Clinical laboratory blood drawing sequence number and test information integration method and system

Abstract

The invention relates to the field of medical information data processing, in particular to a clinical laboratory blood drawing sequence number and inspection information integration method and system. The method comprises the following steps: acquiring a blood drawing serial number and test information; performing serial number feature extraction on the blood drawing serial number to generate serial number feature data; performing data association analysis on the inspection information to generate inspection information analysis data; performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performing priority analysis on the inspection information matching data to generate inspection priority data; performing real-time data monitoring on the clinical laboratory to obtain real-time monitoring data; performing load analysis on the real-time monitoring data to generate clinical laboratory load data; and performing dynamic priority calculation on the test priority data based on the clinical laboratory load data to generate dynamic priority scheduling data. According to the invention, efficient and accurate information integration is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical information data processing, and in particular to a method and system for integrating blood drawing serial numbers and test information in a laboratory. Background Art

[0002] In modern medical practice, laboratory testing plays a crucial role in disease diagnosis and treatment. To obtain accurate diagnostic results, doctors often order blood tests to assess patients' health. However, due to the large volume of test samples and information that must be processed, traditional laboratory testing processes often present challenges, such as low efficiency and poor accuracy in integrating serial numbers and test information. Therefore, an intelligent method and system for integrating serial numbers and test information is needed. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a method and system for integrating blood drawing serial numbers and test information of a laboratory to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for integrating blood drawing serial numbers and test information in a laboratory, comprising the following steps:

[0005] Step S1: Obtaining the blood drawing serial number and test information; extracting the serial number feature of the blood drawing serial number to generate serial number feature data; performing data association analysis on the test information to generate test information analysis data;

[0006] Step S2: performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performing priority analysis on the inspection information matching data to generate inspection priority data;

[0007] Step S3: Monitor the real-time data of the laboratory department to obtain real-time monitoring data; perform load analysis on the real-time monitoring data to generate laboratory department load data; perform dynamic priority calculation on the laboratory priority data based on the laboratory department load data to generate dynamic priority scheduling data;

[0008] Step S4: performing node division on the verification information matching data to generate verification information node data; performing matrix construction on the verification information node data to generate a verification information matrix;

[0009] Step S5: Perform smart contract editing on the verification information node data to generate a verification information smart contract; construct a network topology structure for the verification information matrix based on the verification information smart contract to build a verification information blockchain network;

[0010] Step S6: Perform dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

[0011] The present invention obtains sequence feature data and test information related to a patient's blood draw by acquiring the blood draw sequence number and performing feature extraction and association analysis. This facilitates understanding and organizing the patient's test information, providing foundational data for subsequent steps. By performing identity matching on the sequence feature data and test information analysis data, the patient's test information can be associated with its corresponding blood draw sequence number, generating test information matching data. Further priority analysis of the matching data can determine the priority of each test, strengthening the sorting and priority management of test tasks. By real-time monitoring of the laboratory department's data, the current load of the laboratory department can be obtained, including information such as the number of test tasks and processing capacity. Load analysis based on this data can generate laboratory department load data to help assess the current work status of the laboratory department. Furthermore, dynamic priority calculation is performed on the test priority data based on the load of the laboratory department to generate dynamic scheduling data, which allocates test tasks to the appropriate laboratory department to optimize work efficiency and resource utilization. By partitioning the test information matching data into nodes, similar test tasks can be grouped into the same node, facilitating subsequent data processing and analysis. Subsequently, the node data is matrixed to form an inspection information matrix, which better represents the relationships and interactions between inspection tasks and provides a data foundation for subsequent steps. By implementing smart contract editing on the inspection information node data, an inspection information smart contract can be formed, which contains information such as the rules and constraints for the inspection tasks, facilitating subsequent operations and management. Subsequently, based on the inspection information smart contract, a decentralized network topology is constructed for the inspection information matrix, building an inspection information blockchain network. This provides enhanced security, reliability, and transparency, ensuring the integrity and immutability of inspection information. By performing dynamic policy analysis on dynamic priority scheduling data based on the inspection information blockchain network, a dynamic scheduling policy model can be generated based on real-time inspection task requirements and information from the inspection information blockchain. This model can rationally allocate and schedule inspection tasks based on factors such as the priority of the inspection task and the load of the laboratory department, achieving the integration and efficient execution of inspection information.

[0012] In this manual, a system for integrating blood draw serial numbers and test information is provided, including:

[0013] The information collection module obtains the blood drawing serial number and test information; extracts the serial number feature of the blood drawing serial number to generate serial number feature data; performs data association analysis on the test information to generate test information analysis data;

[0014] The priority analysis module performs identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performs priority analysis on the inspection information matching data to generate inspection priority data;

[0015] The dynamic priority module monitors the real-time data of the laboratory department and obtains the real-time monitoring data; performs load analysis on the real-time monitoring data to generate the load data of the laboratory department; performs dynamic priority calculation on the test priority data based on the load data of the laboratory department to generate dynamic priority scheduling data;

[0016] The information matrix module divides the test information matching data into nodes to generate test information node data; constructs a matrix of the test information node data to generate a test information matrix;

[0017] The blockchain network module performs smart contract editing on the inspection information node data to generate the inspection information smart contract; based on the inspection information smart contract, it builds a decentralized network topology structure for the inspection information matrix to construct the inspection information blockchain network;

[0018] The strategy model module performs dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

[0019] The present invention constructs a system that integrates blood draw sequence numbers and test information for the clinical laboratory. Through an information acquisition module, the system can obtain blood draw sequence numbers and test information, providing the necessary data foundation for subsequent analysis and processing. The system then extracts sequence feature information from the blood draw sequence numbers, converting them into feature data that can be used for analysis and comparison. This allows for statistical analysis of sequence feature information to obtain information about the order and priority of blood draws. By performing data correlation analysis on the test information, the system can identify the correlations and dependencies between different test items. The generated test information analysis data contains information about the relationships between test items, which facilitates subsequent priority analysis and scheduling decisions. By matching and analyzing the sequence feature data with the test information analysis data, the system can determine the test priority corresponding to each blood draw sequence number. This provides reliable data for subsequent dynamic priority scheduling, ensuring that important test items are processed and results are obtained as quickly as possible. Based on real-time monitoring data and load analysis, the system generates load data for the clinical laboratory. Then, through dynamic priority calculation, the test priority data is combined with the load data to generate dynamic priority scheduling data. This allows inspection tasks to be prioritized and scheduled based on real-time conditions, maximizing inspection efficiency and resource utilization. The system partitions inspection information matching data into nodes and constructs an inspection information matrix. This information matrix provides a visual and structured representation of the relationships between inspection items, facilitating further data analysis and decision-making. By implementing smart contract editing on inspection information node data and utilizing smart contracts to build a decentralized blockchain network, an inspection information blockchain network is formed. This ensures the security, traceability, and sharing of inspection information, enhancing the credibility and integrity of the data. Based on the inspection information blockchain network, the system can perform dynamic policy analysis on dynamic priority scheduling data and generate a dynamic scheduling policy model. This model combines real-time data with the information integration capabilities of the blockchain network to more accurately make scheduling decisions and assign tasks, optimizing the efficiency and quality of inspection task execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of the steps of a method and system for integrating blood draw sequence numbers and test information in a laboratory department according to the present invention;

[0021] Figure 2 Detailed implementation flow chart of step S1;

[0022] Figure 3 Detailed implementation flow chart of step S2;

[0023] Figure 4 Schematic diagram of the detailed implementation steps of step S3. DETAILED DESCRIPTION

[0024] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0025] This application example provides a method and system for integrating blood draw serial numbers and test information in a laboratory. The execution entities of the method and system include, but are not limited to, the following: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc., which can be considered as general computing nodes of this application. The data processing platform includes, but is not limited to, at least one of an audio and image management system, an information management system, and a cloud data management system.

[0026] See also Figures 1 to 4 The present invention provides a method for integrating blood drawing serial number and test information of a laboratory, the method comprising the following steps:

[0027] Step S1: Obtaining the blood drawing serial number and test information; extracting the serial number feature of the blood drawing serial number to generate serial number feature data; performing data association analysis on the test information to generate test information analysis data;

[0028] Step S2: performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performing priority analysis on the inspection information matching data to generate inspection priority data;

[0029] Step S3: Monitor the real-time data of the laboratory department to obtain real-time monitoring data; perform load analysis on the real-time monitoring data to generate laboratory department load data; perform dynamic priority calculation on the laboratory priority data based on the laboratory department load data to generate dynamic priority scheduling data;

[0030] Step S4: performing node division on the verification information matching data to generate verification information node data; performing matrix construction on the verification information node data to generate a verification information matrix;

[0031] Step S5: Perform smart contract editing on the verification information node data to generate a verification information smart contract; construct a network topology structure for the verification information matrix based on the verification information smart contract to build a verification information blockchain network;

[0032] Step S6: Perform dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

[0033] The present invention obtains sequence feature data and test information related to a patient's blood draw by acquiring the blood draw sequence number and performing feature extraction and association analysis. This facilitates understanding and organizing the patient's test information, providing foundational data for subsequent steps. By performing identity matching on the sequence feature data and test information analysis data, the patient's test information can be associated with its corresponding blood draw sequence number, generating test information matching data. Further priority analysis of the matching data can determine the priority of each test, strengthening the sorting and priority management of test tasks. By real-time monitoring of the laboratory department's data, the current load of the laboratory department can be obtained, including information such as the number of test tasks and processing capacity. Load analysis based on this data can generate laboratory department load data to help assess the current work status of the laboratory department. Furthermore, dynamic priority calculation is performed on the test priority data based on the load of the laboratory department to generate dynamic scheduling data, which allocates test tasks to the appropriate laboratory department to optimize work efficiency and resource utilization. By partitioning the test information matching data into nodes, similar test tasks can be grouped into the same node, facilitating subsequent data processing and analysis. Subsequently, the node data is matrixed to form an inspection information matrix, which better represents the relationships and interactions between inspection tasks and provides a data foundation for subsequent steps. By implementing smart contract editing on the inspection information node data, an inspection information smart contract can be formed, which contains information such as the rules and constraints for the inspection tasks, facilitating subsequent operations and management. Subsequently, based on the inspection information smart contract, a decentralized network topology is constructed for the inspection information matrix, building an inspection information blockchain network. This provides enhanced security, reliability, and transparency, ensuring the integrity and immutability of inspection information. By performing dynamic policy analysis on dynamic priority scheduling data based on the inspection information blockchain network, a dynamic scheduling policy model can be generated based on real-time inspection task requirements and information from the inspection information blockchain. This model can rationally allocate and schedule inspection tasks based on factors such as the priority of the inspection task and the load of the laboratory department, achieving the integration and efficient execution of inspection information.

[0034] In the embodiment of the present invention, reference Figure 1 The above is a flowchart of a method and system for integrating blood draw sequence numbers and test information of a laboratory laboratory according to the present invention. In this example, the steps of the method for integrating blood draw sequence numbers and test information of a laboratory laboratory include:

[0035] Step S1: Obtain the blood drawing serial number and test information; extract the serial number feature of the blood drawing serial number to generate serial number feature data; perform data association analysis on the test information to generate test information analysis data.

[0036] In this embodiment, the blood draw sequence number and the corresponding test information data are extracted from relevant data sources (such as medical record systems, hospital databases, etc.). This can be achieved by cooperating with medical institutions to obtain data sets, or by integrating data interfaces with systems, etc., to extract features of the blood draw sequence number for subsequent analysis and comparison. Features based on numbers, such as extracting the length, average value, variance, etc. of the sequence number, and features based on time, such as extracting the hours, minutes, and other information string processing features of the blood draw time, such as extracting keywords and character occurrence frequencies from the sequence number, are used to extract features. Association rule algorithms (such as the Apriori algorithm) are used to discover frequently occurring combinations and reveal the correlation between test items. Statistical methods (such as correlation coefficients, covariance, etc.) are used to measure the correlation between different test items. Based on the results of the data association analysis, the test information data is combined with the blood draw sequence number feature data to generate test information analysis data, which contains information about the relationship between the test items. This can be structured data presented in the form of a table, matrix, or graph.

[0037] Step S2: performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performing priority analysis on the inspection information matching data to generate inspection priority data.

[0038] In this embodiment, for the serial feature data and the inspection information analysis data, data cleaning and preprocessing are first performed to ensure the accuracy and consistency of the data. The serial feature data and the inspection information analysis data are matched according to predefined identification rules and matching algorithms. This can be done based on methods such as keyword matching, pattern matching, and similarity comparison. The matching results are recorded to generate inspection information matching data. These data will contain the matched serial feature and the corresponding inspection information. Based on the inspection information matching data, the importance and priority of each matching result are determined. This can be done based on preset rules and parameters. Factors such as the urgency, scope of impact, and clinical significance of the inspection information are analyzed to determine the priority of the inspection. This can be done in combination with expert opinions and medical practice experience. A priority is associated with each matching result to generate inspection priority data. This will help determine the execution order and priority of the inspection in subsequent steps.

[0039] Step S3: Monitor the real-time data of the laboratory department to obtain real-time monitoring data; perform load analysis on the real-time monitoring data to generate laboratory department load data; perform dynamic priority calculation on the laboratory priority data based on the laboratory department load data to generate dynamic priority scheduling data.

[0040] In this embodiment, an appropriate monitoring system is established in the laboratory department. This can be automated data acquisition equipment, sensors, or manual recording monitoring tools. These monitoring systems will record the real-time operating status and relevant data of the laboratory department. Real-time monitoring data is collected to ensure data accuracy and real-time performance. This can be achieved through automated data transmission, real-time data interfaces, or manual recording. Real-time monitoring data is organized and stored for subsequent load analysis and priority calculation. Load analysis is performed on real-time monitoring data to assess the current workload and resource utilization of the laboratory department. Load analysis can consider indicators such as the number of test samples, the number of test items, test equipment utilization, and staff load. Appropriate algorithms and models are used to convert real-time monitoring data into load data. This can include methods such as average calculation, statistical indicators, and time series analysis. The appropriate method should be selected based on actual needs. Load data is recorded for subsequent dynamic priority calculation. Dynamic priority calculation is performed based on the test priority data and load data. Dynamic calculation can adjust and rank test priorities in real time based on the real-time load situation and priority rules. Appropriate algorithms and rules are used to combine test priority and load data to calculate the dynamic priority of each test item. This can include weighted score calculations, dynamic adjustment algorithms, and priority queues to meet real-time scheduling needs. Dynamic priorities are associated with each inspection project to generate dynamic priority scheduling data. This data is used in subsequent inspection project scheduling decisions to achieve more efficient resource utilization and optimize the completion order of inspection tasks.

[0041] Step S4: performing node division on the verification information matching data to generate verification information node data; performing matrix construction on the verification information node data to generate a verification information matrix.

[0042] In this embodiment, test information matching data is prepared. This data contains the test information to be matched and related attributes. For example, it can include information such as test items, test samples, doctors, and treatment departments. The node partitioning method is determined based on needs and specific circumstances. Partitioning can be based on attributes such as test items, treatment departments, and patients to generate different nodes. The test information matching data is partitioned into nodes based on the partitioning method, with data with the same attributes grouped together. Each node represents a specific group of test information. The dimensions and attributes of the test information matrix are determined. These attributes can be node-related features or metrics, such as the number of samples, number of doctors, and average waiting time within a node. Based on the node partitioning results and the selected attributes, a matrix data structure is constructed to represent the associations and attribute information of the test information. The rows and columns of the matrix represent different nodes and attributes, respectively. For each node, the corresponding position in the matrix is filled with the attribute value calculated using the partitioned test information data. Attribute values can be calculated using statistical methods, clustering algorithms, and other methods. The test information matrix can be used to analyze relationships and attribute differences between different nodes. For example, the workload of nodes can be assessed by comparing attributes such as the number of samples and doctor load across different nodes. Based on the inspection information matrix, optimization decisions and resource allocation can be made. For example, by analyzing the attribute differences between nodes, more resources can be allocated to nodes with high load, or scheduling optimization can be performed for nodes with low load.

[0043] Step S5: Perform smart contract editing on the verification information node data to generate a verification information smart contract; construct a network topology structure for the verification information matrix based on the verification information smart contract to build a verification information blockchain network.

[0044] In this embodiment, the development environment and tools required to edit the smart contract are prepared. This may include a smart contract development platform or integrated development environment (IDE) as well as the relevant software and tools for the selected blockchain platform. Based on business requirements, the smart contract's functionality and data structure are determined. In this case, the smart contract needs to be able to process verification information node data and related operations, such as adding, querying, updating, and deleting node data. The smart contract code is written using a smart contract development language (such as Solidity). Based on the structure and properties of the verification information node data, the corresponding data structure and functions are defined to implement the corresponding logic. Ensure that an appropriate blockchain platform, such as Ethereum or Hyperledger Fabric, has been selected and configured. This involves setting up the corresponding nodes, blockchain network, and authentication. Deploy the verification information smart contract to the selected blockchain network. This can be accomplished using the blockchain platform's command line tools, development tools, or web interface. Create a decentralized network topology for the verification information matrix within the blockchain network. This can be achieved by defining appropriate data structures within the smart contract. For example, a mapping or array can be used to store and manage the verification information matrix data. For various operations (addition, query, update, etc.) in the inspection information smart contract, corresponding transaction logic and smart contract functions are implemented. These operations will be executed on the blockchain network and update the data of the inspection information matrix. Based on the inspection information smart contract and blockchain network, a decentralized and tamper-proof inspection information management system can be implemented. Each participant can verify and audit the integrity and accuracy of inspection information without relying on a centralized third-party organization. The characteristics of smart contracts can achieve automated contract execution and conditional triggering. For example, under certain conditions, specific actions on inspection information can be automatically triggered, such as automatically sending notifications and generating reports. The functionality of the inspection information blockchain network can be expanded and improved based on business needs. This may include adding authentication, permission control, privacy protection, and other functions.

[0045] Step S6: Perform dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

[0046] In this embodiment, dynamic priority scheduling data requires research and understanding. This may involve investigating and analyzing the characteristics, sources, and formats of scheduling data, as well as relevant literature and research on scheduling strategies. Understanding the characteristics and requirements of scheduling data is fundamental to developing dynamic scheduling strategies. Relevant data stored in the verification information blockchain network is obtained. This may include node data, transaction records, and smart contract execution results. The required data can be retrieved and extracted through the blockchain network's query function. The collected data is preprocessed and cleaned to ensure accuracy and consistency. This may include removing duplicate data, handling missing values, and standardizing data formats. The data is appropriately transformed and encoded to make it suitable for subsequent policy analysis. This may involve converting the data into an appropriate data structure or feature representation, such as a vector or matrix. Based on the dynamic priority scheduling data in the verification information blockchain network, an appropriate policy analysis method or model is determined. This may involve using machine learning, optimization algorithms, predictive models, and other methods for analysis. Based on the selected method or model, an appropriate algorithm or program is designed and implemented to perform dynamic policy analysis. This may include steps such as data preprocessing, model training, and parameter tuning. The results of the dynamic policy analysis are evaluated and validated to ensure their effectiveness and reliability. Cross-validation and experimental evaluation methods can be used to verify the performance and accuracy of the policy model. Based on the results of dynamic policy analysis, a dynamic scheduling policy model is generated. This may involve extracting and integrating the key features and parameters of the policy model. The dynamic scheduling policy model is converted into executable code or rules to enable its application in the actual verification information integration process. The generated dynamic scheduling policy model is tested and verified to ensure its feasibility and effectiveness in real-world applications.

[0047] In this embodiment, reference Figure 2 The above is a flowchart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0048] Step S11: Obtain the blood drawing serial number and test information, the test information including patient basic information, test item data, reference range and test status data;

[0049] Step S12: Analyze the coding characteristics of the blood sampling sequence number to generate coding characteristic data;

[0050] Step S13: segmenting the blood drawing serial number to generate serial number segmentation data;

[0051] Step S14: extracting serial number features from the serial number segmentation data based on the coding feature data to generate serial number feature data, the serial number feature data including blood drawing time data, blood drawing number data and blood drawing type data;

[0052] Step S15: Perform data association analysis on the test information to generate test information analysis data, which includes blood drawing sequence data, specimen type data, test item data, and test result data.

[0053] By acquiring basic patient information and test information, the present invention can integrate relevant data into a comprehensive system, which is convenient for medical personnel to perform subsequent operations and analyses. By acquiring the blood draw serial number and related test information, errors in manual recording or transmission can be avoided, and the accuracy and completeness of the data can be improved. Automatic acquisition of blood draw serial numbers and test information can reduce the time and error rate of manual operations, save staff time, and improve work efficiency. By performing coding feature analysis on the blood draw serial number, complex serial number information can be converted into feature data with better interpretability and operability, reducing the dimension of the data and facilitating subsequent processing and analysis. Coding feature analysis can help the system extract key features such as patient information and time information from the blood draw serial number, which is helpful for subsequent data mining and analysis. By segmenting the blood draw serial number, the system can parse out key information therein, such as blood draw time, number of blood draws, etc., so that this information can be presented and used more intuitively. Splitting the blood draw serial number into different parts can improve the standardization and consistency of the data, facilitate subsequent data analysis and processing, and by encoding feature numbers. By extracting and further analyzing the serial number segmentation data, the system can obtain more detailed and rich serial number feature data, and provide more dimensional information for subsequent data analysis and application. The serial number feature data includes key information such as blood drawing time, number of blood draws and blood drawing type, which can provide more accurate and detailed data support for subsequent analysis. Correlation analysis of different test information can reveal the relationship and characteristics between them, and provide comprehensive and accurate analysis results. By integrating data such as blood drawing sequence, specimen type, test items and test results, the system can generate more comprehensive and integrated test information analysis data, which is convenient for medical staff to conduct data analysis and application.

[0054] In this embodiment, it is necessary to obtain test information related to the blood draw number. This includes the patient's basic information (such as name, age, gender), test item data (such as blood routine, biochemical indicators, etc.), reference range (normal value range), and test status data (such as completed, pending, etc.). This data can be obtained from the electronic health record system, laboratory information system, or other related systems. It is necessary to perform coding feature analysis on the blood draw number. Coding features are features extracted based on specific rules or patterns in the blood draw number. For example, the blood draw number may contain information about the date, time, and location of the blood draw. Text processing technology, regular expressions, and other methods can be used to extract these features and convert them into numerical or categorical data for subsequent analysis and modeling. The blood draw number needs to be segmented. Serial number segmentation is the process of dividing the blood draw number into different parts or components. For example, the blood draw number may contain information about the number of blood draws, the type of blood draw, etc. By segmenting the blood draw number, these specific serial number segmentation data can be obtained. Further feature extraction of the serial number segmentation data is required. Based on the previous coding feature analysis and serial number segmentation of the blood draw serial number, specific serial number feature data can be extracted. This may include blood draw time data (such as year, month, day, hour, minute), blood draw frequency data (such as the number of blood draws) and blood draw type data (such as venous blood draw, arterial blood draw, etc.). These feature data will be used for subsequent data association analysis. Data association analysis needs to be performed on the acquired test information data. This includes associating different data elements to generate test information analysis data. For example, the blood draw serial number data can be associated with the patient's basic information, test item data and test result data to obtain information about the blood draw order, specimen type, specific test items and their corresponding results. These test information analysis data will provide a more comprehensive perspective to help further analyze and interpret the test data.

[0055] In this embodiment, reference Figure 3 The above is a flowchart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0056] Step S21: performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data;

[0057] Step S22: performing urgency analysis on the inspection information matching data to generate urgency data;

[0058] Step S23: performing resource utilization analysis on the inspection information matching data based on the urgency data to generate resource analysis data;

[0059] Step S24: performing priority analysis on the inspection information matching data based on the resource analysis data to generate inspection priority data.

[0060] The present invention ensures an accurate association between blood draw serial numbers and test results by matching sequence feature data with test information analysis data. This helps avoid incomplete or erroneous information caused by data matching errors or omissions. By matching the blood draw serial number with the test information, the consistency of relevant data throughout the entire test process is ensured. This avoids inconsistencies or conflicts between different data sources, improving data reliability and consistency. Urgency analysis divides test information according to its urgency and determines the priority of different tests. This helps medical institutions rationally allocate resources and time, ensuring timely treatment and diagnosis in emergency situations. Urgency data can help medical institutions optimize patient management, ensuring that patients who urgently need testing receive timely treatment and diagnosis. Rational resource allocation can reduce waiting times, improve patient satisfaction, and enhance treatment outcomes. Resource utilization analysis optimizes resource allocation for test information of different urgency levels. Based on the urgency of the test, resources such as equipment, manpower, and time are rationally allocated to ensure efficient resource utilization and maximized benefits. Resource analysis can avoid unnecessary resource waste and duplication, thereby reducing costs for medical institutions. Rational resource utilization also improves work efficiency and reduces unnecessary idle time for both personnel and equipment. Priority analysis ensures the accurate prioritization of different tests. This helps medical institutions rationally schedule tests, optimize workflows, and improve efficiency and accuracy. Test priority data ensures that patients who urgently need testing receive timely treatment and diagnosis, improving treatment outcomes and safeguarding patient health and safety.

[0061] In this embodiment, the sequence feature data is matched with the test information analysis data to generate test information matching data. First, based on features such as the blood draw sequence and time in the sequence feature data, it is matched with the blood draw sequence data and time data in the test information analysis data. This matching process determines the test information corresponding to each blood draw sequence number, generating test information matching data, which includes basic patient information, test item data, and test result data. Urgency analysis is performed on the test information matching data to determine the urgency of each test item and generate urgency data. Based on specific attributes in the test item data, such as clinical significance and the impact of the test results, each test item can be classified as urgent, routine, or deferrable. Urgency analysis assigns each test item a corresponding urgency level, generating urgency data. Based on the urgency data, resource utilization analysis is performed on the test information matching data to determine the resource requirements for each test item and generate resource analysis data. Based on the urgency level defined in the urgency data, the degree of resource demand for each test item, such as equipment, manpower, and time, can be assessed. Resource utilization analysis determines how resources can be allocated to meet the needs of different test items within given resource constraints, generating resource analysis data. Priority analysis is then performed on the test information matching data based on the resource analysis data to determine the priority of each test item and generate test priority data. Based on the resource requirements in the resource analysis data and other factors such as the urgency of the patient's condition and the requirements of the treatment plan, each test item can be assigned a corresponding priority. Priority analysis determines the order in which test items should be executed and generates test priority data to guide subsequent test operations.

[0062] In this embodiment, reference Figure 4 The above is a flowchart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0063] Step S31: Real-time data monitoring of the laboratory department is performed to obtain real-time monitoring data, which includes medical personnel data, testing instrument data, workload data, medical personnel emotional data, and task allocation data;

[0064] Step S32: Perform workload analysis on the real-time monitoring data to generate workload data of medical personnel;

[0065] Step S33: performing equipment utilization analysis on the real-time monitoring data based on the workload data of medical personnel to generate equipment utilization data;

[0066] Step S34: performing load analysis on the equipment utilization data to generate laboratory load data;

[0067] Step S35: performing sample processing time analysis on the inspection priority data based on the load data of the inspection department to generate processing time data;

[0068] Step S36: performing dynamic priority calculation on the inspection priority data based on the processing time data using the inspection information dynamic scheduling priority calculation formula to generate scheduling priority data;

[0069] Step S37: Dynamically optimize the scheduling priority data to generate dynamic priority scheduling data.

[0070] By performing real-time data monitoring on the clinical laboratory, the present invention can promptly obtain information such as medical personnel data, testing instrument data, workload data, and task allocation data. This data provides a foundation for subsequent analysis and decision-making. Real-time monitoring ensures the timeliness and accuracy of data, avoiding data lags or omissions. This helps maintain data integrity, ensuring that decisions and optimization measures are based on accuracy. By analyzing real-time monitoring data, it is possible to understand the current workload level of medical personnel. This helps assess whether workload is reasonably distributed and provides a basis for the rational scheduling of medical personnel. By analyzing workload data, it is possible to identify situations where workload is too high or too low. This helps optimize workload distribution, ensuring that medical personnel work under appropriate loads, improving work efficiency and satisfaction. Equipment utilization analysis can determine whether equipment is fully utilized. Identifying low equipment utilization provides a basis for optimizing equipment resources. By analyzing equipment utilization data, it is possible to determine equipment busyness and idle time. This helps to rationally adjust equipment usage time and work schedules, maximize equipment resource utilization, and improve testing efficiency and service quality. Load analysis can assess the current load of the clinical laboratory. Understanding load levels helps rationally allocate work and resources, ensuring the smooth operation of the laboratory department. By analyzing load data, it is possible to identify instances of excessive or insufficient load. This helps medical institutions optimize resource allocation, ensuring adequate resources are available when needed. Sample processing time analysis can assess the efficiency of sample processing during the testing process. Understanding processing time helps identify bottlenecks and improve overall efficiency. Dynamic priority calculation allows for the prioritization and scheduling of testing tasks based on factors such as processing time. This helps rationalize the sequencing of testing tasks, improving work efficiency and sample processing speed. Dynamic priority calculation considers multiple factors, such as sample urgency and processing time. This allows for a comprehensive balance of factors, ensuring that high-priority tasks are processed promptly, improving the accuracy and timeliness of test results. Dynamic optimization can further optimize scheduling to ensure that high-priority tasks are optimally assigned. This helps improve work efficiency, reduce wait times, and ensure timely processing in emergencies. Dynamic optimization scheduling allows for better utilization of medical personnel and equipment, improving resource efficiency. Rationalized task sequencing and scheduling can reduce idle resources and waste, thereby improving the overall effectiveness of the laboratory department.

[0071] In this embodiment, real-time data monitoring is performed on the laboratory department to obtain real-time monitoring data, including medical personnel data, testing instrument data, workload data, medical personnel emotional data, and task allocation data. This data can be collected through various methods, such as equipment sensors, work record systems, and personnel scheduling systems. Medical personnel data can include information such as the number of personnel, their positions, and work status; testing instrument data can include information such as the number, status, and availability of equipment; workload data can include information such as the current testing workload and number of samples; medical personnel emotional data can include information such as their emotional state, fatigue level, work stress, and happiness indicators; and task allocation data can include information such as task allocation and priority. Workload analysis is performed on the real-time monitoring data to generate medical personnel workload data. By analyzing task allocation data and medical personnel data, the current workload of each medical personnel can be calculated. Workload data can include information such as the number of tasks, task types, and working hours of medical personnel. This analysis can help identify medical personnel who may have excessive or insufficient workloads, thereby enabling appropriate task scheduling and resource allocation. Equipment utilization analysis is performed on the real-time monitoring data based on the medical personnel workload data to generate equipment utilization data. By analyzing medical staff workload data and testing instrument data, the utilization rate of each testing instrument can be calculated. Equipment utilization data includes information such as instrument operating time, usage time, and idle time. This analysis helps identify which testing instruments have low utilization rates, enabling optimal equipment scheduling and utilization. Load analysis is performed on equipment utilization data to generate clinical laboratory load data. By analyzing equipment utilization data, the clinical laboratory load can be calculated, including information such as the number of testing tasks, task types, and equipment utilization. Clinical laboratory load data helps understand the current workload and determine whether the load is excessive or insufficient. Based on clinical laboratory load data, sample processing time analysis is performed on test priority data to generate processing time data. By analyzing clinical laboratory load data, the processing time of each sample can be calculated. Processing time data helps measure the processing workload and time required for each sample and consider its impact on the overall workflow. Based on processing time data, dynamic priority calculation is performed on the test priority data using the test information dynamic scheduling priority calculation formula to generate scheduling priority data. By using an appropriate scheduling priority calculation formula and combining it with processing time data, each test item can be assigned a corresponding dynamic priority. Dynamic priority calculation can be adjusted and calculated based on real-time workload, sample processing time, urgency and other factors to meet the dynamic work needs of the laboratory department. The scheduling priority data is dynamically optimized to generate dynamic priority scheduling data.By analyzing scheduling priority data and other relevant factors, such as equipment availability and urgency, priorities can be dynamically adjusted and optimized. This ensures that in actual operations, inspection items can be processed in the optimal sequence and scheduling method to improve work efficiency and meet emergency needs.

[0072] In this embodiment, the calculation formula for the dynamic scheduling priority of the inspection information in step S36 is specifically:

[0073]

[0074] Among them, P is the dynamic scheduling priority value, α is the dynamic scheduling priority adjustment factor, β is the workload of medical personnel, γ is the number of medical testing personnel, δ is the equipment utilization rate, ∈ is the test type, ζ is the test information priority, η is the load value of the laboratory, θ is the test information processing time, l is the effective deadline of the test sample, λ is the test sample waiting time, μ is the patient medical priority, and ν is the urgency of the test sample.

[0075] The present invention Adjust the overall value of dynamic scheduling priority. Among them, γln(δ) represents the logarithmic relationship between the number of medical testing personnel and equipment utilization, Represents the logarithmic relationship between the test type and test information priority and the load value of the laboratory. Through the operation of the logarithmic function, the influence of quantity and ratio is converted into the weighting of the logarithmic value, making the weights between different variables more balanced and increasing the flexibility and adaptability of the model. Consider the impact of the effective cut-off time of the test sample. Represents the square root of the time it takes to process test information and the sample's effective deadline. This allows samples with shorter processing times to be prioritized in time-sensitive situations, ensuring timely processing and output of results. Consider the impact of patient medical priorities and the urgency of test specimens. This formula represents the ratio of the sample waiting time to the sum of the patient's medical priority and the sample's urgency. By integrating waiting time with patient priority and urgency, it ensures that high-priority patient samples receive timely processing and diagnosis in emergency situations. The formula integrates multiple factors, including medical staff workload, testing equipment utilization, test type and information priority, laboratory load, sample processing and waiting time, patient medical priority, and sample urgency. By appropriately weighting and combining these factors, dynamic scheduling priorities can be more accurately assessed and determined, improving scheduling effectiveness and overall operational efficiency.

[0076] In this embodiment, the specific steps of step S32 are:

[0077] Step S321: performing emotion fluctuation analysis on the real-time monitoring data to generate emotion fluctuation data;

[0078] Step S322: performing eye trajectory recognition on the medical personnel data based on the emotion fluctuation data to generate eye trajectory data;

[0079] Step S323: performing gaze frequency analysis on the eye trajectory data to generate gaze frequency data;

[0080] Step S324: performing gaze duration analysis on the gaze frequency data to generate gaze duration data;

[0081] Step S325: performing blink frequency analysis on the eye trajectory data based on the gaze duration data to generate blink frequency data;

[0082] Step S326: performing eye movement range detection on the eye trajectory data based on the blink frequency data to generate eye movement range data;

[0083] Step S327: performing eye movement speed analysis on the eye movement range data to generate eye movement speed data;

[0084] Step S328: performing eye fatigue analysis on the eye movement speed data to generate eye fatigue data;

[0085] Step S329: Perform workload analysis on the real-time monitoring data based on the eye fatigue data to generate workload data of medical personnel.

[0086] The present invention analyzes emotional fluctuations in real-time monitoring data to obtain dynamic information on the emotional state of medical personnel. This analysis process can help understand emotional fluctuations experienced by medical personnel during work, such as anxiety, tension, apathy, or joy. The generation of emotional fluctuation data can provide quantitative and qualitative emotional assessments, providing a foundation for subsequent analysis. Eye trajectory recognition based on emotional fluctuation data can obtain information on the path and trajectory of medical personnel's eye movements. This step can utilize eye tracking technology to track medical personnel's gaze movements, fixations, and gaze sequences to generate eye trajectory data. Eye trajectory data can reveal medical personnel's visual attention preferences and attention allocation under different emotional states. Gaze frequency analysis of eye trajectory data can calculate the proportion of time medical personnel spend in different visual areas. Gaze frequency indicates the intensity of medical personnel's visual fixations, that is, the degree of attention paid to specific areas. The generation of gaze frequency data can help understand medical personnel's gaze behavior when observing specific areas, providing further insight into their attention allocation and the degree of focus on important information. Gaze duration analysis of gaze frequency data can calculate the duration of medical personnel's gaze in different areas. Gaze duration indicates the amount of attention and focus a medical practitioner devotes to a specific area, reflecting the time it takes to process specific information. Gaze duration data can help understand medical practitioners' attention allocation to specific areas and their information processing abilities under different emotional states. Blink frequency analysis based on gaze duration data can be used to calculate a medical practitioner's blink frequency under different emotional states. Blink frequency is an indicator of ocular physiology that reflects changes in a medical practitioner's attention and eye fatigue. Blink frequency data can be used to assess a medical practitioner's attention and fatigue under different emotional states. Eye movement range detection based on blink frequency data can be used to assess the range of a medical practitioner's eye movements under different emotional states. Eye movement range indicates the range and spread of a medical practitioner's eye movements when fixating on a target. Eye movement range data can help understand medical practitioners' visual exploration behavior and the breadth of their gaze under different emotional states. Eye movement velocity analysis of eye movement range data can be used to calculate the speed of a medical practitioner's eye movements. Eye movement velocity reflects the speed of a medical practitioner's gaze under different emotional states. The generation of eye movement velocity data can provide an assessment of medical personnel's visual exploration behavior and gaze movements under different emotional states. By analyzing eye fatigue data based on eye movement velocity data, the degree of eye fatigue among medical personnel can be assessed. The generation of eye fatigue data can help understand the degree of eye fatigue among medical personnel during work and the impact of fatigue on visual attention and work performance. Workload analysis based on eye fatigue data can assess the workload level of medical personnel under different emotional states.The generation of workload data can provide an assessment of medical staff's cognitive load and stress levels under different emotional states. This data can help optimize medical staff's work arrangements, reduce workload, and provide guidance and support for emotional management and work efficiency improvement.

[0087] In this embodiment, emotion recognition algorithms and models are used in conjunction with real-time monitoring data from medical personnel, including physiological and speech features such as heart rate, respiratory rhythm, and voice intonation, to classify emotions and assess their degree of fluctuation, generating emotion fluctuation data. Eye trackers and other devices are used to identify and track the medical personnel's eye movements, recording the gaze points and gaze paths. Eye trajectory data is analyzed based on the emotion fluctuation data to generate eye trajectory data. The eye trajectory data is analyzed to calculate the number or frequency of gaze points in different emotional states, generating gaze frequency data that reflects the medical personnel's attention allocation and shifts. The eye trajectory data is analyzed to calculate the duration of gaze fixations in different emotional states, generating gaze duration data that reflects the depth and duration of the medical personnel's attention to specific stimuli or tasks. The gaze duration data and eye trajectory data are analyzed to calculate the number or frequency of blinks in different emotional states, generating blink frequency data that provides information on eye fatigue, attention level, and cognitive load. Analyze blink rate data and eye trajectory data to detect the range and direction of medical personnel's eye movements, including horizontal and vertical movement ranges. This generates eye movement range data, providing information on visual attention range and eye movement habits. Analyze eye movement range data to calculate the speed of medical personnel's eye movements in different emotional states, including horizontal and vertical speeds. This generates eye movement velocity data, providing information on reaction speed and eye movement flexibility. Analyze eye movement velocity data to assess the level of eye fatigue during specific tasks or time periods. This generates eye fatigue data to help determine the degree of visual fatigue and attention level.

[0088] In this embodiment, step S321 includes the following steps:

[0089] Step S3211: performing heart rate variability analysis on the real-time monitoring data to generate heart rate variability data;

[0090] Step S3212: performing heart rate response analysis on the heart rate variability data to obtain heart rate response data;

[0091] Step S3213: performing heart rate fluctuation trend analysis on the heart rate response data to generate heart rate fluctuation trend data;

[0092] Step S3214: Respiratory rhythm recognition is performed on the medical personnel data based on the heart rate fluctuation trend data to generate respiratory rhythm data;

[0093] Step S3215: performing phase analysis on the respiratory rhythm data to generate respiratory phase data;

[0094] Step S3216: performing intonation amplitude analysis on the medical personnel data according to the respiratory phase data to generate intonation amplitude data;

[0095] Step S3217: Perform emotion fluctuation analysis on the medical personnel data based on the intonation amplitude data to generate emotion fluctuation data.

[0096] The present invention uses heart rate variability analysis. Heart rate variability (HRV) is the temporal variation in heart rate, reflecting the activity level of the autonomic nervous system and heart health. Through heart rate variability analysis, heart rate variability data of medical personnel can be obtained, providing an assessment of their autonomic nervous system activity and heart health. Heart rate response analysis can study changes in heart rate under specific stimuli or events, such as exercise, emotional excitement, and stress. By performing heart rate response analysis on heart rate variability data, heart rate changes of medical personnel in different situations can be obtained, thereby understanding their heart rate regulation ability and stress response. Heart rate fluctuation trend analysis can reveal the upward or downward trend of heart rate and assess heart rate stability and fluctuation. By performing fluctuation trend analysis on heart rate response data, trend information on medical personnel's heart rate fluctuations can be obtained, further understanding their heart rate variation patterns. Respiratory rhythm refers to the rhythm and regularity of breathing. By performing respiratory rhythm identification based on heart rate fluctuation trend data, respiratory rhythm data of medical personnel can be obtained, further understanding their breathing regularity and the relationship between breathing and heart rate. Respiratory phase analysis analyzes the duration of the inhalation and exhalation phases of breathing to understand respiratory phase changes. Phase analysis of respiratory rhythm data can provide information about a healthcare provider's respiratory phase, further revealing breathing characteristics and patterns. Intonation amplitude analysis can assess voice pitch changes and emotional expression. By performing intonation amplitude analysis based on respiratory phase data, information about the pitch changes of a healthcare provider's voice can be obtained, further understanding the correlation between voice characteristics and respiration, and exploring the relationship between intonation amplitude and emotion. Emotion fluctuation analysis can identify and assess emotional changes in healthcare providers using intonation amplitude data. Emotion fluctuation analysis based on intonation amplitude data can provide information about a healthcare provider's emotional state, providing insights and assessments of their emotional state. This emotional fluctuation data can be used for applications such as emotional management, individual mental health assessments, and emotion recognition in communication and interactions with healthcare providers.

[0097] In this embodiment, the heart rate monitoring data of medical personnel are collected. The data can be obtained by using devices such as electrocardiogram (ECG) or heart rate sensor to calculate the heart rate variability (HRV) index. Common indexes include time domain indexes (such as standard deviation, mean, etc.) and frequency domain indexes (such as high frequency, low frequency components, etc.). By statistically analyzing the heart rate signal, the heart rate variability data is obtained. The heart rate variability data is used to perform heart rate response analysis to understand the heart rate response of medical personnel to specific stimuli or tasks. According to the changes in the heart rate variability data, the response pattern of the heart rate in different situations is observed, such as increase, decrease or stability, etc. The amplitude and duration of the heart rate response are analyzed to obtain heart rate response data. The heart rate response data is used to analyze the trend and change pattern of heart rate fluctuations. Time series analysis methods, sliding window analysis and other technologies can be used to detect and extract the trend characteristics of heart rate fluctuations. According to the analysis results, heart rate fluctuation trend data is generated to reflect the changing trend of the heart rate of medical personnel in different situations. The heart rate fluctuation trend data is used to identify and analyze the respiratory rhythm. Frequency domain analysis methods, wavelet transform and other technologies can be used to detect and extract the heart rate fluctuation trend characteristics. The frequency and amplitude characteristics of the respiratory rhythm are taken, and respiratory rhythm data is generated based on the analysis results to reflect the changing pattern of the respiratory rhythm of the medical staff. Signal processing methods, phase calculation algorithms and other technologies can be used to detect and extract the characteristics of the respiratory phase. Based on the analysis results, respiratory phase data is generated to reflect the changing pattern of the respiratory phase of the medical staff. The respiratory phase data is used to calculate and analyze the intonation amplitude. The characteristics of the intonation amplitude are detected and extracted through speech signal processing methods, spectrum analysis and other technologies. Based on the analysis results, intonation amplitude data is generated to reflect the changes in the medical staff's intonation under different respiratory phases. Emotion recognition algorithms, emotion recognition models and other technologies can be used to detect and extract the characteristics of emotional fluctuations. Based on the analysis results, emotion fluctuation data is generated to reflect the fluctuations of the medical staff's emotions under different intonation amplitudes.

[0098] In this embodiment, step S4 includes the following steps:

[0099] Step S41: Divide the verification information matching data into nodes to generate verification information node data;

[0100] Step S42: performing node similarity calculation on the inspection information node data using the inspection information node similarity calculation formula to generate node similarity data;

[0101] Step S43: constructing a matrix of the verification information node data based on the node similarity data to generate a verification information matrix.

[0102] By breaking down large blocks of data into multiple nodes, the present invention allows for independent processing of each node. This reduces computational complexity and improves data processing efficiency. By partitioning the data into nodes, the data can be broken down into multiple independent information units, which facilitates better understanding and analysis of the data. In-depth analysis and mining can be performed on each node to extract key information and patterns. After the data is partitioned into nodes, each node can be individually analyzed and calculated. This allows for the application of different algorithms and models to different nodes, allowing for flexible analysis and calculation based on specific circumstances. By calculating node similarity, nodes with similar functions, attributes, or other characteristics can be found. This helps discover correlations and similarities in the data and provides useful information for subsequent analysis and decision-making. Node similarity calculation can be used as an evaluation metric to screen out nodes with high similarity. This allows for filtering out nodes with low correlations with other nodes, improving the effectiveness of subsequent processing and analysis. Node similarity data can be used to construct relationships between nodes. By identifying nodes with high similarity, connections and associations between nodes can be established, contributing to a better understanding of data structures and relationships between data. Converting the node similarity data into a matrix format allows for a more intuitive presentation of relationships between nodes. Visualization allows for a clearer observation and analysis of the similarities and associations between nodes. The test information matrix provides a structured representation of the relationships between nodes. This facilitates subsequent data analysis and modeling, as well as further calculations and inferences based on the relationships between nodes. By constructing a test information matrix, multivariate analysis can be performed to explore the complex relationships between nodes. The matrix can be used for analytical methods such as clustering and association rule mining to uncover hidden patterns and information in the data.

[0103] In this embodiment, the test information matching data is divided into nodes according to certain rules. Node division can be based on specific attributes, keywords, or other relevant factors. For each node, relevant information is extracted and organized and stored in a specific format. Each node can be represented using a data structure (e.g., a list, a dictionary) or an object. Ensure that each node contains the necessary fields and attributes for subsequent similarity calculation and matrix construction. Determine the formula or algorithm for node similarity calculation, such as cosine similarity, Euclidean distance, Jaccard similarity, etc. A similarity calculation method suitable for the specific application scenario is selected. For each pair of nodes, the similarity between them is calculated and the result is stored in a node similarity data structure. The similarity data structure can be a matrix, a list, or other suitable data structure. Create an empty test information matrix with a size equal to the number of nodes multiplied by the number of nodes. Based on the node similarity data, fill the similarity into the corresponding matrix position. The matrix position can be determined based on the node's unique identifier or index. Determine the matrix format and representation method, such as using a two-dimensional array or a sparse matrix. Finally, the resulting test information matrix can be used for subsequent analysis, clustering, recommendation, and other tasks.

[0104] In this embodiment, the calculation formula for the similarity of the verification information nodes in step S42 is specifically:

[0105]

[0106] Among them, S is the similarity of the test information node, i is the i-th test information node, n is the total number of test information nodes, w i is the weight value of the i-th test information node, x i is the difference of the i-th test information node, G is the similarity balance parameter, Y is the weighted average value of the test information node, y i is the phase value of the i-th test information node, z i is the frequency value of the i-th test information node.

[0107] The present invention Calculate the difference and weight of the test information node to the similarity contribution, where, Indicates the derivative operation of the natural logarithm function on the difference of each node. By transforming the difference logarithmically, the smaller difference between nodes can be given a larger weight in the similarity calculation. iIt is used to adjust the importance of each node. G is the similarity balance parameter, which is used to balance the contribution of each node and increase the flexibility of the model. n·Y is a normalization process, which divides the sum of the nodes by the number of nodes and the average weight. Through normalization, it can ensure that the value range of similarity is within a reasonable range, which is convenient for comparison and understanding. Calculate the effect of the cube root of the node difference on the similarity. By performing the cube root operation on the node difference, the effect of the magnitude of the difference on the similarity can be reduced, the weight of the larger difference is reduced, and the similarity is more balanced. Considering the influence of the node's phase value and frequency value on the similarity, Represents the second-order derivative of the node difference multiplied by the square of the frequency value. By considering changes in phase and frequency, more subtle differences between nodes can be captured, improving the accuracy of similarity. The formula comprehensively considers multiple factors, including node difference, weight, phase value, and frequency value, and weights and transforms these factors through mathematical operations to obtain a more accurate similarity value. This can be used to compare the similarity between different test information nodes, analyze and make decisions based on data, and implement similarity-related tasks such as information matching and pattern recognition.

[0108] In this embodiment, step S5 includes the following steps:

[0109] Step S51: Perform contract analysis on the verification information node data to generate smart contract logic;

[0110] Step S52: defining node communication for the verification information node data based on the smart contract logic to generate node communication data;

[0111] Step S53: Perform smart contract editing on the verification information node data based on the node communication data to generate a verification information smart contract;

[0112] Step S54: constructing a network topology structure for the verification information matrix based on the verification information smart contract to generate a blockchain network topology structure;

[0113] Step S55: Reconstruct the topology module of the blockchain network topology structure to generate the blockchain genesis block;

[0114] Step S56: Use the distributed designated consensus algorithm to construct a blockchain network for the blockchain genesis block and build a verification information blockchain network.

[0115] This invention enables automated processing of verification information node data through the generation of smart contract logic. Smart contract code incorporates business rules and logic, which can be automatically executed through a program, reducing the need for manual intervention and processing, improving efficiency and accuracy. The definition of smart contract logic ensures the consistency of verification information node data during processing. Smart contracts can verify and constrain data, specifying its correctness and legality, and ensuring its consistency and integrity. The generation of smart contracts can make business processes transparent and provide data traceability. The logic within smart contracts is publicly accessible, allowing anyone to review and verify the contract execution process, thereby increasing business transparency and credibility. Node communication definitions standardize the data exchange method and format between nodes. This ensures that data is transmitted according to agreed-upon protocols, reduces the risk of data transmission errors and data loss, and improves the efficiency and reliability of data exchange. The generation of node communication data promotes collaboration and coordination between nodes. Nodes exchange and share data through communication definitions, achieving an orderly flow of information. This facilitates collaboration between nodes, improving work efficiency and the accuracy of business execution. Node communication definitions allow the definition of a variety of different communication protocols and methods. This allows for the selection of appropriate communication methods based on specific needs and scenarios, providing flexibility and scalability to accommodate systems of varying scale and complexity. Verification information smart contracts combine node communication requirements with smart contract logic to achieve automated and efficient business execution. Smart contracts process and exchange data based on node communication requirements, ensuring data accuracy and consistency, and improving the efficiency and quality of business execution. Verification information smart contracts enable decentralized data control. The logic and rules within the contract constrain and verify the correctness and legality of data, ensuring data security and credibility. All nodes can execute and verify the contract, eliminating a single point of control, enhancing data security and tamper resistance. The generation of smart contracts allows for programmable and modifiable business logic. Smart contracts can be edited and updated as business needs change, flexibly adjusting and optimizing business processes and logic, and enhancing the system's adaptability and flexibility.

[0116] In this embodiment, the characteristics and requirements of the verification information node data are analyzed and the functions and logic of the smart contract are determined. According to the requirements, the data structure, operations and rules involved in the smart contract are determined, the code logic of the smart contract is written, and the contract programming language (such as Solidity) is used for development to ensure the correctness and security of the smart contract logic, and necessary testing and verification are carried out. Based on the smart contract logic, the communication requirements and methods between nodes are determined, the communication protocol and message format between nodes are defined, the interaction process and communication rules between nodes are designed, and node communication data is generated, including message transmission, data exchange and other information between nodes. Based on the node communication data, the node communication rules and interaction process are integrated with the smart contract code. According to the requirements of the communication data, the smart contract code is modified, and necessary functions and logic are added. According to the communication requirements between nodes, it is ensured that the smart contract can correctly process and respond to the node's request, and finally a verification information smart contract is generated, which includes the node communication rules and smart Contract logic, based on the verification information smart contract, determines the topology of the blockchain network, designs the connection method between nodes, including the node block generation, consensus and transaction verification processes, based on the topology, designs the data transmission and interaction methods between nodes, builds the blockchain network topology, and ensures the correctness of the connection and communication between nodes, analyzes and adjusts the blockchain network topology to ensure the reliability and scalability of the network, and reconstructs the topology according to needs, including node grouping, permission setting, data transmission, etc., designs the structure and content of the genesis block, including the initial state, initial transaction, etc., generates the blockchain genesis block as the initial block of the blockchain network, selects a suitable distributed consensus algorithm (such as PoW, PoS, DPoS, etc.), adds the genesis block to the blockchain network, and starts the network nodes. The nodes reach a consensus based on the consensus algorithm and start generating blocks and verifying transactions. The blockchain network is gradually built up, and each new block is added to the chain according to the consensus algorithm.

[0117] In this embodiment, step S6 includes the following steps:

[0118] Step S61: Perform dynamic strategy analysis on the dynamic priority scheduling data based on the verification information blockchain network to generate dynamic strategy data;

[0119] Step S62: Optimizing the scheduling strategy for the dynamic strategy data to generate scheduling strategy optimization data;

[0120] Step S63: Visualize the scheduling strategy optimization data to generate a scheduling strategy optimization visualization view;

[0121] Step S64: performing dilation convolution on the scheduling strategy optimization visualization view to generate a scheduling strategy optimization network;

[0122] Step S65: Perform data mining modeling on the scheduling strategy optimization network to generate a dynamic scheduling strategy model to perform inspection information integration.

[0123] The present invention uses dynamic policy analysis to evaluate and analyze dynamic priority scheduling based on real-time verification information blockchain network data, thereby generating targeted dynamic policy data. This analysis, based on the verification information blockchain network, can provide a more accurate basis for scheduling decisions, helping to optimize resource utilization, reduce system congestion or delays, and improve scheduling efficiency and user experience. Scheduling policy optimization can utilize dynamic policy data to analyze and improve existing scheduling policies to identify more efficient and high-performance scheduling policies, further optimizing the scheduling process. Scheduling policy optimization can improve overall system performance, reduce resource waste and energy consumption, and enhance user satisfaction and system stability. Data visualization can display scheduling policy optimization data in the form of charts, images, and other formats, making complex data easier to understand and analyze. Visualizations of scheduling policy optimization can help decision makers intuitively observe and compare the effects of different policies, thereby better understanding the pros and cons of scheduling policies and making further improvement decisions. Dilated convolution is an image processing and analysis technique that can further extract features and patterns from scheduling policy optimization visualizations. Dilated convolution processing can transform scheduling policy optimization visualizations into more representative data representations, facilitating subsequent data mining and modeling analysis. Data mining modeling involves statistical analysis and pattern recognition within the scheduling strategy optimization network to uncover hidden patterns or associations. Data mining-based modeling can extract key features and indicators to construct a dynamic scheduling strategy model, which can predict and optimize future scheduling scenarios. This dynamic scheduling strategy model can integrate inspection information to make the scheduling process more robust and adaptable to real-time changing demands and environmental conditions.

[0124] In this embodiment, dynamic priority scheduling data in the verification information blockchain network is collected, including information such as task priority and resource availability, and the dynamic scheduling data is analyzed to understand the relationship and constraints between different tasks and resources. According to the analysis results, the goals and requirements of the dynamic scheduling strategy are determined, such as minimizing task delays, maximizing resource utilization, etc., and appropriate algorithms and techniques are used to analyze the characteristics and problems of dynamic strategy data, determine the optimization goals and constraints of the scheduling strategy, select appropriate optimization algorithms or methods, such as genetic algorithms, simulated annealing algorithms, etc., apply optimization algorithms to dynamic strategy data, perform iterative calculations and optimization to find the optimal scheduling strategy, and generate scheduling strategy optimization data according to the optimization results, including the optimized task scheduling order, resource allocation plan, etc., and convert the scheduling strategy optimization data into the data structure and format required for visualization. Select appropriate data visualization tools or libraries, such as Matplotlib, D3.js, etc., design the layout and style of the visualization view to clearly display the results of the scheduling policy optimization. Based on data visualization tools, convert the scheduling policy optimization data into visual charts, graphs or animations, etc., so as to intuitively observe and analyze the optimization results. Perform dilated convolution on the image data represented by the scheduling policy optimization visualization view, select appropriate dilated convolution algorithms and parameters, such as the size and step size of the convolution kernel, and perform dilated convolution operations to expand specific patterns or structures in the image to highlight relevant features. Based on the dilated convolution results, generate a scheduling policy optimization network, where nodes represent tasks or resources, and edges represent the relationships and connections between them. Based on the scheduling policy optimization network, prepare for data mining and modeling, including data preprocessing and feature engineering. Select appropriate data mining algorithms or technologies, such as machine learning and deep learning. Use mining algorithms to train and model the scheduling policy optimization network to generate a dynamic scheduling policy model. Verify and evaluate the performance and effect of the generated model, and make necessary adjustments and improvements.

[0125] In this embodiment, a system for integrating blood draw sequence numbers and test information in a laboratory is provided, including:

[0126] The information collection module obtains the blood drawing serial number and test information; extracts the serial number feature of the blood drawing serial number to generate serial number feature data; performs data association analysis on the test information to generate test information analysis data;

[0127] The priority analysis module performs identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performs priority analysis on the inspection information matching data to generate inspection priority data;

[0128] The dynamic priority module monitors the real-time data of the laboratory department and obtains the real-time monitoring data; performs load analysis on the real-time monitoring data to generate the load data of the laboratory department; performs dynamic priority calculation on the test priority data based on the load data of the laboratory department to generate dynamic priority scheduling data;

[0129] The information matrix module divides the test information matching data into nodes to generate test information node data; constructs a matrix of the test information node data to generate a test information matrix;

[0130] The blockchain network module performs smart contract editing on the inspection information node data to generate the inspection information smart contract; based on the inspection information smart contract, it builds a decentralized network topology structure for the inspection information matrix to construct the inspection information blockchain network;

[0131] The strategy model module performs dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

[0132] The present invention constructs a system that integrates blood draw sequence numbers and test information for the clinical laboratory. Through an information acquisition module, the system can obtain blood draw sequence numbers and test information, providing the necessary data foundation for subsequent analysis and processing. The system then extracts sequence feature information from the blood draw sequence numbers, converting them into feature data that can be used for analysis and comparison. This allows for statistical analysis of sequence feature information to obtain information about the order and priority of blood draws. By performing data correlation analysis on the test information, the system can identify the correlations and dependencies between different test items. The generated test information analysis data contains information about the relationships between test items, which facilitates subsequent priority analysis and scheduling decisions. By matching and analyzing the sequence feature data with the test information analysis data, the system can determine the test priority corresponding to each blood draw sequence number. This provides reliable data for subsequent dynamic priority scheduling, ensuring that important test items are processed and results are obtained as quickly as possible. Based on real-time monitoring data and load analysis, the system generates load data for the clinical laboratory. Then, through dynamic priority calculation, the test priority data is combined with the load data to generate dynamic priority scheduling data. This allows inspection tasks to be prioritized and scheduled based on real-time conditions, maximizing inspection efficiency and resource utilization. The system partitions inspection information matching data into nodes and constructs an inspection information matrix. This information matrix provides a visual and structured representation of the relationships between inspection items, facilitating further data analysis and decision-making. By implementing smart contract editing on inspection information node data and utilizing smart contracts to build a decentralized blockchain network, an inspection information blockchain network is formed. This ensures the security, traceability, and sharing of inspection information, enhancing the credibility and integrity of the data. Based on the inspection information blockchain network, the system can perform dynamic policy analysis on dynamic priority scheduling data and generate a dynamic scheduling policy model. This model combines real-time data with the information integration capabilities of the blockchain network to more accurately make scheduling decisions and assign tasks, optimizing the efficiency and quality of inspection task execution.

[0133] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0134] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0135] The foregoing description is intended only to provide specific embodiments of the present invention, intended to enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for integrating blood drawing serial number and test information in a laboratory, characterized in that: The following steps are involved: Step S1: Obtain blood drawing serial number and test information; Extracting serial number features from the blood draw serial number to generate serial number feature data; Perform data correlation analysis on inspection information to generate inspection information analysis data; Step S2: performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; Perform priority analysis on inspection information matching data to generate inspection priority data; Step S3: Perform real-time data monitoring on the laboratory department and obtain real-time monitoring data; Perform load analysis on real-time monitoring data to generate laboratory load data; perform dynamic priority calculation on laboratory priority data based on laboratory load data to generate dynamic priority scheduling data; Step S4: Divide the verification information matching data into nodes to generate verification information node data; Matrix construction is performed on the inspection information node data to generate an inspection information matrix; Step S5: Perform smart contract editing on the verification information node data to generate a verification information smart contract; Based on the inspection information smart contract, the network topology structure of the inspection information matrix is constructed to build the inspection information blockchain network; Step S6: Perform dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

2. The method according to claim 1, characterized in that The specific steps of step S1 are: Step S11: Obtain the blood drawing serial number and test information, the test information including patient basic information, test item data, reference range and test status data; Step S12: Analyze the coding characteristics of the blood sampling sequence number to generate coding characteristic data; Step S13: segmenting the blood drawing serial number to generate serial number segmentation data; Step S14: extracting serial number features from the serial number segmentation data based on the coding feature data to generate serial number feature data, the serial number feature data including blood drawing time data, blood drawing number data and blood drawing type data; Step S15: Perform data association analysis on the test information to generate test information analysis data, which includes blood drawing sequence data, specimen type data, test item data, and test result data.

3. The method according to claim 1, characterized in that The specific steps of step S2 are: Step S21: performing identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; Step S22: performing urgency analysis on the inspection information matching data to generate urgency data; Step S23: performing resource utilization analysis on the inspection information matching data based on the urgency data to generate resource analysis data; Step S24: performing priority analysis on the inspection information matching data based on the resource analysis data to generate inspection priority data.

4. The method according to claim 1, wherein The specific steps of step S3 are: Step S31: Real-time data monitoring of the laboratory department is performed to obtain real-time monitoring data, which includes medical personnel data, testing instrument data, workload data, medical personnel emotional data, and task allocation data; Step S32: Perform workload analysis on the real-time monitoring data to generate workload data of medical personnel; Step S33: performing equipment utilization analysis on the real-time monitoring data based on the workload data of medical personnel to generate equipment utilization data; Step S34: performing load analysis on the equipment utilization data to generate laboratory load data; Step S35: performing sample processing time analysis on the inspection priority data based on the load data of the inspection department to generate processing time data; Step S36: performing dynamic priority calculation on the inspection priority data based on the processing time data using the inspection information dynamic scheduling priority calculation formula to generate scheduling priority data; Step S37: Dynamically optimize the scheduling priority data to generate dynamic priority scheduling data; The calculation formula for the dynamic scheduling priority of the inspection information in step S36 is specifically: Among them, P is the dynamic scheduling priority value, α is the dynamic scheduling priority adjustment factor, β is the workload of medical personnel, γ is the number of medical testing personnel, δ is the equipment utilization rate, ∈ is the test type, ζ is the test information priority, η is the load value of the laboratory, θ is the test information processing time, l is the effective deadline of the test sample, λ is the test sample waiting time, μ is the patient medical priority, and ν is the urgency of the test sample.

5. The method according to claim 4, characterized in that The specific steps of step S32 are: Step S321: performing emotion fluctuation analysis on the real-time monitoring data to generate emotion fluctuation data; Step S322: performing eye trajectory recognition on the medical personnel data based on the emotion fluctuation data to generate eye trajectory data; Step S323: performing gaze frequency analysis on the eye trajectory data to generate gaze frequency data; Step S324: performing gaze duration analysis on the gaze frequency data to generate gaze duration data; Step S325: performing blink frequency analysis on the eye trajectory data based on the gaze duration data to generate blink frequency data; Step S326: performing eye movement range detection on the eye trajectory data based on the blink frequency data to generate eye movement range data; Step S327: performing eye movement speed analysis on the eye movement range data to generate eye movement speed data; Step S328: performing eye fatigue analysis on the eye movement speed data to generate eye fatigue data; Step S329: Perform workload analysis on the real-time monitoring data based on the eye fatigue data to generate workload data of medical personnel.

6. The method according to claim 5, characterized in that The specific steps of step S321 are: Step S3211: performing heart rate variability analysis on the real-time monitoring data to generate heart rate variability data; Step S3212: performing heart rate response analysis on the heart rate variability data to obtain heart rate response data; Step S3213: performing heart rate fluctuation trend analysis on the heart rate response data to generate heart rate fluctuation trend data; Step S3214: Respiratory rhythm recognition is performed on the medical personnel data based on the heart rate fluctuation trend data to generate respiratory rhythm data; Step S3215: performing phase analysis on the respiratory rhythm data to generate respiratory phase data; Step S3216: performing intonation amplitude analysis on the medical personnel data according to the respiratory phase data to generate intonation amplitude data; Step S3217: Perform emotion fluctuation analysis on the medical personnel data based on the intonation amplitude data to generate emotion fluctuation data.

7. The method according to claim 1, characterized in that The specific steps of step S4 are: Step S41: Divide the verification information matching data into nodes to generate verification information node data; Step S42: performing node similarity calculation on the inspection information node data using the inspection information node similarity calculation formula to generate node similarity data; Step S43: constructing a matrix of the verification information node data based on the node similarity data to generate a verification information matrix; The calculation formula for the similarity of the verification information nodes in step S42 is specifically: Among them, S is the similarity of the test information node, i is the i-th test information node, n is the total number of test information nodes, w i is the weight value of the i-th test information node, x i is the difference of the i-th test information node, G is the similarity balance parameter, Y is the weighted average value of the test information node, y i is the phase value of the i-th test information node, z i is the i-th test information node.

8. The method according to claim 1, characterized in that The specific steps of step S5 are: Step S51: Perform contract analysis on the verification information node data to generate smart contract logic; Step S52: defining node communication for the verification information node data based on the smart contract logic to generate node communication data; Step S53: Perform smart contract editing on the verification information node data based on the node communication data to generate a verification information smart contract; Step S54: constructing a network topology structure for the verification information matrix based on the verification information smart contract to generate a blockchain network topology structure; Step S55: Reconstruct the topology module of the blockchain network topology structure to generate the blockchain genesis block; Step S56: Use the distributed designated consensus algorithm to construct a blockchain network for the blockchain genesis block and build a verification information blockchain network.

9. The method according to claim 1, characterized in that The specific steps of step S6 are: Step S61: Perform dynamic strategy analysis on the dynamic priority scheduling data based on the verification information blockchain network to generate dynamic strategy data; Step S62: Optimizing the scheduling strategy for the dynamic strategy data to generate scheduling strategy optimization data; Step S63: Visualize the scheduling strategy optimization data to generate a scheduling strategy optimization visualization view; Step S64: performing dilation convolution on the scheduling strategy optimization visualization view to generate a scheduling strategy optimization network; Step S65: Perform data mining modeling on the scheduling strategy optimization network to generate a dynamic scheduling strategy model to perform inspection information integration.

10. A system for integrating blood drawing serial numbers and test information in a laboratory, characterized in that: The method for integrating blood drawing sequence numbers and test information of a laboratory as claimed in claim 1 comprises: The information collection module obtains the blood drawing serial number and test information; extracts the serial number feature of the blood drawing serial number to generate serial number feature data; performs data association analysis on the test information to generate test information analysis data; The priority analysis module performs identification matching on the serial number feature data and the inspection information analysis data to generate inspection information matching data; performs priority analysis on the inspection information matching data to generate inspection priority data; The dynamic priority module monitors the real-time data of the laboratory department and obtains the real-time monitoring data; performs load analysis on the real-time monitoring data to generate the load data of the laboratory department; performs dynamic priority calculation on the test priority data based on the load data of the laboratory department to generate dynamic priority scheduling data; The information matrix module divides the test information matching data into nodes to generate test information node data; constructs a matrix of the test information node data to generate a test information matrix; The blockchain network module performs smart contract editing on the inspection information node data to generate the inspection information smart contract; based on the inspection information smart contract, it builds a decentralized network topology structure for the inspection information matrix to construct the inspection information blockchain network; The strategy model module performs dynamic strategy analysis on the dynamic priority scheduling data based on the inspection information blockchain network to generate a dynamic scheduling strategy model to perform inspection information integration.

Images