A standardized module and method for connecting traditional Chinese medicine enterprise nodes with secondary nodes

Abstract

The present invention provides a standardized module and method for docking a Chinese medicine enterprise node with a secondary node, which solves the problem of docking a Chinese medicine enterprise node with a secondary node, and includes a receiving module, a processing module and a sending module, wherein a data parsing unit inside the receiving module is connected to an external network through an encrypted transmission unit, a data processing unit inside the processing module is connected to a data parsing unit, a data cache unit is built in the sending module and connected to the data processing unit, and a query registration unit is connected to the data cache unit. The present invention has the advantages of good docking effect and high digitization level.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial Internet, and specifically relates to a standardized module and method for docking a traditional Chinese medicine enterprise node with a secondary node. Background Art

[0002] The Industrial Internet Identification Resolution System is a global system used to manage and identify various resources in the Industrial Internet. It is similar to the domain name system in the Internet, but it identifies physical objects rather than URLs. The connection between the TCM enterprise node and the secondary node of the Industrial Internet Identification Resolution can achieve effective management and traceability of TCM resources and promote the standardization and standardization of the TCM industry. However, in the process of connecting the TCM enterprise node with the secondary node, due to the diversity of interface protocols and data formats, it often faces problems such as complex connection and low efficiency. In addition, due to the lack of a unified data format specification, the data formats sent by different enterprise nodes are different, which increases the difficulty of data parsing and processing. Some enterprise nodes lack the necessary security measures during the connection process, and there is a risk of data leakage and tampering.

[0003] In order to solve the shortcomings of the existing technology, people have conducted long-term exploration and proposed various solutions. For example, Chinese patent document CN202110846649.5 discloses an environmental governance secondary node platform based on identity resolution, which includes identity coding, adding identity coding to objects in environmental governance, identifying physical resources such as machines and products and virtual resources such as algorithms and processes through their identity coding to identify their corresponding identity symbols, identification systems, and using identification to uniquely locate and query information on machines and objects in environmental governance. It is the premise and foundation for achieving precise docking of global supply chain systems and enterprise production systems, full life cycle management of products, and intelligent services.

[0004] The above solution has solved the problem of industrial Internet identity resolution to a certain extent, but the solution still has many shortcomings, such as the lack of effective docking methods between traditional Chinese medicine enterprise nodes and secondary nodes. Summary of the invention

[0005] The purpose of the present invention is to provide a standardized module with reasonable design for docking traditional Chinese medicine enterprise nodes with secondary nodes in view of the above problems.

[0006] Another object of the present invention is to provide a method for docking a traditional Chinese medicine enterprise node with a secondary node with high docking efficiency in order to solve the above-mentioned problem.

[0007] To achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a standardized module for docking a traditional Chinese medicine enterprise node with a secondary node, comprising a receiving module, a processing module and a sending module, wherein a data parsing unit inside the receiving module is connected to an external network via an encrypted transmission unit, a data processing unit inside the processing module is connected to the data parsing unit, a data caching unit is built in the sending module and is connected to the data processing unit, and the data caching unit is connected to a query registration unit.

[0008] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, the following steps are included:

[0009] S1: Define nodes and determine the secondary node framework structure;

[0010] S2: Design the node hierarchy and determine the node hierarchy structure according to the requirements of the Industrial Internet;

[0011] S3: Define data fields, and the Chinese medicine industry determines the relevant data fields for each secondary node;

[0012] S4: Build the relationship between data and determine the connection method of different data nodes;

[0013] S5: Set the node management level and determine the management authority of different node levels;

[0014] S6: Introduce data verification mechanism to verify data consistency and specification accuracy.

[0015] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, step S1 includes the following steps:

[0016] S11: The secondary node framework is divided into management system, function system, application system and security system. The management system manages the node naming, and the node naming rules are formulated by the traditional Chinese medicine industry;

[0017] S12: Determine the naming rules for major category nodes, using the combination of TCM categories and secondary node responsible entities. TCM categories include innovative TCM drugs, improved TCM new drugs, classic prescription TCM drugs, and natural medicines;

[0018] S13: Determine the naming rules for subcategory nodes, using the common name of Chinese medicine, prescription, dosage form, main functions, usage and daily dosage of herbal medicine with the same name and prescription and combination.

[0019] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, the functional system in step S11 includes identification registration, identification resolution, identification query, data management, business management and operation monitoring, and the application system includes traditional Chinese medicine planting traceability, medicinal material logistics tracking, traditional Chinese medicine processing management, and drug research and development design.

[0020] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, the node hierarchy structure in step S2 includes four levels: edge layer, IaaS, PaaS and SaaS.

[0021] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, step S3 includes the following steps:

[0022] S31: perform data collection and preprocessing, import Chinese medicine images and perform data cleaning, convert the data set format and adjust the image to the specified specifications;

[0023] S32: Perform model training and call the data set to perform YOLOv8 model training;

[0024] S33: Evaluate and test the training results, use the loss function to judge the model training status, and use the built-in evaluation indicators to judge the accuracy;

[0025] S34: Identify the traditional Chinese medicine and determine the data field. Use the YOLOv8 model to identify the traditional Chinese medicine image and determine the data field.

[0026] In the above-mentioned method for docking a traditional Chinese medicine enterprise node with a secondary node, the traditional Chinese medicine data field in step S34 includes basic data on drug specifications, price rules, pharmaceutical rules and medical insurance rules, wherein the basic data on drug specifications includes unified code, release date, release type, generic name, specification, year, category, preparation method, origin, manufacturer, packaging unit and net content.

[0027] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, step S4 includes the following steps:

[0028] S41: Use clustering algorithm to obtain knowledge graph data of similar Chinese medicines;

[0029] S42: Add force based on the data field of the node, and apply new force on the traditional force-directed layout algorithm;

[0030] S43: edge binding and data interaction are performed. Nodes with the same data field are arranged in the same relationship chain, and relationship chains with the same force direction gather when they are close to the node;

[0031] S44: People in the traditional Chinese medicine industry provide feedback on the connection methods of data nodes.

[0032] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, the node management hierarchy in step S5 includes an access layer, a convergence layer and a core layer, wherein the access layer performs user access, the convergence layer performs data classification, filtering and forwarding, and the core layer is used for high-speed data transmission and exchange.

[0033] In the above-mentioned method for connecting a traditional Chinese medicine enterprise node with a secondary node, step S6 verifies the data submission rate, the data field and node matching rate, and the data upload approval rate.

[0034] Compared with the existing technology, the advantages of the present invention are: through standardized interface protocols and data formats, the present invention can significantly improve the data docking efficiency between enterprise nodes and secondary nodes, and reduce the workload of interface development and maintenance; a variety of security measures can be adopted, including two-way authentication, data encryption and signature, etc., to ensure the security and integrity of data transmission, and reduce the risk of data leakage and tampering; it provides unified standards and specifications for the docking of enterprise nodes with secondary nodes, promotes the digitalization and standardization development of the traditional Chinese medicine industry, and improves the information management level of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the structure of the standardized module of the present invention.

[0036] Figure 2 It is a flow chart of the docking method of the present invention.

[0037] Figure 3 It is a schematic diagram of the secondary node framework of the present invention.

[0038] Figure 4 It is a data node connection flow chart of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] like Figure 1-4 As shown, a standardized module for docking a Chinese medicine enterprise node with a secondary node includes a receiving module, a processing module and a sending module. The data parsing unit inside the receiving module is connected to the external network through an encrypted transmission unit. The receiving module is used to receive identification data from the enterprise node, and a unified interface protocol (such as RESTful API) and data format (such as JSON) are used to ensure the readability and compatibility of the data. The data processing unit inside the processing module is connected to the data parsing unit. The processing module is used to verify and convert the received identification data, and standardized data verification rules and conversion algorithms are used to ensure the accuracy and consistency of the data. The processing module also has data encryption and signature functions to ensure the security of data transmission. The sending module has a built-in data cache unit and is connected to the data processing unit. The data cache unit is connected to a query registration unit. The sending module is used to send the processed data to the secondary node, and a unified interface protocol and data format are used to ensure the timeliness and security of the data. The sending module supports two-way authentication and encrypted transmission to ensure the security and reliability of the communication process.

[0041] Specifically, in this embodiment, the secondary node mainly provides identification services for multiple industries such as Chinese medicine planting, processing, packaging and sales, and provides docking for the upper-level national top-level node, allocates identification changes for downstream enterprises, and provides identification registration, identification resolution, and identification data reset, which specifically includes the following steps:

[0042] S1: Define nodes and determine the secondary node framework structure;

[0043] S2: Design the node hierarchy and determine the node hierarchy structure according to the requirements of the Industrial Internet;

[0044] S3: Define data fields, and the Chinese medicine industry determines the relevant data fields for each secondary node;

[0045] S4: Build the relationship between data and determine the connection method of different data nodes;

[0046] S5: Set the node management level and determine the management authority of different node levels;

[0047] S6: Introduce data verification mechanism to verify data consistency and specification accuracy.

[0048] In-depth, step S1 constructs a secondary node framework, which gives unique identification to each element of the traditional Chinese medicine industry, relies on multiple carriers such as QR codes, radio frequency sensing, and smart terminals to expand the service scope of the industrial Internet for traditional Chinese medicine companies, and improves the efficiency of traditional Chinese medicine data collection, including the following steps:

[0049] S11: The secondary node framework is divided into management system, function system, application system and security system. The management system manages the node naming. The node naming rules are formulated by the traditional Chinese medicine industry. The naming adopts the principle of non-exclusivity. Multiple different secondary nodes can be established in the same industry, but the responsible subject is introduced in the naming rules of major categories and minor categories.

[0050] S12: Determine the naming rules for major category nodes, using the combination of TCM categories and secondary node responsible entities. TCM categories include innovative TCM drugs, improved TCM new drugs, classic prescription TCM drugs, and natural medicines. The naming rules for major category nodes can be expanded to chemical drugs, biopharmaceuticals and other industries according to actual needs.

[0051] S13: Determine the naming rules for subcategory nodes, using the common name of Chinese medicine, prescription, dosage form, main functions, usage and daily dosage of herbal medicine with the same name and prescription and combination.

[0052] Furthermore, the functional system in step S11 includes identification registration, identification resolution, identification query, data management, business management and operation monitoring, and the application system includes Chinese medicine planting traceability, medicinal material logistics tracking, Chinese medicine processing management, and drug research and development design.

[0053] Furthermore, the node hierarchy structure in step S2 includes four levels: edge layer, IaaS, PaaS and SaaS. The IaaS layer is closest to the server hardware resources, so that users can access the network itself with the greatest degree of freedom. The PaaS layer hides the underlying network, storage, operating system and other technical issues from users, that is, the underlying service is transparent to users, and what is open to users is the development and operation environment of the software itself; in the SaaS layer, users can customize the business model from suppliers through the network according to their own needs, and multiple levels are combined to realize the combination of secondary nodes and cloud networks.

[0054] In addition, step S3 performs intelligent identification of traditional Chinese medicine, thereby realizing the rapid definition of node data fields and improving the digital efficiency of the traditional Chinese medicine industry. It specifically includes the following steps:

[0055] S31: perform data collection and preprocessing, import Chinese medicine images and perform data cleaning, convert the data set format and adjust the image to the specified specifications;

[0056] S32: Perform model training and call the dataset to train the YOLOv8 model. Compared with the previous YOLO model, a new backbone network, Ancher-Free detection head and loss function are introduced;

[0057] S33: Evaluate and test the training results, use the loss function to judge the model training status, and use the built-in evaluation indicators to judge the accuracy; for each category of targets, first calculate the confidence of each detection result and the accuracy of the corresponding prediction box. Sort the detection results according to the confidence, usually from high to low.

[0058] Different thresholds (usually 0.5) are used as the IOU (Intersection over Union) thresholds to calculate the Precision-Recall curve for each category. On the Precision-Recall curve, the average precision (Average Precision) at different recall rates (Recall) is calculated. The average precision of all categories is averaged to obtain the mAP0.5 indicator. The value range of mAP0.5 is 0 to 1. The higher the value, the better the performance of the detection algorithm in the target detection task. It comprehensively considers the precision and recall of different categories of targets, and sorts and evaluates the detection results.

[0059] S34: Identify Chinese medicine and determine data fields. Use the YOLOv8 model to identify Chinese medicine images and determine data fields. Enterprises can also use this system to inspect the quality of medicinal materials. In addition to being used for rapid identification of data fields at secondary nodes, the above Chinese medicine identification model can also be used for internal identification data services at enterprise nodes.

[0060] At the same time, the traditional Chinese medicine data field in step S34 includes basic data on drug specifications, price rules, pharmaceutical rules and medical insurance rules, among which the basic data on drug specifications include unified code, release date, release type, generic name, specification, year, category, preparation method, origin, manufacturer, packaging unit and net content.

[0061] The above-mentioned basic data of drug specifications are in text form, in which the unified code is used as a unique identification code to associate with other rule information data tables. The release date and release type determine the release information of the basic data of drug specifications. Subsequent data items such as generic names and specifications are also in text or numerical form.

[0062] It can be seen that before building the relationship between the data, step S4 needs to perform corresponding data preparation, and needs to remove null values ​​and obvious erroneous data, which specifically includes the following steps:

[0063] S41: using a clustering algorithm to obtain knowledge graph data of similar Chinese medicines, wherein the knowledge graph data of Chinese medicines includes the common names, prescriptions, dosage forms, functions and indications, usage and daily dosage of the above Chinese medicines and the forms of the same name and prescription and combination;

[0064] S42: Add force according to the data field of the node, and apply new force on the traditional force-directed layout algorithm; the traditional force-directed layout is represented by G=(V,E), where V is the set of vertices and E is the combination of edges between V. Different nodes produce displacement and velocity under the interaction of forces. The layout formula is as follows:

[0065] F(V,E)=aM*FM+(1-aM)FL;

[0066] Where F is the resultant force, Fm is the multi-body force between all nodes, FL is the connection force between nodes with relationships, aM is the parameter of the FM force, and FM and FL constitute the node resultant force.

[0067] S43: edge binding and data interaction are performed. Nodes with the same data field are arranged in the same relationship chain. Relationship chains with the same force direction gather when they are close to the node. In this embodiment, new forces are introduced on the basis of force-directed layout, including repulsive force FAE, labeling force FLL and node force FND. The specific FND*F(V,E) is as follows:

[0068] F(V,E)=aM*FM+aL*FL+aAE*FAE+aLL*FLL+aND*FND;

[0069] aM+aL+aAE+aLL+aND=1;

[0070] Among them, FL is the connection force between nodes in the force-directed method, and FAE, FLL and FND are new forces.

[0071] S44: Personnel in the traditional Chinese medicine industry provide feedback on the connection method of the data nodes, thereby manually correcting the connection method of the data nodes.

[0072] Obviously, the node management level in step S5 includes the access layer, the aggregation layer and the core layer, wherein the access layer performs user access, the aggregation layer performs data classification, filtering and forwarding, and the core layer is used for high-speed data transmission and exchange. In this embodiment, the secondary node bandwidth resources should have 2-3 times redundancy on the basis of meeting the 10,000 QPS identity resolution. On the basis of meeting the basic bandwidth resource requirements, the secondary node can be equipped with the bandwidth resources required for the service according to the actual situation of the identity application.

[0073] Preferably, step S6 verifies the data reporting rate, the data field and node matching rate, and the data upload bid rate. In addition, data verification relies on security protection mechanisms such as data classification, data encryption, integrity protection, backup, and safe destruction.

[0074] To sum up, the principle of this embodiment is that the receiving module accepts the traditional Chinese medicine industry data through the encrypted transmission unit, the data processing unit processes it, the data cache unit performs identification registration, and the query registration unit provides an identification query function and returns an indication of successful registration.

[0075] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in similar ways, but they will not deviate from the spirit of the present invention or exceed the scope defined by the appended claims.

[0076] Although the terms such as enterprise node and secondary node are used more frequently in this article, the possibility of using other terms is not excluded. These terms are used only to more conveniently describe and explain the essence of the present invention; interpreting them as any additional restrictions is contrary to the spirit of the present invention.

Claims

1. A docking method using a standardized module for docking a Chinese medicine enterprise node with a secondary node, wherein the standardized module comprises a receiving module, a processing module and a sending module, wherein a data parsing unit inside the receiving module is connected to an external network via an encrypted transmission unit, a data processing unit inside the processing module is connected to a data parsing unit, a data cache unit is built in the sending module and is connected to the data processing unit, and the data cache unit is connected to a query registration unit, characterized in that: The docking method comprises the following steps: S1: Define nodes and determine the secondary node framework structure; S11: The secondary node framework is divided into management system, function system, application system and security system. The management system manages the node naming, and the node naming rules are formulated by the traditional Chinese medicine industry; S12: Determine the naming rules for major category nodes, using the combination of TCM categories and secondary node responsible entities. TCM categories include innovative TCM drugs, improved TCM new drugs, classic prescription TCM drugs, and natural medicines; S13: Determine the naming rules for sub-category nodes, using the common name of Chinese medicine, prescription, dosage form, function, usage and daily dosage of decoction pieces with the same name and prescription and combination; S2: Design the node hierarchy and determine the node hierarchy structure according to the requirements of the Industrial Internet; S3: Define data fields, and the Chinese medicine industry determines the relevant data fields for each secondary node; S31: perform data collection and preprocessing, import Chinese medicine images and perform data cleaning, convert the data set format and adjust the image to the specified specifications; S32: Perform model training and call the data set to perform YOLOv8 model training; S33: Evaluate and test the training results, use the loss function to judge the model training status, and use the built-in evaluation indicators to judge the accuracy; S34: Perform Chinese medicine identification and determine data fields, and use the YOLOv8 model to identify Chinese medicine images and determine data fields; S4: Build the relationship between data and determine the connection method of different data nodes; S41: Use clustering algorithm to obtain knowledge graph data of similar Chinese medicines; S42: Add force based on the data field of the node, and apply new force on the traditional force-directed layout algorithm; S43: edge binding and data interaction are performed. Nodes with the same data field are arranged in the same relationship chain, and relationship chains with the same force direction gather when they are close to the node; S44: The Chinese medicine industry personnel provide feedback on the connection method of the data nodes; S5: Set the node management level and determine the management authority of different node levels; S6: Introduce data verification mechanism to verify data consistency and specification accuracy; The node hierarchy structure in step S2 includes four levels: edge layer, IaaS, PaaS and SaaS; In step S5, the node management hierarchy includes an access layer, a convergence layer and a core layer, wherein the access layer performs user access, the convergence layer performs data classification, filtering and forwarding, and the core layer is used for high-speed data transmission and exchange.

2. A docking method using a standardized module for docking a traditional Chinese medicine enterprise node with a secondary node according to claim 1, characterized in that: The functional system in step S11 includes identification registration, identification resolution, identification query, data management, business management and operation monitoring, and the application system includes Chinese medicine planting traceability, medicinal material logistics tracking, Chinese medicine processing management, and drug research and development design.

3. A docking method using a standardized module for docking a traditional Chinese medicine enterprise node with a secondary node according to claim 1, characterized in that: The traditional Chinese medicine data fields in step S34 include basic data on drug specifications, price rules, pharmaceutical rules and medical insurance rules, wherein the basic data on drug specifications include unified coding code, release date, release type, generic name, specification, year, category, preparation method, origin, manufacturer, packaging unit and net content.

4. A docking method using a standardized module for docking a Chinese medicine enterprise node with a secondary node according to claim 1, characterized in that: The step S6 checks the data submission rate, the data field and node matching rate, and the data upload approval rate.

Images