life, and quantity information of different drugs in the smart RFID medicine cabinet based on RFID tags;

[0013] Data processing is performed on the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain a drug usage semantic feature vector and a medicine cabinet inventory drug semantic feature vector;

[0014] Based on the drug usage semantic feature vector and the medicine cabinet inventory drug semantic feature vector, obtaining an inventory drug situation-drug usage situation matching feature vector;

[0015] Based on the drug inventory status-drug usage status matching feature vector, the name and quantity of drugs at risk of expiration at the current time point are obtained.

[0016] Compared with the prior art, the smart RFID medicine cabinet system and method based on smart medical care provided by this application uses RFID tags to understand the drug date information and drug inventory information in the smart RFID medicine cabinet, and at the same time understands the drug usage based on the historical drug application records of different departments in the hospital information system, and comprehensively considers the drug usage, inventory information and date information to obtain the name and quantity of drugs that are at risk of expiration at the current time point. In this way, intelligent management of medicine cabinets can be achieved, and through efficient and accurate data semantic analysis, drugs that are at risk of expiration can be accurately identified, which is conducive to ensuring the safety and effectiveness of drugs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 This is a system block diagram of an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application.

[0019] Figure 2 This is a data flow diagram of an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application.

[0020] Figure 3 This is a block diagram of a drug-related data processing module in an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application.

[0021] Figure 4 This is a block diagram of a drug usage semantic feature extraction unit in an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application.

[0022] Figure 5 This is a block diagram of a semantic feature extraction unit for medicine inventory in a smart RFID medicine cabinet system based on smart healthcare according to an embodiment of the present application.

[0023] Figure 6 The present invention is a flowchart of a smart RFID medicine cabinet method based on smart medical care according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0025] In the development of the medical industry, medical office consumables have problems of low management efficiency and low intelligence level. For example, in traditional medicine cabinet management, inventory of medicines and other consumables often relies on manual work. Staff need to regularly check the name, specification, quantity and other information of the medicines in the medicine cabinet one by one. In a large-scale hospital, there are a large number of medicine cabinets and a variety of medicines, and manual inventory may take a long time. This not only wastes manpower, but also during the inventory, the medicine cabinet cannot be used normally, affecting the development of medical work. For the problem of expired medicines in the medicine cabinet, determining the medicines that are at risk of expiration often relies on manual regular inspections, which is prone to omissions. Once expired medicines are misused for patients, this will pose a serious threat to the health of patients.

[0026] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also shown a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for smart RFID medicine cabinets based on smart medical care.

[0027] Figure 1 This is a system block diagram of an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the smart RFID medicine cabinet system based on smart medical care according to an embodiment of the present application. Figure 1 and Figure 2 As shown, in the smart RFID medicine cabinet system 100 based on smart medical care, it includes: a drug-related data acquisition module 110, which is used to obtain the historical drug application records of different departments in the hospital information system and obtain the production date, shelf life, and quantity information of different drugs in the smart RFID medicine cabinet based on the RFID tag; a drug-related data processing module 120, which is used to process the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain a drug usage semantic feature vector and a medicine cabinet inventory drug semantic feature vector; a drug inventory status-drug usage status matching module 130, which is used to obtain a drug inventory status-drug usage status matching feature vector based on the drug usage semantic feature vector and the medicine cabinet inventory drug semantic feature vector; an expired risk drug result generation module 140, which is used to obtain the name and quantity of drugs with expiration risk at the current time point based on the drug inventory status-drug usage status matching feature vector.

[0028] In the embodiment of the present application, the drug-related data collection module 110 is used to obtain the historical drug application records of different departments in the hospital information system and to obtain the production date, shelf life and quantity information of different drugs in the smart RFID medicine cabinet based on RFID tags.

[0029] RFID (Radio Frequency Identification) tags are a contactless automatic identification technology that uses radio frequency signals and their spatial coupling and transmission characteristics to achieve automatic identification of stationary or moving objects. RFID tags are usually composed of a tag chip and an antenna, and can store relevant information about the identified object. When the RFID tag enters the radio frequency field of the RFID reader, the tag chip will activate and send the stored information to the reader through the antenna, and the reader will then transmit the received information to the background system for processing. In this application, RFID tags are used to store basic information about medicines, such as production date, shelf life, etc. Using RFID tags to read the information of medicines in the medicine cabinet in real time without manual intervention is beneficial to greatly improve data collection efficiency and accuracy.

[0030] It should be understood that the production date and shelf life of different drugs are important bases for judging whether the drugs have the risk of expiration, and the quantity of drugs is used to warn how many drugs have the risk of expiration. The historical drug application records of different departments in the hospital information system contain the name of the drugs applied for, quantity information, time information, etc. By analyzing the historical application records (here can be the application record data within one year before the current time point), we can understand the frequency and quantity of use of different drugs in each department at different times, and then obtain the medication needs of different drugs at different times. By combining medication needs with current drug inventory data and date data to promptly discover drugs with the risk of expiration, it is beneficial for relevant managers to take corresponding treatment measures in a timely manner, thereby realizing smarter drug safety management in the medical industry.

[0031] In the embodiment of the present application, the drug-related data processing module 120 is used to process the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain the drug usage semantic feature vector and the medicine cabinet inventory drug semantic feature vector. Specifically, Figure 3 FIG. 1 is a block diagram of a drug-related data processing module in an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application. Figure 3As shown, the drug-related data processing module 120 includes: a drug usage semantic feature extraction unit 121, which is used to preprocess and extract semantic features of historical drug application records of different departments in the hospital information system to obtain the drug usage semantic feature vector; a medicine cabinet inventory drug semantic feature extraction unit 122, which is used to preprocess and extract semantic features of the production date, shelf life, and quantity information of the different drugs to obtain the medicine cabinet inventory drug semantic feature vector.

[0032] More specifically, Figure 4 FIG. 1 is a block diagram of a drug usage semantic feature extraction unit in an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application. Figure 4 As shown, the drug usage semantic feature extraction unit 121 includes: a historical drug application record preprocessing subunit 121-1, which is used to perform data preprocessing on the historical drug application records of different departments to obtain the historical drug application situation after preprocessing; a drug usage semantic feature generation subunit 121-2, which is used to segment the preprocessed historical drug application situation and pass it through a drug usage situation semantic encoder to obtain the drug usage semantic feature vector.

[0033] Historical drug application records are an important data source for hospital drug management, which contains a wealth of drug use information. However, this information often exists in raw, unprocessed form. In order to better mine the key information, it is necessary to preprocess the historical drug application records of different departments to obtain the historical drug application information after preprocessing. The preprocessed data is neater, more standardized, and in a unified format (all text format data), which is conducive to subsequent data analysis and mining.

[0034] The historical drug application information after preprocessing is often unstructured. In order to convert the unstructured text data into structured data, the preprocessed historical drug application information needs to be segmented first. Word segmentation can help to understand the meaning of the application record text more systematically. For example, although "cefixime" and "cephalosporin" both contain the word "cephalosporin", their meanings and uses are completely different. In order to further extract the semantic features in the drug application record, it is necessary to pass the segmented data through a drug usage semantic encoder to obtain a drug usage semantic feature vector. The drug usage semantic encoder in this application specifically refers to a converter-based semantic encoder that includes a word embedding layer. The word embedding layer can capture the semantic relationship between words. The converter model can understand the semantics of the text more deeply through the self-attention mechanism and the multi-layer Transformer structure, and thus better capture the drug usage in different departments and different time periods.

[0035] More specifically, Figure 5FIG. 1 is a block diagram of a semantic feature extraction unit for medicines in a medicine cabinet inventory in an intelligent RFID medicine cabinet system based on smart medical care according to an embodiment of the present application. Figure 5 As shown, the medicine cabinet inventory drug semantic feature extraction unit 122 includes: an inventory drug basic information preprocessing subunit 122-1, which is used to perform data preprocessing on the production date, shelf life, and quantity information of the different drugs to obtain multiple preprocessed medicine cabinet inventory drug basic information; a medicine cabinet inventory drug basic semantic feature generation subunit 122-2, which is used to segment the multiple preprocessed medicine cabinet inventory drug basic information and then pass them through a medicine basic information semantic encoder to obtain multiple medicine cabinet inventory drug basic semantic feature vectors; a medicine cabinet inventory drug basic semantic feature combination subunit 122-3, which is used to cascade the multiple medicine cabinet inventory drug basic semantic feature vectors to obtain the medicine cabinet inventory drug semantic feature vector.

[0036] Considering that the various drug information collected based on RFID tags may have inconsistent formats, in order to facilitate the subsequent semantic analysis, the technical solution of this application needs to preprocess the production date, shelf life, and quantity information of the different drugs to obtain multiple preprocessed basic information of the medicine cabinet inventory. The basic information of the inventory drugs after preprocessing is in text format. The preprocessed data format is more unified and standardized, which can speed up the semantic analysis and improve the analysis efficiency.

[0037] In order to divide the continuous text information into vocabulary units with specific meanings, and thus facilitate the subsequent semantic analysis, it is necessary to first perform word segmentation on each of the multiple pre-processed medicine cabinet inventory medicine basic information. After word segmentation, each word represents a specific meaning, which helps the system to understand the text content more accurately. Then, the multiple word segmentation basic information keywords of the medicine cabinet inventory medicine obtained by word segmentation of each pre-processed medicine cabinet inventory medicine basic information are passed through the medicine basic information semantic encoder to obtain the medicine cabinet inventory medicine basic semantic feature vector. Through the processing of the medicine basic information semantic encoder, the vocabulary level information can be converted into a higher level semantic feature vector, which can more comprehensively express the basic information of the medicine, including different key attributes and the association and constraint relationship between the attributes. In this application, the medicine basic information semantic encoder refers to a converter-based semantic encoder including a word embedding layer. Those of ordinary skill in the art should know that the word embedding layer can map words to a high-dimensional vector space, so that similar words are closer in the vector space. This helps the system to understand the semantics of the words more accurately, thereby extracting more meaningful features. The converter structure has a strong ability to capture long-distance dependencies and can capture the correlation between different positions in the input sequence, thereby more comprehensively understanding the content of the input sequence. It also has good flexibility and scalability and can be fine-tuned and expanded according to different task requirements to adapt to different application scenarios.

[0038] Each basic semantic feature vector of medicines in the medicine cabinet is a high-level abstract representation of the basic information of a specific medicine. These vectors are obtained by encoding the key attributes of the medicine through a semantic encoder. Each vector is a semantic projection of the medicine in a specific dimension, reflecting its uniqueness in the entire medicine cabinet. In order to facilitate subsequent processing and analysis, the technical solution of this application needs to cascade the multiple basic semantic feature vectors of medicines in the medicine cabinet to obtain the semantic feature vector of medicines in the medicine cabinet.

[0039] In an embodiment of the present application, the inventory drug situation-drug usage matching module 130 is used to obtain the inventory drug situation-drug usage matching feature vector based on the drug usage semantic feature vector and the medicine cabinet inventory drug semantic feature vector. Specifically, in an embodiment of the present application, the inventory drug situation-drug usage matching module is used to: perform topological association modulation based on significant feature heterogeneity adaptation on the medicine cabinet inventory drug semantic feature vector and the drug usage semantic feature vector to obtain the inventory drug situation-drug usage matching feature vector. It should be understood that in order to achieve an accurate match between the basic information of the medicine cabinet inventory drugs and the usage situation, and to help the system more accurately understand the intrinsic connection between the current medicine cabinet inventory drugs and usage trends, the medicine cabinet inventory drug semantic feature vector and the drug usage semantic feature vector can be fused.

[0040] In particular, considering that the semantic feature vector of the medicine cabinet inventory drugs is based on the drug information features obtained from the RFID tag, including physical attribute information such as production date, shelf life, quantity, etc., and the semantic feature vector of drug use is obtained by extracting the historical drug application records of different departments, reflecting the frequency of drug use, department preferences and other usage conditions, feature heterogeneity refers to the difference in nature between different features. In the technical solution of the present application, there is a significant feature heterogeneity between the semantic feature vector of the medicine cabinet inventory drugs and the semantic feature vector of drug use. During feature fusion, this heterogeneity may lead to the mismatch between the feature manifold and the feature space. If the feature manifolds of the two feature vectors do not match, the fused matching feature vector may not be able to maintain the smoothness of the original feature manifold, which will cause the fused features to have large gaps or overlaps in the feature space, which will affect the expression of the features. At the same time, the mismatch of the feature space will cause the fused feature vector to be unable to accurately express the features of the original data, thereby affecting the final prediction results. Therefore, in the technical solution of the present application, the semantic feature vector of the medicine cabinet inventory and the semantic feature vector of the medicine usage are modulated by topological association based on adaptation to significant feature heterogeneity to obtain a matching feature vector of the inventory medicine situation and the medicine usage situation.

[0041] Specifically, in an embodiment of the present application, the semantic feature vector of the medicine cabinet inventory drugs and the semantic feature vector of the drug use are subjected to topological association modulation based on significant feature heterogeneity adaptation to obtain an inventory drug situation-drug use situation matching feature vector, including: constructing an inventory drug situation-drug use situation distance topological matrix between the semantic feature vector of the medicine cabinet inventory drugs and the semantic feature vector of drug use; constructing an inventory drug situation-drug use situation feature value granularity association matrix between the semantic feature vector of the medicine cabinet inventory drugs and the semantic feature vector of drug use; and matching the inventory drug situation-drug use situation based on the inventory drug situation-drug use situation distance topological matrix. The drug inventory-drug usage feature value granularity association matrix is ​​topologically modulated to obtain a drug inventory-drug usage topological modulation association matrix; the drug inventory-drug usage topological modulation association matrix is ​​used as the perspective co-projection space, and the medicine cabinet stock drug semantic feature vector and the drug usage semantic feature vector are projected into the perspective co-projection space to obtain a perspective-modulated medicine cabinet stock drug semantic feature vector and a perspective-modulated drug usage semantic feature vector; the perspective-modulated medicine cabinet stock drug semantic feature vector and the perspective-modulated drug usage semantic feature vector are fused to obtain the drug inventory-drug usage matching feature vector.

[0042] In an embodiment of the present application, another expression of performing topological association modulation based on significant feature heterogeneity adaptation on the semantic feature vector of the medicine cabinet inventory drugs and the semantic feature vector of drug use to obtain a matching feature vector of inventory drug situation-drug use situation can be: processing the semantic feature vector of the medicine cabinet inventory drugs and the semantic feature vector of drug use with the following formula to obtain a matching feature vector of inventory drug situation-drug use situation; wherein the formula is:

[0043] M t =D(V1,V2)

[0044]

[0045] V c =α·V1′+β·V2′

[0046] Wherein, V1 represents the semantic feature vector of the medicine cabinet inventory drugs, V2 represents the semantic feature vector of the drug usage, and D(V1, V2) is the distance topological matrix between the medicine cabinet inventory drug semantic feature vector and the drug usage semantic feature vector, that is, d i,j =d(v 1i ,v 2j ), d i,j is the eigenvalue of the position (i, j) in the distance topological matrix between the inventory drug situation and the drug usage situation, d(v1i ,v 2j ) represents the distance between the feature value of the ith position of the semantic feature vector of the medicine cabinet inventory and the feature value of the jth position of the semantic feature vector of the medicine usage, and V1 and V2 are both column vectors, M t represents the distance topological matrix of the inventory drug situation-drug usage situation, T represents the transpose of the vector, Represents matrix multiplication, M v represents the inventory drug situation-drug usage characteristic value granularity association matrix, exp represents the natural exponential function, M c represents the drug inventory-drug usage topological modulation association matrix, V1' represents the perspective modulation drug inventory semantic feature vector, V2' represents the perspective modulation drug usage semantic feature vector, α and β represent weighted hyperparameters, V c Represents the drug inventory status-drug usage status matching feature vector.

[0047] That is, in the technical solution of the present application, the semantic feature vector of the medicine cabinet inventory and the semantic feature vector of the medicine use are modulated by topological association based on adaptation to significant feature heterogeneity, and firstly, a distance topological matrix of inventory drug situation-drug use situation between the semantic feature vector of the medicine cabinet inventory and the semantic feature vector of the medicine use is constructed. This step utilizes the idea of ​​graph theory, taking the eigenvalues ​​of each position in the semantic feature vector of the medicine cabinet inventory and the semantic feature vector of the medicine use as nodes, and using the distance metric function to determine the low-dimensional embedding expression of the edges between nodes, so as to construct a feature expression that can quantify the topological association relationship between the semantic feature vector of the medicine cabinet inventory and the semantic feature vector of the medicine use. This step is crucial to understanding the spatial distribution of data points and their interconnections, and also provides basic structural information for subsequent steps.

[0048] Next, a granularity association matrix of the inventory drug situation-drug usage feature value between the semantic feature vector of the medicine cabinet inventory drug and the semantic feature vector of drug usage is constructed. This step focuses on exploring the correlation between the internal attributes of the feature vector. In a specific example, the product between the transposed vector of the semantic feature vector of the medicine cabinet inventory drug and the semantic feature vector of drug usage is calculated to obtain the granularity association matrix of the inventory drug situation-drug usage feature value. Furthermore, the topological association modulation of the inventory drug situation-drug usage feature value granularity association matrix is ​​performed based on the inventory drug situation-drug usage distance topological matrix to obtain the inventory drug situation-drug usage topological modulation association matrix. That is, the granularity association information of the eigenvalue of the semantic feature vector of the medicine cabinet inventory drug and the semantic feature vector of drug usage is driven to wander on the distance topological map to construct a low-dimensional modulated perspective co-projection space domain for mapping the semantic feature vector of the medicine cabinet inventory drug and the semantic feature vector of drug usage to a continuous high-dimensional regression space attribute.

[0049] Next, the drug inventory-drug usage topological modulation association matrix is ​​used as the perspective co-projection space, and the medicine cabinet inventory drug semantic feature vector and the drug usage semantic feature vector are projected into the perspective co-projection space to obtain the perspective modulated medicine cabinet inventory drug semantic feature vector and the perspective modulated drug usage semantic feature vector. That is, the key to this technical solution is to find an implicit third space with modulation capability, in which as much information of the original high-dimensional data as possible is retained, so that the converted new feature vector not only reduces the dimension, but also maintains the relative position relationship between the original features.

[0050] Finally, the perspective-modulated medicine cabinet inventory drug semantic feature vector and the perspective-modulated drug usage semantic feature vector are fused to obtain the inventory drug situation-drug usage matching feature vector. Fusion can be achieved in a variety of forms, ranging from simple arithmetic averages to complex ensemble learning algorithms, depending on the application scenario and the goals pursued. The final inventory drug situation-drug usage matching feature vector combines the main features of the two sets of input data and provides a more comprehensive data representation, which is not only conducive to improving the performance of machine learning models, but also promotes the ability of cross-modal or multi-source data analysis, thereby significantly enhancing the understanding and utilization efficiency of complex data structures.

[0051] In the embodiment of the present application, the expired risk drug result generation module 140 is used to obtain the name and quantity of drugs with expired risk at the current time point based on the inventory drug situation-drug usage matching feature vector. Specifically, in the embodiment of the present application, the expired risk drug result generation module is used to: pass the inventory drug situation-drug usage matching feature vector through the focus on drug monitoring result generator to obtain a generation result, and the generation result is the name and quantity of drugs with expired risk at the current time point. It should be understood that the inventory drug situation-drug usage matching feature vector is obtained through a series of complex data processing steps, including data preprocessing, word segmentation, semantic encoding, etc. This matching feature vector is actually a highly generalized and abstract data representation, which reflects the inherent connection and law between the basic information of inventory drugs and usage. In order to convert the abstract matching feature vector into a specific and operational monitoring result, that is, the name and quantity of drugs with expired risk at the current time point, it is necessary to pass the inventory drug situation-drug usage matching feature vector through the focus on drug monitoring result generator. The drug monitoring result generator is a machine learning-based model that can decode the information in the feature vector to generate specific results through training. Through the decoded results about expired risk drugs, drug managers can take corresponding measures to ensure the safety and effectiveness of drugs.

[0052] In summary, the smart RFID medicine cabinet system 100 based on smart medical care according to the embodiment of the present application is explained, which uses RFID tags to understand the drug date information and drug inventory information in the smart RFID medicine cabinet, and at the same time understands the drug usage based on the historical drug application records of different departments in the hospital information system, and comprehensively considers the drug usage, inventory information and date information to obtain the name and quantity of drugs with expiration risk at the current time point. In this way, the intelligent management of the medicine cabinet can be realized, and through efficient and accurate data semantic analysis, drugs with expiration risk can be accurately identified, which is conducive to ensuring the safety and effectiveness of drugs.

[0053] As described above, the smart RFID medicine cabinet system 100 based on smart medical care according to the embodiment of the present application can be implemented in various terminal devices, such as a server for a smart RFID medicine cabinet based on smart medical care. In one example, the smart RFID medicine cabinet system 100 based on smart medical care according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the smart RFID medicine cabinet system 100 based on smart medical care can be a software module in the operating system of the terminal device, or it can be an application developed for the terminal device; of course, the smart RFID medicine cabinet system 100 based on smart medical care can also be one of the many hardware modules of the terminal device.

[0054] Alternatively, in another example, the smart RFID medicine cabinet system 100 based on smart healthcare and the terminal device may also be separate devices, and the smart RFID medicine cabinet system 100 based on smart healthcare may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0055] Figure 6 FIG. 1 is a flow chart of a smart RFID medicine cabinet method based on smart medical treatment according to an embodiment of the present application. Figure 6 As shown, in the smart RFID medicine cabinet method based on smart medical care, it includes: S110, obtaining the historical drug application records of different departments in the hospital information system and obtaining the production date, shelf life, and quantity information of different drugs in the smart RFID medicine cabinet based on the RFID tag; S120, respectively processing the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain a drug usage semantic feature vector and a medicine cabinet inventory drug semantic feature vector; S130, based on the drug usage semantic feature vector and the medicine cabinet inventory drug semantic feature vector, obtain the inventory drug situation-drug usage matching feature vector; S140, based on the inventory drug situation-drug usage matching feature vector, obtain the name and quantity of drugs that are at risk of expiration at the current time point.

[0056] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned smart RFID medicine cabinet method based on smart medical care have been referred to above. Figures 1 to 5 The invention has been introduced in detail in the description of the smart RFID medicine cabinet system based on smart medical care, and therefore, its repeated description will be omitted.

[0057] In summary, the smart RFID medicine cabinet method based on smart medical care based on the embodiment of the present application is explained, which uses RFID tags to understand the drug date information and drug inventory information in the smart RFID medicine cabinet, and at the same time understands the drug usage based on the historical drug application records of different departments in the hospital information system, and comprehensively considers the drug usage, inventory information and date information to obtain the name and quantity of drugs that are at risk of expiration at the current time point. In this way, intelligent management of medicine cabinets can be achieved, and through efficient and accurate data semantic analysis, drugs that are at risk of expiration can be accurately identified, which is conducive to ensuring the safety and effectiveness of drugs.

[0058] The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprise and / or comprising" when used in this specification specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, element components, and / or groups thereof.

[0059] Those skilled in the art will appreciate that various example embodiments are shown and described herein, each example embodiment having certain features in a particular embodiment, but the present application is not limited thereto. On the contrary, the present application can be modified to incorporate any number of variants, changes, substitutions, combinations, sub-combinations, or equivalent arrangements not previously described but commensurate with the scope of the present application. In addition, although various embodiments of the present application have been described, it will be understood that aspects of the present application may include only some of the described embodiments. Therefore, the present application will not be considered to be limited by the foregoing description, but only by the scope of the appended claims.

Claims

1. An intelligent RFID medicine cabinet system based on smart medical care, characterized in that: include: Drug-related data collection module, used to obtain historical drug application records of different departments in the hospital information system and obtain production date, shelf life and quantity information of different drugs in the smart RFID medicine cabinet based on RFID tags; A drug-related data processing module is used to process the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain a drug usage semantic feature vector and a medicine cabinet inventory drug semantic feature vector; A drug inventory status-drug usage status matching module, used to obtain a drug inventory status-drug usage status matching feature vector based on the drug usage semantic feature vector and the drug inventory semantic feature vector of the medicine cabinet; The expired risk drug result generation module is used to obtain the name and quantity of drugs with expiration risk at the current time point based on the inventory drug situation-drug usage matching feature vector.

2. The intelligent RFID medicine cabinet system based on smart medical care according to claim 1 is characterized in that: The drug-related data processing module includes: A drug usage semantic feature extraction unit, used for preprocessing and extracting semantic features from historical drug application records of different departments in the hospital information system to obtain the drug usage semantic feature vector; The medicine cabinet inventory drug semantic feature extraction unit is used to pre-process the production date, shelf life, and quantity information of the different drugs and extract semantic features to obtain the medicine cabinet inventory drug semantic feature vector.

3. The intelligent RFID medicine cabinet system based on smart medical care according to claim 2 is characterized in that: The drug uses a semantic feature extraction unit, including: A historical drug application record preprocessing subunit is used to perform data preprocessing on the historical drug application records of the different departments to obtain the historical drug application status after preprocessing; The drug use semantic feature generation subunit is used to segment the pre-processed historical drug application situation and pass it through a drug use situation semantic encoder to obtain the drug use semantic feature vector.

4. The intelligent RFID medicine cabinet system based on smart medical care according to claim 3 is characterized in that: The medicine cabinet inventory medicine semantic feature extraction unit comprises: The basic information preprocessing subunit of the inventory drugs is used to preprocess the production date, shelf life and quantity information of the different drugs to obtain a plurality of basic information of the inventory drugs in the medicine cabinet after preprocessing; A medicine cabinet inventory medicine basic semantic feature generation subunit, used for segmenting the plurality of pre-processed medicine cabinet inventory medicine basic information and passing them through a medicine basic information semantic encoder to obtain a plurality of medicine cabinet inventory medicine basic semantic feature vectors; The medicine cabinet stock medicine basic semantic feature combination subunit is used to cascade the multiple medicine cabinet stock medicine basic semantic feature vectors to obtain the medicine cabinet stock medicine semantic feature vector.

5. The intelligent RFID medicine cabinet system based on smart medical care according to claim 4 is characterized in that: The drug basic information semantic encoder and the drug usage semantic encoder are converter-based semantic encoders that include a word embedding layer.

6. The intelligent RFID medicine cabinet system based on smart medical care according to claim 5 is characterized in that: The drug inventory status-drug usage status matching module is used to: perform topological association modulation based on significant feature heterogeneity adaptation on the semantic feature vector of drug inventory in the medicine cabinet and the semantic feature vector of drug usage to obtain the drug inventory status-drug usage matching feature vector.

7. The intelligent RFID medicine cabinet system based on smart medical care according to claim 6 is characterized in that: The inventory drug status-drug usage status matching module is used to: Constructing a distance topological matrix between the medicine cabinet inventory medicine semantic feature vector and the medicine usage semantic feature vector; Constructing a drug inventory status-drug usage status feature value granularity association matrix between the drug inventory semantic feature vector of the medicine cabinet and the drug usage semantic feature vector; Based on the inventory drug situation-drug usage situation distance topological matrix, the inventory drug situation-drug usage situation characteristic value granularity association matrix is ​​topologically modulated to obtain an inventory drug situation-drug usage situation topological modulation association matrix; Taking the drug inventory situation-drug usage situation topological modulation association matrix as the perspective co-projection space, projecting the medicine cabinet inventory drug semantic feature vector and the drug usage semantic feature vector into the perspective co-projection space to obtain the perspective-modulated medicine cabinet inventory drug semantic feature vector and the perspective-modulated drug usage semantic feature vector; The perspective-modulated medicine cabinet inventory drug semantic feature vector and the perspective-modulated medicine usage semantic feature vector are fused to obtain the inventory drug situation-drug usage situation matching feature vector.

8. The intelligent RFID medicine cabinet system based on smart medical care according to claim 7 is characterized in that: The expired risk drug result generation module is used to: match the inventory drug situation-drug usage situation matching feature vector through the key focus drug monitoring result generator to obtain a generation result, and the generation result is the name and quantity of the drug with expiration risk at the current time point.

9. A smart RFID medicine cabinet method based on smart medical care, characterized in that: include: Obtain historical drug application records from different departments in the hospital information system and obtain production date, shelf life, and quantity information of different drugs in the smart RFID medicine cabinet based on RFID tags; Data processing is performed on the historical drug application records of different departments in the hospital information system and the production date, shelf life, and quantity information of the different drugs to obtain a drug usage semantic feature vector and a medicine cabinet inventory drug semantic feature vector; Based on the drug usage semantic feature vector and the medicine cabinet inventory drug semantic feature vector, obtaining an inventory drug situation-drug usage situation matching feature vector; Based on the drug inventory status-drug usage status matching feature vector, the name and quantity of drugs at risk of expiration at the current time point are obtained.

10. The smart RFID medicine cabinet method based on smart medical care according to claim 9, characterized in that: Based on the drug inventory status-drug usage status matching feature vector, the name and quantity of drugs at risk of expiration at the current time point are obtained, including: The inventory drug situation-drug usage situation matching feature vector is passed through the focused drug monitoring result generator to obtain a generated result, and the generated result is the name and quantity of drugs that are at risk of expiration at the current time point.

Images