A detection method for evaluating psychological state through wearable devices

Abstract

The present invention provides a detection method for evaluating psychological state through a wearable device, comprising: S1: obtaining a user's pulse sensor signal and physiological indicators and environmental indicators within a preset period through the wearable device; S2: determining a corresponding pulse wave feature point set based on the pulse sensor signal; S3: obtaining a final psychological state detection result based on massive data from a big data platform and the pulse wave feature point set, in combination with the physiological indicators and the environmental indicators; S4: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result; based on the big data platform, utilizing the characteristics of the pulse signal and the physiological indicators and environmental indicators related to the user's health and life patterns, in combination with massive data, a comprehensive analysis of the user's psychological state is performed, thereby overcoming the problem of large information monotony error in traditional detection methods and greatly improving the detection accuracy of the psychological state.

Description

Technical Field

[0001] The present invention relates to the technical field of psychological assessment, and in particular to a detection method for assessing psychological state through a wearable device. Background Art

[0002] Currently, heart rate monitoring features in smart wearable products, such as smart bracelets and smart watches, are gaining increasing acceptance, with some even considering it a must-have feature. Heart rate variability can be used to analyze autonomic nervous system function, such as stress, tension and relaxation levels, and sleep quality.

[0003] However, the current methods of using wearable devices to assess mental states have the following problems:

[0004] 1. Mental states have many complex classifications and fuzzy distinctions, and current data is not comprehensive enough;

[0005] 2. If the user is affected by factors such as illness, the information may be inaccurate, affecting the detection accuracy;

[0006] 3. Non-wearable devices cannot detect psychological states in a long-term and real-time manner;

[0007] 4. The collected information is monotonous. The psychological state is affected by many factors, and only considering the electrocardiogram characteristics will result in large errors.

[0008] Therefore, the present invention proposes a detection method for evaluating psychological state through a wearable device. Summary of the Invention

[0009] The present invention provides a detection method for assessing psychological state through wearable devices. Based on the support of a big data platform, the method utilizes the characteristics of pulse signals and physiological and environmental indicators related to the user's health, lifestyle, etc., and combines massive data to comprehensively analyze the user's psychological state. This overcomes the problem of large errors in information monotony caused by traditional detection methods and greatly improves the accuracy of psychological state detection.

[0010] The present invention provides a detection method for evaluating psychological state through a wearable device, comprising:

[0011] S1: Obtain the user's pulse sensor signal and physiological indicators and environmental indicators within a preset period through the wearable device;

[0012] S2: determining a corresponding pulse wave feature point set based on the pulse sensing signal;

[0013] S3: Based on the massive data of the big data platform and the set of pulse wave feature points, and in combination with the physiological indicators and the environmental indicators, a final psychological state detection result is obtained;

[0014] S4: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result.

[0015] Preferably, the method for evaluating a psychological state through a wearable device, S1: obtaining a user's pulse sensor signal and various physiological indicators within a preset period through the wearable device, includes:

[0016] S101: Acquire a pulse sensor signal corresponding to the user based on a pulse sensor provided on the wearable device;

[0017] S102: Based on the biosensors provided on the wearable device, obtaining the user's exercise monitoring data, respiratory monitoring data, sleep monitoring data, body temperature monitoring data, blood pressure monitoring data, and oxygen supply detection data within a preset period, and simultaneously, combining the medical history data input by the user, obtaining the user's corresponding physiological indicators;

[0018] S103: Acquire temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user's environment within a preset period based on a network platform as corresponding environmental indicators.

[0019] Preferably, the detection method for evaluating psychological state through a wearable device, S103: obtaining the temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user within a preset period as corresponding environmental indicators based on a network platform, includes:

[0020] Establishing a communication link between the wearable device and the network platform;

[0021] Acquiring the user's location information based on a built-in GPS module of the wearable device;

[0022] Based on the communication link and the location information, the temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user's environment within a preset period are retrieved from the network platform in real time as corresponding environmental indicators.

[0023] Preferably, the detection method for evaluating psychological state through a wearable device, S2: determining a corresponding set of pulse wave feature points based on the pulse sensing signal, includes:

[0024] performing noise reduction and filtering on the pulse sensing signal to obtain a corresponding first pulse sensing signal;

[0025] performing noise reduction filtering on the pulse sensing signal to obtain a corresponding first pulse sensing signal;

[0026] removing a baseline interference signal in a low-frequency band from the first pulse sensing signal to obtain a corresponding second pulse sensing signal;

[0027] performing wavelet packet decomposition on the second pulse sensor signal to obtain a corresponding decomposition result, and performing multi-band denoising on the pulse sensor signal segment based on the decomposition result to obtain a corresponding denoising result;

[0028] Reconstruct all denoising results to obtain the corresponding reconstructed pulse wave signal;

[0029] All pulse wave feature points are determined in the reconstructed pulse wave signal to obtain a corresponding pulse wave feature point set.

[0030] Preferably, the detection method for assessing psychological state through a wearable device is characterized in that the second pulse sensor signal is subjected to wavelet packet decomposition to obtain a corresponding decomposition result, and multi-band denoising is performed on the pulse sensor signal segment based on the decomposition result to obtain a corresponding low-noise signal segment, including:

[0031] decomposing the second pulse sensing signal into a pulse sensing scaling function and a pulse sensing wavelet function;

[0032] performing bandpass filtering on the second pulse sensor signal to obtain a corresponding filtered signal;

[0033] Calculating a periodic evaluation mean of the filtered signal;

[0034] Determining the corresponding number of decomposition layers based on the periodic evaluation mean;

[0035] Decomposing the pulse sensing scaling function and the pulse sensing wavelet function based on the number of decomposition layers to obtain corresponding scaling wavelet packet decomposition trees and sensing wavelet packet decomposition trees;

[0036] Determining a corresponding first wavelet packet decomposition coefficient based on the scale wavelet packet decomposition tree, and determining a corresponding second wavelet packet decomposition coefficient based on the sensing wavelet packet decomposition tree, and using the scale wavelet packet decomposition tree and the sensing wavelet packet decomposition tree as corresponding decomposition results;

[0037] Correspondingly associating the nodes of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree to obtain corresponding associated nodes;

[0038] Based on the first wavelet packet decomposition coefficient, the second wavelet packet decomposition coefficient and the associated node, obtaining a two-dimensional coefficient vector corresponding to the associated node of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree;

[0039] Calculating a similarity measure between the two-dimensional coefficient vector and an average value of the two-dimensional coefficient vectors corresponding to all associated nodes;

[0040] Determine whether the similarity metric value is less than a similarity metric threshold; if so, set the wavelet coefficient corresponding to the similarity metric value to zero; otherwise, retain the wavelet coefficient corresponding to the similarity metric value to obtain the corresponding retained wavelet coefficient;

[0041] Obtaining corresponding denoised scale wavelet packet decomposition trees and denoised sensor wavelet packet decomposition trees based on the retained wavelet coefficients;

[0042] The denoising scale wavelet packet decomposition tree and the denoising sensor wavelet packet decomposition tree are taken as corresponding denoising results.

[0043] Preferably, the detection method for assessing psychological state through a wearable device is characterized in that all pulse wave feature points are determined in the reconstructed pulse wave signal to obtain a corresponding set of pulse wave feature points, including:

[0044] Screening out all first maxima and all first minima contained in the reconstructed pulse wave signal, and determining a first average time interval between all adjacent first maxima and a second average time interval between all adjacent first minima in the reconstructed pulse wave signal;

[0045] determining a corresponding sampling period based on the first averaging time interval and the second averaging time interval;

[0046] determining a plurality of sampling points in the reconstructed pulse wave signal starting from a starting point of the reconstructed pulse wave signal based on the sampling period to obtain a corresponding sampling point set;

[0047] Randomly select a sampling point from the reference sampling point set as the corresponding reference sampling point;

[0048] Determining, in the reconstructed pulse wave signal, a second maximum value closest to the reference sampling point as a first feature point corresponding to the reference sampling point, and simultaneously determining a second minimum value closest to the reference sampling point as a second feature point corresponding to the reference sampling point;

[0049] Determine a first vector between the reference sampling point and the corresponding second maximum value and a second vector between the reference sampling point and the corresponding second minimum value;

[0050] Determining a third vector between the reference sampling point and the corresponding adjacent sampling point;

[0051] determining a first angle between the first vector and the third vector and a second angle between the second vector and the third vector;

[0052] Determine a first feature point corresponding to the adjacent sampling point based on the first angle and the third vector, and simultaneously determine a second feature point corresponding to the vector sampling point based on the second angle and the third vector;

[0053] Then, the adjacent sampling points are used as new reference sampling points to determine new first characteristic points and new second characteristic points, until all first characteristic points and all second characteristic points included in the reconstructed pulse wave signal are determined;

[0054] taking all extreme points in the reconstructed pulse wave signal except the extreme points that coincide with the first characteristic point and the second characteristic point as third characteristic points;

[0055] Based on all the first feature points, all the second feature points, and all the third feature points, a corresponding pulse wave feature point set is obtained.

[0056] Preferably, the method for evaluating a psychological state through a wearable device, S3: based on the massive data of the big data platform and the set of pulse wave feature points, and in combination with the physiological indicators and the environmental indicators, obtaining a final psychological state detection result, includes:

[0057] Extracting from the massive data a historical pulse wave feature point set and a corresponding historical psychological state detection result corresponding to the user, and a reference pulse wave feature point set and a corresponding reference psychological state detection result corresponding to an environmental indicator that is consistent with the environmental indicator as corresponding correction reference data;

[0058] Determining a corresponding first state coefficient based on the physiological indicator;

[0059] Determining a corresponding second state coefficient based on the environmental indicator;

[0060] determining a corresponding third state coefficient based on a first slope corresponding to a first feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, a second slope corresponding to a second feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, and the first and second average time intervals;

[0061] Obtaining a corresponding first mental state detection result based on the first state coefficient, the second state coefficient, and the third state coefficient;

[0062] The first mental state detection result is corrected based on the correction reference data to obtain a corresponding final mental state detection result.

[0063] Preferably, the method for evaluating a mental state through a wearable device, correcting the first mental state detection result based on the correction reference data to obtain the corresponding final mental state detection result, includes:

[0064] Correcting the first mental state detection result based on the historical pulse wave feature point set and the historical mental state detection result to obtain a corresponding first correction result;

[0065] The first correction result is corrected based on the reference pulse wave feature point set and the reference psychological state detection result to obtain a corresponding final psychological state detection result.

[0066] Preferably, the method for evaluating a psychological state through a wearable device, S4: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result, includes:

[0067] S401: Obtain a link identification mark corresponding to the information category contained in the information storage table corresponding to the user in the big data platform;

[0068] S402: Based on the link identification mark, the pulse wave feature point set and the corresponding final psychological state detection result are updated to the big data platform to obtain a data update result.

[0069] Preferably, the method for evaluating a psychological state through a wearable device, S402: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform based on the link identification mark to obtain a data update result, includes:

[0070] Based on the link identification mark corresponding to the corresponding information category, establishing a first data update link between the pulse wave feature point set and the corresponding information category in the information storage table, and a second data update link between the final mental state detection result and the corresponding information category in the information storage table;

[0071] Based on the first data update link, the pulse wave feature point set is updated to the corresponding information category in the corresponding information storage table in the big data platform. At the same time, based on the second data update link, the final psychological state detection result is updated to the corresponding information category in the corresponding information storage table in the big data platform to obtain the data update result.

[0072] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0073] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] 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:

[0075] Figure 1 This is a flow chart of a detection method for assessing psychological state through a wearable device in an embodiment of the present invention;

[0076] Figure 2 This is a flow chart of another detection method for assessing psychological state through a wearable device in an embodiment of the present invention;

[0077] Figure 3 This is a flow chart of another detection method for assessing psychological state through a wearable device in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] The preferred embodiments of the present invention are described below with reference to 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.

[0079] Example 1:

[0080] The present invention provides a detection method for evaluating psychological state through wearable devices, referring to Figure 1 ,include:

[0081] S1: Obtain the user's pulse sensor signal and physiological indicators and environmental indicators within a preset period through the wearable device;

[0082] S2: determining a corresponding pulse wave feature point set based on the pulse sensing signal;

[0083] S3: Based on the massive data of the big data platform and the set of pulse wave feature points, and in combination with the physiological indicators and the environmental indicators, a final psychological state detection result is obtained;

[0084] S4: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result.

[0085] In this embodiment, the pulse sensing signal is a wave signal representing the user's pulse obtained based on the wearable device.

[0086] In this embodiment, the physiological indicators are indicators representing the user's physiological conditions within a preset period and obtained based on the wearable device.

[0087] In this embodiment, the environmental index is an index obtained based on the wearable device that represents the environmental conditions in the user's environment.

[0088] In this embodiment, the pulse wave feature point set is a set consisting of all pulse wave feature points determined in the pulse sensing signal.

[0089] In this embodiment, the final psychological state detection result is a detection result for evaluating the user's psychological state obtained based on massive data and a set of pulse wave feature points on a big data platform, combined with corresponding physiological indicators and environmental indicators.

[0090] In this embodiment, the big data platform is used to store data such as pulse wave feature point sets, physiological indicators, environmental indicators, etc. related to psychological state assessment of a large number of users.

[0091] In this embodiment, the massive data refers to a set of pulse wave feature points, physiological indicators, environmental indicators and other data related to psychological state assessment of a large number of users.

[0092] In this embodiment, the data update result is the result obtained after updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform.

[0093] The beneficial effects of the above technology are: based on the support of the big data platform, it utilizes the characteristics of the pulse signal and physiological and environmental indicators related to the user's health, life patterns, etc., and combines massive data to comprehensively analyze the user's psychological state, overcoming the problem of large errors in information monotony caused by traditional detection methods, and greatly improving the accuracy of psychological state detection.

[0094] Example 2:

[0095] Based on Example 1, the method for evaluating psychological state through a wearable device is as follows: S1: obtaining the user's pulse sensor signal and various physiological indicators within a preset period through the wearable device, referring to Figure 2 ,include:

[0096] S101: Acquire a pulse sensor signal corresponding to the user based on a pulse sensor provided on the wearable device;

[0097] S102: Based on the biosensors provided on the wearable device, obtaining the user's exercise monitoring data, respiratory monitoring data, sleep monitoring data, body temperature monitoring data, blood pressure monitoring data, and oxygen supply detection data within a preset period, and simultaneously, combining the medical history data input by the user, obtaining the user's corresponding physiological indicators;

[0098] S103: Acquire temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user's environment within a preset period based on a network platform as corresponding environmental indicators.

[0099] In this embodiment, the pulse sensor is a device for detecting the user's pulse and converting it into a sensing signal.

[0100] In this embodiment, the pulse sensing signal is a wave signal used to represent the user's pulse.

[0101] In this embodiment, the biosensor is a device for obtaining the user's motion monitoring data, breathing monitoring data, sleep monitoring data, body temperature monitoring data, blood pressure monitoring data, and oxygen supply detection data within a preset period.

[0102] In this embodiment, the exercise monitoring data is the monitoring data of the user's exercise amount within a preset period.

[0103] In this embodiment, the respiratory monitoring data is monitoring data related to the user's respiratory frequency and apnea within a preset period.

[0104] In this embodiment, the sleep monitoring data is monitoring data related to the user's sleep time and sleep depth within a preset period.

[0105] In this embodiment, the body temperature monitoring data is the body temperature change data of the user within a preset period.

[0106] In this embodiment, the blood pressure monitoring data is the blood pressure change data of the user within a preset period.

[0107] In this embodiment, the oxygen supply detection data is data related to the user's blood oxygen content within a preset period.

[0108] In this embodiment, the medical record data is the user's medical history related data input by the user.

[0109] In this embodiment, the network platform is a networking platform for storing environmental data.

[0110] In this embodiment, the temperature and humidity monitoring data is the temperature and humidity change data of the user's environment obtained based on the network platform.

[0111] In this embodiment, the weather monitoring data is weather-related data of the user's environment obtained based on a network platform.

[0112] In this embodiment, the light monitoring data is data related to the light conditions of the user's environment obtained based on a network platform.

[0113] The beneficial effects of the above technology are: based on the different sensors and networking modules built into the wearable device, the pulse sensor signals, physiological indicators and environmental data related to the user can be accurately and in real time obtained, thereby providing a massive data foundation for the subsequent accurate and real-time analysis of the user's psychological state.

[0114] Example 3:

[0115] Based on Example 2, the method for evaluating a psychological state using a wearable device, S103: obtaining temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user within a preset period as corresponding environmental indicators based on a network platform, includes:

[0116] Establishing a communication link between the wearable device and the network platform;

[0117] Acquiring the user's location information based on a built-in GPS module of the wearable device;

[0118] Based on the communication link and the location information, the temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user's environment within a preset period are retrieved from the network platform in real time as corresponding environmental indicators.

[0119] In this embodiment, the communication link is a link used to implement a real-time communication relationship between the wearable device and the network platform.

[0120] In this embodiment, the built-in GPS module is used by the user to obtain the GPS location information of the wearable device (ie, the user's location information).

[0121] The beneficial effects of the above technology are: based on the communication link between wearable devices and network platforms, the environmental indicators of the user's environment can be accurately obtained, which is more universal than the direct measurement of environmental indicators by sensors, and the method of obtaining information through network communication is faster than the direct measurement method.

[0122] Example 4:

[0123] Based on Example 3, the method for evaluating a psychological state using a wearable device, S2: determining a corresponding set of pulse wave feature points based on the pulse sensor signal, includes:

[0124] performing noise reduction filtering on the pulse sensing signal to obtain a corresponding first pulse sensing signal;

[0125] removing a baseline interference signal in a low-frequency band from the first pulse sensing signal to obtain a corresponding second pulse sensing signal;

[0126] performing wavelet packet decomposition on the second pulse sensor signal to obtain a corresponding decomposition result, and performing multi-band denoising on the pulse sensor signal segment based on the decomposition result to obtain a corresponding denoising result;

[0127] Reconstruct all denoising results to obtain the corresponding reconstructed pulse wave signal;

[0128] All pulse wave feature points are determined in the reconstructed pulse wave signal to obtain a corresponding pulse wave feature point set.

[0129] In this embodiment, the first pulse sensing signal is a wave signal obtained by performing noise reduction and filtering on the pulse sensing signal.

[0130] In this embodiment, the second pulse sensing signal is a wave signal obtained after removing the baseline interference signal in the low frequency band of the first pulse sensing signal.

[0131] In this embodiment, the decomposition result is a result obtained by performing wavelet packet decomposition on the second pulse sensor signal.

[0132] In this embodiment, the denoising result is the result obtained after low-frequency denoising is performed on the pulse sensing signal segment.

[0133] In this embodiment, the reconstructed pulse wave signal is a pulse wave signal obtained by reconstructing all low-noise signal segments.

[0134] In this embodiment, the pulse wave characteristic points are characteristic points determined in the reconstructed pulse wave signal.

[0135] In this embodiment, reconstructing all denoising results to obtain the corresponding reconstructed pulse wave signal means reconstructing all denoising results according to the original wavelet packet decomposition structure.

[0136] The beneficial effects of the above technology are: by denoising the pulse sensor signal, removing the baseline interference signal, and decomposing and reconstructing the wavelet packet, the low-frequency multiple denoising of the pulse wave signal is achieved, so that the proposed pulse wave feature points can more accurately represent the user's pulse characteristics, and indirectly improve the accuracy of psychological state detection.

[0137] Example 5:

[0138] Based on Example 4, the method for assessing a psychological state using a wearable device is characterized in that: performing wavelet packet decomposition on the second pulse sensor signal to obtain a corresponding decomposition result; and performing multi-band denoising on the pulse sensor signal segment based on the decomposition result to obtain a corresponding low-noise signal segment, including:

[0139] decomposing the second pulse sensing signal into a pulse sensing scaling function and a pulse sensing wavelet function;

[0140] performing bandpass filtering on the second pulse sensor signal to obtain a corresponding filtered signal;

[0141] Calculating a periodic evaluation mean of the filtered signal;

[0142] Determining the corresponding number of decomposition layers based on the periodic evaluation mean;

[0143] Decomposing the pulse sensing scaling function and the pulse sensing wavelet function based on the number of decomposition layers to obtain corresponding scaling wavelet packet decomposition trees and sensing wavelet packet decomposition trees;

[0144] Determining a corresponding first wavelet packet decomposition coefficient based on the scale wavelet packet decomposition tree, and determining a corresponding second wavelet packet decomposition coefficient based on the sensing wavelet packet decomposition tree, and using the scale wavelet packet decomposition tree and the sensing wavelet packet decomposition tree as corresponding decomposition results;

[0145] Correspondingly associating the nodes of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree to obtain corresponding associated nodes;

[0146] Based on the first wavelet packet decomposition coefficient, the second wavelet packet decomposition coefficient and the associated node, obtaining a two-dimensional coefficient vector corresponding to the associated node of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree;

[0147] Calculating a similarity measure between the two-dimensional coefficient vector and an average value of the two-dimensional coefficient vectors corresponding to all associated nodes;

[0148] Determine whether the similarity metric value is less than a similarity metric threshold; if so, set the wavelet coefficient corresponding to the similarity metric value to zero; otherwise, retain the wavelet coefficient corresponding to the similarity metric value to obtain the corresponding retained wavelet coefficient;

[0149] Obtaining corresponding denoised scale wavelet packet decomposition trees and denoised sensor wavelet packet decomposition trees based on the retained wavelet coefficients;

[0150] The denoising scale wavelet packet decomposition tree and the denoising sensor wavelet packet decomposition tree are taken as corresponding denoising results.

[0151] In this embodiment, the second pulse sensing signal is decomposed into a pulse sensing scaling function and a pulse sensing wavelet function. Generally, the pulse sensing signal is not an orthogonal function, so the pulse sensing function can be decomposed into a linear combination of a scaling function and a wavelet function, where the scaling function generates a low-frequency part and the wavelet function generates a high-frequency part.

[0152] In this embodiment, the pulse sensing scaling function is a scaling function decomposed from the second pulse sensing signal.

[0153] In this embodiment, the pulse sensing wavelet function is a wavelet function decomposed from the second pulse sensing signal.

[0154] In this embodiment, the filtered signal is a signal obtained by performing band-pass filtering on the second pulse sensor signal.

[0155] In this embodiment, calculating the periodic evaluation mean of the filtered signal includes:

[0156]

[0157] Where Q is the periodic evaluation mean of the filtered signal, i is the currently calculated sampling period, n is the total number of sampling periods, iT is the cutoff time of the i-th sampling period, (i-1)T is the cutoff time of the (i-1)-th sampling period, f(t) is the filtered signal, t is the time variable of the filtered signal, and T is the length of the sampling period;

[0158] For example, f(t)=1, there are two sampling periods, and the length of each sampling period is 1, then Q is 1.

[0159] In this embodiment, the corresponding number of decomposition layers is determined based on the periodic evaluation mean, that is, the corresponding number of decomposition layers is determined based on the periodic evaluation mean and the fourth preset list (that is, a list that characterizes the correspondence between the periodic evaluation mean and the number of decomposition layers), and the value range of the decomposition layer number is (1,3].

[0160] In this embodiment, the scaled wavelet packet decomposition tree is a wavelet packet tree obtained by decomposing the pulse sensor scaling function based on the number of decomposition layers.

[0161] In this embodiment, the sensor wavelet packet decomposition tree is a wavelet packet tree obtained by decomposing the pulse sensor wavelet function based on the number of decomposition levels.

[0162] In this embodiment, the first wavelet packet decomposition coefficients are wavelet packet coefficients contained in the scaled wavelet packet decomposition tree.

[0163] In this embodiment, the second wavelet packet decomposition coefficients are wavelet packet coefficients included in the sensing wavelet packet decomposition tree.

[0164] In this embodiment, the decomposition results are the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree.

[0165] In this embodiment, the associated nodes are corresponding group nodes in the scaled wavelet packet decomposition tree and the sensor wavelet packet decomposition tree obtained by correspondingly associating the nodes of the scaled wavelet packet decomposition tree and the sensor wavelet packet decomposition tree.

[0166] In this embodiment, based on the first wavelet packet decomposition coefficient, the second wavelet packet decomposition coefficient and the associated nodes, the two-dimensional coefficient vectors corresponding to the associated nodes of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree are obtained: for example, the first wavelet packet decomposition coefficient corresponding to the associated node is α1, and the second wavelet packet decomposition coefficient corresponding to the associated node is α2, then the corresponding two-dimensional coefficient vector is (α1, α2).

[0167] In this embodiment, calculating the similarity measure between the two-dimensional coefficient vector and the average value of the two-dimensional coefficient vectors corresponding to all associated nodes includes:

[0168] Assume that the two-dimensional coefficient vector is (a, b), and the average value of the two-dimensional coefficient vectors corresponding to all associated nodes is (A, B);

[0169] Then the similarity measure between the two-dimensional coefficient vector and the average value of the two-dimensional coefficient vectors corresponding to all associated nodes is:

[0170]

[0171] For example, the two-dimensional coefficient vector is (2, 3), and the average value of the two-dimensional coefficient vectors corresponding to all associated nodes is (4, 6). Then the similarity measure between the two-dimensional coefficient vector and the average value of the two-dimensional coefficient vectors corresponding to all associated nodes is 0.5.

[0172] In this embodiment, retaining the wavelet coefficients is to determine whether the similarity measure value is less than the similarity measure threshold. If so, the wavelet coefficients corresponding to the similarity measure value are set to zero; otherwise, the wavelet coefficients obtained by retaining the wavelet coefficients corresponding to the similarity measure value are retained.

[0173] In this embodiment, the denoised scaled wavelet packet decomposition tree is a wavelet packet tree obtained based on the retained wavelet coefficients contained in the scaled wavelet packet decomposition tree.

[0174] In this embodiment, the denoised scale wavelet packet is a wavelet packet tree obtained based on the retained wavelet coefficients contained in the sensor wavelet packet decomposition tree.

[0175] The beneficial effects of the above technology are as follows: by determining the number of decomposition layers through the periodic evaluation mean obtained after bandpass filtering the second pulse sensor signal, wavelet packet decomposition is achieved for the signal characteristics of the second pulse sensor signal, thereby ensuring reasonable frequency band division and denoising effect, and then by extracting the scaling function and wavelet function contained in the second pulse sensor signal, frequency band denoising of the second pulse sensor signal is achieved, which will further ensure the denoising effect, and by associating the corresponding nodes in the wavelet packet tree corresponding to the scaling function and the wavelet function, high- and low-frequency correlation denoising is achieved, avoiding the occurrence of false denoising, and setting the corresponding wavelet coefficient threshold based on the similarity measurement threshold between the correlation results, thereby achieving reasonable setting of the denoising threshold for high- and low-frequency correlation, further ensuring the denoising effect.

[0176] Example 6:

[0177] Based on Example 5, the detection method for assessing psychological state through a wearable device is characterized in that all pulse wave feature points are determined in the reconstructed pulse wave signal to obtain a corresponding set of pulse wave feature points, including:

[0178] Screening out all first maxima and all first minima contained in the reconstructed pulse wave signal, and determining a first average time interval between all adjacent first maxima and a second average time interval between all adjacent first minima in the reconstructed pulse wave signal;

[0179] determining a corresponding sampling period based on the first averaging time interval and the second averaging time interval;

[0180] determining a plurality of sampling points in the reconstructed pulse wave signal starting from a starting point of the reconstructed pulse wave signal based on the sampling period to obtain a corresponding sampling point set;

[0181] Randomly select a sampling point from the reference sampling point set as the corresponding reference sampling point;

[0182] Determining, in the reconstructed pulse wave signal, a second maximum value closest to the reference sampling point as a first feature point corresponding to the reference sampling point, and simultaneously determining a second minimum value closest to the reference sampling point as a second feature point corresponding to the reference sampling point;

[0183] Determine a first vector between the reference sampling point and the corresponding second maximum value and a second vector between the reference sampling point and the corresponding second minimum value;

[0184] Determining a third vector between the reference sampling point and the corresponding adjacent sampling point;

[0185] determining a first angle between the first vector and the third vector and a second angle between the second vector and the third vector;

[0186] Determine a first feature point corresponding to the adjacent sampling point based on the first angle and the third vector, and simultaneously determine a second feature point corresponding to the vector sampling point based on the second angle and the third vector;

[0187] Then, the adjacent sampling points are used as new reference sampling points to determine new first characteristic points and new second characteristic points, until all first characteristic points and all second characteristic points included in the reconstructed pulse wave signal are determined;

[0188] taking all extreme points in the reconstructed pulse wave signal except the extreme points that coincide with the first characteristic point and the second characteristic point as third characteristic points;

[0189] Based on all the first feature points, all the second feature points, and all the third feature points, a corresponding pulse wave feature point set is obtained.

[0190] In this embodiment, the first maximum value is the maximum value contained in the reconstructed pulse wave signal.

[0191] In this embodiment, the first minimum value is the minimum value contained in the reconstructed pulse wave signal.

[0192] In this embodiment, the first average time interval is the average time interval between all adjacent first maximum values ​​in the reconstructed pulse wave signal.

[0193] In this embodiment, the second average time interval is the average time interval between all adjacent first minimum values ​​in the reconstructed pulse wave signal.

[0194] In this embodiment, a corresponding sampling period is determined based on the first averaging time interval and the second averaging time interval, and an average of the first averaging time interval and the second averaging time interval is used as the corresponding sampling period.

[0195] In this embodiment, the starting point is the point corresponding to the starting point of the reconstructed pulse wave signal.

[0196] In this embodiment, the sampling point set is a set consisting of a plurality of sampling points determined in the reconstructed pulse wave signal starting from the starting point of the reconstructed pulse wave signal based on the sampling period.

[0197] In this embodiment, the reference sampling point is the reference point for determining the first feature point and the second feature point.

[0198] In this embodiment, the first characteristic point is the second maximum value determined in the reconstructed pulse wave signal that is closest to the reference sampling point.

[0199] In this embodiment, the second maximum value is the maximum value in the reconstructed pulse wave signal that is closest to the reference sampling point.

[0200] In this embodiment, the second characteristic point is the second minimum value that is closest to the reference sampling point.

[0201] In this embodiment, the second minimum value is the minimum value in the reconstructed pulse wave signal that is closest to the reference sampling point.

[0202] In this embodiment, the first vector is a vector formed from the reference sampling point to the corresponding second maximum value.

[0203] In this embodiment, the second vector is a vector formed from the reference sampling point to the corresponding second minimum value.

[0204] In this embodiment, the third vector is a vector formed from the reference sampling point to the corresponding adjacent sampling point.

[0205] In this embodiment, the first angle is the angle between the first vector and the third vector.

[0206] In this embodiment, the second angle is the angle between the second vector and the third vector.

[0207] In this embodiment, determining the first feature point corresponding to the adjacent sampling point based on the first angle and the third vector is as follows: determining a fourth vector whose angle with the third vector is the first angle, taking the adjacent sampling point as the starting point of the fourth vector, and the end point corresponding to the fourth vector is the first feature point.

[0208] In this embodiment, the second feature point corresponding to the vector sampling point is determined based on the second angle and the third vector, namely: a fifth vector whose angle with the third vector is the second angle is determined, and the adjacent sampling point is used as the starting point of the fifth vector. The point where the end point corresponding to the fifth vector is located is the second feature point.

[0209] In this embodiment, the third characteristic point is all extreme points in the reconstructed pulse wave signal except the extreme points that coincide with the first characteristic point and the second characteristic point.

[0210] The beneficial effects of the above technology are: based on the average time interval between adjacent maximum values ​​and the average time interval between adjacent minimum values ​​in the reconstructed pulse wave signal, the sampling period can be reasonably determined, and then the corresponding reference sampling point can be reasonably determined, and then each sampling point can be used as a reference sampling point, and all the first feature points and second feature points in the reconstructed pulse wave signal can be determined by the vector between the reference sampling point and the nearest maximum value and the vector between the reference sampling point and the nearest minimum value, which is conducive to extracting feature points according to preset time intervals and provides an important basis for subsequent analysis of pulse wave changes and psychological states based on the slopes corresponding to the feature points.

[0211] Example 7:

[0212] Based on Example 6, the method for evaluating a psychological state using a wearable device, S3: obtaining a final psychological state detection result based on the massive data from a big data platform and the set of pulse wave feature points, and combining the physiological indicators and the environmental indicators, includes:

[0213] Extracting from the massive data a historical pulse wave feature point set and a corresponding historical psychological state detection result corresponding to the user, and a reference pulse wave feature point set and a corresponding reference psychological state detection result corresponding to an environmental indicator that is consistent with the environmental indicator as corresponding correction reference data;

[0214] Determining a corresponding first state coefficient based on the physiological indicator;

[0215] Determining a corresponding second state coefficient based on the environmental indicator;

[0216] determining a corresponding third state coefficient based on a first slope corresponding to a first feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, a second slope corresponding to a second feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, and the first and second average time intervals;

[0217] Obtaining a corresponding first mental state detection result based on the first state coefficient, the second state coefficient, and the third state coefficient;

[0218] The first mental state detection result is corrected based on the correction reference data to obtain a corresponding final mental state detection result.

[0219] In this embodiment, the historical pulse wave feature point set is a previous pulse wave feature point set of the corresponding user extracted from massive data.

[0220] In this embodiment, the historical mental state detection result is the previous mental state detection result of the corresponding user extracted from the massive data.

[0221] In this embodiment, the equivalent environmental indicator is an environmental indicator that is consistent with the environmental indicator currently corresponding to the user.

[0222] In this embodiment, the reference pulse wave feature point set is a pulse wave feature point set that is consistent with the current environmental index corresponding to the user.

[0223] In this embodiment, the reference psychological state detection result is a psychological state detection result that is consistent with the user's current corresponding environmental indicator.

[0224] In this embodiment, determining the corresponding first state coefficient based on the physiological indicator includes: determining the corresponding first state coefficient based on the physiological indicator and a first preset list (ie, a list for characterizing the functional relationship between the physiological indicator and the first state coefficient).

[0225] In this embodiment, determining the corresponding second state coefficient based on the environmental indicator includes: determining the corresponding second state coefficient based on the environmental indicator and a second preset list (ie, a list for characterizing the functional relationship between the environmental indicator and the second state coefficient).

[0226] In this embodiment, a corresponding third state coefficient is determined based on a first slope corresponding to a first feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, a second slope corresponding to a second feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, and the first average time interval and the second average time interval, including: determining a first ratio between an average of all first slopes and an average of the second slopes, calculating a second ratio between the third time interval and the fourth average time interval, and determining the corresponding third state coefficient based on the first ratio, the second ratio, and a third preset list (i.e., a list representing the functional relationship between the first ratio, the second ratio, and the third state coefficient).

[0227] In this embodiment, obtaining a corresponding first mental state detection result based on the first state coefficient, the second state coefficient, and the third state coefficient includes:

[0228] In this embodiment, the correction reference data is the historical pulse wave feature point set and the corresponding historical psychological state detection results corresponding to the user, and the reference pulse wave feature point set and the corresponding reference psychological state detection results corresponding to the same environmental indicators.

[0229] In this embodiment, the first psychological state detection result is a psychological state detection result obtained based on physiological indicators, environmental indicators, and a set of pulse wave feature points.

[0230] The beneficial effects of the above technology are: based on physiological indicators, environmental indicators and a set of pulse wave feature points, the first psychological state detection result is preliminarily determined, and then the first psychological state detection result is corrected in combination with the historical data corresponding to the user in the massive data and the reference data corresponding to the same environmental indicators to obtain the final psychological state detection result, which realizes the use of physiological indicators and environmental indicators related to the user's health and life patterns and combines massive data to comprehensively analyze the user's psychological state, so that the user feature dimension is further expanded and the detection accuracy is greatly improved.

[0231] Example 8:

[0232] Based on Example 7, the method for evaluating a mental state using a wearable device, correcting the first mental state detection result based on the correction reference data to obtain a corresponding final mental state detection result, includes:

[0233] Correcting the first mental state detection result based on the historical pulse wave feature point set and the historical mental state detection result to obtain a corresponding first correction result;

[0234] The first correction result is corrected based on the reference pulse wave feature point set and the reference psychological state detection result to obtain a corresponding final psychological state detection result.

[0235] In this embodiment, the first correction result is a result obtained by correcting the first mental state detection result based on the historical pulse wave feature point set and the historical mental state detection results.

[0236] The beneficial effect of the above technology is: the first psychological state detection result is corrected in stages through the historical data corresponding to the user and the reference data corresponding to the same environmental indicators, thereby greatly improving the detection accuracy.

[0237] Example 9:

[0238] Based on Example 8, the method for evaluating psychological state through a wearable device, S4: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result, reference Figure 3 ,include:

[0239] S401: Obtain a link identification mark corresponding to the information category contained in the information storage table corresponding to the user in the big data platform;

[0240] S402: Based on the link identification mark, the pulse wave feature point set and the corresponding final psychological state detection result are updated to the big data platform to obtain a data update result.

[0241] In this embodiment, the information storage table is a table for storing the pulse wave feature point set, physiological indicators, environmental indicators and final psychological state detection results of the corresponding user.

[0242] In this embodiment, information categories include, for example: a set of pulse wave feature points, physiological indicators, environmental indicators, and final psychological state detection results.

[0243] In this embodiment, the link identification mark is an identification mark used to identify the corresponding information category in the information storage table during the network communication process.

[0244] The beneficial effects of the above technology are: based on the link identification mark corresponding to the information category contained in the information storage table corresponding to the user, the pulse wave feature point set and the corresponding final psychological state detection result are automatically updated and stored in the corresponding information category in the corresponding information storage table, realizing automatic updating and sorting of data, and providing convenience for subsequent data classification and retrieval.

[0245] Example 10:

[0246] Based on Example 9, the method for evaluating a psychological state using a wearable device, S402: Based on the link identification mark, updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result, includes:

[0247] Based on the link identification mark corresponding to the corresponding information category, establishing a first data update link between the pulse wave feature point set and the corresponding information category in the information storage table, and a second data update link between the final mental state detection result and the corresponding information category in the information storage table;

[0248] Based on the first data update link, the pulse wave feature point set is updated to the corresponding information category in the corresponding information storage table in the big data platform. At the same time, based on the second data update link, the final psychological state detection result is updated to the corresponding information category in the corresponding information storage table in the big data platform to obtain the data update result.

[0249] In this embodiment, the first data update link is a data update link between the pulse wave feature point set and the corresponding information category in the information storage table, which is established based on the link identification mark corresponding to the corresponding information category.

[0250] In this embodiment, the second data update link is a data update link between the final mental state detection result and the corresponding information category in the information storage table.

[0251] The beneficial effect of the above technology is: based on the link identification mark corresponding to the corresponding information category, a data update link is established between the information to be updated and the corresponding information category in the information storage table, so that the pulse wave feature point set and the corresponding final psychological state detection results are automatically updated and stored in the corresponding information category in the corresponding information storage table, realizing automatic update and organization of data, and providing convenience for subsequent data classification and retrieval.

[0252] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for evaluating psychological state through a wearable device, characterized in that: include: S1: Obtain the user's pulse sensor signal and physiological indicators and environmental indicators within a preset period through the wearable device; S2: Determining a corresponding set of pulse wave feature points based on the pulse sensing signal, including: Screening out all first maxima and all first minima contained in the reconstructed pulse wave signal, and determining a first average time interval between all adjacent first maxima and a second average time interval between all adjacent first minima in the reconstructed pulse wave signal; determining a corresponding sampling period based on the first averaging time interval and the second averaging time interval; determining a plurality of sampling points in the reconstructed pulse wave signal starting from a starting point of the reconstructed pulse wave signal based on the sampling period to obtain a corresponding sampling point set; Randomly select a sampling point from the sampling point set as the corresponding reference sampling point; Determining, in the reconstructed pulse wave signal, a second maximum value closest to the reference sampling point as a first feature point corresponding to the reference sampling point, and simultaneously determining a second minimum value closest to the reference sampling point as a second feature point corresponding to the reference sampling point; Determine a first vector between the reference sampling point and the corresponding second maximum value and a second vector between the reference sampling point and the corresponding second minimum value; Determining a third vector between the reference sampling point and the corresponding adjacent sampling point; determining a first angle between the first vector and the third vector and a second angle between the second vector and the third vector; Determine a fourth vector whose angle with the third vector is the first angle, use the adjacent sampling point as the starting point of the fourth vector, and the point where the end point corresponding to the fourth vector is the first feature point. At the same time, determine a fifth vector whose angle with the third vector is the second angle, use the adjacent sampling point as the starting point of the fifth vector, and the point where the end point corresponding to the fifth vector is the second feature point. Then, the adjacent sampling points are used as new reference sampling points to determine new first characteristic points and new second characteristic points, until all first characteristic points and all second characteristic points included in the reconstructed pulse wave signal are determined; taking all extreme points in the reconstructed pulse wave signal except the extreme points that coincide with the first characteristic point and the second characteristic point as third characteristic points; Based on all the first characteristic points, all the second characteristic points, and all the third characteristic points, obtaining a corresponding pulse wave characteristic point set; S3: Based on the massive data of the big data platform and the set of pulse wave feature points, and in combination with the physiological indicators and the environmental indicators, a final psychological state detection result is obtained; S4: updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result.

2. A method for evaluating psychological state through a wearable device according to claim 1, characterized in that: S1: Obtain the user's pulse sensor signal and various physiological indicators within a preset period through the wearable device, including: S101: Acquire a pulse sensor signal corresponding to the user based on a pulse sensor provided on the wearable device; S102: Based on the biosensors provided on the wearable device, obtaining the user's exercise monitoring data, respiratory monitoring data, sleep monitoring data, body temperature monitoring data, blood pressure monitoring data, and oxygen supply detection data within a preset period, and simultaneously, combining the medical history data input by the user, obtaining the user's corresponding physiological indicators; S103: Acquire temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user's environment within a preset period based on a network platform as corresponding environmental indicators.

3. The method for evaluating psychological state through a wearable device according to claim 2, characterized in that: S103: Acquiring temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user within a preset period as corresponding environmental indicators based on the network platform, including: Establishing a communication link between the wearable device and the network platform; Acquiring the user's location information based on a built-in GPS module of the wearable device; Based on the communication link and the location information, the temperature and humidity monitoring data, weather monitoring data, and light monitoring data corresponding to the user's environment within a preset period are retrieved from the network platform in real time as corresponding environmental indicators.

4. The method for evaluating psychological state through a wearable device according to claim 3, characterized in that: S2: Determining a corresponding set of pulse wave feature points based on the pulse sensing signal, including: performing noise reduction filtering on the pulse sensing signal to obtain a corresponding first pulse sensing signal; removing a baseline interference signal in a low-frequency band from the first pulse sensing signal to obtain a corresponding second pulse sensing signal; performing wavelet packet decomposition on the second pulse sensor signal to obtain a corresponding decomposition result, and performing multi-band denoising on the pulse sensor signal segment based on the decomposition result to obtain a corresponding denoising result; Reconstruct all denoising results to obtain the corresponding reconstructed pulse wave signal; All pulse wave feature points are determined in the reconstructed pulse wave signal to obtain a corresponding pulse wave feature point set.

5. The method for evaluating psychological state through a wearable device according to claim 4, characterized in that: Performing wavelet packet decomposition on the second pulse sensor signal to obtain a corresponding decomposition result, and performing multi-band denoising on the pulse sensor signal segment based on the decomposition result, including: Decomposing the second pulse sensor signal into a pulse sensor scaling function and a pulse sensor wavelet function, wherein the pulse sensor scaling function is a low-frequency portion of the second pulse sensor signal and the wavelet function is a high-frequency portion of the second pulse sensor signal; performing bandpass filtering on the second pulse sensor signal to obtain a corresponding filtered signal; Calculating a periodic evaluation mean of the filtered signal; Determining the corresponding number of decomposition layers based on the periodic evaluation mean; Decomposing the pulse sensing scaling function and the pulse sensing wavelet function based on the number of decomposition layers to obtain corresponding scaling wavelet packet decomposition trees and sensing wavelet packet decomposition trees; Determining a corresponding first wavelet packet decomposition coefficient based on the scale wavelet packet decomposition tree, and determining a corresponding second wavelet packet decomposition coefficient based on the sensing wavelet packet decomposition tree, and using the scale wavelet packet decomposition tree and the sensing wavelet packet decomposition tree as corresponding decomposition results; Correspondingly associating the nodes of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree to obtain corresponding associated nodes; Based on the first wavelet packet decomposition coefficient, the second wavelet packet decomposition coefficient and the associated node, obtaining a two-dimensional coefficient vector corresponding to the associated node of the scale wavelet packet decomposition tree and the sensor wavelet packet decomposition tree; Calculating a similarity measure between the two-dimensional coefficient vector and an average value of the two-dimensional coefficient vectors corresponding to all associated nodes; Determine whether the similarity metric value is less than a similarity metric threshold; if so, set the wavelet coefficient corresponding to the similarity metric value to zero; otherwise, retain the wavelet coefficient corresponding to the similarity metric value to obtain the corresponding retained wavelet coefficient; Obtaining corresponding denoised scale wavelet packet decomposition trees and denoised sensor wavelet packet decomposition trees based on the retained wavelet coefficients; The denoising scale wavelet packet decomposition tree and the denoising sensor wavelet packet decomposition tree are taken as corresponding denoising results.

6. The method for evaluating psychological state through a wearable device according to claim 1, characterized in that: S3: Based on the massive data from the big data platform and the pulse wave feature point set, and in combination with the physiological indicators and the environmental indicators, a final psychological state detection result is obtained, including: Extracting from the massive data a historical pulse wave feature point set and a corresponding historical psychological state detection result corresponding to the user, and a reference pulse wave feature point set and a corresponding reference psychological state detection result corresponding to an environmental indicator that is consistent with the environmental indicator as corresponding correction reference data; Determining a corresponding first state coefficient based on the physiological indicator; Determining a corresponding second state coefficient based on the environmental indicator; determining a corresponding third state coefficient based on a first slope corresponding to a first feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, a second slope corresponding to a second feature point included in the pulse wave feature point set in the reconstructed pulse wave signal, and the first and second average time intervals; Obtaining a corresponding first mental state detection result based on the first state coefficient, the second state coefficient, and the third state coefficient; The first mental state detection result is corrected based on the correction reference data to obtain a corresponding final mental state detection result.

7. The method for evaluating psychological state through a wearable device according to claim 6, characterized in that: Correcting the first mental state detection result based on the correction reference data to obtain a corresponding final mental state detection result includes: Correcting the first mental state detection result based on the historical pulse wave feature point set and the historical mental state detection result to obtain a corresponding first correction result; The first correction result is corrected based on the reference pulse wave feature point set and the reference psychological state detection result to obtain a corresponding final psychological state detection result.

8. The method for evaluating psychological state through a wearable device according to claim 7, characterized in that: S4: Updating the pulse wave feature point set and the corresponding final psychological state detection result to the big data platform to obtain a data update result, including: S401: Obtain a link identification mark corresponding to the information category contained in the information storage table corresponding to the user in the big data platform; S402: Based on the link identification mark, the pulse wave feature point set and the corresponding final psychological state detection result are updated to the big data platform to obtain a data update result.

9. The method for evaluating psychological state through a wearable device according to claim 8, characterized in that: S402: Based on the link identification mark, the pulse wave feature point set and the corresponding final psychological state detection result are updated to the big data platform to obtain a data update result, including: Based on the link identification mark corresponding to the corresponding information category, establishing a first data update link between the pulse wave feature point set and the corresponding information category in the information storage table, and a second data update link between the final mental state detection result and the corresponding information category in the information storage table; Based on the first data update link, the pulse wave feature point set is updated to the corresponding information category in the corresponding information storage table in the big data platform. At the same time, based on the second data update link, the final psychological state detection result is updated to the corresponding information category in the corresponding information storage table in the big data platform to obtain the data update result.

Images