Clinical examination data management method and system based on artificial intelligence

Abstract

The invention belongs to the technical field of data management, and discloses a clinical examination data management method and system based on artificial intelligence. The method comprises the following steps that a cloud data center constructs a clinical examination data management engine and a clinical examination knowledge graph, and deploys a block chain storage network; the data server is used for uploading the real-time clinical examination data to the cloud data center by using an OPC UA protocol; the cloud data center is used for performing standardization processing by using a clinical examination data management engine; the cloud data center is used for performing semantic extension by using a clinical examination data management engine according to the clinical examination knowledge graph; the cloud data center is used for performing data analysis by using a clinical examination data management engine; the cloud data center carries out encryption; and the cloud data center is used for storing data by using a block chain storage network. According to the invention, the problems of high management difficulty, low data security and poor analysis accuracy in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data management, and particularly relates to a clinical test data management method and system based on artificial intelligence. Background Art

[0002] Clinical test is an important branch in the medical field, mainly involving laboratory tests on samples such as blood, body fluids, and tissues of patients to assist in disease diagnosis, condition monitoring, and treatment effect evaluation. Clinical test data refers to the information obtained from samples (such as blood, urine, tissues, etc.) collected from patients through laboratory test means and used for aspects such as disease diagnosis, condition monitoring, and treatment effect evaluation.

[0003] Clinical test data is an important basis for medical diagnosis, treatment, and disease prevention. With the continuous development of medical technology and the acceleration of the informatization process, the volume of clinical test data shows exponential growth, and clinical test data involves patients' privacy information. Therefore, the management of clinical test data has become increasingly important. However, the existing clinical test data management technologies have exposed many defects in practical applications, specifically including: 1) Difficult management: In the existing technology, the formats, units, naming specifications, etc. of clinical test data from different data sources are often inconsistent, resulting in difficulties in data integration and comparison. The lack of a unified data standardization process makes it difficult to exchange and share data, increasing the management difficulty of clinical test data; 2) Low data security: Traditional databases use a centralized storage method, which is easily a single target for hacker attacks. Once breached, a large amount of data may be leaked, posing a security risk for centralized storage; 3) Poor analysis accuracy: Traditional data analysis methods often rely on manual experience or simple statistical tools, unable to deeply mine and predict data, lacking the ability of deep learning and big data analysis, resulting in inaccurate and incomplete analysis results and being difficult to meet complex clinical needs. Summary of the Invention

[0004] In order to solve the problems of difficult management, low data security, and poor analysis accuracy existing in the prior art, the purpose of the present invention is to provide a clinical test data management method and system based on artificial intelligence.

[0005] The technical solution adopted by the present invention is as follows: A clinical test data management method based on artificial intelligence, comprising the following steps: A cloud data center, using artificial intelligence algorithms, constructs a clinical test data management engine and a clinical test knowledge graph, and uses blockchain technology to deploy a blockchain storage network; A data server collects real-time clinical test data and uploads the real-time clinical test data to the cloud data center using the OPC UA protocol; The cloud data center uses a clinical test data management engine to standardize the real-time clinical test data from different data sources to obtain standard real-time clinical test data; The cloud data center semantically expands the standard real-time clinical test data using the clinical test knowledge graph and the clinical test data management engine to obtain extended real-time clinical test data; The cloud data center uses the clinical test data management engine to perform data analysis on the extended real-time clinical test data to obtain corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results; The cloud data center encrypts the extended real-time clinical test data using the corresponding encryption key according to the real-time open permissions to obtain encrypted real-time clinical test data, and performs controlled management on the encryption key; The cloud data center uses a blockchain storage network to store the encrypted real-time clinical test data, the corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results.

[0006] Furthermore, the cloud data center uses artificial intelligence algorithms to build a clinical test data management engine and a clinical test knowledge graph, and uses blockchain technology to deploy a blockchain storage network, including the following steps: The cloud data center collects a number of clinical test knowledge and a number of historical clinical test data, and performs preprocessing to obtain a number of preprocessed clinical test knowledge and a number of preprocessed historical clinical test data; According to a number of preprocessed clinical test knowledge, use natural language processing algorithms to build a named entity and entity relationship extraction model, and obtain a clinical test knowledge graph; According to a number of preprocessed historical clinical test data, use a deep learning and reinforcement learning fusion algorithm to build a standardization processing model, and generate a number of standard historical clinical test data; According to the clinical test knowledge graph, semantically expand a number of standard historical clinical test data to obtain a number of extended historical clinical test data; According to a number of extended historical clinical test data, use a multi-output deep learning algorithm to build a data analysis model; Integrate the named entity and entity relationship extraction model, the standardization processing model, and the data analysis model to obtain a clinical test data management engine; Distributively connect a number of data nodes in the cloud data center to build a blockchain consensus network, and set up an IPFS system and a smart contract for the blockchain consensus network to obtain a blockchain storage network.

[0007] Furthermore, according to a number of pre - processed clinical test knowledge, using natural language processing algorithms, construct a named entity and entity relationship extraction model, and obtain a clinical test knowledge graph, including the following steps: Use natural language processing algorithms to construct an initial named entity and entity relationship extraction model; According to a number of pre - processed clinical test knowledge, optimize and train the initial named entity and entity relationship extraction model to obtain a final named entity and entity relationship extraction model, and generate a number of knowledge named entities and a number of knowledge entity relationships; According to a number of knowledge named entities and a number of knowledge entity relationships, conduct knowledge graph construction to obtain a clinical test knowledge graph.

[0008] Furthermore, the named entity and entity relationship extraction model is constructed based on the BERT - CRF - SVM algorithm; The standardization processing model is constructed based on the GCN - MOPPO - SPA algorithm; The data analysis model is constructed based on the GCN - Attention - DBN algorithm.

[0009] Furthermore, a data server collects real - time clinical test data and uses the OPC UA protocol to upload the real - time clinical test data to the cloud data center, including the following steps: The data server constructs an OPC UA information model according to historical clinical test data, extracts the model metadata of the OPC UA information model, and sends the model metadata to the cloud data center; The cloud data center deploys an OPC UA server and constructs an OPC UA instance in the address space of the OPC UA server according to the model metadata; The data server collects the original real - time clinical test data according to the OPC UA information model and uses the OPC UA protocol to upload the original real - time clinical test data to the cloud data center; The cloud data center writes the original real - time clinical test data into the OPC UA instance and obtains the final real - time clinical test data based on the OPC UA instance.

[0010] Furthermore, the cloud data center uses a clinical test data management engine to standardize the real - time clinical test data from different data sources to obtain standard real - time clinical test data, including the following steps: The cloud data center extracts the real - time clinical test data of the OPC UA instances from different data sources and inputs the real - time clinical test data into the standardization processing model of the clinical test data management engine; Using a standardized processing model, extract the first real-time graph structure features of real-time clinical test data; According to the first real-time graph structure features, generate a standardized processing strategy to obtain a real-time standardized processing strategy; According to the real-time standardized processing strategy, extract the corresponding several target SPA algorithms; According to the several target SPA algorithms, perform standardized processing on the real-time clinical test data to obtain the corresponding standard real-time clinical test data.

[0011] Furthermore, the cloud data center, according to the clinical test knowledge graph, uses the clinical test data management engine to perform semantic expansion on the standard real-time clinical test data to obtain the expanded real-time clinical test data, including the following steps: The cloud data center inputs the standard real-time clinical test data into the named entity and entity relationship extraction model of the clinical test data management engine; Use the named entity and entity relationship extraction model to extract the real-time semantic features of the standard real-time clinical test data; According to the real-time semantic features, obtain the corresponding several data named entities; Obtain the similarity between each data named entity and several knowledge named entities in the clinical test knowledge graph, and use the knowledge named entity with the highest similarity as the first target knowledge named entity of the data named entity; Use the several knowledge entity relationships of the first target knowledge named entity as the several target knowledge entity relationships of the data named entity, and use the knowledge named entity on the other side of the target knowledge entity relationship as the second target knowledge named entity of the data named entity; According to the first target knowledge named entity, several target knowledge entity relationships and several second target knowledge named entities of each data named entity, perform semantic expansion on the standard real-time clinical test data to obtain the expanded real-time clinical test data.

[0012] Furthermore, the cloud data center uses the clinical test data management engine to perform data analysis on the expanded real-time clinical test data to obtain the corresponding real-time retrieval tags, real-time open permissions and real-time data analysis results, including the following steps: The cloud data center inputs the expanded real-time clinical test data into the data analysis model of the clinical test data management engine; Extract the second real-time graph structure features of the expanded real-time clinical test data; According to the preset first attention weight value, perform weighted fusion on the second real-time graph structure features to obtain the first real-time weighted fusion features; According to the preset second attention weight value, perform weighted fusion on the second real-time graph structure features to obtain the second real-time weighted fusion features; According to the preset third attention weight value, the second real-time graph structure features are weighted and fused to obtain the third real-time weighted fusion features; According to the first real-time weighted fusion features, retrieval tags are generated to obtain corresponding real-time retrieval tags; According to the second real-time weighted fusion features, open permissions are generated to obtain corresponding real-time open permissions; According to the third real-time weighted fusion features, data analysis is performed to obtain corresponding real-time data analysis results.

[0013] Furthermore, the cloud data center uses a blockchain storage network to store encrypted real-time clinical test data, corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results, including the following steps: The cloud data center stores the encrypted real-time clinical test data into the IPFS system of the blockchain storage network to obtain a real-time data hash value, and uses a smart contract to generate a real-time storage request; The real-time storage request is sent to the blockchain consensus network of the blockchain storage network, and the data node that receives the real-time storage request is used as the primary node; Based on the primary node, a consensus algorithm is used to broadcast a pre-prepared message to other data nodes and verify the legality of the real-time storage request; If the legality verification passes, the primary node is used to broadcast a prepare message containing the voting information of the primary node to other data nodes, and the prepare message is written into the message log; Based on all data nodes, confirmation messages are exchanged. If the primary node receives more than the quantity threshold of confirmation messages, the consensus is successful, and the real-time consensus timestamp is extracted. Otherwise, the consensus fails; After the consensus is successful, a smart contract is used to generate real-time transaction data according to the real-time storage request, real-time consensus timestamp, and real-time data hash value; The primary node is used to convert the real-time transaction data into a data block, and the blockchain consensus network is used to link and chain the data block.

[0014] An artificial intelligence-based clinical test data management system for implementing a clinical test data management method. The system includes a cloud data center and several data servers. The several data servers are all communicatively connected to the cloud data center. The cloud data center is provided with a clinical test data management engine and a clinical test knowledge graph, and the cloud data center includes an initialization unit, a standardization processing unit, a semantic extension unit, a data analysis unit, a data encryption unit, and a data storage unit that are connected in sequence.

[0015] The beneficial effects of the present invention are: The present invention discloses a method and system for managing clinical test data based on artificial intelligence. By constructing a unified OPC UA information model, it realizes standardized data transmission between the cloud data center and different data sources, simplifies the subsequent standardized processing flow, improves the transmission efficiency, and performs data standardization processing through the clinical test data management engine to achieve a unified format and specification for data from different data sources, eliminate data heterogeneity, improve the efficiency of data processing and analysis, reduce the difficulty of data management, and has a high degree of automation. It can automatically complete steps such as data collection, upload, standardization processing, semantic expansion, data analysis, and storage, reduce manual intervention, and improve work efficiency. A blockchain storage network constructed using blockchain technology is used for data storage to achieve decentralized storage and distributed management of data, effectively prevent data leakage and illegal access, and improve data security. Semantic expansion is performed on clinical test data by combining clinical test data with a clinical knowledge graph to enrich data semantic information, improve the depth and breadth of data analysis, and through the clinical test data management engine, in-depth mining and prediction are performed on clinical test data to improve the accuracy and comprehensiveness of analysis results, providing a more reliable basis for subsequent clinical diagnosis, treatment, and prevention.

[0016] Other beneficial effects of the present invention will be further described in the specific implementation manner. Brief Description of the Drawings

[0017] Figure 1 is a flowchart of the method for managing clinical test data based on artificial intelligence in the present invention.

[0018] Figure 2 is a structural block diagram of the system for managing clinical test data based on artificial intelligence in the present invention. Specific Embodiment

[0019] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0020] Embodiment 1: As Figure 1 shown, this embodiment provides a method for managing clinical test data based on artificial intelligence, including the following steps: S1: The cloud data center uses artificial intelligence algorithms to construct a clinical test data management engine and a clinical test knowledge graph, and uses blockchain technology to deploy a blockchain storage network, including the following steps: S1-1: The cloud data center collects a number of clinical test knowledge and a number of historical clinical test data, and performs preprocessing to obtain a number of preprocessed clinical test knowledge and a number of preprocessed historical clinical test data; In this embodiment, clinical test data is collected through the Open Platform Communications Unified Architecture (OPC UA) protocol. Therefore, the clinical test data itself is a graph-structured data. The data included in the clinical test data are patient information: name, age, gender, medical record number, etc.; test items: such as blood routine, urine routine, biochemical indicators, etc.; test results: specific numerical or qualitative results, such as white blood cell count, blood glucose level, positive / negative, etc.; time stamps: the specific time of data collection, device information: the device number, model, etc. of the data collection device, quality information: the quality status of the data, such as valid, invalid, requiring reexamination, etc.; the nodes and edges included in the graph structure are patient nodes: representing patients, including basic patient information; test item nodes: representing specific test items, such as blood routine; test result nodes: representing specific test results, such as white blood cell count; device nodes: representing data collection devices, including device information; time nodes: representing the time points of data collection; quality nodes: representing the quality status of the data; alarm and event nodes: representing abnormal alarms and events; the edge types are, patient-test item edge: indicating which test items the patient has undergone; test item-test result edge: indicating the specific result corresponding to a certain test item; device-test result edge: indicating the test results collected by a certain device; time-test result edge: indicating the time when the test results were collected; quality-test result edge: indicating the quality status of the test results; The preprocessing includes data cleaning, error data screening and other processing of the original data to improve the data quality and provide data support for subsequent model construction; S1-2: According to a number of preprocessed clinical test knowledge, use natural language processing algorithms to construct a named entity and entity relationship extraction model, and obtain a clinical test knowledge graph, including the following steps: S1-2-1: Use natural language processing algorithms to construct an initial named entity and entity relationship extraction model; The named entity and entity relationship extraction model is constructed based on the Bidirectional Encoder Representations from Transformers (BERT)-Conditional Random Fields (CRF)-Support Vector Machine (SVM) algorithm, and the named entity and entity relationship extraction model includes a semantic feature extraction module constructed based on the BERT algorithm, a named entity extraction module constructed based on the CRF algorithm, and an entity relationship extraction module constructed based on the SVM algorithm that are connected in sequence; The BERT module can capture the deep semantic information in knowledge texts, which is very useful for identifying different types of knowledge named entities (such as clinical test terms, clinical test component names, etc.). The CRF module can consider the dependencies between adjacent knowledge named entity tags, which can help the model learn the sequence dependencies of entity tags, thereby improving the accuracy of named entity annotation and realizing the extraction of knowledge named entities. The entity relationship extraction module is mainly used to classify the relationships of the extracted named entity pairs, judge whether there is a specific relationship between them, and the type of the relationship, and convert the named entities and their context information into high-dimensional feature vectors, which can effectively represent the relationships between entities. By combining the deep semantic information extracted by BERT and the sequence dependencies considered by CRF, complex entity relationships can be processed more effectively. S1-2-2: Optimize and train the initial named entity and entity relationship extraction model according to a number of preprocessed clinical test knowledge to obtain the final named entity and entity relationship extraction model, and generate a number of knowledge named entities and a number of knowledge entity relationships. S1-2-3: Construct a knowledge graph according to a number of knowledge named entities and a number of knowledge entity relationships to obtain a clinical test knowledge graph. S1-3: According to a number of preprocessed historical clinical test data, use a deep learning and reinforcement learning fusion algorithm to construct a standardized processing model and generate a number of standard historical clinical test data. The standardized processing model is constructed based on the Graph Convolutional Network (GCN)-Multi-Objective Proximal Policy Optimization (MOPPO)-Standardized Processing Algorithm (SPA) algorithm, and the standardized processing model includes a first graph structure feature extraction module constructed based on the GCN algorithm, a standardized processing strategy generation module constructed based on the MOPPO algorithm, and a standardized processing algorithm that stores a number of SPA algorithms. The standardized processing strategy generation module includes a set of objective functions, an experience replay pool, an Actor network, a Critic network, and an agent, and the agent is respectively connected to the set of objective functions, the experience replay pool, the Actor network, and the Critic network. The first graph structure feature extraction module extracts the graph structure features in the clinical test data, converts the relationships between nodes into feature representations that can be used for model learning. The first graph structure feature extraction module uses a graph convolutional network to capture the complex dependencies between nodes, enhance the expression ability of features, effectively utilize the graph structure information, improve the model's understanding ability of complex relationships, and provide rich input information for the standardized processing strategy generation module; The Actor network of the standardized processing strategy generation module is responsible for outputting the probability distribution of the actions that should be taken in a given state. The goal is to learn an optimal strategy, that is, to maximize the long-term cumulative reward. In a continuous action space, the Actor network usually outputs a mean value and an optional variance parameter to describe the probability distribution of actions. The Critic network is responsible for evaluating the value of a given state, that is, predicting the expected return that can be obtained starting from this state and following the current strategy, and usually outputs a scalar value representing the value of the state or the state-action value. The experience replay pool is used to store historical experiences for reuse during the training process. The set of objective functions includes functions that define multiple standardized processing objectives, including minimizing the standardized processing time cost, minimizing the standardized processing computing resource cost, and maximizing the standardized processing efficiency, etc. It can generate a standardized processing strategy based on the graph structure features to guide how to standardize the data. The standardized processing strategy includes several call decisions for the SPA algorithm; The standardized processing algorithm stores several SPA algorithms, which are used to accept call decisions and standardize the clinical test data. The SPA algorithms include normalization algorithms, format conversion algorithms, sequence conversion algorithms, regularization algorithms, discretization algorithms, etc. The purpose is to convert the original data into a standard format so that the subsequent model can process it more effectively; S1-4: According to the clinical test knowledge graph, semantically expand several standard historical clinical test data to obtain several expanded historical clinical test data; S1-5: Integrate the named entity and entity relationship extraction model, the standardized processing model, and the data analysis model to obtain a clinical test data management engine; S1-6: According to several expanded historical clinical test data, use a multi-output deep learning algorithm to construct a data analysis model; The data analysis model is constructed based on the GCN-Attention-Deep Belief Network (DBN) algorithm. The data analysis model includes a second graph structure feature extraction module constructed based on the GCN algorithm, an attention weight module constructed based on the Attention mechanism, a retrieval label generation module constructed based on the DBN algorithm, an open permission generation module constructed based on the DBN algorithm, and a data analysis module constructed based on the DBN algorithm. The second graph structure feature extraction module is connected to the attention weight module. The attention weight module is provided with a first weighted fusion channel, a second weighted fusion channel, and a third weighted fusion channel in parallel. The first weighted fusion channel is connected to the retrieval label generation module, the second weighted fusion channel is connected to the open permission generation module, and the third weighted fusion channel is connected to the data analysis module; The second graph structure feature extraction module extracts graph structure features from the extended clinical test data, uses GCN to capture the complex relationships between nodes, effectively utilizes the graph structure information, enhances the expression ability of features, provides rich and structured feature representations for subsequent modules, and improves the model's understanding and analysis ability of complex clinical data; The attention weight module assigns attention weights to different features, highlights important information, and realizes multi-angle feature fusion through multiple parallel weighted fusion channels, improves the model's attention to key information, enhances the analysis accuracy, increases the flexibility and adaptability of the model, enriches the feature representation through multi-channel fusion, and improves the model performance; The retrieval label generation module uses the deep belief network to generate retrieval labels for quickly locating and retrieving relevant data, improves the efficiency and accuracy of data retrieval, provides fast and accurate information retrieval services, and automatically discovers potential patterns and relationships in the data; The open permission generation module generates data open permissions, ensures data security and privacy protection, realizes fine-grained access control of data, guarantees data security, improves the flexibility and operability of data sharing, and reduces management costs and human errors through automatic permission generation; The data analysis module deeply analyzes the data after feature extraction and weighted fusion, generates valuable data analysis results, such as trend prediction, anomaly detection, etc., provides comprehensive and in-depth data analysis services, provides scientific and accurate basis for clinical decision-making, and mines the potential in the data; S1-7: Distributively connect several data nodes in the cloud data center to construct a blockchain consensus network, and set the InterPlanetary File System (IPFS) and smart contracts for the blockchain consensus network to obtain a blockchain storage network; S2: The data server collects real-time clinical test data and uploads the real-time clinical test data to the cloud data center using the OPC UA protocol, including the following steps: S2-1: The data server constructs an OPC UA information model based on historical clinical test data, extracts the model metadata of the OPC UA information model, and sends the model metadata to the cloud data center; S2-2: The cloud data center deploys an OPC UA server and constructs an OPC UA instance in the address space of the OPC UA server according to the model metadata; S2-3: The data server collects the original real-time clinical test data according to the OPC UA information model and uploads the original real-time clinical test data to the cloud data center using the OPC UA protocol; S2-4: The cloud data center writes the original real-time clinical test data into the OPC UA instance and obtains the final real-time clinical test data based on the OPC UA instance; S3: The cloud data center uses the clinical test data management engine to standardize the real-time clinical test data from different data sources to obtain the standard real-time clinical test data, including the following steps: S3-1: The cloud data center extracts the real-time clinical test data of the OPC UA instances from different data sources and inputs the real-time clinical test data into the standardization processing model of the clinical test data management engine; S3-2: Use the first real-time graph structure feature extraction module of the standardization processing model to extract the first real-time graph structure feature of the real-time clinical test data; S3-3: Use the standardization processing strategy generation module of the standardization processing model to generate a standardization processing strategy according to the first real-time graph structure feature to obtain a real-time standardization processing strategy; S3-4: According to the real-time standardization processing strategy, extract several corresponding target SPA algorithms from the standardization processing algorithm library of the standardization processing model; S3-5: Standardize the real-time clinical test data according to several target SPA algorithms to obtain the corresponding standard real-time clinical test data; S4: The cloud data center uses the clinical test data management engine to semantically expand the standard real-time clinical test data according to the clinical test knowledge graph to obtain the expanded real-time clinical test data, including the following steps: S4-1: The cloud data center inputs the standard real-time clinical test data into the named entity and entity relationship extraction model of the clinical test data management engine; S4-2: Use the semantic feature extraction module of the named entity and entity relationship extraction model to extract the real-time semantic feature of the standard real-time clinical test data; S4-3: Use the named entity extraction module of the named entity and entity relationship extraction model to obtain several corresponding data named entities according to the real-time semantic feature; S4-4: Obtain the similarity between each data named entity and several knowledge named entities in the clinical examination knowledge graph, and use the knowledge named entity with the highest similarity as the first target knowledge named entity of the data named entity; S4-5: Use several knowledge entity relationships of the first target knowledge named entity as several target knowledge entity relationships of the data named entity, and use the knowledge named entity on the other side of the target knowledge entity relationship as the second target knowledge named entity of the data named entity; S4-6: Semantically expand the standard real-time clinical examination data according to the first target knowledge named entity, several target knowledge entity relationships, and several second target knowledge named entities of each data named entity to obtain the expanded real-time clinical examination data; S5: The cloud data center uses the clinical examination data management engine to perform data analysis on the expanded real-time clinical examination data to obtain the corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results, including the following steps: S5-1: The cloud data center inputs the expanded real-time clinical examination data into the data analysis model of the clinical examination data management engine; S5-2: Use the second real-time graph structure feature extraction module of the data analysis model to extract the second real-time graph structure feature of the expanded real-time clinical examination data; S5-3: According to the preset first attention weight value, use the first weighted fusion channel of the attention weight module of the data analysis model to perform weighted fusion on the second real-time graph structure feature to obtain the first real-time weighted fusion feature; S5-4: According to the preset second attention weight value, use the second weighted fusion channel of the attention weight module of the data analysis model to perform weighted fusion on the second real-time graph structure feature to obtain the second real-time weighted fusion feature; S5-5: According to the preset third attention weight value, use the third weighted fusion channel of the attention weight module of the data analysis model to perform weighted fusion on the second real-time graph structure feature to obtain the third real-time weighted fusion feature; S5-6: Use the retrieval tag generation module of the data analysis model to generate retrieval tags according to the first real-time weighted fusion feature to obtain the corresponding real-time retrieval tags; S5-7: Use the open permission generation module of the data analysis model to generate open permissions according to the second real-time weighted fusion feature to obtain the corresponding real-time open permissions; S5-8: Use the data analysis module of the data analysis model to perform data analysis according to the third real-time weighted fusion feature to obtain the corresponding real-time data analysis results; The real-time data analysis results include the real-time inspection index trend prediction results (predicting the future change trends of specific inspection indexes, such as blood glucose, cholesterol, etc.), the real-time abnormal value prediction results of clinical inspection data indexes (such as abnormal white blood cell count index, etc.), and the real-time classification levels of clinical inspection data (such as disease risk level, severity level, etc.); S6: The cloud data center, according to the real-time open permission, uses the corresponding encryption key to encrypt the extended real-time clinical inspection data to obtain the encrypted real-time clinical inspection data, and conducts controlled management on the encryption key, including the following steps: S6-1: The cloud data center sets the encryption keys for different preset open permissions. The encryption keys for different preset open permissions have different levels of complexity. The higher the level of the preset open permission, the more complex the encryption key; S6-2: According to the real-time open permission, match among a number of preset encryption keys to obtain the encryption key corresponding to the preset open permission; S6-3: Use the corresponding encryption key to encrypt the extended real-time clinical inspection data to obtain the encrypted real-time clinical inspection data; S6-4: Store the encryption keys for different preset open permissions in the controlled database of the cloud data center for controlled management. Only when the user permission is greater than the real-time open permission can the corresponding encryption key for the preset open permission be called; S7: The cloud data center uses the blockchain storage network to store the encrypted real-time clinical inspection data, the corresponding real-time retrieval tags, the real-time open permission, and the real-time data analysis results, including the following steps: S7-1: The cloud data center stores the encrypted real-time clinical inspection data in the IPFS system of the blockchain storage network to obtain the real-time data hash value, and uses a smart contract to generate a real-time storage request; S7-2: Send the real-time storage request to the blockchain consensus network of the blockchain storage network, and use the data node that receives the real-time storage request as the primary node; S7-3: Based on the primary node, use the consensus algorithm to broadcast a pre-prepared message to other data nodes and verify the legality of the real-time storage request; S7-4: If the legality verification passes, use the primary node to broadcast a prepared message containing the voting information of the primary node to other data nodes and write the prepared message into the message log; S7-5: Based on all data nodes, exchange confirmation messages. If the primary node receives more than the quantity threshold of confirmation messages, the consensus is successful, and the real-time consensus timestamp is extracted. Otherwise, the consensus fails; S7-6: After the consensus is successful, use the smart contract to generate real-time transaction data according to the real-time storage request, the real-time consensus timestamp, and the real-time data hash value; S7-7: Use the master node to convert real-time transaction data into data blocks, and use the blockchain consensus network to link and chain the data blocks.

[0021] Embodiment 2: As Figure 2 shown, this embodiment provides an artificial intelligence-based clinical test data management system for implementing the clinical test data management method. The system includes a cloud data center and several data servers. The several data servers are all communicatively connected to the cloud data center. The cloud data center is provided with a clinical test data management engine and a clinical test knowledge graph, and the cloud data center includes an initialization unit, a standardization processing unit, a semantic extension unit, a data analysis unit, a data encryption unit, and a data storage unit that are connected in sequence.

[0022] The data server is used to collect real-time clinical test data and upload the real-time clinical test data to the cloud data center using the OPC UA protocol; The initialization unit is used to build a clinical test data management engine and a clinical test knowledge graph using artificial intelligence algorithms, and deploy a blockchain storage network using blockchain technology; The standardization processing unit is used to standardize the real-time clinical test data from different data sources using the clinical test data management engine to obtain standard real-time clinical test data; The semantic extension unit is used to semantically extend the standard real-time clinical test data according to the clinical test knowledge graph using the clinical test data management engine to obtain extended real-time clinical test data; The data analysis unit is used to perform data analysis on the extended real-time clinical test data using the clinical test data management engine to obtain corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results; The data encryption unit is used to encrypt the extended real-time clinical test data using the corresponding encryption key according to the real-time open permissions to obtain encrypted real-time clinical test data, and perform controlled management on the encryption key; The data storage unit is used to store the encrypted real-time clinical test data, the corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results using the blockchain storage network.

[0023] The present invention discloses a clinical test data management method and system based on artificial intelligence. By constructing a unified OPC UA information model, it realizes standardized data transmission between the cloud data center and different data sources, simplifies the subsequent standardized processing process, improves the transmission efficiency, and performs data standardization processing through a clinical test data management engine to achieve a unified format and specification for data from different data sources, eliminate data heterogeneity, improve the efficiency of data processing and analysis, reduce the difficulty of data management, and has a high degree of automation. It can automatically complete steps such as data collection, upload, standardization processing, semantic extension, data analysis, and storage, reduce manual intervention, and improve work efficiency; uses a blockchain storage network constructed by blockchain technology for data storage to achieve decentralized storage and distributed management of data, effectively prevent data leakage and illegal access, and improve data security; performs semantic extension on clinical test data, combines clinical test data with a clinical knowledge graph, enriches data semantic information, improves the depth and breadth of data analysis, and deeply mines and predicts clinical test data through a clinical test data management engine to improve the accuracy and comprehensiveness of analysis results, providing a more reliable basis for subsequent clinical diagnosis, treatment, and prevention.

[0024] The present invention is not limited to the above optional embodiments, and anyone can obtain other various forms of products under the inspiration of the present invention. The above specific embodiments should not be construed as limiting the protection scope of the present invention. The protection scope of the present invention should be defined by the claims, and the specification can be used to interpret the claims.

Claims

1. A clinical test data management method based on artificial intelligence, characterized in that: Including the following steps: The cloud data center uses artificial intelligence algorithms to build a clinical test data management engine and a clinical test knowledge graph, and uses blockchain technology to deploy a blockchain storage network; The data server collects real-time clinical test data and uploads the real-time clinical test data to the cloud data center using the OPC UA protocol; The cloud data center uses the clinical test data management engine to standardize the real-time clinical test data from different data sources to obtain standard real-time clinical test data; The cloud data center uses the clinical test data management engine to semantically expand the standard real-time clinical test data according to the clinical test knowledge graph to obtain extended real-time clinical test data; The cloud data center uses the clinical test data management engine to perform data analysis on the extended real-time clinical test data to obtain corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results; The cloud data center encrypts the extended real-time clinical test data using the corresponding encryption key according to the real-time open permissions to obtain encrypted real-time clinical test data, and performs controlled management on the encryption key; The cloud data center uses the blockchain storage network to store the encrypted real-time clinical test data, the corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results; 2. The method for managing clinical test data based on artificial intelligence according to claim 1, characterized in that: The cloud data center uses artificial intelligence algorithms to build a clinical test data management engine and a clinical test knowledge graph, and uses blockchain technology to deploy a blockchain storage network, including the following steps: The cloud data center collects a number of clinical test knowledge and a number of historical clinical test data, and performs preprocessing to obtain a number of preprocessed clinical test knowledge and a number of preprocessed historical clinical test data; According to a number of preprocessed clinical test knowledge, use natural language processing algorithms to build a named entity and entity relationship extraction model, and obtain a clinical test knowledge graph; According to a number of preprocessed historical clinical test data, use a fusion algorithm of deep learning and reinforcement learning to build a standardization processing model, and generate a number of standard historical clinical test data; According to the clinical test knowledge graph, semantically expand a number of standard historical clinical test data to obtain a number of extended historical clinical test data; According to a number of extended historical clinical test data, use a multi-output deep learning algorithm to build a data analysis model; Integrate the named entity and entity relationship extraction model, the standardization processing model, and the data analysis model to obtain a clinical test data management engine; Distributively connect a number of data nodes in the cloud data center to build a blockchain consensus network, and set up an IPFS system and a smart contract for the blockchain consensus network to obtain a blockchain storage network; 3. The method for managing clinical test data based on artificial intelligence according to claim 2, characterized in that: According to a number of preprocessed clinical test knowledge, use natural language processing algorithms to build a named entity and entity relationship extraction model, and obtain a clinical test knowledge graph, including the following steps: Use natural language processing algorithms to build an initial named entity and entity relationship extraction model; Optimize and train the initial named entity and entity relationship extraction model according to a number of pre - processed clinical test knowledge to obtain the final named entity and entity relationship extraction model, and generate a number of knowledge named entities and a number of knowledge entity relationships; Construct a knowledge graph according to a number of knowledge named entities and a number of knowledge entity relationships to obtain a clinical test knowledge graph.

4. The clinical test data management method based on artificial intelligence according to claim 3, characterized in that: The named entity and entity relationship extraction model is constructed based on the BERT - CRF - SVM algorithm; The standardization processing model is constructed based on the GCN - MOPPO - SPA algorithm; The data analysis model is constructed based on the GCN - Attention - DBN algorithm.

5. The method for managing clinical test data based on artificial intelligence according to claim 4, characterized in that: A data server collects real - time clinical test data and uploads the real - time clinical test data to the cloud data center using the OPC UA protocol, including the following steps: The data server constructs an OPC UA information model according to historical clinical test data, extracts the model metadata of the OPC UA information model, and sends the model metadata to the cloud data center; The cloud data center deploys an OPC UA server and constructs an OPC UA instance in the address space of the OPC UA server according to the model metadata; The data server collects the original real - time clinical test data according to the OPC UA information model and uploads the original real - time clinical test data to the cloud data center using the OPC UA protocol; The cloud data center writes the original real - time clinical test data into the OPC UA instance and obtains the final real - time clinical test data based on the OPC UA instance.

6. The method for managing clinical test data based on artificial intelligence according to claim 5, characterized in that: The cloud data center uses a clinical test data management engine to standardize the real - time clinical test data from different data sources to obtain standard real - time clinical test data, including the following steps: The cloud data center extracts the real - time clinical test data of the OPC UA instance from different data sources and inputs the real - time clinical test data into the standardization processing model of the clinical test data management engine; Use the standardization processing model to extract the first real - time graph structure features of the real - time clinical test data; Generate a standardization processing strategy according to the first real - time graph structure features to obtain a real - time standardization processing strategy; Extract a number of corresponding target SPA algorithms according to the real - time standardization processing strategy; Standardize the real - time clinical test data according to a number of target SPA algorithms to obtain the corresponding standard real - time clinical test data.

7. The method for managing clinical test data based on artificial intelligence according to claim 6, wherein: The cloud data center uses the clinical test data management engine to semantically expand the standard real - time clinical test data according to the clinical test knowledge graph to obtain extended real - time clinical test data, including the following steps: The cloud data center inputs the standard real - time clinical test data into the named entity and entity relationship extraction model of the clinical test data management engine; Use the named entity and entity relationship extraction model to extract the real - time semantic features of the standard real - time clinical test data; Obtain a number of corresponding data named entities according to the real - time semantic features; Obtain the similarity between each data named entity and several knowledge named entities in the clinical test knowledge graph, and use the knowledge named entity with the highest similarity as the first target knowledge named entity of the data named entity; Use several knowledge entity relationships of the first target knowledge named entity as several target knowledge entity relationships of the data named entity, and use the knowledge named entity on the other side of the target knowledge entity relationship as the second target knowledge named entity of the data named entity; According to the first target knowledge named entity, several target knowledge entity relationships, and several second target knowledge named entities of each data named entity, perform semantic expansion on the standard real-time clinical test data to obtain the expanded real-time clinical test data.

8. The method for managing clinical test data based on artificial intelligence according to claim 7, wherein: The cloud data center uses the clinical test data management engine to perform data analysis on the expanded real-time clinical test data to obtain the corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results, including the following steps: The cloud data center inputs the expanded real-time clinical test data into the data analysis model of the clinical test data management engine; Use the data analysis model to extract the second real-time graph structure features of the expanded real-time clinical test data; According to the preset first attention weight value, perform weighted fusion on the second real-time graph structure features to obtain the first real-time weighted fusion features; According to the preset second attention weight value, perform weighted fusion on the second real-time graph structure features to obtain the second real-time weighted fusion features; According to the preset third attention weight value, perform weighted fusion on the second real-time graph structure features to obtain the third real-time weighted fusion features; According to the first real-time weighted fusion features, generate retrieval tags to obtain the corresponding real-time retrieval tags; According to the second real-time weighted fusion features, generate open permissions to obtain the corresponding real-time open permissions; According to the third real-time weighted fusion features, perform data analysis to obtain the corresponding real-time data analysis results.

9. The method for managing clinical test data based on artificial intelligence according to claim 8, wherein: The cloud data center uses the blockchain storage network to store the encrypted real-time clinical test data, the corresponding real-time retrieval tags, real-time open permissions, and real-time data analysis results, including the following steps: The cloud data center stores the encrypted real-time clinical test data in the IPFS system of the blockchain storage network to obtain the real-time data hash value, and uses a smart contract to generate a real-time storage request; Send the real-time storage request to the blockchain consensus network of the blockchain storage network, and use the data node that receives the real-time storage request as the primary node; Based on the primary node, use the consensus algorithm to broadcast a pre-prepared message to other data nodes and verify the legality of the real-time storage request; If the legality verification passes, use the primary node to broadcast a prepared message containing the voting information of the primary node to other data nodes and write the prepared message into the message log; Based on all data nodes, exchange confirmation messages. If the primary node receives more than the quantity threshold of confirmation messages, the consensus is successful, and the real-time consensus timestamp is extracted, otherwise, the consensus fails; After the consensus is successful, use the smart contract to generate real-time transaction data according to the real-time storage request, real-time consensus timestamp, and real-time data hash value; Using the master node, convert real-time transaction data into data blocks, and use the blockchain consensus network to link and chain the data blocks.

10. A clinical test data management system based on artificial intelligence, which is used to implement the clinical test data management method described in any one of claims 1-9, and is characterized in that: The system includes a cloud data center and several data servers. All the several data servers are communicatively connected to the cloud data center. The cloud data center is provided with a clinical test data management engine and a clinical test knowledge graph. The cloud data center includes an initialization unit, a standardization processing unit, a semantic extension unit, a data analysis unit, a data encryption unit, and a data storage unit that are connected in sequence.

Images