Intelligent control method and system for bone trauma therapeutic apparatus

Abstract

The invention discloses an intelligent control method and system for a bone trauma therapeutic apparatus, and particularly relates to the technical field of intelligent medical equipment. And based on a patient data set stored in the therapeutic apparatus, screening and classifying the patients receiving bone trauma treatment to obtain a treatment parameter frequent adjustment group. And analyzing the time sequence change of the treatment scheme of the group in the treatment cycle, and evaluating the internal matching degree of the treatment scheme to bone tissue repair. Meanwhile, real-time feedback data of the group under stimulation of the same kind of treatment parameters is processed, the divergence of group response is quantified, and the accepting stability of the group to the treatment scheme is judged. By analyzing the complexity of sensing signals collected in the treatment process, the necessity of improving diversified regulation and control strategies is evaluated. The above analysis results are comprehensively considered, the parameter configuration strategy of the bone trauma therapeutic apparatus is dynamically adjusted, it is ensured that the therapeutic apparatus can be widely applied to the field of intelligent treatment of bone trauma, and the clinical value is remarkable.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent medical equipment, and more specifically, to an intelligent control method and system for a bone trauma therapeutic apparatus. Background Art

[0002] Traditional bone trauma treatment devices usually use fixed treatment parameters and implement the same treatment plan for different patients. However, due to individual differences in age, gender, bone density, trauma type, and healing ability, fixed treatment parameters are difficult to meet the needs of all patients, which may lead to poor treatment effects or prolonged recovery periods. Some patients need to frequently adjust treatment parameters during treatment to seek treatment plans that are more suitable for their own conditions. In addition, existing treatment devices lack the ability to analyze real-time feedback data from patients and cannot dynamically adjust treatment parameters based on individual responses of patients, resulting in a lack of precision and personalization in the treatment process.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent control method and system for a bone trauma treatment instrument to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent control method for a bone trauma therapeutic apparatus comprises the following steps:

[0007] Based on the patient data set stored in the bone trauma treatment instrument, the patients receiving bone trauma treatment are screened and classified to obtain the group with frequent treatment parameter adjustment;

[0008] Analyze the temporal changes of the treatment regimen of the group with frequent treatment parameter adjustments during the treatment cycle to evaluate the intrinsic matching degree of the treatment regimen to bone tissue repair;

[0009] Analyze the real-time feedback data of the treatment process of the group with frequent treatment parameter adjustments, and evaluate the response divergence of the group with frequent treatment parameter adjustments under the stimulation of the same treatment parameters;

[0010] Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters, the stability of the group with frequent treatment parameter adjustments in accepting the treatment plan is determined;

[0011] When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument is evaluated by analyzing the complexity of the sensor signals collected by the bone trauma treatment instrument during the treatment process;

[0012] A comprehensive analysis is conducted on the intrinsic matching degree of the treatment plan for bone tissue repair, the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters, and the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument, so as to dynamically adjust the configuration strategy of the treatment parameters of the bone trauma treatment instrument.

[0013] In a preferred embodiment, based on the patient data set stored in the bone trauma treatment instrument, the patients receiving bone trauma treatment are screened and classified to obtain a group with frequent treatment parameter adjustment, specifically:

[0014] Extract the treatment data of all patients from the database of the bone trauma treatment instrument;

[0015] Clean the extracted data to exclude duplicate, invalid or abnormal data;

[0016] Based on the patient treatment records and parameter change frequency, screening rules are designed to screen the patient group whose treatment parameters are frequently adjusted during the treatment process: for each patient, for each treatment parameter, the adjustment frequency of the parameter in the entire treatment cycle is calculated, and the adjustment frequency is defined as the number of adjustments of the parameter divided by the total duration of the treatment cycle; according to the adjustment frequency of all treatment parameters, different weights are assigned according to their importance to the treatment effect, and the weighted result of the overall adjustment frequency is obtained;

[0017] A threshold for the overall adjustment frequency is set. If the patient's overall adjustment frequency reaches or exceeds the set threshold, the patient is considered to belong to the group with frequent treatment parameter adjustments.

[0018] In a preferred embodiment, the temporal changes of the treatment regimen of the group with frequent treatment parameter adjustment within the treatment cycle are analyzed to evaluate the intrinsic matching degree of the treatment regimen to bone tissue repair, specifically:

[0019] Extract the treatment plan data of the group with frequent treatment parameter adjustment during the treatment cycle and establish a time series data set;

[0020] According to the time dimension of treatment parameters, the time series distribution curve of parameters within the treatment cycle is constructed;

[0021] Analyze the correlation between the changing trend of parameters in the time series curve and the staged demand for bone tissue repair;

[0022] Based on correlation analysis, calculate the matching degree index of the contribution of treatment parameters to the repair effect: Based on the matching degree of each treatment parameter, calculate the comprehensive matching coefficient of all treatment parameters to the repair effect:

[0023] Among them, CMC is the comprehensive matching coefficient; M k is the matching degree of each treatment parameter; Q k is the weight of the kth treatment parameter; n is the total number of treatment parameters.

[0024] In a preferred embodiment, the real-time feedback data of the treatment parameter adjustment frequent group during the treatment process is analyzed to evaluate the response divergence of the treatment parameter adjustment frequent group under the stimulation of the same treatment parameter, specifically:

[0025] Collect real-time feedback data from the group with frequent treatment parameter adjustments during the treatment process and build a feedback data set;

[0026] Extract features from feedback data, including physiological signal amplitude, frequency, and response delay;

[0027] Cluster analysis of feedback characteristics under stimulation of similar treatment parameters to identify response patterns of patient groups;

[0028] Calculate the discreteness of feedback characteristics and evaluate the response divergence of the frequent treatment parameter adjustment group under the stimulation of similar treatment parameters: Based on the clustering results, calculate the discreteness of feedback characteristics under the stimulation of similar treatment parameters. The calculation formula is: Among them, V x represents the discreteness of the feedback features of the x-th type of treatment parameter stimulation; M represents the total number of feedback features belonging to the x-th type of treatment parameter stimulation in the clustering results; z y represents the actual value of the yth feedback feature data; μ x Represents the average value of the feedback characteristics of the x-th type of treatment parameter stimulation.

[0029] In a preferred embodiment, based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the frequent treatment parameter adjustment group under the stimulation of the same treatment parameters, the stability of the frequent treatment parameter adjustment group's acceptance of the treatment plan is judged, specifically:

[0030] Preset the comprehensive matching coefficient threshold, and compare the comprehensive matching coefficient with the comprehensive matching coefficient threshold:

[0031] When the comprehensive matching coefficient is greater than the comprehensive matching coefficient threshold, it indicates that the intrinsic matching degree of the treatment plan to bone tissue repair is high;

[0032] When the comprehensive matching coefficient is less than or equal to the comprehensive matching coefficient threshold, it indicates that the intrinsic matching degree of the treatment plan to bone tissue repair is low;

[0033] Preset the discreteness threshold and compare the discreteness with the discreteness threshold:

[0034] When the dispersion is greater than or equal to the dispersion threshold, it means that the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters is large;

[0035] When the dispersion is less than the dispersion threshold, it means that the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters is low;

[0036] When the comprehensive matching coefficient is greater than the comprehensive matching coefficient threshold and the dispersion is less than the dispersion threshold, the acceptance stability of the treatment plan by the group with frequent treatment parameter adjustment is high acceptance stability; otherwise, the acceptance stability of the treatment plan by the group with frequent treatment parameter adjustment is low acceptance stability.

[0037] In a preferred embodiment, when the acceptance stability of the treatment scheme by the frequent treatment parameter adjustment group is low, the necessity of improving the diversified control strategy of the bone trauma treatment instrument is evaluated by analyzing the complexity of the sensor signals collected by the bone trauma treatment instrument during the treatment process, specifically:

[0038] Collect multi-channel sensor signals of the bone trauma treatment device during the treatment process;

[0039] Preprocess the signal data and extract characteristic signals;

[0040] Calculate the temporal entropy of each sensor signal to evaluate the necessity of improving the diversified regulation strategy of the bone trauma treatment device: abc , the Shannon entropy formula is used to calculate the time series entropy, the calculation formula is: Among them, E abc represents the temporal entropy value of the a-th channel, the b-th time point, and the c-th signal type; p d represents the probability of the dth value in the time series; m represents the total number of all values ​​in the time series.

[0041] In a preferred embodiment, a comprehensive analysis is conducted on the intrinsic matching degree of the treatment scheme to bone tissue repair, the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, and the necessity of the bone trauma treatment instrument to improve the diversified regulation strategy, and the configuration strategy of the treatment parameters of the bone trauma treatment instrument is dynamically adjusted, specifically:

[0042] The comprehensive matching coefficient corresponding to the intrinsic matching degree of the treatment plan for bone tissue repair, the discreteness corresponding to the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, and the time series entropy value corresponding to the necessity of the bone trauma treatment instrument to improve the diversified regulation strategy are normalized, and the normalized comprehensive matching coefficient, discreteness and time series entropy value are comprehensively analyzed to calculate the regulation demand coefficient. The calculation formula of the regulation demand coefficient is: CDRI = α*(1-CMC)+β*Vx+δ*Eabc|; where CDRI represents the regulation demand coefficient; CMC is the comprehensive matching coefficient; V x Indicates the discreteness; E abc represents the time series entropy value; α, β, δ are the weight coefficients of comprehensive matching coefficient, dispersion and time series entropy value respectively;

[0043] Preset the control demand coefficient threshold and compare the control demand coefficient with the control demand coefficient threshold:

[0044] When the control demand coefficient is greater than or equal to the control demand coefficient threshold, it is necessary to dynamically adjust the treatment parameter configuration strategy of the bone trauma treatment instrument, including optimizing the treatment parameter range, adding personalized control strategies, and improving the precision of signal acquisition and processing;

[0045] When the regulation demand coefficient is less than the regulation demand coefficient threshold, there is no need to dynamically adjust the treatment parameter configuration strategy of the bone trauma treatment device.

[0046] On the other hand, the present invention provides an intelligent control system for a bone trauma treatment instrument, comprising a data processing module, a timing analysis module, a feedback analysis module, an acceptance stability judgment module, a complexity evaluation module and a comprehensive control module;

[0047] Data processing module: based on the patient data set stored in the bone trauma treatment instrument, screen and classify the patients receiving bone trauma treatment to obtain the group with frequent treatment parameter adjustment;

[0048] Timing analysis module: Analyze the timing changes of treatment plans for groups with frequent treatment parameter adjustments during the treatment cycle to evaluate the intrinsic matching degree of the treatment plans for bone tissue repair;

[0049] Feedback analysis module: Analyze the real-time feedback data during the treatment process of the group with frequent treatment parameter adjustments, and evaluate the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters.

[0050] Acceptance stability judgment module: Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, the acceptance stability of the group with frequent treatment parameter adjustment to the treatment plan is judged;

[0051] Complexity evaluation module: When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the complexity of the sensor signals collected by the bone trauma treatment device during the treatment process is analyzed to evaluate the necessity of improving the diversified regulation strategy of the bone trauma treatment device;

[0052] Comprehensive control module: Comprehensively analyze the intrinsic matching degree of the treatment plan to bone tissue repair, the response divergence of the group with frequent treatment parameter adjustment under the stimulation of similar treatment parameters, and the necessity of improving the diversified control strategy of the bone trauma treatment device, and dynamically adjust the configuration strategy of the treatment parameters of the bone trauma treatment device.

[0053] The technical effects and advantages of the intelligent control method and system of a bone trauma treatment device of the present invention are as follows:

[0054] Through screening and classification based on patient data, the groups with frequent treatment parameter adjustments can be accurately identified, making the treatment plan more targeted and improving the scientific nature of patient grouping; combined with the analysis of treatment plan time series changes and the divergence evaluation of real-time feedback data, the acceptance stability of the treatment plan for the patient group can be comprehensively judged, solving the problem of insufficient personalization in the traditional treatment model; by analyzing the complexity of multi-channel sensor signals, the necessity of improving the diversified control strategy of the therapeutic instrument is scientifically evaluated, providing a theoretical basis for dynamic optimization in complex treatment processes; through a comprehensive analysis of the degree of bone tissue repair matching, patient response divergence and signal complexity, dynamic adjustment of treatment parameters is achieved, which not only meets the personalized needs of patients, but also improves the accuracy and effectiveness of treatment, can effectively shorten the bone tissue repair cycle, improve treatment safety and efficiency, and promote the development of intelligent medical equipment in the field of bone trauma. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of an intelligent control method of a bone trauma therapeutic apparatus according to the present invention;

[0056] Figure 2 The figure is a schematic diagram of the structure of an intelligent control system of a bone trauma therapeutic apparatus according to the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] Figure 1The present invention provides an intelligent control method for a bone trauma therapeutic apparatus, which comprises the following steps:

[0060] Based on the patient data set stored in the bone trauma treatment instrument, the patients receiving bone trauma treatment are screened and classified to obtain the group with frequent treatment parameter adjustment;

[0061] Analyze the temporal changes of the treatment regimen of the group with frequent treatment parameter adjustments during the treatment cycle to evaluate the intrinsic matching degree of the treatment regimen to bone tissue repair;

[0062] Analyze the real-time feedback data of the treatment process of the group with frequent treatment parameter adjustments, and evaluate the response divergence of the group with frequent treatment parameter adjustments under the stimulation of the same treatment parameters;

[0063] Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters, the stability of the group with frequent treatment parameter adjustments in accepting the treatment plan is determined;

[0064] When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument is evaluated by analyzing the complexity of the sensor signals collected by the bone trauma treatment instrument during the treatment process;

[0065] A comprehensive analysis is conducted on the intrinsic matching degree of the treatment plan for bone tissue repair, the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters, and the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument, so as to dynamically adjust the configuration strategy of the treatment parameters of the bone trauma treatment instrument.

[0066] Specifically, based on the patient data set stored in the bone trauma treatment instrument, the patients receiving bone trauma treatment are screened and classified to obtain the group with frequent treatment parameter adjustment, including:

[0067] Extract all patients' treatment data from the database of the bone trauma treatment instrument: The database of the bone trauma treatment instrument contains historical information on patient treatment, including treatment time, treatment method, initial value and adjustment record of treatment parameters, patient physiological feedback signals, etc. The extracted data is stored in a structured form, covering the patient's basic information (such as age, gender, medical history) and personalized treatment parameters (such as mechanical vibration frequency, ultrasonic stimulation intensity, electric field stimulation level, biological factor release cycle, etc.). When extracting data, a unified coding rule is used to map the fields, and each piece of data is assigned a unique identifier.

[0068] Clean the extracted data to exclude duplicate, invalid or abnormal data: filter and remove records with missing values ​​in the data, or use reasonable interpolation methods to fill in the missing values;

[0069] Check for duplicate records in the data and merge duplicate data based on the patient's unique identifier;

[0070] Outlier detection was performed on the time series data of treatment parameters, using statistical methods (such as the triple standard deviation method) to identify and remove values ​​that were outside the reasonable range;

[0071] Verify that the patient's treatment information is complete, ensuring that all key treatment parameters are recorded and meet device specifications.

[0072] Based on the patient's treatment records and the frequency of parameter changes, we designed screening rules to screen the patient group whose treatment parameters were frequently adjusted during the treatment process: Based on the patient's treatment records, we extracted the adjustment information of all treatment parameters, including the number of adjustments of each parameter and the total duration of the treatment cycle. By analyzing the adjustment information of all treatment parameters, we designed rules to measure the frequency of treatment parameter adjustments.

[0073] For each patient, for each treatment parameter, the adjustment frequency of the parameter during the entire treatment cycle was calculated. The adjustment frequency was defined as the number of adjustments of the parameter divided by the total duration of the treatment cycle. Based on the adjustment frequency of all treatment parameters, different weights were assigned to each parameter according to its importance to the treatment effect, and the weighted result of the overall adjustment frequency was obtained.

[0074] Set a threshold standard for the overall adjustment frequency to screen the patient group with frequent adjustment of treatment parameters. If the overall adjustment frequency of a patient reaches or exceeds the set threshold, the patient is considered to belong to the group with frequent adjustment of treatment parameters. The design of the screening rules needs to be combined with the opinions of clinical experts and the actual treatment effects of patients to ensure the scientificity and applicability of the screening criteria.

[0075] Specifically, the temporal changes of the treatment regimens of the group with frequent treatment parameter adjustments during the treatment cycle are analyzed to evaluate the intrinsic matching degree of the treatment regimens for bone tissue repair, including:

[0076] Extract the treatment plan data of the group with frequent treatment parameter adjustment within the treatment cycle and establish a time series data set: Extract all treatment plan data within the treatment cycle from the records of the group with frequent treatment parameter adjustment. Each treatment plan data contains multiple treatment parameters, including mechanical micro-vibration frequency, ultrasonic intensity, electric field stimulation level, and biological factor release cycle. These data are uniformly coded to ensure the consistency and integrity of the data structure.

[0077] The treatment plan data is sorted by time dimension to establish a time series data set, denoted as D(t), where t is the treatment time. Each time t contains multiple treatment parameter values, represented as {P t1 ,P t2 ,...P tn}, where P tk represents the kth treatment parameter at time t, and n is the total number of treatment parameters.

[0078] According to the time dimension of the treatment parameters, the time series distribution curve of the parameters in the treatment cycle is constructed: Based on the time series data set D(t), the time series distribution curve of each treatment parameter in the treatment cycle is constructed. For each treatment parameter Ptk, the time series data {Pt1, Pt2, ... Ptn} is plotted into a curve C according to time t. k (t). Curve C k (t) represents the dynamic change of the kth treatment parameter during the treatment cycle.

[0079] In order to avoid the influence of data noise, smoothing is required before curve construction, and the moving average method is used to calculate the treatment parameter value at each time point: Where W represents the window width, which indicates the time window size of the smoothing process; C k (t) represents the smoothed value of the kth treatment parameter at time t; P ki represents the actual value of the kth treatment parameter at time i.

[0080] Analysis of the correlation between the changing trend of parameters in the time series curve and the staged demand for bone tissue repair: Based on the time series distribution curve C k (t), combined with the staged demand model of bone tissue repair, evaluate the matching between treatment parameters and repair requirements. The repair demand model is based on the typical stages of bone repair (such as inflammation, repair, and reconstruction), and defines the ideal demand range R for treatment parameters in each stage. k (t).

[0081] Through the matching function, the time series distribution curve C is calculated k (t) and the ideal required range of treatment parameters R k Correlation of (t): Where Mk represents the matching degree of the kth treatment parameter; t1 and t2 represent the start time and end time of the treatment cycle respectively; min(C k (t),R k (t)) represents the minimum value of the smoothed value of the kth treatment parameter and the corresponding ideal demand range at time t.

[0082] Based on correlation analysis, the matching degree index of the contribution of treatment parameters to the repair effect is calculated: based on the matching degree M of each treatment parameter k , calculate the comprehensive matching coefficient of all treatment parameters on the repair effect:

[0083] Among them, CMC is the comprehensive matching coefficient; M k is the matching degree of each treatment parameter; Qk is the weight of the kth treatment parameter, indicating the relative importance of the corresponding treatment parameter on the bone tissue repair effect; n is the total number of treatment parameters.

[0084] The larger the comprehensive matching coefficient, the higher the intrinsic matching degree of the treatment plan for bone tissue repair. The larger the comprehensive matching coefficient, the more consistent the temporal change trend of the treatment parameters is with the requirements of different stages of bone tissue repair. For example, in the inflammatory phase, repair phase and reconstruction phase of bone tissue, each stage may have different ideal ranges and dynamic change requirements for vibration frequency, ultrasonic intensity or electric field stimulation level. When the actual value of the treatment parameter can be adjusted more accurately in accordance with these staged requirements, and the overlap between the temporal distribution and the demand curve is high, the value of the comprehensive matching coefficient also increases accordingly. This shows that the treatment plan can not only accurately respond to the physiological requirements of bone tissue repair, but also provide more personalized and dynamic support, thereby improving the treatment effect, accelerating the repair process, and reducing unnecessary interventions or possible side effects.

[0085] Specifically, the real-time feedback data of the treatment process of the group with frequent treatment parameter adjustment is analyzed to evaluate the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, including:

[0086] Collect real-time feedback data from the group with frequent treatment parameter adjustment during the treatment process and construct a feedback data set: During the treatment process of the group with frequent treatment parameter adjustment, collect real-time feedback data, including the patient's physiological signals (such as electrophysiological response, blood flow change signals) and physical feedback signals collected by the treatment device (such as force sensor readings). These data are classified and marked according to patient number, treatment time, and stimulation parameter category.

[0087] Construct feedback dataset F uvw , where u represents the u-th patient; v represents the v-th treatment moment; and w represents the type of feedback signal, such as a physiological signal or a physical signal.

[0088] Extract features from feedback data, including physiological signal amplitude, frequency, and response delay: For feedback data set F uvw , using fast Fourier transform to extract key features of real-time feedback signals, including:

[0089] Signal Amplitude uvw , the maximum intensity of the physiological response or physical feedback elicited by the therapeutic stimulus;

[0090] Signal frequency f uvw , the periodic changes of the signal in the time dimension;

[0091] Response delay T uvw , the time delay for the feedback signal to reach its peak after the therapeutic stimulation.

[0092] The feature dataset after feature extraction is represented as D uvw ={A uvw ,f uvw ,T uvw}.

[0093] Cluster analysis is performed on the feedback features under stimulation of similar treatment parameters to identify the response patterns of the patient groups: Based on the feedback feature dataset D uvw , group the data by the type of treatment parameters. For example, mechanical vibration stimulation group, ultrasound stimulation group, electric field stimulation group, etc. For each group of data, an unsupervised clustering algorithm (such as K-means algorithm) is applied to perform cluster analysis to identify the response patterns of the patient group under the same treatment parameters.

[0094] The clustering steps include:

[0095] 1. Initialize the cluster center;

[0096] 2. Calculate the Euclidean distance from each feature data to the cluster center and assign it to the nearest cluster;

[0097] 3. Update the cluster center to minimize the distance between the data in the group;

[0098] 4. Repeat steps 2 and 3 until the clustering results converge.

[0099] The clustering results divide the patients' feedback characteristics into different patterns, each of which represents a typical response behavior.

[0100] Calculate the discreteness of feedback characteristics and evaluate the response divergence of the frequent treatment parameter adjustment group under the stimulation of similar treatment parameters: Based on the clustering results, calculate the discreteness of feedback characteristics under the stimulation of similar treatment parameters. The calculation formula is: Among them, V x represents the discreteness of the feedback features of the x-th type of treatment parameter stimulation; M represents the total number of feedback features belonging to the x-th type of treatment parameter stimulation in the clustering results; z y represents the actual value of the yth feedback feature data; μ x Represents the average value of the feedback characteristics of the x-th type of treatment parameter stimulation.

[0101] The larger the dispersion, the greater the divergence of the response of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, that is, the group with frequent treatment parameter adjustment shows more obvious differences in the stimulation of the same treatment parameter. The larger dispersion reflects the increased discreteness of the physiological or physical feedback characteristics of the patient group in the statistical distribution, which means that some patients have low adaptability to the current treatment parameters. The larger dispersion usually means that more refined parameter grouping or dynamic adjustment mechanism is needed to optimize the applicability and effectiveness of the treatment plan.

[0102] Specifically, based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, the stability of the group with frequent treatment parameter adjustment in accepting the treatment plan is judged, including:

[0103] Preset the comprehensive matching coefficient threshold, and compare the comprehensive matching coefficient with the comprehensive matching coefficient threshold:

[0104] When the comprehensive matching coefficient is greater than the comprehensive matching coefficient threshold, it indicates that the treatment plan has a high degree of intrinsic matching to bone tissue repair, and the temporal changes of the treatment parameters are highly consistent with the requirements of each stage of bone tissue repair, which can effectively support the healing and functional recovery of bone tissue.

[0105] When the comprehensive matching coefficient is less than or equal to the comprehensive matching coefficient threshold, it means that the intrinsic matching degree of the treatment plan to bone tissue repair is low, and the setting of the treatment parameters does not fully meet the needs of the bone tissue repair process;

[0106] The comprehensive matching coefficient threshold is set based on the clinical needs of bone tissue repair, statistical analysis of historical treatment data, and expert experience. Usually, by analyzing the distribution of comprehensive matching coefficients of different treatment plans and combining the minimum effective needs of bone repair, a value that can reflect the applicability of the treatment plan is selected as the threshold.

[0107] Preset the discreteness threshold and compare the discreteness with the discreteness threshold:

[0108] When the dispersion is greater than or equal to the dispersion threshold, it means that the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters is large, and there are obvious differences in the feedback of the same stimulation parameters among patients;

[0109] When the dispersion is less than the dispersion threshold, it means that the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters is low, and most patients have similar responses to the current treatment parameters;

[0110] The setting of the discreteness threshold is based on statistical analysis and clinical needs. By calculating the discreteness of historical feedback data from a large number of patient groups and combining it with the evaluation of treatment effects, a value that reflects the balance between response consistency and variability is selected as the threshold.

[0111] When the comprehensive matching coefficient is greater than the comprehensive matching coefficient threshold and the dispersion is less than the dispersion threshold, the acceptance stability of the treatment plan by the group with frequent treatment parameter adjustment is high acceptance stability; otherwise, the acceptance stability of the treatment plan by the group with frequent treatment parameter adjustment is low acceptance stability.

[0112] Specifically, when the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the necessity of improving the diversified regulation strategy of the bone trauma therapeutic device is evaluated by analyzing the complexity of the sensor signals collected by the bone trauma therapeutic device during the treatment process, including:

[0113] Collect multi-channel sensor signals of the bone trauma treatment device during the treatment process: During the bone trauma treatment process, the multi-channel sensor signals collected by the treatment device include the real-time output of mechanical vibration sensors, mechanical sensors, bioelectric sensors, and temperature sensors. Each type of signal represents a different interaction characteristic between the treatment device and the patient. For example, mechanical vibration feedback reflects the effect of external force, and bioelectric signals represent nerve or muscle response. Record these signals and annotate information such as signal source and parameter settings to form structured signal data, recorded as S abc , where a represents the channel number of the signal (such as mechanical, mechanical, bioelectric, etc.); b represents the time point of acquisition; and c represents the signal type.

[0114] Preprocess the signal data and extract characteristic signals: use a bandpass filter to filter signal noise and retain the effective frequency band within the operating range of the therapeutic device;

[0115] Normalize the signal to make the signal amplitude range of all channels consistent;

[0116] Apply wavelet transform to decompose the signal and extract the features of specific frequency bands;

[0117] Divide the processed signal into time segments to generate the feature sequence G abc ,The signal characteristics of each segment include amplitude, frequency and spectral energy distribution.

[0118] Calculate the temporal entropy of each sensor signal to evaluate the necessity of improving the diversified regulation strategy of the bone trauma treatment device: abc , the Shannon entropy formula is used to calculate the time series entropy, the calculation formula is: Among them, E abc represents the temporal entropy value of the a-th channel, the b-th time point, and the c-th signal type; p d represents the probability of the dth value in the time series; m represents the total number of all values ​​in the time series.

[0119] Compare the temporal entropy value of each sensor signal with the preset reference range:

[0120] When the time series entropy value of each sensor signal is within the preset reference range, it means that the control strategy of the bone trauma treatment instrument can meet the needs of signal diversity and there is no need to improve the diversified control strategy;

[0121] When the time series entropy value of each sensor signal is lower than the preset reference range, it means that the signal is not complex enough and may have overly simple or highly repetitive features, resulting in insufficient information in the signal and unable to fully reflect the dynamic needs of the treatment process. The control strategy of the bone trauma treatment device cannot meet the needs of signal diversity and needs to improve the diversified control strategy.

[0122] When the timing entropy value of each sensor signal is higher than the preset reference range, it means that the signal complexity is too high and may contain too much noise or random components, which increases the difficulty of extracting effective information. The control strategy of the bone trauma treatment device cannot meet the needs of signal diversity and needs to improve the diversified control strategy.

[0123] Specifically, a comprehensive analysis is conducted on the intrinsic matching degree of the treatment plan to bone tissue repair, the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, and the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument, and the configuration strategy of dynamically adjusting the treatment parameters of the bone trauma treatment instrument is included:

[0124] The comprehensive matching coefficient corresponding to the intrinsic matching degree of the treatment plan for bone tissue repair, the discreteness corresponding to the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, and the time series entropy value corresponding to the necessity of the bone trauma treatment instrument to improve the diversified regulation strategy are normalized, and the normalized comprehensive matching coefficient, discreteness and time series entropy value are comprehensively analyzed to calculate the regulation demand coefficient. According to the regulation demand coefficient, the configuration strategy of the treatment parameters of the bone trauma treatment instrument is dynamically adjusted.

[0125] The calculation formula of the control demand coefficient is: CDRI = α*(1-CMC)+β*Vx+δ*Eabc|; where CDRI represents the control demand coefficient; CMC is the comprehensive matching coefficient; V x Indicates the discreteness; E abc represents the time series entropy value; α, β, and δ are the weight coefficients of the comprehensive matching coefficient, dispersion, and time series entropy value, respectively.

[0126] Preset the control demand coefficient threshold and compare the control demand coefficient with the control demand coefficient threshold:

[0127] When the regulation demand coefficient is greater than or equal to the regulation demand coefficient threshold, it is necessary to dynamically adjust the treatment parameter configuration strategy of the bone trauma treatment instrument, including optimizing the treatment parameter range, adding personalized regulation strategies, and improving the precision of signal acquisition and processing to meet the actual needs of patients and improve the treatment effect;

[0128] When the regulation demand coefficient is less than the regulation demand coefficient threshold, there is no need to dynamically adjust the treatment parameter configuration strategy of the bone trauma treatment device, and the existing configuration strategy is maintained to ensure the stability of the treatment.

[0129] Example 2

[0130] The difference between Example 2 of the present invention and Example 1 is that this example introduces an intelligent control system of a bone trauma treatment device.

[0131] Figure 2 A structural schematic diagram of an intelligent control system of a bone trauma therapeutic instrument of the present invention is given, and an intelligent control system of a bone trauma therapeutic instrument includes a data processing module, a timing analysis module, a feedback analysis module, an acceptance stability judgment module, a complexity evaluation module and a comprehensive control module;

[0132] Data processing module: based on the patient data set stored in the bone trauma treatment instrument, screen and classify the patients receiving bone trauma treatment to obtain the group with frequent treatment parameter adjustment;

[0133] Timing analysis module: Analyze the timing changes of treatment plans for groups with frequent treatment parameter adjustments during the treatment cycle to evaluate the intrinsic matching degree of the treatment plans for bone tissue repair;

[0134] Feedback analysis module: Analyze the real-time feedback data during the treatment process of the group with frequent treatment parameter adjustments, and evaluate the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters.

[0135] Acceptance stability judgment module: Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, the acceptance stability of the group with frequent treatment parameter adjustment to the treatment plan is judged;

[0136] Complexity evaluation module: When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the complexity of the sensor signals collected by the bone trauma treatment device during the treatment process is analyzed to evaluate the necessity of improving the diversified regulation strategy of the bone trauma treatment device;

[0137] Comprehensive control module: Comprehensively analyze the intrinsic matching degree of the treatment plan to bone tissue repair, the response divergence of the group with frequent treatment parameter adjustment under the stimulation of similar treatment parameters, and the necessity of improving the diversified control strategy of the bone trauma treatment device, and dynamically adjust the configuration strategy of the treatment parameters of the bone trauma treatment device.

[0138] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0139] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0140] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0143] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0145] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0147] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control method for a bone trauma treatment instrument, characterized in that: The steps include: Based on the patient data set stored in the bone trauma treatment instrument, the patients receiving bone trauma treatment are screened and classified to obtain the group with frequent treatment parameter adjustment; Analyze the temporal changes of the treatment regimen of the group with frequent treatment parameter adjustments during the treatment cycle to evaluate the intrinsic matching degree of the treatment regimen to bone tissue repair; Analyze the real-time feedback data of the treatment process of the group with frequent treatment parameter adjustments, and evaluate the response divergence of the group with frequent treatment parameter adjustments under the stimulation of the same treatment parameters; Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters, the stability of the group with frequent treatment parameter adjustments in accepting the treatment plan is determined; When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument is evaluated by analyzing the complexity of the sensor signals collected by the bone trauma treatment instrument during the treatment process; A comprehensive analysis is conducted on the intrinsic matching degree of the treatment plan for bone tissue repair, the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters, and the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument, so as to dynamically adjust the configuration strategy of the treatment parameters of the bone trauma treatment instrument.

2. The intelligent control method of a bone trauma treatment instrument according to claim 1, characterized in that: Based on the patient data set stored in the bone trauma treatment instrument, the patients receiving bone trauma treatment were screened and classified to obtain the group with frequent treatment parameter adjustment, specifically: Extract the treatment data of all patients from the database of the bone trauma treatment instrument; Clean the extracted data to exclude duplicate, invalid or abnormal data; Based on the patient treatment records and parameter change frequency, screening rules are designed to screen the patient group whose treatment parameters are frequently adjusted during the treatment process: for each patient, for each treatment parameter, the adjustment frequency of the parameter in the entire treatment cycle is calculated, and the adjustment frequency is defined as the number of adjustments of the parameter divided by the total duration of the treatment cycle; according to the adjustment frequency of all treatment parameters, different weights are assigned according to their importance to the treatment effect, and the weighted result of the overall adjustment frequency is obtained; A threshold for the overall adjustment frequency is set. If the patient's overall adjustment frequency reaches or exceeds the set threshold, the patient is considered to belong to the group with frequent treatment parameter adjustments.

3. The intelligent control method of a bone trauma treatment instrument according to claim 2, characterized in that: The temporal changes of the treatment regimens of the group with frequent treatment parameter adjustments during the treatment cycle were analyzed to evaluate the intrinsic matching degree of the treatment regimens to bone tissue repair, specifically: Extract the treatment plan data of the group with frequent treatment parameter adjustment during the treatment cycle and establish a time series data set; According to the time dimension of treatment parameters, the time series distribution curve of parameters within the treatment cycle is constructed; Analyze the correlation between the changing trend of parameters in the time series curve and the staged demand for bone tissue repair; Based on correlation analysis, calculate the matching degree index of the contribution of treatment parameters to the repair effect: Based on the matching degree of each treatment parameter, calculate the comprehensive matching coefficient of all treatment parameters to the repair effect: Among them, CMC is the comprehensive matching coefficient; M k is the matching degree of each treatment parameter; Q k is the weight of the kth treatment parameter; n is the total number of treatment parameters.

4. The intelligent control method of a bone trauma treatment instrument according to claim 3, characterized in that: The real-time feedback data of the treatment process of the group with frequent treatment parameter adjustment was analyzed to evaluate the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, specifically: Collect real-time feedback data from the group with frequent treatment parameter adjustments during the treatment process and build a feedback data set; Extract features from feedback data, including physiological signal amplitude, frequency, and response delay; Cluster analysis of feedback characteristics under stimulation of similar treatment parameters to identify response patterns of patient groups; Calculate the discreteness of feedback characteristics and evaluate the response divergence of the frequent treatment parameter adjustment group under the stimulation of similar treatment parameters: Based on the clustering results, calculate the discreteness of feedback characteristics under the stimulation of similar treatment parameters. The calculation formula is: Among them, V x represents the discreteness of the feedback features of the x-th type of treatment parameter stimulation; M represents the total number of feedback features belonging to the x-th type of treatment parameter stimulation in the clustering results; z y represents the actual value of the yth feedback feature data; μ x Represents the average value of the feedback characteristics of the x-th type of treatment parameter stimulation.

5. The intelligent control method of a bone trauma treatment instrument according to claim 4, characterized in that: Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, the stability of the group with frequent treatment parameter adjustment to the treatment plan is judged, specifically: Preset the comprehensive matching coefficient threshold, and compare the comprehensive matching coefficient with the comprehensive matching coefficient threshold: When the comprehensive matching coefficient is greater than the comprehensive matching coefficient threshold, it indicates that the intrinsic matching degree of the treatment plan to bone tissue repair is high; When the comprehensive matching coefficient is less than or equal to the comprehensive matching coefficient threshold, it indicates that the intrinsic matching degree of the treatment plan to bone tissue repair is low; Preset the discreteness threshold and compare the discreteness with the discreteness threshold: When the dispersion is greater than or equal to the dispersion threshold, it means that the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters is large; When the dispersion is less than the dispersion threshold, it means that the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters is low; When the comprehensive matching coefficient is greater than the comprehensive matching coefficient threshold and the dispersion is less than the dispersion threshold, the acceptance stability of the treatment plan by the group with frequent treatment parameter adjustment is high acceptance stability; otherwise, the acceptance stability of the treatment plan by the group with frequent treatment parameter adjustment is low acceptance stability.

6. The intelligent control method of a bone trauma treatment instrument according to claim 5, characterized in that: When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the necessity of improving the diversified regulation strategy of the bone trauma therapeutic instrument is evaluated by analyzing the complexity of the sensor signals collected by the bone trauma therapeutic instrument during the treatment process, specifically: Collect multi-channel sensor signals of the bone trauma treatment device during the treatment process; Preprocess the signal data and extract characteristic signals; Calculate the temporal entropy of each sensor signal to evaluate the necessity of improving the diversified regulation strategy of the bone trauma treatment device: abc , the Shannon entropy formula is used to calculate the time series entropy, the calculation formula is: Among them, E abc represents the temporal entropy value of the a-th channel, the b-th time point, and the c-th signal type; p d represents the probability of the dth value in the time series; m represents the total number of all values ​​in the time series.

7. The intelligent control method of a bone trauma treatment instrument according to claim 6, characterized in that: A comprehensive analysis is conducted on the intrinsic matching degree of the treatment plan to bone tissue repair, the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, and the necessity of improving the diversified regulation strategy of the bone trauma treatment instrument, and the configuration strategy of dynamically adjusting the treatment parameters of the bone trauma treatment instrument is as follows: The comprehensive matching coefficient corresponding to the intrinsic matching degree of the treatment plan for bone tissue repair, the discreteness corresponding to the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameter, and the time series entropy value corresponding to the necessity of the bone trauma treatment instrument to improve the diversified regulation strategy are normalized, and the normalized comprehensive matching coefficient, discreteness and time series entropy value are comprehensively analyzed to calculate the regulation demand coefficient. The calculation formula of the regulation demand coefficient is: CDRI = α*(1-CMC)+β*V x +δ*|E abc |; CDRI represents the control demand coefficient; CMC is the comprehensive matching coefficient; V x Indicates the discreteness; E abc represents the time series entropy value; α, β, δ are the weight coefficients of comprehensive matching coefficient, dispersion and time series entropy value respectively; Preset the control demand coefficient threshold and compare the control demand coefficient with the control demand coefficient threshold: When the control demand coefficient is greater than or equal to the control demand coefficient threshold, it is necessary to dynamically adjust the treatment parameter configuration strategy of the bone trauma treatment instrument, including optimizing the treatment parameter range, adding personalized control strategies, and improving the precision of signal acquisition and processing; When the regulation demand coefficient is less than the regulation demand coefficient threshold, there is no need to dynamically adjust the treatment parameter configuration strategy of the bone trauma treatment device.

8. An intelligent control system for a bone trauma therapeutic apparatus, used to implement the intelligent control method for a bone trauma therapeutic apparatus according to any one of claims 1 to 7, characterized in that: It includes data processing module, timing analysis module, feedback analysis module, acceptance stability judgment module, complexity assessment module and comprehensive control module; Data processing module: based on the patient data set stored in the bone trauma treatment instrument, screen and classify the patients receiving bone trauma treatment to obtain the group with frequent treatment parameter adjustment; Timing analysis module: Analyze the timing changes of treatment plans for groups with frequent treatment parameter adjustments during the treatment cycle to evaluate the intrinsic matching degree of the treatment plans for bone tissue repair; Feedback analysis module: Analyze the real-time feedback data during the treatment process of the group with frequent treatment parameter adjustments, and evaluate the response divergence of the group with frequent treatment parameter adjustments under the stimulation of similar treatment parameters. Acceptance stability judgment module: Based on the intrinsic matching degree of the treatment plan to bone tissue repair and the response divergence of the group with frequent treatment parameter adjustment under the stimulation of the same treatment parameters, the acceptance stability of the group with frequent treatment parameter adjustment to the treatment plan is judged; Complexity evaluation module: When the acceptance stability of the treatment plan for the group with frequent treatment parameter adjustment is low, the complexity of the sensor signals collected by the bone trauma treatment device during the treatment process is analyzed to evaluate the necessity of improving the diversified regulation strategy of the bone trauma treatment device; Comprehensive control module: Comprehensively analyze the intrinsic matching degree of the treatment plan to bone tissue repair, the response divergence of the group with frequent treatment parameter adjustment under the stimulation of similar treatment parameters, and the necessity of improving the diversified control strategy of the bone trauma treatment device, and dynamically adjust the configuration strategy of the treatment parameters of the bone trauma treatment device.

Images