Intelligent parameter regulation method and system for ultrashort wave therapeutic apparatus

Abstract

This invention relates to the field of postpartum body data analysis technology, specifically to a method and system for intelligent parameter control of a shortwave diathermy device. The method involves: acquiring the patient's body data; determining the data stability based on changes in the body data over a period of time; determining the baseline tolerance level based on the point at which the body data reaches stability; determining the tolerance level deviation based on the difference between the baseline tolerance level of each dimension and the overall tolerance level; obtaining a dynamic risk factor by combining the residual terms of the curve-fitted data with the predicted data; acquiring historical patient body data and determining the initial output power based on the similarity between historical patients and the patient to be treated; obtaining the optimal output power by combining the dynamic risk factor; and thereby intelligently controlling the parameters of the shortwave diathermy device. This invention enables the output power of the shortwave diathermy device to closely match the patient's actual condition, preventing discomfort.

Description

Technical Field

[0001] This invention relates to the field of maternal body data analysis technology, specifically to a method and system for intelligent parameter control of an ultra-shortwave therapy device. Background Technology

[0002] Shortwave diathermy is a precision medical electronic instrument that uses electron tube oscillation to generate a high-frequency electric field of ultra-short waves to treat lesions on the patient's body. During the postpartum recovery phase, the mother's immune system and vaginal environment may change, increasing the risk of infection and inflammation. Shortwave diathermy can stimulate local tissues with short waves, promoting blood circulation, improving tissue nutrition, and enhancing metabolism, ultimately reducing inflammation and alleviating postpartum pain. The output power of the shortwave diathermy device is one of its key parameters, directly affecting the treatment effect and patient comfort. Therefore, intelligent control of the device's output power is a crucial issue that needs to be addressed.

[0003] Conventional methods for adjusting the output power of shortwave diathermy devices typically involve monitoring the patient's real-time physical condition data and analyzing the data to determine the magnitude and direction of power adjustments. However, each patient's tolerance to shortwave diathermy varies, and conventional adjustment methods often overlook these individual differences. This results in the output power not accurately matching the patient's actual physical condition, ultimately leading to unstable treatment outcomes. Furthermore, the lack of monitoring of the patient's physical condition makes it easy for parameters to be adjusted untimely, increasing the risk of patient discomfort during treatment. Summary of the Invention

[0004] To address the technical problem that adjusting the output power of a shortwave diathermy device during treatment can lead to mismatches with the patient's actual physical condition, resulting in untimely parameter adjustments and increased risk of patient discomfort, this invention provides an intelligent parameter control method and system for a shortwave diathermy device. The specific technical solution is as follows: An intelligent parameter control method for a shortwave diathermy device, comprising: acquiring body data of the patient at each sampling moment in different dimensions; selecting one dimension of the patient's body data as a reference dimension; selecting a sampling moment within the reference dimension as a reference sampling moment; obtaining the data stability of the reference sampling moment under the reference dimension based on the data change characteristics of the body data in the reference dimension within a preset period; obtaining the stable moment when the reference dimension reaches stability based on the data stability; obtaining the basic tolerance level of the patient in all dimensions based on the number of sampling moments required for each dimension to reach stability and the data change rate; and further determining the patient's tolerance level based on the data stability characteristics of the patient. The tolerance level deviation of the reference dimension for the patient to be treated is obtained by considering the degree of deviation between the baseline tolerance level of the reference dimension and the baseline tolerance levels of all dimensions. Curve fitting is performed on all body data of the patient to be treated in the reference dimension to obtain the data residual term at each sampling time and the predicted body data for a preset number of future sampling times. Based on the data residual term and tolerance level deviation at each sampling time of the reference dimension, as well as the data deviation between the predicted body data and the actual body data, a dynamic risk factor for the reference dimension at the reference sampling time is obtained. Body data of several historical patients at each sampling time in different dimensions are acquired. Based on the similarity between the patient to be treated and all historical patients in all body data of each dimension, and the average output power of historical patients during shortwave therapy, the initial output power of the patient to be treated during treatment is obtained. Based on the initial output power and the dynamic risk factor, the optimal output power at the reference sampling time is obtained. The parameters of the shortwave therapy device are intelligently adjusted based on the optimal output power.

[0005] Furthermore, the data stability includes: the preset period is set to a first number of sampling times between the reference sampling time and the time preceding the reference sampling time; the data stability is obtained according to the data stability calculation formula, which is shown below: ; In the formula, Indicates the sequence number of the reference sampling time; This indicates the stability of the data at the reference sampling time within the reference dimension; This indicates the first number of sampling times included in the preset period; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; This indicates the maximum change in body data within a preset period. This represents an exponential function with the natural constant as its base.

[0006] Furthermore, the method for obtaining the stable moment when the reference dimension reaches stability includes: taking the sampling moment when the data stability level under the reference dimension is not less than a preset first threshold as the stable moment when the reference dimension reaches stability.

[0007] Furthermore, the method for obtaining the baseline tolerance level of the patient to be treated in all dimensions includes: obtaining the baseline tolerance level according to the baseline tolerance level calculation formula, which is shown below: ; In the formula, This indicates the baseline tolerance level of the patient in all dimensions to be treated; This indicates the number of dimensions in the patient's physical data to be treated. Indicates the first The number of sampling times required for each dimension to reach a stable moment; Indicates the first The first dimension before reaching stability Body data at each sampling time; Indicates the first The first dimension before reaching stability Body data at each sampling time; Represents an exponential function with the natural constant as the base; This represents the absolute value function.

[0008] Furthermore, the method for obtaining the tolerance level deviation includes: obtaining the tolerance level deviation according to the tolerance level deviation calculation formula, the tolerance level deviation calculation formula is as follows: ; In the formula, This indicates the tolerance level deviation of the reference dimension for the patient to be treated; This represents the number of sampling times required for the reference dimension to reach a stable state. This indicates the reference dimension before it reaches stability. Body data at each sampling time; This indicates the reference dimension before it reaches stability. Body data at each sampling time; This indicates the baseline tolerance level of the patient in all dimensions to be treated; This represents the maximum value function.

[0009] Furthermore, the method for obtaining the dynamic risk factor includes: obtaining the dynamic risk factor according to the dynamic risk factor calculation formula, which is shown below: ; In the formula, This represents the dynamic risk factor of the reference dimension at the reference sampling time; This represents the number of data residuals after curve fitting of all body data in the reference dimension. The first dimension of the reference dimension One data residual term; This indicates the tolerance level deviation of the reference dimension for the patient to be treated; This indicates the preset number of body data to be predicted; Indicates the first The distance between the predicted body data at a future sampling time and the upper and lower limits of the normal data range; Describes the minimum value function; This represents the set of distances between the predicted body data and the upper and lower limits of the normal data range for a preset number of future sampling times.

[0010] Furthermore, the method for obtaining the initial output power of the patient to be treated during treatment includes: using all dimensions of the patient's body data as a first multidimensional vector; using all dimensions of the body data of each historical patient as each historical multidimensional vector; calculating the cosine similarity between the first multidimensional vector and each historical multidimensional vector; selecting a preset second number of historical multidimensional vectors with the largest cosine similarity as similar multidimensional vectors of the first multidimensional vector; and calculating the average output power of all historical patients corresponding to the preset second number of similar multidimensional vectors during treatment, as the initial output power of the patient to be treated during treatment.

[0011] Furthermore, the method for obtaining the optimal output power includes: obtaining the optimal output power according to the optimal output power calculation formula, the optimal output power calculation formula being as follows: ; In the formula, This indicates the optimal output power for the patient to be treated at the reference sampling time; This indicates the initial output power of the patient during treatment. This indicates the risk factor threshold, which is set by the implementer. This represents the maximum dynamic risk factor value for the patient awaiting treatment.

[0012] A smart parameter control system for an ultra-shortwave therapy device, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the steps of the smart parameter control method for an ultra-shortwave therapy device as described above.

[0013] A computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the above-described intelligent parameter control method for an ultra-shortwave therapy device.

[0014] This invention has the following beneficial effects: This invention acquires the patient's physical data at each sampling moment in different dimensions; because different obstetric patients have different physical reactions to shortwave therapy, which may lead to differences in changes in physical data across different dimensions, the shortwave output power setting needs to be adjusted according to the tolerance of different obstetric patients. Therefore, it is necessary to obtain the patient's baseline tolerance level through their physical performance at the beginning of treatment, which serves as the main basis for adjusting the shortwave output power; the stronger the patient's baseline tolerance level, the shorter the time required for the physical data to reach a stable state. Therefore, the stability of the patient's data at each sampling moment in each dimension is analyzed first; after obtaining the stability of the data at each sampling moment, it is necessary to determine at which sampling moment each dimension reaches stability, obtaining the stable moment when the reference dimension reaches stability; based on the number of sampling moments required for each dimension to reach stability and the rate of data change, the baseline tolerance level of the patient in all dimensions is obtained; because the patient's baseline tolerance level is adjusted according to the patient's physical performance at the beginning of treatment, the basic ... Because patients react differently to physiological stimuli corresponding to different dimensions, the tolerance level deviation of each dimension for the patient to be treated is analyzed. Since the larger the overall data residual term at all sampling times, and the larger the tolerance level deviation of the reference dimension, the higher the possibility of unstable changes in the body data of that dimension. Furthermore, the closer the predicted body data of the reference dimension is to the upper and lower limits of the normal data range, the higher the possibility of discomfort caused by the shortwave diathermy. Therefore, the dynamic risk factors of each dimension of the patient to be treated at the reference sampling time are analyzed by combining the residual terms of the predicted body data and all body data. To improve the accuracy and safety of the operation, historical patients most similar to the current patient in terms of treatment needs and health status are matched, and the initial output power of the current patient is determined using the shortwave diathermy usage data of these patients. After obtaining the dynamic risk factors of the body data for each dimension, the dimension with the highest risk is selected, and the optimal output power at the reference sampling time is calculated, thus completing the intelligent adjustment of the shortwave diathermy parameters. This invention enables the output power of the shortwave diathermy to match the actual situation of the patient, without causing discomfort. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 The flowchart illustrates a method for intelligent parameter control of an ultra-shortwave therapy device according to an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent parameter control method and system for an ultra-shortwave therapy device proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent parameter control method and system for an ultra-shortwave therapy device provided by this invention.

[0020] Please see Figure 1 This invention illustrates an intelligent parameter control method for an ultra-shortwave therapy device provided by an embodiment of the present invention. The method includes: step S1: acquiring the body data of the patient to be treated at each sampling time in different dimensions.

[0021] This invention is mainly applied to the scenario of parameter adjustment when using a shortwave diathermy device to treat obstetric patients. In order to adjust the parameters of the shortwave diathermy device, it is first necessary to analyze the patient's physical data. Since relevant personnel will refer to multiple dimensions of the patient's physical data when operating the shortwave diathermy device, such as the patient's heart rate, blood pressure, body temperature and muscle tension, this invention acquires the patient's physical data at each sampling time in different dimensions.

[0022] In this embodiment of the invention, sensors, monitoring devices and other equipment are used to collect four dimensions of body data of the patient to be treated during the ultra-shortwave therapy process: heart rate, blood pressure, body temperature and muscle tension. It should be noted that the dimensions can be set by the user and are not limited here.

[0023] The sampling time is set to 1 second, and the sampling time can be set by the user; there are no restrictions here.

[0024] To facilitate subsequent operations, the obtained body data will be standardized to unify the data scale. It should be noted that the data standardization methods are well-known to those skilled in the art and are not limited here.

[0025] Step S2: Select any dimension of the patient's body data as a reference dimension; select any sampling time in the reference dimension as a reference sampling time; obtain the data stability of the reference sampling time under the reference dimension based on the data change characteristics of the body data of the reference dimension within a preset period; obtain the stable time when the reference dimension reaches stability based on the data stability; obtain the basic tolerance level of all dimensions of the patient to be treated based on the number of sampling times required for each dimension to reach stability and the data change rate.

[0026] Because different obstetric patients react differently to shortwave diathermy, such as skin temperature stimulation and muscle relaxation, each patient has varying tolerance levels. This can lead to differences in variations in different dimensions of bodily data. Therefore, the output power of the shortwave diathermy needs to be adjusted according to the tolerance of different obstetric patients to balance treatment effectiveness and comfort. However, patient tolerance is influenced by various factors and often lacks a fixed universal index, instead changing dynamically. Therefore, it is necessary to first obtain the patient's baseline tolerance level through their physical performance at the beginning of treatment, which serves as the primary basis for adjusting the output power of the shortwave diathermy. The stronger the patient's baseline tolerance level, the shorter the time required for bodily data to reach a stable state. Therefore, this embodiment of the invention first analyzes the stability of the patient's data at each sampling time in each dimension.

[0027] Preferably, in one embodiment of the present invention, the data stability includes: the data stability at each sampling time can be analyzed by the changes in body data over a period prior to that sampling time; therefore, the preset period is set to a reference sampling time and a first number of sampling times prior to the reference sampling time. In one embodiment of the present invention, the first number is set to 10. It should be noted that the first number can be set arbitrarily and is not limited here. Furthermore, in this embodiment of the present invention, the reference sampling time is the sampling time at which the most recently acquired body data was obtained, and the following steps are all performed according to this provision.

[0028] The data stability is obtained according to the data stability calculation formula, which is shown below: ; In the formula, Indicates the sequence number of the reference sampling time; This indicates the stability of the data at the reference sampling time within the reference dimension; This indicates the first number of sampling times included in the preset period; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; This indicates the maximum change in body data within a preset period. This represents an exponential function with the natural constant as its base.

[0029] In the formula for calculating data stability, the average difference in the amount of change in body data between the reference sampling time and each previous sampling time within the preset period is used. The smaller the value, the smaller the data change in the reference dimension over the preset period before the reference sampling time, and the greater the stability of the data at the reference sampling time; the ratio between the change in body data over the preset period and the maximum change in the data of the reference dimension. The smaller the value, the smaller the change in body data within the preset period, and the greater the stability of the data at the reference sampling time.

[0030] After obtaining the data stability at each sampling time, it is necessary to determine at which sampling time each dimension reaches stability. Preferably, in one embodiment of the present invention, the method for obtaining the stable time when the reference dimension reaches stability includes: taking the sampling time where the data stability of the reference dimension is not less than a preset first threshold as the stable time when the reference dimension reaches stability. In one embodiment of the present invention, the preset first threshold is set to 0.85. It should be noted that the preset first threshold can be set arbitrarily and is not limited here.

[0031] Based on the number of sampling times required for each dimension to reach a steady state and the rate of data change, the baseline tolerance level of all dimensions of the patient to be treated is obtained.

[0032] Preferably, in one embodiment of the present invention, the method for obtaining the baseline tolerance level includes: obtaining the baseline tolerance level according to a baseline tolerance level calculation formula, wherein the baseline tolerance level calculation formula is as follows: ; In the formula, This indicates the baseline tolerance level of the patient in all dimensions to be treated; This indicates the number of dimensions in the patient's physical data to be treated. Indicates the first The number of sampling times required for each dimension to reach a stable moment; Indicates the first The first dimension before reaching stability Body data at each sampling time; Indicates the first The first dimension before reaching stability Body data at each sampling time; Represents an exponential function with the natural constant as the base; This represents the absolute value function.

[0033] In the formula for calculating the baseline tolerance level, the first... The number of sampling times required for each dimension to reach a stable time. The fewer the number of seconds, the shorter the time required for the patient's body to reach stability. At this point, the patient is in the [number]th [day / month / time - context needed]. The higher the baseline tolerance level in each dimension, and the smaller the difference in body data between each two adjacent sampling times before reaching a steady state, the faster the average data change rate before reaching a steady state. The smaller, the higher the number of... The slower the change in each dimension of body data, the more likely it is that the [missing information] dimension is changing. The higher the baseline tolerance level of each dimension of the body data, the better; by analyzing each dimension, the baseline tolerance level of the patient to be treated across all dimensions can be obtained.

[0034] Step S3: Based on the deviation between the baseline tolerance level of the reference dimension of the patient to be treated and the baseline tolerance levels of all dimensions, obtain the tolerance level deviation of the reference dimension of the patient to be treated; perform curve fitting on all body data of the reference dimension of the patient to be treated to obtain the data residual term at each sampling time in the reference dimension and the predicted body data at a preset number of future sampling times; based on the data residual term and tolerance level deviation at each sampling time of the reference dimension, as well as the data deviation between the predicted body data and the body data, obtain the dynamic risk factor of the reference dimension at the reference sampling time.

[0035] Since patients undergoing treatment respond differently to physiological stimuli corresponding to each dimension, for example, postpartum patients with higher baseline tolerance levels are more sensitive to temperature stimuli and are more likely to experience body temperature discomfort during treatment, this embodiment of the invention analyzes the tolerance level deviation of patients undergoing treatment for each dimension.

[0036] Preferably, in one embodiment of the present invention, the method for obtaining the tolerance level deviation includes: obtaining the tolerance level deviation according to a tolerance level deviation calculation formula, wherein the tolerance level deviation calculation formula is as follows: ; In the formula, This indicates the tolerance level deviation of the reference dimension for the patient to be treated; This represents the number of sampling times required for the reference dimension to reach a stable state. This indicates the reference dimension before it reaches stability. Body data at each sampling time; This indicates the reference dimension before it reaches stability. Body data at each sampling time; This indicates the baseline tolerance level of the patient in all dimensions to be treated; This represents the maximum value function.

[0037] In the formula for calculating tolerance level deviation, the tolerance level of the reference dimension can be derived from... This is represented as a percentage of the baseline tolerance level of all dimensions. The larger the proportion, the more... The smaller, and A value greater than 0 indicates a smaller deviation in tolerance levels.

[0038] The least squares method is used to perform curve fitting on all body data of the patient's reference dimension to obtain the data residual term at each sampling time in the reference dimension. Then, the body data at future sampling times is predicted to obtain a preset number of predicted body data at future sampling times. In one embodiment of the invention, the preset number is set to 15. It should be noted that in other embodiments of the invention, the preset number can be set arbitrarily and is not limited here. Furthermore, the least squares method is a well-known technique among those skilled in the art and will not be described in detail here.

[0039] Since a larger overall data residual term across all sampling times, and a greater deviation in the tolerance level of the reference dimension, indicates a higher likelihood of unstable changes in the body data for that dimension; and the closer the predicted body data for the reference dimension is to the upper and lower limits of the normal data range, the higher the likelihood that the shortwave diathermy will cause discomfort to the patient being treated. Therefore, in this embodiment of the invention, the dynamic risk factors for each dimension of the patient being treated at the reference sampling time are analyzed by combining the residual terms of the predicted body data and all body data.

[0040] Preferably, in one embodiment of the present invention, the method for obtaining dynamic risk factors includes: obtaining the dynamic risk factors according to a dynamic risk factor calculation formula, wherein the dynamic risk factor calculation formula is as follows: ; In the formula, This represents the dynamic risk factor of the reference dimension at the reference sampling time; This represents the number of data residuals after curve fitting of all body data in the reference dimension. The first dimension of the reference dimension One data residual term; This indicates the tolerance level deviation of the reference dimension for the patient to be treated; This indicates the preset number of body data to be predicted; Indicates the first The distance between the predicted body data at a future sampling time and the upper and lower limits of the normal data range; Describes the minimum value function; This represents the set of distances between the predicted body data and the upper and lower limits of the normal data range for a preset number of future sampling times.

[0041] In the dynamic risk factor calculation formula, the larger the overall data residual term at all sampling times, and the larger the tolerance level deviation of the reference dimension, the more likely it is that... The larger the value, the higher the likelihood of unstable changes in the body data for that dimension, and the greater the dynamic risk factor of the reference dimension at the reference sampling time. The normal data range can be directly obtained through the instruction manual of the shortwave diathermy device, etc. The smaller the distance between the predicted body data and the upper and lower limits of the normal data range, the closer the predicted body data is to the extreme value of the normal data range. A preset number of minimum distances between the predicted body data and the upper and lower limits of the normal data range are selected. , The smaller the value, the more abnormal the predicted physical data will be, and the greater the dynamic risk factor of the reference dimension at the reference sampling time.

[0042] Step S4: Acquire body data of several historical patients at each sampling time in different dimensions; based on the similarity between the body data of the patient to be treated and all historical patients in each dimension, and the average output power of historical patients during shortwave therapy, obtain the initial output power of the patient to be treated during treatment; based on the initial output power and the dynamic risk factor, obtain the optimal output power at the reference sampling time; intelligently adjust the parameters of the shortwave therapy device based on the optimal output power.

[0043] When treating postpartum patients with shortwave diathermy, the initial power is typically set low and gradually increased to the required level, with the patient's response observed and adjustments made accordingly. However, this method is highly susceptible to subjective human factors, leading to judgment or operational errors and low treatment efficiency. To improve operational accuracy and safety, and to draw inspiration from the treatment experiences of historical patients, this invention identifies historical patients whose treatment needs and health conditions are most similar to the current patient, and uses their shortwave diathermy usage data to determine the initial output power for the current patient.

[0044] Preferably, in one embodiment of the present invention, the method for obtaining the initial output power of the patient to be treated during treatment includes: taking all dimensions of the patient's body data as a first multidimensional vector; taking all dimensions of the body data of each historical patient as each historical multidimensional vector; calculating the cosine similarity between the first multidimensional vector and each historical multidimensional vector; and selecting a preset second number of historical multidimensional vectors with the largest cosine similarity as similar multidimensional vectors of the first multidimensional vector.

[0045] The average output power of all historical patients corresponding to a predetermined second number of similar multidimensional vectors during treatment is calculated and used as the initial output power of the patient to be treated during treatment. In this embodiment of the invention, the predetermined second number is set to 3. It should be noted that the predetermined second number can be set arbitrarily and is not limited here.

[0046] After obtaining the dynamic risk factors for each dimension of body data, the dimension with the highest risk is selected, and the optimal output power at the reference sampling time is calculated.

[0047] Preferably, in this embodiment of the invention, the method for obtaining the optimal output power includes: obtaining the optimal output power according to the optimal output power calculation formula, wherein the optimal output power calculation formula is as follows: ; In the formula, This indicates the optimal output power for the patient to be treated at the reference sampling time; This indicates the initial output power of the patient during treatment. The risk factor threshold is set by the implementer. In this embodiment of the invention, the risk factor threshold is set to 0.8. This represents the maximum dynamic risk factor value of the patient to be treated. The dimension corresponding to the highest risk.

[0048] In the formula for calculating the optimal output power, when the maximum dynamic risk factor is lower than the risk factor threshold, the output power of the ultra-shortwave therapy device should be appropriately increased; when the maximum dynamic risk factor is higher than the risk factor threshold, the initial output power may cause discomfort to the patient being treated, so the output power of the ultra-shortwave therapy device should be appropriately reduced.

[0049] At this point, the intelligent control of the parameters of the ultra-shortwave therapy device is complete.

[0050] In summary, the following steps are taken: First, acquire body data of the patient to be treated at each sampling time across different dimensions. Second, randomly select one dimension of the patient's body data as a reference dimension. Third, randomly select a sampling time within the reference dimension as a reference sampling time. Fourth, based on the data change characteristics of the body data in the reference dimension within a preset period, obtain the data stability at the reference sampling time under the reference dimension. Fifth, based on the data stability, obtain the stable time when the reference dimension reaches stability. Sixth, based on the number of sampling times required for each dimension to reach stability and the rate of data change, obtain the baseline tolerance level of all dimensions of the patient to be treated. Seventh, based on the deviation between the baseline tolerance level of the reference dimension and the baseline tolerance levels of all dimensions, obtain the tolerance level deviation of the reference dimension of the patient to be treated. Finally, analyze all body data of the patient to be treated in the reference dimension. Curve fitting is used to obtain the data residuals at each sampling time in the reference dimension and the predicted body data for a preset number of future sampling times. Based on the data residuals and tolerance level deviations at each sampling time in the reference dimension, as well as the data deviation between the predicted body data and the actual body data, a dynamic risk factor for the reference dimension at the reference sampling time is obtained. Body data from several historical patients at each sampling time in different dimensions are acquired. Based on the similarity between the body data of the patient to be treated and all historical patients in each dimension, and the average output power of historical patients during shortwave therapy, the initial output power of the patient to be treated during treatment is obtained. Based on the initial output power and the dynamic risk factor, the optimal output power at the reference sampling time is obtained. The parameters of the shortwave therapy device are intelligently adjusted based on the optimal output power.

[0051] An embodiment of the present invention also provides an intelligent control system for parameters of an ultra-shortwave therapy device. The system includes a memory, a processor, and a computer program. The memory is used to store the corresponding computer program, and the processor is used to run the corresponding computer program. When the computer program runs in the processor, it can implement the methods described in steps S1-S4.

[0052] The third objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned intelligent parameter control method for an ultra-shortwave therapy device.

[0053] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0054] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for intelligent parameter control of a shortwave diathermy device, characterized in that, The method includes: acquiring body data of the patient to be treated at each sampling time in different dimensions; randomly selecting one dimension of the patient's body data as a reference dimension; randomly selecting a sampling time in the reference dimension as a reference sampling time; obtaining the data stability of the reference sampling time under the reference dimension based on the data change characteristics of the body data of the reference dimension within a preset period; obtaining the stable time when the reference dimension reaches stability based on the data stability; obtaining the baseline tolerance level of all dimensions of the patient to be treated based on the number of sampling times required for each dimension to reach stability and the data change rate; obtaining the tolerance level deviation of the reference dimension of the patient to be treated based on the deviation between the baseline tolerance level of the reference dimension and the baseline tolerance level of all dimensions; and performing... Curve fitting is performed to obtain the data residuals at each sampling time in the reference dimension and the predicted body data for a preset number of future sampling times. Based on the data residuals and tolerance level deviations at each sampling time in the reference dimension, as well as the data deviations between the predicted body data and the actual body data, a dynamic risk factor for the reference dimension at the reference sampling time is obtained. Body data of several historical patients at each sampling time in different dimensions are acquired. Based on the similarity between the body data of the patient to be treated and all historical patients in each dimension, and the average output power of historical patients during shortwave therapy, the initial output power of the patient to be treated during treatment is obtained. Based on the initial output power and the dynamic risk factor, the optimal output power at the reference sampling time is obtained. The parameters of the shortwave therapy device are intelligently adjusted based on the optimal output power.

2. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The data stability level includes: the preset period is set to a first number of sampling times between the reference sampling time and the reference sampling time; the data stability level is obtained according to the data stability level calculation formula, which is as follows: ； In the formula, Indicates the sequence number of the reference sampling time; This indicates the stability of the data at the reference sampling time within the reference dimension; This indicates the first number of sampling times included in the preset period; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; Indicates from the first The amount of change in body data between a sampling time and a reference sampling time; This indicates the maximum change in body data within a preset period. This represents an exponential function with the natural constant as its base.

3. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The method for obtaining the stable moment when the reference dimension reaches stability includes: taking the sampling moment when the data stability under the reference dimension is not less than a preset first threshold as the stable moment when the reference dimension reaches stability.

4. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The method for obtaining the baseline tolerance level of the patient to be treated in all dimensions includes: obtaining the baseline tolerance level according to the baseline tolerance level calculation formula, which is shown below: ; In the formula, This indicates the baseline tolerance level of the patient in all dimensions to be treated; This indicates the number of dimensions in the patient's physical data to be treated. Indicates the first The number of sampling times required for each dimension to reach a stable moment; Indicates the first The first dimension before reaching stability Body data at each sampling time; Indicates the first The first dimension before reaching stability Body data at each sampling time; Represents an exponential function with the natural constant as its base; This represents the absolute value function.

5. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The method for obtaining the tolerance level deviation includes: obtaining the tolerance level deviation according to the tolerance level deviation calculation formula, which is shown below: ； In the formula, This indicates the tolerance level deviation of the reference dimension for the patient to be treated; This represents the number of sampling times required for the reference dimension to reach a stable state. This indicates the reference dimension before it reaches stability. Body data at each sampling time; This indicates the reference dimension before it reaches stability. Body data at each sampling time; This indicates the baseline tolerance level of the patient in all dimensions to be treated; This represents the maximum value function.

6. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The method for obtaining the dynamic risk factor includes: obtaining the dynamic risk factor according to the dynamic risk factor calculation formula, which is shown below: ； In the formula, This represents the dynamic risk factor of the reference dimension at the reference sampling time; This represents the number of data residuals after curve fitting of all body data in the reference dimension. The first dimension of the reference dimension One data residual term; This indicates the tolerance level deviation of the reference dimension for the patient to be treated; This indicates the preset number of body data to be predicted; Indicates the first The distance between the predicted body data at a future sampling time and the upper and lower limits of the normal data range; Describes the minimum value function; This represents the set of distances between the predicted body data and the upper and lower limits of the normal data range for a preset number of future sampling times.

7. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The method for obtaining the initial output power of the patient to be treated during treatment includes: taking all dimensions of the patient's body data as a first multidimensional vector; taking all dimensions of the body data of each historical patient as each historical multidimensional vector; calculating the cosine similarity between the first multidimensional vector and each historical multidimensional vector; selecting a preset second number of historical multidimensional vectors with the largest cosine similarity as similar multidimensional vectors of the first multidimensional vector; and calculating the average output power of all historical patients corresponding to the preset second number of similar multidimensional vectors during treatment, as the initial output power of the patient to be treated during treatment.

8. The intelligent parameter control method for a shortwave diathermy device according to claim 1, characterized in that, The method for obtaining the optimal output power includes: obtaining the optimal output power according to the optimal output power calculation formula, which is shown below: ； In the formula, This indicates the optimal output power for the patient to be treated at the reference sampling time; This indicates the initial output power of the patient during treatment. This indicates the risk factor threshold, which is set by the implementer. This represents the maximum dynamic risk factor value for the patient awaiting treatment.

9. A smart parameter control system for a shortwave diathermy device, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent parameter control method for an ultra-shortwave therapy device as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent parameter control method for an ultra-shortwave therapy device as described in any one of claims 1 to 8.

Images