Nerve treatment detector and detection method thereof

Abstract

The invention relates to the technical field of detection equipment management, in particular to a nerve treatment detector and a detection method thereof.The detection method comprises the steps that S100, sleep and respiration data of a user are detected through the nerve treatment detector, S101, used historical data and historical power consumption data of the nerve treatment detector are collected, and S104, the used historical data and the historical power consumption data of the nerve treatment detector are stored; the method comprises the following steps of S102, analyzing a current change state coefficient which is adjusted in the past of the nerve treatment detector, S103, preprocessing the current change state coefficient and used historical data and historical power consumption data of the nerve treatment detector to generate training data, and S104, fitting the training data to establish a power consumption analysis model of the nerve treatment detector. And S105, acquiring data of the current to-be-used nerve treatment detector, predicting whether the current to-be-used nerve treatment detector has an abnormal power consumption condition in a use process, selecting whether to carry out pre-use prompt of the equipment according to a prediction result, and carrying out planned pre-use prompt of the equipment to guarantee and maintain a normal working state of the nerve treatment detector.

Description

Technical Field

[0001] The present invention relates to the technical field of detection equipment management, and in particular to a neurotherapy detection instrument and a detection method thereof. Background Art

[0002] Neurotherapy detectors are usually used to detect users' sleep and breathing conditions to further alleviate users' insomnia, anxiety and other problems. The detector may have low battery during use. Since the initial battery power may be different when used, adjusting the current during the use of the detector will also have a certain impact on the power consumption of the detector battery. The existing technology does not carry out necessary pre-use prompt planning for the detector. During the use of the neurotherapy detector, the detector may be interrupted due to battery exhaustion, which will cause some detection data to be missing and affect the use effect of the neurotherapy detector, which is not conducive to ensuring and maintaining the normal working state of the neurotherapy detector.

[0003] Therefore, people need a neurotherapy detector and a detection method thereof to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a neurotherapy detector and a detection method thereof to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for detecting nerve treatment, comprising the following steps: S100: Uses a neurotherapy detector to detect the user's sleep and breathing data; S101: Collecting historical usage data and historical power consumption data of the neurotherapy detector; S102: Analyze the current change state coefficient of the nerve treatment detector that was previously adjusted; S103: pre-processing the current change state coefficient, the historical usage data and the historical power consumption data of the nerve treatment detector to generate training data; S104: Establishing a power consumption analysis model of the nerve treatment detector after fitting the training data; S105: Acquire data of the neurotherapy detector to be used currently, predict whether the neurotherapy detector to be used currently will have abnormal power consumption during use, and choose whether to provide a pre-use reminder based on the prediction result.

[0006] Furthermore, in step S101: the usage history data includes the duration data of each previous use of the neurotherapy detector and the current data adjusted during each use; The historical power consumption data includes the initial power data of the battery at the beginning of each use of the neurotherapy detector and the remaining power data after each use. The collection of the duration of each use of the neurotherapy detector is U={U1, U2, ..., U m}, the number of times the nerve treatment detector is adjusted to increase the current during each use is H={H1, H2, ..., H m}, and the current value set of the neurotherapy detector that is adjusted to increase during a random use is obtained as I={I1, I2, ..., I n}, m represents the number of times the neurotherapy detector has been used, and n represents the number of times the neurotherapy detector has been adjusted to increase the current during a random use; The initial battery charge of the neurotherapy detector each time it was used is collected as B={B1, B2, ..., B m}, the remaining power set after each use is b={b1, b2, ..., b m}.

[0007] Further, in step S102: the current change state coefficient R of the neurotherapy detector adjusted during the previous random use is calculated according to the following formula: i : R i =[H i / ∑ m i=1 (H i )]+[(∑ n j=1 (I j )) / n]; Where i represents the i-th time the neurotherapy detector has been used in the past, I j represents the jth adjusted current value of the neurotherapy detector during the i-th use, and the current change state coefficient set of the neurotherapy detector during the previous m uses is calculated to be R={R1, R2, ..., R i , ..., R m}; Taking into account that the neurotherapy detector involves current adjustment operations during use, and the current adjustment will have a certain impact on the power consumption of the detector, for example, increasing the current during use may accelerate the power consumption of the neurotherapy detector, and frequently increasing the current may further accelerate the power consumption. Big data technology is used to collect the adjustment data of the neurotherapy detector during its previous use, and the current change state coefficient of the neurotherapy detector is analyzed by combining the adjustment number data and the adjusted current value data. This is conducive to reasonably and accurately analyzing the current change data of the detector during its historical use. The purpose of analyzing the current change state coefficient is to use it as one of the training data to establish a battery consumption analysis model for the detector, which improves the reference value of the model for predicting whether the battery will be exhausted abnormally during the use of the detector currently to be used, and improves the accuracy of the prediction results.

[0008] Further, in step S103: according to E i =(B i -b i ) / U i Analyze the unit power consumption E of the neurotherapy detector during its previous i-th use i , the unit power consumption set of the neurotherapy detector in the past m times of use is obtained as E={E1, E2, ..., E i , ..., E m}, B i represents the initial battery charge of the neurotherapy detector when it was used for the i-th time in the past, b i represents the remaining power after the i-th use. The initial power, current change state coefficient and unit power consumption of the battery of the neurotherapy detector are combined and preprocessed to generate training data {(B1, R1, E1), (B2, R2, E2), ..., (B i , R i , E i ), ..., (B m , R m , E m )}; The initial power level of the detector battery is used as another training data because different initial power levels will also have a certain impact on the power consumption of the detector battery. For example, when the initial power level is low, the power consumption rate of the detector battery will be faster than when the initial power level is high. Adding the initial power level as another training data to the training of the power consumption analysis model further improves the accuracy of the model as a reference data for predicting whether the current detector to be used will experience abnormal battery depletion during use.

[0009] Further, in step S104: for the training data {(B1, R1, E1), (B2, R2, E2), ..., (B i , R i , E i ), ..., (B m , R m , E m )}After fitting, the power consumption analysis model of the nerve treatment detector is established: Z = ξ0*X+ξ1*Y+ξ2; Wherein, * represents a multiplication sign, ξ0, ξ1 and ξ2 represent fitting coefficients, X represents the first independent variable representing the initial power of the battery in the power consumption analysis model, Y represents the second independent variable representing the current change state coefficient in the power consumption analysis model, and Z represents the dependent variable representing the unit power consumption in the power consumption analysis model.

[0010] Further, in step S105: the initial power of the battery of the current neurotherapy detector to be used is obtained as W, and the number of times the current of the current neurotherapy detector to be used was adjusted to increase when it was used to detect the target user is h={h1, h2, ..., h c}, c represents the number of times the current neurotherapy detector to be used has been used in the past, the target user refers to the user who needs to use the current neurotherapy detector to be used at the current time, and the set of current values ​​of the current neurotherapy detector to be used that is adjusted to increase during a random use is obtained as I ’ ={I1 ’ , I2 ’ , ..., I k ’}, k represents the number of times the current of the currently used neurotherapy detector is adjusted to increase during a random one-time use, and the current change state coefficient r of the currently used neurotherapy detector during the previous random one-time use is calculated. e , r e =[h e / ∑ c e=1 (h e )]+[(∑ k v=1 (I v ’ )) / k],I v ’ represents the current value of the current that was adjusted and increased by the current of the current treatment detector to be used for the vth time during the previous use for the eth time. The current change state coefficient set of the current that was adjusted by the current treatment detector to be used for the cth time during the previous use is calculated in the same way as r={r1, r2, ..., r e , ..., rc}, and obtain the comprehensive current change state coefficient G when the current nerve treatment detector to be used is used to detect the target user, G=(∑ c e=1 (r e ’ )) / c, obtain the planned usage time T of the neurotherapy detector to be used for testing the target user at the current time, input W and G into the power consumption analysis model: let X=W, Y=G, obtain the estimated unit power consumption of the battery of the neurotherapy detector to be used as ξ0*W+ξ1*G+ξ2, predict the estimated power consumption of the battery of the neurotherapy detector to be used as T*(ξ0*W+ξ1*G+ξ2), compare W and T*(ξ0*W+ξ1*G+ξ2): if WT*(ξ0*W+ξ1*G+ξ2)≥0, it is predicted that the neurotherapy detector to be used will not have an abnormal battery depletion during use, and choose not to prompt before using the device; if WT*(ξ0*W+ξ1*G+ξ2)<0, it is predicted that the neurotherapy detector to be used will have an abnormal battery depletion during use, and choose to prompt before using the device: remind the neurotherapy detector to be charged before use; By obtaining relevant data of the neurotherapy detector to be used currently, substituting the relevant data into the power consumption analysis model to predict that the neurotherapy detector to be used currently will not have abnormal battery depletion during use, and then judging whether it is necessary to remind the device to charge the battery before the neurotherapy detector to be used currently is used based on the prediction result, and reminding the device to charge before use when necessary, the probability of the neurotherapy detector working or operation being interrupted due to battery depletion during use is effectively reduced, thereby effectively reducing the probability of missing detection data and affecting the use effect of the neurotherapy detector, thereby ensuring and maintaining the normal working state of the neurotherapy detector.

[0011] Compared with the prior art, the beneficial effects achieved by the present invention are: The present invention uses big data technology to collect data on adjustments made during the past use of a neurotherapy detector, and combines the adjustment times data and the adjusted current value data to analyze the current change state coefficient of the neurotherapy detector, which is conducive to reasonably and accurately analyzing the current change data during the historical use of the detector. The purpose of analyzing the current change state coefficient is to use it as one of the training data to establish a battery power consumption analysis model for the detector, thereby improving the reference value of the model for predicting whether the current detector to be used will experience an abnormal battery exhaustion state during use, and improving the accuracy of the prediction result; the initial power is added as another training data to the training of the power consumption analysis model, further improving the accuracy of the model as a reference data for predicting whether the current detector to be used will experience an abnormal battery exhaustion state during use; By obtaining relevant data of the neurotherapy detector to be used currently, substituting the relevant data into the power consumption analysis model to predict that the neurotherapy detector to be used currently will not have abnormal battery depletion during use, and then judging whether it is necessary to remind the device to charge the battery before the neurotherapy detector to be used currently is used based on the prediction result, and reminding the device to charge before use when necessary, the probability of the neurotherapy detector working or operation being interrupted due to battery depletion during use is effectively reduced, thereby effectively reducing the probability of missing detection data and affecting the use effect of the neurotherapy detector, thereby ensuring and maintaining the normal working state of the neurotherapy detector. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a neurotherapy detection method of the present invention. DETAILED DESCRIPTION

[0013] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0014] Combine the following Figure 1 The present invention is further described with reference to the accompanying drawings and specific embodiments.

[0015] Example 1: Figure 1 As shown, this embodiment provides a method for detecting nerve treatment, comprising the following steps: S100: Uses a neurotherapy detector to detect the user's sleep and breathing data; S101: Collecting the usage history data and the historical power consumption data of the neurotherapy detector: the usage history data includes the usage duration data of each time the neurotherapy detector was used and the current data adjusted during each use; The historical power consumption data includes the initial power data of the battery at the beginning of each use of the neurotherapy detector and the remaining power data after each use. The collection of the duration of each use of the neurotherapy detector is U={U1, U2, ..., U m}, the number of times the nerve treatment detector is adjusted to increase the current during each use is H={H1, H2, ..., H m}, and the current value set of the neurotherapy detector that is adjusted to increase during a random use is obtained as I={I1, I2, ..., I n}, m represents the number of times the neurotherapy detector has been used, and n represents the number of times the neurotherapy detector has been adjusted to increase the current during a random use; The initial battery charge of the neurotherapy detector each time it was used is collected as B={B1, B2, ..., B m}, the remaining power set after each use is b={b1, b2, ..., b m}; S102: Analyze the current change state coefficient of the neurotherapy detector that was previously adjusted: Calculate the current change state coefficient R of the neurotherapy detector that was adjusted during a random use in the past according to the following formula: i : R i =[H i / ∑ m i=1 (H i )]+[(∑ n j=1 (I j )) / n]; Where i represents the i-th time the neurotherapy detector has been used in the past, I j represents the jth adjusted current value of the neurotherapy detector during the i-th use, and the current change state coefficient set of the neurotherapy detector during the previous m uses is calculated to be R={R1, R2, ..., R i , ..., R m}; S103: Preprocess the current change state coefficient, the historical usage data and the historical power consumption data of the nerve treatment detector to generate training data: i =(B i -b i ) / Ui Analyze the unit power consumption E of the neurotherapy detector during its previous i-th use i , the unit power consumption set of the neurotherapy detector in the past m times of use is obtained as E={E1, E2, ..., E i , ..., E m}, B i represents the initial battery charge of the neurotherapy detector when it was used for the i-th time in the past, b i represents the remaining power after the i-th use. The initial power, current change state coefficient and unit power consumption of the battery of the neurotherapy detector are combined and preprocessed to generate training data {(B1, R1, E1), (B2, R2, E2), ..., (B i , R i , E i ), ..., (B m , R m , E m )}; S104: After fitting the training data, establish a power consumption analysis model for the neurotherapy detector: fit the training data {(B1, R1, E1), (B2, R2, E2), ..., (B i , R i , E i ), ..., (B m , R m , E m )}After fitting, the power consumption analysis model of the nerve treatment detector is established: Z = ξ0*X+ξ1*Y+ξ2; Wherein, * represents a multiplication sign, ξ0, ξ1 and ξ2 represent fitting coefficients, X represents the first independent variable representing the initial power of the battery in the power consumption analysis model, Y represents the second independent variable representing the current change state coefficient in the power consumption analysis model, and Z represents the dependent variable representing the unit power consumption in the power consumption analysis model; S105: Obtain data of the neurotherapy detector to be used, predict whether the neurotherapy detector to be used will have abnormal power consumption during use, and choose whether to provide a pre-use reminder based on the prediction result: The initial power of the battery of the neurotherapy detector to be used is obtained as W, and the number of times the neurotherapy detector to be used was adjusted to increase the current when it was used to detect the target user is h={h1, h2, ..., h c}, c represents the number of times the current neurotherapy detector to be used has been used in the past, the target user refers to the user who needs to use the current neurotherapy detector to be used at the current time, and the set of current values ​​of the current neurotherapy detector to be used that is adjusted to increase during a random use is obtained as I’ ={I1 ’ , I2 ’ , ..., I k ’}, k represents the number of times the current of the currently used neurotherapy detector is adjusted to increase during a random one-time use, and the current change state coefficient r of the currently used neurotherapy detector during the previous random one-time use is calculated. e , r e =[h e / ∑ c e=1 (h e )]+[(∑ k v=1 (I v ’ )) / k],I v ’ represents the current value of the current that was adjusted and increased by the current of the current treatment detector to be used for the vth time during the previous use for the eth time. The current change state coefficient set of the current that was adjusted by the current treatment detector to be used for the cth time during the previous use is calculated in the same way as r={r1, r2, ..., r e , ..., r c}, and obtain the comprehensive current change state coefficient G when the current nerve treatment detector to be used is used to detect the target user, G=(∑ c e=1 (r e ’ )) / c, obtain the planned usage time T of the neurotherapy detector to be used for testing the target user at the current time, input W and G into the power consumption analysis model: let X=W, Y=G, obtain the estimated unit power consumption of the battery of the neurotherapy detector to be used as ξ0*W+ξ1*G+ξ2, predict the estimated power consumption of the battery of the neurotherapy detector to be used as T*(ξ0*W+ξ1*G+ξ2), compare W and T*(ξ0*W+ξ1*G+ξ2): if WT*(ξ0*W+ξ1*G+ξ2)≥0, it is predicted that the neurotherapy detector to be used will not have an abnormal battery depletion during use, and choose not to prompt before using the device; if WT*(ξ0*W+ξ1*G+ξ2)<0, it is predicted that the neurotherapy detector to be used will have an abnormal battery depletion during use, and choose to prompt before using the device: remind the neurotherapy detector to be charged before use; For example: establish a power consumption analysis model for a neurotherapy detector: Z=0.1X+0.02*Y+0.15, obtain the initial power of the battery of the neurotherapy detector to be used as W=0.6, that is, the initial power is 60%, the number of times the neurotherapy detector to be used was adjusted to increase the current when it was used to detect the target user is h={h1, h2, h3}={5, 2, 1}, and the current value set of the neurotherapy detector to be used to be adjusted to increase during the first use is I ’ ={I1 ’ , I2 ’ , I3 ’ , I4 ’ , I5 ’}={0.1, 0.2, 0.22, 0.15, 0.12}, unit: mA, calculate the current change state coefficient r1 of the current treatment detector to be used during the first use in the past, r1=0.783, collect the current value data of the current treatment detector to be used during the past three uses, calculate the current change state coefficient of the current treatment detector to be used during the past three uses, and obtain the comprehensive current change state coefficient G of the current treatment detector to be used when it is used to detect the target user, G=0.51, input W and G into the power consumption analysis In the model: let X=W=0.6, Y=G=0.51, and obtain the estimated unit power consumption of the battery of the current neurotherapy detector to be used is about 0.22, and obtain that the planned usage time of the current neurotherapy detector to be used for testing the target user at the current time is 4 hours, T*(ξ0*W+ξ1*G+ξ2)=0.88, W=0.6, WT*(ξ0*W+ξ1*G+ξ2)<0, and predict that the current neurotherapy detector to be used will have an abnormal battery depletion during use, and choose to perform the device pre-use prompt: remind the current neurotherapy detector to be charged before use.

[0016] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting neurological treatment, characterized in that: The following steps are involved: S100: Uses a neurotherapy detector to detect the user's sleep and breathing data; S101: Collecting historical usage data and historical power consumption data of the neurotherapy detector; S102: Analyze the current change state coefficient of the nerve treatment detector that was previously adjusted; S103: pre-processing the current change state coefficient, the historical usage data and the historical power consumption data of the nerve treatment detector to generate training data; S104: Establishing a power consumption analysis model of the nerve treatment detector after fitting the training data; S105: Acquire data of the neurotherapy detector to be used currently, predict whether the neurotherapy detector to be used currently will have abnormal power consumption during use, and choose whether to provide a pre-use reminder based on the prediction result.

2. A nerve treatment detection method according to claim 1, characterized in that: In step S101: the usage history data includes the duration data of each previous use of the neurotherapy detector and the current data adjusted during each use; The historical power consumption data includes the initial power data of the battery each time the neurotherapy detector was used and the remaining power data after each use.

3. A nerve treatment detection method according to claim 2, characterized in that: The collection of the duration of each use of the neurotherapy detector in the past is U={U1, U2, ..., U m }, the number of times the nerve treatment detector is adjusted to increase the current during each use is H={H1, H2, ..., H m }, and the current value set of the neurotherapy detector that is adjusted to increase during a random use is obtained as I={I1, I2, ..., I n }, m represents the number of times the neurotherapy detector has been used, and n represents the number of times the neurotherapy detector has been adjusted to increase the current during a random use; The initial battery charge of the neurotherapy detector each time it was used is collected as B={B1, B2, ..., B m }, the remaining power set after each use is b={b1, b2, ..., b m }.

4. A nerve treatment detection method according to claim 3, characterized in that: In step S102: the current change state coefficient R of the neurotherapy detector adjusted during a random use in the past is calculated according to the following formula: i : R i =[H i / ∑ m i=1 (H i )]+[(∑ n j=1 (I j )) / n]; Where i represents the i-th time the neurotherapy detector has been used in the past, I j represents the jth adjusted current value of the neurotherapy detector during the i-th use, and the current change state coefficient set of the neurotherapy detector during the previous m uses is calculated to be R={R1, R2, ..., R i , ..., R m }.

5. A nerve treatment detection method according to claim 4, characterized in that: In step S103: according to E i =(B i -b i ) / U i Analyze the unit power consumption E of the neurotherapy detector during its previous i-th use i , the unit power consumption set of the neurotherapy detector in the past m times of use is obtained as E={E1, E2, ..., E i , ..., E m }, B i represents the initial battery charge of the neurotherapy detector when it was used for the i-th time in the past, b i represents the remaining power after the i-th use. The initial power, current change state coefficient and unit power consumption of the battery of the neurotherapy detector are combined and preprocessed to generate training data {(B1, R1, E1), (B2, R2, E2), ..., (B i , R i , E i ), ..., (B m , R m , E m )}.

6. A nerve treatment detection method according to claim 5, characterized in that: In step S104: the training data {(B1, R1, E1), (B2, R2, E2), ..., (B i , R i , E i ), ..., (B m , R m , E m )}After fitting, the power consumption analysis model of the nerve treatment detector is established: Z = ξ0*X+ξ1*Y+ξ2; Among them, ξ0, ξ1 and ξ2 represent fitting coefficients, X represents the first independent variable representing the initial power of the battery in the power consumption analysis model, Y represents the second independent variable representing the current change state coefficient in the power consumption analysis model, and Z represents the dependent variable representing the unit power consumption in the power consumption analysis model.

7. A nerve treatment detection method according to claim 6, characterized in that: In step S105: the initial power of the battery of the current neurotherapy detector to be used is obtained as W, and the number of times the current of the current neurotherapy detector to be used was adjusted to increase when it was used to detect the target user is h={h1, h2, ..., h c }, c represents the number of times the current neurotherapy detector to be used has been used in the past, the target user refers to the user who needs to use the current neurotherapy detector to be used at the current time, and the set of current values ​​of the current neurotherapy detector to be used that is adjusted to increase during a random use is obtained as I ’ ={I1 ’ , I2 ’ , ..., I k ’ }, k represents the number of times the current of the currently used neurotherapy detector is adjusted to increase during a random one-time use, and the current change state coefficient r of the currently used neurotherapy detector during the previous random one-time use is calculated. e , r e =[h e / ∑ c e=1 (h e )]+[(∑ k v=1 (I v ’ )) / k],I v ’ represents the current value of the current that was adjusted and increased by the current of the current treatment detector to be used for the vth time during the previous use for the eth time. The current change state coefficient set of the current that was adjusted by the current treatment detector to be used for the cth time during the previous use is calculated in the same way as r={r1, r2, ..., r e , ..., r c }, and obtain the comprehensive current change state coefficient G when the current nerve treatment detector to be used is used to detect the target user, G=(∑ c e=1 (r e ’ )) / c, it is obtained that the planned usage time of the current neurotherapy detector to be used to detect the target user at the current time is T.

8. A nerve treatment detection method according to claim 7, characterized in that: Input W and G into the power consumption analysis model: let X=W, Y=G, and obtain the estimated unit power consumption of the battery of the current neurotherapy detector to be used as ξ0*W+ξ1*G+ξ2. The predicted estimated power consumption of the battery of the current neurotherapy detector to be used is T*(ξ0*W+ξ1*G+ξ2). Compare W and T*(ξ0*W+ξ1*G+ξ2): if WT*(ξ0*W+ξ1*G+ξ2)≥0, it is predicted that the neurotherapy detector to be used will not have an abnormal battery depletion during use, and choose not to prompt before using the device; if WT*(ξ0*W+ξ1*G+ξ2)<0, it is predicted that the neurotherapy detector to be used will have an abnormal battery depletion during use, and choose to prompt before using the device: remind the user to charge the neurotherapy detector to be used before use.

9. A neurotherapy detector, characterized in that: The neurotherapy detector adopts a neurotherapy detection method as described in any one of claims 1-8.

Images