A laboratory test flow control method and system

Abstract

This application provides a method and system for controlling the inspection process in a laboratory. The method includes: structurally decomposing the task links in the inspection process, obtaining the inspection nodes of different links, establishing directed connections between the inspection nodes according to the execution sequence and timestamp order of different inspection nodes, and constructing a process state evolution diagram; constructing inspection node state vectors based on time consumption characteristic parameters, risk characteristic parameters, and resource occupancy parameters; constructing inspection node control cost functions based on the inspection node state vectors, mapping time consumption characteristics, risk characteristics, and resource occupancy to control costs, and accumulating the control costs of each inspection node on the process path to obtain the cumulative cost of the corresponding inspection path; optimizing the inspection node paths based on the process state evolution diagram and the control costs of each inspection node, obtaining the target control inspection path with the minimum global cost from all feasible paths, thereby realizing dynamic scheduling and control of the inspection process, improving the efficiency of inspection process control, and reducing inspection risks.

Description

Technical Field

[0001] This application relates to the field of laboratory testing process control technology, specifically a laboratory testing process control method and system. Background Technology

[0002] With advancements in medical testing technology, particularly in medical imaging, molecular biology, and clinical laboratory testing, the workload of laboratory testing is increasing significantly. Modern laboratories integrate various high-throughput analyzers, such as biochemical, immunological, and hematological analyzers, onto a unified hardware platform via tracks, achieving fully automated workflow from sample collection and preprocessing to detection and storage. However, while increasing processing capacity, complex automated systems also face the challenge of dynamic scheduling under conflicting multi-objective conditions.

[0003] Existing laboratory information management systems and pipeline control software primarily rely on static rules or preset linear logic for task allocation. This approach exhibits significant limitations when dealing with complex and ever-changing clinical scenarios. For example, current scheduling strategies typically focus on the operational status of a single node. When a single node in the pipeline experiences suboptimal performance or hardware failure, existing technologies often employ circuit breaker shutdowns or manual intervention, lacking the capability for automatic path rewriting and self-healing scheduling based on real-time cost assessment. Therefore, effective process control and optimization strategies are particularly important. Summary of the Invention

[0004] To overcome the aforementioned problems in the prior art, this application provides a method and system, which adopts the following technical solution:

[0005] Firstly, this application provides a method for controlling the laboratory testing process, including:

[0006] The task steps in the inspection process are decomposed in a structured manner to obtain the inspection nodes of different steps. Based on the execution sequence and timestamp order of different inspection nodes, a directed connection relationship is established between the inspection nodes, and a directed process state evolution diagram is constructed.

[0007] Extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and construct the inspection node state vector.

[0008] Based on the state vector of the inspection node, a control cost function for the inspection node is constructed, which maps the time consumption characteristics, risk characteristics, and resource occupation into control costs. The control costs of each inspection node on the process path are cumulatively added in a directed manner to obtain the cumulative cost of the corresponding inspection path.

[0009] Based on the process state evolution diagram and the control cost of each inspection node, the inspection node path is optimized, and the target control inspection path with the minimum global cost is obtained from all feasible paths.

[0010] Based on the target control inspection path, a corresponding process control strategy is generated. By applying the process control strategy to the inspection process, dynamic scheduling and control of the inspection process can be achieved.

[0011] Furthermore, the tasks in the inspection process are broken down into structural steps, including:

[0012] Based on historical inspection process data, the complexity index of different inspection steps is calculated. When the complexity index exceeds the preset threshold, the corresponding inspection step is refined into multiple sub-inspection nodes. When the complexity index is lower than the preset threshold, adjacent inspection nodes are merged to form a dynamically adjusted set of inspection nodes.

[0013] Furthermore, based on the execution sequence and timestamp order of different inspection nodes, directed connections are established between the inspection nodes, including:

[0014] Based on historical data mining of the dependencies between nodes, a node state influence function is constructed to calculate the influence strength of the current node on the state distribution of subsequent nodes and obtain the dependency strength index. When the dependency strength index exceeds a preset threshold, an enhancement edge is added to the process state evolution graph to form a composite directed graph structure.

[0015] Furthermore, the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram are extracted to construct the inspection node state vector, including: when the time consumption characteristic parameter or risk characteristic parameter in the node state vector changes abruptly, a topology reconstruction operation is triggered, including inspection path redirection and bypass path generation.

[0016] Furthermore, the process state evolution diagram is restructured topologically, including: restructuring the process state evolution diagram topologically by comparing the changes between the current state vector and the historical state vector, determining the node to be restructured and tested, calculating the connection weights between the node to be restructured and other nodes, and by evaluating the path connection weights and the load capacity and processing speed of different paths, redirecting the task of the node to be restructured and tested to other nodes or generating a bypass path.

[0017] Furthermore, based on the state vector of the inspection node, a control cost function for the inspection node is constructed, mapping time consumption characteristics, risk characteristics, and resource consumption to control costs, including: ,in The cost scalar, generated by weighted summation, represents the overall resistance to the task currently being performed by this node. , , This represents the corresponding weight parameter.

[0018] Furthermore, the control costs of each inspection node along the process path are cumulatively summed in a directed manner to obtain the cumulative cost of the corresponding inspection path, including: the control cost of each node based on the state change function. Make corrections, accumulate the control costs of all nodes on the given test path, and construct a cumulative cost function. ,in Indicates the first The control cost of each inspection node This indicates the total number of inspection nodes included in the current inspection path. This represents the additional cost of the transfer process between nodes. An index representing the connection relationship between adjacent nodes during transit.

[0019] Secondly, this application also provides a laboratory testing process control system, including:

[0020] A directed process state evolution graph module is constructed to structurally decompose the task links in the inspection process, obtain the inspection nodes of different links, establish directed connection relationships between inspection nodes according to the execution sequence and timestamp order of different inspection nodes, and construct a directed process state evolution graph.

[0021] A module for constructing inspection node state vectors is used to extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and to construct the inspection node state vector.

[0022] The cumulative cost acquisition module is used to construct the control cost function of the inspection node based on the inspection node state vector, map the time consumption characteristics, risk characteristics and resource occupation into control costs, and perform directed accumulation of the control costs of each inspection node on the process path to obtain the cumulative cost of the corresponding inspection path.

[0023] The target control inspection path generation module is used to optimize the inspection node path based on the process state evolution diagram and the control cost of each inspection node, and obtain the target control inspection path with the minimum global cost from all feasible paths.

[0024] The dynamic scheduling and control module is used to generate corresponding process control strategies based on the target control inspection path. By applying the process control strategies to the inspection process, dynamic scheduling and control of the inspection process can be achieved.

[0025] Thirdly, this application provides an electronic device, comprising:

[0026] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the method as described in the first aspect.

[0027] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect.

[0028] Fifthly, this application provides a computer program that, when executed by a computer, performs the method described in the first aspect.

[0029] In one possible design, the program in the fifth aspect can be stored wholly or partially on a storage medium packaged with the processor, or it can be stored wholly or partially on a memory not packaged with the processor.

[0030] This application has the following beneficial effects:

[0031] 1. This application decomposes the various processes of inspection into independent process nodes and establishes directed connections between these nodes. This enables accurate process control and scheduling. By calculating the state vectors of the inspection nodes, the operating status of each node can be obtained in real time, optimizing the execution order of the inspection process, minimizing unnecessary time consumption and resource occupation, and improving the overall efficiency of the inspection process. For example, by optimizing the selection of inspection paths, samples can be transmitted to the target device in the shortest possible time, avoiding unnecessary waiting time.

[0032] 2. This application establishes a control cost function to quantify the time consumption, risk level, and resource consumption of each stage, evaluates the global cost of each feasible path, and selects the target control path with the minimum global cost to ensure optimal allocation of testing resources, avoid excessive resource consumption and equipment overload, and reduce resource waste. Simultaneously, based on the identification of abnormal nodes, path redirection is used to promptly prevent risks from occurring, ensuring the reliability of the detection results.

[0033] 3. This application achieves dynamic scheduling and control of the testing process by optimizing the process path and generating control strategies. It adaptively adjusts based on actual execution conditions. For example, a sample priority ranking strategy ensures that urgent samples are processed first, while a sample diversion strategy dynamically adjusts the task flow based on the load status of each node, avoiding overload or resource bottlenecks in any stage. Simultaneously, through equipment allocation strategies, it can select lighter-loaded and healthier equipment for sample processing in real time, improving equipment utilization and reducing the risk of equipment failure.

[0034] 4. By constructing a process state evolution diagram, this application can comprehensively understand the state evolution of the entire inspection process. Through the dynamic update of node state vectors, the processing time, risk level, and resource consumption of each node can be predicted in real time, allowing for advance adjustment of inspection paths and resource scheduling, thereby reducing the uncertainty in the execution of the inspection process.

[0035] 5. This application optimizes the sample transport path, testing equipment, and task allocation to avoid overload of a certain link or equipment, maintain a balanced workload of each link, and improve the testing response speed and processing capacity. For example, when the equipment is overloaded or in poor condition, the task is automatically redirected to the equipment with a lighter load or in good condition to ensure that each testing task can be processed in a timely manner and avoid delays or process stagnation caused by equipment problems. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of a laboratory testing process control method according to an embodiment of this application;

[0037] Figure 2 This is a flowchart illustrating the breakdown of the inspection process in an embodiment of this application.

[0038] Figure 3 This is a flowchart illustrating the construction process of the composite directed graph structure according to an embodiment of this application.

[0039] Figure 4 This is a flowchart illustrating the determination of the target control inspection path in an embodiment of this application.

[0040] Figure 5 This is a system flowchart of an embodiment of this application. Detailed Implementation

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0042] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0043] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0044] Please refer to Figure 1 The above is a flowchart illustrating a laboratory testing process control method provided in an embodiment of this application. The specific implementation process is as follows:

[0045] Step 110: Decompose the task links in the inspection process in a structured manner, obtain the inspection nodes of different links, establish the directed connection relationship between the inspection nodes according to the execution relationship and timestamp order of different inspection nodes, and construct a directed process state evolution diagram.

[0046] In this embodiment, the task steps in the inspection process are structurally broken down. Please refer to [reference needed]. Figure 2 The specific content includes:

[0047] Step 21: Calculate the complexity index for different inspection stages based on historical inspection process data. The complexity index includes processing time coefficient, anomaly frequency, and resource consumption intensity. The complexity function can be expressed as: ,in , , These are the weighting coefficients. To handle the duration factor, This represents the frequency of anomalies. This refers to the intensity of resource consumption.

[0048] Step 22, when the complexity index If the threshold is exceeded, the corresponding inspection step will be broken down into multiple sub-inspection nodes; when the complexity index... When the value falls below a preset threshold, adjacent inspection nodes are merged to form a dynamically adjusted set of inspection nodes. This application decomposes or merges inspection nodes, making the division of inspection nodes not fixed and allowing for adaptive adjustment as the complexity of inspection operations changes.

[0049] It should be noted that the processing time coefficient represents an indicator describing the time stability and efficiency characteristics of the current process node during execution. It reflects the dispersion and fluctuation level of processing time and is obtained based on the ratio of the standard deviation of processing time to the mean of processing time. When the processing time coefficient is large, that is, exceeds the preset threshold, it indicates that the processing time of the corresponding node is unstable, with obvious random fluctuations or potential sources of interference.

[0050] Anomaly frequency represents the probability of an abnormal event occurring at a certain process node during operation. It indicates the reliability and risk index of the node and is obtained by comparing the number of times anomalies occur at the corresponding node within a statistical period to the total number of times the corresponding node is executed. A higher anomaly frequency indicates a higher degree of uncertainty for the corresponding node, which can be mitigated by providing risk penalty measures.

[0051] Resource occupancy intensity indicates the degree to which a node utilizes critical resources, representing its load level. It can be obtained by comparing the amount of resources occupied to the total capacity of the corresponding resources within a statistical period. Higher resource occupancy intensity indicates that the corresponding node is under high load or congestion, which increases waiting time and the probability of concurrent conflicts.

[0052] In this embodiment, a directed connection relationship is established between the inspection nodes based on their execution order and timestamp sequence. Please refer to [reference needed]. Figure 3 ,include:

[0053] Step 31: Based on historical data, mine the dependencies between nodes and construct a node state influence function. Calculate the influence strength of the current node on the state distribution of subsequent nodes to obtain the dependency strength index. ,in Represents a node For nodes The intensity of the impact, Represents a node State events, Represents a node State events, Indicates at node In a specific state Under the condition, node Status The conditional probability represents the conditional triggering relationship; Represents a node Status The unconditional probability of represents the level of spontaneous occurrence. When Time represents node State changes will enhance nodes The occurrence The probability of is positively dependent, when Time represents node State changes will inhibit nodes The occurrence The probability when Represents a node With nodes They are approximately independent.

[0054] Step 32, when the dependence strength index When the threshold is exceeded, an enhanced edge is added to the process state evolution diagram to form an implicit set edge. A composite directed graph structure is constructed by using dynamic node sets and explicit and implicit set edges. ,in This indicates the display of set edges. This application, by establishing the dependency strength relationship between the current node and subsequent nodes, can uncover deep associations not reflected in the traditional verification process definition.

[0055] For example, when a sampling node detects abnormal blood sample viscosity, i.e., discovers a hidden factor, the back-end testing node can increase the washing frequency or adjust the dilution factor, without waiting for the corresponding blood sample to reach the corresponding testing site, and send a pre-test instruction to the remote subsequent node by adding a contract.

[0056] Step 120: Extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and construct the inspection node state vector.

[0057] It should be noted that the time consumption characteristic parameters include node processing time, waiting time, etc.; the risk characteristic parameters are risk characteristic parameters such as anomaly probability and contamination probability extracted from sample data and detection image or signal data; the resource usage parameters are equipment load, resource usage, etc. extracted from equipment operation data; and the node state vector represents the resource usage of the corresponding node at the current moment.

[0058] In this embodiment, the time consumption characteristic parameter is the access time, processing time, and queuing time of the test specimen when it passes through any physical node, collected via radio frequency identification. The risk characteristic parameter is the pressure pulsation curve of the biochemical analyzer sampling needle acquired in real time. Instantaneous pressure fluctuations during the sampling process are identified through signal processing to determine whether the test specimen contains microscopic clots or fibrin interference.

[0059] In this embodiment of the application, constructing the test node state vector includes obtaining the time consumption feature parameters for each node. Risk characteristic parameters and resource usage parameters Perform fusion to obtain the state vector of the test node. .

[0060] Step 130: Based on the inspection node state vector, construct the inspection node control cost function, map the time consumption characteristics, risk characteristics and resource occupation into control costs, and perform directed accumulation of the control costs of each inspection node on the process path to obtain the cumulative cost of the corresponding inspection path.

[0061] In this embodiment of the application, a control cost function for the inspection node is constructed based on the inspection node state vector, mapping time consumption characteristics, risk characteristics, and resource consumption to control costs, including: ,in The cost scalar, generated by weighted summation, represents the overall resistance to the task currently being performed by this node. , , This represents the corresponding weighting parameters. For time consumption feature mapping, the actual dwell time is compared with the standard turnaround time threshold of the test item using a deviation penalty function. When it approaches or exceeds the preset threshold, the cost of the time consumption feature increases exponentially, achieving congestion penalty. Risk features are mapped using a vulnerability assessment model; the higher the risk coefficient, the higher the potential retesting cost and the greater the risk cost. The remaining reagent quantity of the equipment is mapped to resource occupancy cost through energy efficiency balancing; when under high load, the resource occupancy cost is increased.

[0062] In this embodiment of the application, the control costs of each inspection node on the process path are cumulatively summed in a directed manner to obtain the cumulative cost of the corresponding inspection path, including:

[0063] Control cost of each node based on state change function Make corrections, accumulate the control costs of all nodes on the given test path, and construct a cumulative cost function. ,in Indicates the first The control cost of each inspection node This indicates the total number of inspection nodes included in the current inspection path. This represents the additional costs associated with the transfer between nodes, such as the power consumption of logistics robots and the risks involved in transportation. This index represents the connection relationship between adjacent nodes during transit. By directionally accumulating the control costs of all nodes on the path and combining this with the additional costs of transit links between nodes, the execution cost of the test path is comprehensively evaluated. The additional cost of each transit link is dynamically adjusted based on real-time data to reflect the actual situation of the operation.

[0064] In this embodiment, the control cost of each node is based on the state change function. The correction includes: when the state change of a node exceeds a preset threshold, calculating the control cost based on the state characteristics of the state node. ,in It is a function that adjusts the control cost based on the change in state. The adjustment function can be based on linear adjustment, exponential decay, or threshold judgment, etc. This represents the change in state. The control cost of a node is recalculated after each state vector update.

[0065] Step 140: Based on the process state evolution diagram and the control cost of each inspection node, perform inspection node path optimization, and obtain the target control inspection path with the minimum global cost from all feasible paths.

[0066] Specifically, based on the process state evolution diagram and the control cost of each inspection node, inspection node path optimization is performed. The target control inspection path with the minimum global cost is obtained from all feasible paths. Please refer to [reference needed]. Figure 4 The specific implementation process includes:

[0067] Step 41: Based on the combination of test items corresponding to the test specimens, search all logically reachable paths through graph traversal in the process state evolution diagram to obtain a set of candidate test paths. Remove paths that do not meet the preset medical timeliness constraints or violate biosafety sequence constraints to obtain an initial set of feasible test paths that meet the test task rules.

[0068] It should be noted that during the search process, the operating status parameters of the equipment are introduced in real time, and abnormal inspection nodes are marked. By increasing the cost weight of abnormal inspection nodes, abnormal inspection nodes are transformed into high-resistance nodes, thus avoiding abnormal nodes during the inspection path search process.

[0069] Step 42: Construct an evaluation function based on the cumulative cost of each path in the initial feasible path test path set. ,in This represents the estimated minimum cost from the current node to the target node. It is calculated by starting from the initial node, expanding to each adjacent node, calculating the cumulative cost from the initial node to the current node, and combining this with the estimated cost from the current node to the target node to obtain a comprehensive evaluation value. The comprehensive evaluation values ​​of all candidate nodes are sorted, and the node with the lowest cost is selected for expansion to obtain the test path with the lowest comprehensive evaluation value.

[0070] The optimal testing path is obtained by continuously adjusting and updating the estimated value of the path evaluation function during the search process.

[0071] Among them, the estimated minimum cost It is constructed based on the predicted values ​​of remaining path time consumption characteristics, risk characteristics, and resource consumption. Among them, It is a node The estimated time consumption, It checks adjacent nodes on the path. arrive The risk assessment value represents the transmission risk between nodes. Represents a node Resource consumption assessment is performed. Specifically, regression analysis based on historical data is used to predict the time required for each node to process each task in the current state. Future time consumption characteristics can be predicted using regression analysis or time series forecasting models. The risk level of the current inspection path is predicted using a classification model based on historical fault data. Classification models can employ support vector machines, decision trees, etc., which will not be elaborated upon here. The resource consumption of each node is predicted based on queuing theory.

[0072] In this embodiment, when the time consumption feature parameter or risk feature parameter in the node state vector undergoes a sudden change, a topology reconstruction operation is triggered, including path redirection verification and bypass path generation. Specifically, a state change function is defined. When the change in state When the preset threshold is exceeded, the process state evolution diagram is topologically reconstructed. By reconstructing the process state evolution diagram, it can dynamically change with the real-time resource consumption of the inspection, possessing online adaptability and avoiding static inspection process failure issues. For at any time nodes At least one of the time consumption characteristic parameters and risk characteristic parameters. It represents the historical state record of the previous moment.

[0073] It should be noted that the topology reconstruction operation is based on the state changes of the nodes and dynamically adjusts the graph structure, including but not limited to path redirection and bypass path generation. In the specific implementation process, it depends on the changes of time parameters or risk parameters in the node state vector. When the time parameters or risk parameters change abruptly, it will trigger the automatic adjustment of the graph structure.

[0074] When a certain inspection node is unable to continue executing the inspection task due to overload, failure, or insufficient resources, path redirection will transfer the task or data flow to an alternative path or other node for processing, avoiding the inspection task from stalling or being delayed, and ensuring that the process continues to run.

[0075] Bypass path generation is based on the normal inspection path and generates a parallel bypass inspection path according to specific needs or priorities. It is used to accelerate the inspection process, reduce the burden on critical inspection paths, or handle urgent tasks under specific conditions.

[0076] Specifically, topology reconstruction of the process state evolution diagram involves comparing the changes between the current state vector and the historical state vector to determine the nodes to be reconstructed and tested. For each node to be reconstructed and tested, connection weights are calculated between it and other nodes. These connection weights include node processing capacity, execution time, risk level, and resource usage. By evaluating path connection weights and the load capacity and processing speed of different paths, the tasks of the node to be reconstructed and tested are redirected to other nodes or bypass paths are generated. The path connection weights are... ,in , , Indicates the weighting coefficient. , and This represents the increment in time consumption, risk level, and resource usage. , Representing nodes respectively and nodes The load capacity reflects the node's resource consumption and processing power, among which The cost of testing path connectivity can be adjusted through weighted and nonlinear adjustments.

[0077] In one possible implementation, ,in This represents an adjustment factor that controls the impact of load capacity on cost. This application is approved. The process of selecting the inspection path is optimized based on the actual load and resource status.

[0078] It should be noted that topology reconstruction of the process state evolution diagram is performed by comparing the changes between the current state vector and the historical state vector to determine the node to be reconstructed. This includes: if the change between the current state vector and the historical state vector exceeds a preset threshold, then the current node is an affected node and needs to be reconstructed.

[0079] Step 150: Generate a corresponding process control strategy based on the target control inspection path, and apply the process control strategy to the inspection process to achieve dynamic scheduling and control of the inspection process.

[0080] In the embodiments of this application, the control strategy includes sample priority sorting, sample diversion, testing equipment allocation, and transfer path adjustment. By applying the control strategy to the actual testing process, dynamic scheduling and control of the execution order, resource allocation, and processing rhythm of different testing links are achieved, thereby improving the efficiency of testing process control and reducing testing risks.

[0081] Please refer to Figure 5This is a block diagram of a laboratory testing process control system provided in an embodiment of this application. The specific modules include:

[0082] The module 510 for constructing a directed process state evolution graph is used to structurally decompose the task links in the inspection process, obtain the inspection nodes of different links, establish directed connection relationships between inspection nodes according to the execution relationship and timestamp order of different inspection nodes, and construct a directed process state evolution graph.

[0083] The module 520 for constructing inspection node state vectors is used to extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and to construct the inspection node state vector.

[0084] The cumulative cost acquisition module 530 is used to construct the control cost function of the inspection node based on the inspection node state vector, map the time consumption characteristics, risk characteristics and resource occupation into control costs, and perform directed accumulation of the control costs of each inspection node on the process path to obtain the cumulative cost of the corresponding inspection path.

[0085] The target control inspection path generation module 540 is used to optimize the inspection node path based on the process state evolution diagram and the control cost of each inspection node, and obtain the target control inspection path with the minimum global cost from all feasible paths.

[0086] The dynamic scheduling and control module 550 is used to generate corresponding process control strategies based on the target control inspection path. By applying the process control strategies to the inspection process, dynamic scheduling and control of the inspection process can be achieved.

[0087] This application structurally decomposes the task stages in the inspection process to obtain inspection nodes at different stages. Based on the sequential execution and timestamp order of these inspection nodes, directed connections are established between them, constructing a process state evolution diagram. A state vector for each inspection node is constructed based on time consumption, risk, and resource usage parameters. A control cost function for each inspection node is then built, mapping time consumption, risk, and resource usage to control costs. The control costs of each inspection node along the process path are cumulatively accumulated to obtain the cumulative cost of the corresponding inspection path. Based on the process state evolution diagram and the control costs of each inspection node, inspection node paths are optimized. The target control inspection path with the minimum global cost is selected from all feasible paths, enabling dynamic scheduling and control of the inspection process, improving control efficiency, and reducing inspection risks.

[0088] This application also provides another embodiment, namely, a non-volatile computer-readable storage medium storing a program for a laboratory testing process control method, which can be executed by at least one processor to perform the steps of the laboratory testing process control method as described above.

[0089] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0090] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method for controlling the testing process in a clinical laboratory, characterized in that, include: The task steps in the inspection process are decomposed in a structured manner to obtain the inspection nodes of different steps. Based on the execution relationship and timestamp order of different inspection nodes, a directed connection relationship between inspection nodes is established to construct a directed process state evolution diagram. Extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and construct the inspection node state vector; Based on the state vector of the inspection node, a control cost function for the inspection node is constructed, which maps the time consumption characteristics, risk characteristics and resource occupation into control costs. The control costs of each inspection node on the process path are cumulatively added in a directed manner to obtain the cumulative cost of the corresponding inspection path. Based on the process state evolution diagram and the control cost of each inspection node, the inspection node path is optimized, and the target control inspection path with the minimum global cost is obtained from all feasible paths. Based on the target control inspection path, a corresponding process control strategy is generated. By applying the process control strategy to the inspection process, dynamic scheduling and control of the inspection process can be achieved.

2. The laboratory testing process control method according to claim 1, characterized in that, The task steps in the inspection process are broken down into a structured manner, including: Based on historical inspection process data, the complexity index of different inspection steps is calculated. When the complexity index exceeds the preset threshold, the corresponding inspection step is refined into multiple sub-inspection nodes. When the complexity index is lower than the preset threshold, adjacent inspection nodes are merged to form a dynamically adjusted set of inspection nodes.

3. The laboratory testing process control method according to claim 1, characterized in that, Based on the execution sequence and timestamp order of different inspection nodes, a directed connection relationship is established between the inspection nodes, including: Based on historical data mining of the dependencies between nodes, a node state influence function is constructed to calculate the influence strength of the current node on the state distribution of subsequent nodes and obtain the dependency strength index. When the dependency strength index exceeds a preset threshold, an enhancement edge is added to the process state evolution graph to form a composite directed graph structure.

4. The laboratory testing process control method according to claim 1, characterized in that, Extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and construct the inspection node state vector, including: When the time consumption feature parameter or risk feature parameter in the node state vector changes abruptly, a topology reconstruction operation is triggered, including verification path redirection and bypass path generation.

5. The laboratory testing process control method according to claim 4, characterized in that, The process state evolution diagram is restructured topologically, including: Topology reconstruction of the process state evolution diagram involves comparing the changes between the current state vector and the historical state vector to determine the nodes to be reconstructed and tested. For the nodes to be reconstructed and tested, the connection weights between them and other nodes are calculated. By evaluating the path connection weights and the load capacity and processing speed of different paths, the tasks of the nodes to be reconstructed and tested are redirected to other nodes or bypass paths are generated.

6. The laboratory testing process control method according to claim 1, characterized in that, Based on the state vector of the inspection node, a control cost function for the inspection node is constructed, mapping time consumption characteristics, risk characteristics, and resource consumption to control costs, including: ,in The cost scalar, generated by weighted summation, represents the overall resistance to the task currently being performed by this node. , , This represents the corresponding weight parameter.

7. The laboratory testing process control method according to claim 6, characterized in that, The control costs of each inspection node along the process path are cumulatively summed in a directed manner to obtain the cumulative cost of the corresponding inspection path, including: Control cost of each node based on state change function Make corrections, accumulate the control costs of all nodes on the given test path, and construct a cumulative cost function. ,in Indicates the first The control cost of each inspection node This indicates the total number of inspection nodes included in the current inspection path. This represents the additional cost of the transfer process between nodes. An index representing the connection relationship between adjacent nodes during transit.

8. The laboratory testing process control method according to claim 7, characterized in that, Control cost of each node based on state change function The correction includes: when the state change of a node exceeds a preset threshold, calculating the control cost based on the state characteristics of the state node. ,in It is a function that adjusts the control cost based on the change in state. The adjustment function can be based on linear adjustment, exponential decay, or threshold judgment, etc. It represents the change in state.

9. A laboratory testing process control method according to claim 1, characterized in that, Based on the process state evolution diagram and the control cost of each inspection node, inspection node path optimization is performed. The target control inspection path with the minimum global cost is obtained from all feasible paths, including: Based on the combination of test items corresponding to the test specimens, search all logically reachable paths from the process state evolution diagram through graph traversal to obtain a set of candidate test paths, and obtain an initial set of feasible test paths that satisfy the test task rules from the set of candidate test paths. Based on the cumulative cost of each path in the initial set of feasible test paths, an evaluation function is constructed. Starting from the starting test node, the evaluation function is expanded to each adjacent node, and the cumulative cost from the starting node to the current node is calculated. Combined with the estimated cost from the current node to the target node, a comprehensive evaluation value is obtained. The comprehensive evaluation values ​​of all candidate nodes are sorted, and the node with the lowest cost is selected for expansion to obtain the test path with the lowest comprehensive evaluation value.

10. A laboratory testing process control system, used to implement the method described in any one of claims 1-9, characterized in that, include: A directed process state evolution graph module is used to structurally decompose the task links in the inspection process, obtain the inspection nodes of different links, establish directed connection relationships between inspection nodes according to the execution relationship and timestamp order of different inspection nodes, and construct a directed process state evolution graph. A module for constructing inspection node state vectors is used to extract the time consumption characteristic parameters, risk characteristic parameters, and resource consumption parameters corresponding to each inspection node in the process state evolution diagram, and to construct the inspection node state vector. The cumulative cost acquisition module is used to construct the control cost function of the inspection node based on the inspection node state vector, map the time consumption characteristics, risk characteristics and resource occupation into control costs, and perform directed accumulation of the control costs of each inspection node on the process path to obtain the cumulative cost of the corresponding inspection path. The target control inspection path generation module is used to optimize the inspection node path based on the process state evolution diagram and the control cost of each inspection node, and to obtain the target control inspection path with the minimum global cost from all feasible paths. The dynamic scheduling and control module is used to generate corresponding process control strategies based on the target control inspection path. By applying the process control strategies to the inspection process, dynamic scheduling and control of the inspection process can be achieved.

Images