Orthopedic treatment data analysis method and system

Abstract

The invention relates to the technical field of medical data analysis, in particular to an orthopedic treatment data analysis method and system, and the method comprises the following steps: analyzing demand data based on operation data, evaluating heterogeneous computing resources, enabling the processing capability and the response time to correspond to the analysis demands of operation time and rehabilitation progress data, and obtaining an analysis result; and determining the dependency degree of multiple tasks on the computing resources, and generating a resource demand matching table. According to the method, the heterogeneous computing resources are evaluated to match operation time and rehabilitation progress data requirements, the resources are accurately configured, each task can be matched with the optimal computing resource, the resource utilization rate and the data processing efficiency are improved, the task execution sequence and the resource utilization are dynamically optimized, resource vacancy and task delay are reduced, and the operation efficiency is improved. The response speed and accuracy of data processing are improved, the performance of differentiated resources is monitored and analyzed in real time, key resources are effectively identified and reconfigured, the flexibility and expandability of data processing are enhanced, and the high efficiency of orthopedic data analysis is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data analysis, and in particular to an orthopedic treatment data analysis method and system. Background Art

[0002] The field of medical data analysis technology involves the use of advanced data processing technology, statistical methods and machine learning algorithms to collect, process and analyze medical and health data. The core goal of this field is to extract valuable information from multiple data sources such as clinical trials, patient health records, medical imaging and biomarkers to optimize disease diagnosis, treatment and prevention strategies. This technology not only helps to improve treatment effects and patient safety, but also supports the decision-making process of the medical system and promotes the development of personalized medicine and precision treatment.

[0003] Among them, the orthopedic treatment data analysis method mainly refers to the use of data analysis technology to process and analyze various types of data collected in orthopedic treatment, including surgical data, rehabilitation process data, patient pain scores, and motor function recovery records. The purpose of this method is to optimize treatment plans through data-driven insights, predict treatment effects, and evaluate the efficiency and safety of different treatment methods, thereby providing doctors and patients with more accurate treatment options. In this way, orthopedic surgeons can better understand the disease process and treatment response, thereby improving patients' treatment effects and quality of life.

[0004] When processing large amounts of medical and health data, existing orthopedic treatment data analysis methods waste or lack computing resources due to improper or fixed resource allocation, which affects the efficiency and effectiveness of data processing. Especially when facing highly variable medical data, fixed resource allocation strategies often cannot flexibly respond to fluctuations in data processing needs, resulting in slow processing speeds and long response times. Existing technologies lack effective performance monitoring and bottleneck analysis mechanisms, making it difficult to adjust resource allocation in real time, which is particularly evident when processing orthopedic treatment data that requires high real-time performance. For example, during peak hours, data processing tasks may be queued due to insufficient resources, delaying the processing and analysis of critical data. This delay leads to adverse consequences in clinical decision-making, such as delays or errors in treatment plans, limiting the potential of medical data analysis. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an orthopedic treatment data analysis method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an orthopedic treatment data analysis method, comprising the following steps:

[0007] S1: Based on the surgical data analysis demand data, evaluate heterogeneous computing resources, match the processing capacity and response time with the analysis requirements of surgical time and rehabilitation progress data, determine the degree of dependence of multiple tasks on computing resources, and generate a resource demand matching table;

[0008] S2: Determine the optimal computing resources for each task according to the resource demand matching table, generate a resource allocation execution plan, implement the resource allocation execution plan, allocate the task to the specified computing resource, and obtain the resource allocation execution result;

[0009] S3: According to the resource allocation execution result, the tasks are scheduled, the task execution order and resource utilization are dynamically optimized, resource idleness and task delay are reduced, task scheduling optimization output is obtained, and according to the task scheduling optimization output, the resource utilization strategy is adjusted to generate resource scheduling optimization results;

[0010] S4: Based on the resource scheduling optimization results, evaluate the computing resource performance for orthopedic treatment data analysis, monitor the performance of differentiated resources in real-time processing of orthopedic data, record performance data, generate performance monitoring records, analyze the performance monitoring records, identify performance bottlenecks in processing orthopedic data, reconfigure resources in a targeted manner, and generate orthopedic treatment data analysis efficiency enhancement strategies.

[0011] As a further solution of the present invention, the step of obtaining the resource demand matching table is specifically as follows:

[0012] S111: Analyze demand data based on surgical data, collect surgical time and rehabilitation progress data, analyze the relationship between heterogeneous computing resources, and use the formula:

[0013]

[0014] Calculate the fitness of each resource and get a preliminary resource fitness list, where Ra i represents the fitness of the i-th computing resource, S i is the processing capacity of the ith resource, C i is the response time, D i is the surgical data correlation, α and β are the weights of processing capability and response time, and γ and δ are used for normalization processing;

[0015] S112: Optimize resource allocation according to the preliminary resource fitness list, using the formula:

[0016]

[0017] Calculate the fitness score of the resource and obtain the optimized resource fitness list, where Pa i is the fitness score of the i-th resource, Rai represents the fitness of the i-th computing resource, D i is the data point association, κ is the fitness amplification parameter, and Θ is the sum of all resource fitnesses;

[0018] S113: Use the optimized resource fitness list to match the optimal computing resources for each surgical task, using the formula:

[0019]

[0020] Establish a resource demand matching table, where Ma represents the selected optimal resource, Pa i is the fitness score of the ith resource, and max(P) is the highest value among the resource scores.

[0021] As a further solution of the present invention, the step of obtaining the resource allocation execution result is specifically:

[0022] S211: Select the optimal computing resource for each task from the resource requirement matching table using the formula:

[0023]

[0024] By enhancing the impact of the score and adjusting the bias, we can optimize resource selection and obtain the optimal computing resource list, where R b represents the optimal computing resources allocated to each task, σ is the amplification parameter, and P i is the computational resource fitness score, max(P) is the maximum value in the resource fitness score, and ∈ is a constant;

[0025] S212: Based on the optimal computing resource list, implement a resource allocation plan, allocate tasks according to the determined resources, and use the formula:

[0026]

[0027] Referring to the exponential enhancement of resources and reflecting the nonlinear impact of resource capabilities, a mapping table of task resources is obtained, where E b For task i in resource R b The execution plan on x ij is a binary decision variable, λ is the resource capacity adjustment coefficient, T is the task set, R b represents the optimal computing resources to be allocated to each task;

[0028] S213: Based on the mapping table of the task resources, by formula:

[0029]

[0030] Use adjustment factors and constant bias to optimize efficiency trials and establish resource allocation execution results, where O b represents the task execution efficiency of computing resources, E b For task i in resource R b The execution plan on , max(E) is the execution amount in the execution plan, μ is the efficiency adjustment coefficient, φ is the constant bias, and R is the resource set.

[0031] As a further solution of the present invention, the step of obtaining the task scheduling optimization output is specifically as follows:

[0032] S311: According to the resource allocation execution result, the current task load of multiple resources is evaluated using the formula:

[0033]

[0034] The influence of the processing time and urgency of the weighted reference task is calculated to obtain the resource load table after adjusting the total load of each resource, where L c represents the adjusted total load of resource i, α and β are the weights of the nonlinear effects of adjustment time and urgency, t ij is the processing time of task j on resource i, u j is the urgency of task j, T is the set of tasks;

[0035] S312: Based on the resource load table, perform task optimization scheduling using the formula:

[0036]

[0037] By optimizing the task execution order by referring to the inverse power of resource load, a task optimization scheduling scheme is generated, where S c is the scheduling optimization score of resource i, γ is the priority adjustment coefficient, and p j is the priority of task j, L c represents the adjusted total load of resource i, N is the total number of tasks;

[0038] S313: Integrate the resource load table and the task optimization scheduling plan, using the formula:

[0039]

[0040] Adjust the scheduling score of each resource, optimize the overall task execution efficiency and resource utilization, and obtain the task scheduling optimization output, where O out represents the task scheduling optimization output, S c is the scheduling optimization score for resource i, θ is the adjustment coefficient of the scheduling score, κ is a constant bias, φ is a small positive number to prevent the denominator from being zero, and R is the resource set.

[0041] As a further solution of the present invention, the step of obtaining the resource scheduling optimization result is specifically:

[0042] S321: Based on the task scheduling optimization output, by analyzing the execution time and resource requirements of multiple tasks, the total occupied time of each resource under the current task scheduling is calculated by the formula:

[0043]

[0044] Referring to the nonlinear relationship between time and resource requirements, we get a list of task resource occupancy time, where Q di represents the adjusted total occupied time of the i-th resource, t j is the execution time of the jth task, r ij represents the adjustment coefficient of the time occupied by the i-th resource in the j-th task;

[0045] S322: According to the task resource occupation time list, readjust the resources and apply the formula:

[0046]

[0047] Evaluate the optimal utilization of resources and generate a resource utilization adjustment list, where U di is the adjusted optimal utilization of the i-th resource, s k is the demand urgency of the k-th resource type, n k is the total demand for the kth resource type, Q di represents the adjusted total occupied time of the i-th resource;

[0048] S323: Utilize the resource utilization adjustment list to optimize the resource scheduling strategy, using the formula:

[0049]

[0050] By accumulating resource utilization, we can obtain the resource scheduling optimization result, where R d represents the resource scheduling optimization result, U di The adjusted optimal utilization of the i-th resource, and p is the total number of resources.

[0051] As a further solution of the present invention, the step of obtaining the performance monitoring record is specifically as follows:

[0052] S411: Based on the performance monitoring record, for the orthopedic treatment data, a performance benchmark test is performed on the computing resources using the formula:

[0053]

[0054] Evaluate the performance benchmark of the resource and generate a benchmark performance score list, where Pf i represents the performance score of computing resources, S i Represents the processing frequency of resources, B i is the bandwidth of the resource, σ and ρ are weight factors, and λ, ω, and δ are adjustment parameters;

[0055] S412: According to the benchmark performance score list, monitor the real-time performance of the resource when processing orthopedic data, using the formula:

[0056]

[0057] Calculate real-time performance indicators and obtain real-time performance monitoring data, where Rf t is the performance index at time t, Pf i represents the performance score of computing resources, L t is the load factor at time t, κ, θ, η are adjustment parameters;

[0058] S413: Using the real-time performance monitoring data, adopt the formula:

[0059]

[0060] Integrate performance data and establish performance monitoring records, where Mf represents performance monitoring records and Rf represents t is the performance index at time t, and T is the monitoring time range.

[0061] As a further solution of the present invention, the steps for obtaining the orthopedic treatment data analysis efficiency enhancement strategy are specifically as follows:

[0062] S421: Analyze the performance monitoring records and identify performance bottlenecks in data processing using the formula:

[0063]

[0064] Calculate performance bottleneck indicators and generate performance bottleneck analysis results, where Bh i Represents the performance bottleneck indicator, R i represents the real-time performance index of the resource, γ represents the impact coefficient, ∈ represents a small positive number with a non-zero divisor, and δ represents the stability parameter;

[0065] S422: Optimize resource allocation according to the performance bottleneck analysis result, using the formula:

[0066]

[0067] Generate a new resource configuration, where Ch new represents the new resource configuration, Bh irepresents the performance bottleneck indicator, α represents the optimization coefficient, and L eff represents the expected efficiency improvement ratio, β represents the parameter for regulating efficiency growth, and ξ represents a small positive number;

[0068] S423: Integrate the new resource configuration using the formula:

[0069]

[0070] By normalizing parameters and adjusting coefficients to enhance the rationality of the strategy, a strategy to enhance the efficiency of orthopedic treatment data analysis is established, where S eff represents the efficiency enhancement strategy, Ch new represents the new resource configuration, ζ represents the normalization parameter, and ψ represents the adjustment coefficient.

[0071] An orthopedic treatment data analysis system, the orthopedic treatment data analysis system is used to execute the orthopedic treatment data analysis method, the system comprising:

[0072] The resource evaluation module analyzes demand data based on surgical data, compares the processing speed and response time of heterogeneous computing resources, evaluates the processing adaptability of resources to differentiated data tasks, analyzes the matching degree between resource performance and demand, and constructs a resource characteristic analysis table;

[0073] The resource allocation module analyzes the load capacity of computing resources based on the resource characteristic analysis table, allocates resource data-intensive tasks through resource performance scoring, and forms a resource allocation plan;

[0074] The task scheduling module uses the resource configuration scheme to optimize the execution sequence of tasks, adjust resource allocation, reduce execution delays and resource idle time through dynamic scheduling, and obtain scheduling strategy details;

[0075] The performance monitoring module monitors the real-time performance of computing resources when processing surgical data based on the scheduling strategy details, records the processing time and resource consumption of multiple tasks, analyzes performance data and identifies inefficient links, and generates performance monitoring results;

[0076] The efficiency optimization module evaluates the effect of resource allocation based on the performance monitoring results, reallocates computing load according to the discovered bottlenecks, optimizes data flow and processing strategies, and establishes an efficiency enhancement strategy for orthopedic treatment data analysis.

[0077] Compared with the prior art, the advantages and positive effects of the present invention are:

[0078] In the present invention, by evaluating the correspondence between heterogeneous computing resources and the analysis requirements of surgical time and rehabilitation progress data, the key requirements and resource allocation of data processing are accurately located. The formulation of this resource requirement matching table allows each task to match the optimal computing resources, thereby significantly improving resource utilization and data processing efficiency in actual operation. By dynamically optimizing the task execution order and resource utilization, resource idleness and task delays are significantly reduced, thereby improving the response speed and accuracy of overall data processing. In particular, in terms of performance monitoring and bottleneck analysis, by real-time monitoring and analysis of the performance of differentiated resources, key resources for processing orthopedic data can be effectively identified and reconfigured, which not only improves data processing efficiency, but also enhances the flexibility and scalability of the method. This continuous optimization of resource allocation and scheduling ensures the efficiency of orthopedic treatment data analysis, enables the medical team to obtain key data faster, and supports the accuracy of treatment decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0080] Figure 2 It is a flow chart of the resource demand matching table in the present invention;

[0081] Figure 3 A flow chart showing the resource allocation execution result in the present invention;

[0082] Figure 4 A flowchart of the task scheduling optimization output in the present invention;

[0083] Figure 5 It is a flow chart of the resource scheduling optimization result in the present invention;

[0084] Figure 6 A flow chart of the performance monitoring record in the present invention;

[0085] Figure 7 The figure is a flow chart of the orthopedic treatment data analysis efficiency enhancement strategy in the present invention. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0087] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0088] Example

[0089] See also Figure 1 The present invention provides a technical solution: an orthopedic treatment data analysis method, comprising the following steps:

[0090] S1: Based on the surgical data analysis demand data, evaluate heterogeneous computing resources, match the processing capacity and response time with the analysis requirements of surgical time and rehabilitation progress data, determine the degree of dependence of multiple tasks on computing resources, and generate a resource demand matching table;

[0091] S2: According to the resource demand matching table, determine the optimal computing resources for each task, generate a resource allocation execution plan, implement the resource allocation execution plan, allocate the task to the specified computing resources, and obtain the resource allocation execution result;

[0092] S3: Schedule tasks according to the resource allocation execution results, dynamically optimize the task execution order and resource utilization, reduce resource idleness and task delays, obtain task scheduling optimization output, adjust resource utilization strategies according to the task scheduling optimization output, and generate resource scheduling optimization results;

[0093] S4: Based on the resource scheduling optimization results, evaluate the computing resource performance for orthopedic treatment data analysis, monitor the performance of differentiated resources in real-time processing of orthopedic data, record performance data, generate performance monitoring records, analyze performance monitoring records, identify performance bottlenecks in processing orthopedic data, reconfigure resources in a targeted manner, and generate orthopedic treatment data analysis efficiency enhancement strategies.

[0094] The resource demand matching table includes processing power requirements, storage space requirements, and network bandwidth requirements. The resource allocation execution results include allocated computing resources, allocated storage resources, and allocated network resources. The task scheduling optimization output includes a computing task list, a storage task list, and a network task list. The resource scheduling optimization results include optimized computing resource configuration, optimized storage resource configuration, and optimized network resource configuration. Performance monitoring records include computing performance logs, storage performance logs, and network performance logs. The orthopedic treatment data analysis efficiency enhancement strategy includes computing efficiency improvement measures, storage efficiency improvement measures, and network efficiency improvement measures.

[0095] See also Figure 2 , the specific steps for obtaining the resource demand matching table are:

[0096] S111: Analyze demand data based on surgical data, collect surgical time and rehabilitation progress data, analyze the relationship between heterogeneous computing resources, and use the formula:

[0097]

[0098] Calculate the fitness of each resource and get a preliminary resource fitness list, where Ra i represents the fitness of the i-th computing resource, S i is the processing capacity of the ith resource, C i is the response time, D i is the surgical data correlation, α and β are the weights of processing capability and response time, and γ and δ are used for normalization processing;

[0099] S112: Optimize resource allocation based on the preliminary resource fitness list using the formula:

[0100]

[0101] Calculate the fitness score of the resource and obtain the optimized resource fitness list, where Pa i is the fitness score of the i-th resource, Ra i represents the fitness of the i-th computing resource, D i is the data point association, κ is the fitness amplification parameter, and Θ is the sum of all resource fitnesses;

[0102] S113: Use the optimized resource fitness list to match the optimal computing resources for each surgical task, using the formula:

[0103]

[0104] Establish a resource demand matching table, where Ma represents the selected optimal resource, Pa iis the fitness score of the ith resource, and max(P) is the highest value among the resource scores.

[0105] The fitness formula of the i-th computing resource is:

[0106]

[0107] Ra i : The fitness of the i-th computing resource;

[0108] S i : The processing capacity of the i-th resource;

[0109] C i : Response time;

[0110] D i : correlation of surgical data;

[0111] α, β: weights of processing power and response time;

[0112] γ, δ: parameters used for normalization processing;

[0113] Assume parameter values: α = 0.5, β = 0.3, γ = 0.7, δ = 1, S i =100, C i =25, D i =50;

[0114] Calculate the processing power squared and multiply the weight:

[0115]

[0116] Calculate the square root of the response time multiplied by the weight:

[0117]

[0118] Calculate the logarithm of the association of surgical data:

[0119] γ·log(D i +1)=0.7·log(51)≈0.7·1.71=1.197

[0120] Calculate the normalization factor:

[0121] Y·log(D i +1)+δ=1.197+1=2.197

[0122] Calculate the final fitness:

[0123]

[0124] Final fitness Ra i≈2277.20 represents the fitness score of the i-th computing resource under given parameters, which is used to compare the adaptability of different computing resources.

[0125] The fitness formula of the i-th computing resource is:

[0126]

[0127] Assumed parameter values: κ = 0.1, Ra i =2277.20, D i =50, Θ=500 (assuming the sum of all fitness scores);

[0128] Calculation of κ·Ra i =0.1·2277.20=227.72;

[0129] Calculate the exponential function: e 227.72 (Note: This value is very large and is usually scaled in practical applications);

[0130] Compute the square root of a logarithm:

[0131] Calculate the final fitness score: (Due to e 227.72 Too large, here we use scaling processing);

[0132] The result Pa i Represents the resource fitness score after exponential and logarithmic processing, which is used to determine the priority of resource allocation. Since the exponential value may be very large in actual calculation, further processing or scaling is usually required.

[0133] The optimal resource formula selected is:

[0134]

[0135] Assumed parameter value: Pa i =e 227.72 1.308, max(P) = e 227.72 1.308 (assuming this resource has the highest adaptability);

[0136] Calculate the ratio:

[0137] Here, M=1 indicates that the selected resource has the highest fitness score and is the best choice of computing resource.

[0138] See also Figure 3 , the specific steps for obtaining the resource allocation execution results are:

[0139] S211: Select the optimal computing resource for each task from the resource requirement matching table using the formula:

[0140]

[0141] By enhancing the impact of the score and adjusting the bias, we can optimize resource selection and obtain the optimal computing resource list, where R b represents the optimal computing resources allocated to each task, σ is the amplification parameter, and P i is the computational resource fitness score, max(P) is the maximum value in the resource fitness score, and ∈ is a constant;

[0142] S212: Based on the optimal computing resource list, implement the resource allocation plan and allocate tasks according to the determined resources using the formula:

[0143]

[0144] Referring to the exponential enhancement of resources and reflecting the nonlinear impact of resource capabilities, a mapping table of task resources is obtained, where E b For task i in resource R b The execution plan on x ij is a binary decision variable, λ is the resource capacity adjustment coefficient, T is the task set, R b represents the optimal computing resources to be allocated to each task;

[0145] S213: Based on the task resource mapping table, through the formula:

[0146]

[0147] Use adjustment factors and constant bias to optimize efficiency trials and establish resource allocation execution results, where O b represents the task execution efficiency of computing resources, E b For task i in resource R b The execution plan on , max(E) is the execution amount in the execution plan, μ is the efficiency adjustment coefficient, φ is the constant bias, and R is the resource set.

[0148] The optimal computing resource formula for each task is:

[0149]

[0150] Assumed parameter values:

[0151] σ = 1.2: amplification factor, enhancing the impact of the score;

[0152] P i : The fitness score of resource i, assuming P1 = 85, P2 = 95, P3 = 75;

[0153] max(P): maximum fitness score, which is 95;

[0154] ∈=0.1: small constant used to prevent division by zero error;

[0155] Calculate the score for each resource:

[0156] For R1:

[0157] For R2:

[0158] For R3:

[0159] Select the resource with the highest score, i.e. R2;

[0160] R2 is the optimal computing resource because it has the highest weight-adjusted score.

[0161] Task i in resource R b The execution plan formula on:

[0162]

[0163] Assumed parameter values:

[0164] λ=0.5: resource capacity adjustment coefficient;

[0165] R b : Optimal resources, using R2 value 95;

[0166] T = {1, 2, 3}: three tasks;

[0167] x ij :Assume that all tasks are assigned to R b , that is, x 21 =1,x 22 =1,x 23 =1;

[0168] Calculate the sum of execution plans:

[0169] E b =(1 0.5 95 1.5 +1 0.5 95 1.5 +1 0.5 95 1.5 )≈3·0.5·925≈1387.5

[0170] The total execution plan score is 1387.5, which means R b The collective efficiency of the three tasks performed on .

[0171] The formula for task execution efficiency of computing resources is:

[0172]

[0173] Assumed parameter values:

[0174] μ=0.8:efficiency adjustment coefficient;

[0175] E b : The result obtained from the previous step is 1387.5;

[0176] max(E): Assume the maximum execution amount is 1500;

[0177] φ=10:constant bias;

[0178] Computational efficiency:

[0179]

[0180] O b ≈0.735, this value represents the task execution efficiency of computing resources and its relative efficiency among all execution plans.

[0181] See also Figure 4 ,The specific steps for obtaining the task scheduling optimization output are:

[0182] S311: According to the resource allocation execution result, the current task load of multiple resources is evaluated using the formula:

[0183]

[0184] The influence of the processing time and urgency of the weighted reference task is calculated to obtain the resource load table after adjusting the total load of each resource, where L c represents the adjusted total load of resource i, α and β are the weights of the nonlinear effects of adjustment time and urgency, t ij is the processing time of task j on resource i, u j is the urgency of task j, T is the set of tasks;

[0185] S312: Based on the resource load table, perform task optimization scheduling using the formula:

[0186]

[0187] By optimizing the task execution order by referring to the inverse power of resource load, a task optimization scheduling scheme is generated, where S c is the scheduling optimization score of resource i, γ is the priority adjustment coefficient, and p j is the priority of task j, L c represents the adjusted total load of resource i, N is the total number of tasks;

[0188] S313: Integrate the resource load table and the task optimization scheduling plan, using the formula:

[0189]

[0190] Adjust the scheduling score of each resource, optimize the overall task execution efficiency and resource utilization, and obtain the task scheduling optimization output, where O out represents the task scheduling optimization output, S c is the scheduling optimization score for resource i, θ is the adjustment coefficient of the scheduling score, κ is a constant bias, φ is a small positive number to prevent the denominator from being zero, and R is the resource set.

[0191] The adjusted total load formula for resource i is:

[0192]

[0193] Assumed values:

[0194] α=0.5: time weight coefficient;

[0195] β = 0.3: weight coefficient of urgency;

[0196] t ij : The processing time of task j on resource i is assumed to be 2 hours;

[0197] u j : The urgency of task j, assumed to be 3 (on a scale of 1-5);

[0198] T: task set, assuming there are two tasks j;

[0199] Calculation process L c :

[0200]

[0201]

[0202] The calculated L c The value is 8.782, which means that under the given parameters, the total load score of the resource is 8.782. This number can be used to compare the load levels of different resources.

[0203] Scheduling optimization score formula for resource i:

[0204]

[0205] Assumed values:

[0206] γ=2:priority adjustment coefficient;

[0207] p j =5: Task priority;

[0208] L c =8.782: the result obtained from the previous step;

[0209] N=2: number of tasks;

[0210] Calculate S c :

[0211]

[0212] S C =0.433

[0213] The calculated S c The value is 0.433, which indicates the average optimization scheduling score of resources. This value is used to evaluate the efficiency of resource scheduling.

[0214] Task scheduling optimization output formula:

[0215]

[0216] Assumed values:

[0217] θ=1.5: adjustment coefficient of scheduling score;

[0218] S c =0.433: the scheduling score obtained from the previous step;

[0219] κ=1:constant bias;

[0220] φ=0.1: small positive number to avoid division by zero error;

[0221] R: resource set, assuming there is 1 resource;

[0222] Calculate O out :

[0223]

[0224] O out =0.591

[0225] The calculated O out The value is 0.591, which represents the efficiency index of the overall task scheduling optimization output.

[0226] See also Figure 5 , the specific steps for obtaining resource scheduling optimization results are:

[0227] S321: Based on the task scheduling optimization output, by analyzing the execution time and resource requirements of multiple tasks, the total occupied time of each resource under the current task scheduling is calculated through the formula:

[0228]

[0229] Referring to the nonlinear relationship between time and resource requirements, a list of task resource occupancy time is obtained, where: represents the adjusted total occupied time of the i-th resource, t j is the execution time of the jth task, r ij represents the adjustment coefficient of the time occupied by the i-th resource in the j-th task;

[0230] S322: Readjust resources according to the task resource occupancy time list and apply the formula:

[0231]

[0232] Evaluate the optimal utilization of resources and generate a resource utilization adjustment list, where: is the adjusted optimal utilization of the i-th resource, s k is the demand urgency of the k-th resource type, n k is the total demand for the kth resource type, represents the adjusted total occupied time of the i-th resource;

[0233] S323: Use the resource utilization adjustment list to optimize the resource scheduling strategy using the formula:

[0234]

[0235] By accumulating resource utilization, we can obtain the resource scheduling optimization result, where R d Indicates the resource scheduling optimization result. The adjusted optimal utilization of the i-th resource, and p is the total number of resources.

[0236] The formula for the adjusted total occupied time of the i-th resource is:

[0237]

[0238] The adjusted total occupied time of the i-th resource;

[0239] t j : The execution time of the jth task;

[0240] r ij : The adjustment coefficient of the time occupied by the i-th resource in the j-th task;

[0241] Assume parameters: number of tasks n = 3, t = [2, 3, 1.5] task execution time (hours), r ij =[0.5, 0.75, 0.6 resource occupancy time coefficient;

[0242] For each task j, calculate

[0243] Mission 1: 2 1.2 0.5 0.8 ≈2.297·0.574=1.318;

[0244] Second task: 3 1.2 0.75 0.8 ≈3.737·0.768=2.870;

[0245] Mission 3: 1.5 1.2 0.6 0.8 ≈1.778·0.633=1.125;

[0246] Add the values ​​to get

[0247]

[0248] It means that under the given task and resource occupancy coefficient conditions, the total adjusted occupancy time of the i-th resource is 5.313 hours.

[0249] The formula for the adjusted optimized utilization of the i-th resource is:

[0250]

[0251] U di : The adjusted optimal utilization rate of the i-th resource;

[0252] s k : The urgency of the demand for the k-th resource type;

[0253] n k : The total demand for the kth resource type;

[0254] The adjusted total occupied time of the i-th resource;

[0255] Assume parameters: resource type m = 2, s = [0.9, 0.7] resource demand urgency, n = [30, 20·total resource demand,

[0256]

[0257] calculate

[0258] The first resource: 0.9]30 -0.5 ≈0.9 · 0.183 = 0.165;

[0259] Second resource: 0.7·20 -0.5 ≈0.7·0.224=0.157;

[0260] Cumulative: 0.165+0.157=0.322

[0261] calculate

[0262]

[0263] It means that under the given urgency and resource demand, the optimal utilization rate of the i-th resource is 0.048, which is an indicator with the dimension of "unit utilization rate".

[0264] The formula for resource scheduling optimization results is:

[0265]

[0266] R d : Resource scheduling optimization results;

[0267] Optimal utilization of the i-th resource;

[0268] p: total number of resources;

[0269] Assume parameters: number of resources p = 3, U d = [0.048, 0.056, 0.042];

[0270] Accumulate the optimal utilization of each resource to get R d :

[0271] R d =0.048+0.056+0.042=0.146

[0272] R d =0.146 means that the total optimized utilization of all resources is 0.146, which reflects the overall efficiency of resources under the current configuration.

[0273] See also Figure 6 , the specific steps for obtaining performance monitoring records are as follows:

[0274] S411: Based on the performance monitoring records, for orthopedic treatment data, the computing resources are benchmarked using the formula:

[0275]

[0276] Evaluate the performance benchmark of the resource and generate a benchmark performance score list, where Pf i represents the performance score of computing resources, Si Represents the processing frequency of resources, B i is the bandwidth of the resource, σ and ρ are weight factors, and λ, ω, and δ are adjustment parameters;

[0277] S412: Based on the benchmark performance score list, monitor the real-time performance of the resource when processing orthopedic data using the formula:

[0278]

[0279] Calculate real-time performance indicators and obtain real-time performance monitoring data, where Rf t is the performance index at time t, Pf i represents the performance score of computing resources, L t is the load factor at time t, κ, θ, η are adjustment parameters;

[0280] S413: Using real-time performance monitoring data, use the formula:

[0281]

[0282] Integrate performance data and establish performance monitoring records, where Mf represents performance monitoring records and Rf represents t is the performance index at time t, and T is the monitoring time range.

[0283] The performance scoring formula for computing resources is:

[0284]

[0285] σ=0.2:weight factor for processing frequency;

[0286] ρ = 0.1: bandwidth weight factor;

[0287] λ=0.5: normalization parameter;

[0288] ω=0.01: attenuation parameter, affecting the exponential attenuation of bandwidth;

[0289] δ=1: a constant to ensure that the denominator is non-zero;

[0290] S i =3GHz: the processing frequency of the i-th resource;

[0291] B i =100MB / s: bandwidth of the i-th resource;

[0292] calculate Impact: 3 3 =27GHz^3;

[0293] Calculate the square root of the bandwidth:

[0294] Calculate the exponential decay of bandwidth: e -0.01·100 ≈0.37;

[0295] Calculate the denominator: 0.5 0.37 + 1 = 1.185;

[0296] Final performance score Pf i :

[0297]

[0298] Performance score Pf i ≈5.4 represents the performance score of the i-th computing resource under given parameters, which is used to compare the adaptability of different computing resources.

[0299] The performance indicator formula at time t is:

[0300]

[0301] κ=0.8:performance index magnification factor;

[0302] θ=0.02:Influence parameter of load factor;

[0303] η=0.05:Influence coefficient of load square;

[0304] L t =50%: load factor at time t;

[0305] Calculate the logarithmic part: log(1+0.02·50)=log(2)≈0.693;

[0306] Calculate the denominator: 1 + 0.05 2500 = 126;

[0307] The final performance index Rf t :

[0308]

[0309] Performance index Rf t ≈0.028 indicates the performance status of the resource at a given moment, reflecting the real-time processing capability.

[0310] Performance monitoring record formula:

[0311]

[0312] T=10: The monitoring time range is 10 time units;

[0313] Assume that each Rf t Both are 0.028;

[0314] Calculate the total performance over the entire time range:

[0315] Mf=10·0.028=0.28

[0316] The performance monitoring record Mf=0.28 represents the performance score accumulated during the entire monitoring period and is used to evaluate the long-term performance of the resource.

[0317] See also Figure 7 ,The specific steps for obtaining the strategy for enhancing the efficiency of orthopedic treatment data analysis are as follows:

[0318] S421: Analyze performance monitoring records and identify performance bottlenecks in data processing using the formula:

[0319]

[0320] Calculate performance bottleneck indicators and generate performance bottleneck analysis results, where Bh i Represents the performance bottleneck indicator, R i represents the real-time performance index of the resource, γ represents the impact coefficient, ∈ represents a small positive number with a non-zero divisor, and δ represents the stability parameter;

[0321] S422: Optimize resource allocation based on performance bottleneck analysis results, using the formula:

[0322]

[0323] Generate a new resource configuration, where Ch new represents the new resource configuration, Bh i represents the performance bottleneck indicator, α represents the optimization coefficient, and L eff represents the expected efficiency improvement ratio, β represents the parameter for regulating efficiency growth, and ξ represents a small positive number;

[0324] S423: Integrate new resource configuration, using the formula:

[0325]

[0326] By normalizing parameters and adjusting coefficients to enhance the rationality of the strategy, a strategy to enhance the efficiency of orthopedic treatment data analysis is established, where S eff represents the efficiency enhancement strategy, Ch new represents the new resource configuration, ζ represents the normalization parameter, and ψ represents the adjustment coefficient.

[0327] Performance bottleneck indicator formula:

[0328]

[0329] Assume the parameters are:

[0330] R i =2GHz (real-time performance indicator of resources);

[0331] γ = 5 (influence coefficient for enhancing calculation sensitivity);

[0332] ∈=0.1 (a small positive number that guarantees a non-zero divisor);

[0333] δ = 0.01 (stability parameter);

[0334] calculate

[0335] Calculate the denominator:

[0336] Calculate Bh i :

[0337]

[0338] Bh i =6.25 means that under the given performance index, the calculated value of the resource's performance bottleneck index is 6.25, which is used to identify the critical bottleneck.

[0339] New resource allocation formula:

[0340]

[0341] Assume the parameters are:

[0342] Bh i =6.25 (calculated from the previous step);

[0343] α = 3 (optimization coefficient);

[0344] L eff =0.5 (expected efficiency improvement ratio);

[0345] β = 2 (parameter to adjust efficiency growth);

[0346] ξ=0.05 (a small positive number to ensure calculation stability);

[0347] Calculate L eff :

[0348] Calculate the denominator: 1+2×2+0.05=1+4+0.05=5.05;

[0349] Calculate Ch new :

[0350]

[0351] Ch new≈3.71 means that the resource value of the new configuration is 3.71, which reflects the amount of resource configuration optimization.

[0352] Efficiency enhancement strategy formula:

[0353]

[0354] Assume the parameters are:

[0355] Ch new =3.71 (calculated from the previous step);

[0356] ζ = 1.5 (normalization parameter);

[0357] ψ=0.3(adjustment coefficient);

[0358] Calculation of molecules: Ch new ζ=3.71×1.5=5.565

[0359] Calculate S eff :

[0360]

[0361] S eff ≈18.55 means that the value of the entire efficiency enhancement strategy is 18.55, indicating that efficiency is improved through optimized resource allocation.

[0362] An orthopedic treatment data analysis system is used to execute the orthopedic treatment data analysis method, and the system includes:

[0363] The resource evaluation module analyzes demand data based on surgical data, compares the processing speed and response time of heterogeneous computing resources, evaluates the processing adaptability of resources to differentiated data tasks, analyzes the matching degree between resource performance and demand, and constructs a resource characteristic analysis table;

[0364] The resource allocation module analyzes the load capacity of computing resources based on the resource characteristic analysis table, allocates resource data-intensive tasks through resource performance scoring, and forms a resource allocation plan;

[0365] The task scheduling module uses resource configuration schemes to optimize the execution sequence of tasks, adjust resource allocation, reduce execution delays and resource idle time through dynamic scheduling, and obtain scheduling strategy details;

[0366] The performance monitoring module monitors the real-time performance of computing resources when processing surgical data based on the scheduling strategy details, records the processing time and resource consumption of multiple tasks, analyzes performance data and identifies inefficient links, and generates performance monitoring results;

[0367] The efficiency optimization module evaluates the effectiveness of resource allocation based on performance monitoring results, reallocates computing loads based on discovered bottlenecks, optimizes data flow and processing strategies, and establishes strategies to enhance the efficiency of orthopedic treatment data analysis.

[0368] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for analyzing orthopedic treatment data, characterized in that: The following steps are involved: Based on the surgical data analysis demand data, heterogeneous computing resources are evaluated, and the processing power and response time are matched with the analysis requirements of surgical time and rehabilitation progress data, the degree of dependence of multiple tasks on computing resources is determined, and a resource demand matching table is generated; According to the resource demand matching table, determine the optimal computing resources for each task, generate a resource allocation implementation suggestion, implement the resource allocation implementation suggestion, allocate the task to the specified computing resource, and obtain the resource allocation execution result; According to the resource allocation execution result, the tasks are scheduled, the task execution order and resource utilization are dynamically optimized, resource idleness and task delay are reduced, task scheduling optimization output is obtained, and according to the task scheduling optimization output, the resource utilization strategy is adjusted to generate resource scheduling optimization results; Based on the resource scheduling optimization results, evaluate the computing resource performance for orthopedic treatment data analysis, monitor the performance of differentiated resources in real-time processing of orthopedic data, record performance data, generate performance monitoring records, analyze the performance monitoring records, identify performance bottlenecks in processing orthopedic data, reconfigure resources in a targeted manner, and generate orthopedic treatment data analysis efficiency enhancement strategies.

2. The orthopedic treatment data analysis method according to claim 1, characterized in that: The steps for obtaining the resource requirement matching table are specifically as follows: Analyze the demand data based on surgical data, collect the surgical time and rehabilitation progress data, analyze the relationship between heterogeneous computing resources, and use the formula: Calculate the fitness of each resource and get a preliminary resource fitness list, where Ra i represents the fitness of the i-th computing resource, S i is the processing capacity of the ith resource, C i is the response time, D i is the surgical data correlation, α and β are the weights of processing capability and response time, and γ and δ are used for normalization processing; According to the preliminary resource fitness list, resource allocation optimization is performed using the formula: Calculate the fitness score of the resource and obtain the optimized resource fitness list, where Pa i is the fitness score of the i-th resource, Ra i represents the fitness of the i-th computing resource, D i is the data point association, κ is the fitness amplification parameter, and Θ is the sum of all resource fitnesses; The optimized resource fitness list is used to match the optimal computing resources for each surgical task using the formula: Establish a resource demand matching table, where Ma represents the selected optimal resource, Pa i is the fitness score of the ith resource, and max(P) is the highest value among the resource scores.

3. The orthopedic treatment data analysis method according to claim 2, characterized in that: The steps for obtaining the resource allocation execution result are specifically as follows: The optimal computing resource for each task is selected from the resource requirement matching table using the formula: By enhancing the impact of the score and adjusting the bias, we can optimize resource selection and obtain the optimal computing resource list, where R b represents the optimal computing resources allocated to each task, σ is the amplification parameter, and P i is the computational resource fitness score, max(P) is the maximum value in the resource fitness score, and ∈ is a constant; Based on the optimal computing resource list, a resource allocation plan is implemented to allocate tasks according to the determined resources using the formula: Referring to the exponential enhancement of resources and reflecting the nonlinear impact of resource capabilities, a mapping table of task resources is obtained, where E b For task i in resource R b The execution plan on x ij is a binary decision variable, λ is the resource capacity adjustment coefficient, T is the task set, R b represents the optimal computing resources to be allocated to each task; Based on the mapping table of the task resources, by the formula: Use adjustment factors and constant bias to optimize efficiency trials and establish resource allocation execution results, where O b represents the task execution efficiency of computing resources, E b For task i in resource R b The execution plan on , max(E) is the execution amount in the execution plan, μ is the efficiency adjustment coefficient, φ is the constant bias, and R is the resource set.

4. The orthopedic treatment data analysis method according to claim 3, characterized in that: The steps for obtaining the task scheduling optimization output are specifically as follows: According to the resource allocation execution result, the current task load of multiple resources is evaluated using the formula: The influence of the processing time and urgency of the weighted reference task is calculated to obtain the resource load table after adjusting the total load of each resource, where L c represents the adjusted total load of resource i, α and β are the weights of the nonlinear effects of adjustment time and urgency, t ij is the processing time of task j on resource i, u j is the urgency of task j, T is the set of tasks; Based on the resource load table, perform task optimization scheduling using the formula: By optimizing the task execution order by referring to the inverse power of resource load, a task optimization scheduling scheme is generated, where S c is the scheduling optimization score of resource i, γ is the priority adjustment coefficient, and p j is the priority of task j, L c represents the adjusted total load of resource i, N is the total number of tasks; Integrate the resource load table with the task optimization scheduling scheme and use the formula: Adjust the scheduling score of each resource, optimize the overall task execution efficiency and resource utilization, and obtain the task scheduling optimization output, where O out represents the task scheduling optimization output, S c is the scheduling optimization score for resource i, θ is the adjustment coefficient of the scheduling score, κ is a constant bias, φ is a small positive number to prevent the denominator from being zero, and R is the resource set.

5. The orthopedic treatment data analysis method according to claim 4, characterized in that: The steps for obtaining the resource scheduling optimization result are specifically as follows: Based on the task scheduling optimization output, by analyzing the execution time and resource requirements of multiple tasks, the total occupied time of each resource under the current task scheduling is calculated through the formula: Referring to the nonlinear relationship between time and resource requirements, a list of task resource occupancy time is obtained, where: represents the adjusted total occupied time of the i-th resource, t j is the execution time of the jth task, r ij represents the adjustment coefficient of the time occupied by the i-th resource in the j-th task; According to the task resource occupation time list, readjust the resources and apply the formula: Evaluate the optimal utilization of resources and generate a resource utilization adjustment list, where: is the adjusted optimal utilization of the i-th resource, s k is the demand urgency of the k-th resource type, n k is the total demand for the kth resource type, represents the adjusted total occupied time of the i-th resource; The resource utilization adjustment list is used to optimize the resource scheduling strategy using the formula: By accumulating resource utilization, we can obtain the resource scheduling optimization result, where R d Indicates the resource scheduling optimization result. The adjusted optimal utilization of the i-th resource, and p is the total number of resources.

6. The orthopedic treatment data analysis method according to claim 5, characterized in that: The steps for obtaining the performance monitoring record are specifically as follows: Based on the performance monitoring records, a performance benchmark test of computing resources was performed for orthopedic treatment data using the formula: Evaluate the performance benchmark of the resource and generate a benchmark performance score list, where Pf i represents the performance score of computing resources, S i Represents the processing frequency of resources, B i is the bandwidth of the resource, σ and ρ are weight factors, and λ, ω, and δ are adjustment parameters; Based on the benchmark performance score list, monitor the real-time performance of the resource when processing orthopedic data using the formula: Calculate real-time performance indicators and obtain real-time performance monitoring data, where Rf t is the performance index at time t, Pf i represents the performance score of computing resources, L t is the load factor at time t, κ, θ, η are adjustment parameters; Using the real-time performance monitoring data, the formula is used: Integrate performance data and establish performance monitoring records, where Mf represents performance monitoring records and Rf represents t is the performance index at time t, and T is the monitoring time range.

7. The orthopedic treatment data analysis method according to claim 6, characterized in that: The steps for obtaining the orthopedic treatment data analysis efficiency enhancement strategy are as follows: Analyze the performance monitoring records and identify performance bottlenecks in data processing using the formula: Calculate performance bottleneck indicators and generate performance bottleneck analysis results, where Bh i Represents the performance bottleneck indicator, R i represents the real-time performance index of the resource, γ represents the impact coefficient, ∈ represents a small positive number with a non-zero divisor, and δ represents the stability parameter; According to the performance bottleneck analysis results, optimize resource allocation using the formula: Generate a new resource configuration, where Ch new represents the new resource configuration, Bh i represents the performance bottleneck indicator, α represents the optimization coefficient, and L eff represents the expected efficiency improvement ratio, β represents the parameter for regulating efficiency growth, and ξ represents a small positive number; Integrate the new resource configuration, using the formula: By normalizing parameters and adjusting coefficients to enhance the rationality of the strategy, a strategy to enhance the efficiency of orthopedic treatment data analysis is established, where S eff represents the efficiency enhancement strategy, Ch new represents the new resource configuration, ζ represents the normalization parameter, and ψ represents the adjustment coefficient.

8. An orthopedic treatment data analysis system, characterized in that: According to the orthopedic treatment data analysis method according to any one of claims 1 to 7, the system comprises: The resource evaluation module analyzes demand data based on surgical data, compares the processing speed and response time of heterogeneous computing resources, evaluates the processing adaptability of resources to differentiated data tasks, analyzes the matching degree between resource performance and demand, and constructs a resource characteristic analysis table; The resource allocation module analyzes the load capacity of computing resources based on the resource characteristic analysis table, allocates resource data-intensive tasks through resource performance scoring, and forms a resource allocation plan; The task scheduling module uses the resource configuration scheme to optimize the execution sequence of tasks, adjust resource allocation, reduce execution delays and resource idle time through dynamic scheduling, and obtain scheduling strategy details; The performance monitoring module monitors the real-time performance of computing resources when processing surgical data based on the scheduling strategy details, records the processing time and resource consumption of multiple tasks, analyzes performance data and identifies inefficient links, and generates performance monitoring results; The efficiency optimization module evaluates the effect of resource allocation based on the performance monitoring results, reallocates computing load according to the discovered bottlenecks, optimizes data flow and processing strategies, and establishes an efficiency enhancement strategy for orthopedic treatment data analysis.

Images