Surgery duration prediction and scheduling method based on machine learning

Abstract

The present invention discloses a method for predicting and scheduling operation duration based on machine learning, which belongs to the technical field of medical care informatics and comprises the following steps: obtaining historical processing data of a platform of the same operation type as the predicted operation type, and analyzing to obtain a historical processing difficulty index; analyzing to obtain a resource consumption index, and comprehensively analyzing to obtain an emergency judgment result of operation duration prediction; analyzing to obtain a data transmission channel effect index, and obtaining a final data segmentation judgment result based on a preliminary judgment result of data segmentation and a data transmission channel effect index analysis, and performing corresponding data processing to obtain a feature data packet; selecting a corresponding data transmission protocol based on the emergency judgment result of the operation duration prediction, thereby transmitting the feature data packet to an operation duration prediction module; the operation duration prediction module receives the feature data packet, and uses a machine learning algorithm to analyze to obtain an operation duration prediction value, and performs automatic scheduling prompts, thereby solving the problem of slow response of operation duration prediction in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of medical care informatics, and in particular to a method for predicting and scheduling surgery duration based on machine learning. Background Art

[0002] With the continuous advancement of medical technology and the rise of information technology, accurate prediction of surgical duration has become crucial for improving the quality of healthcare services. As a core component of the healthcare system, accurate estimation of surgical duration is crucial for the efficient allocation of hospital resources, the optimal scheduling of surgical procedures, and the improvement of the patient experience.

[0003] The existing surgery duration prediction system is achieved by mutual learning and integration of features from different modalities, extracting key important features that affect surgery duration and inputting them into the existing surgery duration prediction model.

[0004] For example, the invention patent with publication number CN118711779A discloses a method for predicting surgical duration based on multimodal feature fusion, which includes: using a feature initialization module to encode and initialize preoperative data to obtain feature information of different modalities; using a cross-attention feature fusion module to learn and fuse features of different modalities, extract key important features that affect surgical duration, and obtain multimodal features; using a multimodal feature fusion and duration prediction module to fuse the multimodal features, and then using the fused features to predict the duration of the surgery.

[0005] For example, the invention patent with publication number CN111951946A discloses a deep learning-based surgery scheduling system, method, storage medium and terminal, which include: a surgery duration prediction module, which is used to construct a surgery duration prediction model and use the surgery duration prediction model to predict the duration data of the current surgery; a surgery duration correction module, which is used to correct the predicted duration data; a surgery resource reservation module, which is used to reserve resources related to the current surgery; and a surgery scheduling optimization module, which is used to optimize the scheduling of the predicted and / or corrected duration data according to a genetic algorithm.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] Existing medical platforms require large-scale data processing and analysis, which leads to some parallel data processing. This can easily lead to excessive consumption of computing resources or bottlenecks, which in turn affects the immediate response and accuracy of the prediction model. Therefore, there is a problem of slow response in the prediction of surgical duration. Summary of the Invention

[0008] The present invention provides a machine learning-based surgery duration prediction and scheduling method, which solves the problem in the prior art that when the medical system encounters insufficient resources due to data concurrency, resource allocation cannot be flexibly adjusted according to the urgency of the duration prediction, resulting in slow response to surgery duration prediction, thereby achieving accurate and timely prediction of surgery duration.

[0009] The present invention provides a method for predicting and scheduling operation duration based on machine learning, comprising the following steps: when a medical information platform receives an operation duration prediction request, it obtains the platform's historical processing data and analyzes it to obtain a historical processing difficulty index; it obtains the medical information platform's resource parameters within a first preset time period, analyzes it to obtain a resource consumption index, and obtains an emergency judgment result of the operation duration prediction based on a comprehensive analysis of the historical processing difficulty index and the resource consumption index, wherein the emergency judgment result of the operation duration prediction includes an urgent operation duration prediction and a non-urgent operation duration prediction; the medical information platform automatically retrieves prediction feature data, and obtains a preliminary data segmentation judgment result based on the analysis of the emergency judgment result of the operation duration prediction; it obtains data transmission channel effect parameters, analyzes it to obtain a data transmission channel effect index, obtains a final data segmentation judgment result based on the preliminary data segmentation judgment result and the data transmission channel effect index, and performs corresponding data processing to obtain a feature data packet; it selects a corresponding data transmission protocol based on the emergency judgment result of the time prediction, thereby transmitting the feature data packet to the operation duration prediction module; the operation duration prediction module receives the feature data packet, uses a machine learning algorithm to analyze it to obtain a predicted operation duration value, and performs automatic scheduling prompts.

[0010] Furthermore, when the medical information platform receives a request for predicting the length of surgery, it obtains the platform's historical processing data and analyzes it to obtain a historical processing difficulty index. The specific steps include: when the medical information platform receives a request for predicting the length of surgery, it obtains the predicted surgery type, and thereby collects historical data of the medical information platform processing the same type of surgery as the predicted surgery type, and records it as the platform's historical processing data. The platform's historical processing data includes historical average data loading time, historical average CPU usage, historical average I / O waiting time, historical average number of input and output operations per second, and historical average GPU memory occupancy; obtaining a preset low-performance verification set in the medical database, The low-performance verification set includes the maximum historical data loading time, the maximum historical I / O waiting time and the maximum historical input and output operations per second; the historical processing difficulty index is obtained based on the analysis of the platform's historical processing data and the low-performance verification set; the historical processing difficulty index can be obtained by comparing the historical average data loading time, the historical average I / O waiting time and the historical average input and output operations per second with the maximum historical data loading time, the maximum historical I / O waiting time and the maximum historical input and output operations per second, and combining them with the historical average CPU usage and the historical average GPU memory occupancy, and then introducing influence weights to combine them respectively.

[0011] Furthermore, the resource parameters of the medical information platform within the first preset time period are obtained and analyzed to obtain a resource consumption index. The specific steps include: obtaining the resource parameters of the medical information platform within the first preset time period, the medical information platform resource parameters including the number of surgery duration prediction requests, the average number of data queries per second, the average response time, the prediction failure rate, the number of user accesses and the number of concurrent requests; obtaining the ideal set of platform resources preset in the medical database, and analyzing it with the medical information platform resource parameters to obtain a resource consumption index; the ideal set of platform resources preset in the medical database includes the ideal value of the number of surgery duration prediction requests, the ideal value of the average number of data queries per second, the ideal value of the average response time, the ideal value of the prediction failure rate, the ideal value of the number of user accesses and the ideal value of the number of concurrent requests; the resource consumption index is used to compare the average number of data queries per second with the ideal value of the average number of data queries per second, and the comparison results of comparing the average response time, the prediction failure rate, the number of user accesses and the number of concurrent requests with the ideal value of the average response time, the critical value of the prediction failure rate, the ideal value of the number of user accesses and the ideal value of the number of concurrent requests, and introducing the corresponding influence weights for fusion processing to obtain the resource consumption index.

[0012] Furthermore, the duration prediction emergency judgment result is obtained based on the comprehensive analysis of the historical processing difficulty index and the resource consumption index, and the specific steps include: obtaining the historical processing difficulty lower limit value and the resource consumption index lower limit value preset in the medical information platform; comparing the historical processing difficulty index with the historical processing difficulty lower limit value, and comparing the resource consumption index with the resource consumption index lower limit value to obtain the duration prediction emergency judgment result; if the historical processing difficulty index is above the historical processing difficulty lower limit value and the resource consumption index is above the resource consumption index lower limit value, then the duration prediction emergency judgment result is duration prediction emergency, otherwise the duration prediction is not urgent; the duration prediction emergency judgment result includes duration prediction emergency and duration prediction not urgent.

[0013] Furthermore, the analysis of the emergency judgment result of the duration prediction obtains the preliminary judgment result of the data segmentation, and the specific steps include: obtaining the emergency judgment result of the duration prediction; if the emergency judgment result of the duration prediction is that the duration prediction is urgent, then the preliminary judgment result of the data segmentation is that the segmentation is preliminarily executed; if the emergency judgment result of the duration prediction is that the duration prediction is not urgent, then the preliminary judgment result of the data segmentation is that the segmentation is preliminarily not executed.

[0014] Furthermore, the data transmission channel effect parameters are obtained and the data transmission channel effect indicators are obtained by analysis. The specific steps include: obtaining the data transmission channel effect parameters, the data transmission channel effect parameters including the average network upload speed, average bandwidth, average CPU utilization, average channel occupancy and channel bit error rate in the second preset time period; obtaining the ideal channel effect data set preset in the medical information platform, and analyzing it with the data transmission channel effect parameters to obtain the data transmission channel effect indicator; the ideal channel effect data set includes the ideal network upload speed value, the ideal bandwidth value and the channel bit error rate limit value; the data transmission channel effect indicator is used to introduce influence weights after comparing the average network upload speed with the ideal network upload speed value, comparing the average bandwidth with the ideal bandwidth value, and comparing the channel bit error rate with the channel bit error rate limit value, and combining the average CPU utilization and average channel occupancy introduced with the influence weights to obtain the data transmission channel effect indicator.

[0015] Furthermore, the final data segmentation judgment result is obtained based on the preliminary judgment result of data segmentation and the data transmission channel effect index analysis, and corresponding data processing is performed to obtain a feature data packet. The specific steps include: obtaining the data transmission channel effect threshold preset in the medical information platform, and comparing it with the data transmission channel effect index to obtain the data transmission channel quality assessment result, and the data transmission channel quality assessment result includes the data transmission channel quality being qualified and the data transmission channel quality being unqualified; obtaining the final data segmentation judgment result based on the preliminary judgment result of data segmentation and the data transmission channel effect index analysis, and the final data segmentation judgment result includes data segmentation and data not segmented; if the preliminary judgment result of data segmentation is that preliminary segmentation is not performed and the data transmission channel quality assessment result is that the data transmission channel quality is qualified, then the final data segmentation judgment result is that the data is not segmented, otherwise it is segmented; if the final data segmentation judgment result is that the data is segmented, then the data segmentation mark is obtained by analysis. The data segmentation standard is used to determine the data segmentation process, and the data segmentation process is performed based on the data segmentation standard to obtain a characteristic data packet, wherein the data segmentation standard includes a first data segmentation standard, a second data segmentation standard, and a third data segmentation standard; wherein, if the preliminary judgment result of the data segmentation is that the segmentation is preliminarily executed and the data transmission channel quality assessment result is that the data transmission channel quality is qualified, then the first data segmentation standard is obtained by analysis, and the data segmentation process is performed based on the first data segmentation standard to obtain a characteristic data packet; if the preliminary judgment result of the data segmentation is that the segmentation is preliminarily executed and the data transmission channel quality assessment result is that the data transmission channel quality is unqualified, then the second data segmentation standard is obtained by analysis, and the data segmentation process is performed based on the second data segmentation standard to obtain a characteristic data packet; if the preliminary judgment result of the data segmentation is that the segmentation is not preliminarily executed and the data transmission channel quality assessment result is that the data transmission channel quality is unqualified, then the third data segmentation standard is obtained by analysis, and the data segmentation process is performed based on the third data segmentation standard to obtain a characteristic data packet.

[0016] Furthermore, the analysis obtains a first data segmentation standard, and data segmentation processing is performed based on the first data segmentation standard to obtain a characteristic data packet. The specific steps include: obtaining a comprehensive emergency assessment index based on the analysis of historical processing difficulty indicators and resource consumption indicators; obtaining each comprehensive emergency assessment index interval preset in the medical information platform and the single data transmission standard corresponding to each comprehensive emergency assessment index interval, and matching them with the comprehensive emergency assessment index. If the comprehensive emergency assessment index is within a preset comprehensive emergency assessment index interval, the single data transmission standard corresponding to the interval is obtained as the first data segmentation standard; data segmentation processing is performed based on the first data segmentation reference standard to obtain a characteristic data packet; the comprehensive emergency assessment index is used to combine the historical processing difficulty indicator with the historical processing difficulty impact weight, and then process the result with the resource consumption indicator and the resource consumption impact weight to obtain a comprehensive emergency assessment index.

[0017] Furthermore, the analysis obtains a second data segmentation standard, and data segmentation processing is performed based on the second data segmentation standard to obtain a characteristic data packet. The specific steps include: obtaining a processing evaluation efficiency indicator based on the comprehensive emergency evaluation index and the data transmission channel effect index analysis; obtaining the processing evaluation efficiency indicator threshold preset in the medical information platform, and performing difference processing with the processing evaluation efficiency index to obtain a processing evaluation efficiency difference, performing comprehensive processing based on the processing evaluation efficiency difference to obtain a processing evaluation efficiency deviation; obtaining each processing evaluation efficiency deviation interval preset in the medical information platform and the single data transmission standard corresponding to the processing evaluation efficiency deviation interval, if the processing evaluation efficiency deviation is within a certain preset processing evaluation efficiency deviation interval, obtaining the single data transmission standard corresponding to the interval as the second data segmentation standard; obtaining the second data segmentation standard based on the analysis, and performing data segmentation processing based on the second data segmentation standard to obtain a characteristic data packet; the processing evaluation efficiency indicator is used to characterize the comprehensive complexity of data processing by the comprehensive emergency evaluation index and the data transmission channel effect index.

[0018] Furthermore, the corresponding data transmission protocol is selected based on the emergency judgment result of the duration prediction, thereby transmitting the feature data packet to the operation duration prediction module. The specific steps include: analyzing based on the emergency judgment result of the duration prediction to obtain the corresponding data transmission protocol, and the data transmission protocol includes the UDP protocol and the TCP protocol; if the emergency judgment result of the duration prediction is that the duration prediction is urgent, the UDP protocol is used to upload the predicted feature data to the operation duration prediction module; if the emergency judgment result of the duration prediction is that the duration prediction is not urgent, the TCP protocol is used to upload the predicted feature data to the operation duration prediction module.

[0019] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0020] 1. The machine learning-based surgery duration prediction and scheduling method provided by the present invention obtains the platform historical processing data of the same surgery type as the predicted surgery and the resource parameters of the medical information platform, and comprehensively analyzes to obtain the emergency judgment result of the duration prediction, so as to dynamically evaluate the urgency of the duration prediction and adjust the data processing flow according to the urgency of the duration prediction, thereby realizing accurate and timely prediction of the surgery duration, and effectively solving the problem in the prior art that it is impossible to flexibly adjust resource allocation according to the urgency of the duration prediction, resulting in slow response to the surgery duration prediction.

[0021] 2. The present invention can accurately judge the status and efficiency of the data transmission channel through a comprehensive analysis based on historical processing difficulty indicators and resource consumption indicators, as well as the evaluation of data transmission channel effect parameters, thereby realizing the selection of more efficient data transmission protocols in emergency situations of duration prediction to speed up data transmission, ensure the timeliness and accuracy of operation duration prediction data, and improve the response capability and service quality of the medical information platform in emergency situations.

[0022] 3. By determining the reference standard for data segmentation based on the data transmission channel effect index, the data size during the data transmission process can be optimized, thereby reducing the data transmission delay and bandwidth occupancy while maintaining data integrity, thereby improving the data processing efficiency and prediction accuracy of the surgery duration prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Flowchart of the method for predicting and scheduling surgical duration based on machine learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiments of the present application provide a method for predicting and scheduling surgery duration based on machine learning, thereby solving the problem in the prior art of being unable to flexibly adjust resource allocation according to the urgency of the duration prediction when insufficient resources are caused by data concurrency in the medical system, resulting in slow response to surgery duration prediction, thereby achieving accurate and timely prediction of surgery duration.

[0025] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0026] like Figure 1As shown, it is a flow chart of the operation duration prediction and scheduling method based on machine learning provided in an embodiment of the present application, and the method includes the following steps: when the medical information platform receives the operation duration prediction request, it obtains the platform's historical processing data and analyzes it to obtain the historical processing difficulty index; obtains the medical information platform resource parameters within the first preset time period, analyzes it to obtain the resource consumption index, and obtains the duration prediction emergency judgment result based on the comprehensive analysis of the historical processing difficulty index and the resource consumption index, and the duration prediction emergency judgment result includes the duration prediction urgent and the duration prediction non-urgent; the medical information platform automatically retrieves the prediction feature data, and obtains the data segmentation preliminary judgment result based on the duration prediction emergency judgment result; obtains the data transmission channel effect parameter, analyzes it to obtain the data transmission channel effect index, obtains the data segmentation final judgment result based on the data segmentation preliminary judgment result and the data transmission channel effect index, and performs corresponding data processing to obtain a feature data packet; selects the corresponding data transmission protocol based on the duration prediction emergency judgment result, and transmits the feature data packet to the operation duration prediction module; the operation duration prediction module receives the feature data packet, uses the machine learning algorithm to analyze it to obtain the operation duration prediction value, and performs automatic scheduling prompts.

[0027] In this embodiment, by dynamically analyzing equipment processing capabilities and information platform resource consumption, data processing flows can be flexibly adjusted to ensure that urgent surgeries receive priority and, when insufficient, dynamically allocate system resources based on the urgency of the surgery. This improves system efficiency. Based on the duration prediction of urgency and the effectiveness of the data transmission channel, data transmission protocols are intelligently selected and data segmented, effectively reducing data transmission latency and bandwidth usage. Precise data processing and transmission strategies, coupled with advanced machine learning algorithms, improve the accuracy and reliability of surgery duration predictions.

[0028] Furthermore, when the medical information platform receives a request for surgery duration prediction, it obtains the platform's historical processing data and analyzes it to obtain a historical processing difficulty index. The specific steps include: when the medical information platform receives a request for surgery duration prediction, it obtains the predicted surgery type, and thereby collects historical data of the medical information platform processing the same type of surgery as the predicted surgery type, and records it as the platform's historical processing data. The platform's historical processing data includes the historical average data loading time, the historical average CPU usage, the historical average I / O waiting time, the historical average number of input and output operations per second, and the historical average GPU memory occupancy rate; obtains a preset low-performance verification set in the medical database, and The low-performance verification set includes the maximum historical data loading time, the maximum historical I / O waiting time, and the maximum historical input and output operations per second; the historical processing difficulty index is obtained based on the analysis of the platform's historical processing data and the low-performance verification set; the historical processing difficulty index can be obtained by comparing the historical average data loading time, the historical average I / O waiting time, and the historical average input and output operations per second with the maximum historical data loading time, the maximum historical I / O waiting time, and the maximum historical input and output operations per second, and combining them with the historical average CPU usage and the historical average GPU memory occupancy, and then introducing influence weights to combine them respectively.

[0029] In this embodiment, it should be noted that the historical average data loading time of the computer refers to the historical average loading time when the computer opens the surgery duration prediction module, and the CPU usage refers to the percentage of the CPU occupied when processing tasks. The historical average CPU usage shows the historical average CPU load of the computer. A high CPU usage indicates that the computer system is running a large number of computationally intensive tasks, or that there are certain processes that occupy too many CPU resources. The historical average I / O waiting time, the historical average number of input and output operations per second, and the historical average GPU memory occupancy are all historical average data when the computer device opens the surgery duration prediction module.

[0030] The platform's historical processing data includes the computer's historical average data loading time, historical average CPU usage, historical average I / O wait time, historical average number of input and output operations per second, and historical average GPU memory usage. These performance indicators can be collected by installing a monitoring tool (such as Nagios, Zabbix, or Windows Performance Monitor) on the server.

[0031] Through this comprehensive monitoring solution, multiple key performance indicators of computer equipment can be simultaneously captured, providing a comprehensive and accurate data foundation for calculating the historical processing difficulty index. This helps to more accurately assess the difficulty of analyzing historical processing data. Based on comprehensive historical processing data and low-performance validation sets, the medical information platform can more intelligently analyze equipment performance bottlenecks and optimize resource allocation. Accurate historical processing difficulty indicators help improve the accuracy of surgery duration predictions.

[0032] By analyzing the historical processing difficulty index, we can understand the historical processing performance and difficulty of a device. This helps the medical information platform rationally allocate computing resources when receiving prediction requests, ensuring the timeliness and accuracy of prediction tasks. By monitoring the platform's historical processing data, potential performance issues can be promptly identified and resolved, helping to improve the overall stability of the medical information platform and reduce prediction task failures or delays caused by device failures or performance degradation. The historical processing difficulty index provides important decision-making support for the medical information platform. When faced with multiple prediction tasks, the platform can intelligently select the most appropriate device for prediction based on its performance bottlenecks and difficulty level, optimizing overall performance and resource utilization.

[0033] Through historical processing difficulty indicators, we can identify the performance bottlenecks of the platform when processing specific types of surgeries, such as data loading speed, CPU usage, I / O waiting time, etc., to help the platform optimize resource allocation and ensure the stable operation of the medical information platform.

[0034] By analyzing the platform's historical processing data (including the computer's historical average data loading time, historical average CPU usage, historical average I / O wait time, historical average number of input / output operations per second, and historical average GPU memory utilization), we consider the interplay between these parameters. For example, a long I / O wait time increases data loading time. CPU utilization and IOPS are interdependent; high values ​​in one lead to high values ​​in the other. CPU utilization and GPU memory utilization influence each other during data processing tasks. When GPU memory utilization is high, the CPU needs to handle more data scheduling tasks, resulting in increased CPU utilization. Conversely, high CPU utilization affects GPU task scheduling efficiency. I / O wait time is closely related to IOPS. When IOPS is high, the I / O device becomes a bottleneck, increasing I / O wait time. When data loading takes a long time, the CPU needs to wait for data loading to complete, resulting in decreased CPU utilization.

[0035] Get the historical processing difficulty index, the specific method is:

[0036]

[0037] Where H represents the historical processing difficulty index, T represents the historical average data loading time of the computer, and T a represents the maximum historical data loading time, e represents a natural constant, V represents the historical average CPU usage, D represents the historical average I / O waiting time, and D a Indicates the maximum historical I / O waiting time, C a represents the historical maximum number of input and output operations per second, C represents the historical average number of input and output operations per second, X represents the historical average GPU memory occupancy, α1 represents the impact weight of data loading duration, α2 represents the impact weight of CPU usage, α3 represents the impact weight of I / O wait time, α4 represents the impact weight of input and output operations, and α5 represents the impact weight of GPU memory occupancy.

[0038] The data loading time impact weight, CPU usage impact weight, I / O waiting time impact weight, input and output operation number impact weight and GPU memory occupancy impact weight can be obtained from the database. For example, the data loading time impact weight can be obtained by obtaining the historical data loading time stored in the database, and the data loading time impact weight corresponding to the historical data loading time, thereby constructing a data loading time mapping set, wherein there is a one-to-one or many-to-one correspondence in the mapping set. The data loading time impact weight can be obtained by inputting the data loading time data to be used into the data loading time mapping set. The other impact weights such as the CPU usage impact weight, the I / O waiting time impact weight, the input and output operation number impact weight and the GPU memory occupancy impact weight are obtained in the same way as the data loading time impact weight, and can all be matched in the corresponding mapping set.

[0039] Furthermore, resource parameters of the medical information platform within the first preset time period are obtained, and resource consumption indicators are obtained by analysis. The specific steps include: obtaining resource parameters of the medical information platform within the first preset time period, the medical information platform resource parameters include the number of surgery duration prediction requests, the average number of data queries per second, the average response time, the prediction failure rate, the number of user visits, and the number of concurrent requests; obtaining the ideal set of platform resources preset in the medical database, and analyzing them with the medical information platform resource parameters to obtain a resource consumption indicator; the ideal set of platform resources preset in the medical database includes the ideal value of the number of surgery duration prediction requests, the ideal value of the average number of data queries per second, the ideal value of the average response time, the critical value of the prediction failure rate, the ideal value of the number of user visits, and the ideal value of the number of concurrent requests; the resource consumption indicator is used to characterize the degree of consumption of medical information platform resources by the number of surgery duration prediction requests, the average number of data queries per second, the average response time, the prediction failure rate, the number of user visits, and the number of concurrent requests of the medical information platform within the first preset time period.

[0040] In this embodiment, the number of surgery duration prediction requests can be obtained by counting the number of surgery duration prediction requests received within the first preset time period in the background management system of the medical information platform and counting them. The average number of data queries per second can be obtained by calculating the average value by monitoring the number of query requests processed by the platform database per unit time. The average response time can be obtained by recording the response time of each request processed by the platform and calculating the average value. The prediction failure rate can be obtained by counting the proportion of failed surgery duration prediction requests in the first preset time period to the total number of requests. The number of user visits can be obtained by counting the number of users who access the platform within the first preset time period through the background management system. The number of concurrent requests can be obtained by the number of requests processed simultaneously by the background management system per unit time.

[0041] By acquiring and analyzing the resource parameters of the medical information platform within a first preset time period and comparing them with the preset ideal set of platform resources, resource consumption indicators are derived that can intuitively reflect the resource usage of the medical information platform in different time periods, helping managers accurately understand the platform's resource consumption trends and thus carry out more reasonable resource planning and management. Through in-depth analysis of resource consumption indicators, wasteful or inefficient resource use can be identified, such as idle resources due to predicted request volumes far below ideal values, or resource shortages due to excessively high concurrent requests.

[0042] Analyzing resource consumption metrics can help assess the efficiency of platform resource usage, identify instances of over- or under-utilization, and enable appropriate adjustments. By analyzing resource consumption metrics, the platform can better balance load and avoid system performance degradation caused by overuse of certain resources. Monitoring resource consumption metrics allows the platform to promptly identify resource shortages, avoid prediction failures caused by insufficient resources, and improve prediction success rates. By optimizing resource consumption, the platform can shorten response times, reduce user wait times, and enhance the user experience.

[0043] It should be noted that the prediction failure rate refers to the ratio of timeouts or errors caused by insufficient resources to the total number of predictions, and the number of concurrent requests refers to the number of access requests processed by the medical information platform at the same time.

[0044] Resource consumption indicators are used to compare the average number of data queries per second with the ideal value of the average number of data queries per second, and to compare the average response time, predicted failure rate, number of user accesses, and number of concurrent requests with the ideal value of the average response time, the critical value of the predicted failure rate, the ideal value of the number of user accesses, and the ideal value of the number of concurrent requests, respectively. The corresponding impact weights are introduced for fusion processing to obtain resource consumption indicators.

[0045] Get the resource consumption index. The specific method is:

[0046]

[0047] It should be noted that XH represents the resource consumption indicator, YC represents the number of surgery duration prediction requests, YC1 represents the ideal value of the surgery duration prediction request volume, CX represents the average number of data queries per second, CX1 represents the ideal value of the average number of data queries per second, SC represents the average response time, SC1 represents the ideal value of the average response time, SA represents the prediction failure rate, SA1 represents the ideal value of the prediction failure rate, SM represents the number of user accesses, SM1 represents the ideal value of the number of user accesses, BF represents the number of concurrent requests, BF1 represents the ideal value of the number of concurrent requests, β1 represents the impact weight of the surgery duration prediction request volume, β2 represents the impact weight of the number of data queries, β3 represents the impact weight of the response time, β4 represents the impact weight of the prediction failure rate, β5 represents the impact weight of the number of user accesses, and β6 represents the impact weight of the number of concurrent requests.

[0048] The weights influencing the number of surgery time prediction requests, the weights influencing the number of data queries, the weights influencing the response time, the weights influencing the prediction failure rate, the weights influencing the number of user visits and the weights influencing the number of concurrent requests can be obtained from the database. For example, the weights influencing the number of surgery time prediction requests can be obtained by obtaining the historical number of surgery time prediction requests stored in the database, and the weights influencing the number of surgery time prediction requests corresponding to the historical number of surgery time prediction requests, thereby constructing a mapping set of surgery time prediction requests, wherein there is a one-to-one or many-to-one correspondence in the mapping set. The weights influencing the number of surgery time prediction requests can be obtained by inputting the required surgery time prediction request data into the mapping set of surgery time prediction requests. The other weights such as the weights influencing the number of data queries, the weights influencing the response time, the weights influencing the prediction failure rate, the weights influencing the number of user visits and the weights influencing the number of concurrent requests are obtained in the same way as the weights influencing the number of surgery time prediction requests, and can all be matched in the corresponding mapping set.

[0049] Resource consumption indicators are derived by analyzing the resource parameters of the medical information platform (number of surgery duration prediction requests, average number of data queries per second, average response time, prediction failure rate, number of user accesses, and number of concurrent requests). This takes into account the interplay between these parameters. For example, an increase in surgery duration prediction requests will lead to an increase in the number of concurrent requests, thereby increasing the platform load. An increase in the number of data queries per second will increase the database load, thereby extending the average response time. An excessively long average response time will cause some requests to time out, increasing the prediction failure rate. An increase in the number of user accesses will lead to an increase in the number of concurrent requests, thereby increasing the platform load. An increase in the number of concurrent requests will directly lead to increased consumption of resources such as CPU, memory, and network bandwidth.

[0050] By analyzing these parameters, we can identify performance bottlenecks in the platform. For example, if the average response time is too long and the prediction failure rate is high, it indicates inefficient database queries; if the number of concurrent requests is too high and resource consumption is high, it indicates insufficient system resources.

[0051] Furthermore, based on a comprehensive analysis of historical processing difficulty indicators and resource consumption indicators, an emergency judgment result of duration prediction is obtained, and the specific steps include: obtaining the historical processing difficulty lower limit value and the resource consumption indicator lower limit value preset in the medical information platform; comparing the historical processing difficulty indicator with the historical processing difficulty lower limit value, and comparing the resource consumption indicator with the resource consumption indicator lower limit value to obtain an emergency judgment result of duration prediction; if the historical processing difficulty indicator is above the historical processing difficulty lower limit value and the resource consumption indicator is above the resource consumption indicator lower limit value, then the emergency judgment result of duration prediction is urgent, otherwise the duration prediction is not urgent; the emergency judgment result of duration prediction includes urgent duration prediction and not urgent duration prediction.

[0052] In this embodiment, by comprehensively considering the historical processing difficulty index and resource consumption index, the urgency of the duration prediction can be more comprehensively evaluated, avoiding the one-sidedness that may be caused by a single indicator judgment, and can capture the dynamic relationship between surgical complexity and hospital resource utilization, thereby more accurately assigning priorities to surgeries. By dividing surgeries into two categories, urgent and non-urgent, it is convenient to more effectively allocate limited medical resources. Urgent surgeries can quickly obtain resources predicted by the platform's surgical duration, improving treatment efficiency and quality, while non-urgent surgeries can be arranged when resources permit, avoiding waste of resources, and non-urgent duration predictions can be analyzed in detail to make surgical duration predictions more accurate. Through data analysis and comparison, the surgical scheduling process can be continuously monitored and improved, improving the overall quality of medical services.

[0053] Furthermore, based on the analysis of the duration prediction emergency judgment result, the preliminary judgment result of data segmentation is obtained. The specific steps include: obtaining the duration prediction emergency judgment result. If the duration prediction emergency judgment result is that the duration prediction is urgent, the preliminary judgment result of data segmentation is that segmentation is preliminarily executed. If the duration prediction emergency judgment result is that the duration prediction is not urgent, the preliminary judgment result of data segmentation is that segmentation is preliminarily not executed.

[0054] In this embodiment, by deciding whether to perform data segmentation based on the urgency of the duration prediction, the method can quickly respond to the data needs of urgent duration predictions, avoid unnecessary processing steps, and thus improve the efficiency of overall data processing. For urgent duration prediction needs, timely data segmentation can ensure that key medical information is prioritized for processing and storage, helping the medical platform to quickly obtain the required information and make accurate diagnosis and treatment decisions. For non-urgent duration predictions, avoiding unnecessary data segmentation can reduce data redundancy and storage costs, and optimize the management and utilization of medical data. Through the automated data segmentation judgment process, manual intervention is reduced and the accuracy and efficiency of data processing are improved.

[0055] Furthermore, data transmission channel effect parameters are obtained and analyzed to obtain data transmission channel effect indicators. The specific steps include: obtaining data transmission channel effect parameters, which include the average network upload speed, average bandwidth, average CPU utilization, average channel occupancy and channel bit error rate within the second preset time period; obtaining the ideal channel effect data set preset in the medical information platform, and analyzing it with the data transmission channel effect parameters to obtain the data transmission channel effect indicator; the ideal channel effect data set includes the ideal value of network upload speed, ideal value of bandwidth and channel bit error rate limit value; the data transmission channel effect indicator is used to characterize the degree of influence of the average network upload speed, average bandwidth, average CPU utilization, average channel occupancy and channel bit error rate on data transmission of the data transmission channel.

[0056] In this embodiment, by acquiring and analyzing data transmission channel performance parameters (such as average network upload speed and average bandwidth), the status of the data transmission channel can be monitored in real time, and potential performance bottlenecks can be promptly identified and resolved, thereby improving data transmission efficiency and stability. By monitoring the channel bit error rate, errors in data transmission can be promptly detected, and measures can be taken to reduce the bit error rate, ensuring the accuracy and integrity of medical data. Monitoring the average channel occupancy rate helps optimize the priority and efficiency of emergency data transmission, ensuring that critical medical information can be transmitted quickly and accurately at critical moments. Based on data such as average CPU utilization, server resource allocation can be rationally adjusted to avoid resource waste, improve resource utilization, and reduce medical resource waste and cost expenditures caused by poor or interrupted data transmission.

[0057] Feedback on data transmission channel performance indicators helps users of the medical information platform understand the data transmission status and improve their trust and satisfaction with the platform. By optimizing the data transmission channel, the overall performance and user experience of the medical information platform can be improved, and users' dependence and loyalty to the platform can be enhanced.

[0058] The data transmission channel performance index is derived by analyzing data transmission channel performance parameters (average network upload speed, average bandwidth, average CPU utilization, average channel occupancy, and channel bit error rate during the second preset period). This index takes into account the interplay between these parameters. For example, a faster upload speed means data reaches its destination more quickly. A wider bandwidth allows for greater data transfer at the same time, thus supporting higher upload speeds. A channel with a higher average bandwidth can accommodate more data transmission simultaneously. Full utilization of bandwidth also depends on the CPU's processing power. When large amounts of data need to be uploaded quickly, the CPU must process this data efficiently. This is a key indicator of whether the CPU is overloaded when handling data upload tasks. Frequent channel occupancy affects its response speed and reliability, ultimately impacting the overall performance of the data transmission channel. A high bit error rate indicates that data has been erroneously transmitted or lost, increasing the need for data retransmission and reducing overall transmission efficiency. Furthermore, a high bit error rate can negatively impact CPU utilization.

[0059] Data transmission channel performance indicators can be used to identify bottlenecks in data transmission (such as network speed, bandwidth, and CPU utilization), thereby optimizing data transmission efficiency and reducing data transmission time. By monitoring parameters such as the channel bit error rate, data transmission problems can be promptly detected, preventing data loss or corruption and ensuring data transmission stability. By analyzing channel performance indicators, the platform can rationally allocate network resources to prevent excessive utilization of certain channels and the degradation of other channels. In emergency situations, data transmission channel performance indicators can help select the optimal transmission protocol (such as UDP or TCP) to ensure timely data transmission.

[0060] In summary, these parameters are interrelated and mutually influential, collectively determining the performance of a data transmission channel. A high-performing data channel should have fast upload speeds, sufficient bandwidth, reasonable CPU utilization, efficient channel responsiveness, and a low bit error rate. By comprehensively analyzing these parameters, we can assess the quality of the data transmission channel and the amount of data it can carry, providing strong support for optimizing data transmission.

[0061] The data transmission channel effectiveness index is used to introduce influence weights by comparing the average network upload speed with the ideal network upload speed, the average bandwidth with the ideal bandwidth, and the channel bit error rate with the channel bit error rate limit. The weighted average CPU utilization and average channel occupancy are then combined to obtain the data transmission channel effectiveness index.

[0062] The data transmission channel effect index is obtained by:

[0063]

[0064] Where GX represents the data transmission channel effect indicator, DS represents the average network upload speed, DS1 represents the ideal network upload speed, UK represents the average bandwidth, UK1 represents the ideal bandwidth, US represents the average CPU utilization, e represents the natural constant, OE represents the average channel occupancy, WM represents the channel bit error rate, WM1 represents the channel bit error rate limit, μ1 represents the network upload speed impact weight, μ2 represents the bandwidth impact weight, μ3 represents the CPU utilization impact weight, μ4 represents the average channel occupancy impact weight, and μ5 represents the channel bit error rate impact weight.

[0065] The network upload speed influence weight, bandwidth influence weight, CPU utilization influence weight, channel average occupancy influence weight, and channel bit error rate influence weight can be obtained from a database. For example, the network upload speed influence weight can be obtained by obtaining the historical network upload speed stored in the database, and the network upload speed influence weight corresponding to the historical network upload speed, thereby constructing a network upload speed mapping set, wherein there is a one-to-one or many-to-one correspondence in the mapping set. The network upload speed influence weight can be obtained by inputting the required network upload speed data into the network upload speed mapping set. The other influence weights, such as the bandwidth influence weight, CPU utilization influence weight, channel average occupancy influence weight, and channel bit error rate influence weight, are obtained in the same manner as the network upload speed influence weight, and can all be matched in the corresponding mapping set.

[0066] It should be noted that the comprehensive emergency assessment index is obtained based on the analysis of historical processing difficulty indicators and resource consumption indicators. The specific method is as follows: Where PZ represents the comprehensive emergency assessment index, H represents the historical processing difficulty index, XH represents the resource consumption index, γ1 represents the impact weight of historical processing difficulties, and γ2 represents the impact weight of resource consumption.

[0067] The historical processing difficulty impact weights and resource consumption impact weights can be obtained from the database. For example, the historical processing difficulty impact weights can be obtained by obtaining the historical processing difficulty indicators within the historical preset time period stored in the database, and the historical processing difficulty impact weights corresponding to the historical processing difficulty indicators within the historical preset time period, thereby constructing a historical processing difficulty mapping set, wherein there is a one-to-one or many-to-one correspondence in the mapping set. The historical processing difficulty impact weights can be obtained by inputting the historical processing difficulty data to be used into the historical processing difficulty mapping set. The method for obtaining the resource consumption impact weights is the same as the method for obtaining the historical processing difficulty impact weights, and both can be matched in the corresponding mapping sets.

[0068] Comprehensive emergency assessment indicators can help the platform quickly identify emergency situations (such as excessive resource consumption or significant historical processing difficulties) and initiate appropriate emergency measures. Using these indicators, the platform can prioritize requests with different predicted surgical durations to ensure timely processing. In emergencies, the platform can dynamically adjust resource allocation based on these indicators to ensure critical tasks receive sufficient resources. This allows the platform to optimize system response strategies, reduce emergency response times, and improve overall efficiency.

[0069] Furthermore, based on the preliminary judgment result of data segmentation and the analysis of the data transmission channel effect index, the final data segmentation judgment result is obtained, and corresponding data processing is performed to obtain a feature data packet. The specific steps include: obtaining the data transmission channel effect threshold preset in the medical information platform, and comparing it with the data transmission channel effect index to obtain the data transmission channel quality assessment result, the data transmission channel quality assessment result includes the data transmission channel quality being qualified and the data transmission channel quality being unqualified; based on the preliminary judgment result of data segmentation and the analysis of the data transmission channel effect index, the final data segmentation judgment result is obtained, the final data segmentation judgment result includes data segmentation and data not segmented; if the preliminary judgment result of data segmentation is that preliminary segmentation is not performed and the data transmission channel quality assessment result is that the data transmission channel quality is qualified, then the final data segmentation judgment result is that the data is not segmented, otherwise it is segmented; if the final data segmentation judgment result is that the data is segmented, then the data segmentation standard is obtained by analysis. , and perform data segmentation processing based on the data segmentation standard to obtain a characteristic data packet, the data segmentation standard includes a first data segmentation standard, a second data segmentation standard and a third data segmentation standard; wherein, if the preliminary judgment result of data segmentation is that segmentation is preliminarily performed and the data transmission channel quality assessment result is that the data transmission channel quality is qualified, then the first data segmentation standard is analyzed and the data segmentation processing is performed based on the first data segmentation standard to obtain a characteristic data packet; if the preliminary judgment result of data segmentation is that segmentation is preliminarily performed and the data transmission channel quality assessment result is that the data transmission channel quality is unqualified, then the second data segmentation standard is analyzed and the data segmentation processing is performed based on the second data segmentation standard to obtain a characteristic data packet; if the preliminary judgment result of data segmentation is that segmentation is not preliminarily performed and the data transmission channel quality assessment result is that the data transmission channel quality is unqualified, then the third data segmentation standard is analyzed and the data segmentation processing is performed based on the third data segmentation standard to obtain a characteristic data packet.

[0070] In this embodiment, by obtaining data transmission channel performance indicators (such as network upload speed, bandwidth, CPU utilization, etc.), the data segmentation strategy can be dynamically adjusted based on the current network and resource status. For example, when the network upload speed is low, the data can be segmented into smaller segments to reduce the amount of data transmitted in a single transmission, thereby improving transmission efficiency, ensuring the timely transmission of critical data, and avoiding delays caused by network congestion.

[0071] Data segmentation is based on criteria such as data size and time window, allowing for flexible adjustment of segmentation strategies based on specific needs. For example, for large-scale data, a more granular segmentation approach can be adopted to reduce the complexity of single-shot processing; for structured data, optimized segmentation based on data type can be used to improve processing efficiency.

[0072] It should be noted that if a first data segmentation criterion is obtained through analysis, and data segmentation processing is performed based on the first data segmentation criterion to obtain characteristic data packets, the specific method is as follows: obtaining the first data segmentation criterion, which includes the data size and data time window for data segmentation, and performing data segmentation on the predicted characteristic data based on the first data segmentation criterion. For example, if the first data segmentation criterion is: data size is 100MB, and the data time window is a data block every 5 minutes, then the original data is segmented according to the preset single transmission standard, ensuring that the size of each data packet is close to but does not exceed the maximum carrying capacity of the channel (100MB), and the data time window does not exceed 5 minutes.

[0073] If the second data segmentation criterion is obtained through analysis, and data segmentation processing is performed based on the second data segmentation criterion to obtain characteristic data packets, the specific method is as follows: obtaining the second data segmentation criterion, which includes the data size and data time window for data segmentation, and segmenting the predicted characteristic data based on the second data segmentation criterion. For example, if the second data segmentation criterion includes a data size of 50MB and a data time window of 2-minute data blocks, the original data is segmented according to the preset single transmission standard, ensuring that the size of each data packet is close to but does not exceed the maximum carrying capacity of the channel (50MB), and the data time window does not exceed 2 minutes.

[0074] If the third data segmentation criterion is obtained through analysis, and data segmentation processing is performed based on the third data segmentation criterion to obtain characteristic data packets, the specific method is to obtain the third data segmentation criterion, which includes the data size and data time window for data segmentation, and then segment the predicted characteristic data based on the third data segmentation criterion. For example, if the second data segmentation criterion is: data size 70MB, data block every 3 minutes in the data time window, then the original data will be segmented according to the preset single transmission standard, ensuring that the size of each data packet is close to but does not exceed the maximum carrying capacity of the channel (70MB), and the data time window does not exceed 3 minutes.

[0075] By analyzing resource parameters such as CPU utilization and bandwidth, data segmentation strategies can be dynamically adjusted to avoid resource overload or idleness. For example, when CPU utilization is high, the complexity of data segmentation can be reduced to reduce the computational burden; when bandwidth is sufficient, the amount of data transmitted per transmission can be increased to improve resource utilization. This dynamic adjustment mechanism helps optimize system performance and ensure efficient resource utilization.

[0076] When channel occupancy is high, the UDP protocol can be used for data transmission, sacrificing some reliability in exchange for higher transmission speeds. This ensures timely transmission of predicted data and improves emergency response capabilities. Through data segmentation, large-scale data can be broken down into smaller segments, making it easier for machine learning models to process them efficiently. For example, in a surgical duration prediction model, data segmentation can reduce the amount of data processed at a single time, lowering the model's computational complexity while ensuring data integrity and consistency, helping to improve the model's prediction accuracy and generalization capabilities.

[0077] It should also be noted that the third standard for data segmentation is obtained by performing corresponding data processing to obtain a characteristic data packet. The specific method is: obtain the data transmission channel effect indicator interval preset in the medical information platform and the single data transmission standard corresponding to each data transmission channel effect indicator interval. If the data transmission channel effect indicator is within a certain preset data transmission channel effect indicator interval, then obtain the single data transmission standard corresponding to the interval as the third standard for data segmentation.

[0078] Furthermore, a first data segmentation standard is obtained by analysis, and data segmentation processing is performed based on the first data segmentation standard to obtain a characteristic data packet. The specific steps include: obtaining a comprehensive emergency assessment index based on the historical processing difficulty index and the resource consumption index; obtaining each comprehensive emergency assessment index interval preset in the medical information platform and the single data transmission standard corresponding to each comprehensive emergency assessment index interval, and matching them with the comprehensive emergency assessment index. If the comprehensive emergency assessment index is within a preset comprehensive emergency assessment index interval, the single data transmission standard corresponding to the interval is obtained as the first data segmentation standard; data segmentation processing is performed based on the first data segmentation reference standard to obtain a characteristic data packet; the comprehensive emergency assessment index is used to combine the historical processing difficulty index with the historical processing difficulty impact weight, and then process the result with the resource consumption index and the resource consumption impact weight to obtain a comprehensive emergency assessment index.

[0079] In this embodiment, it should be noted that comprehensive processing is performed based on the processing evaluation efficiency difference to obtain the processing evaluation efficiency deviation. The specific method is: dividing the processing evaluation efficiency difference by the processing evaluation efficiency index threshold to obtain the processing evaluation efficiency deviation.

[0080] Based on the analysis of comprehensive emergency evaluation indicators and data transmission channel effect indicators, the processing evaluation efficiency indicators are obtained. The specific method is as follows: Where BX represents the processing evaluation efficiency index, GX represents the data transmission channel effect index, PZ represents the comprehensive emergency evaluation index, B1 represents the processing evaluation efficiency impact weight, and B2 represents the comprehensive emergency evaluation impact weight.

[0081] The processing evaluation efficiency impact weights and the comprehensive emergency evaluation impact weights can be obtained from the database. For example, the processing evaluation efficiency impact weights can be obtained by obtaining the historical processing evaluation efficiency stored in the database, and the processing evaluation efficiency impact weights corresponding to the historical processing evaluation efficiency, thereby constructing a processing evaluation efficiency mapping set, wherein there is a one-to-one or many-to-one correspondence in the mapping set. The processing evaluation efficiency impact weights can be obtained by inputting the processing evaluation efficiency data to be used into the processing evaluation efficiency mapping set. The method for obtaining the comprehensive emergency evaluation impact weights is the same as the method for obtaining the processing evaluation efficiency impact weights.

[0082] Through data segmentation, the system can break down large-scale data into smaller fragments, reducing the amount of data transmitted at a single time. This helps optimize network bandwidth utilization, significantly improves data transmission efficiency, and ensures that the surgical duration prediction module can obtain the required data in a timely manner. After data segmentation, each data fragment contains metadata (such as fragment ID, data range, storage location, and hash function), which enables flexible management and retrieval of data fragments. For example, when data needs to be reassembled, the fragment ID and storage location can be used to quickly locate and retrieve relevant data fragments, improving data processing flexibility.

[0083] By storing data segments according to predefined storage locations, storage resources can be used more efficiently. For example, data segments can be distributed across different storage locations based on their storage locations, reducing the storage pressure on a single device and improving data access efficiency.

[0084] After data segmentation, different data segments can be processed in parallel. For example, in a surgery duration prediction module, multiple data segments can be analyzed simultaneously, accelerating data processing and improving prediction speed. Using hash functions to verify data segments ensures integrity and consistency during transmission and storage. For example, when data segments are reassembled, hash functions can be used to verify whether the data has been tampered with or damaged, thereby ensuring data reliability.

[0085] Furthermore, a second data segmentation standard is obtained through analysis, and data segmentation processing is performed based on the second data segmentation standard to obtain a characteristic data packet. The specific steps include: obtaining a processing evaluation efficiency indicator based on analysis of a comprehensive emergency evaluation index and a data transmission channel effect index; obtaining a processing evaluation efficiency indicator threshold preset in the medical information platform, and performing difference processing with the processing evaluation efficiency index to obtain a processing evaluation efficiency difference, performing comprehensive processing based on the processing evaluation efficiency difference to obtain a processing evaluation efficiency deviation; obtaining each processing evaluation efficiency deviation interval preset in the medical information platform and a single data transmission standard corresponding to the processing evaluation efficiency deviation interval, and if the processing evaluation efficiency deviation is within a certain preset processing evaluation efficiency deviation interval, obtaining the single data transmission standard corresponding to the interval as the second data segmentation standard; obtaining the second data segmentation standard based on the analysis, and performing data segmentation processing based on the second data segmentation standard to obtain a characteristic data packet; the processing evaluation efficiency indicator is used to characterize the comprehensive complexity of data processing by the comprehensive emergency evaluation index and the data transmission channel effect index.

[0086] In this embodiment, when the emergency judgment result of the duration prediction is "duration prediction is urgent", the UDP protocol is used to transmit data. The connectionless characteristics of the UDP protocol enable it to have lower latency and higher transmission speed, and can quickly transmit data to the operation duration prediction module, ensuring that key data is processed in time and improving emergency response capabilities. When the emergency judgment result of the duration prediction is "duration prediction is not urgent", the TCP protocol is used to transmit data. The reliability and connection-oriented characteristics of the TCP protocol can ensure the integrity and sequence of the data, and avoid data loss or errors.

[0087] Dynamically selecting a transmission protocol based on the duration prediction emergency determination results optimizes resource utilization. For example, in emergency situations, UDP is prioritized to reduce resource usage and ensure rapid transmission of critical data. In non-emergency situations, TCP is used to fully utilize system resources and ensure reliable data transmission. In emergency situations, UDP can be used to transmit data, reducing the amount of data transmitted and further improving transmission efficiency. In non-emergency situations, TCP can be used to transmit predicted feature data, ensuring data integrity and accuracy.

[0088] Furthermore, a corresponding data transmission protocol is selected based on the emergency judgment result of the duration prediction, thereby transmitting the feature data packet to the operation duration prediction module. The specific steps include: analyzing the emergency judgment result of the duration prediction to obtain the corresponding data transmission protocol, and the data transmission protocol includes the UDP protocol and the TCP protocol; if the emergency judgment result of the duration prediction is that the duration prediction is urgent, the UDP protocol is used to upload the predicted feature data to the operation duration prediction module; if the emergency judgment result of the duration prediction is that the duration prediction is not urgent, the TCP protocol is used to upload the predicted feature data to the operation duration prediction module.

[0089] In this embodiment, after the predicted feature data is uploaded to the operation duration prediction module, the operation duration prediction module receives the feature data packet, and uses the machine learning algorithm to analyze to obtain the predicted value of the operation duration, and performs automatic scheduling prompts. According to the predicted value of the operation duration, the day surgery schedule can be freely set to ensure the reasonable implementation of the day surgery schedule. By predicting the operation duration, a basis is provided for the subsequent arrangement of the operation duration and the scheduling of medical staff, avoiding the problem of inaccurate operation duration prediction caused by the traditional prediction of the operation duration based on the doctor's personal experience. This scientific and refined operation duration prediction facilitates more reasonable arrangements for day surgeries, reduces the waste of operating room resources due to inaccurate duration prediction, and avoids the problem of medical staff not being able to get effective rest due to inaccurate duration prediction.

[0090] To sum up, this embodiment obtains the platform historical processing data and medical information platform resource parameters of the same surgical type as the predicted surgical type, and comprehensively analyzes to obtain the emergency judgment result of the duration prediction, so as to dynamically evaluate the urgency of the duration prediction and intelligently adjust the data processing process according to the urgency of the duration prediction, thereby achieving accurate and timely prediction of the surgical duration, and effectively solving the problem in the existing technology that it is impossible to flexibly adjust resource allocation according to the urgency of the duration prediction, resulting in slow response to the surgical duration prediction.

[0091] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0092] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for predicting and scheduling surgical duration based on machine learning, characterized in that: The following steps are involved: When the medical information platform receives a request for surgery duration prediction, it obtains the platform's historical processing data and analyzes it to obtain historical processing difficulty indicators; Obtaining resource parameters of the medical information platform within a first preset time period, analyzing to obtain a resource consumption index, and obtaining a duration prediction emergency determination result based on a comprehensive analysis of a historical processing difficulty index and a resource consumption index, wherein the duration prediction emergency determination result includes a duration prediction emergency and a duration prediction non-urgent; The medical information platform automatically retrieves the predicted feature data and analyzes the emergency judgment results based on the duration prediction to obtain the preliminary judgment results of data segmentation; Obtain data transmission channel effect parameters, analyze and obtain data transmission channel effect indicators, obtain final data segmentation judgment results based on the preliminary judgment results of data segmentation and the data transmission channel effect indicators, and perform corresponding data processing to obtain feature data packets; Selecting a corresponding data transmission protocol based on the duration prediction emergency determination result, thereby transmitting the feature data packet to the surgery duration prediction module; The surgery duration prediction module receives feature data packets and uses machine learning algorithms to analyze and obtain the predicted surgery duration value, and then automatically schedules the patient. The historical processing difficulty indicator is obtained by comparing the historical average data loading time, the historical average I / O waiting time, and the historical average number of input and output operations per second with the historical maximum data loading time, the historical maximum I / O waiting time, and the historical maximum number of input and output operations per second, respectively, and combining them with the historical average CPU usage and the historical average GPU memory occupancy, and then introducing influence weights; The resource consumption index is used to compare the average number of data queries per second with the ideal value of the average number of data queries per second, and to compare the average response time, the predicted failure rate, the number of user accesses, and the number of concurrent requests with the ideal value of the average response time, the critical value of the predicted failure rate, the ideal value of the number of user accesses, and the ideal value of the number of concurrent requests, respectively, and introduce the corresponding influence weights for fusion processing to obtain the resource consumption index; The data transmission channel effect index is used to introduce influence weights after comparing the average network upload speed with the ideal network upload speed, comparing the average bandwidth with the ideal bandwidth, and comparing the channel bit error rate with the channel bit error rate limit, and combining the average CPU utilization and average channel occupancy with the introduced influence weights to obtain the data transmission channel effect index.

2. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: When the medical information platform receives the surgery duration prediction request, it obtains the platform's historical processing data and analyzes it to obtain the historical processing difficulty index. The specific steps include: When the medical information platform receives a request for surgery duration prediction, it obtains the predicted surgery type and collects historical data of surgeries processed by the medical information platform that are of the same type as the predicted surgery type. This data is recorded as the platform's historical processing data, which includes the historical average data loading time, the historical average CPU usage, the historical average I / O waiting time, the historical average number of input and output operations per second, and the historical average GPU memory occupancy rate. Obtaining a preset low-performance verification set in a medical database, wherein the low-performance verification set includes a historical maximum data loading time, a historical maximum I / O waiting time, and a historical maximum number of input and output operations per second; The historical processing difficulty index is obtained based on the analysis of the platform's historical processing data and the low-performance validation set.

3. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: The steps of obtaining the resource parameters of the medical information platform within the first preset time period and analyzing to obtain the resource consumption index include: Obtaining resource parameters of the medical information platform within a first preset time period, wherein the resource parameters of the medical information platform include the number of surgery duration prediction requests, the average number of data queries per second, the average response time, the prediction failure rate, the number of user accesses, and the number of concurrent requests; Obtain the ideal set of platform resources preset in the medical database and analyze it with the resource parameters of the medical information platform to obtain resource consumption indicators; The ideal set of platform resources preset in the medical database includes the ideal value of the number of requests for surgery duration prediction, the ideal value of the average number of data queries per second, the ideal value of the average response time, the critical value of the prediction failure rate, the ideal value of the number of user accesses and the ideal value of the number of concurrent requests.

4. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: The step of obtaining the emergency judgment result of duration prediction based on comprehensive analysis of historical processing difficulty indicators and resource consumption indicators includes: Obtain the historical processing difficulty lower limit and resource consumption indicator lower limit preset in the medical information platform; Compare the historical processing difficulty index with the historical processing difficulty lower limit value, and compare the resource consumption index with the resource consumption index lower limit value to obtain the duration prediction emergency judgment result; If the historical processing difficulty index is above the historical processing difficulty lower limit and the resource consumption index is above the resource consumption index lower limit, the duration forecast urgency determination result is duration forecast urgent; otherwise, the duration forecast is not urgent. The duration prediction urgency determination result includes the duration prediction being urgent and the duration prediction being not urgent.

5. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: The analysis of the emergency judgment result based on the duration prediction obtains the preliminary judgment result of data segmentation, and the specific steps include: Obtain the duration prediction emergency judgment result. If the duration prediction emergency judgment result is that the duration prediction is urgent, the data segmentation preliminary judgment result is to preliminarily execute segmentation. If the duration prediction emergency judgment result is that the duration prediction is not urgent, the data segmentation preliminary judgment result is to preliminarily not execute segmentation.

6. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: The steps of obtaining the data transmission channel effect parameter and analyzing to obtain the data transmission channel effect index include: Acquire data transmission channel effect parameters, wherein the data transmission channel effect parameters include an average network upload speed, an average bandwidth, an average CPU utilization, an average channel occupancy rate, and a channel bit error rate within a second preset time period; Obtain the ideal channel effect data set preset in the medical information platform, and analyze it with the data transmission channel effect parameters to obtain the data transmission channel effect index; The ideal channel effect data set includes an ideal network upload speed, an ideal bandwidth, and a channel bit error rate limit value.

7. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: The final data segmentation judgment result is obtained based on the preliminary judgment result of data segmentation and the data transmission channel effect index analysis, and the corresponding data processing is performed to obtain the feature data packet. The specific steps include: Obtaining a data transmission channel effect threshold preset in the medical information platform and comparing it with the data transmission channel effect index to obtain a data transmission channel quality assessment result, wherein the data transmission channel quality assessment result includes a data transmission channel quality that is qualified and a data transmission channel quality that is unqualified; Based on the preliminary data segmentation judgment result and the data transmission channel effect index analysis, the final data segmentation judgment result is obtained, and the final data segmentation judgment result includes data segmentation and data non-segmentation; If the preliminary judgment result of data segmentation is that the data segmentation is not to be performed and the data transmission channel quality assessment result is that the data transmission channel quality is qualified, then the final judgment result of data segmentation is that the data is not segmented, otherwise the data is segmented; If the final data segmentation judgment result is data segmentation, the data segmentation criteria are obtained through analysis, and data segmentation processing is performed based on the data segmentation criteria to obtain a feature data packet, wherein the data segmentation criteria include a first data segmentation criteria, a second data segmentation criteria, and a third data segmentation criteria; If the preliminary determination result of data segmentation is that segmentation is preliminarily performed and the data transmission channel quality assessment result is that the data transmission channel quality is qualified, a first data segmentation standard is obtained by analysis, and data segmentation processing is performed based on the first data segmentation standard to obtain a characteristic data packet; If the preliminary determination result of data segmentation is that segmentation is performed preliminarily and the data transmission channel quality assessment result is that the data transmission channel quality is unqualified, a second data segmentation standard is obtained by analysis, and data segmentation processing is performed based on the second data segmentation standard to obtain a characteristic data packet; If the preliminary judgment result of data segmentation is that segmentation is not performed and the data transmission channel quality assessment result is that the data transmission channel quality is unqualified, the third data segmentation standard is analyzed and data segmentation processing is performed based on the third data segmentation standard to obtain a feature data packet.

8. The method for predicting and scheduling surgical duration based on machine learning according to claim 7, wherein: The analysis obtains a first data segmentation standard, and performs data segmentation processing based on the first data segmentation standard to obtain a feature data packet. The specific steps include: Based on the analysis of historical processing difficulty indicators and resource consumption indicators, a comprehensive emergency assessment index is obtained; Obtain each preset comprehensive emergency assessment indicator interval in the medical information platform and the single data transmission standard corresponding to each comprehensive emergency assessment indicator interval, and match them with the comprehensive emergency assessment indicator. If the comprehensive emergency assessment indicator is within a preset comprehensive emergency assessment indicator interval, obtain the single data transmission standard corresponding to the interval as the first data segmentation standard; Performing data segmentation processing based on a first reference standard for data segmentation to obtain a feature data packet; The comprehensive emergency assessment index is used to combine the historical processing difficulty index with the historical processing difficulty impact weight and then process the result of combining it with the resource consumption index and the resource consumption impact weight to obtain the comprehensive emergency assessment index.

9. The method for predicting and scheduling surgical duration based on machine learning according to claim 8, wherein: The analysis obtains a second data segmentation standard, and performs data segmentation processing based on the second data segmentation standard to obtain a feature data packet. The specific steps include: Based on the analysis of comprehensive emergency evaluation indicators and data transmission channel effect indicators, the processing evaluation efficiency indicators are obtained; Obtaining a treatment evaluation effectiveness indicator threshold preset in the medical information platform, performing difference processing with the treatment evaluation effectiveness indicator to obtain a treatment evaluation effectiveness difference, and performing comprehensive processing based on the treatment evaluation effectiveness difference to obtain a treatment evaluation effectiveness deviation; Obtaining each treatment evaluation efficiency deviation interval preset in the medical information platform and the single data transmission standard corresponding to the treatment evaluation efficiency deviation interval; if the treatment evaluation efficiency deviation is within a certain preset treatment evaluation efficiency deviation interval, obtaining the single data transmission standard corresponding to the interval as the second data segmentation standard; A second data segmentation standard is obtained based on the analysis, and data segmentation processing is performed based on the second data segmentation standard to obtain a feature data packet; The processing evaluation efficiency index is used to characterize the comprehensive complexity of data processing by the comprehensive emergency evaluation index and the data transmission channel effect index.

10. The method for predicting and scheduling surgical duration based on machine learning according to claim 1, wherein: The method of selecting a corresponding data transmission protocol based on the emergency judgment result of the duration prediction, thereby transmitting the feature data packet to the surgery duration prediction module, specifically includes the following steps: Analyze the emergency judgment result based on the duration prediction to obtain the corresponding data transmission protocol, which includes the UDP protocol and the TCP protocol; If the duration prediction urgency judgment result is that the duration prediction is urgent, the UDP protocol is used to upload the predicted feature data to the operation duration prediction module. If the duration prediction urgency judgment result is that the duration prediction is not urgent, the TCP protocol is used to upload the predicted feature data to the operation duration prediction module.

Images