A health scanning method and system based on multi-dimensional slow waves and AI

Abstract

The present invention provides a health scanning method and system based on multi-dimensional slow waves and AI, belonging to the technical field of data processing. Specifically, it includes: determining the distribution data of body movement data in the data analysis period, and combining the distribution data of the data deviation period in the adjacent period of the data analysis period to determine the data credibility coefficient and the credible data period of different data analysis periods. Obtain the slow wave monitoring data of monitoring devices in different dimensions during the credible data period. Based on the slow wave monitoring data and the body movement data at the corresponding moment, use a preset AI model to determine the matching scanning results in different credible data periods. Based on the matching scanning results and the credibility coefficient in different credible data periods, determine whether the output of the body scanning result of the tester can be performed, improving the accuracy of the body scanning result.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a health scanning method and system based on multi-dimensional slow waves and AI. Background Art

[0002] With the rapid economic development, people's pursuit of sleep health and quality of life is getting higher and higher. At the same time, with the acceleration of the pace of life, the number of people with sleep quality disorders is increasing day by day. In order to identify and process people with sleep disorders, in the invention patent application CN202410140388.9, "A Near-Infrared Spectroscopy Physical and Mental Stress and Sleep Quality Monitoring System", near-infrared spectroscopy data is used to calculate the physiological characteristics of the test personnel, and a sleep state recognition model is established in combination with a classification algorithm. At the same time, an analysis model is constructed by combining frequency domain change technology to analyze and evaluate the physical signs of the test personnel from multiple dimensions. However, through analysis, the following technical problems exist:

[0003] During the evaluation of sleep disorders, when the test personnel are in the time period of frequent turning over and moving, the slow wave data such as electroencephalogram signals, ultrasonic echoes, and infrared blood oxygen will inevitably change. Therefore, if the above slow wave change data is ignored, the accuracy of the scanning results of the sleep disorders of the test personnel cannot be guaranteed.

[0004] In view of the above technical problems, specifically, the present application provides a health scanning method and system based on multi-dimensional slow waves and AI. Summary of the Invention

[0005] To achieve the object of the present invention, the present invention adopts the following technical solutions:

[0006] A health scanning method based on multi-dimensional slow waves and AI specifically includes:

[0007] S1 Based on the analysis results of the body movement data of the test personnel in different time periods, determine the distribution data of the body movement data at different times, and use the distribution data to divide the time period into a data analysis time period and a data deviation time period;

[0008] S2 Determine the distribution data of the body movement data in the data analysis time period, and combine the distribution data of the data deviation time period in the adjacent time period of the data analysis time period to determine the data credibility coefficient and the credible data time period of different data analysis time periods;

[0009] S3 Obtain the slow wave monitoring data of different dimensions of the monitoring device in the credible data time period. Based on the slow wave monitoring data and the body movement data at the corresponding time, use a preset AI model to determine the matching scanning results in different credible data time periods;

[0010] S4 determines whether the output of the physical scan result of the tester can be performed based on the matching scan results and the credibility coefficients in different credible data periods.

[0011] The beneficial effects of the present invention are as follows:

[0012] Based on the slow-wave monitoring data and the body movement data at the corresponding moments, the matching scan results in different credible data periods are determined by using a preset AI model. This not only takes into account the difference in the credibility of the slow-wave monitoring data caused by the difference in the body movement data at different moments in the credible period, but also realizes the determination of the matching scan results by using the preset AI model based on the slow-wave monitoring data at different moments in the credible period, ensuring the accuracy of the physical scan results in different credible data periods.

[0013] Based on the matching scan results and the credibility coefficients in different credible data periods, it is determined whether the output of the physical scan result of the tester can be performed, thus avoiding the technical problem of insufficient reliability of the output result of the physical scan result of the tester caused by solely considering the matching scan results in a certain credible data period, and realizing the output of the physical scan result of the tester from the matching scan results in multiple credible data periods, improving the accuracy of the physical scan result.

[0014] A further technical solution is that the period is divided according to a preset unit duration.

[0015] A further technical solution is that the body movement data is determined based on the monitoring data of the inertial sensing chip installed in the sleep chamber.

[0016] A further technical solution is that the period is divided into a data analysis period and a data deviation period, specifically including:

[0017] Based on the distribution data of the body movement data at different moments, the moments with body movement data in the period are determined and used as body movement moments;

[0018] The period is divided into a data analysis period and a data deviation period according to the quantity proportion of the body movement moments.

[0019] A further technical solution is that the period is divided into a data analysis period and a data deviation period according to the quantity proportion of the body movement moments, specifically including:

[0020] When the quantity proportion of the body movement moments in the period is not greater than the preset quantity proportion, it is determined that the period is a data analysis period;

[0021] When the proportion of the number of body movement moments in the time period is greater than the preset proportion, it is determined that the time period is a data deviation time period.

[0022] A further technical solution lies in determining whether the output of the body scan result of the tester can be performed, specifically including:

[0023] Using the matching scan results in different credible data time periods, determine the credible data time periods corresponding to different types of matching scan results;

[0024] According to the sum of the credibility coefficients of the credible data time periods corresponding to different types of matching scan results, determine the sum of the credibility coefficients of different types of matching scan results;

[0025] Based on the sum of the credibility coefficients of different types of matching scan results, determine whether the output of the body scan result of the tester can be performed.

[0026] A further technical solution lies in determining whether the output of the body scan result of the tester can be performed based on the sum of the credibility coefficients of different types of matching scan results, specifically including:

[0027] When there is no matching scan result with a sum of credibility coefficients greater than the credibility coefficient setting value, it is determined that the output of the body scan result of the tester cannot be performed;

[0028] When there is a matching scan result with a sum of credibility coefficients greater than the credibility coefficient setting value, and when there is only one matching scan result with a sum of credibility coefficients greater than the credibility coefficient setting value, then use the matching scan result with the largest sum of credibility coefficients as the body scan result of the tester;

[0029] When there are multiple matching scan results with a sum of credibility coefficients greater than the credibility coefficient setting value, it is determined that the output of the body scan result of the tester cannot be performed.

[0030] In a second aspect, the present invention provides a computer system, including: a memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, and when the processor runs the computer program, it executes the above-mentioned health scan method based on multi-dimensional slow waves and AI.

[0031] Other features and advantages will be described in the subsequent specification, and the objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0032] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specifically lists preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. Description of the Drawings

[0033] The above and other features and advantages of the present invention will become more apparent by describing in detail its exemplary embodiments with reference to the accompanying drawings;

[0034] Figure 1 is a flowchart of a health scanning method based on multi-dimensional slow waves and AI;

[0035] Figure 2 is a flowchart of a method for dividing a time period into a data analysis period and a data deviation period;

[0036] Figure 3 is a flowchart of a method for determining the data credibility coefficient in the data analysis period;

[0037] Figure 4 is a flowchart of a method for determining the matching scan results in the credible data period;

[0038] Figure 5 is a flowchart of a method for determining whether the body scan results of the tester can be output;

[0039] Figure 6 is a framework diagram of a computer system. Detailed Embodiments

[0040] In order to enable those skilled in the art of the present technology to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0041] When the tester is in a time period of frequent turning over and moving, the slow wave data such as electroencephalogram signals, ultrasonic echoes, and infrared blood oxygen will inevitably change. Therefore, it is necessary to comprehensively consider the slow wave change data to ensure the accuracy of the scan results of the tester's sleep disorder.

[0042] When the proportion of the number of moments with body movement data is greater than 0.6, it is determined that the time period is a data deviation period. When the proportion of the number of moments with body movement data is not greater than 0.6, it is determined that the time period is a data analysis period.

[0043] Take the proportion of the number of moments with body movement data in the data analysis period in the data analysis period as the proportion of the number of body movement moments, take the proportion of the number of data deviation periods in the adjacent period of the data analysis period, and take it as the proportion of the number of deviation periods. Determine the data credibility coefficient of the data analysis period according to the average value of the proportion of the number of body movement moments and the proportion of the number of deviation periods, and take the data analysis period with a data credibility coefficient greater than 0.8 as the credible data period.

[0044] The AI model is built using a fuzzy neural network and a multi-layer neural network algorithm model.

[0045] Take the matching scan result with the maximum credibility coefficient as the output of the tester's body scan result.

[0046] Intelligent algorithms include Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Decision Trees, Random Forests, and K-Nearest Neighbors (KNN).

[0047] Example 1 To solve the above problems, according to one aspect of the present invention, as Figure 1 shown, provide a health scanning method based on multi-dimensional slow waves and AI, specifically including:

[0048] S1 Determine the distribution data of body movement data at different moments based on the analysis results of the tester's body movement data in different periods, and use the distribution data to divide the period into a data analysis period and a data deviation period;

[0049] Further, the period is divided according to a preset unit duration.

[0050] Specifically, the body movement data is determined according to the monitoring data of the inertial sensing chip installed in the sleep cabin.

[0051] It should be noted that, as Figure 2 shown, dividing the period into a data analysis period and a data deviation period specifically includes:

[0052] Determine the moments with body movement data in the period based on the distribution data of body movement data at different moments, and take it as the body movement moment;

[0053] Divide the period into a data analysis period and a data deviation period according to the proportion of the number of the body movement moments.

[0054] Further, divide the time period into a data analysis time period and a data deviation time period according to the proportion of the number of body movement moments, specifically including:

[0055] When the proportion of the number of body movement moments in the time period is not greater than the preset proportion, determine that the time period is a data analysis time period;

[0056] When the proportion of the number of body movement moments in the time period is greater than the preset proportion, determine that the time period is a data deviation time period.

[0057] Optionally, dividing the time period into a data analysis time period and a data deviation time period specifically includes:

[0058] Based on the distribution data of body movement data at different times, determine the moments with body movement data in the time period and use them as body movement moments;

[0059] According to the distribution data of body movement moments in different unit time periods, determine the proportion of the number of body movement moments in different unit time periods;

[0060] Use the proportion of the number of body movement moments to determine the body movement unit time periods in the unit time period, and divide the time period into a data analysis time period and a data deviation time period using the number of the body movement unit time periods.

[0061] Specifically, dividing the time period into a data analysis time period and a data deviation time period using the number of the body movement unit time periods specifically includes:

[0062] When the number of the body movement unit time periods is greater than the preset time period number, determine that the time period is a data deviation time period;

[0063] When the number of the body movement unit time periods is not greater than the preset time period number, determine that the time period is a data analysis time period.

[0064] In another embodiment, dividing the time period into a data analysis time period and a data deviation time period specifically includes:

[0065] S11 Based on the distribution data of body movement data at different times, determine the moments with body movement data in the time period and use them as body movement moments;

[0066] Optionally, the above step S11 includes the following content:

[0067] S111 Based on the distribution data of body movement data at different times, determine the moments with body movement data in the time period and use them as body movement moments. When the number of body movement moments in the time period is less than the preset body movement moment number threshold, go to step S112; when the number of body movement moments in the time period is not less than the preset body movement moment number threshold, go to step S113;

[0068] Based on the interval data between different body movement times, when it is determined that the number of interval times between different body movement times is greater than the preset interval time number, then it is determined that the time period is a data analysis time period. When there is a body movement time with the number of interval times not greater than the preset interval time number, it proceeds to step S12;

[0069] In S113, when the number of body movement times in the time period is greater than the preset time number threshold, then it is determined that the time period is a data deviation time period. When the number of body movement times in the time period is not greater than the preset time number threshold, it proceeds to step S12.

[0070] In S12, based on the distribution data of body movement times in different unit time periods, determine the proportion of the number of body movement times in different unit time periods. Based on the proportion of the number of body movement times in different unit time periods and the interval data between different body movement times, determine the data deviation coefficient of different unit time periods;

[0071] Optionally, the following content is included in the above step S12:

[0072] In S121, based on the distribution data of body movement times in different unit time periods, determine the proportion of the number of body movement times in different unit time periods. When there is a unit time period with the proportion of the number of body movement times greater than the preset proportion, it proceeds to step S122. When there is no unit time period with the proportion of the number of body movement times greater than the preset proportion, it proceeds to step S123;

[0073] In S122, when the number of unit time periods with the proportion of the number of body movement times greater than the preset proportion does not meet the requirements, then it is determined that the time period is a data deviation time period. When the number of unit time periods with the proportion of the number of body movement times greater than the preset proportion meets the requirements, it proceeds to step S123;

[0074] In S123, based on the proportion of the number of body movement times in different unit time periods and the interval data between different body movement times, determine the data deviation coefficient of different unit time periods. When the data deviation coefficients of different unit time periods are all less than the preset deviation coefficient threshold, it proceeds to step S124. When there is a unit time period with the data deviation coefficient not less than the preset deviation coefficient threshold, it proceeds to step S125;

[0075] In S124, when the number of unit time periods with body movement times is within the preset time period number range, then it is determined that the time period is a data analysis time period. When the number of unit time periods with body movement times is not within the preset time period number range, it proceeds to step S13;

[0076] S125 When the number of unit time periods with a data deviation coefficient not less than the preset deviation coefficient threshold is greater than the preset deviation time period number, determine that the time period is a data deviation time period. When the number of unit time periods with a data deviation coefficient not less than the preset deviation coefficient threshold is not greater than the preset deviation time period number, proceed to step S13.

[0077] S13 Determine a comprehensive deviation coefficient using the data deviation coefficients of different unit time periods, and divide the time period into a data analysis time period and a data deviation time period using the comprehensive deviation coefficient.

[0078] Furthermore, the comprehensive deviation coefficient is determined based on the weighted sum of the data deviation coefficients of different unit time periods.

[0079] S2 Determine the distribution data of the body movement data in the data analysis time period, and combine the distribution data of the data deviation time periods in the adjacent time periods of the data analysis time period to determine the data credibility coefficients and credible data time periods of different data analysis time periods;

[0080] Specifically, the adjacent time period is a time period with a deviation from the data analysis time period within a preset time length interval.

[0081] Specifically, as Figure 3 shown, the method for determining the data credibility coefficient of the data analysis time period is:

[0082] Based on the distribution data of the body movement data in the data analysis time period, determine the moments with body movement data in the data analysis time period, and use them as body movement moments. Take the proportion of the number of body movement moments in the data analysis time period as the proportion of the number of body movement moments;

[0083] Determine the proportion of the number of data deviation time periods in the adjacent time period of the data analysis time period, and use it as the proportion of the number of deviation time periods;

[0084] Determine the data credibility coefficient of the data analysis time period based on the average value of the proportion of the number of body movement moments and the proportion of the number of deviation time periods.

[0085] Furthermore, the data credibility coefficient of the data analysis time period is determined based on the deviation amount between the preset value and the average value of the proportion of the number of body movement moments and the proportion of the number of deviation time periods.

[0086] It should be noted that the method for determining the data credibility coefficient of the data analysis time period is:

[0087] Based on the distribution data of the body movement data in the data analysis time period, determine the moments with body movement data in the data analysis time period, and use them as body movement moments;

[0088] Determine the number of data deviation periods in the adjacent period of the data analysis period;

[0089] Based on the body movement moment, the number of data deviation periods, and determine the data credibility coefficient of the data analysis period.

[0090] Furthermore, the data credibility coefficient of the data analysis period is determined according to the body movement moment, the number of data deviation periods, and the corresponding preset credibility coefficient.

[0091] Furthermore, the value range of the data credibility coefficient of the data analysis period is between 0 and 1. When the data credibility coefficient of the data analysis period is greater than the preset credibility coefficient threshold, it is determined that the data analysis period is a credible data period.

[0092] S3 Obtain the slow wave monitoring data of the monitoring devices in different dimensions during the credible data period. Based on the slow wave monitoring data and the body movement data at the corresponding moments, use a preset AI model to determine the matching scan results in different credible data periods;

[0093] Specifically, as Figure 4 shown, the method for determining the matching scan results in the credible data period is:

[0094] Based on the body movement data at different moments, determine the preset credible weight coefficients at different moments;

[0095] Use the slow wave monitoring data in different dimensions at different moments as input quantities, and use the output results of the preset AI model to determine the matching scan results at different moments;

[0096] Based on the matching scan results at different moments, determine the sum of the preset credible weight coefficients corresponding to different types of scan results, and use the sum of the preset credible weight coefficients to determine the matching scan results in the credible data period.

[0097] Furthermore, the preset credible weight coefficient is determined according to whether there is body movement data in the moment.

[0098] Optionally, the slow wave monitoring data includes respiratory data, heartbeat data, electroencephalogram signal data, cerebral blood pressure, cerebral blood oxygen, and ultrasonic echo.

[0099] S4 Based on the matching scan results and the credibility coefficients in different credible data periods, determine whether the body scan results of the test person can be output.

[0100] Specifically, as Figure 5 shown, determining whether the body scan results of the test person can be output specifically includes:

[0101] Determine the trusted data periods corresponding to different types of matching scan results based on the matching scan results in different trusted data periods;

[0102] Determine the sum of the trust coefficients of different types of matching scan results based on the sum of the trust coefficients of the trusted data periods corresponding to different types of matching scan results;

[0103] Based on the sum of the trust coefficients of different types of matching scan results, determine whether the output of the physical scan results of the tester can be performed.

[0104] Furthermore, based on the sum of the trust coefficients of different types of matching scan results, determine whether the output of the physical scan results of the tester can be performed, specifically including:

[0105] When there is no matching scan result with a sum of trust coefficients greater than the trust coefficient setting value, it is determined that the output of the physical scan results of the tester cannot be performed;

[0106] When there is a matching scan result with a sum of trust coefficients greater than the trust coefficient setting value, and when there is only one matching scan result with a sum of trust coefficients greater than the trust coefficient setting value, then use the matching scan result with the largest sum of trust coefficients as the physical scan results of the tester;

[0107] When there are multiple matching scan results with a sum of trust coefficients greater than the trust coefficient setting value, it is determined that the output of the physical scan results of the tester cannot be performed.

[0108] Furthermore, the matching scan results include primary sleep disorder, secondary sleep disorder, and no sleep disorder.

[0109] In another embodiment, determining whether the output of the physical scan results of the tester can be performed specifically includes:

[0110] Based on the matching scan results in different trusted data periods, when the matching scan results in different trusted periods are the same, then use the matching scan results as the physical scan results of the tester;

[0111] When there are multiple types of matching scan results in different trusted data periods: determine the trusted data periods corresponding to different types of matching scan results. When the number of trusted data periods corresponding to different types of matching scan results is less than the preset quantity threshold, it is determined that the output of the physical scan results of the tester cannot be performed;

[0112] When there is a type of matching scan result with a number of trusted data periods not less than the preset quantity threshold:

[0113] When there is only one type of matching scan result in which the number of credible data periods is not less than the preset number threshold, it is determined that the output of the physical scan result of the tester can be performed;

[0114] When there are multiple types of matching scan results in which the number of credible data periods is not less than the preset number threshold, the sum of the credible coefficients of the credible data periods corresponding to the different types of matching scan results is used to determine the sum of the credible coefficients of the different types of matching scan results. When the sum of the credible coefficients of the different types of matching scan results is less than the preset coefficient setting value, it is determined that the output of the physical scan result of the tester cannot be performed;

[0115] When there is a type of matching scan result in which the sum of the credible coefficients is not less than the preset coefficient setting value:

[0116] When the type of matching scan result with the largest sum of credible coefficients is used as the candidate scan result, and when there is a matching scan result whose deviation from the sum of the credible coefficients of the candidate scan result is less than the preset credible coefficient deviation, it is determined that the output of the physical scan result of the tester cannot be performed;

[0117] When there is no matching scan result whose deviation from the sum of the credible coefficients of the candidate scan result is less than the preset credible coefficient deviation,

[0118] Based on the sum of the credible coefficients of the candidate scan result and the deviation of other matching scan results from the credible coefficient of the candidate scan result, the comprehensive credible coefficient is determined, and the comprehensive credible coefficient is used to determine whether the output of the physical scan result of the tester can be performed.

[0119] Furthermore, when the comprehensive credible coefficient is greater than the credible coefficient setting threshold, it is determined that the output of the physical scan result of the tester can be performed.

[0120] In the second aspect of Embodiment 2, as Figure 6 shown, the present invention provides a computer system, including: a memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor. When the processor runs the computer program, it executes the above-mentioned health scan method based on multi-dimensional slow waves and AI.

[0121] Optionally, the method for determining the data credible coefficient of the data analysis period is:

[0122] Determine the moments with body movement data in the data analysis period based on the distribution data of the body movement data in the data analysis period, and use them as body movement moments. When the number of body movement moments is not within the preset moment number range, and it is determined that there is a data deviation period in the adjacent period of the data analysis period, then it is determined that the data analysis period does not belong to the reliable data period;

[0123] When there is no data deviation period in the adjacent period of the data analysis period, then use the number of body movement moments to determine the data reliability coefficient of the data analysis period;

[0124] When the number of body movement moments is within the preset moment number range:

[0125] Determine the number of data deviation periods in the adjacent period of the data analysis period. When the sum of the number of body movement moments and the number of data deviation periods does not meet the requirements, then it is determined that the data analysis period does not belong to the reliable data period;

[0126] When the sum of the number of body movement moments and the number of data deviation periods meets the requirements:

[0127] Determine the basic anomaly coefficient of the data analysis period based on the number of body movement moments in the data analysis period and the number of interval moments between different body movement moments. When the basic anomaly coefficient is greater than the preset anomaly coefficient threshold:

[0128] When there is a data deviation period, then it is determined that the data analysis period does not belong to the reliable data period;

[0129] When there is no data deviation period, use the basic anomaly coefficient of the data analysis period to determine the data reliability coefficient of the data analysis period;

[0130] When the basic anomaly coefficient is not greater than the preset anomaly coefficient threshold:

[0131] Determine the adjacent anomaly coefficient based on the proportion of the number of data deviation periods in the adjacent period and the interval periods between different data deviation periods and the data analysis period. When the average value of the adjacent anomaly coefficient and the basic anomaly coefficient does not meet the requirements, then it is determined that the data analysis period does not belong to the reliable data period;

[0132] When the average value of the adjacent anomaly coefficient and the basic anomaly coefficient meets the requirements:

[0133] Determine the data reliability coefficient of the data analysis period based on the adjacent anomaly coefficient and the basic anomaly coefficient.

[0134] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus, device, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0135] The specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0136] The above description is only for one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, various changes and modifications can be made to one or more embodiments of this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A health scanning method based on multi-dimensional slow waves and AI, characterized in that, Specifically include: Based on the analysis results of the body movement data of the testers in different time periods, determine the distribution data of the body movement data at different times, and use the distribution data to divide the time period into a data analysis time period and a data deviation time period; Determine the distribution data of the body movement data in the data analysis time period, and combine the distribution data of the data deviation time period in the adjacent time period of the data analysis time period to determine the data credibility coefficient and the credible data time period of different data analysis time periods; Obtain the slow wave monitoring data of the monitoring devices in different dimensions in the credible data time period. Based on the slow wave monitoring data and the body movement data at the corresponding time, use a preset AI model to determine the matching scan results in different credible data time periods; Based on the matching scan results and the credibility coefficient in different credible data time periods, determine whether the body scan results of the tester can be output; The method for determining the matching scan results in the credible data time period is as follows: Based on the body movement data at different times, determine the preset credible weight coefficients at different times; Use the slow wave monitoring data in different dimensions at different times as input quantities, and use the output results of the preset AI model to determine the matching scan results at different times; Based on the matching scan results at different times, determine the sum of the preset credible weight coefficients corresponding to different types of scan results, and use the sum of the preset credible weight coefficients to determine the matching scan results in the credible data time period; Determining whether the body scan results of the tester can be output specifically includes: Based on the matching scan results in different credible data time periods, determine the credible data time periods corresponding to different types of matching scan results; According to the sum of the credibility coefficients of the credible data time periods corresponding to different types of matching scan results, determine the sum of the credibility coefficients of different types of matching scan results; Based on the sum of the credibility coefficients of different types of matching scan results, determine whether the body scan results of the tester can be output; When there is no matching scan result with a credibility coefficient sum greater than the set value of the credibility coefficient, it is determined that the body scan results of the tester cannot be output; When there is a matching scan result with a credibility coefficient sum greater than the set value of the credibility coefficient, and when there is only one matching scan result with a credibility coefficient sum greater than the set value of the credibility coefficient, then use the matching scan result with the largest credibility coefficient sum as the body scan result of the tester; When there are multiple matching scan results with a credibility coefficient sum greater than the set value of the credibility coefficient, it is determined that the body scan results of the tester cannot be output.

2. The health scanning method based on multi-dimensional slow waves and AI according to claim 1, wherein The time period is divided according to a preset unit time length.

3. The health scanning method based on multi-dimensional slow waves and AI according to claim 1, characterized in that, The body movement data is determined according to the monitoring data of the inertial sensing chip installed in the sleep cabin.

4. The health scanning method based on multi-dimensional slow waves and AI according to claim 1, characterized in that Dividing the time period into a data analysis time period and a data deviation time period specifically includes: Based on the distribution data of the body movement data at different times, determine the times when there is body movement data in the time period, and use them as body movement times; Divide the time period into a data analysis time period and a data deviation time period according to the proportion of the number of body movement times.

5. The health scanning method based on multi-dimensional slow waves and AI according to claim 4, characterized in that Divide the time period into a data analysis time period and a data deviation time period according to the proportion of the number of body movement moments, specifically including: When the proportion of the number of body movement moments in the time period is not greater than a preset proportion, determine that the time period is a data analysis time period; When the proportion of the number of body movement moments in the time period is greater than the preset proportion, determine that the time period is a data deviation time period.

6. The health scanning method based on multi-dimensional slow waves and AI according to claim 1, characterized in that, The adjacent time period is a time period whose deviation from the data analysis time period is within a preset time period range.

7. The health scanning method based on multi-dimensional slow waves and AI according to claim 1, characterized in that, The method for determining the data credibility coefficient of the data analysis time period is as follows: Based on the distribution data of the body movement data in the data analysis time period, determine the moments with body movement data in the data analysis time period, and use them as body movement moments. Use the proportion of the number of body movement moments in the data analysis time period as the proportion of the number of body movement moments; Determine the proportion of the number of data deviation time periods in the adjacent time period of the data analysis time period, and use it as the proportion of the number of deviation time periods; Determine the data credibility coefficient of the data analysis time period according to the average value of the proportion of the number of body movement moments and the proportion of the number of deviation time periods.

8. A computer system, comprising: A memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, wherein when the processor runs the computer program, it executes a health scanning method based on multi-dimensional slow waves and AI according to any one of claims 1-7.

Images