A method and system for intelligent sorting based on medical product label classification

Abstract

The application provides a kind of method and system based on medical product label classification intelligent sorting, belong to data transmission technical field, to effectively solve the problems such as high error rate, low efficiency and poor safety caused by artificial classification in background art.The method comprises the following steps: the reader sends a paging message, and the paging message requests the specified type of medical product label to report label information;The reader receives the label information returned by each of the plurality of medical product labels, a plurality of label information, the plurality of medical product labels are the specified type of medical product label, and each label information in the plurality of label information is the description of the corresponding one of the plurality of medical product labels;The reader intelligently analyzes and sorts the plurality of label information to determine the storage location of the plurality of medical products, and the plurality of medical products correspond to the plurality of medical product labels one by one.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for intelligent sorting based on medical product label classification. Background Technology

[0002] In the healthcare industry, the management and retrieval of medical products (such as pharmaceuticals, medical devices, and medical consumables) rely on label information (such as product name, specifications, production batch number, expiration date, storage conditions, and applicable departments). Currently, the classification and sorting of medical product labels mostly adopts a combination of "manual classification + fixed field sorting" (such as sorting by the first letter of the product name or by the date of entry into the warehouse).

[0003] Manual classification relies on the experience of operators and is prone to errors due to misinterpretation of label information (such as misclassifying "orthopedic medical consumables" as "surgical consumables") or omission of label fields (such as ignoring the "cold chain storage" label). The error rate is as high as 15%, which affects product retrieval efficiency and storage security. Summary of the Invention

[0004] This invention provides a method and system for intelligent sorting based on medical product label classification, which effectively solves the problems of high error rate, low efficiency and poor security caused by manual classification in the background art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a method for intelligent sorting based on medical product label classification is provided, applied to a medical product label classification intelligent sorting system. The system includes a reader and multiple medical product labels. The method includes: the reader sending a paging message requesting medical product labels of a specified type to report label information; the reader receiving label information returned by each of the multiple medical product labels, resulting in multiple label information entries, where the multiple medical product labels are of a specified type, and each label information entry is a description of a corresponding medical product label among the multiple medical product labels; the reader intelligently analyzes and sorts the multiple label information entries to determine the inventory location where each of the multiple medical products needs to be stored, with each medical product corresponding to one of the multiple medical product labels.

[0006] Optionally, the reader intelligently analyzes and sorts multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored. This includes: for any target tag information among the multiple tag information: the reader extracts multiple key fields from the target tag information through a lightweight network; the reader maps the multiple key fields to a target point cloud; the reader determines the target pre-set point cloud that best matches the target point cloud from multiple pre-set point clouds. The multiple pre-set point clouds correspond one-to-one with multiple departments. Each pre-set point cloud is mapped from the key fields in the tag information of the medical products stored in the corresponding department. The department corresponding to the target pre-set point cloud is the inventory location of the target medical product corresponding to the target tag information.

[0007] Optionally, the reader maps multiple key fields to a target point cloud, including: the reader maps each of the multiple key fields to a corresponding vector in the xy coordinate system, resulting in multiple vectors, the starting endpoints of the multiple vectors are all located at the origin of the xy coordinate system, and the coordinates of the ending point of each of the multiple vectors in the xy coordinate system are used as a corresponding point cloud point, resulting in multiple point cloud points, which constitute the target point cloud.

[0008] Optionally, the reader determines the target preset point cloud that best matches the target point cloud from multiple preset point clouds, including: the reader determining the target circumscribed circle of the target point cloud in the xy coordinate system; the reader determining the intersection area between the target circumscribed circle and multiple circumscribed circles in the xy coordinate system, where each of the multiple circumscribed circles is the circumscribed circle of a corresponding preset point cloud among the multiple preset point clouds; the reader determining the preset point cloud circumscribed by the circumscribed circle of the intersection area among the multiple circumscribed circles as the target preset point cloud that best matches the target point cloud.

[0009] Optionally, the reader intelligently analyzes and sorts multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored. This includes: for any target tag information among the multiple tag information: the reader extracts multiple key fields from the target tag information through a lightweight network; the reader determines the matching degree between the multiple key fields and the key fields corresponding to each department in the multiple departments; the reader determines the department with the highest matching degree among the multiple departments, and the department with the highest matching degree is the inventory location of the target medical product corresponding to the target tag information.

[0010] Optionally, the reader determines the matching degree between multiple key fields and the key fields corresponding to each department in multiple departments, including: for any target department in multiple departments, multiple medical products correspond to target scenarios in multiple scenarios: the reader determines the matching degree between each key field in multiple key fields and the key field corresponding to the target department, obtaining multiple matching degrees; the reader performs a weighted summation of the multiple matching degrees according to the weight corresponding to the target department in the target scenario, obtaining a summed matching, wherein the weight corresponding to the target department is different in different scenarios in multiple scenarios.

[0011] Optionally, each of the multiple label information also includes verification information of the corresponding medical product label among the multiple medical product labels, for a total of multiple verification information. The method further includes: the reader performing identity verification on the multiple medical product labels based on the multiple verification information.

[0012] Optionally, the reader performs identity verification on multiple medical product labels based on multiple verification information, including: the reader divides the multiple verification information into M information groups, where M is an integer greater than or equal to 3, and any two information groups contain only one verification information that is the same; the reader uses a lightweight network to analyze the M information groups sequentially; the reader uses the lightweight network to analyze the M information groups sequentially to determine whether there are any information groups with abnormal information; if there is a first information group and a second information group with abnormal information among the M information groups, the reader determines that the medical product label corresponding to the target verification information has an information security risk, and the target verification information is the same verification information contained in the first information group and the second information group.

[0013] Optionally, the reader sequentially analyzes M information groups through a lightweight network, including: for any target information group among the M information groups: the reader concatenates the verification information contained in the target information group into a continuous information; the reader inputs the continuous information into the lightweight network to obtain a target vector sequence output by the lightweight network; the reader determines the spatial distance value between the target vector sequence and the corresponding preset vector sequence. If the spatial distance value is less than the distance threshold, it indicates that there is no information anomaly in the target information group; otherwise, it indicates that there is information anomaly in the target information group.

[0014] Secondly, a system for intelligent sorting based on medical product label classification is provided. This system includes a reader and multiple medical product labels. The system is configured as follows: the reader sends a paging message requesting medical product labels of a specified type to report label information; the reader receives label information returned by each of the multiple medical product labels, resulting in multiple label information entries. Each label information entry describes a specific medical product label within the multiple medical product labels; the reader intelligently analyzes and sorts the multiple label information entries to determine the appropriate inventory location for each medical product, ensuring a one-to-one correspondence between the multiple medical products and the multiple medical product labels.

[0015] It should be understood that the specific implementation of the system can also refer to the relevant introduction of the above methods, and will not be repeated here.

[0016] Thirdly, an electronic device is provided, comprising: a processor and a memory; the memory is used to store a computer program, which, when executed by the processor, causes the electronic device to perform the method described in the first aspect.

[0017] In one possible design, the electronic device described in the third aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the electronic device described in the third aspect and other electronic devices.

[0018] In the embodiments of the present invention, the electronic device described in the third aspect may be a terminal, or a chip (system) or other component or assembly disposed in the terminal, or a system containing the terminal.

[0019] Fourthly, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer causes the computer to perform the method described in the first aspect.

[0020] In summary, the above methods and systems have the following technical effects: 1. Improve classification accuracy and reliability, and reduce error rate. The reader automatically requests and receives tag information and processes this information using an intelligent analysis and sorting algorithm, eliminating subjective judgment factors. Intelligent analysis accurately parses tag fields (such as product name, specifications, storage conditions, etc.), avoiding misreading or omissions, thereby significantly reducing the classification error rate. The error rate is expected to be reduced to below 1%, improving the reliability and consistency of classification.

[0021] 2. Improve product search efficiency Intelligent analysis and sorting automates the processing of tag information, quickly determining the product's inventory location. The reader can process multiple tag information simultaneously, enabling batch sorting and significantly reducing classification time. Furthermore, accurate classification makes products easier to retrieve, reducing the time healthcare staff waste searching for products and improving the overall efficiency of the medical process.

[0022] 3. Enhance storage security Intelligent analysis and sorting take into account key fields in the label (such as storage conditions, expiration date, and applicable departments) to ensure that each product is assigned to an inventory location that matches its characteristics. For example, the system will automatically identify the "cold chain storage" label and direct the product to the refrigerated area, thereby ensuring product quality and patient safety and reducing medical risks.

[0023] 4. Achieve standardized and automated management This solution processes all label information using a unified intelligent analysis algorithm, achieving standardization and automation of the classification process. This not only reduces reliance on operators and lowers training costs, but also ensures the consistency and repeatability of classification results, facilitating system maintenance and expansion.

[0024] 5. Supports real-time dynamic adjustment Intelligent analysis and sorting can dynamically adjust the sorting results based on real-time received tag information, such as prioritizing products nearing their expiration date or products for departments with high demand. This flexibility improves the responsiveness of inventory management and optimizes resource allocation.

[0025] The technical solution of this application effectively solves the problems of high error rate, low efficiency, and poor security caused by manual classification in the background technology through automated and intelligent label information processing. The technical effects are mainly reflected in classification accuracy, retrieval efficiency, storage security, management standardization, and real-time adaptability, providing a more reliable and efficient solution for medical product management. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the architecture of a system based on intelligent sorting of medical product labels provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating the intelligent sorting method based on medical product label classification provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0028] The technical solutions of this invention can be applied to various intelligent sorting systems based on medical product label classification, such as Wi-Fi wireless network systems, vehicle-to-everything (V2X) intelligent sorting systems based on medical product label classification, device-to-device (D2D) intelligent sorting systems based on medical product label classification, vehicle-to-everything (V2X) intelligent sorting systems based on medical product label classification, fourth-generation (4G) mobile intelligent sorting systems based on medical product label classification, such as Long Term Evolution (LTE) systems, Worldwide Interoperability for Microwave Access (WiMAX) intelligent sorting systems based on medical product label classification, fifth-generation (5G) systems, such as New Radio (NR) systems, and future intelligent sorting systems based on medical product label classification, etc.

[0029] In this embodiment of the invention, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In specific implementation, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a correlation between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0030] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be elaborated upon here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In specific implementation, the required indication method can be selected according to specific needs. This embodiment of the invention does not limit the selected indication method; therefore, the indication methods involved in this embodiment of the invention should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0031] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this embodiment of the invention. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0032] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This embodiment of the invention does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or electronic device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or electronic device. The type of memory can be any form of storage medium, and this embodiment of the invention does not limit this.

[0033] In the embodiments of this invention, the “protocol” may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to a future intelligent sorting system based on medical product label classification. The embodiments of this invention do not specifically limit this.

[0034] In this embodiment of the invention, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0035] In the description of the embodiments of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this invention, words such as "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0036] The network architecture and business scenarios described in the embodiments of this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0037] To facilitate understanding of the embodiments of the present invention, firstly, let's take... Figure 1 The system for intelligent sorting based on medical product label classification, illustrated in the diagram, is described in detail as an example of a system applicable to embodiments of the present invention. For instance, Figure 1 This is a schematic diagram of the architecture of a system for intelligent sorting based on medical product label classification, applicable to the intelligent sorting method based on medical product label classification provided in this embodiment of the invention.

[0038] like Figure 1 As shown, the system for intelligent sorting based on medical product label classification can include: a reader and multiple labels.

[0039] The reader can be a base station, pole station, micro base station, macro station, etc., or it can be a terminal device, such as a mobile phone, IoT device, or handheld reader. Base stations or access network devices that support ambient IoT (AIoT) functionality conduct non-contact two-way data communication via radio frequency, using radio frequency to read and write to IoT devices, thereby achieving the purpose of target identification and data exchange.

[0040] Tags can be understood as similar to semi-passive AIoT devices. Semi-passive AIoT devices can obtain energy through solar, radio frequency, wind, hydro, or tidal power, with no restrictions on the energy source. These tags do not have their own power supply devices such as batteries; instead, they obtain energy from the environment to support data sensing, transmission, and distributed computing. Alternatively, tags can also be understood as similar to active AIoT devices.

[0041] In this system: the reader sends a paging message requesting a specified type of medical product label to report its label information; the reader receives label information returned by multiple medical product labels, totaling multiple label information entries. These multiple medical product labels are of the specified type, and each label information entry describes a corresponding medical product label among the multiple labels; the reader intelligently analyzes and sorts the multiple label information entries to determine the inventory location where each of the multiple medical products needs to be stored. There is a one-to-one correspondence between the multiple medical products and the multiple medical product labels. For details, please refer to the relevant descriptions in the following method embodiments, which will not be repeated here.

[0042] Figure 2 This is a flowchart illustrating the method provided in an embodiment of the present invention. This intelligent sorting method based on medical product label classification is applicable to the aforementioned system and involves the interaction between a reader and labels (such as medical product labels). The specific process is as follows: S201, the reader sends a paging message, which requests the reporting of tag information for a specified type of medical product tag.

[0043] Each medical product label can be set on the corresponding medical product.

[0044] The paging message may include a mask for a specified type of medical product tag. This mask may be a feature common to the specified type of medical product tag, such as a field common to the tag information, such as the xth to yth bits being 000111. Alternatively, it may be area information, indicating that tags located in that area need to respond to the paging message and perform inventory checks.

[0045] S202, the reader receives tag information returned by multiple medical product tags, for a total of multiple tag information.

[0046] Multiple medical product labels are medical product labels of a specified type. Each label information in the multiple label information is a description of a corresponding medical product label among the multiple medical product labels. For example, each label information can describe at least one of the following for the corresponding medical product label: three methods of system integration (i.e., integration with the manufacturer's system and the hospital's HIS system), name, specifications, batch number, expiration date, applicable departments, storage conditions, product type, inventory quantity, warning status, and outbound records, etc.

[0047] S203, the reader intelligently analyzes and sorts multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored, and the multiple medical products correspond one-to-one with the multiple medical product tags.

[0048] There are two implementation methods for S203, which will be introduced below.

[0049] Method 1: For any one of the multiple tag information: The reader extracts multiple key fields from the target label information using lightweight networks (such as natural language processing algorithms (NLP)); for example, extracting "Applicable Department: Cardiology", "Product Type: Stent", and "Specification: 3.0mm" from "Coronary Artery Stent for Cardiology (Specification: 3.0mm)".

[0050] The reader maps multiple key fields to a target point cloud. For example, the reader maps each key field to a corresponding vector in the xy coordinate system (the mapping algorithm can be Word2Vec, GloVe, or FastText, etc.), resulting in multiple vectors. The starting points of these multiple vectors are all located at the origin of the xy coordinate system. The coordinates of the ending point of each vector in the xy coordinate system are used as a corresponding point cloud point, resulting in multiple point cloud points. These multiple point cloud points constitute the target point cloud.

[0051] The reader determines the target preset point cloud that best matches the target point cloud from multiple preset point clouds. These preset point clouds correspond one-to-one with multiple departments. Each preset point cloud is mapped from a key field in the label information of a medical product in stock within its corresponding department. The department corresponding to the target preset point cloud represents the stock location of the target medical product corresponding to the target label information. For example, the reader determines the target circumcircle of the target point cloud in the xy coordinate system; the reader determines the intersection area between the target circumcircle and multiple circumcircles in the xy coordinate system, where each circumcircle is the circumcircle of a corresponding preset point cloud; the preset point cloud circumscribed by the circumcircle of the intersection area among the multiple circumcircles is the target preset point cloud that best matches the target point cloud.

[0052] Method 1, by extracting "multiple key fields" (such as applicable departments, product types, and specifications) and mapping each field to a vector, essentially projects all key information about each product into a high-dimensional feature space. The final decision (point cloud matching) is based on the overall similarity of all features, rather than a single field. This significantly reduces classification errors caused by the omission or misjudgment of a single field. Furthermore, by mapping text to point clouds and using the "area of ​​intersection of circumcircles" as a similarity metric, it can capture the "distribution patterns" of different product labels in the feature space. For example, all "cardiology" products, even with different specific names, may have their point clouds clustered within a specific region in the XY coordinate system. This method better understands the essential product attribution than simple keyword matching. In reality, the description of label information may have subtle differences or be non-standard. Using the area of ​​intersection of circumcircles for comparison is a form of fuzzy matching. As long as the core distribution areas of two point clouds are close, even if the positions of individual vector points (corresponding to a non-key field) are slightly off, they may still be judged as similar. This makes the system somewhat robust to non-key differences in description.

[0053] Method 2: For any one of the multiple tag information: The reader extracts multiple key fields from the target tag information through a lightweight network. For details, please refer to the relevant introduction of Method 1 above, which will not be repeated here.

[0054] The reader determines the matching degree between multiple key fields and the corresponding key fields in each of the multiple departments. For example, for any target department among multiple departments, multiple medical products correspond to target scenarios in multiple scenarios: the reader determines the matching degree between each of the multiple key fields and the key field corresponding to the target department, obtaining multiple matching degrees; the reader performs a weighted summation of the multiple matching degrees according to the weight corresponding to the target department in the target scenario, obtaining a summed matching, where the weight corresponding to the target department is different in different scenarios. For example, suppose the scenarios include: clinical requisition scenario, warehouse inventory scenario, and emergency allocation scenario. For the clinical requisition scenario: the default sorting dimension (weight) is "applicable department matching degree (40%) + expiration date (30%) + inventory quantity (20%) + product priority (10%, such as emergency products have higher priority)"; for the warehouse inventory scenario: the default sorting dimension (weight) is "expiration warning level (40%, expiring within 1 month is a level 1 warning, 1-3 months is a level 2 warning) + inventory quantity (30%) + product type (20%) + storage conditions (10%)"; for the emergency allocation scenario: the default sorting dimension (weight) is "distance from the department in need (40%) + inventory quantity (30%) + applicable matching degree (20%) + allocation time (10%)".

[0055] Therefore, the reader determines the department with the highest matching degree among multiple departments, and the department with the highest matching degree is the inventory location of the target medical product corresponding to the target tag information.

[0056] It is understandable that, compared to Method 1 (point cloud circumcircle), Method 2 adopts a strategy based on weighted matching degree. Its technical effects are distinctly different, demonstrating significant advantages in practicality, interpretability, and flexibility, making the system no longer a rigid "one-size-fits-all" sorting approach. For example, during clinical requisition, the most applicable and most easily expired products are prioritized for doctors. During warehouse inventory checks, priority is given to products nearing their expiration date and with high inventory levels, focusing on asset management risks. During emergency allocations, priority is given to products that are closest and in sufficient quantity, focusing on response speed. This design enables the system to intelligently adapt to the complex and ever-changing needs of the medical process, achieving a leap from "static classification" to "dynamic intelligent sorting." If the system makes a sorting decision (such as prioritizing the allocation of a product to the cardiology department), managers can easily trace how this decision was made—because its "applicable department matching degree" score is high, and this field has the highest weight in the current "clinical requisition" scenario. This interpretability is crucial for fields with high reliability requirements like healthcare, facilitating manual review, verification, and trust in the system. Furthermore, Method 2 is very suitable for real-time or near-real-time systems. Low latency is a key advantage when dealing with the need for rapid sorting and location of massive amounts of medical products. At the same time, simple computational logic reduces the complexity of code implementation and the probability of errors.

[0057] In conjunction with S201-S203 above, each of the multiple label information also includes verification information for the corresponding medical product label from multiple medical product labels, resulting in a total of multiple verification information. The method further includes: The reader verifies the identity of multiple medical product labels based on multiple verification information.

[0058] Each verification message can be generated by the corresponding medical product label based on its own pre-set key. For example, the key can be used to hash a fixed parameter to obtain the verification message. Of course, the key of the medical product label is also pre-set in the reader, so the reader can also generate verification message (or verification message response) in the same way. The medical product label is then verified using the response and the verification message. The details are as follows.

[0059] The reader can divide multiple verification messages into M information groups, where M is an integer greater than or equal to 3. Any two information groups within the M information groups must contain only one identical verification message. For example, multiple verification messages include verification message #1, verification message #2, and verification message #3. The M information groups could be: information group 1 includes verification message #1 and verification message #2; information group 2 includes verification message #1 and verification message #3; and information group 3 includes verification message #2 and verification message #3.

[0060] The reader can use a lightweight network to sequentially analyze M information groups. For example, for any target information group among the M information groups: the reader concatenates the verification information contained in the target information group into a continuous information; the reader inputs the continuous information into a lightweight network (such as MLP, LightGBM, or XGBoost), obtaining a target vector sequence output by the lightweight network; the reader determines the spatial distance value (such as Euclidean distance, Manhattan distance, etc.) between the target vector sequence and the corresponding preset vector sequence. If the spatial distance value is less than the distance threshold, it indicates that there is no information anomaly in the target information group; otherwise, it indicates that there is information anomaly in the target information group. The preset vector sequence is obtained by the reader grouping the responses according to the grouping method of the M information groups after determining the corresponding responses, and then inputting them into the lightweight network for processing. For example, the reader can generate the responses of verification information #1 and verification information #2 in the same way as medical product labels, and then input the responses of verification information #1 and verification information #2 as a group into the lightweight network for processing to obtain the corresponding preset vector sequence.

[0061] The reader analyzes M information groups sequentially through a lightweight network to determine whether there are any information groups with abnormal information. If a certain verification information is tampered with, the two information groups containing that verification information will show abnormalities. In other words, information groups with abnormal information appear in pairs.

[0062] Therefore, if there is no abnormal information in the first or second information group among the M information groups, the reader determines that the medical product label corresponding to the target verification information has an information security risk, and the target verification information is the same verification information contained in the first and second information groups respectively.

[0063] It's understandable that traditional label authentication methods are inefficient when dealing with a large number of labels. This solution significantly improves authentication efficiency by grouping multiple verification messages and using a lightweight network for batch analysis. More importantly, it not only detects anomalies but also pinpoints the specific verification message (i.e., which medical product label) is faulty. This "batch processing + precise location" capability is the core advantage of the solution. The key to the solution's design is that "any two information groups contain only one identical verification message." This constructs a perfect cross-validation network. If any verification message is tampered with, all information groups containing it (two in this example) will fail verification. Since the other information groups are normal, the system can immediately pinpoint the source of the problem through logical reasoning (finding the two information groups that share the same anomalous verification message). This mechanism is highly reliable and fault-tolerant. Furthermore, using the "spatial distance" of vector sequences as the judgment criterion is a fuzzy matching method, which, compared to strict binary comparison (complete equality / inequality), may be more resistant to minor noise or errors generated during transmission. As long as the noise does not cause the spatial distance to exceed a threshold, it will not be misjudged as an anomaly.

[0064] Furthermore, the solution chooses lightweight networks (such as MLP and LightGBM) to process the information groups, rather than complex deep models, demonstrating its emphasis on computational efficiency. In other words, the reader, as an edge device, has limited computing resources. Using lightweight networks enables this advanced security verification mechanism to run in real time under resource constraints, achieving a balance between security and practicality. It transforms complex cryptographic hash comparisons into a single, efficient feedforward neural network inference.

[0065] In summary, this application has the following technical effects: 1. Improve classification accuracy and reliability, and reduce error rate. The reader automatically requests and receives tag information and processes this information using an intelligent analysis and sorting algorithm, eliminating subjective judgment factors. Intelligent analysis accurately parses tag fields (such as product name, specifications, storage conditions, etc.), avoiding misreading or omissions, thereby significantly reducing the classification error rate. The error rate is expected to be reduced to below 1%, improving the reliability and consistency of classification.

[0066] 2. Improve product search efficiency Intelligent analysis and sorting automates the processing of tag information, quickly determining the product's inventory location. The reader can process multiple tag information simultaneously, enabling batch sorting and significantly reducing classification time. Furthermore, accurate classification makes products easier to retrieve, reducing the time healthcare staff waste searching for products and improving the overall efficiency of the medical process.

[0067] 3. Enhance storage security Intelligent analysis and sorting take into account key fields in the label (such as storage conditions, expiration date, and applicable departments) to ensure that each product is assigned to an inventory location that matches its characteristics. For example, the system will automatically identify the "cold chain storage" label and direct the product to the refrigerated area, thereby ensuring product quality and patient safety and reducing medical risks.

[0068] 4. Achieve standardized and automated management This solution processes all label information using a unified intelligent analysis algorithm, achieving standardization and automation of the classification process. This not only reduces reliance on operators and lowers training costs, but also ensures the consistency and repeatability of classification results, facilitating system maintenance and expansion.

[0069] 5. Supports real-time dynamic adjustment Intelligent analysis and sorting can dynamically adjust the sorting results based on real-time received tag information, such as prioritizing products nearing their expiration date or products for departments with high demand. This flexibility improves the responsiveness of inventory management and optimizes resource allocation.

[0070] In summary, the technical solution presented in this application effectively addresses the problems of high error rates, low efficiency, and poor security caused by manual classification in the background technology through automated and intelligent tag information processing. The technical benefits are mainly reflected in classification accuracy, retrieval efficiency, storage security, standardized management, and real-time adaptability, providing a more reliable and efficient solution for medical product management.

[0071] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Exemplarily, the electronic device may be a network device, or a chip (system) or other component or assembly that can be disposed in a network device. Figure 3 As shown, the electronic device 400 may include a processor 401. Optionally, the electronic device 400 may also include a memory 402 and / or a transceiver 403. The processor 401 is coupled to the memory 402 and the transceiver 403, for example, via a communication bus.

[0072] The following is combined Figure 3 A detailed description of each component of the electronic device 400 is provided below: The processor 401 is the control center of the electronic device 400. It can be a single processor or a collective term for multiple processing elements. For example, the processor 401 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0073] Optionally, the processor 401 can perform various functions of the electronic device 400 by running or executing software programs stored in the memory 402 and calling data stored in the memory 402, such as performing the aforementioned functions. Figure 2 The method shown is an intelligent sorting method based on medical product label classification.

[0074] In a specific implementation, as one example, processor 401 may include one or more CPUs, for example... Figure 3 CPU0 and CPU1 are shown in the diagram.

[0075] In a specific implementation, as one example, the electronic device 400 may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0076] The memory 402 is used to store the software program that executes the solution of the present invention, and is controlled by the processor 401 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0077] Optionally, the memory 402 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 402 may be integrated with the processor 401 or exist independently, and may be accessed through the interface circuit of the electronic device 400. Figure 3 (Not shown in the image) is coupled to processor 401, and this embodiment of the invention does not specifically limit this.

[0078] Transceiver 403 is used for communication with other electronic devices. For example, if electronic device 400 is a terminal, transceiver 403 can be used to communicate with a network device or with another terminal device. As another example, if electronic device 400 is a network device, transceiver 403 can be used to communicate with a terminal or with another network device.

[0079] Alternatively, transceiver 403 may include a receiver and a transmitter. Figure 3 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0080] Alternatively, the transceiver 403 can be integrated with the processor 401, or it can exist independently and be connected via the interface circuit of the electronic device 400. Figure 3 (Not shown in the image) is coupled to processor 401, and this embodiment of the invention does not specifically limit this.

[0081] Understandable Figure 3 The structure of the electronic device 400 shown does not constitute a limitation on the electronic device. Actual electronic devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0082] Furthermore, the technical effects of the electronic device 400 can be referred to the technical effects of the methods described in the above method embodiments, and will not be repeated here.

[0083] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0084] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0085] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0086] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0088] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0092] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0093] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for intelligent sorting based on medical product label classification, characterized in that, An intelligent sorting system based on medical product labels is applied, the system including a reader and multiple medical product labels, the method including: The reader sends a paging message, which requests a medical product tag of a specified type to report tag information; The reader receives tag information returned by each of the multiple medical product tags, which are of a specified type. Each tag information is a description of a corresponding medical product tag among the multiple medical product tags. The reader intelligently analyzes and sorts the multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored, and the multiple medical products correspond one-to-one with the multiple medical product tags; The reader intelligently analyzes and sorts the multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored, including: For any one of the multiple tag information: The reader extracts multiple key fields from the target tag information using a lightweight network; The reader maps the multiple key fields to a target point cloud; The reader determines the target preset point cloud that best matches the target point cloud from multiple preset point clouds. The multiple preset point clouds correspond one-to-one with multiple departments. Each preset point cloud is mapped from the key field in the label information of the medical products in the inventory of the corresponding department. The department corresponding to the target preset point cloud is the inventory location of the target medical product corresponding to the target label information. The reader maps the multiple key fields to a target point cloud, including: The reader maps each of the multiple key fields to a corresponding vector in the xy coordinate system, resulting in multiple vectors. The starting points of the multiple vectors are all located at the origin of the xy coordinate system. The coordinates of the ending point of each of the multiple vectors in the xy coordinate system are used as a corresponding point cloud point, resulting in multiple point cloud points. The multiple point cloud points constitute the target point cloud.

2. The method according to claim 1, characterized in that, The reader determines the target preset point cloud that best matches the target point cloud from multiple preset point clouds, including: The reader determines the target circumcircle of the target point cloud in the xy coordinate system; The reader determines the intersection area between the target circumcircle and multiple circumcircles in the xy coordinate system, where each of the multiple circumcircles is the circumcircle of a corresponding preset point cloud among the multiple preset point clouds. The reader determines the preset point cloud circumscribed by the circumscribed circle of the intersecting area among the plurality of circumscribed circles, which is the target preset point cloud that best matches the target point cloud.

3. The method according to claim 1, characterized in that, The reader intelligently analyzes and sorts the multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored, including: For any one of the multiple tag information: The reader extracts multiple key fields from the target tag information using a lightweight network; The reader determines the degree of matching between the plurality of key fields and the key fields corresponding to each department in the plurality of departments; The reader determines the department with the highest matching degree among the multiple departments, and the department with the highest matching degree is the inventory location of the target medical product corresponding to the target tag information.

4. The method according to claim 3, characterized in that, The reader determines the matching degree between the plurality of key fields and the key fields corresponding to each department in the plurality of departments, including: For any one of the multiple departments, the multiple medical products correspond to multiple target scenarios: The reader determines the matching degree between each of the multiple key fields and the key field corresponding to the target department, thus obtaining multiple matching degrees; The reader performs a weighted summation of the multiple matching degrees based on the weight corresponding to the target department in the target scenario, to obtain a summed matching, wherein the weight corresponding to the target department is different in different scenarios among the multiple scenarios.

5. The method according to any one of claims 1-4, characterized in that, Each of the multiple label information also includes verification information for the corresponding medical product label among the multiple medical product labels, resulting in a total of multiple verification information. The method further includes: The reader verifies the identity of the multiple medical product tags based on the multiple verification information.

6. The method according to claim 5, characterized in that, The reader performs identity verification on the multiple medical product tags based on the multiple verification information, including: The reader divides the multiple verification information into M information groups, where M is an integer greater than or equal to 3, and any two information groups in the M information groups contain only one identical verification information. The reader uses a lightweight network to sequentially analyze the M information groups; The reader analyzes the M information groups sequentially through the lightweight network to determine whether there are any information groups with abnormal information among the M information groups; If there is no first information group or second information group with abnormal information among the M information groups, the reader determines that the medical product label corresponding to the target verification information has information security risks. The target verification information is the same verification information contained in the first information group and the second information group.

7. The method according to claim 6, characterized in that, The reader analyzes the M information groups sequentially through the lightweight network, including: For any one of the M information groups: The reader concatenates the verification information contained in the target information group into a continuous information; The reader inputs the continuous information into the lightweight network to obtain a target vector sequence output by the lightweight network; The reader determines the spatial distance value between the target vector sequence and the corresponding preset vector sequence. If the spatial distance value is less than a distance threshold, it indicates that there is no information anomaly in the target information group; otherwise, it indicates that there is information anomaly in the target information group.

8. A system for intelligent sorting based on medical product label classification, characterized in that, The system includes a reader and multiple medical product labels, and the system is configured to: The reader sends a paging message, which requests a medical product tag of a specified type to report tag information; The reader receives tag information returned by each of the multiple medical product tags, which are of a specified type. Each tag information is a description of a corresponding medical product tag among the multiple medical product tags. The reader intelligently analyzes and sorts the multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored, and the multiple medical products correspond one-to-one with the multiple medical product tags; The reader intelligently analyzes and sorts the multiple tag information to determine the inventory location where each of the multiple medical products needs to be stored, including: For any one of the multiple tag information: The reader extracts multiple key fields from the target tag information using a lightweight network; The reader maps the multiple key fields to a target point cloud; The reader determines the target preset point cloud that best matches the target point cloud from multiple preset point clouds. The multiple preset point clouds correspond one-to-one with multiple departments. Each preset point cloud is mapped from the key field in the label information of the medical products in the inventory of the corresponding department. The department corresponding to the target preset point cloud is the inventory location of the target medical product corresponding to the target label information. The reader maps the multiple key fields to a target point cloud, including: The reader maps each of the multiple key fields to a corresponding vector in the xy coordinate system, resulting in multiple vectors. The starting points of the multiple vectors are all located at the origin of the xy coordinate system. The coordinates of the ending point of each of the multiple vectors in the xy coordinate system are used as a corresponding point cloud point, resulting in multiple point cloud points. The multiple point cloud points constitute the target point cloud.

Images