Consumption and supply dispatching platform based on regional digital brain

Abstract

The present application provides a disinfection and supply dispatching platform based on a regional digital brain, which involves the field of data processing technology, including: a communication module establishes a digital connection between a disinfection supply center and a hospital terminal, and synchronizes data to a dispatching platform; an information base module constructs a basic and feature information base, and records location, path, task, and trust information; a constraint module sets throughput and time node restrictions; a compensation module analyzes task and trust data, and generates compensation constraints; an intelligent dispatching module uses this information to optimize dispatching through a regional digital brain, generates optimal dispatching results, and manages accordingly. This application can solve the problem that the prior art cannot accurately predict the future needs of hospital terminals, resulting in the inability of dispatching plans to adapt to changes in actual needs, and the inability to quickly adjust plans to deal with emergencies, further reducing the quality and efficiency of services, improving the efficiency and responsiveness of operations, and enhancing customer satisfaction.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a consumption and supply dispatching platform based on a regional digital brain. Background Art

[0002] The city brain is mainly composed of the hub, system and platform, digital cockpit and application scenarios. It is based on and supported by data, computing power, algorithms, and uses new technologies such as big data, cloud computing, and blockchain. It aims to promote the modernization of urban governance systems and governance capabilities, and realize the intelligence, predictability and self-learning capabilities of urban management. The proposal and development of the city brain reflects the transformation of smart cities from information empowerment to intelligent technology empowerment, and the evolution from single-field management to diversified governance scenario integration. The development of the city brain also faces some challenges, such as the lack of unified construction specifications and standards, which makes it difficult for the city brain systems of different cities and technology companies to interconnect, and it is difficult for technology companies to form synergies.

[0003] In summary, existing technologies cannot accurately predict the future needs of hospital terminals, resulting in scheduling plans that cannot adapt to changes in actual demand and cannot quickly adjust plans to deal with emergencies, further reducing the quality and efficiency of services. Summary of the invention

[0004] The purpose of this application is to provide a consumption and supply scheduling platform based on a regional digital brain to solve the problem that the existing technology is unable to accurately predict the future demand of hospital terminals, resulting in the inability of scheduling plans to adapt to changes in actual demand and the inability to quickly adjust plans to deal with emergencies, further reducing the quality and efficiency of services.

[0005] In view of the above problems, this application provides a consumption and supply scheduling platform based on a regional digital brain.

[0006] The present application also provides a disinfection and supply scheduling platform based on a regional digital brain, the platform comprising: a communication module for establishing digital communication between a disinfection and supply center and N hospital terminals, and synchronously transmitting data to the disinfection and supply scheduling platform; an information base construction module for constructing a basic information base and a feature information base of the disinfection and supply center and the N hospital terminals based on the received data, the basic information base comprising the location distribution information and scheduling path information of the disinfection and supply center and the N hospital terminals, the feature information base comprising the task feature information and trust feature information of the disinfection and supply center and the N hospital terminals; a constraint construction module for establishing the total task throughput constraint of the disinfection and supply center, And through the communication module, the appointment tasks of N hospital terminals are obtained, and the extreme constraint time nodes are created based on the appointment tasks; the first compensation module is used to perform a stability analysis of the scheduling based on the appointment tasks and the basic information library, and generate a first compensation constraint; the second compensation module is used to perform a trust analysis of N hospital terminals based on the feature information library and the appointment tasks, and construct a second compensation constraint; the intelligent scheduling module is used to receive appointment tasks, extreme constraint time nodes, total task throughput constraints, first compensation constraints and second compensation constraints, perform scheduling analysis through the regional digital brain, generate consumption and supply scheduling results, and manage based on the consumption and supply scheduling results.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The communication module is used to establish digital communication between the disinfection supply center and N hospital terminals, and synchronously transmit the data to the disinfection supply scheduling platform; the information base construction module is used to construct the basic information base and feature information base of the disinfection supply center and N hospital terminals based on the received data, the basic information base includes the location distribution information and scheduling path information of the disinfection supply center and the N hospital terminals, and the feature information base includes the task feature information and trust feature information of the disinfection supply center and the N hospital terminals; the constraint construction module is used to establish the total task throughput constraint of the disinfection supply center, and obtain the appointment tasks of the N hospital terminals through the communication module, and create the limit constraint time node based on the appointment tasks; the first compensation module is used to construct the basic information base and feature information base of the disinfection supply center and the ... appointment tasks The basic information database performs scheduling stability analysis to generate a first compensation constraint; the second compensation module is used to perform trust analysis of N hospital terminals based on the feature information database and the appointment task to construct a second compensation constraint; the intelligent scheduling module is used to receive appointment tasks, limit constraint time nodes, total task throughput constraints, first compensation constraints and second compensation constraints, perform scheduling analysis through the regional digital brain, generate consumption and supply scheduling results, and manage based on the consumption and supply scheduling results, which effectively solves the problem that the existing technology cannot accurately predict the future demand of hospital terminals, resulting in the inability of scheduling plans to adapt to changes in actual demand and the inability to quickly adjust plans to deal with emergencies, further reducing the quality and efficiency of services, improving the efficiency and responsiveness of operations, and enhancing customer satisfaction.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or 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 in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a schematic diagram of the structure of the consumption and supply dispatching platform based on the regional digital brain in this application;

[0012] Figure 2This is a flow chart of trust analysis in the consumption and supply dispatching platform based on the regional digital brain in this application.

[0013] Description of reference numerals:

[0014] Communication module 11, information base construction module 12, constraint construction module 13, first compensation module 14, second compensation module 15, intelligent scheduling module 16. DETAILED DESCRIPTION

[0015] This application solves the problem that the existing technology is unable to accurately predict the future demand of hospital terminals, resulting in the inability of scheduling plans to adapt to changes in actual demand and the inability to quickly adjust plans to deal with emergencies, further reducing the quality and efficiency of services by providing a consumption and supply scheduling platform based on a regional digital brain. It improves the efficiency and responsiveness of operations and enhances customer satisfaction.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] This application provides a consumption and supply dispatching platform based on the regional digital brain. Please refer to the attached Figure 1 , the platform comprises:

[0018] The communication module 11 is used to establish digital communication between the disinfection supply center and N hospital terminals, and synchronously transmit data to the disinfection supply scheduling platform.

[0019] Specifically, establish digital communication between the disinfection supply center and hospital terminals based on HTTP / HTTPS API interfaces. Use real-time data synchronization technologies, such as WebSockets or polling mechanisms, to ensure real-time data updates. Establish data synchronization middleware to handle data conversion, verification, and routing to ensure that data is correctly transmitted between the disinfection supply center and hospital terminals. Deploy the disinfection supply scheduling platform in the cloud. Use the elastic scaling capabilities of cloud services to dynamically adjust resources according to demand to ensure stable system operation.

[0020] The information database construction module 12 is used to construct a basic information database and a feature information database of the disinfection supply center and N hospital terminals based on the received data. The basic information database includes the location distribution information and scheduling path information of the disinfection supply center and N hospital terminals, and the feature information database includes the task feature information and trust feature information of the disinfection supply center and N hospital terminals.

[0021] Specifically, collect and store the geographical location information of the disinfection supply center and each hospital terminal, including longitude and latitude, address, region, etc. Use geographic information system technology to integrate this information into an electronic map for visualization and management. Determine the best dispatch path from the disinfection supply center to each hospital terminal through historical data and real-time traffic information. Establish an optimized delivery route for each hospital terminal based on factors such as traffic conditions, distance, and estimated time. Collect disinfection demand information for each hospital terminal, including item type, quantity, frequency, urgency, etc. Analyze historical data to identify demand patterns and changing trends for different hospital terminals. Establish a trust evaluation system for hospital terminals based on historical cooperation records, feedback, and evaluation. Give each hospital terminal a trust score based on factors such as the hospital terminal's payment record and contract performance.

[0022] The constraint construction module 13 is used to establish the total task throughput constraint of the disinfection supply center, obtain the appointment tasks of N hospital terminals through the communication module, and create the limit constraint time node based on the appointment tasks.

[0023] Specifically, a detailed assessment of the production capacity of the disinfection supply center is conducted, including the maximum daily processing volume, the processing speed of different types of disinfection items, etc. According to the maintenance cycle of the equipment and the shifts of the employees, the available working time and processing capacity are determined. The upper limit of the total task throughput is set, that is, the maximum daily task volume that the center can handle. According to fluctuations and unexpected situations, a certain buffer is set to increase the flexibility of the system. Through the communication module, the appointment task data is collected from N hospital terminals, including the type, quantity, expected delivery time, etc. of the required disinfection items. Use automated tools such as data interfaces or spreadsheets to ensure the accuracy and timeliness of the data. According to the collected appointment tasks, the urgency of the needs and the processing priority of each hospital terminal are analyzed. According to the disinfection cycle and processing flow of the items, the required time window is calculated for each task. Combined with the total task throughput constraint and the time window of each task, the limit completion time of each task is determined. For urgent tasks, a stricter completion time node is set to ensure timely delivery.

[0024] The first compensation module 14 is used to perform a scheduling stability analysis based on the scheduled task and the basic information library to generate a first compensation constraint.

[0025] Specifically, use the historical scheduling data in the basic information database to analyze the execution of previous tasks and the problems encountered. Identify factors that may lead to scheduling instability, such as equipment failure, staff absence, traffic delays, etc. Conduct a risk assessment for each scheduled task, including the importance and urgency of the task, as well as factors that may affect the completion of the task. Assess the potential impact of changes in the internal and external environment of the disinfection supply center on scheduling stability. Based on the results of the stability analysis, allocate additional preparation time for each task as a time buffer. This allows for a certain amount of adjustment space when problems are encountered during task execution without affecting the overall scheduling plan.

[0026] The second compensation module 15 is used to perform trust analysis on N hospital terminals based on the feature information database and the reservation task, and construct a second compensation constraint.

[0027] Specifically, analyze historical data in the feature information library, including the order fulfillment, payment records, and contract compliance of hospital terminals. Evaluate the performance of hospital terminals in previous cooperation, including timeliness, accuracy, and communication quality. Give scores based on the historical performance of hospital terminals, and the scores are based on quantitative indicators such as order punctuality and qualitative assessments such as customer feedback. Adjust the scheduling priority of hospital terminals based on the trust score. Hospital terminals with high trust may receive higher priority services. For hospital terminals with low trust, additional review steps or higher advance payments can be set.

[0028] The intelligent scheduling module 16 is used to receive scheduled tasks, limit constraint time nodes, total task throughput constraints, first compensation constraints and second compensation constraints, perform scheduling analysis through the regional digital brain, generate consumption and supply scheduling results, and manage based on the consumption and supply scheduling results.

[0029] Specifically, all relevant data, including appointment tasks, time nodes, throughput constraints, compensation constraints, etc., are integrated into the scheduling system. Scheduling analysis is performed based on scheduling algorithms, such as genetic algorithms, linear programming, dynamic programming, etc. Simulation technology is used to test the effects of different scheduling strategies and adjust them according to actual conditions. According to the results of the scheduling analysis, specific execution time and resources are assigned to each appointment task. Ensure that the allocation plan meets all constraints, including extreme time nodes and total task throughput. Generate a scheduling plan, including the execution order of each task, the allocation of required materials and human resources, etc. When executing the scheduling plan, implement real-time monitoring to ensure that the plan is carried out as expected. Timely discover and solve possible problems, such as resource shortages, equipment failures, etc.

[0030] Furthermore, the first compensation module 14 is also used for:

[0031] Based on the scheduling path information, path data is read to build a historical path period traffic database for each scheduling path; through the reservation task, a traffic period analysis is performed, and based on the traffic period analysis result and the historical path period traffic database, a scheduling stability analysis is performed to establish the first compensation constraint.

[0032] Specifically, collect the traffic data of historical dispatch paths, including traffic conditions in different time periods, such as peak hours and off-peak hours. Organize the collected data and establish a structured historical path time period traffic database. The database contains information such as paths, time periods, travel times, and traffic flow. Obtain current and predicted traffic conditions through traffic information services or real-time monitoring, integrate real-time data and historical data, and obtain a more comprehensive analysis of traffic periods. Use data analysis techniques, such as time series analysis or machine learning models, to predict the traffic conditions of different paths in different time periods. Include special events such as road construction and holidays that affect traffic conditions. Based on the results of the traffic period analysis, evaluate the stability and reliability of different dispatch paths. Based on the stability evaluation results, establish compensation constraints for each dispatch path. Compensation constraints include reserving extra time, selecting alternative paths, or adjusting the dispatch plan.

[0033] Further, if Figure 2 As shown, the second compensation module 15 is also used for:

[0034] Execute data sorting in the task feature library, and construct a feature database after denoising the data; establish a time series decay factor, and weight the data in the feature database through the time series decay factor to construct a feature trust value identifier; execute feature similarity clustering under the same hospital terminal of the feature database, perform trust analysis of N hospital terminals based on the feature similarity clustering results, feature trust value identifiers and trust feature information, and construct a second compensation constraint.

[0035] Specifically, according to the characteristics of time series data, a time series decay factor is established to reflect the change in the importance of data over time. The decay factor is determined based on factors such as the novelty of the data and the frequency of orders. The time series decay factor is used to perform weighted calculations on the data in the feature database to reflect the importance of data at different time points to the current decision. Weighted calculations can enhance the accuracy and predictive power of feature data. Cluster analysis is performed on the data in the feature database to group hospital terminals with similar features. Clustering algorithms such as K-means and hierarchical clustering are used to identify different demand patterns and service features. Trust analysis is performed on N hospital terminals based on the feature similarity clustering results, feature trust value identification, and trust feature information. The trust of each hospital terminal is evaluated, including factors such as its historical performance, demand stability, and cooperative relationship. Based on the results of the trust analysis, a second compensation constraint is constructed for each hospital terminal. Compensation constraints include adjusting service priorities, resource allocation strategies, or setting specific service standards.

[0036] Furthermore, the intelligent scheduling module 16 is also used for:

[0037] Configure the trigger penalty coefficient of the extreme constraint time node; when executing the scheduling analysis through the regional digital brain, arrange the task sequence based on the appointment task, and move the task within the extreme constraint time point according to the appointment time of the appointment task; use the total task throughput constraint as the constraint barrier of the unit time node, perform task movement adjustment, and establish a scheduling set; construct a comprehensive fitness scoring network, and use the comprehensive fitness scoring network to perform scoring calculation based on the trigger penalty coefficient, the task level of the appointment task, the first compensation constraint, and the second compensation constraint to construct a scoring set mapped with the scheduling set; perform scoring screening according to the scoring set to generate the consumption and supply scheduling result.

[0038] Specifically, the penalty coefficient is defined as the trigger penalty coefficient configured at the limit constraint time node, which is used to measure the severity of the task exceeding the limit time. The penalty coefficient can be determined according to the importance and urgency of the task. When the task exceeds the limit time, the scheduling result is deducted or the cost is increased according to the penalty coefficient. The penalty mechanism can encourage the scheduling algorithm to avoid violating the time constraint. Based on the requirements and characteristics of the scheduled tasks, the priority and order of task execution are determined. Within the limit constraint time point, the task allocation time is adjusted according to the flexibility and urgency of the task, and the time window of the task is dynamically adjusted to adapt to the changes in resources and demand. The total task throughput constraint is used as a constraint barrier per unit time node to ensure that the task volume does not exceed the capacity of the disinfection supply center at any time point. The throughput constraint is considered in the scheduling set to avoid resource overload. A comprehensive fitness scoring network is constructed, which considers the trigger penalty coefficient, task level, first compensation constraint and second compensation constraint. The scoring network can be a multi-factor evaluation model, specifically a neural network model, which scores and calculates each possible scheduling scheme in the scheduling set. The scoring result reflects the fitness and feasibility of the scheduling scheme. Screening is performed according to the scoring set to select the scheduling scheme with the highest fitness. The screening process can be based on multiple indicators, such as minimizing penalties, maximizing customer satisfaction, etc. Based on the screening results, the final consumption and supply scheduling results are generated. The results should include task allocation, execution schedule and any necessary adjustments or compensation measures.

[0039] Furthermore, the intelligent scheduling module 16 also includes:

[0040] The early warning analysis module is used to obtain the task sequence arrangement result, perform continuous fitness anomaly evaluation on the task sequence arrangement result, and establish an abnormal warning; the compensation processing module is used to perform the first compensation constraint of the preset early warning front window and the task level evaluation of the scheduled task based on the abnormal warning, obtain the hospital terminal corresponding to the lowest evaluation result, adjust the scheduled task of the corresponding hospital terminal, and optimize the consumption and supply scheduling according to the task adjustment result.

[0041] Specifically, the task sequence arrangement results are continuously evaluated for fitness to monitor the execution of the scheduling scheme. The evaluation is based on the comparison of actual execution data with expected data, such as task completion time, resource utilization, etc. When the fitness evaluation results show anomalies, such as task delays, resource shortages, etc., an abnormal warning is established. An early warning pre-window is set, that is, an early warning evaluation is performed a certain period of time before the task is executed. Intervention and adjustment can be made before the problem actually occurs. Based on the early warning pre-window, the first compensation constraint is evaluated to identify tasks that may violate the constraint. The evaluation includes factors such as task level, resource availability, and historical performance. During the evaluation process, the hospital terminals corresponding to the lowest evaluation results are identified. These hospital terminals have the highest scheduling risk and require special attention. Task adjustments are made to the appointment tasks of the corresponding hospital terminals to reduce the risk of violating constraints. Adjustments include reallocating resources, adjusting task schedules, or changing the order of task execution. According to the task adjustment results, the consumption and supply scheduling plan is re-optimized. The optimization goal is to minimize scheduling risks while maximizing customer satisfaction and resource utilization.

[0042] Furthermore, the platform also includes:

[0043] A creation module is used to establish unique identification IDs of N hospital terminals and a universal identification ID for instruments; a coding module is used to perform instrument coding identification of N hospital terminals based on the unique identification ID and the universal identification ID; and a management module is used to track and manage N hospital terminals based on the instrument coding identification.

[0044] Specifically, assign a unique identification ID to each hospital terminal, such as UUID, which is a universal unique identifier. This ID can uniquely identify each hospital terminal and is persistent and unchanged in the system. Assign a universal identification ID to each device type. This ID can identify the type and properties of the device, regardless of which hospital terminal it is used in. Develop coding rules based on factors such as the type, specification, and purpose of the device. The code contains enough information for easy tracking and management. Use coding rules to assign a unique coding identifier to the device at each hospital terminal. The coding identifier can be generated by combining the unique identification ID of the hospital terminal and the universal identification ID of the device. The tracking system can record information such as the location, usage status, and maintenance history of each device, and can also update the status of the device in real time and provide historical tracking information.

[0045] Furthermore, the platform also includes:

[0046] An information analysis module is used to perform feature analysis based on the feature information library and construct a prediction fitting model for N hospital terminals; a prediction module is used to perform demand analysis on N hospital terminals based on the prediction fitting model and establish a prediction result; a reconstruction module is used to reconstruct the consumption and supply scheduling result according to the appointment task and the prediction result, and manage according to the reconstructed consumption and supply scheduling result.

[0047] Specifically, extract features related to hospital terminal demand from the feature information library, such as historical order data, hospital-specific demand, etc. Features include time series data, categorical data, numerical data, etc. Select appropriate prediction models, such as linear regression, time series analysis, neural network, etc., according to the feature type and prediction target. Use historical data to train the model so that it can learn the changing rules of hospital terminal demand, and then perform parameter tuning and cross-validation to improve the prediction accuracy of the model. Use the trained prediction model to predict the future demand of the hospital terminal, including the quantity, type, and time distribution of demand. Compare the prediction results with the actual execution data to evaluate the prediction accuracy of the model. Adjust and optimize the model according to the verification results. Reconstruct the original disinfection and supply scheduling results based on the scheduled tasks and prediction results. Reconstruction includes adjusting the task order, increasing or decreasing resource allocation, etc. to improve scheduling efficiency. Based on the reconstructed disinfection and supply scheduling results, execute the disinfection and supply tasks. During the execution process, continuously monitor the scheduling status to ensure that the tasks are completed on time.

[0048] Furthermore, the platform also includes:

[0049] An adaptive update module is used to perform monitoring based on the consumption and supply scheduling result, establish a verification data set, adaptively update the consumption and supply scheduling result through the verification data set, and manage with the adaptively updated consumption and supply scheduling result.

[0050] Specifically, the execution process of the consumption and supply scheduling results is monitored in real time. Monitoring includes task execution status, resource utilization, customer feedback, etc. Actual data during the execution process is collected, including task completion time, resource usage, etc. These data are used as part of the validation data set to evaluate the accuracy of the scheduling results. The execution monitoring data is integrated with the prediction results generated by the prediction module. The integrated data set contains actual execution data and prediction data. The data is cleaned and processed to remove noise and outliers, and the prediction model is trained and updated using the validation data set. By learning the actual data during the execution process, its prediction ability is optimized. According to the prediction results after the model is updated, the consumption and supply scheduling results are adjusted, including reallocating resources and adjusting the order of task execution.

[0051] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0052] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. The consumption and supply dispatching platform based on the regional digital brain is characterized by: The consumption and supply dispatching platform comprises: The communication module is used to establish digital communication between the disinfection supply center and N hospital terminals, and synchronously transmit data to the disinfection supply dispatching platform; An information base construction module is used to construct a basic information base and a feature information base of the disinfection supply center and the N hospital terminals based on the received data, wherein the basic information base includes the location distribution information and dispatch path information of the disinfection supply center and the N hospital terminals, and the feature information base includes the task feature information and trust feature information of the disinfection supply center and the N hospital terminals; A constraint building module is used to establish the total task throughput constraint of the disinfection supply center, obtain the appointment tasks of N hospital terminals through the communication module, and create the limit constraint time node based on the appointment tasks; A first compensation module, configured to perform a scheduling stability analysis based on the scheduled task and the basic information library, and generate a first compensation constraint; A second compensation module, configured to perform a trust analysis of N hospital terminals based on the feature information database and the reservation task, and construct a second compensation constraint; An intelligent scheduling module is used to receive scheduled tasks, limit constraint time nodes, total task throughput constraints, first compensation constraints and second compensation constraints, perform scheduling analysis through the regional digital brain, generate consumption and supply scheduling results, and manage based on the consumption and supply scheduling results; Wherein, the first compensation module is further used for: Reading path data based on the dispatch path information to build a historical path time period pass database for each dispatch path; Performing a traffic period analysis through the reservation task, performing a scheduling stability analysis based on the traffic period analysis result and the historical path period traffic database, and establishing the first compensation constraint; The second compensation module is also used for: Execute the data sorting in the task feature library, and build the feature database after denoising the data; Establishing a time series decay factor, performing weighted calculation on the data in the feature database by using the time series decay factor, and constructing a feature trust value identifier; Execute feature similarity clustering under the same hospital terminal of the feature database, perform trust analysis on N hospital terminals according to the feature similarity clustering result, feature trust value identifier and trust feature information, and construct a second compensation constraint; The intelligent scheduling module is also used for: Configure the trigger penalty coefficient of the limit constraint time node; When the regional digital brain performs scheduling analysis, the task sequence is arranged based on the scheduled tasks, and the tasks are moved and allocated within the limit constraint time point according to the scheduled time of the scheduled tasks; Taking the total task throughput constraint as the constraint barrier of the unit time node, performing task movement adjustment, and establishing a scheduling set; Constructing a comprehensive fitness scoring network, performing scoring calculation based on the trigger penalty coefficient, the task level of the scheduled task, the first compensation constraint, and the second compensation constraint through the comprehensive fitness scoring network, and constructing a scoring set mapped with the scheduling set; Perform score screening according to the score set to generate a consumption and supply scheduling result; An early warning analysis module is used to obtain the task sequence arrangement result, perform continuous fitness abnormality evaluation on the task sequence arrangement result, and establish an abnormality early warning; A compensation processing module is used to evaluate the first compensation constraint of the preset warning front window and the task level of the scheduled task based on the abnormal warning, obtain the hospital terminal corresponding to the lowest evaluation result, adjust the scheduled task of the corresponding hospital terminal, and optimize the consumption and supply scheduling according to the task adjustment result; The consumption and supply dispatching platform also includes: Create a module for establishing unique identification IDs of N hospital terminals and universal identification IDs of equipment; A coding module, used for coding and identifying the equipment of N hospital terminals based on the unique identification ID and the universal identification ID; A management module, used for tracking and managing N hospital terminals based on the equipment coding identification; An information analysis module, used to perform feature analysis based on the feature information library and construct a prediction fitting model for N hospital terminals; A prediction module, used to perform demand analysis of N hospital terminals based on the prediction fitting model and establish prediction results; A reconstruction module, used to reconstruct the consumption and supply scheduling result according to the reservation task and the prediction result, and manage according to the reconstructed consumption and supply scheduling result; An adaptive update module is used to perform monitoring based on the consumption and supply scheduling result, establish a verification data set, adaptively update the consumption and supply scheduling result through the verification data set, and manage with the adaptively updated consumption and supply scheduling result.

Images