Machine learning based implant sensor regulatory data analysis method and system

Abstract

This application provides a machine learning-based data analysis method and system for implantable sensor regulation, relating to the field of implantation regulation application technology. By introducing an unbalanced set of reference optimization parameters, the method expands the parameter search space, explores and applies previously overlooked potential optimization schemes, and effectively reduces the loss of regulation effect. Specifically, by comprehensively considering multiple balanced and unbalanced combinations of reference optimization parameters, personalized regulation can be performed for different patients' physiological characteristics and disease states, significantly improving treatment outcomes. The results of each regulation optimization are used as training samples for machine learning, enabling online learning and updating of machine learning, continuously improving its predictive accuracy and generalization ability, and allowing it to better adapt to changes in patients' physiological states. This provides a scientific and quantitative basis for regulation optimization, enhances the automation and intelligence of the entire optimization process, and opens up new possibilities for the application of implantable medical devices.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of implant regulation and control, in particular to an implant sensor regulation and control data analysis method and system based on machine learning. BACKGROUND

[0002] With the rapid development of medical technology, implantable medical devices are increasingly widely used in clinical medicine, especially in the field of neural regulation, such as the treatment of Parkinson's disease, epilepsy and other nervous system diseases. As a key component of these devices, implantable sensors can monitor patients' physiological indicators in real time, providing important diagnostic and treatment basis for doctors. However, how to effectively regulate these implantable sensors to achieve the best treatment effect is an important challenge faced by the medical community and the engineering technology field.

[0003] Traditional implantable sensor regulation methods mainly rely on doctors' experience or pre-set fixed parameters, and these methods often have unstable regulation effects, poor adaptability, and difficulty in coping with individual differences. SUMMARY

[0004] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the embodiments of the present application is to provide an implant sensor regulation and control data analysis method and system based on machine learning.

[0005] According to one aspect of the present application, an implant sensor regulation and control data analysis method based on machine learning is provided, the method comprising:

[0006] Obtaining implant sensor regulation signal data to be optimized, and obtaining X reference optimization parameter groups; there is an unbalanced correlation between the reference optimization parameters of at least one reference optimization parameter group in the X reference optimization parameter groups; X is a positive integer greater than 1;

[0007] Determining the regulation effect loss required for regulating and optimizing the target implant sensor regulation signal based on the X reference optimization parameter groups under the target implantable neural regulation state label, generating X regulation effect losses; the target implant sensor regulation signal belongs to the implant sensor regulation signal data;

[0008] Based on the X regulation effect losses, extracting a target optimization parameter group of the implant sensor regulation signal data under the target implantable neural regulation state label from the X reference optimization parameter groups;

[0009] Based on the target optimization parameter group under the target implantable neural regulation state label, regulating and optimizing the implant sensor regulation signal in the implant sensor regulation signal data, and generating a target regulation and optimization result of the implant sensor regulation signal data.

[0010] In a possible implementation of the first aspect, the X reference optimization parameter groups include a first reference optimization parameter group and a second reference optimization parameter group, reference optimization parameter pairs in the first reference optimization parameter group present unbalanced correlations; wherein the reference optimization parameter pairs in the first reference optimization parameter group are determined based on different reference optimization parameters in a same reference optimization parameter range; or the reference optimization parameter pairs in the first reference optimization parameter group are determined based on reference optimization parameters in different reference optimization parameter ranges, the optimization parameters in the different reference optimization parameter ranges are different;

[0011] reference optimization parameter pairs in the second reference optimization parameter group present balanced correlations, wherein the reference optimization parameter pairs in the second reference optimization parameter group are determined based on a same reference optimization parameter in a same reference optimization parameter range.

[0012] In a possible implementation of the first aspect, the X reference optimization parameter groups are obtained by:

[0013] determining a control effect loss required for control optimization of the target implanted sensor control signal under the target implanted neuromodulation state label according to a balanced optimization parameter group Ya, the balanced optimization parameter group Ya belongs to Y balanced optimization parameter groups, the balanced optimization parameter groups in the Y balanced optimization parameter groups cover reference optimization parameter pairs that present balanced correlations, Y is a positive integer greater than 1, and a is a positive integer not less than Y;

[0014] if the Y balanced optimization parameter groups corresponding to Y control effect losses are obtained, then a basic optimization parameter group of the target implanted sensor control signal under the target implanted neuromodulation state label is extracted from the Y balanced optimization parameter groups based on the Y control effect losses;

[0015] updating the basic optimization parameter group based on the variation amplitudes in the variation amplitude sequence to generate the X reference optimization parameter groups.

[0016] In a possible implementation of the first aspect, the X reference optimization parameter groups include a third reference optimization parameter group; reference optimization parameter pairs in the third reference optimization parameter group present unbalanced correlations;

[0017] one reference optimization parameter in the third reference optimization parameter group is obtained by updating a first basic optimization parameter in the basic optimization parameter group based on a first variation amplitude in the variation amplitude sequence;

[0018] Another reference optimization parameter in the third reference optimization parameter group is obtained by updating a second base optimization parameter in the base optimization parameter group based on a second variation amplitude in the variation amplitude sequence.

[0019] In a possible implementation of the first aspect, the X reference optimization parameter groups further include a fourth reference optimization parameter group; reference optimization parameters in the fourth reference optimization parameter group present balanced correlations between pairs of reference optimization parameters;

[0020] One reference optimization parameter in the fourth reference optimization parameter group is obtained by updating the first base optimization parameter based on a third variation amplitude in the variation amplitude sequence;

[0021] Another reference optimization parameter in the fourth reference optimization parameter group is obtained by updating the second base optimization parameter based on an inverse of the third variation amplitude.

[0022] In a possible implementation of the first aspect, the determining of the control effect loss required for the control optimization of the target implant sensor control signal based on the X reference optimization parameter groups respectively under the target implantable neural regulation state label includes:

[0023] Obtaining a target control signal node in the target implant sensor control signal, determining a candidate signal node of the target control signal node under the target implantable neural regulation state label from the target implant sensor control signal;

[0024] Determining a control deviation degree between a control parameter of the target control signal node and a control parameter of the candidate signal node;

[0025] Comparing the control deviation degree with the X reference optimization parameter groups respectively to generate comparison information corresponding to the X reference optimization parameter groups respectively;

[0026] Determining a corresponding control optimization knowledge point of the target control signal node under a reference optimization parameter group Yb based on the comparison information corresponding to the reference optimization parameter group Yb; the reference optimization parameter group Yb belongs to the X reference optimization parameter groups, b is a positive integer not greater than X, and until the corresponding control optimization knowledge points of the target control signal node under the X reference optimization parameter groups are obtained respectively;

[0027] Based on the X control optimization knowledge points obtained, control optimization processing is performed on the control parameters of the target control signal node respectively to generate X control optimization results;

[0028] Based on the X regulation optimization results, determine the regulation effect loss required for regulating and optimizing the target implant sensor regulation signal under the X reference optimization parameter groups respectively under the target implantable neural regulation state label, and generate X regulation effect losses.

[0029] In a possible implementation of the first aspect, the candidate signal nodes include a first candidate signal node and a second candidate signal node, and the regulation deviation includes a first regulation deviation and a second regulation deviation. The first regulation deviation is the regulation deviation between the regulation parameter of the first candidate signal node and the regulation parameter of the target regulation signal node, and the second regulation deviation is the regulation deviation between the regulation parameter of the second candidate signal node and the regulation parameter of the target regulation signal node.

[0030] The comparison of the regulation deviation with the X reference optimization parameter groups respectively generates corresponding comparison information of the X reference optimization parameter groups, including:

[0031] Obtain the number of regulation optimization knowledge points under the target implantable neural regulation state label, and obtain the first comparison information between the first regulation deviation and the reference optimization parameter group Yb based on the number of regulation optimization knowledge points under the target implantable neural regulation state label.

[0032] Obtain the second comparison information between the second regulation deviation and the reference optimization parameter group Yb based on the number of regulation optimization knowledge points under the target implantable neural regulation state label.

[0033] The first comparison information and the second comparison information are used as the corresponding comparison information of the reference optimization parameter group Yb, and the X reference optimization parameter groups are obtained respectively.

[0034] In a possible implementation of the first aspect, the determination of the corresponding regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter group Yb based on the corresponding comparison information of the reference optimization parameter group Yb includes:

[0035] Determine the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb based on the first comparison information.

[0036] Determine the second knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb based on the second comparison information.

[0037] Determine the regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter group Yb based on the first knowledge point mapping value and the second knowledge point mapping value.

[0038] In a possible implementation of the first aspect, the reference optimization parameter set Yb includes a first reference optimization parameter and a second reference optimization parameter, the first reference optimization parameter is smaller than the second reference optimization parameter, and the regulation optimization knowledge points include four knowledge points.

[0039] The first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb is determined based on the first comparison information, including:

[0040] If the first comparison information indicates that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is smaller than the first reference optimization parameter, a first mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb.

[0041] If the first comparison information indicates that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is not smaller than the first reference optimization parameter, a second mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb.

[0042] If the first comparison information indicates that the first regulation deviation degree is not a decrease deviation, and the first regulation deviation degree is smaller than the second reference optimization parameter, a third mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb.

[0043] If the first comparison information indicates that the first regulation deviation degree is an increase deviation, and the first regulation deviation degree is not smaller than the second reference optimization parameter, a fourth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb. The first mapping value, the second mapping value, the third mapping value, and the fourth mapping value are in mapping relationship with the four regulation optimization knowledge points respectively.

[0044] In a possible implementation of the first aspect, the reference optimization parameter set Yb includes a first reference optimization parameter and a second reference optimization parameter, the first reference optimization parameter is smaller than the second reference optimization parameter, and the regulation optimization knowledge points include three knowledge points.

[0045] The first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb is determined based on the first comparison information, including:

[0046] If the first comparison information represents that the first regulation deviation degree is less than the first reference optimization parameter, a fifth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb.

[0047] If the first comparison information represents that the first regulation deviation degree is greater than the second reference optimization parameter, a sixth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb.

[0048] If the first comparison information represents that the first regulation deviation degree is equal to the first reference optimization parameter, or the first regulation deviation degree is equal to the second reference optimization parameter, a seventh mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb.

[0049] If the first comparison information represents that the first regulation deviation degree is greater than the first reference optimization parameter, and the first regulation deviation degree is less than the second reference optimization parameter, a seventh mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; the fifth mapping value, the sixth mapping value, and the seventh mapping value are in mapping relationship with three regulation optimization knowledge points respectively.

[0050] For example, in a possible implementation of the first aspect, the regulation optimization processing is performed on the regulation parameters of the target regulation signal node based on the X regulation optimization knowledge points to generate X regulation optimization results, including:

[0051] The X regulation optimization knowledge points correspond to X regulation optimization amounts, which are queried from a regulation optimization amount template to generate the X regulation optimization amounts.

[0052] The regulation optimization processing is performed on the regulation parameters of the target regulation signal node based on the X regulation optimization amounts to generate the X regulation optimization results.

[0053] For example, in a possible implementation of the first aspect, the regulation effect loss required for regulating and optimizing the target implant sensor regulation signal according to the X reference optimization parameter groups under the target implantable neural regulation state label is determined based on the X regulation optimization results to generate X regulation effect losses, including:

[0054] determine a control error rate of the target implantable sensor control signal under the reference optimization parameter set Yb according to the target implantable sensor control signal and an initial control signal corresponding to the target implantable sensor control signal, the reference optimization parameter set Yb belonging to the X reference optimization parameter sets, b being a positive integer not greater than X, the control optimization result Yb being a control optimization result obtained by performing control optimization on the target implantable sensor control signal according to the reference optimization parameter set Yb, and the target implantable sensor control signal being obtained by reconstructing an encoded feature of the initial control signal;

[0055] obtain an efficiency evaluation index of the reference optimization parameter set Yb, and determine a control effect loss of the target implantable sensor control signal under the reference optimization parameter set Yb according to the control error rate of the target implantable sensor control signal under the reference optimization parameter set Yb and the efficiency evaluation index of the reference optimization parameter set Yb, until the X control effect losses corresponding to the target implantable sensor control signal under the X reference optimization parameter sets are obtained, and X control effect losses are generated.

[0056] For example, in a possible implementation of the first aspect, the extracting the target optimization parameter set of the implantable sensor control signal data under the target implantable neural control state label from the X reference optimization parameter sets based on the X control effect losses comprises:

[0057] extracting, from the X reference optimization parameter sets, a reference optimization parameter set with the minimum control effect loss based on the X control effect losses.

[0058] outputting the extracted reference optimization parameter set as the target optimization parameter set of the implantable sensor control signal data under the target implantable neural control state label.

[0059] For example, in a possible implementation of the first aspect, the number of the target implantable neural control state labels is Z, and Z is a positive integer.

[0060] the control optimization on the implantable sensor control signal in the implantable sensor control signal data based on the target optimization parameter set under the target implantable neural control state label to generate a target control optimization result of the implantable sensor control signal data, comprising:

[0061] The control parameters of the implant sensor control signal of the implant sensor control signal data are controlled and optimized based on the target optimization parameter group under the target implantable neuromodulation state label Kc, to generate a control optimization result of the implant sensor control signal of the implant sensor control signal data under the target implantable neuromodulation state label Kc; the target implantable neuromodulation state label Kc belongs to Z target implantable neuromodulation state labels, and c is a positive integer not greater than Z;

[0062] Based on the control optimization result of the implant sensor control signal of the implant sensor control signal data under the target implantable neuromodulation state label Kc, the control effect loss of the implant sensor control signal of the implant sensor control signal data under the target implantable neuromodulation state label Kc is determined.

[0063] If the Z control effect losses corresponding to the Z target implantable neuromodulation state labels are obtained, the control optimization result corresponding to the minimum control effect loss in the Z control effect losses is output as the target control optimization result of the implant sensor control signal of the implant sensor control signal data.

[0064] For example, in a possible implementation of the first aspect, the method further includes:

[0065] The first optimization parameter and the second optimization parameter in the target optimization parameter group under the target implantable neuromodulation state label are loaded to the controller, and the controller is used to determine the target control optimization result of the implant sensor control signal data based on the first optimization parameter and the second optimization parameter in the target optimization parameter group under the target implantable neuromodulation state label.

[0066] For example, in a possible implementation of the first aspect, the loading of the first optimization parameter and the second optimization parameter in the target optimization parameter group under the target implantable neuromodulation state label to the controller includes:

[0067] The first parameter tag code of the first evaluation index of the first optimization parameter in the first reference optimization parameter range and the second parameter tag code of the second evaluation index of the second optimization parameter in the second reference optimization parameter range are obtained;

[0068] The first parameter tag code corresponding to the first optimization parameter and the second parameter tag code corresponding to the second optimization parameter are loaded to the controller.

[0069] For example, in a possible implementation form of the first aspect, the loading the first optimization parameter and the second optimization parameter in the target optimization parameter group under the target implantable neuromodulation state tag to the modulator comprises:

[0070] obtaining a first parameter tag code of a first evaluation index of the first optimization parameter in a first reference optimization parameter range, and a second parameter tag code of a second evaluation index of the second optimization parameter in a second reference optimization parameter range;

[0071] obtaining a code deviation value between the first parameter tag code and the second parameter tag code;

[0072] loading the first parameter tag code and the code deviation value to the modulator, or loading the second parameter tag code and the code deviation value to the modulator.

[0073] For example, in a possible implementation form of the first aspect, the loading the first optimization parameter and the second optimization parameter in the target optimization parameter group under the target implantable neuromodulation state tag to the modulator comprises:

[0074] generating a first representation attribute corresponding to the first evaluation index of the first optimization parameter; the first representation attribute is used to represent that the first evaluation index is an evaluation index of the first optimization parameter;

[0075] generating a second representation attribute corresponding to the second evaluation index of the second optimization parameter; the second representation attribute is used to represent that the second evaluation index is an evaluation index of the second optimization parameter;

[0076] loading the first evaluation index, the first representation attribute, the second evaluation index and the second representation attribute to the modulator.

[0077] For example, in a possible implementation form of the first aspect, the loading the first optimization parameter and the second optimization parameter in the target optimization parameter group under the target implantable neuromodulation state tag to the modulator comprises:

[0078] generating a first representation attribute corresponding to the first evaluation index of the first optimization parameter group; the first representation attribute is used to represent that the first evaluation index is an evaluation index of the first optimization parameter;

[0079] generating a second representation attribute corresponding to the second evaluation index of the second optimization parameter group; the second representation attribute is used to represent that the second evaluation index is an evaluation index of the second optimization parameter;

[0080] obtaining a target loss value between the first evaluation index and the second evaluation index;

[0081] loading the first evaluation index, the first characteristic attribute, and the target loss value to the controller, or loading the second evaluation index, the second characteristic attribute, and the target loss value to the controller.

[0082] According to an aspect of the embodiments of the present application, a deep learning system is provided, which comprises a processor and a machine readable storage medium, the machine readable storage medium stores machine executable instructions, the machine executable instructions are loaded and executed by the processor to implement the machine learning based implanted sensor regulation data analysis method in any of the possible implementation manners.

[0083] According to an aspect of the embodiments of the present application, a computer program product or computer program is provided, which comprises computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to make the computer device execute the method provided in the various optional implementation manners of the three aspects.

[0084] In the technical solutions provided in some embodiments of the present application, the embodiments of the present application significantly improve the accuracy and efficiency of implanted sensor regulation optimization. By introducing the unbalanced reference optimization parameter group, the parameter search space is expanded, and the potential optimization scheme that has been ignored in the past is successfully explored and applied, thereby effectively reducing the regulation effect loss. Specifically, by comprehensively considering a variety of balanced and unbalanced reference optimization parameter combinations, personalized regulation can be performed according to the physiological characteristics and disease states of different patients, the treatment effect is significantly improved, and the result of each regulation optimization is taken as a training sample for machine learning, online learning and updating of machine learning are realized, the prediction accuracy and generalization ability are continuously improved, so that it can better adapt to the changes of the physiological state of the patient, thereby providing a scientific and quantitative regulation optimization basis, improving the automation and intelligent level of the entire optimization process, and opening up new possibilities for the application of implanted medical devices. BRIEF DESCRIPTION OF DRAWINGS

[0085] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be enabled in the embodiments will be briefly introduced below, and it should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be extracted in combination with these drawings without creative labor.

[0086] Figure 1A flowchart of a machine learning-based implanted sensor regulation data analysis method provided by an embodiment of the present application is shown in FIG. 1.

[0087] Figure 2 An architecture schematic block diagram of a deep learning system for implementing the machine learning-based implanted sensor regulation data analysis method described above is shown in FIG. 2. DETAILED DESCRIPTION

[0088] The following description is provided so that others skilled in the art can have the best possible understanding of the application and its underlying principles. It is apparent that various modifications can be made to the disclosed embodiments without departing from the principles and scope of the application. The general principles defined herein can be applied to other embodiments and applications without departing from the scope of the application. Therefore, the present application is not limited to the embodiments described but should be given the widest possible scope consistent with the principles and scope of the claims.

[0089] Figure 1 A flowchart of a machine learning-based implanted sensor regulation data analysis method provided by an embodiment of the present application is shown in FIG. 1. The machine learning-based implanted sensor regulation data analysis method is described in detail below.

[0090] In step S110, implanted sensor regulation signal data to be optimized is obtained, and X reference optimization parameter groups are obtained. There are at least one pair of reference optimization parameters in the X reference optimization parameter groups that exhibit an unbalanced correlation. X is a positive integer greater than 1.

[0091] In detail, the implanted sensor regulation signal data is collected from a sensor implanted in a patient's body, reflecting the patient's physiological state or pathological condition. The reference optimization parameter group is a series of parameter combinations set in advance to try different regulation strategies. Each reference optimization parameter group contains multiple parameters, such as stimulation frequency, stimulation intensity, etc., which act together on the implanted sensor to achieve a specific therapeutic effect. Among them, if the ratio or relationship between certain parameters is not regular or linear, it is considered to exhibit an unbalanced correlation. For example, a combination of high stimulation frequency and low stimulation intensity is less common or special compared to the conventional treatment range.

[0092] In this embodiment, it is assumed that an implanted sensor system for monitoring and adjusting the brain waves of a Parkinson's patient is being processed. The server first receives regulation signal data from the implanted sensor, which reflects the patient's brain wave activity pattern in a specific time period.

[0093] Meanwhile, the server obtains 5 reference optimization parameter sets (X = 5). Take two reference optimization parameter sets as examples:

[0094] Reference optimization parameter set 1: stimulation frequency: 50Hz, stimulation intensity: 2mA

[0095] In this set, the parameter pair of stimulation frequency and stimulation intensity presents a balanced correlation, and they are both in the common treatment range and the proportion is relatively stable.

[0096] Reference optimization parameter set 2: stimulation frequency: 100Hz, stimulation intensity: 0.5mA

[0097] In this set, the stimulation frequency is high and the stimulation intensity is low, and the parameter pair presents an unbalanced correlation. This imbalance may be based on specific experimental research or an attempt to set for certain special symptoms.

[0098] Step S120, determine the control effect loss required for control optimization of the target implant sensor control signal based on the X reference optimization parameter sets under the target implantable neuromodulation state label, and generate X control effect losses. The target implant sensor control signal belongs to the implant sensor control signal data.

[0099] In detail, the target implantable neuromodulation state label is a specific treatment target or desired treatment effect, which is used to guide the direction of control optimization. For example, "relieving Parkinson's symptoms-hand tremor" is a specific treatment target.

[0100] The control effect loss is the difference between the actual treatment effect and the ideal effect when trying to use a certain reference optimization parameter set for control. This index is used to quantify the effectiveness of the control strategy. By comparing the control effect losses of different parameter sets, the effect of each parameter set in actual application can be evaluated, and the optimal parameter combination can be selected.

[0101] That is, assuming that the target implantable neuromodulation state label is "relieving Parkinson's symptoms-hand tremor". The server will simulate control optimization of the target implant sensor control signal according to the 5 reference optimization parameter sets.

[0102] For reference optimization parameter set 1, the server processes the target implant sensor control signal according to the stimulation frequency of 50Hz and the stimulation intensity of 2mA. Then, by comparing with the preset ideal effect, the control effect loss under this parameter set is evaluated. For example, it may be found that although the hand tremor is reduced to a certain extent, there is still obvious shaking, and after complex calculation and analysis, the control effect loss is 30%.

[0103] For reference optimization parameter group 2, the treatment is carried out at a stimulation frequency of 100 Hz and a stimulation intensity of 0.5 mA. It may be found that this parameter combination has no obvious effect on relieving hand tremor, and even other discomfort symptoms of the patient appear, and the calculated regulation effect loss is 60%.

[0104] By analogy, similar processing and evaluation are carried out on the five reference optimization parameter groups, and finally five regulation effect losses are generated.

[0105] In step S130, based on the X regulation effect losses, the target optimization parameter group of the implanted sensor regulation signal data under the target implanted neural regulation state label is extracted from the X reference optimization parameter groups.

[0106] In this embodiment, the server compares the five generated regulation effect losses. It is assumed that the regulation effect losses are: reference optimization parameter group 1-30%, reference optimization parameter group 2-60%, reference optimization parameter group 3-25%, reference optimization parameter group 4-40%, and reference optimization parameter group 5-18%.

[0107] Since the goal is to find the parameter group with the smallest loss, it can be seen that the regulation effect loss of reference optimization parameter group 5 is the smallest. Therefore, the server extracts reference optimization parameter group 5 as the target optimization parameter group under the target implanted neural regulation state label of "relieving Parkinson's symptoms-hand tremor".

[0108] In step S140, based on the target optimization parameter group under the target implanted neural regulation state label, the implanted sensor regulation signal in the implanted sensor regulation signal data is regulated and optimized, the target regulation and optimization result of the implanted sensor regulation signal data is generated, and the target regulation and optimization result of the implanted sensor regulation signal data is used as a training sample for machine learning.

[0109] In this embodiment, after the server obtains the target optimization parameter group (it is assumed that the stimulation frequency is 80 Hz and the stimulation intensity is 1.5 mA), the server applies these parameters to the actual implanted sensor regulation signal data.

[0110] After a period of regulation and optimization, the server collects the patient's brain wave data and physiological indicators related to hand tremor again. By comparing with the previous state and detailed analysis, it is found that the hand tremor has been significantly relieved and is almost close to the normal state.

[0111] Finally, the server determines that this regulation result is the target regulation and optimization result of the implanted sensor regulation signal data, and records the related data and result for subsequent tracking and evaluation, and provides a reference for possible further optimization.

[0112] The above is just a simple scenario example. In actual applications, the implanted sensor control signal data and the reference optimization parameter set will be more complex, involving more physiological indicators and parameter settings. The server needs to perform a large amount of calculation and analysis to achieve precise control optimization.

[0113] Suppose in another scenario, the implanted sensor is used to adjust the working parameters of a cardiac pacemaker.

[0114] In step S110, the implanted sensor control signal data to be optimized obtained by the server includes the frequency, intensity, rhythm, etc. of heartbeats. At the same time, the 8 reference optimization parameter sets (X=8) obtained cover different pacing frequency ranges (such as 60 times / minute to 120 times / minute) and pacing intensity settings (such as 1 volt to 5 volts).

[0115] For example, the reference optimization parameter set 1 may be a pacing frequency of 70 times / minute and a pacing intensity of 2 volts; the reference optimization parameter set 2 may be a pacing frequency of 100 times / minute and a pacing intensity of 4 volts. Among them, the combination of pacing frequency and pacing intensity of some parameter sets may present an uneven correlation, such as the reference optimization parameter set 3 with a pacing frequency of 60 times / minute and a pacing intensity of 5 volts.

[0116] In step S120, the target implanted neural regulation state label is "improve heart failure symptoms". The server simulates and optimizes the target implanted sensor control signal according to the 8 reference optimization parameter sets. For each parameter set, the server will analyze its improvement effect on heart function, such as monitoring indicators such as cardiac output, blood pressure, myocardial oxygen consumption, etc. to evaluate the control effect loss.

[0117] Taking the reference optimization parameter set 1 as an example, after applying a pacing frequency of 70 times / minute and a pacing intensity of 2 volts for control, it is found that the cardiac output has increased, but the blood pressure has not improved significantly, and the myocardial oxygen consumption has slightly increased. The comprehensive calculation obtains a control effect loss of 25%.

[0118] For the reference optimization parameter set 3, after applying a pacing frequency of 60 times / minute and a pacing intensity of 5 volts for control, it may appear that the myocardium is over-stimulated, and the heart function indicators are actually deteriorated, and the calculation obtains a control effect loss of 55%.

[0119] After evaluating the 8 reference optimization parameter sets, 8 control effect losses are generated.

[0120] In step S130, the server compares the eight regulation effect losses. Assume that the regulation effect losses are: 25% for the reference optimization parameter set 1, 30% for the reference optimization parameter set 2, 55% for the reference optimization parameter set 3, 20% for the reference optimization parameter set 4, 28% for the reference optimization parameter set 5, 35% for the reference optimization parameter set 6, 18% for the reference optimization parameter set 7, and 22% for the reference optimization parameter set 8. Obviously, the regulation effect loss of the reference optimization parameter set 7 is the smallest.

[0121] In step S140, the server uses the parameters of the reference optimization parameter set 7 (assuming that the pacing frequency is 85 times per minute and the pacing strength is 3 volts) to perform actual regulation optimization on the implanted sensor regulation signal. After a period of time, the patient's cardiac function indicators, such as the ejection fraction, are significantly improved, and the symptoms of heart failure are significantly reduced, and it is determined that this regulation result is the target regulation optimization result.

[0122] Based on the above steps, the embodiments of the present application significantly improve the accuracy and efficiency of implanted sensor regulation optimization. By introducing the unbalanced associated reference optimization parameter set, the parameter search space is expanded, and the potential optimization scheme previously ignored is successfully explored and applied, thereby effectively reducing the regulation effect loss. Specifically, by comprehensively considering a variety of balanced and unbalanced reference optimization parameter combinations, individualized regulation can be performed for different patients' physiological characteristics and disease states, significantly improving the treatment effect, and using the result of each regulation optimization as a training sample for machine learning, online learning and updating of machine learning are realized, and the prediction accuracy and generalization ability are continuously improved, so that it can better adapt to the changes in the patient's physiological state, thereby providing a scientific and quantitative basis for regulation optimization, improving the automation and intelligence level of the entire optimization process, and opening up new possibilities for the application of implanted medical devices.

[0123] In a possible implementation, the X reference optimization parameter sets include a first reference optimization parameter set and a second reference optimization parameter set, and the reference optimization parameters in the first reference optimization parameter set are in unbalanced association. The reference optimization parameter pair in the first reference optimization parameter set is determined based on different reference optimization parameters in the same reference optimization parameter range. Alternatively, the reference optimization parameter pair in the first reference optimization parameter set is determined based on reference optimization parameters in different reference optimization parameter ranges, and the optimization parameters in different reference optimization parameter ranges are different.

[0124] The reference optimization parameter pair in the second reference optimization parameter set is in balanced association, and the reference optimization parameter pair in the second reference optimization parameter set is determined based on the same reference optimization parameter in the same reference optimization parameter range.

[0125] In this embodiment, the scenario of processing the implanted sensor system for Parkinson's patients' brain waves is continued to be taken as an example.

[0126] The first reference optimization parameter set obtained by the server is: stimulation frequency 120 Hz, stimulation intensity 0.8 mA. In this set, the stimulation frequency is higher and the stimulation intensity is lower, and the parameter pair presents an unbalanced correlation. This imbalance can be determined based on different reference optimization parameter ranges. For example, in order to target the symptoms of severe hand tremors that some Parkinson's patients have in a certain time period, the stimulation frequency of 120 Hz is selected from the high-frequency stimulation range, and the stimulation intensity of 0.8 mA is selected from the lower stimulation intensity range, expecting that the abnormal hand tremor can be more effectively suppressed through this unbalanced combination.

[0127] The second reference optimization parameter set is: stimulation frequency 70 Hz, stimulation intensity 1.5 mA. In this set, the parameter pair of the stimulation frequency and the stimulation intensity presents a balanced correlation. They are determined based on common values in the same reference optimization parameter range. For example, for most Parkinson's patients in the relatively stable stage of the disease, this balanced parameter setting can more smoothly regulate brain waves and reduce the symptoms of hand tremor, while reducing possible side effects.

[0128] In another scenario about the adjustment of the working parameters of a cardiac pacemaker.

[0129] The first reference optimization parameter set is: pacing frequency 110 times / minute, pacing intensity 1.5 volts. This parameter pair presents an unbalanced correlation, and it can be based on a specific experimental study. For patients with more severe heart failure symptoms but limited myocardial tolerance, 110 times / minute is selected from a higher pacing frequency range, and 1.5 volts is selected from a lower pacing intensity range, trying to enhance the heart pumping function without over-stimulating the myocardium.

[0130] The second reference optimization parameter set is: pacing frequency 80 times / minute, pacing intensity 3 volts. This parameter pair presents a balanced correlation, which is based on typical values in the common parameter range of a cardiac pacemaker. It is suitable for general heart failure patients, providing sufficient pacing support to improve heart function while ensuring normal heart rhythm.

[0131] Through the above examples in specific scenarios, it can be more intuitively understood how the unbalanced correlation of the first reference optimization parameter set and the balanced correlation of the second reference optimization parameter set are determined according to different conditions and treatment needs.

[0132] In a possible implementation, step S110 comprises:

[0133] Step S111, determine the control effect loss required for the target implant sensor control signal to be controlled and optimized under the target implantable neuromodulation state label according to the balanced optimization parameter set Ya. The balanced optimization parameter set Ya belongs to Y balanced optimization parameter sets, the balanced optimization parameter sets in the Y balanced optimization parameter sets present balanced correlation between the reference optimization parameters, Y is a positive integer greater than 1, and a is a positive integer not less than Y.

[0134] Step S112, if the Y control effect losses corresponding to the Y balanced optimization parameter sets are obtained, the basic optimization parameter set of the target implant sensor control signal under the target implantable neuromodulation state label is extracted from the Y balanced optimization parameter sets based on the Y control effect losses.

[0135] Step S113, update the basic optimization parameter set based on the variation amplitudes in the variation amplitude sequence to generate the X reference optimization parameter sets.

[0136] Still taking the implant sensor system for processing the brain waves of Parkinson's patients as an example.

[0137] The server first obtains 3 balanced optimization parameter sets (Y=3), which are:

[0138] Balanced optimization parameter set 1: stimulation frequency 60Hz, stimulation intensity 1.5mA

[0139] Balanced optimization parameter set 2: stimulation frequency 70Hz, stimulation intensity 2mA

[0140] Balanced optimization parameter set 3: stimulation frequency 80Hz, stimulation intensity 2.5mA

[0141] Under the target implantable neuromodulation state label of "relieving Parkinson's symptoms-hand tremor", the server controls and optimizes the target implant sensor control signal according to the three balanced optimization parameter sets.

[0142] For the balanced optimization parameter set 1, the server processes the target implant sensor control signal according to the stimulation frequency of 60Hz and the stimulation intensity of 1.5mA. Through comparison with the preset ideal effect and complex calculation and analysis, it is concluded that the control effect loss under this parameter set is 40%.

[0143] For the balanced optimization parameter set 2, the stimulation frequency of 70Hz and the stimulation intensity of 2mA are used for processing, and the calculation shows that the control effect loss is 30%.

[0144] For the balanced optimization parameter set 3, the stimulation frequency of 80Hz and the stimulation intensity of 2.5mA are used for processing, and the control effect loss is 25%.

[0145] The server obtains the three regulation effect losses, and compares them. Since the regulation effect loss of the balanced optimization parameter group 3 is the smallest, the balanced optimization parameter group 3 is extracted from the three balanced optimization parameter groups as the basic optimization parameter group of the target implanted sensor regulation signal under the target implanted neural regulation state label of “relieving Parkinson's disease symptoms - hand tremor”.

[0146] Suppose the variation range sequence is: the stimulation frequency variation range is ±10 Hz, and the stimulation intensity variation range is ±0.5 mA.

[0147] Based on this variation range, the basic optimization parameter group (stimulation frequency 80 Hz, stimulation intensity 2.5 mA) is updated to obtain a new reference optimization parameter group.

[0148] For example, the generated new reference optimization parameter group 1 is: stimulation frequency 90 Hz, stimulation intensity 2 mA; the new reference optimization parameter group 2 is: stimulation frequency 70 Hz, stimulation intensity 3 mA; the new reference optimization parameter group 3 is: stimulation frequency 80 Hz, stimulation intensity 2 mA, and so on, and finally X reference optimization parameter groups are generated.

[0149] In the scene of heart pacemaker working parameter adjustment:

[0150] The server obtains four balanced optimization parameter groups (Y=4):

[0151] Balanced optimization parameter group 1: pacing frequency 75 times / minute, pacing intensity 2.5 volts

[0152] Balanced optimization parameter group 2: pacing frequency 85 times / minute, pacing intensity 3 volts

[0153] Balanced optimization parameter group 3: pacing frequency 95 times / minute, pacing intensity 3.5 volts

[0154] Balanced optimization parameter group 4: pacing frequency 105 times / minute, pacing intensity 4 volts

[0155] Under the target implanted neural regulation state label of “improving heart failure symptoms”, the server performs regulation optimization processing and obtains the corresponding regulation effect loss.

[0156] For example, the regulation effect loss of the balanced optimization parameter group 1 is 35%, the regulation effect loss of the balanced optimization parameter group 2 is 28%, the regulation effect loss of the balanced optimization parameter group 3 is 22%, and the regulation effect loss of the balanced optimization parameter group 4 is 25%.

[0157] After comparison, the balanced optimization parameter group 3 with the smallest regulation effect loss is extracted as the basic optimization parameter group.

[0158] Assume the variation range is: the pacing frequency variation range is ±5 times / minute, and the pacing intensity variation range is ±0.5 volts.

[0159] Based on the variation range, the basic optimization parameter group (pacing frequency 95 times / minute, pacing intensity 3.5 volts) is updated to generate a new reference optimization parameter group, such as pacing frequency 100 times / minute, pacing intensity 3 volts; pacing frequency 90 times / minute, pacing intensity 4 volts, and so on, thereby obtaining X reference optimization parameter groups.

[0160] In a possible implementation, the X reference optimization parameter groups include a third reference optimization parameter group. The reference optimization parameters in the third reference optimization parameter group are unevenly associated. One reference optimization parameter in the third reference optimization parameter group is obtained by updating a first basic optimization parameter in the basic optimization parameter group based on a first variation range in the variation range sequence. Another reference optimization parameter in the third reference optimization parameter group is obtained by updating a second basic optimization parameter in the basic optimization parameter group based on a second variation range in the variation range sequence.

[0161] Still taking the implanted sensor system for processing the brain waves of Parkinson's patients as an example.

[0162] Assume that the basic optimization parameter group has been determined through the preceding steps: the stimulation frequency is 80 Hz, and the stimulation intensity is 2.5 mA. The variation range sequence is: the stimulation frequency variation range is ±10 Hz, and the stimulation intensity variation range is ±0.5 mA.

[0163] Among the X generated reference optimization parameter groups, one is a third reference optimization parameter group. For example, the third reference optimization parameter group is: the stimulation frequency is 95 Hz, and the stimulation intensity is 2 mA.

[0164] In this third reference optimization parameter group, the stimulation frequency 95 Hz is obtained by updating a first basic optimization parameter (stimulation frequency 80 Hz) in the basic optimization parameter group based on a first variation range (+15 Hz) in the variation range sequence; and the stimulation intensity 2 mA is obtained by updating a second basic optimization parameter (stimulation intensity 2.5 mA) in the basic optimization parameter group based on a second variation range (-0.5 mA) in the variation range sequence.

[0165] In the scenario of adjusting the working parameters of a cardiac pacemaker.

[0166] The basic optimization parameter group is: the pacing frequency is 90 times / minute, and the pacing intensity is 3 volts. The variation range is: the pacing frequency variation range is ±5 times / minute, and the pacing intensity variation range is ±0.5 volts.

[0167] The third reference optimization parameter set in the X reference optimization parameter sets generated can be: a pacing frequency of 85 beats per minute and a pacing intensity of 3.5 volts.

[0168] The pacing frequency of 85 beats per minute is obtained by updating the first base optimization parameter (a pacing frequency of 90 beats per minute) in the base optimization parameter set based on the first variation amplitude (-5 beats per minute) in the variation amplitude sequence; and the pacing intensity of 3.5 volts is obtained by updating the second base optimization parameter (a pacing intensity of 3 volts) in the base optimization parameter set based on the second variation amplitude (+0.5 volt) in the variation amplitude sequence.

[0169] In a possible implementation, the X reference optimization parameter sets further include a fourth reference optimization parameter set. The reference optimization parameters in the fourth reference optimization parameter set are in a balanced correlation. One reference optimization parameter in the fourth reference optimization parameter set is obtained by updating the first base optimization parameter based on a third variation amplitude in the variation amplitude sequence. Another reference optimization parameter in the fourth reference optimization parameter set is obtained by updating the second base optimization parameter based on an opposite number of the third variation amplitude.

[0170] In a scenario of processing an implanted sensor system of brain waves of a Parkinson's patient:

[0171] Suppose that the base optimization parameter set is: a stimulation frequency of 80 Hz and a stimulation intensity of 2.5 mA, and the variation amplitude sequence is: a stimulation frequency variation amplitude of ±10 Hz and a stimulation intensity variation amplitude of ±0.5 mA.

[0172] The fourth reference optimization parameter set in the X reference optimization parameter sets generated is, for example: a stimulation frequency of 90 Hz and a stimulation intensity of 2 mA.

[0173] In this fourth reference optimization parameter set, the stimulation frequency of 90 Hz is obtained by updating the first base optimization parameter (a stimulation frequency of 80 Hz) in the base optimization parameter set based on a third variation amplitude (+10 Hz) in the variation amplitude sequence; and the stimulation intensity of 2 mA is obtained by updating the second base optimization parameter (a stimulation intensity of 2.5 mA) in the base optimization parameter set based on an opposite number (-0.5 mA corresponding to -10 Hz) of the third variation amplitude (+10 Hz).

[0174] In a scenario of adjusting working parameters of a cardiac pacemaker:

[0175] The base optimization parameter set is: a pacing frequency of 90 beats per minute and a pacing intensity of 3 volts, and the variation amplitude is: a pacing frequency variation amplitude of ±5 beats per minute and a pacing intensity variation amplitude of ±0.5 volt.

[0176] The fourth reference optimization parameter set in the X generated reference optimization parameter sets can be: a pacing frequency of 95 beats per minute and a pacing intensity of 2.5 volts.

[0177] The pacing frequency of 95 beats per minute is obtained by updating the first basic optimization parameter (pacing frequency of 90 beats per minute) in the basic optimization parameter set based on the third variation amplitude (+5 beats per minute) in the variation amplitude sequence; and the pacing intensity of 2.5 volts is obtained by updating the second basic optimization parameter (pacing intensity of 3 volts) in the basic optimization parameter set based on the opposite number (-0.5 volts corresponding to -5 beats per minute) of the third variation amplitude (+5 beats per minute).

[0178] In a possible implementation, the step S120 comprises:

[0179] In step S121, a target regulation signal node in the target implantable sensor regulation signal is obtained, and a candidate signal node of the target regulation signal node under the target implantable neural regulation state label is determined from the target implantable sensor regulation signal.

[0180] In step S122, a regulation deviation degree between a regulation parameter of the target regulation signal node and a regulation parameter of the candidate signal node is determined.

[0181] In step S123, the regulation deviation degree is compared with the X reference optimization parameter sets respectively, and comparison information corresponding to the X reference optimization parameter sets respectively is generated.

[0182] In step S124, based on the comparison information corresponding to the reference optimization parameter set Yb, a regulation optimization knowledge point corresponding to the target regulation signal node under the reference optimization parameter set Yb is determined. The reference optimization parameter set Yb belongs to the X reference optimization parameter sets, b is a positive integer not greater than X, and until the regulation optimization knowledge points corresponding to the target regulation signal node under the X reference optimization parameter sets respectively are obtained.

[0183] In step S125, based on the X obtained regulation optimization knowledge points, regulation optimization processing is performed on the regulation parameters of the target regulation signal node respectively, and X regulation optimization results are generated.

[0184] In step S126, based on the X regulation optimization results, a regulation effect loss required for regulation optimization of the target implantable sensor regulation signal according to the X reference optimization parameter sets under the target implantable neural regulation state label is determined, and X regulation effect losses are generated.

[0185] Still taking the implantable sensor system for processing the brain waves of Parkinson's patients as an example. The target implantable neural regulation state label is "relieving Parkinson's symptoms-hand tremor".

[0186] The server obtains a target regulation signal node in the target implanted sensor regulation signal, such as a brain wave frequency peak in a certain time period. From the target implanted sensor regulation signal, a candidate signal node of this target regulation signal node under the target implanted neural regulation state label is determined, such as a brain wave frequency peak in other similar time periods under the same symptom label.

[0187] The regulation deviation between the regulation parameter (for example, the frequency value) of the target regulation signal node (the brain wave frequency peak in the certain time period) and the regulation parameter of the candidate signal node (the brain wave frequency peak in the other similar time period) is determined. Assuming that the frequency of the target regulation signal node is 10 Hz and the frequency of the candidate signal node is 8 Hz, the regulation deviation is 2 Hz.

[0188] The regulation deviation is compared with X reference optimization parameter groups respectively to generate comparison information corresponding to the X reference optimization parameter groups respectively.

[0189] For the reference optimization parameter group 1, the corresponding comparison information is generated by comparing its parameter range and setting standard.

[0190] Based on the comparison information corresponding to the reference optimization parameter group 1, the corresponding regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter group 1 is determined. For example, the ideal frequency range set by the reference optimization parameter group 1 is 8-12 Hz, the current regulation deviation is 2 Hz, and the corresponding regulation optimization knowledge point may be to maintain the current stimulation parameter within the range.

[0191] In the same way, the corresponding regulation optimization knowledge points of the target regulation signal node under other reference optimization parameter groups are determined until all regulation optimization knowledge points of the target regulation signal node under the X reference optimization parameter groups are obtained.

[0192] Based on the X obtained regulation optimization knowledge points, the regulation parameter of the target regulation signal node is respectively subjected to regulation optimization processing. For example, the corresponding regulation optimization knowledge point of the reference optimization parameter group 1 is to keep unchanged, so no adjustment is made; the corresponding regulation optimization knowledge point of the reference optimization parameter group 2 is to increase the stimulation intensity by 0.5 mA, so the corresponding parameter adjustment is made to generate X regulation optimization results.

[0193] Based on the X regulation optimization results, it is determined that under the target implantable neuroregulation state label of "relieving Parkinson's symptoms-hand tremor", the regulation effect loss required for regulating and optimizing the target implant sensor regulation signal according to the X reference optimization parameter groups. For example, a certain regulation optimization result makes the hand tremor reduce by 80%, but there is still slight shaking. After complex calculation, it is concluded that the regulation effect loss of the reference optimization parameter group is 20%. In turn, X regulation effect losses are calculated.

[0194] In the scene of heart pacemaker working parameter adjustment, the target implantable neuroregulation state label is "improving heart failure symptoms". The server acquires the target regulation signal node, such as the heart beat interval time at a certain time. The candidate signal nodes under the state label are determined, such as the heart beat interval time at other similar times. The regulation deviation of the target regulation signal node and the candidate signal nodes is calculated. The regulation deviation is compared with each reference optimization parameter group to generate comparison information, and the corresponding regulation optimization knowledge points under each reference optimization parameter group are determined. Based on the regulation optimization knowledge points, regulation optimization processing is performed to generate regulation optimization results. Finally, the regulation effect loss of each reference optimization parameter group is determined according to the regulation optimization results, and X regulation effect losses are generated.

[0195] In a possible implementation, the candidate signal nodes include a first candidate signal node and a second candidate signal node, and the regulation deviation includes a first regulation deviation and a second regulation deviation. The first regulation deviation is the regulation deviation between the regulation parameter of the first candidate signal node and the regulation parameter of the target regulation signal node, and the second regulation deviation is the regulation deviation between the regulation parameter of the second candidate signal node and the regulation parameter of the target regulation signal node.

[0196] Step S123 includes:

[0197] Step S1231, the number of regulation optimization knowledge points under the target implantable neuroregulation state label is acquired, and based on the number of regulation optimization knowledge points under the target implantable neuroregulation state label, the first comparison information between the first regulation deviation and the reference optimization parameter group Yb is acquired.

[0198] Step S1232, based on the number of regulation optimization knowledge points under the target implantable neuroregulation state label, the second comparison information between the second regulation deviation and the reference optimization parameter group Yb is acquired.

[0199] Step S1233, the first comparison information and the second comparison information are taken as the comparison information corresponding to the reference optimization parameter group Yb, and the comparison information corresponding to the X reference optimization parameter groups is acquired.

[0200] Still taking the implanted sensor system of brain waves of Parkinson's patients as an example, the target implanted neural regulation state label is "relieve Parkinson's symptoms-hand tremor".

[0201] The target regulation signal node obtained by the server is the brain wave frequency peak at a certain time, the first candidate signal node is the brain wave frequency peak at the same time the day before, and the second candidate signal node is the brain wave frequency peak at the same time the week before.

[0202] Suppose the frequency of the target regulation signal node is 12Hz, the frequency of the first candidate signal node is 10Hz, and the frequency of the second candidate signal node is 15Hz. Then the first regulation deviation is 2Hz (12Hz-10Hz), and the second regulation deviation is -3Hz (12Hz-15Hz).

[0203] The server obtains the number of regulation optimization knowledge points under the target implanted neural regulation state label "relieve Parkinson's symptoms-hand tremor", for example, there are 5.

[0204] Based on this number, the first control information between the first regulation deviation and the reference optimization parameter group 1 is obtained. Suppose the acceptable deviation range specified by the reference optimization parameter group 1 is ±1Hz, and since the first regulation deviation is 2Hz, it is out of range, so the first control information may indicate that the deviation is too large.

[0205] Similarly, based on the number of regulation optimization knowledge points, the second control information between the second regulation deviation and the reference optimization parameter group 1 is obtained. Because the second regulation deviation is -3Hz, it is also out of the acceptable deviation range, so the second control information also indicates that the deviation is too large.

[0206] The first control information and the second control information are taken as the control information corresponding to the reference optimization parameter group 1.

[0207] In the same way, the control information corresponding to the first regulation deviation and the second regulation deviation and other reference optimization parameter groups (such as reference optimization parameter group 2, 3, etc.) respectively is obtained, until X reference optimization parameter groups each corresponding control information is obtained.

[0208] In the scene of adjusting the working parameters of a cardiac pacemaker, the target implanted neural regulation state label is "improve heart failure symptoms".

[0209] The target regulation signal node obtained by the server is the cardiac pacing interval time at a certain time, the first candidate signal node is the cardiac pacing interval time at the same time the hour before, and the second candidate signal node is the cardiac pacing interval time at the same time the two days before.

[0210] Assume that the pacing interval time of the target regulation signal node is 0.8 seconds, the first candidate signal node is 0.9 seconds, and the second candidate signal node is 0.7 seconds. Then the first regulation deviation is -0.1 seconds, and the second regulation deviation is 0.1 seconds.

[0211] The server obtains the number of regulation optimization knowledge points under the target implantable neuromodulation state label of "improving heart failure symptoms", for example, 4.

[0212] Based on this number, the first comparison information between the first regulation deviation and the reference optimization parameter group 1 is obtained. Assume that the acceptable deviation range specified by the reference optimization parameter group 1 is ±0.05 seconds, and the first regulation deviation is out of range. The first comparison information shows that the deviation is too large.

[0213] The second comparison information between the second regulation deviation and the reference optimization parameter group 1 is obtained, and since it is within the range, the second comparison information shows that it is within the acceptable range.

[0214] The two comparison information are taken as the comparison information corresponding to the reference optimization parameter group 1, and then the comparison information with other reference optimization parameter groups is obtained.

[0215] In the implanted sensor regulation scene of sleep apnea patients, the target implantable neuromodulation state label is "improving sleep apnea symptoms".

[0216] The target regulation signal node obtained by the server is the number of apneas in a certain time period, the first candidate signal node is the number of apneas in the same time period last week, and the second candidate signal node is the number of apneas in the same time period last month.

[0217] Assume that the number of apneas of the target regulation signal node is 8 times, the first candidate signal node is 10 times, and the second candidate signal node is 12 times. Then the first regulation deviation is -2 times, and the second regulation deviation is -4 times.

[0218] The server obtains the number of regulation optimization knowledge points under the target implantable neuromodulation state label of "improving sleep apnea symptoms", for example, 6.

[0219] Based on this number, the first comparison information between the first regulation deviation and the reference optimization parameter group 1 is obtained. Assume that the acceptable deviation range specified by the reference optimization parameter group 1 is ±3 times, and since the first regulation deviation is -2 times, it is within the range, so the first comparison information may indicate that the deviation is within the acceptable range.

[0220] Similarly, based on the regulation optimization knowledge point quantity, second control information between the second regulation deviation and the reference optimization parameter group 1 is obtained. Because the second regulation deviation is-4 times, which is out of the acceptable deviation range, the second control information indicates that the deviation is too large.

[0221] The first control information and the second control information are taken as the corresponding control information of the reference optimization parameter group 1.

[0222] In the same way, the first regulation deviation and the second regulation deviation are obtained, and the corresponding control information of the other reference optimization parameter groups is obtained respectively, until the corresponding control information of the X reference optimization parameter groups is obtained.

[0223] In a possible implementation, the step S124 includes:

[0224] In a possible implementation, the step S124 includes:

[0225] The step S1241 includes: determining a first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb based on the first control information.

[0226] The step S1242 includes: determining a second knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb based on the second control information.

[0227] In this embodiment, the implanted sensor system of the Parkinson's patient's brain wave is taken as an example, and the target implanted neural regulation state label is "relieve Parkinson's symptoms-hand tremor".

[0228] Suppose the reference optimization parameter group 1 (Yb=1), the first control information indicates that the deviation of the target regulation signal node and the first candidate signal node is within the acceptable range, and based on this, the first knowledge point mapping value is determined to be 1. The second control information indicates that the deviation of the target regulation signal node and the second candidate signal node is too large, and the second knowledge point mapping value is determined to be 0.

[0229] Then, based on the first knowledge point mapping value 1 and the second knowledge point mapping value 0, the regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter group 1 is comprehensively determined to be "properly fine-tune the stimulation frequency".

[0230] In the scene of heart pacemaker working parameter adjustment, the target implanted neural regulation state label is "improve heart failure symptoms".

[0231] For the reference optimization parameter set 2 (Yb = 2), the first control information shows that the target regulation signal node deviates from the first candidate signal node too much, and the first knowledge point mapping value is determined to be 0. The second control information shows that the deviation is within an acceptable range, and the second knowledge point mapping value is determined to be 1.

[0232] Based on the first knowledge point mapping value 0 and the second knowledge point mapping value 1, it is determined that the regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter set 2 is “keep the pacing strength unchanged”.

[0233] In the implantation of a sensor regulation scene of a sleep apnea patient, the target implantable neural regulation state label is “improve sleep apnea symptoms”.

[0234] For the reference optimization parameter set 3 (Yb = 3), the first control information shows that the deviation is within an acceptable range, and the first knowledge point mapping value is determined to be 1. The second control information also shows that the deviation is within an acceptable range, and the second knowledge point mapping value is determined to be 1.

[0235] Based on the first knowledge point mapping value 1 and the second knowledge point mapping value 1, it is determined that the regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter set 3 is “maintain the current respiratory stimulation parameter”.

[0236] In a possible implementation, the reference optimization parameter set Yb includes a first reference optimization parameter and a second reference optimization parameter, the first reference optimization parameter is smaller than the second reference optimization parameter, and the regulation optimization knowledge point includes four knowledge points.

[0237] Step S1241 includes:

[0238] If the first control information represents that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is smaller than the first reference optimization parameter, a first mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb.

[0239] If the first control information represents that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is not smaller than the first reference optimization parameter, a second mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb.

[0240] If the first control information represents that the first regulation deviation degree is not a decrease deviation, and the first regulation deviation degree is smaller than the second reference optimization parameter, a third mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter set Yb.

[0241] If the first control information represents that the first regulation deviation degree is deviated to the decrease direction, and the first regulation deviation degree is less than the first reference optimization parameter, a first mapping value of the target regulation signal node under the reference optimization parameter group Yb is output as the first knowledge point mapping value.

[0242] Taking the implanted sensor system of the brain waves of Parkinson's patients as an example, the target implanted neural regulation state label is "relieve Parkinson's symptoms-hand tremor".

[0243] Suppose that the first reference optimization parameter of the reference optimization parameter group 4 (Yb=4) is 5 Hz, and the second reference optimization parameter is 15 Hz.

[0244] The first control information represents that the first regulation deviation degree is deviated to the decrease direction, and the first regulation deviation degree is 3 Hz, which is less than the first reference optimization parameter 5 Hz. At this time, the first mapping value (supposed to be 0.1) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 4.

[0245] If the first control information represents that the first regulation deviation degree is deviated to the decrease direction, and the first regulation deviation degree is 7 Hz, which is not less than the first reference optimization parameter 5 Hz, the second mapping value (supposed to be 0.2) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 4.

[0246] If the first control information represents that the first regulation deviation degree is not deviated to the decrease direction, and the first regulation deviation degree is 12 Hz, which is less than the second reference optimization parameter 15 Hz, the third mapping value (supposed to be 0.3) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 4.

[0247] If the first control information represents that the first regulation deviation degree is deviated to the increase direction, and the first regulation deviation degree is 18 Hz, which is not less than the second reference optimization parameter 15 Hz, the fourth mapping value (supposed to be 0.4) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 4.

[0248] In the scene of heart pacemaker working parameter adjustment, the target implanted neural regulation state label is "improve heart failure symptoms".

[0249] Suppose that the first reference optimization parameter of the reference optimization parameter group 5 (Yb=5) is 60 times / minute, and the second reference optimization parameter is 90 times / minute.

[0250] The first control information represents that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is less than the first reference optimization parameter 60 times / minute. At this time, the first mapping value (assuming 0.5) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 5.

[0251] If the first control information represents that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is not less than the first reference optimization parameter 60 times / minute, the second mapping value (assuming 0.6) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 5.

[0252] If the first control information represents that the first regulation deviation degree is not a decrease deviation, and the first regulation deviation degree is less than the second reference optimization parameter 90 times / minute, the third mapping value (assuming 0.7) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 5.

[0253] If the first control information represents that the first regulation deviation degree is an increase deviation, and the first regulation deviation degree is not less than the second reference optimization parameter 90 times / minute, the fourth mapping value (assuming 0.8) is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 5.

[0254] In a possible implementation, the reference optimization parameter group Yb includes a first reference optimization parameter and a second reference optimization parameter, the first reference optimization parameter is less than the second reference optimization parameter, and the regulation optimization knowledge point includes three knowledge points.

[0255] Step S1241 includes:

[0256] If the first control information represents that the first regulation deviation degree is less than the first reference optimization parameter, the fifth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb.

[0257] If the first control information represents that the first regulation deviation degree is greater than the second reference optimization parameter, the sixth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb.

[0258] If the first control information represents that the first regulation deviation degree is equal to the first reference optimization parameter, or the first regulation deviation degree is equal to the second reference optimization parameter, the seventh mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb.

[0259] If the first comparison information represents that the first regulation deviation is greater than the first reference optimization parameter and the first regulation deviation is less than the second reference optimization parameter, a seventh mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb. The fifth mapping value, the sixth mapping value, and the seventh mapping value are in mapping relationship with three kinds of regulation optimization knowledge points, respectively.

[0260] In the embodiment, it is assumed that in the scenario of processing the brain waves of Parkinson's patients, the first reference optimization parameter of the reference optimization parameter group 6 (Yb=6) is 10 Hz, and the second reference optimization parameter is 18 Hz.

[0261] The first comparison information represents that the first regulation deviation is 8 Hz, which is less than the first reference optimization parameter 10 Hz. At this time, the server outputs the fifth mapping value (assuming 0.5) as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 6.

[0262] If the first comparison information represents that the first regulation deviation is 20 Hz, which is greater than the second reference optimization parameter 18 Hz, the server outputs the sixth mapping value (assuming 0.7) as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 6.

[0263] If the first comparison information represents that the first regulation deviation is equal to 10 Hz (i.e., the first reference optimization parameter) or equal to 18 Hz (i.e., the second reference optimization parameter), the server outputs the seventh mapping value (assuming 0.6) as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 6.

[0264] If the first comparison information represents that the first regulation deviation is 15 Hz, which is greater than the first reference optimization parameter 10 Hz and less than the second reference optimization parameter 18 Hz, the server also outputs the seventh mapping value 0.6 as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group 6.

[0265] For example, in a possible implementation, the step S125 includes:

[0266] In step S1251, the X regulation optimization quantities corresponding to the X regulation optimization knowledge points are queried from the regulation optimization quantity template, and the X regulation optimization quantities are generated.

[0267] In step S1252, the regulation parameters of the target regulation signal node are respectively regulated and optimized according to the X regulation optimization quantities, and the X regulation optimization results are generated.

[0268] The server has obtained 5 pieces of regulation optimization knowledge, corresponding to 5 sets of reference optimization parameters. Now, the regulation optimization results are to be generated based on the regulation optimization knowledge.

[0269] First, the server queries the regulation optimization quantities corresponding to the 5 pieces of regulation optimization knowledge from the regulation optimization quantity template.

[0270] The first piece of regulation optimization knowledge indicates that the stimulation frequency needs to be increased by 5 Hz, and the server finds in the regulation optimization quantity template that the corresponding regulation optimization quantity is to increase the stimulation frequency by 5 Hz.

[0271] The second piece of regulation optimization knowledge indicates that the stimulation intensity needs to be reduced by 0.5 mA, and the server finds in the template that the corresponding regulation optimization quantity is to reduce the stimulation intensity by 0.5 mA.

[0272] The third piece of regulation optimization knowledge indicates that the stimulation frequency needs to be increased by 10 Hz and the stimulation intensity needs to be increased by 0.8 mA, and the server obtains the regulation optimization quantity from the template, which is to adjust the values accordingly.

[0273] The fourth piece of regulation optimization knowledge suggests that the stimulation frequency should remain unchanged, but the stimulation intensity should be increased by 1 mA, so the corresponding regulation optimization quantity is to increase the stimulation intensity by 1 mA and keep the stimulation frequency unchanged.

[0274] The fifth piece of regulation optimization knowledge proposes to reduce the stimulation frequency by 8 Hz and the stimulation intensity by 0.3 mA, and the server finds the regulation optimization quantity from the template, which is to adjust the values accordingly.

[0275] Next, the server processes the regulation optimization of the target regulation signal node according to the 5 regulation optimization quantities, and generates 5 regulation optimization results.

[0276] For the first regulation optimization quantity, the server increases the stimulation frequency of the target regulation signal node by 5 Hz based on the original value, and obtains the first regulation optimization result. Assuming that the original stimulation frequency is 60 Hz, it becomes 65 Hz after increasing by 5 Hz.

[0277] For the second regulation optimization quantity, the server reduces the stimulation intensity of the target regulation signal node by 0.5 mA. If the original stimulation intensity is 2 mA, it becomes 1.5 mA after reduction, thereby generating the second regulation optimization result.

[0278] For the third regulation optimization quantity, the server adjusts both the stimulation frequency and the stimulation intensity. For example, the original stimulation frequency is 70 Hz, which becomes 80 Hz after increasing by 10 Hz, and the original stimulation intensity is 1.2 mA, which becomes 2 mA after increasing by 0.8 mA, thereby forming the third regulation optimization result.

[0279] For the fourth control optimization amount, the server keeps the stimulation frequency of the target control signal node unchanged at 85 Hz, but increases the stimulation intensity by 1 mA. Assuming the original stimulation intensity is 1.8 mA, it increases to 2.8 mA, and the fourth control optimization result is generated in this way.

[0280] For the fifth control optimization amount, the server reduces the stimulation frequency of the target control signal node by 8 Hz and the stimulation intensity by 0.3 mA. If the original stimulation frequency is 90 Hz, it decreases to 82 Hz, and the original stimulation intensity is 2.5 mA, it decreases to 2.2 mA, and the fifth control optimization result is finally generated.

[0281] In this way, the server completes the control optimization processing of the control parameters of the target control signal node based on the five control optimization knowledge points and the corresponding control optimization amounts, and successfully generates five control optimization results.

[0282] In this process, the server strictly follows the settings in the control optimization amount template and accurately adjusts the control parameters in order to achieve the target implantable neural control state of "relieving Parkinson's symptoms - hand tremor".

[0283] The server will also further evaluate and analyze the five control optimization results. For example, it will observe whether the frequency and amplitude of the patient's hand tremor have decreased and whether the brain wave activity pattern tends to be within the normal range after these control optimizations. If a control optimization result fails to achieve the expected effect, the server may re-examine the corresponding control optimization knowledge points and control optimization amounts, or even query more appropriate adjustment schemes from the control optimization amount template and perform control optimization processing again until the control optimization result that can effectively relieve Parkinson's symptoms is found.

[0284] At the same time, the server will also consider the individual differences and real-time physiological responses of the patient. For example, if the patient experiences discomfort or side effects after the implementation of a certain control optimization result, the server will immediately stop the current adjustment and re-evaluate all reference optimization parameter groups and control optimization knowledge points to ensure the safety and effectiveness of the control optimization process.

[0285] In addition, the server will record each control optimization process and result in detail, forming a rich database. This not only helps to provide reference for the subsequent treatment of the current patient, but also accumulates valuable experience and data for the treatment of other Parkinson's patients. Through continuous learning and improvement, the server can provide more and more precise and efficient implantable sensor control optimization services for patients.

[0286] Suppose that in another control optimization, the server obtains five different control optimization knowledge points.

[0287] The regulation optimization knowledge point 1 indicates that the stimulation frequency needs to be significantly increased, such as by 20 Hz. The server queries the corresponding specific increase from the regulation optimization amount template, which is 20 Hz.

[0288] The regulation optimization knowledge point 2 suggests a slight decrease in stimulation intensity, for example, by 0.2 mA. The server confirms in the template that the corresponding regulation optimization amount for this knowledge point is a decrease of 0.2 mA.

[0289] The regulation optimization knowledge point 3 proposes to significantly increase the stimulation frequency and moderately increase the stimulation intensity. The server queries the specific regulation optimization amounts as an increase of 30 Hz in stimulation frequency and an increase of 1.5 mA in stimulation intensity.

[0290] The regulation optimization knowledge point 4 indicates that only a slight adjustment of the stimulation frequency is needed, a decrease of 3 Hz. The server obtains the regulation optimization amount from the template as an exact decrease of 3 Hz.

[0291] The regulation optimization knowledge point 5 advocates a significant decrease in stimulation intensity, for example, by 1 mA. The server finds the corresponding decrease amount in the regulation optimization amount template as 1 mA.

[0292] Then, the server processes the regulation parameters of the target regulation signal node based on these regulation optimization amounts.

[0293] If the initial stimulation frequency is 50 Hz, for the regulation optimization knowledge point 1, the server increases it by 20 Hz to obtain 70 Hz, generating the corresponding regulation optimization result.

[0294] For the regulation optimization knowledge point 2, assuming the original stimulation intensity is 2.5 mA, the server decreases it by 0.2 mA to obtain 2.3 mA, forming a new regulation optimization result.

[0295] For the regulation optimization knowledge point 3, if the initial stimulation frequency is 60 Hz and the stimulation intensity is 1 mA, the server increases them respectively to 90 Hz and 2.5 mA, generating a new result.

[0296] For the regulation optimization knowledge point 4, if the original stimulation frequency is 80 Hz, the server decreases it by 3 Hz to adjust it to 77 Hz, obtaining the corresponding regulation optimization result.

[0297] For the regulation optimization knowledge point 5, if the initial stimulation intensity is 3 mA, the server decreases it by 1 mA to 2 mA, completing the regulation optimization processing.

[0298] Through the above series of operations, the server generates 5 different regulation optimization results again, and prepares for subsequent effect evaluation and analysis to determine which result can most effectively achieve the goal of "relieving Parkinson's symptoms - hand tremor".

[0299] Such a regulation optimization process is a dynamic process of continuous trial and optimization. The server will continuously adjust and improve the regulation strategy according to the actual treatment effect and the feedback of the patient, so as to provide the most suitable treatment plan for the patient.

[0300] Therefore, in the regulation optimization of the implanted sensor system for processing the brain waves of Parkinson's patients, the regulation parameters of the target regulation signal node are processed according to the regulation optimization amount template and the regulation optimization amount, so as to continuously explore the best regulation scheme for the treatment of the patient.

[0301] For example, in a possible implementation, step S126 includes:

[0302] In step S1261, the regulation error rate of the target implanted sensor regulation signal under the reference optimization parameter set Yb is determined based on the target implanted sensor regulation signal after regulation optimization covered by the regulation optimization result Yb and the initial regulation signal corresponding to the target implanted sensor regulation signal. The reference optimization parameter set Yb belongs to the X reference optimization parameter sets, b is a positive integer not greater than X, the regulation optimization result Yb is the regulation optimization result obtained by regulating and optimizing the target implanted sensor regulation signal according to the reference optimization parameter set Yb, and the target implanted sensor regulation signal is obtained by reconstructing the encoding features of the initial regulation signal.

[0303] In step S1262, the performance evaluation index of the reference optimization parameter set Yb is obtained, and the regulation effect loss of the target implanted sensor regulation signal under the reference optimization parameter set Yb is determined according to the regulation error rate of the target implanted sensor regulation signal under the reference optimization parameter set Yb and the performance evaluation index of the reference optimization parameter set Yb. Until the regulation effect loss corresponding to the target implanted sensor regulation signal under the X reference optimization parameter sets is obtained, X regulation effect losses are generated.

[0304] Suppose that in the implanted sensor system for monitoring and adjusting the brain waves of Parkinson's patients, 3 regulation optimization results have been obtained, corresponding to 3 reference optimization parameter sets respectively.

[0305] First, for the reference optimization parameter set 1, the obtained regulation optimization result 1 covers the target implanted sensor regulation signal after regulation optimization. The initial regulation signal is the brain wave signal of the patient before any optimization processing. By analyzing and comparing the target implanted sensor regulation signal after regulation optimization and the initial regulation signal in detail.

[0306] Assuming that the abnormal frequency fluctuations of the brain waves of Parkinson's patients are more obvious in the initial control signal, and in the optimization result 1 of the control, the abnormal frequency fluctuations are improved to a certain extent, but there are still some unstable periods. After complex calculation and comparison, it is determined that the control error rate of the target implanted sensor control signal under the reference optimization parameter group 1 is 25%.

[0307] Next, the performance evaluation index of the reference optimization parameter group 1 is obtained. This performance evaluation index is based on a large number of previous experiments and clinical data, and is used to measure the ratio of the expected effect and the actual effect of the parameter group under similar conditions. Assuming that the performance evaluation index of the reference optimization parameter group 1 is 0.8.

[0308] Then, according to the control error rate of 25% of the target implanted sensor control signal under the reference optimization parameter group 1 and the performance evaluation index of 0.8 of the group, the control effect loss of the target implanted sensor control signal under the reference optimization parameter group 1 is calculated by a specific algorithm (for example: control effect loss = control error rate / performance evaluation index) is 31.25%.

[0309] Next, for the reference optimization parameter group 2. Similarly, based on the control optimization result 2 covering the control optimized target implanted sensor control signal and the initial control signal, it is found that the stability of the brain waves has been greatly improved, but there are still some minor abnormal fluctuations. After accurate calculation, it is determined that the control error rate of the target implanted sensor control signal under the reference optimization parameter group 2 is 18%.

[0310] The performance evaluation index of the reference optimization parameter group 2 is assumed to be 0.7. According to the control error rate of 18% and the performance evaluation index of 0.7, the control effect loss of the target implanted sensor control signal under the reference optimization parameter group 2 is calculated to be about 25.71%.

[0311] Finally, for the reference optimization parameter group 3. Analyze the target implanted sensor control signal and the initial control signal in the control optimization result 3, and the brain waves almost reach the ideal state of stability, only occasionally appearing for a very short time. After calculation, the control error rate is 8%.

[0312] The performance evaluation index of the reference optimization parameter group 3 is assumed to be 0.9. Therefore, the control effect loss of the target implanted sensor control signal under the reference optimization parameter group 3 is calculated to be about 8.89%.

[0313] Through the above steps, the server obtains the corresponding regulation effect loss of the target implantable sensor regulation signal under the three reference optimization parameter groups, and generates three regulation effect losses, which are 31.25%, 25.71% and 8.89% respectively. The server will evaluate the effect of each reference optimization parameter group according to these loss values, and select the most suitable optimization scheme for the patient to achieve the target implantable neural regulation state of "relieving Parkinson's symptoms-hand tremor".

[0314] For example, in a possible implementation, step S130 includes:

[0315] Step S131, based on the X regulation effect losses, extracting a reference optimization parameter group with the smallest regulation effect loss from the X reference optimization parameter groups.

[0316] Step S132, outputting the extracted reference optimization parameter group as the target optimization parameter group of the implantable sensor regulation signal data under the target implantable neural regulation state label.

[0317] Suppose that in an implantable sensor system for monitoring and adjusting the brain waves of Parkinson's patients, a total of 5 reference optimization parameter groups are obtained, which are reference optimization parameter groups 1 to 5, and their corresponding regulation effect losses have been calculated.

[0318] After calculation, the regulation effect loss of the reference optimization parameter group 1 is 28%, the regulation effect loss of the reference optimization parameter group 2 is 35%, the regulation effect loss of the reference optimization parameter group 3 is 20%, the regulation effect loss of the reference optimization parameter group 4 is 25%, and the regulation effect loss of the reference optimization parameter group 5 is 15%.

[0319] The server first compares the five regulation effect losses. By comparing one by one, the server finds that the regulation effect loss 15% of the reference optimization parameter group 5 is the smallest among the five values.

[0320] Then, the server extracts the reference optimization parameter group 5.

[0321] Finally, the server outputs the extracted reference optimization parameter group 5 as the target optimization parameter group of the implantable sensor regulation signal data under the target implantable neural regulation state label of "relieving Parkinson's symptoms-hand tremor".

[0322] This means that in the current evaluation and calculation, the reference optimization parameter group 5 is considered to be the best parameter combination in achieving the "relieving Parkinson's symptoms-hand tremor" target, and subsequent actual regulation and optimization operations of the implantable sensor regulation signal data will be based on this target optimization parameter group.

[0323] For example, in a possible implementation, the number of target implantable neuromodulation state tags is Z, where Z is a positive integer.

[0324] Step S140 includes:

[0325] Step S141, based on the target optimization parameter group under the target implantable neuromodulation state tag Kc, the control parameters of the implant sensor control signal of the implant sensor control signal data are optimized and processed, and the control optimization result of the implant sensor control signal of the implant sensor control signal data under the target implantable neuromodulation state tag Kc is generated. The target implantable neuromodulation state tag Kc belongs to Z target implantable neuromodulation state tags, and c is a positive integer not greater than Z.

[0326] Step S142, based on the control optimization result of the implant sensor control signal of the implant sensor control signal data under the target implantable neuromodulation state tag Kc, the control effect loss of the implant sensor control signal of the implant sensor control signal data under the target implantable neuromodulation state tag Kc is determined.

[0327] Step S143, if the implant sensor control signal data of the implant sensor control signal is obtained under the Z target implantable neuromodulation state tag corresponding to the Z control effect loss, the minimum control effect loss corresponding to the Z control effect loss is output as the target control optimization result of the implant sensor control signal data of the implant sensor control signal.

[0328] Suppose in an implant sensor system for monitoring and adjusting the brain waves of Parkinson's patients, the number of target implantable neuromodulation state tags is 3, which are "relieving Parkinson's symptoms-hand tremor", "improving Parkinson's symptoms-movement retardation", and "reducing Parkinson's symptoms-muscle stiffness".

[0329] First, for the target implantable neuromodulation state tag "relieving Parkinson's symptoms-hand tremor". The server optimizes and processes the control parameters of the implant sensor control signal data based on the target optimization parameter group under this tag, such as a stimulation frequency of 70Hz and a stimulation intensity of 1.8mA. After processing, the control optimization result under the state tag "relieving Parkinson's symptoms-hand tremor" is generated. Then, the server calculates the control effect loss under this state tag by comparing the relevant data before and after optimization, such as the frequency and amplitude changes of hand tremor, which is assumed to be 20%.

[0330] Then, for the target implantable neuromodulation state label "improve Parkinson's symptoms - slow movement", the server processes the implant sensor control signal according to the target optimization parameter set corresponding to the target implantable neuromodulation state label, for example, a stimulation frequency of 80 Hz and a stimulation intensity of 2 mA, to obtain the control optimization result under the target implantable neuromodulation state label. Then, the server determines the control effect loss under the target implantable neuromodulation state label "improve Parkinson's symptoms - slow movement" through a series of evaluations and calculations, which is assumed to be 15%.

[0331] Finally, for the target implantable neuromodulation state label "reduce Parkinson's symptoms - muscle stiffness", the server processes the implant sensor control signal according to the target optimization parameter set, for example, a stimulation frequency of 65 Hz and a stimulation intensity of 1.5 mA, to generate the corresponding control optimization result. After detailed analysis and calculation, the server obtains the control effect loss under the target implantable neuromodulation state label "reduce Parkinson's symptoms - muscle stiffness", which is assumed to be 18%.

[0332] The server obtains the control effect loss of the implant sensor control signal data under the three target implantable neuromodulation state labels, which are 20%, 15%, and 18% respectively. After comparison, the server finds that 15% is the smallest among the three control effect losses. Therefore, the server outputs the control optimization result under the target implantable neuromodulation state label "improve Parkinson's symptoms - slow movement" as the target control optimization result of the implant sensor control signal data. This means that in this round of control optimization, the optimization effect for "improve Parkinson's symptoms - slow movement" is the most ideal, and subsequent treatment and adjustment may be more based on this result.

[0333] For example, in a possible implementation, the method further includes:

[0334] Step A110, loading the first optimization parameter and the second optimization parameter in the target optimization parameter set under the target implantable neuromodulation state label to the controller, so that the controller determines the target control optimization result of the implant sensor control signal data based on the first optimization parameter and the second optimization parameter in the target optimization parameter set under the target implantable neuromodulation state label.

[0335] For example, in a possible implementation, step A110 includes:

[0336] obtaining the first parameter label code of the first evaluation index of the first optimization parameter in the first reference optimization parameter range, and the second parameter label code of the second evaluation index of the second optimization parameter in the second reference optimization parameter range.

[0337] The first parameter tag code corresponding to the first set of optimization parameters and the second parameter tag code corresponding to the second set of optimization parameters are loaded into the controller.

[0338] For example, in another possible implementation, step A110 can further include:

[0339] The first parameter tag code of the first evaluation index of the first optimization parameter in the first reference optimization parameter range and the second parameter tag code of the second evaluation index of the second optimization parameter in the second reference optimization parameter range are obtained.

[0340] The coding deviation value between the first parameter tag code and the second parameter tag code is obtained.

[0341] The first parameter tag code and the coding deviation value are loaded into the controller, or the second parameter tag code and the coding deviation value are loaded into the controller.

[0342] For example, in another possible implementation, step A110 can further include:

[0343] A first characterization attribute corresponding to the first evaluation index of the first optimization parameter is generated. The first characterization attribute is used to characterize that the first evaluation index is the evaluation index of the first optimization parameter.

[0344] A second characterization attribute corresponding to the second evaluation index of the second optimization parameter is generated. The second characterization attribute is used to characterize that the second evaluation index is the evaluation index of the second optimization parameter.

[0345] The first evaluation index, the first characterization attribute, the second evaluation index, and the second characterization attribute are loaded into the controller.

[0346] For example, in another possible implementation, step A110 can further include:

[0347] A first characterization attribute corresponding to the first evaluation index of the first set of optimization parameters is generated. The first characterization attribute is used to characterize that the first evaluation index is the evaluation index of the first optimization parameter.

[0348] A second characterization attribute corresponding to the second evaluation index of the second set of optimization parameters is generated. The second characterization attribute is used to characterize that the second evaluation index is the evaluation index of the second optimization parameter.

[0349] The target loss value between the first evaluation index and the second evaluation index is obtained.

[0350] The first evaluation index, the first characterization attribute, and the target loss value are loaded to the controller. Alternatively, the second evaluation index, the second characterization attribute, and the target loss value are loaded to the controller.

[0351] In an implanted sensor system for monitoring and adjusting the brain waves of a Parkinson's patient, a target optimal parameter set under the target implanted neuromodulation state label of "relieving Parkinson's symptoms - hand tremor" has been determined, in which the first optimal parameter is a stimulation frequency of 80 Hz, and the second optimal parameter is a stimulation intensity of 2.5 mA.

[0352] First, the server obtains a first parameter label code of a first evaluation index (for example, an evaluation of the effect of relieving hand tremor) of a first optimal parameter (stimulation frequency of 80 Hz) in a first reference optimal parameter range (for example, a common stimulation frequency range). Assume that this code is "0101". At the same time, a second parameter label code of a second evaluation index (for example, an evaluation of the effect of relieving hand tremor) of a second optimal parameter (stimulation intensity of 2.5 mA) in a second reference optimal parameter range (for example, a common stimulation intensity range) is obtained, which is assumed to be "1010". Then, "0101" and "1010" are loaded to the controller.

[0353] Alternatively, after the server obtains the first parameter label code "0101" and the second parameter label code "1010" described above, it calculates the code deviation value between the two. Assume that the code deviation value is "0011". Next, "0101" and "0011" are loaded to the controller, or "1010" and "0011" are loaded to the controller.

[0354] Alternatively, the server generates a first characterization attribute corresponding to the first evaluation index of the first optimal parameter, such as "this evaluation index is specifically for the evaluation of a stimulation frequency of 80 Hz". At the same time, a second characterization attribute corresponding to the second evaluation index of the second optimal parameter is generated, such as "this evaluation index is specifically for the evaluation of a stimulation intensity of 2.5 mA". Then, the first evaluation index, the first characterization attribute, the second evaluation index, and the second characterization attribute are loaded to the controller.

[0355] Alternatively, after the server generates the first characterization attribute and the second characterization attribute described above, it obtains a target loss value between the first evaluation index and the second evaluation index, which is assumed to be "0.15". Subsequently, the first evaluation index, the first characterization attribute, and the target loss value are loaded to the controller, or the second evaluation index, the second characterization attribute, and the target loss value are loaded to the controller.

[0356] Through the above different manners, the server loads the first optimization parameter and the second optimization parameter in the target optimization parameter group to the controller, so that the controller can more accurately determine the target control optimization result of the implanted sensor control signal data based on these parameters and related information, thereby better achieving the adjustment of the brain waves of the Parkinson's patient and the relief of the symptoms.

[0357] Figure 2 The hardware structure of the deep learning system 100 for implementing the above-mentioned machine learning-based implanted sensor control data analysis method provided by the embodiments of the present application is shown as follows. Figure 2 As shown, the deep learning system 100 can include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

[0358] In an alternative embodiment, the deep learning system 100 can be a single server or a server group. The server group can be centralized or distributed (for example, the deep learning system 100 can be a distributed system). In an alternative embodiment, the deep learning system 100 can be local or remote. For example, the deep learning system 100 can access information and / or data stored in the machine-readable storage medium 120 via a network. For another example, the deep learning system 100 can be directly connected to the machine-readable storage medium 120 to access the stored information and / or data. In an alternative embodiment, the deep learning system 100 can be implemented on a cloud platform. For example only, the cloud platform can include a private cloud, a public cloud, an aggregated cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc. or any integration thereof.

[0359] The machine-readable storage medium 120 can store data and / or instructions. In an alternative embodiment, the machine-readable storage medium 120 can store data obtained from an external terminal. In an alternative embodiment, the machine-readable storage medium 120 can store data and / or instructions used by the deep learning system 100 to perform or use to complete the exemplary methods described in the present application. In an alternative embodiment, the machine-readable storage medium 120 can include a mass storage, a removable storage, a volatile read-write memory, a read-only memory, etc. or any integration thereof. The exemplary mass storage can include a magnetic disk, an optical disk, a solid-state disk, etc. The exemplary removable storage can include a flash drive, a floppy disk, an optical disk, a memory card, a compact disk, a magnetic tape, etc.

[0360] In the implementation process, the plurality of processors 110 execute computer executable instructions stored in the machine readable storage medium 120, so that the processor 110 can execute the machine learning based implanted sensor regulation data analysis method of the method embodiments as described above, the processor 110, the machine readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 can be used to describe the transceiving action of the communication unit 140.

[0361] The specific implementation process of the processor 110 can refer to the various method embodiments executed by the deep learning system 100 described above, which have similar implementation principles and technical effects, and will not be described here.

[0362] In addition, the embodiment of the present application also provides a readable storage medium, wherein the readable storage medium is pre-installed with computer executable instructions, and when the processor executes the computer executable instructions, the machine learning based implanted sensor regulation data analysis method is realized.

[0363] Similarly, it should be noted that, in order to simplify the description of the present application and help understand one or more embodiments of the application, in the foregoing description of the embodiments of the present application, sometimes multiple features are combined into one embodiment, figure or description thereof. Similarly, it should be noted that, in order to simplify the description of the present application and help understand one or more embodiments of the application, in the foregoing description of the embodiments of the present application, sometimes multiple features are combined into one embodiment, figure or description thereof.

Claims

1. A deep learning system, characterized by, The deep learning system comprises a processor and a machine readable storage medium, the machine readable storage medium stores machine executable instructions, the machine executable instructions are loaded and executed by the processor to implement a machine learning based implanted sensor regulation data analysis method, the method comprises: Obtaining implanted sensor regulation signal data to be optimized, and obtaining X reference optimization parameter groups; there is an unbalanced correlation between the reference optimization parameters of at least one reference optimization parameter group in the X reference optimization parameter groups; X is a positive integer greater than 1, wherein if the ratio or relationship between certain parameters is not regular in the reference optimization parameter groups, it is determined that there is an unbalanced correlation, otherwise it is determined that there is a balanced correlation; Determine the regulation effect loss required for regulation optimization of the target implanted sensor regulation signal based on the X reference optimization parameter groups under the target implanted neural regulation state label, generate X regulation effect losses; the target implanted sensor regulation signal belongs to the implanted sensor regulation signal data, wherein the target implanted neural regulation state label is an explicit treatment target or a desired treatment effect, which is used to guide the direction of regulation optimization; Based on the X regulation effect losses, extract the target optimization parameter group of the implanted sensor regulation signal data under the target implanted neural regulation state label from the X reference optimization parameter groups; Based on the target optimization parameter group under the target implanted neural regulation state label, the implanted sensor regulation signal in the implanted sensor regulation signal data is regulated and optimized, the target regulation optimization result of the implanted sensor regulation signal data is generated, and the target regulation optimization result of the implanted sensor regulation signal data is used as a machine learning training sample; The determination of the regulation effect loss required for regulation optimization of the target implanted sensor regulation signal based on the X reference optimization parameter groups under the target implanted neural regulation state label, generating X regulation effect losses, comprises: Obtaining a target regulation signal node in the target implanted sensor regulation signal, determining a candidate signal node of the target regulation signal node under the target implanted neural regulation state label from the target implanted sensor regulation signal; Determine the regulation deviation between the regulation parameters of the target regulation signal node and the candidate signal node; Contrast the regulation deviation with the X reference optimization parameter groups respectively to generate the corresponding contrast information of the X reference optimization parameter groups; Based on the corresponding contrast information of the reference optimization parameter group Yb, determine the corresponding regulation optimization knowledge point of the target regulation signal node under the reference optimization parameter group Yb; the reference optimization parameter group Yb belongs to the X reference optimization parameter groups, b is a positive integer not greater than X, until the corresponding regulation optimization knowledge point of the target regulation signal node under the X reference optimization parameter groups is obtained respectively; Based on the obtained X regulation optimization knowledge points, the regulation parameters of the target regulation signal node are respectively subjected to regulation optimization processing, and X regulation optimization results are generated; Based on the X regulation optimization results, the regulation effect loss required for regulating and optimizing the target implant sensor control signal according to the X reference optimization parameter groups under the target implantable neural regulation state label is determined, and X regulation effect losses are generated.

2. The deep learning system of claim 1, wherein, The X reference optimization parameter groups include a first reference optimization parameter group and a second reference optimization parameter group, and the reference optimization parameter pairs in the first reference optimization parameter group present an unbalanced correlation; wherein the reference optimization parameter pairs in the first reference optimization parameter group are determined based on different reference optimization parameters in the same reference optimization parameter range; or the reference optimization parameter pairs in the first reference optimization parameter group are determined based on reference optimization parameters in different reference optimization parameter ranges, and the optimization parameters in different reference optimization parameter ranges are not the same; The reference optimization parameter pairs in the second reference optimization parameter group present balanced correlation, wherein the reference optimization parameter pairs in the second reference optimization parameter group are determined based on the same reference optimization parameter in the same reference optimization parameter range.

3. The deep learning system of claim 1 or 2, wherein, The X reference optimization parameter groups are obtained, including: Determine the regulation effect loss required for regulating and optimizing the target implant sensor control signal according to the balanced optimization parameter group Ya under the target implantable neural regulation state label; the balanced optimization parameter group Ya belongs to Y balanced optimization parameter groups, the balanced optimization parameter groups in the Y balanced optimization parameter groups cover reference optimization parameter pairs that present balanced correlation, Y is a positive integer greater than 1, and a is a positive integer not less than Y; If the Y regulation effect losses corresponding to the Y balanced optimization parameter groups are obtained, the basic optimization parameter group of the target implant sensor control signal under the target implantable neural regulation state label is extracted from the Y balanced optimization parameter groups based on the Y regulation effect losses; Based on the variation amplitudes in the variation amplitude sequence, the basic optimization parameter group is updated to generate the X reference optimization parameter groups.

4. The deep learning system of claim 3, wherein, The X reference optimization parameter groups include a third reference optimization parameter group; the reference optimization parameter pairs in the third reference optimization parameter group present unbalanced correlation; One of the reference optimization parameters in the third reference optimization parameter group is obtained by updating a first basic optimization parameter in the basic optimization parameter group based on a first variation amplitude in the variation amplitude sequence; The other reference optimization parameter in the third reference optimization parameter group is obtained by updating a second basic optimization parameter in the basic optimization parameter group based on a second variation amplitude in the variation amplitude sequence.

5. The deep learning system of claim 4, wherein, The X reference optimization parameter groups also include a fourth reference optimization parameter group; the reference optimization parameter pairs in the fourth reference optimization parameter group present balanced correlation; One reference optimization parameter in the fourth reference optimization parameter group is obtained by updating the first basic optimization parameter based on a third variation amplitude in the variation amplitude sequence; Another reference optimization parameter in the fourth reference optimization parameter group is obtained by updating the second basic optimization parameter based on an opposite number of the third variation amplitude.

6. The deep learning system of claim 1, wherein, The candidate signal nodes include a first candidate signal node and a second candidate signal node, and the control deviation includes a first control deviation and a second control deviation. The first control deviation is a control deviation between a control parameter of the first candidate signal node and a control parameter of the target control signal node, and the second control deviation is a control deviation between a control parameter of the second candidate signal node and the control parameter of the target control signal node. The control deviations are respectively compared with the X reference optimization parameter groups to generate corresponding comparison information of the X reference optimization parameter groups, including: The number of control optimization knowledge points under the target implantable neural control state label is obtained, and the first control deviation and the reference optimization parameter group Yb are compared based on the number of control optimization knowledge points under the target implantable neural control state label to obtain the first comparison information. The second control deviation and the reference optimization parameter group Yb are compared based on the number of control optimization knowledge points under the target implantable neural control state label to obtain the second comparison information. The first comparison information and the second comparison information are used as the comparison information corresponding to the reference optimization parameter group Yb, and the comparison information corresponding to the X reference optimization parameter groups is obtained. Based on the comparison information corresponding to the reference optimization parameter group Yb, the control optimization knowledge point corresponding to the target control signal node under the reference optimization parameter group Yb is determined, including: Based on the first comparison information, the first knowledge point mapping value of the target control signal node under the reference optimization parameter group Yb is determined. Based on the second comparison information, the second knowledge point mapping value of the target control signal node under the reference optimization parameter group Yb is determined. Based on the first knowledge point mapping value and the second knowledge point mapping value, the control optimization knowledge point of the target control signal node under the reference optimization parameter group Yb is determined.

7. The deep learning system of claim 6, wherein, The reference optimization parameter group Yb includes a first reference optimization parameter and a second reference optimization parameter, the first reference optimization parameter is smaller than the second reference optimization parameter, and the control optimization knowledge point includes four knowledge points. Based on the first comparison information, the first knowledge point mapping value of the target control signal node under the reference optimization parameter group Yb is determined, including: If the first comparison information indicates that the first control deviation is a decreasing deviation, and the first control deviation is smaller than the first reference optimization parameter, the first mapping value is output as the first knowledge point mapping value of the target control signal node under the reference optimization parameter group Yb. if the first control information represents that the first regulation deviation degree is a decrease deviation, and the first regulation deviation degree is not less than the first reference optimization parameter, a second mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; if the first control information represents that the first regulation deviation degree is not a decrease deviation, and the first regulation deviation degree is less than the second reference optimization parameter, a third mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; if the first control information represents that the first regulation deviation degree is an increase deviation, and the first regulation deviation degree is not less than the second reference optimization parameter, a fourth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; the first mapping value, the second mapping value, the third mapping value and the fourth mapping value are in mapping relationship with four regulation optimization knowledge points respectively.

8. The deep learning system of claim 6, wherein, The reference optimization parameter group Yb includes a first reference optimization parameter and a second reference optimization parameter, the first reference optimization parameter is less than the second reference optimization parameter, and the regulation optimization knowledge point includes three knowledge points. The first control information represents that the first regulation deviation degree is less than the first reference optimization parameter, a fifth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; if the first control information represents that the first regulation deviation degree is greater than the second reference optimization parameter, a sixth mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; if the first control information represents that the first regulation deviation degree is equal to the first reference optimization parameter, or the first regulation deviation degree is equal to the second reference optimization parameter, a seventh mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; if the first control information represents that the first regulation deviation degree is greater than the first reference optimization parameter, and the first regulation deviation degree is less than the second reference optimization parameter, a seventh mapping value is output as the first knowledge point mapping value of the target regulation signal node under the reference optimization parameter group Yb; the fifth mapping value, the sixth mapping value, the seventh mapping value and three regulation optimization knowledge points are in mapping relationship respectively. ​

Images