Data analysis platform management method and system

Abstract

The invention discloses a data analysis platform management method and system, and belongs to the technical field of computer data processing, and the method comprises the steps: obtaining multi-source heterogeneous data from a medical information system; establishing a cross-system data association model, performing dynamic feature extraction and weight distribution on multi-source heterogeneous data, and outputting a resource supply-demand relationship graph; analyzing the resource supply-demand relation graph, and identifying business conflicts in medical resource scheduling; generating a conflict solution of the business conflict based on a multi-objective optimization algorithm, and generating an execution instruction; and issuing an execution instruction to the target medical system, verifying an execution result of the execution instruction, and updating system parameters. According to the method, a cross-system dynamic modeling and multi-objective optimization strategy is adopted, and a closed-loop verification mechanism and a multi-source heterogeneous data fusion technology are combined, so that intelligent prediction, accurate scheduling and self-learning optimization of medical resource conflicts can be realized, full-process traceable execution of high-value consumables is ensured, and the resource utilization efficiency and the emergency response capability are comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and in particular to a data analysis platform management method and system. Background Art

[0002] At present, the scheduling of medical resources faces the problem of difficulty in integrating multi-source heterogeneous data. The independent operation of various systems within the hospital has led to the widespread phenomenon of data silos. Patient diagnosis and treatment, consumable inventory and equipment operation data are scattered on different platforms and the format is not standardized, making it difficult to achieve dynamic perception and real-time response to business needs. Resource conflicts mainly rely on manual experience to identify, and there are defects such as delayed warning of supply and demand imbalances and inaccurate priority determination of emergency tasks, which are particularly prone to mismatch risks of key resources in large-scale emergencies.

[0003] Traditional solutions focus on local optimization of a single system, using periodic data batch processing and static rule engines for resource matching. For example, limited data interoperability is achieved through basic database association technology, or resource warning lines are set using fixed thresholds. Some systems introduce linear programming models to optimize path selection, but fail to effectively integrate spatiotemporal dynamic parameters and multi-dimensional constraints, resulting in large deviations between decision-making and actual execution. Such methods lack adaptive tuning capabilities when faced with complex and changing medical scenarios, and cannot support cross-hospital collaboration needs.

[0004] Existing technologies have problems such as single modeling dimension and lack of real-time feedback when processing cross-system data. The static weight allocation mechanism is difficult to capture dynamic changes in business, which can easily lead to rigid algorithmic decision-making. At the same time, the medical resource scheduling process lacks a closed-loop verification mechanism, the execution effect is difficult to quantify and evaluate, and historical experience has not been fully converted into a basis for model optimization. In addition, the security verification methods for high-value consumables scheduling are fragmented, and there are shortcomings such as difficulty in tracing operational risks and low emergency response efficiency, which makes it difficult to meet the requirements of refined management of modern medical care. Summary of the invention

[0005] To solve the above problems, the present invention provides a data analysis platform management method and system, which adopts cross-system dynamic modeling and multi-objective optimization strategy, combined with closed-loop verification mechanism and multi-source heterogeneous data fusion technology, can realize intelligent prediction, precise scheduling and self-learning optimization of medical resource conflicts, ensure the traceability of the entire process of high-value consumables, and comprehensively improve resource utilization efficiency and emergency response capabilities.

[0006] The above objectives can be achieved through the following solutions: A data analysis platform management method comprises acquiring multi-source heterogeneous data from a medical information system, the data comprising patient diagnosis and treatment data, medical consumables data and equipment operation data; establishing a cross-system data association model, dynamically extracting features and allocating weights for the multi-source heterogeneous data, and outputting a resource supply and demand relationship map; analyzing the resource supply and demand relationship map, identifying business conflicts in medical resource scheduling; generating conflict resolution solutions for the business conflicts based on a multi-objective optimization algorithm, and generating execution instructions; issuing the execution instructions to a target medical system, the instructions comprising a resource scheduling path and time constraints; verifying the execution results of the execution instructions and updating system parameters.

[0007] Optionally, the acquisition of multi-source heterogeneous data from the medical information system includes: connecting the electronic medical record system and the material management system through a standardized protocol conversion module, and outputting a structured interface data stream; based on the structured interface data stream, identifying the treatment type keywords and consumable identification code segments in the medical order text, and converting the unstructured data into medical resource tags in a unified coding format; according to the attribute characteristics of the medical resource tags, adjusting the data collection mode according to a preset time period, the data collection mode includes: real-time data processing mode, capturing key fields at a frequency of seconds; batch update mode, integrating all-day data to generate incremental update packages.

[0008] Optionally, the establishment of a cross-system data association model, dynamic feature extraction and weight assignment of the multi-source heterogeneous data, and output of a resource supply and demand relationship map include: constructing a three-dimensional feature coordinate system, the dimensions of which include business type, data format and timeliness level, and generating an initial feature vector set; based on the initial feature vector set, establishing a dynamic weight adjustment mechanism, when it is detected that the frequency of application for the same type of consumables exceeds a preset frequency threshold, calculating the weight increase parameter through a sliding window algorithm, and adjusting the feature vector in the initial feature vector set; inputting the adjusted feature vector into a preset graph database, constructing a multi-level association relationship between nodes, and outputting a resource supply and demand relationship map.

[0009] Optionally, the identification of business conflicts in medical resource scheduling includes: scanning multi-system data records of medical resources, extracting a three-value difference set of inventory quantity, allocated quantity, and in-transit quantity; based on the difference set, analyzing the spatiotemporal matching degree of operating room reservation data and consumables inventory data, and locating the conflict coordinates; and calculating the conflict level and generating a conflict warning signal based on the node parameters of the resource supply and demand relationship map.

[0010] Optionally, the conflict resolution solution for the business conflict generated based on the multi-objective optimization algorithm includes: receiving the conflict warning signal, configuring a time priority strategy for clinical treatment decisions and a cost priority strategy for administrative material decisions; generating a multi-path scheduling plan based on the resource supply and demand relationship map, including intra-hospital adjustments, emergency inventory calls, and cross-hospital transfers; executing a database based on a preset historical scheduling plan, predicting and calculating the time deviation rate, cost deviation value, and feasibility of each plan, and generating a three-dimensional decision matrix; and selecting a scheduling plan using the three-dimensional decision matrix.

[0011] Optionally, sending the execution instruction to the target medical system includes: decomposing the selected scheduling plan into standardized instruction units, each instruction unit containing a target system identifier, an operation content code, and an expiration mark; setting up electronic tag verification points on the consumables transfer path, collecting and feeding back consumables coordinates and timestamps; and activating a double electronic signature confirmation mechanism when a high-value consumables scheduling instruction is detected.

[0012] Optionally, verifying the execution result of the execution instruction and updating the system parameters includes: based on the consumable coordinates and timestamp, real-time acquisition of consumable position data and timeliness data during the instruction execution process; based on the consumable position data and timeliness data, calculating the time deviation and space deviation between the actual execution path and the optimized path, generating a comprehensive deviation, and generating an alarm level based on the comprehensive deviation; based on the alarm level, triggering an immediate correction instruction for the weight gain parameter, and adjusting the weight gain parameter using the comprehensive deviation.

[0013] Optionally, verifying the execution result of the execution instruction and updating the system parameters also includes: integrating the execution results to construct an experience knowledge base, the experience knowledge base including successful case templates and exception handling reports; periodically adjusting system parameters based on historical data of the experience knowledge base; establishing a department execution energy efficiency score, and updating the weight of the corresponding node of the department in the resource supply and demand relationship map based on the score result.

[0014] Optionally, the method also includes: making anomaly judgment based on the spatial deviation, and when an anomaly is detected, loading the success case template and switching to a degraded mode; based on the success case template, calling the path data with the smallest average spatial deviation within a preset time window to generate an emergency scheduling plan; in the degraded mode, reducing the data collection frequency, simplifying label conversion, and allocating emergency resources according to the scoring results.

[0015] Based on the same inventive concept, the present invention also provides a data analysis platform management system, which includes: a data acquisition module, used to acquire multi-source heterogeneous data from a medical information system, the data including patient diagnosis and treatment data, medical consumables data and equipment operation data; a supply and demand relationship establishment module, used to establish a cross-system data association model, dynamically extract features and assign weights to the multi-source heterogeneous data, and output a resource supply and demand relationship map; a business conflict identification module, used to analyze the resource supply and demand relationship map, and identify business conflicts in medical resource scheduling; a decision generation module, used to generate a conflict resolution solution to the business conflict based on a multi-objective optimization algorithm, and generate an execution instruction; an instruction execution module, used to issue the execution instruction to the target medical system, the instruction including a resource scheduling path and time constraints; a closed-loop verification module, used to verify the execution result of the execution instruction and update system parameters.

[0016] Compared with the prior art, the present invention has the following advantages: 1. The present invention constructs an accurate resource supply and demand relationship map through standardized conversion and dynamic feature modeling of heterogeneous data such as electronic medical records, equipment operation, and consumable inventory, breaking through the data island limitations of traditional medical systems and significantly improving cross-departmental collaboration efficiency; it can automatically identify key resource bottlenecks and quantify conflict levels, providing global data support for complex scheduling scenarios; 2. Based on time-space matching analysis and multi-objective optimization algorithms, the present invention strikes a balance between timeliness priority and cost control, generating an optimal path that takes into account both emergency treatment needs and operational efficiency. Compared with traditional manual scheduling, it can quickly locate the conflicting nodes between operating room scheduling and inventory misalignment, and adaptively adjust decision-making strategies through historical experience databases to avoid the risk of delays caused by mismatch of medical resources. 3. The present invention uses electronic tag verification points to track the instruction execution path in real time, combines the time-space deviation to dynamically correct the model weight parameters, and establishes full-chain monitoring of the transportation process; continuously accumulates successful cases and abnormal handling experience, realizes the intelligent linkage between department energy efficiency scores and resource allocation weights, and promotes the continuous optimization and upgrading of medical resource allocation strategies; 4. Use dual electronic signatures and blockchain evidence storage technology to ensure that operations for dispatching critical medical supplies are traceable and permissions are verifiable; standardized instruction units and downgrade mode switching mechanisms effectively prevent the risk of abuse of medical resources while ensuring the continuity of core business, providing reliable technical support for refined management.

[0017] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a structural diagram of a data analysis platform management method according to an embodiment of the present invention.

[0020] Figure 2 is an initial feature vector distribution diagram of an embodiment of the present invention.

[0021] Figure 3 It is a schematic diagram of a weight gain adjustment curve according to an embodiment of the present invention.

[0022] Figure 4 Schematic diagram of the spatial structure of a three-dimensional decision matrix according to an embodiment of the present invention.

[0023] Figure 5 It is a resource scheduling deviation analysis bar chart according to an embodiment of the present invention.

[0024] Figure 6 It is a structural diagram of a data analysis platform management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Reference Figure 1 An embodiment of the present invention proposes a data analysis platform management method, which adopts cross-system dynamic modeling and multi-objective optimization strategy, combined with closed-loop verification mechanism and multi-source heterogeneous data fusion technology, can realize intelligent prediction, precise scheduling and self-learning optimization of medical resource conflicts, ensure the traceability of the entire process of high-value consumables, and comprehensively improve resource utilization efficiency and emergency response capabilities.

[0027] The method of this embodiment specifically includes: Acquire multi-source heterogeneous data from medical information systems, including patient diagnosis and treatment data, medical consumables data, and equipment operation data; Establish a cross-system data association model, perform dynamic feature extraction and weight allocation on the multi-source heterogeneous data, and output a resource supply and demand relationship map; Analyze the resource supply and demand relationship map to identify business conflicts in medical resource scheduling; Generate a conflict resolution method for the business conflict based on a multi-objective optimization algorithm and generate an execution instruction; Sending the execution instruction to the target medical system, wherein the instruction includes a resource scheduling path and a time constraint condition; Verify the execution result of the execution instruction and update system parameters.

[0028] Specifically, the present invention constructs a resource supply and demand relationship map through multi-source data fusion and dynamic modeling, uses a three-dimensional decision matrix to achieve conflict classification and optimal path selection, and combines electronic tag closed-loop verification to form a self-learning optimization mechanism. Break through the data island limitations of traditional systems to achieve global visualization and accurate prediction of cross-level medical resources; reduce reliance on manual experience through spatiotemporal matching analysis to improve decision-making efficiency in emergency scenarios; double verification mechanism to ensure the safety and compliance of medical resource scheduling; historical experience-driven model self-optimization to reduce repeated execution deviations. For example, after being applied in a tertiary hospital, it automatically calls cross-campus consumables resources in emergency rescue tasks and completes delivery within 30 minutes, which is better than the average time consumed in the traditional manual scheduling mode.

[0029] Optionally, the acquiring of multi-source heterogeneous data from a medical information system includes: Connect the electronic medical record system and the material management system through a standardized protocol conversion module, and output a structured interface data stream; Specifically, the HL7 v2.6 protocol adapter is deployed in the electronic medical record system (HIS) to define field mapping rules; the material management system (SPD) extracts the code through the UDI parser, and its encoding format is UDI = (01) [14-bit identification code] (17) [6-bit validity period] [other fields]; for example, "(01) 00884745041942 (17) 250831" is parsed into the product identifier 00884745041942, which is valid until August 31, 2025. Generate a structured data stream, the format of which is shown in Table 1.

[0030] Table 1 Data stream format table

[0031] For example, suppose a hospital needs to monitor the reserves of infusion consumables in different departments in real time, such as saline and antibiotics. The hospital's electronic medical record system records the infusion orders issued by doctors, such as "daily intravenous drip of ceftriaxone sodium 2g", and the material management system tracks the inventory batches and expiration dates of infusion bags in the warehouse. Through the universal protocol converter, the data of different systems are converted into a unified format. For example, the free text order "cefotaxime sodium 2g, q12h" in the electronic medical record and the UDI code of the warehouse, such as "valid until August 2025" are converted into a structured table, as shown in Table 2: Table 2 Structured table

[0032] Based on the structured interface data stream, identifying treatment type keywords and consumable identification code segments in the medical order text, and converting unstructured data into medical resource tags in a unified coding format; Specifically, based on the BiLSTM-CRF algorithm, word segmentation captures medical entities, and the medical order text outputs data in the format of {verb, noun, frequency} through the algorithm model; for example, the input "intravenous drip of ceftriaxone sodium, 2g, q12h" outputs the label {operation = intravenous drip, drug = ceftriaxone sodium, dose = 2g, frequency = every 12 hours}; key parameters are extracted according to the UDI coding structure, such as: Among them, the unstructured data output format is shown in Table 3.

[0033] Table 3 Example of unstructured data output results For example, a doctor's handwritten emergency order may be unstructured text, such as "Urgent! Prioritize immunoglobulin infusion for patient bed 5". Automatically extract keywords to obtain the treatment type of immunoglobulin infusion classified as "high priority biologics", the consumables are identified as matching the UDI code in the electronic label and converted to a standardized format, such as "Biologics-Immunoglobulin-Batch B15", and the emergency mark is automatically marked as "First-level response" based on "Urgent!". Free text orders are automatically translated into machine-readable labels for subsequent scheduling.

[0034] According to the attribute characteristics of the medical resource tag, the data collection mode is adjusted according to the preset time period, and the data collection mode includes: Real-time data processing mode, capturing key fields at a frequency of seconds; Batch update mode integrates all-day data to generate incremental update packages.

[0035] Specifically, the data collection mode is selected according to the time period. For example, the real-time data processing mode is adopted from 8:00 to 18:00, and the batch update mode is adopted from 0:00 to 6:00. Among them, the urgency label of the medical resource label is collected. When the urgency label is level 2 or level 1, the real-time data processing mode is adopted, and the collected data is {real-time orders, inventory changes, operating room status}, and the collection frequency is 0.5 seconds / time; in other cases, the collection frequency is 5 seconds / time.

[0036] Optionally, the establishing of a cross-system data association model, the dynamic feature extraction and weight allocation of the multi-source heterogeneous data, and the output of a resource supply and demand relationship map include: Constructing a three-dimensional feature coordinate system, wherein the dimensions of the three-dimensional feature coordinate system include business type, data format and timeliness level, and generating an initial feature vector set; Specifically, the scattered multi-source heterogeneous data, such as medical records, consumables identification, and inventory status, are unified into a quantifiable mathematical model. The business type dimension is to classify medical resources by purpose, such as surgical consumables, emergency drugs, and test reagents. The data format dimension is to unify the data expression form, such as structured tables, semi-structured JSON, and unstructured text. The timeliness level dimension is to classify according to the frequency of data updates, such as real-time, high / medium / low timeliness. Figure 2 As shown in the figure, each data entity is mapped to a three-dimensional coordinate point. For example, the feature vector of a surgical consumable can be (business type = surgical consumables, data format = structured data, timeliness level = high) converted to (X, Y, Z). The value ranges of different dimensions are normalized to generate an initial feature vector set. For example, the business type is assigned a numerical code, surgical consumables is 1, and emergency medicines are 2.

[0037] Based on the initial feature vector set, a dynamic weight adjustment mechanism is established. When it is detected that the frequency of claiming for the same type of consumables exceeds a preset frequency threshold, a weight increase parameter is calculated by a sliding window algorithm to adjust the feature vectors in the initial feature vector set; Specifically, the dynamic weight adjustment mechanism is as follows: Figure 3 As shown, the frequency threshold of the same type of consumables is preset, for example, if the same type of consumables are applied for more than 10 times per hour, the adjustment is triggered. The weight increase parameter calculated by the sliding window algorithm can be to count the application records in a certain time period, such as the last 30 minutes, and calculate the ratio of the actual frequency to the frequency threshold, that is: In the formula, is the weight increase parameter, is the actual frequency, is the frequency threshold, is the correction coefficient; for example, when the correction coefficient is 1, the frequency threshold is 10 times, and the actual frequency is 15 times, the weight increase parameter is 0.5, that is, the weight increases by 50%. The weight value of the feature vector is updated according to the weight increase parameter. For example, the consumable with an original weight of 1 is adjusted to 1.5. The adjustment formula is: In the formula, is the new weight of the feature vector, is the original weight of the feature vector.

[0038] The adjusted feature vector is input into the preset graph database, a multi-level association relationship between nodes is constructed, and a resource supply and demand relationship map is output.

[0039] Specifically, the complex relationships between data are visualized to support scheduling decisions. The adjusted feature vector is input into a graph database such as Neo4j, where each node represents an entity, such as a consumable, a department, or a surgical device. Node attributes carry three-dimensional feature data, such as consumable timeliness level and business type weight. Edge relationships are constructed based on dynamic weights, such as level 1 for the "supply and demand" relationship between consumables and departments, and level 2 for the "dependency call" relationship between departments and equipment. The weight of the edge is determined by dynamically adjusted parameters, such as edges with higher weights have darker colors or thicker connections. Finally, a visualized resource supply and demand relationship map is generated, such as a high-weight consumable associated with emergency surgical needs in multiple departments.

[0040] For example, suppose that a tertiary hospital has a surge in demand for oxygen cylinders due to the flu season, and needs to optimize resource scheduling immediately. The feature vector of the oxygen cylinder is mapped to (business type = emergency equipment, data format = structured UDI code, timeliness level = real-time), and the coordinates are converted to (5,2,8). The business type dimension range is 1-5, for example, 1 = ordinary equipment, 5 = emergency equipment, and the oxygen cylinder is assigned a value of 5 due to its high priority. It is detected that the frequency of oxygen cylinders in the respiratory department has reached 15 times within 30 minutes, and the frequency threshold is 10 times. Therefore, the weight increase parameter is calculated to be 0.5, so the weight is adjusted to 1.5 times the original value, so the oxygen cylinder timeliness level is increased from 8 to 12, and the priority is significantly improved. Then, the graph database modeling is carried out, and the nodes are the weight of the respiratory department 12, the weight of oxygen cylinder A 12, the weight of ICU 10, and the weight of oxygen supply vehicle 8. The edge is defined as the respiratory department to oxygen cylinder A, the edge weight = 12, the red thick line, high urgency; ICU to oxygen cylinder A, the edge weight = 8, the yellow middle line, medium demand. The graph shows that the respiratory department is most dependent on oxygen cylinders, and their supplies are allocated first.

[0041] Optionally, identifying a service conflict in medical resource scheduling includes: Scan multi-system data records of medical resources and extract the difference set of three values: inventory quantity, allocated quantity, and in-transit quantity; Specifically, the electronic medical record system (HIS), material management system (SPD) and logistics tracking system (LIS) are integrated to obtain real-time data, including inventory, allocated, in-transit and surgical demand to be allocated. The inventory is the current available inventory in the SPD database, the allocated is the number of consumables marked as "occupied by surgery" but not yet collected in the HIS, the in-transit is the number of consumables in transportation and the estimated arrival time in the LIS, and the surgical demand to be allocated extracts the consumable demand for planned surgery within the next 72 hours through the surgical reservation system. The data in the difference set includes the gap, and the calculation logic of the gap is "gap = allocated + surgical demand to be allocated - (inventory + in-transit)". When the gap is greater than 0.2 times the inventory, an exception is triggered, and a triplet {inventory, allocated, in-transit} is generated. The difference set is stored in a dynamic table, and each record contains a timestamp, consumable type and gap.

[0042] Based on the difference set, analyzing the spatiotemporal matching between the operating room reservation data and the consumables inventory data, and locating the conflicting coordinates; Specifically, the time interval of the surgery plan in the reservation system is parsed, and the estimated arrival time of the in-transit quantity is checked to see whether it satisfies the condition that the estimated arrival time of the in-transit quantity is less than the end time of the surgery minus the buffer time, where the buffer time is 2 hours by default. If the estimated arrival time of the in-transit quantity does not meet the condition or the inventory is insufficient to complete the current surgery, a conflicting coordinate is generated to obtain the coordinates (department, time interval of the surgery plan, type of consumables).

[0043] According to the node parameters of the resource supply and demand relationship map, the conflict level is calculated and a conflict warning signal is generated.

[0044] Specifically, the node parameters of the resource supply and demand relationship map include the coordinate values ​​corresponding to the consumable type and the conflict level. ,have In the formula, is the weight coefficient, the default is 0.4, 0.4, 0.2, which can be configured by the hospital. is the gap amount, To be allocated demand, is the coordinate value corresponding to the consumable type, The estimated arrival time of the in-transit quantity is counted down from the start of the operation. is the total time window. , assuming that the consumable type is oxygen cylinder, the coordinates of the node corresponding to the oxygen cylinder in the resource supply and demand relationship map are the three-dimensional feature data of the oxygen cylinder, that is, the feature vector of the oxygen cylinder (business type = oxygen cylinder, data format = structured UDI code, timeliness level = real-time), for example, it can be the aforementioned (5,2,8). Since it is detected that the frequency of respiratory oxygen cylinders applied for within 30 minutes reaches 15 times, and the frequency threshold is 10 times, the weight increase parameter is calculated to be 0.5, so the weight is adjusted to 1.5 times the original value, so the oxygen cylinder timeliness level is increased from 8 to 12, then at this time Then the value is 12. Then the levels are divided according to the value of the conflict level. When it is greater than 8, it is a red warning. When it is greater than 4 and less than or equal to 8, it is a yellow warning. When it is less than or equal to 4, it is a blue warning.

[0045] Optionally, generating a conflict resolution method for the business conflict based on a multi-objective optimization algorithm includes: Receiving the conflict warning signal, configuring a time priority strategy for clinical treatment decisions and a cost priority strategy for administrative material decisions; Specifically, when the system receives a conflict warning signal, it matches the decision-making strategy according to the conflict level. For clinical treatment conflicts, such as shortage of emergency surgery resources, the timeliness priority strategy is triggered. This strategy sets the timeliness weight of medical supplies arriving at the operating room to 70%, the transportation cost weight to 30%, and stipulates that the response time of the resource scheduling path shall not exceed 15 minutes. For administrative material conflicts, such as excessive inventory of general outpatient consumables, the cost priority strategy is implemented. The transportation cost weight is increased to 65%, the timeliness weight is reduced to 35%, and the scheduling response time is allowed to be extended to 4 hours. When configuring the strategy, the preset parameter table is called to dynamically adjust the coefficient combination of each factor in the objective function, and at the same time, the timeliness red line constraint is inserted into the decision model.

[0046] The timeliness priority strategy is a medical resource dispatching rule for critically ill patients, requiring that key supplies be delivered to the designated location in the shortest possible time. The cost priority strategy is a distribution optimization rule for non-emergency supplies, giving priority to the path and method with the lowest total transportation cost.

[0047] For example, an acute myocardial infarction case suddenly occurred in the inpatient department of a tertiary hospital, and the electrocardiogram system automatically triggered a catheter room activation request. At this time, the system identified that the conflict type was clinical treatment and activated the time priority strategy. The time constraint was set to "complete the preparation of all interventional consumables and the arrival of personnel within 20 minutes", and the consumables warehouse on the 3rd floor closest to the catheter room was given priority when making transportation route decisions, rather than the more distant central warehouse. The system automatically blocks cost overlimit warnings, forcibly retrieves high-priority inventory, and generates the shortest path navigation to the operating room. By automatically distinguishing between clinical emergencies and administrative affairs, the timeliness of emergency scenarios is ensured not to be dragged down by routine processes, and seamless connection of medical resources is achieved during the rescue window period to ensure patient life safety.

[0048] Generate a multi-path scheduling plan based on the resource supply and demand relationship map, including intra-campus transfer, emergency inventory call and inter-campus transfer; Specifically, based on the topological structure of the resource supply and demand relationship map, the multi-level associated path of the current material node is searched. The search depth of the same-campus transfer is set to 3 layers of associated nodes, and the path planning algorithm automatically matches the location of alternative resources in the same campus and calculates the transportation distance. The trigger condition for emergency inventory call is that the regular inventory is 20% lower than the safety threshold. When this strategy is activated, it will connect to the regional medical material reserve center to generate a special scheduling plan that includes cold chain transportation requirements. The path evaluation of cross-campus transfer includes real-time access to the traffic condition prediction module, and dynamically calculates the time and tolls required for cross-regional logistics. The same-campus transfer is the material flow path planning between different departments or warehouses within the medical institution. Emergency inventory call is to obtain the distribution plan of regional centralized reserve warehouses or strategic reserve resources. Cross-campus transfer is the coordinated transportation planning of materials between different medical institutions.

[0049] For example, an orthopedic surgery department discovered that a specific type of artificial joint prosthesis was missing, and the system initiated a three-level path exploration. First, a search was conducted in the same hospital area, and it was found that there was available inventory in the warehouse of the Orthopedic Traumatology Department on the 14th floor, and a walking ladder transportation plan was generated; the second step was to check the emergency reserve data and find that the emergency center in the adjacent administrative district had this type of material, and plan the ambulance special approval channel to pick up the goods; finally, the regional medical consortium database was searched to locate the inventory of a cooperative hospital 80 kilometers away, and a helicopter emergency transportation plan was generated and the meteorological impact on the route was estimated. A multi-level resource scheduling network was established to quickly expand the search radius when the single-point inventory was insufficient, form a three-dimensional resource supply plan, and effectively avoid interruptions in medical processes due to local shortages.

[0050] According to the preset historical scheduling plan execution database, the timeliness deviation rate, cost deviation value and feasibility of each plan are predicted and calculated to generate a three-dimensional decision matrix; A scheduling scheme is selected using the three-dimensional decision matrix.

[0051] Specifically, historical scheduling plans, historical timeliness data, and historical cost data are obtained based on historical scheduling records to construct a training set. The historical scheduling plans are used as input, and the historical timeliness data and historical cost data are used as output. A neural network model is established and trained, and finally a timeliness cost prediction model is obtained. The selected scheduling plan is input into the timeliness cost prediction model, and the predicted timeliness and predicted cost are output.

[0052] Among them, the time deviation rate The calculation formula is: In the formula, To predict the timeliness, The actual time. Cost deviation value Calculated by the following formula: In the formula, To predict costs, is the actual cost. , The feasibility of the scheme constitutes a three-dimensional decision space, where the feasibility is calculated by weighting the dual parameters of path pass rate and protocol compliance. ,have In the formula, The path pass rate weight is 0.6 by default and can be configured. is the path pass rate, that is, the historical execution completion rate. For example, 0.95 means a 95% success rate. The default value is 0.4, which satisfies , Protocol compliance, that is, the probability of meeting medical transportation regulations, such as the pass rate of cold chain integrity inspection.

[0053] The final result is an interactive three-dimensional matrix view, and the optimal solution is located in the low deviation area of ​​the first quadrant. The three-dimensional decision matrix is ​​a three-dimensional evaluation model that includes the time dimension, cost dimension, and feasibility dimension. The scale of each dimension is converted into a percentage indicator through normalization. The timeliness deviation rate is the relative error ratio between the actual execution time and the predicted time. The cost deviation value is the absolute difference between the actual cost and the estimated cost.

[0054] For example, the system generates three plans for a certain tumor drug dispatch demand. Plan A predicts that it will take 45 minutes to complete the transfer, with an estimated cost of 1,200 yuan; Plan B predicts that it will take 60 minutes, with a cost of 900 yuan; Plan C predicts that it will take 30 minutes, with a cost of 1,800 yuan. Historical data training shows that the average time for similar plans is ±8%, The fluctuation range is ±15%. After execution, the actual data is that Plan A takes 50 minutes and costs 1,250 yuan, Plan B takes 75 minutes and costs 850 yuan, and Plan C takes 28 minutes and costs 2,000 yuan. , ; , ; , Among them, the path passing rate of plan A is 95%, the compliance rate is 90%, and the calculated feasibility is 0.93. The path passing rate of plan B is 80%, the compliance rate is 85%, and the calculated feasibility is 0.82. The path passing rate of plan C is 60%, the compliance rate is 75%, and the calculated feasibility is 0.66. Figure 4 As shown in the figure, the X-axis is the timeliness deviation rate, negative values ​​indicate faster-than-expected execution, and positive values ​​indicate the opposite. The Y-axis is the cost deviation value, negative values ​​indicate cost overruns, and positive values ​​indicate savings. The Z-axis is the feasibility, and the larger the value, the higher the comprehensive score of the scheme, so Scheme A is the best choice. By intuitively displaying the multi-objective optimization results through three-dimensional visualization, decision makers can quickly weigh between timeliness, cost, and reliability, give priority to high-site schemes, significantly reduce the complexity of manual analysis, and improve the scientific nature of resource scheduling decisions. By quantitatively evaluating the execution deviation of historical schemes, a traceable decision optimization system is constructed to assist managers in selecting the scheduling scheme with the best comprehensive benefits under multiple constraints and reduce the cost of trial and error in decision-making.

[0055] Optionally, the sending the execution instruction to the target medical system includes: Decompose the selected scheduling scheme into standardized instruction units, each of which contains the target system identification, operation content coding and timeliness mark; Specifically, the selected resource scheduling scheme needs to be converted into machine instructions that can be recognized by the medical system. The splitting process decomposes the scheduling path into independent operation units according to the standard protocol of the medical Internet of Things. Each instruction unit contains a target system identification field, which is automatically generated by the hospital coding system in the format of administrative area code plus hospital area code plus floor number plus department code, such as Beijing A01-C3053A. The operation content coding adopts the international general medical operation code library mapping, such as infusion operations are the coding extension of HCPCS-J7040. The time limit is preset according to the total time of the scheduling path, and millisecond-level synchronization is achieved through binary timestamp coding. The generation logic of the standardized instruction unit must follow the predetermined template in XML format, and ensure data integrity through redundant check bits.

[0056] Among them, the standardized instruction unit is a set of computer executable commands split according to predefined rules, including the operation object, action type and time requirement. The target system identifier is the unique code of the medical node receiving the instruction in the Internet of Things. The operation content is coded according to the internationally accepted medical service coding rules. The timeliness mark is the time threshold identifier generated based on the total duration of the scheduling path.

[0057] For example, a tertiary hospital needs to perform cross-floor ventilator scheduling, and the resource scheduling plan is to transfer from the ICU on the 7th floor to the emergency department on the 3rd floor. The system automatically generates three instruction units: Unit 1 targets the ICU medical equipment controller, and the content encodes the removal of the fixture; Unit 2 targets the logistics robot navigation module, and the content encodes the setting of the transfer path L7→L3; Unit 3 targets the emergency department material receiving terminal, and the content encodes the device access detection. Each unit marks the time point that must be completed and is packaged into a JSON instruction stream that complies with the HL7 FHIR standard. Through instruction splitting, complex scheduling is accurately decomposed into independently executable atomic operations to ensure that the responsibility of each link is traceable and the timeliness is quantifiable. Standardized instruction splitting avoids semantic ambiguity in traditional manual scheduling, uses machine-readable encoding to reduce the risk of operational errors, and improves the compatibility and reliability of cross-system instruction execution.

[0058] Set up electronic tag verification points on the consumables transfer path to collect and feedback the consumables coordinates and timestamps; Specifically, interface devices based on RFID or NFC technology are installed at key nodes of the transportation route of medical consumables. The spacing between verification points is set according to the type of consumables. For example, high-value consumables require a detection device every 20 meters, and general consumables are set at a spacing of 50 meters. Each verification point reads the electronic tag ID on the consumable packaging, obtains real-time geographic coordinates through the Beidou / GPS positioning module, and records the Unix timestamp. The collected data is transmitted back to the central monitoring system via the LoRa wireless protocol. When the transmission delay of two consecutive verification points exceeds the set threshold, the path deviation warning is automatically triggered. For refrigerated consumables, the verification point synchronously collects temperature sensor data and compares it with the preset cold chain specifications. The verification point storage chip has a power-off data protection function to ensure the integrity of the audit tracking data.

[0059] The electronic tag verification point is an intelligent node device with reading, positioning and communication functions, which is deployed on the physical path of the consumables transportation channel. The consumables coordinates are the longitude and latitude data of the geographic location coordinate system. The timestamp is the execution time mark recorded by the computer system with accuracy to milliseconds.

[0060] For example, a tertiary hospital transports heart stents to the catheterization room, and the path runs through the medical street, the surgical special channel and the clean area. Seven verification points are arranged along the path, with the coordinates of the entrance gate (116.403, 39.914), the coordinates of the transition area of ​​the surgical building (116.4035, 39.915), and the coordinates of the clean area buffer zone (116.4037, 39.916). When the transfer box carrying the stent passes through, each verification point reads the label code and records the time, such as 09:30:15.234, 09:31:03.112, 09:32:57.889. The system compares the preset standard path time curve, detects that the stay in the clean area exceeds 120 seconds, and immediately notifies the quality control department to intervene. Through dynamic path monitoring, the transportation of high-value consumables can be tracked throughout the process, and any abnormal deviation can be warned in time. Build a monitoring network that integrates physical and digital, realize the process visualization of medical material transportation, and use spatiotemporal data cross-validation to improve the ability to prevent loss and tampering.

[0061] When a high-value consumables scheduling instruction is detected, a double electronic signature confirmation mechanism is activated.

[0062] Specifically, the high-value category is identified through the prefix of the UDI code of the consumables, triggering the security verification process. The first signature is an asymmetric encryption signature generated by the authorized person of the Medical Department using the national secret SM2 algorithm to verify the compliance of the consumables application. The second signature is the digital certificate signature issued by the director of the equipment receiving department through the PKI system to confirm the receiving qualification. After the double signature is generated, blockchain evidence will be executed. Each signature contains the operator's work number, timestamp and device fingerprint information. The signature data is bound to the consumables logistics track to form an unalterable audit chain. If the signature verification fails three times, the system automatically freezes the relevant scheduling process and activates the manual review channel. For high-value implantable consumables, an additional electronic signature link for the surgeon is added.

[0063] Among them, high-value consumables are medical items whose unit price exceeds the set medical payment standard, such as artificial joints, heart stents, etc. The dual electronic signature confirmation mechanism uses two independent digital identity authentication technologies to perform security verification on key operations. Blockchain evidence storage is the encrypted storage of important operation records using distributed ledger technology.

[0064] For example, a patient needs to use an artificial heart valve urgently. The system identifies the consumable UDI code as (01) 88521023456784 (21) A1015, and determines that it is a high-value consumable. When generating a dispatch instruction, the director of cardiac surgery and the head nurse of the interventional catheterization room are required to sign using a mobile phone digital certificate. The first signature confirms that the surgical indication is in line with the medical insurance catalog, and the second signature verifies the receiving department's material storage qualifications. The two signatures are transmitted to the blockchain node via quantum encryption and a hash value of 0x7d5a...ef2c is generated. When the consumable arrives, the system compares the symmetric name hash chain, and unlocks the safe if a match is successful. Double verification eliminates the risk of illegal calls and ensures full life cycle supervision of high-value consumables. Establish a multi-layered material security system, and through the combination of cryptographic technology and distributed ledgers, effectively prevent the theft and abuse of medical resources and protect the rights and interests of patients.

[0065] Optionally, verifying the execution result of the execution instruction and updating the system parameters includes: Based on the consumable coordinates and timestamps, real-time collection of consumable position data and timeliness data during the execution of the instruction; Specifically, the system continuously acquires consumable logistics data through IoT sensor nodes deployed on medical transportation routes. The location data comes from the Beidou / GPS dual-mode positioning chip built into the transportation equipment, and the collection frequency is set to once per second. The timeliness data is calculated and generated by comparing the time difference between the planned timestamp and the actual arrival time at the verification point. The calculation formula is: in, The time node preset for the scheduling plan, It is the Unix timestamp recorded for the electronic tag verification point. Multi-source heterogeneous data is integrated every 3 seconds and uploaded to the central monitoring system database through the MQTT protocol. The data collection mechanism includes a fault-tolerant design. When a single node signal is lost, the redundant data interpolation of adjacent verification points is automatically enabled. The consumables coordinates are the real-time geographic location coordinates of medical supplies in three-dimensional space, including longitude, latitude and floor height. The timeliness data is the difference between the actual transportation time and the planned time, reflecting the deviation of the execution progress. The electronic tag verification point is a fixed-point detection device equipped with a radio frequency identification and time synchronization module, which is used to verify the logistics node.

[0066] Based on the consumables location data and timeliness data, calculate the time deviation and space deviation between the actual execution path and the optimized path, generate a comprehensive deviation, and generate an alarm level based on the comprehensive deviation; Specifically, the path deviation calculation adopts a time-space dual-dimensional comprehensive evaluation model. The calculation formula is: Time deviation The calculation formula is: Comprehensive deviation The fusion formula is: in, is the actual coordinate, are the planned coordinates, The largest deviation distance in history, is the total allowed time, is the weight coefficient, the default , , and is configurable. The alarm level determination rules are: Green is normal. For yellow observation, Red emergency. When a red alarm is detected, the system automatically freezes the subsequent scheduling instructions and waits for manual confirmation. The actual execution path is the actual trajectory coordinate sequence of the consumables transportation. The optimized path is the theoretical trajectory in the optimal scheduling solution generated by the algorithm. The deviation is a quantitative indicator of the difference between the actual transportation path and the ideal path. The alarm level is a response priority label divided according to the degree of deviation.

[0067] Based on the alarm level, an immediate correction instruction of the weight increase parameter is triggered, and the weight increase parameter is adjusted using the comprehensive deviation.

[0068] Specifically, the weight increase parameter is a dynamic coefficient for adjusting the importance of the feature vector in the data association model. The immediate correction instruction is a model adaptive adjustment instruction triggered based on real-time deviation data. When the alarm level is non-green, the immediate correction instruction is triggered. The immediate correction instruction adjusts the weight increase parameter by calculating the correction coefficient. For the current correction coefficient ,have In the formula, For the The secondary correction factor, that is, the current correction factor, For the The correction coefficient is the previous correction coefficient. is the dynamic coefficient, is a constant coefficient, is the comprehensive deviation threshold; Adjust according to the alarm level. When the alarm level is yellow, , when the alarm level is red,

[0069] This method implements a closed-loop feedback optimization mechanism by real-time tracking of the spatiotemporal data of medical resource scheduling paths, dynamically evaluating execution deviations and adaptively adjusting model parameters. It improves the adaptability of the dynamic model to abnormal situations, optimizes the accuracy of subsequent resource scheduling, strengthens risk management capabilities through alarm classification, and combines electronic tags with correction algorithms to ensure the reliability and self-learning capabilities of the scheduling process. For example, when the transportation of cold chain drugs is delayed, the system automatically increases the model weight of such consumables and prioritizes matching of backup path resources.

[0070] For example, a hospital dispatched a batch of vaccines to the emergency department. The planned route was through the corridor of Area A, with coordinates X=102, Y=58, and the planned time was 8 minutes. In actual transportation, due to temporary control, it detoured to Area B, with coordinates X=105, Y=55, and took 12 minutes. The calculated spatial deviation was 4.24, the temporal deviation was 50%, and the comprehensive deviation was 22.54%, triggering a red alarm. Since the alarm level was red, an immediate correction instruction was triggered. At this time, the dynamic coefficient ; Assuming the previous correction coefficient is 1 and the comprehensive deviation threshold is 10, The current correction factor is 0.2, so the calculated correction factor is 1.3, so the weight increase parameter of this type of vaccine is increased by 30%. Quickly identify deviations when sudden paths are blocked, dynamically enhance the model weight of cold chain drugs, ensure that emergency needs are matched with reliable paths first, and reduce the execution risk of subsequent tasks.

[0071] Optionally, verifying the execution result of the execution instruction and updating the system parameters further includes: Integrate the execution results to build an experience knowledge base, which includes successful case templates and exception handling reports; Specifically, after each medical resource scheduling task is completed, core indicator data such as execution time, path deviation and resource utilization are automatically collected. Execution time is the average time deviation of department consumables, path deviation is the average time deviation of various consumables in the department, and resource utilization is calculated by the ratio of the actual amount of consumables used in the department to the amount of consumables allocated in the department. The experience knowledge base adopts a hierarchical storage structure, and sets data cleaning rules to filter out invalid records. The successful case template is defined as a historical record with a path deviation of less than 5% and a resource waste rate of less than 3%, which is stored by department type through the K-means clustering algorithm. The abnormal handling report records the handling process of emergencies such as resource loss and cold chain breakage, and associates the original conflict warning level with the corrective measures. Each report is marked with the root cause code, such as "EC-102" for time delay caused by transportation equipment failure. The construction mechanism performs incremental updates at dawn every day and retains valid data for the past 365 days.

[0072] Among them, the experience knowledge base is a structured database that stores historical scheduling cases, including positive experience and problem handling records. The success case template is a scheduling path template that meets the preset excellent standards. The abnormal handling report is a fault file that records unexpected events in resource scheduling and response measures.

[0073] According to the historical data of the experience knowledge base, the system parameters are adjusted periodically; specifically, the adjustment period may be once a month, and the adjusted system parameters include the frequency threshold , safety threshold of inventory, comprehensive deviation threshold . When the proportion of successful cases of a certain type of consumables in the experience knowledge base exceeds 60%, the safety threshold of the inventory will automatically drop by 5%. After the parameters are updated, three months of historical data must be simulated in the sandbox environment to verify the improvement effect before deployment. For example, due to the stable volume of surgeries for artificial joint consumables, the safety threshold of the inventory is reduced from 200 sets to 190 sets, freeing up storage space while ensuring continuous supply.

[0074] Establish department execution energy efficiency scoring, and update the weight of the corresponding node of the department in the resource supply and demand relationship map according to the scoring results.

[0075] Specifically, the department's execution energy efficiency score is a comprehensive evaluation indicator that quantifies the department's resource scheduling capabilities. ,have In the formula, is the weight coefficient, , The actual amount of consumables used in the department. The amount of consumables allocated to the department. is the average spatial deviation of department consumables, is the time deviation average value of department consumables; among them, the allocated amount of department consumables is the data in the three-value difference concentration. By the aforementioned spatial deviation Calculated, is the average value of spatial deviation of various consumables in the department; Through the time deviation mentioned above Calculated, It is the average time deviation of various consumables in the department. Map the execution energy efficiency score of the department to the corresponding node in the resource supply and demand relationship map, and update the weight of the corresponding node. For example, if the execution energy efficiency score is 90 points or above, it is grade A, then the corresponding weight of the department is ×1.2; if the execution energy efficiency score is 75-89 points, it is grade B, then the corresponding weight of the department is ×1.0; if the execution energy efficiency score is 60-74 points, it is grade C, then the corresponding weight of the department is ×0.8. The execution energy efficiency score is updated monthly and synchronized to the resource supply and demand relationship map. For example, because the emergency department has scored 92 points for three consecutive months, its node association weight is increased by 20%, and it will be given priority in the allocation of scarce resources. The energy efficiency score is simultaneously pushed to the hospital performance appraisal system as a basis for department management evaluation.

[0076] The present invention achieves continuous improvement in the scheduling of medical resources by constructing a closed-loop feedback self-learning optimization system. The experience knowledge base accumulates historical operation data to form a decision-making think tank, periodic parameter tuning ensures that the model keeps pace with the times, and the energy efficiency scoring mechanism is implemented to encourage departments to improve operational efficiency. In the event of sudden resource demand, the best practice solution can be quickly matched, and the experience of handling abnormal events forms a standardized plan to effectively avoid repeated errors. The dynamic adjustment of department weights promotes the rational flow of medical resources and builds an adaptive medical ecosystem.

[0077] Optionally, the method further comprises: Anomaly judgment is performed according to the spatial deviation, and when an anomaly is detected, the success case template is loaded and switched to a degradation mode; Specifically, the abnormal state is determined by monitoring the average value of spatial deviation. Figure 5 As shown in the figure, when the average spatial deviation of any carrier unit exceeds 15%, the anomaly detection mechanism is triggered and the degradation mode is activated. At this time, the successful case template with attribute matching is retrieved from the experience knowledge base, for example, a historical scheduling scheme with a timeliness deviation rate of less than 8% and a path repeatability of more than 90% is selected as the template benchmark. The degradation mode is a simplified operation mode in an emergency state, which shuts down non-core algorithm modules and compresses data transmission.

[0078] Among them, the anomaly detection mechanism is judged through real-time data monitoring. The degradation mode is a disaster recovery operation state that reduces the system operation accuracy but ensures the continuity of key business. The success case template is a standardized storage template of the historical scheduling plan that meets the preset execution standard, including path trajectory, time consumption record and resource utilization parameters. For example, if a consumable transportation contains three stages of spatial deviation (25%, 12%, 18%), the average deviation is 18.33%, which is greater than 15%, so it is judged to be an abnormal state and switched to degradation mode.

[0079] According to the successful case template, the path data with the smallest average spatial deviation within the preset time window is called to generate an emergency dispatch plan; Specifically, the path with the smallest average spatial deviation within the preset time window is screened out. The time window can be set to 24 hours, and the screened path data is used as an alternative plan to build an emergency dispatch plan. For example, three candidate paths are retrieved, the average spatial deviation of path A is 9.2%, the average spatial deviation of path B is 11.8%, and the average spatial deviation of path C is 8.7%. Path C with the smallest average spatial deviation is selected to generate an emergency plan, shortening the manual decision-making time.

[0080] In degraded mode, data collection frequency is reduced, label conversion is simplified, and urgent resources are allocated according to the scoring results.

[0081] Specifically, the data transmission protocol is adjusted to improve the response speed. The frequency of data collection is reduced from seconds to minutes, and non-critical data points are filtered through filtering algorithms. The label conversion process cancels the redundant verification step and retains the core field mapping. Emergency resource allocation is sorted from large to small according to the latest department execution energy efficiency score, and allocated in proportion according to the sorting results; for example, the A-level department with the highest execution energy efficiency score will be given priority to obtain 70% of the emergency resource allocation, the B-level department with the second highest execution energy efficiency score will be allocated 25%, and the rest will be allocated to the shared resource pool.

[0082] Among them, label conversion is a data cleaning process that transcribes medical identifiers with different coding rules into a standard format. The filtering algorithm is a noise reduction processing method that generates a data fitting curve based on the principle of least squares.

[0083] This method achieves rapid disaster recovery while ensuring the basic functions of the system by building a two-layer emergency response mechanism. The organic combination of anomaly detection and degradation mode can avoid system-level crashes, and case-driven emergency plan generation significantly improves decision-making efficiency. The dynamically adjusted data collection strategy reduces system load while ensuring the integrity of core business data, and the scoring-based resource allocation mechanism ensures that emergency resources are tilted towards high-performance departments.

[0084] Based on the same inventive concept, Figure 6 As shown, the present invention also provides a data analysis platform management system, the system comprising: A data acquisition module is used to acquire multi-source heterogeneous data from a medical information system, including patient diagnosis and treatment data, medical consumables data, and equipment operation data; A supply and demand relationship establishment module is used to establish a cross-system data association model, dynamically extract features and assign weights to the multi-source heterogeneous data, and output a resource supply and demand relationship map; A business conflict identification module, used to analyze the resource supply and demand relationship map and identify business conflicts in medical resource scheduling; A decision generation module, used to generate a conflict resolution method for the business conflict based on a multi-objective optimization algorithm and generate an execution instruction; An instruction execution module, used to send the execution instruction to the target medical system, wherein the instruction includes a resource scheduling path and time constraint conditions; A closed-loop verification module, used to verify the execution result of the execution instruction and update the system parameters; It should be noted that the electrical connection between the above-mentioned units does not necessarily mean direct connection of the lines, and the indirect connection mode can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention.

[0085] That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present invention. This application is intended to cover any variation, use or adaptive change of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the art that are not described in the present invention.

Claims

1. A data analysis platform management method, characterized in that: The method comprises: Acquire multi-source heterogeneous data from medical information systems, including patient diagnosis and treatment data, medical consumables data, and equipment operation data; Establish a cross-system data association model, perform dynamic feature extraction and weight allocation on the multi-source heterogeneous data, and output a resource supply and demand relationship map; Analyze the resource supply and demand relationship map to identify business conflicts in medical resource scheduling; Generate a conflict resolution method for the business conflict based on a multi-objective optimization algorithm and generate an execution instruction; Sending the execution instruction to the target medical system, wherein the instruction includes a resource scheduling path and a time constraint condition; Verify the execution result of the execution instruction and update system parameters.

2. A data analysis platform management method according to claim 1, characterized in that: The acquisition of multi-source heterogeneous data from the medical information system includes: Connect the electronic medical record system and the material management system through a standardized protocol conversion module, and output a structured interface data stream; Based on the structured interface data stream, identifying treatment type keywords and consumable identification code segments in the medical order text, and converting unstructured data into medical resource tags in a unified coding format; According to the attribute characteristics of the medical resource tag, the data collection mode is adjusted according to the preset time period, and the data collection mode includes: Real-time data processing mode, capturing key fields at a frequency of seconds; Batch update mode integrates all-day data to generate incremental update packages.

3. A data analysis platform management method according to claim 1, characterized in that: The establishment of a cross-system data association model, dynamic feature extraction and weight allocation of the multi-source heterogeneous data, and output of a resource supply and demand relationship map include: Constructing a three-dimensional feature coordinate system, wherein the dimensions of the three-dimensional feature coordinate system include business type, data format and timeliness level, and generating an initial feature vector set; Based on the initial feature vector set, a dynamic weight adjustment mechanism is established. When it is detected that the frequency of claiming for the same type of consumables exceeds a preset frequency threshold, a weight increase parameter is calculated by a sliding window algorithm to adjust the feature vectors in the initial feature vector set; The adjusted feature vector is input into the preset graph database, a multi-level association relationship between nodes is constructed, and a resource supply and demand relationship map is output.

4. A data analysis platform management method according to claim 1, characterized in that: The identifying of business conflicts in medical resource scheduling includes: Scan multi-system data records of medical resources and extract the difference set of three values: inventory quantity, allocated quantity, and in-transit quantity; Based on the difference set, analyzing the spatiotemporal matching between the operating room reservation data and the consumables inventory data, and locating the conflicting coordinates; According to the node parameters of the resource supply and demand relationship map, the conflict level is calculated and a conflict warning signal is generated.

5. A data analysis platform management method according to claim 4, characterized in that: The conflict resolution method for generating the business conflict based on the multi-objective optimization algorithm includes: Receiving the conflict warning signal, configuring a time priority strategy for clinical treatment decisions and a cost priority strategy for administrative material decisions; Generate a multi-path scheduling plan based on the resource supply and demand relationship map, including intra-campus transfer, emergency inventory call and inter-campus transfer; According to the preset historical scheduling plan execution database, the timeliness deviation rate, cost deviation value and feasibility of each plan are predicted and calculated to generate a three-dimensional decision matrix; A scheduling scheme is selected using the three-dimensional decision matrix.

6. A data analysis platform management method according to claim 3, characterized in that: The sending of the execution instruction to the target medical system includes: Decompose the selected scheduling scheme into standardized instruction units, each of which contains the target system identification, operation content coding and timeliness mark; Set up electronic tag verification points on the consumables transfer path to collect and feedback the consumables coordinates and timestamps; When a high-value consumables scheduling instruction is detected, a double electronic signature confirmation mechanism is activated.

7. A data analysis platform management method according to claim 6, characterized in that: The verifying the execution result of the execution instruction and updating the system parameters includes: Based on the consumable coordinates and timestamps, real-time collection of consumable position data and timeliness data during the execution of the instruction; Based on the consumables location data and timeliness data, calculate the time deviation and space deviation between the actual execution path and the optimized path, generate a comprehensive deviation, and generate an alarm level based on the comprehensive deviation; Based on the alarm level, an immediate correction instruction of the weight increase parameter is triggered, and the weight increase parameter is adjusted using the comprehensive deviation.

8. A data analysis platform management method according to claim 7, characterized in that: The verifying the execution result of the execution instruction and updating the system parameters also includes: Integrate the execution results to build an experience knowledge base, which includes successful case templates and exception handling reports; periodically adjusting system parameters according to historical data of the experience knowledge base; Establish department execution energy efficiency scoring, and update the weight of the corresponding node of the department in the resource supply and demand relationship map according to the scoring results.

9. A data analysis platform management method according to claim 8, characterized in that: The method further comprises: Anomaly judgment is performed according to the spatial deviation, and when an anomaly is detected, the success case template is loaded and switched to a degradation mode; According to the successful case template, the path data with the smallest average spatial deviation within the preset time window is called to generate an emergency dispatch plan; In degraded mode, data collection frequency is reduced, label conversion is simplified, and urgent resources are allocated according to the scoring results.

10. A data analysis platform management system, applied to a data analysis platform management method as claimed in any one of claims 1 to 9, characterized in that: The system comprises: A data acquisition module is used to acquire multi-source heterogeneous data from a medical information system, including patient diagnosis and treatment data, medical consumables data, and equipment operation data; A supply and demand relationship establishment module is used to establish a cross-system data association model, dynamically extract features and assign weights to the multi-source heterogeneous data, and output a resource supply and demand relationship map; A business conflict identification module, used to analyze the resource supply and demand relationship map and identify business conflicts in medical resource scheduling; A decision generation module, used to generate a conflict resolution method for the business conflict based on a multi-objective optimization algorithm and generate an execution instruction; An instruction execution module, used to send the execution instruction to the target medical system, wherein the instruction includes a resource scheduling path and time constraint conditions; The closed-loop verification module is used to verify the execution result of the execution instruction and update the system parameters.

Images