A psychological emotion insight analysis method and system

Abstract

The present invention provides a method for analyzing psychological and emotional insights, comprising: collecting a user's blood light reflection signal, pulse wave signal, and electrocardiogram signal through a wearable device, and preprocessing the blood light reflection signal, pulse wave signal, and electrocardiogram signal to obtain human physiological signals; calculating and analyzing the values of the human physiological signals to obtain multiple physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure; using the user's multiple physiological indicators, identifying and judging the user's psychological and emotional state through a cosine similarity algorithm to obtain an emotional judgment result, and displaying the result in real time on a mobile terminal. The present invention enables real-time monitoring and analysis of a user's psychological and emotional state through ordinary everyday wearable devices.

Description

Technical Field

[0001] The present invention relates to the field of wearable device data collection and analysis, and in particular to a psychological emotion insight analysis method and system. Background Art

[0002] Emotions are a state that integrates a person's feelings, thoughts, and behaviors, and play a crucial role in interpersonal communication. Emotions encompass psychological reactions to external or internal stimuli, as well as the physiological responses that accompany these reactions. Emotions are ubiquitous in our daily lives and work. In healthcare, understanding the emotional state of patients, especially those with expressive disorders, allows for tailored care interventions and improved patient care. In product development, identifying users' emotional states during product use and understanding their user experience can improve product functionality and design products that better meet user needs. In various human-computer interaction systems, if the system can recognize a person's emotional state, interactions between humans and machines will become more friendly and natural. Therefore, analyzing and recognizing emotions is a crucial interdisciplinary research topic across fields such as neuroscience, psychology, cognitive science, computer science, and artificial intelligence.

[0003] Existing emotion recognition technologies primarily include text analysis and micro-expression recognition. Text analysis obtains the textual content of all user statements, calculates the user's emotional index based on sentence-level sentiment analysis, and classifies the user's emotions using cosine similarity. Finally, it presents the user's psychological assessment and early warning results. Micro-expression recognition, on the other hand, obtains psychological counseling videos of users, identifies micro-expressions during counseling, captures and labels each time point, and determines the user's emotional state. However, both emotion recognition technologies suffer from the following major issues:

[0004] 1. The measurement process is cumbersome: professional equipment is required to record the user's expressions and behaviors, and the cooperation of professionals is also required to mark and interpret the records.

[0005] 2. Unable to monitor in real time: Conventional psychological emotion recognition methods are subject to limitations such as external equipment and cannot be monitored in real time. Summary of the Invention

[0006] The present invention provides a psychological emotion insight analysis method for realizing real-time monitoring and analysis of a user's psychological emotions through ordinary daily wearable devices.

[0007] The present invention provides a psychological emotion insight analysis method, comprising:

[0008] The wearable device collects the user's blood light reflection signal, pulse wave signal and electrocardiogram signal, and pre-processes the blood light reflection signal, pulse wave signal and electrocardiogram signal to obtain human physiological signals;

[0009] Calculating and analyzing the human physiological signal values to obtain multiple physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure;

[0010] By using multiple physiological indicators of the user, the user's psychological and emotional state is identified and judged through the cosine similarity algorithm to obtain the emotion judgment result and display it in real time on the mobile terminal.

[0011] Preferably, the pre-processing of the blood light reflection signal, the pulse wave signal and the electrocardiogram signal includes:

[0012] Digital filtering is used to remove baseline drift and ambient light noise caused by power frequency interference and respiratory jitter in blood light reflection signals, pulse waves and ECG signals;

[0013] After digital filtering, blood flow sounds in blood light reflection signals, pulse waves and ECG signals are removed through adaptive filtering;

[0014] Finally, the blood light reflection signal, pulse wave and ECG signal are subjected to mean filtering and peak filtering to eliminate the gross errors.

[0015] Preferably, the calculating and analyzing of the human physiological signal values to obtain multiple physiological indicators of the user includes:

[0016] Determining the user's heart rate and atrial fibrillation by calculation based on the electrocardiogram signal in the human physiological signal;

[0017] determining the user's blood oxygen saturation by calculation based on the blood light reflection signal in the human physiological signal;

[0018] The user's blood pressure is determined by calculation according to the pulse wave signal in the human physiological signal.

[0019] Preferably, the method of using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm includes:

[0020] Acquire multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected from the user at the current moment;

[0021] Determine the historical average values of each physiological indicator of the user based on the historical physiological indicator data of the user account stored in the cloud server, and establish a normal physiological indicator control group using multiple historical average values;

[0022] Determine the relative deviation between each physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group;

[0023] If the relative deviation between a certain physiological indicator and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group is greater than a preset deviation threshold, it is determined that the user's physiological indicator is abnormal;

[0024] When it is determined that the physiological indicators of the user are abnormal, a first calculation group is established according to a plurality of relative deviation values corresponding to the plurality of current physiological indicators of the user;

[0025] Performing cosine similarity calculations on the first calculation group and the plurality of second calculation groups stored in the cloud, respectively, to obtain similarity values between the first calculation group and the plurality of second calculation groups stored in the cloud;

[0026] The emotion noun bound to the second calculation group corresponding to the highest similarity value is output as the emotion judgment result.

[0027] Preferably, while outputting the emotion judgment result, it is also necessary to calculate the intensity of the user's emotion by the following method:

[0028] Determining a plurality of relative deviation values within the second calculation group corresponding to the highest similarity value;

[0029] Calculating second relative deviation values between the plurality of relative deviation values in the first calculation group and the corresponding plurality of relative deviation values in the second calculation group;

[0030] Calculate the average of the multiple second relative deviation values to obtain the intensity of the user's emotion;

[0031] When the intensity of the user's emotions exceeds a preset fluctuation threshold, the user is reminded through the mobile terminal to pay attention to regulating his or her emotions.

[0032] Preferably, the second calculation group is determined by:

[0033] Determine, through a volunteer data survey, a plurality of relative deviation values corresponding to a plurality of physiological indicators of a volunteer user under anger and a historical average value of the corresponding physiological indicators in a control group of the volunteer user with normal physiological indicators;

[0034] Establishing a third calculation group according to the multiple relative deviation values corresponding to the multiple current physiological indicators of the volunteer user;

[0035] A plurality of third calculation groups corresponding to the anger emotions of the plurality of volunteer users are determined, and corresponding mean calculations are performed on the data in the plurality of third calculation groups to obtain a second calculation group corresponding to the anger emotions.

[0036] Preferably, the method of using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm further includes:

[0037] The multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected at the same time are divided into an indicator reference group;

[0038] Pre-set upper and lower boundary values for each physiological indicator, and compare the user's current physiological indicators with their corresponding preset upper and lower boundary values;

[0039] If a physiological indicator in a certain indicator reference group is higher than the preset upper boundary value or lower than the preset lower boundary value corresponding to the physiological indicator, it is determined that the indicator reference group has an abnormality, and it is determined whether the indicator reference group corresponding to multiple consecutive moments has the same abnormality, and the number of times the abnormality occurs is recorded;

[0040] When the consecutive number of times exceeds the preset upper limit, it is determined that the user has emotional fluctuations, and multiple indicator reference groups are continuously extracted starting from the indicator reference group where the abnormality first occurs;

[0041] The multiple physiological indicators in the extracted multiple indicator reference groups are classified according to the project category and arranged in order, and a trend change curve of each physiological indicator is established, and finally the trend change curves corresponding to the multiple physiological indicators are obtained, and the trend change curves corresponding to the multiple physiological indicators are used to establish a comparative data group;

[0042] Retrieving from the cloud a comparison data template corresponding to each of the plurality of psychological emotions, performing a cosine similarity calculation on the comparison data template for each psychological emotion and the comparison data group, and determining a degree of match between the comparison data group and the comparison data template corresponding to each psychological emotion;

[0043] The psychological emotion corresponding to the comparison data template with the greatest matching degree is output as the emotion judgment result.

[0044] Preferably, the upper boundary value and the lower boundary value are determined by the following method:

[0045] Obtain the first fluctuation range of a physiological indicator of the human body under normal emotional state through self-volunteer data survey or user group feedback;

[0046] Obtain the second fluctuation range of a physiological indicator of the current user in a normal emotional state while using the wearable device;

[0047] Determine a first fluctuation median value according to the first fluctuation range, where the first fluctuation median value is the average of the maximum value and the minimum value of the first fluctuation range;

[0048] determining a second fluctuation median according to the second fluctuation range, where the second fluctuation median is the average of the maximum value and the minimum value of the second fluctuation range;

[0049] determining an absolute difference between the first fluctuation median and the second fluctuation median, and multiplying the absolute difference by a preset proportional coefficient to obtain a correction value;

[0050] taking the maximum value in the second fluctuation range as a first upper boundary value, and adding the correction value to the first upper boundary value to obtain an upper boundary value;

[0051] The minimum value in the second fluctuation range is used as the first lower boundary value, and the correction value is added to the first lower boundary value to obtain the lower boundary value.

[0052] Preferably, performing cosine similarity calculation on the comparison data template of each psychological emotion and the comparison data group to determine the matching degree between the comparison data group and the comparison data template corresponding to each psychological emotion includes:

[0053] Select a comparison data template of a certain psychological emotion and perform similarity calculation between it and the comparison data group;

[0054] When performing similarity calculation, cosine similarity calculation is performed on all trend change curves in the comparison data group and trend change template curves of corresponding physiological indicators in the comparison data template to obtain multiple first-class similarities, and each first-class similarity is respectively bound to its corresponding physiological indicator item; wherein, the cosine similarity calculation process includes:

[0055] Determine two curves, the trend change curve and the trend change template curve;

[0056] According to the length of the trend change curve, the trend change template curve is trimmed to equal length to obtain a second curve;

[0057] quantizing the trend change curve and the second curve at equal distances to obtain a plurality of sequentially arranged quantified data points;

[0058] determining slopes of a plurality of quantified data points on the trend change curve, and arranging the slopes of the plurality of quantified data points on the trend change curve to generate a first calculation sequence;

[0059] determining slopes of a plurality of quantized data points on the second curve, and arranging the slopes of the plurality of quantized data points on the second curve to generate a second calculation sequence;

[0060] Using the first calculation sequence and the second calculation sequence, calculating the similarity between the trend change curve and the second curve using a cosine similarity calculation formula as a first type of similarity;

[0061] According to the weight coefficient preset for each physiological indicator corresponding to the comparison data template of the psychological emotion, a weighted calculation is performed based on multiple first-category similarities to obtain the degree of matching between the comparison data group and the comparison data template corresponding to the psychological emotion.

[0062] To achieve the above objectives, an embodiment of the present invention further provides a psychological and emotional insight analysis system, comprising:

[0063] The signal acquisition and processing module is used to collect the user's blood light reflection signal, pulse wave signal and electrocardiogram signal through the wearable device, and pre-process the blood light reflection signal, pulse wave signal and electrocardiogram signal to obtain human physiological signals;

[0064] A signal analysis module, configured to calculate and analyze the human physiological signal values to obtain a plurality of physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure;

[0065] The emotion judgment module is used to use multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through the cosine similarity algorithm to obtain the emotion judgment result and display it in real time on the mobile terminal;

[0066] The method of using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm includes:

[0067] Acquire multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected from the user at the current moment;

[0068] Determine the historical average values of each physiological indicator of the user based on the historical physiological indicator data of the user account stored in the cloud server, and establish a normal physiological indicator control group using multiple historical average values;

[0069] Determine the relative deviation between each physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group;

[0070] If the relative deviation between a certain physiological indicator and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group is greater than a preset deviation threshold, it is determined that the user's physiological indicator is abnormal;

[0071] When it is determined that the physiological indicators of the user are abnormal, a first calculation group is established according to a plurality of relative deviation values corresponding to the plurality of current physiological indicators of the user;

[0072] Performing cosine similarity calculations on the first calculation group and the plurality of second calculation groups stored in the cloud, respectively, to obtain similarity values between the first calculation group and the plurality of second calculation groups stored in the cloud;

[0073] Output the emotion noun bound to the second calculation group corresponding to the highest similarity value as the emotion judgment result;

[0074] The method of using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm also includes:

[0075] The multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected at the same time are divided into an indicator reference group;

[0076] Pre-set upper and lower boundary values for each physiological indicator, and compare the user's current physiological indicators with their corresponding preset upper and lower boundary values;

[0077] If a physiological indicator in a certain indicator reference group is higher than the preset upper boundary value or lower than the preset lower boundary value corresponding to the physiological indicator, it is determined that the indicator reference group has an abnormality, and it is determined whether the indicator reference group corresponding to multiple consecutive moments has the same abnormality, and the number of times the abnormality occurs is recorded;

[0078] When the consecutive number of times exceeds the preset upper limit, it is determined that the user has emotional fluctuations, and multiple indicator reference groups are continuously extracted starting from the indicator reference group where the abnormality first occurs;

[0079] The multiple physiological indicators in the extracted multiple indicator reference groups are classified according to the project category and arranged in order, and a trend change curve of each physiological indicator is established, and finally the trend change curves corresponding to the multiple physiological indicators are obtained, and the trend change curves corresponding to the multiple physiological indicators are used to establish a comparative data group;

[0080] Retrieving from the cloud a comparison data template corresponding to each of the plurality of psychological emotions, performing a cosine similarity calculation on the comparison data template for each psychological emotion and the comparison data group, and determining a degree of match between the comparison data group and the comparison data template corresponding to each psychological emotion;

[0081] The psychological emotion corresponding to the comparison data template with the greatest matching degree is output as the emotion judgment result;

[0082] The step of performing cosine similarity calculation on the comparison data template of each psychological emotion and the comparison data group to determine the degree of matching between the comparison data group and the comparison data template corresponding to each psychological emotion comprises:

[0083] Select a comparison data template of a certain psychological emotion and perform similarity calculation between it and the comparison data group;

[0084] When performing similarity calculation, cosine similarity calculation is performed on all trend change curves in the comparison data group and trend change template curves of corresponding physiological indicators in the comparison data template to obtain multiple first-class similarities, and each first-class similarity is respectively bound to its corresponding physiological indicator item; wherein, the cosine similarity calculation process includes:

[0085] Determine two curves, the trend change curve and the trend change template curve;

[0086] According to the length of the trend change curve, the trend change template curve is trimmed to equal length to obtain a second curve;

[0087] quantizing the trend change curve and the second curve at equal distances to obtain a plurality of sequentially arranged quantified data points;

[0088] determining slopes of a plurality of quantified data points on the trend change curve, and arranging the slopes of the plurality of quantified data points on the trend change curve to generate a first calculation sequence;

[0089] determining slopes of a plurality of quantized data points on the second curve, and arranging the slopes of the plurality of quantized data points on the second curve to generate a second calculation sequence;

[0090] Using the first calculation sequence and the second calculation sequence, calculating the similarity between the trend change curve and the second curve using a cosine similarity calculation formula as a first type of similarity;

[0091] According to the weight coefficient preset for each physiological indicator corresponding to the comparison data template of the psychological emotion, a weighted calculation is performed based on multiple first-category similarities to obtain the degree of matching between the comparison data group and the comparison data template corresponding to the psychological emotion.

[0092] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] 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:

[0094] Figure 1 This is a flowchart of a psychological emotion insight analysis method according to an embodiment of the present invention;

[0095] Figure 2 Flowchart of a method for preprocessing a signal in an embodiment of the present invention;

[0096] Figure 3 Schematic diagram of the structure of a psychological emotion insight analysis system in an embodiment of the present invention. DETAILED DESCRIPTION

[0097] 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.

[0098] An embodiment of the present invention provides a psychological emotion insight analysis method, comprising:

[0099] Step S1: collecting the user's blood light reflection signal, pulse wave signal, and electrocardiogram signal through the wearable device, and preprocessing the blood light reflection signal, pulse wave signal, and electrocardiogram signal to obtain human physiological signals;

[0100] Step S2: Calculating and analyzing the human body physiological signal values to obtain multiple physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure;

[0101] Step S3: using the user's multiple physiological indicators, the user's psychological emotional state is identified and judged by a cosine similarity algorithm to obtain an emotional judgment result and display it in real time on the mobile terminal.

[0102] The working principle and beneficial effects of the above technical solution are as follows: The user's blood light reflection signal, pulse wave signal, and electrocardiogram signal are collected through daily wearable devices such as watches and wristbands. These signals are then pre-processed by filtering and noise removal to obtain human physiological signals. The human physiological signal values are then calculated and analyzed to obtain multiple physiological indicators of the user, including heart rate, blood oxygen saturation, atrial fibrillation, blood pressure, etc. Finally, using these multiple physiological indicators, the user's psychological and emotional state is identified and judged using a cosine similarity algorithm. The emotional judgment result is then displayed in real time on the mobile terminal, thereby achieving continuous and uninterrupted insight and analysis of the user's psychological and emotional state.

[0103] In a preferred embodiment, preprocessing the blood light reflection signal, the pulse wave signal, and the electrocardiogram signal includes:

[0104] Step S21: filtering out baseline drift and ambient light noise caused by power frequency interference and respiratory jitter in blood light reflection signals, pulse waves, and ECG signals through digital filtering;

[0105] Step S22: After digital filtering, blood flow sound is removed from the blood light reflection signal, pulse wave, and electrocardiogram signal through adaptive filtering;

[0106] Step S23: Finally, mean filtering and peak filtering are performed on the blood light reflection signal, pulse wave and ECG signal to eliminate gross errors therein.

[0107] The working principle and beneficial effects of the above technical solution are: digital filtering is used to remove baseline drift and ambient light noise caused by power frequency interference and respiratory jitter in blood light reflection signals, pulse waves and ECG signals; adaptive filtering is used to remove blood flow sounds in blood light reflection signals, pulse waves and ECG signals; mean filtering and peak filtering are performed on blood light reflection signals, pulse waves and ECG signals to eliminate gross errors therein, thereby achieving filtering and denoising of the collected signals to obtain more accurate signal data.

[0108] In a preferred embodiment, the human body physiological signal values are calculated and analyzed to obtain multiple physiological indicators of the user including:

[0109] Determine the user's heart rate and atrial fibrillation through calculation based on the electrocardiogram signal in the human body's physiological signals;

[0110] Determine the user's blood oxygen saturation by calculation based on the blood light reflection signal in the human body's physiological signals;

[0111] The user's blood pressure is determined by calculation based on the pulse wave signal in the human body's physiological signals.

[0112] The working principle and beneficial effects of the above technical solution are: using the electrocardiogram signal in the human physiological signal to determine the user's heart rate and atrial fibrillation through calculation, using the blood light reflection signal in the human physiological signal to determine the user's blood oxygen saturation through calculation, and using the pulse wave signal in the human physiological signal to determine the user's blood pressure through calculation, thereby realizing the conversion from the collected basic signal wave data to usable indicator data.

[0113] In a preferred embodiment, using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm includes:

[0114] Acquire multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected from the user at the current moment;

[0115] Determine the historical average values of each physiological indicator of the user based on the historical physiological indicator data of the user account stored in the cloud server, and establish a normal physiological indicator control group using multiple historical average values;

[0116] Determine the relative deviation between each physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group;

[0117] If the relative deviation between a certain physiological indicator and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group is greater than a preset deviation threshold, it is determined that the user's physiological indicator is abnormal;

[0118] When it is determined that the physiological indicators of the user are abnormal, a first calculation group is established according to a plurality of relative deviation values corresponding to the plurality of current physiological indicators of the user;

[0119] Performing cosine similarity calculations on the first calculation group and the plurality of second calculation groups stored in the cloud, respectively, to obtain similarity values between the first calculation group and the plurality of second calculation groups stored in the cloud;

[0120] The emotion noun bound to the second calculation group corresponding to the highest similarity value is output as the emotion judgment result.

[0121] The working principle and beneficial effects of the above technical solution are as follows: by obtaining the multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected from the user at the current moment; determining the historical average value of each physiological indicator of the user according to the historical physiological indicator data under the user account stored in the cloud server, and reflecting the specific values of each physiological indicator of the user under daily circumstances through the historical average value (because people have different physiques, it is impossible to refer to a fixed historical physiological indicator template to analyze the user's emotions, so it is very important to use the user's own historical physiological indicators as a comparison benchmark), and using multiple historical average values to establish a normal physiological indicator control group; determining the relative deviation between each physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group. The relative deviation value is the percentage of the difference between a physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the historical average value; if the relative deviation value between a physiological indicator and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group is greater than the preset deviation threshold, it is determined that the user's physiological indicator is abnormal (that is, when a physiological indicator deviates too much, it is determined that the emotion is abnormal); when it is determined that the user's physiological indicator is abnormal, a first calculation group is established based on multiple relative deviation values corresponding to multiple physiological indicators of the user's current physiological indicators. The multiple data in the first calculation group can reflect the deviation between the user's current physiological indicators and the physiological indicators in daily life; the first calculation group is respectively subjected to cosine similarity calculation with multiple second calculation groups stored in the cloud, and the calculation formula is as follows:

[0122]

[0123] In the formula, Similar represents the similarity value, A i Indicates the i-th value in the first calculation group, B iRepresents the i-th value in the second calculation group, and n represents the number of values in the first calculation group or the second calculation group; the second calculation group can reflect the overall deviation between the various physiological indicators of most users under a certain emotion and the various physiological indicators in daily life, and obtain the similarity values between the first calculation group and multiple second calculation groups stored in the cloud; the emotion noun bound to the second calculation group corresponding to the highest similarity value is output as the emotion judgment result, so as to realize the comparison between the current physiological indicators of the user and the daily physiological indicators, and reflect the deviation of the user's physiological indicators through relative deviation. The second calculation group is used as a common physiological indicator deviation template for the majority of users under a certain emotion (such as anger) to perform similarity comparison calculation, and the emotion corresponding to the deviation template that is most similar to the deviation of the user's current physiological indicators is determined to be the user's current psychological emotion, thereby realizing the recognition of the user's emotion.

[0124] In a preferred embodiment, while outputting the emotion judgment result, the intensity of the user's emotion needs to be calculated by the following method:

[0125] Determining a plurality of relative deviation values within the second calculation group corresponding to the highest similarity value;

[0126] Calculating second relative deviation values between the plurality of relative deviation values in the first calculation group and the corresponding plurality of relative deviation values in the second calculation group;

[0127] Calculate the average of the multiple second relative deviation values to obtain the intensity of the user's emotion;

[0128] When the intensity of the user's emotions exceeds a preset fluctuation threshold, the user is reminded through the mobile terminal to pay attention to regulating his or her emotions.

[0129] The working principle and beneficial effects of the above technical solution are: while outputting the emotion judgment results, it is also necessary to determine multiple relative deviation values in the second calculation group corresponding to the highest similarity value; calculate the second relative deviation value between the multiple relative deviation values in the first calculation group and the corresponding multiple relative deviation values in the second calculation group, and use the second relative deviation to reflect the deviation between the user's emotional intensity under the current emotion and the normal emotional intensity. The larger the deviation, the more intense the user's emotion. For example, if the relative deviation value of a certain item in the first calculation group is 10%, it means that the user's heart rate is 10% faster than usual. If the relative deviation value of the corresponding item in the second calculation group is 20%, it means that the heart rate of most users in this emotion is 20% faster than usual. Then the second relative deviation value is 10% minus 20% and then divided by Taking 20% as negative half, the higher the relative deviation value corresponding to a physiological indicator in the first calculation group, the higher the corresponding second relative deviation value. The physiological indicator of the user represented in this regard changes more strongly than that of most users. Since the physiological indicators of each user will change with the corresponding amplitude when the user's mood changes, emotional feedback is not determined by a fixed physiological indicator, so the average of multiple second relative deviation values is calculated to obtain the intensity of the user's emotions. A more scientific method is to preset a weight coefficient for the second relative deviation corresponding to each physiological indicator, so as to perform a weighted average calculation on the multiple second relative deviation values to obtain a more accurate intensity of the user's emotions. When the intensity of the user's emotions is greater than the preset fluctuation threshold, the user is reminded through the mobile terminal to pay attention to regulating his or her emotions.

[0130] In a preferred embodiment, the second calculation group is determined by:

[0131] Determine, through a volunteer data survey, a plurality of relative deviation values corresponding to a plurality of physiological indicators of a volunteer user under anger and a historical average value of the corresponding physiological indicators in a control group of the volunteer user with normal physiological indicators;

[0132] Establishing a third calculation group according to the multiple relative deviation values corresponding to the multiple current physiological indicators of the volunteer user;

[0133] A plurality of third calculation groups corresponding to the anger emotions of the plurality of volunteer users are determined, and corresponding mean calculations are performed on the data in the plurality of third calculation groups to obtain a second calculation group corresponding to the anger emotions.

[0134] The working principle and beneficial effects of the above technical solution are as follows: the second calculation group is determined by calculating using the data of most users. It is necessary to determine the multiple relative deviation values corresponding to the multiple physiological indicators of the volunteer users under anger and the historical average values of the corresponding physiological indicators in the control group of the volunteer users' normal physiological indicators through volunteer data surveys; establish a third calculation group based on the multiple relative deviation values corresponding to the multiple physiological indicators of the volunteer users; determine the multiple third calculation groups corresponding to the anger of multiple volunteer users, and perform corresponding mean calculations on the data in the multiple third calculation groups to obtain the second calculation group corresponding to the anger emotion, thereby using the volunteer data to determine the average line of the relative deviation corresponding to each physiological indicator. The obtained average line can be formed into the second calculation group. The second calculation groups corresponding to other emotions can also be calculated and determined in the above manner. It is worth noting that for some mixed emotions, since the emotions are determined by observing the physiological feedback of the emotions on the human body according to the preset template, they can also be determined by the above method. It is only necessary to pre-train the second calculation group template corresponding to the mixed emotions.

[0135] In a preferred embodiment, using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm further includes:

[0136] The multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected at the same time are divided into an indicator reference group;

[0137] Pre-set upper and lower boundary values for each physiological indicator, and compare the user's current physiological indicators with their corresponding preset upper and lower boundary values;

[0138] If a physiological indicator in a certain indicator reference group is higher than the preset upper boundary value or lower than the lower boundary value corresponding to the physiological indicator, it is determined that the indicator reference group has an abnormality, and it is determined whether the indicator reference group corresponding to multiple consecutive moments has the same abnormality, and the number of times the abnormality occurs is recorded;

[0139] When the consecutive number of times exceeds the preset upper limit, it is determined that the user has emotional fluctuations, and multiple indicator reference groups are continuously extracted starting from the indicator reference group where the abnormality first occurs;

[0140] The multiple physiological indicators in the extracted multiple indicator reference groups are classified according to the project category and arranged in order, and a trend change curve of each physiological indicator is established, and finally the trend change curves corresponding to the multiple physiological indicators are obtained, and the trend change curves corresponding to the multiple physiological indicators are used to establish a comparative data group;

[0141] Retrieving the corresponding comparison data templates of various psychological emotions from the cloud, performing cosine similarity calculations on the comparison data templates of each psychological emotion and the comparison data group, and determining the degree of match between the comparison data group and the comparison data templates corresponding to each psychological emotion;

[0142] The psychological emotion corresponding to the comparison data template with the greatest matching degree is output as the emotion judgment result.

[0143] The working principle and beneficial effects of the above technical solution are: providing another judgment method, that is, using the change of physiological indicators to determine psychological emotions. For some emotions, the characteristics corresponding to the physiological indicators when the emotions occur are changing, which is a change curve of the physiological indicators. For example, from tension to panic, the process is from accelerated heartbeat to rapid contraction of the heart, resulting in an instantaneous increase in blood pressure. This is a change process of physiological indicators. It is impossible to obtain a judgment result by comparing only with real-time data. Therefore, another method for emotional judgment based on linear change law is provided. Specifically, the blood light reflection signal collected at the same time is converted into the blood pressure curve. , pulse wave signal and electrocardiogram signal analysis to obtain a plurality of physiological indicators into an indicator reference group; set the upper boundary value and the lower boundary value for each physiological indicator in advance, and compare the user's current physiological indicators with the corresponding preset upper boundary value and lower boundary value respectively; if a physiological indicator in a certain indicator reference group is higher than the preset upper boundary value or lower than the preset lower boundary value of the physiological indicator, it is determined that the indicator reference group has an abnormality, and the abnormal physiological indicator is quickly detected. It is also determined whether the indicator reference group corresponding to multiple consecutive moments has the same abnormality, and the number of times the abnormality occurs is recorded; when the consecutive number is greater than When the upper limit of the preset number of times is reached, it is determined that the user has emotional fluctuations. When the physiological indicators are abnormal for many consecutive times, it means that the emotion begins to occur (to prevent misjudgment caused by crude data), and multiple indicator reference groups are continuously extracted starting from the indicator reference group where the abnormality first occurs; the multiple physiological indicators in the extracted multiple indicator reference groups are classified according to the project category and arranged in sequence, and a trend change curve for each physiological indicator is established, and finally the trend change curves corresponding to the multiple physiological indicators are obtained, such as the trend change curve A corresponding to the heart rate, the trend change curve B corresponding to the blood pressure, the trend change curve C corresponding to the blood oxygen saturation, etc., and multiple physiological indicators are used. A comparison data set (e.g., [A, B, C]) is created based on the trend change curves corresponding to each indicator. Comparison data templates corresponding to various psychological emotions are retrieved from the cloud. For example, the template corresponding to anger is [a, b, c]. Cosine similarity calculations are performed on each psychological emotion's comparison data template and the comparison data set to determine the degree of match between the comparison data set and the comparison data template corresponding to each psychological emotion. For example, cosine similarity calculations are performed on [A, B, C] and [a, b, c] to determine the similarity between the two. Finally, the psychological emotion corresponding to the comparison data template with the highest degree of match is output as the emotion judgment result. This method provides a method for emotion judgment based on linear change patterns, allowing for the judgment of emotions that can cause linear characteristic changes in physiological indicators.

[0144] In a preferred embodiment, the upper and lower boundary values are determined by the following method:

[0145] Obtain the first fluctuation range of a physiological indicator of the human body under normal emotional state through self-volunteer data survey or user group feedback;

[0146] Obtain the second fluctuation range of a physiological indicator of the current user in a normal emotional state while using the wearable device;

[0147] Determine a first fluctuation median value according to the first fluctuation range, where the first fluctuation median value is the average of the maximum value and the minimum value of the first fluctuation range;

[0148] Determine a second fluctuation median value according to the second fluctuation range, where the second fluctuation median value is the average of the maximum value and the minimum value of the second fluctuation range;

[0149] Determine the absolute difference between the first fluctuation median and the second fluctuation median, and multiply the absolute difference by a preset proportional coefficient to obtain a correction value;

[0150] Taking the maximum value in the second fluctuation range as the first upper boundary value, and adding the correction value to the first upper boundary value to obtain the upper boundary value;

[0151] The minimum value in the second fluctuation range is used as the first lower boundary value, and the correction value is added to the first lower boundary value to obtain the lower boundary value.

[0152] The working principle and beneficial effects of the above technical solution are as follows: obtaining the first fluctuation range of a physiological indicator of the human body in a normal emotional state through self-volunteer data surveys or user group usage feedback; obtaining the second fluctuation range of a physiological indicator of the current user in a normal emotional state while using the wearable device; determining the first fluctuation median according to the first fluctuation range, and the first fluctuation median is the average of the maximum value and the minimum value of the first fluctuation range; determining the second fluctuation median according to the second fluctuation range, and the second fluctuation median is the average of the maximum value and the minimum value of the second fluctuation range; determining the absolute difference between the first fluctuation median and the second fluctuation median, multiplying the absolute difference by a preset proportional coefficient to obtain a correction value; taking the maximum value in the second fluctuation range as the first upper boundary value, adding the correction value to the first upper boundary value, and obtaining the upper boundary value; taking the minimum value in the second fluctuation range as the first lower boundary value, adding the correction value to the first lower boundary value, and obtaining the lower boundary value. Through the above technical solution, the bias and trend of the first fluctuation range of a physiological indicator under the normal emotional state of the human body of the general users are taken into consideration. Combined with the second fluctuation range of a physiological indicator under the normal emotional state collected multiple times by the current user during the use of the wearable device, upper and lower boundary values with the user's own characteristics are established, which is more suitable for judging the user's emotional state based on the user's own physiological condition.

[0153] In a preferred embodiment, performing cosine similarity calculations on the comparison data templates for each psychological emotion and the comparison data group, and determining the degree of matching between the comparison data group and the comparison data templates corresponding to each psychological emotion includes:

[0154] Select a comparison data template of a certain psychological emotion and calculate its similarity with the comparison data group;

[0155] When performing similarity calculation, all trend change curves in the comparison data group are respectively subjected to cosine similarity calculation with the trend change template curves of the corresponding physiological indicators in the comparison data template to obtain multiple first-class similarities, and each first-class similarity is respectively bound to its corresponding physiological indicator item;

[0156] According to the preset weight coefficient for each physiological indicator corresponding to the comparison data template of the psychological emotion, a weighted calculation is performed based on multiple first-class similarities to obtain the degree of matching between the comparison data group and the comparison data template corresponding to the psychological emotion.

[0157] The working principle and beneficial effects of the above technical solution are as follows: when calculating cosine similarity between the comparison data template and the comparison data group, it is necessary to perform cosine similarity calculation on all trend change curves in the comparison data group and the trend change template curve of the corresponding physiological indicator in the comparison data template, thereby obtaining multiple first-class similarities, each of which represents the similarity between the trend change curve of a certain physiological indicator of the user and the trend change curve of the template corresponding to the physiological indicator. After obtaining the multiple first-class similarities, a weighted calculation is performed based on the multiple first-class similarities according to the weight coefficient preset for each physiological indicator corresponding to the comparison data template of the psychological emotion to obtain the degree of match between the comparison data group and the comparison data template corresponding to the psychological emotion. For different physiological indicators that need to be paid attention to in judging a certain psychological emotion, for example, panic emotion places more emphasis on the detection of heartbeat. Therefore, higher weight coefficients are preset for the multiple physiological indicators related to heartbeat in the comparison data template of panic emotion. After the weighted calculation, the degree of match between the comparison data group and the comparison data template corresponding to the psychological emotion will be more accurate.

[0158] In a preferred embodiment, the cosine similarity calculation process includes:

[0159] Determine two curves: a trend change curve and a trend change template curve;

[0160] According to the length of the trend change curve, the trend change template curve is cut to equal length to obtain a second curve;

[0161] Quantifying the trend change curve and the second curve with equal distances respectively to obtain a plurality of sequentially arranged quantitative data points;

[0162] determining slopes of a plurality of quantified data points on a trend change curve, and arranging the slopes of the plurality of quantified data points on the trend change curve to generate a first calculation sequence;

[0163] determining slopes of a plurality of quantized data points on the second curve, and arranging the slopes of the plurality of quantized data points on the second curve to generate a second calculation sequence;

[0164] The first calculation sequence and the second calculation sequence are used to calculate the similarity between the trend change curve and the second curve using a cosine similarity calculation formula as a first type of similarity.

[0165] The working principle and beneficial effects of the above technical solution are as follows: all trend change curves in the comparison data group are respectively subjected to cosine similarity calculation with the trend change template curves of the corresponding physiological indicators in the comparison data template, and the cosine similarity calculation process includes: determining two curves, the trend change curve and the trend change template curve; trimming the trend change template curve to equal length according to the length of the trend change curve to obtain a second curve, thereby preventing the data lengths of the two curves from being unequal; quantizing the trend change curve and the second curve at equal distances to obtain multiple sequentially arranged quantized data points; determining the slopes of multiple quantized data points on the trend change curve, and dividing the trend change curve into two curves; The slopes of multiple quantized data points on the trend change curve are arranged to generate a first calculation sequence; the slopes of multiple quantized data points on the second curve are determined, and the slopes of the multiple quantized data points on the second curve are arranged to generate a second calculation sequence; the first calculation sequence and the second calculation sequence are used to calculate the similarity between the trend change curve and the second curve using the cosine similarity calculation formula as the first type of similarity, and the curve is decomposed into quantized data points, and the slopes of the quantized data point positions are used to characterize the specific situation of the curve fluctuation change. Finally, the cosine similarity calculation method is used to calculate the two groups of quantized data points to determine the similarity of the two curves, thereby realizing data dimensionality reduction calculation.

[0166] To achieve the above objectives, an embodiment of the present invention further provides a psychological and emotional insight analysis system, comprising:

[0167] Signal acquisition and processing module 1, used to collect the user's blood light reflection signal, pulse wave signal and electrocardiogram signal through the wearable device, and pre-process the blood light reflection signal, pulse wave signal and electrocardiogram signal to obtain human physiological signals;

[0168] Signal analysis module 2 is used to calculate and analyze the human physiological signal values to obtain multiple physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure;

[0169] The emotion judgment module 3 is used to use multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through the cosine similarity algorithm to obtain the emotion judgment result and display it in real time on the mobile terminal.

[0170] The working principle and beneficial effects of the above technical solution are as follows: Signal acquisition and processing module 1 collects the user's blood light reflection signal, pulse wave signal, and electrocardiogram signal through wearable devices such as watches and wristbands, and performs pre-processing such as filtering and noise removal on the blood light reflection signal, pulse wave signal, and electrocardiogram signal to obtain human physiological signals. Signal analysis module 2 calculates and analyzes the human physiological signal values to obtain multiple physiological indicators of the user, including heart rate, blood oxygen saturation, atrial fibrillation, blood pressure, etc. Finally, emotion judgment module 3 uses multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm, obtains the emotion judgment result, and displays it in real time on the mobile terminal. This achieves continuous and uninterrupted psychological and emotional insight analysis of the user.

[0171] 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 psychological emotion insight analysis method, characterized in that: include: The wearable device collects the user's blood light reflection signal, pulse wave signal and electrocardiogram signal, and pre-processes the blood light reflection signal, pulse wave signal and electrocardiogram signal to obtain human physiological signals; Calculating and analyzing the human physiological signal values to obtain multiple physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure; Using multiple physiological indicators of the user, the cosine similarity algorithm is used to identify and judge the user's psychological and emotional state, and the emotional judgment results are displayed in real time on the mobile terminal; The method of using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm includes: Acquire multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected from the user at the current moment; Determine the historical average values of each physiological indicator of the user based on the historical physiological indicator data of the user account stored in the cloud server, and establish a normal physiological indicator control group using multiple historical average values; Determine the relative deviation between each physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group; If the relative deviation between a certain physiological indicator and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group is greater than a preset deviation threshold, it is determined that the user's physiological indicator is abnormal; When it is determined that the physiological indicators of the user are abnormal, a first calculation group is established according to a plurality of relative deviation values corresponding to the plurality of current physiological indicators of the user; Performing cosine similarity calculations on the first calculation group and the plurality of second calculation groups stored in the cloud, respectively, to obtain similarity values between the first calculation group and the plurality of second calculation groups stored in the cloud; Output the emotion noun bound to the second calculation group corresponding to the highest similarity value as the emotion judgment result; While outputting the emotion judgment results, it is also necessary to calculate the intensity of the user's emotions using the following method: Determining a plurality of relative deviation values within the second calculation group corresponding to the highest similarity value; Calculating second relative deviation values between the plurality of relative deviation values in the first calculation group and the corresponding plurality of relative deviation values in the second calculation group; Calculate the average of the multiple second relative deviation values to obtain the intensity of the user's emotion; When the intensity of the user's emotions exceeds a preset fluctuation threshold, the user is reminded through the mobile terminal to pay attention to regulating his or her emotions.

2. A psychological emotion insight analysis method according to claim 1, characterized in that: The pre-processing of the blood light reflection signal, the pulse wave signal and the electrocardiogram signal includes: Digital filtering is used to remove baseline drift and ambient light noise caused by power frequency interference and respiratory jitter in blood light reflection signals, pulse waves and ECG signals; After digital filtering, blood flow sounds in blood light reflection signals, pulse waves and ECG signals are removed through adaptive filtering; Mean filtering and peak filtering are performed on the blood light reflection signal, pulse wave and ECG signal to eliminate the gross errors.

3. A psychological emotion insight analysis method according to claim 1, characterized in that: The calculation and analysis of the human body physiological signal values to obtain multiple physiological indicators of the user include: Determining the user's heart rate and atrial fibrillation by calculation based on the electrocardiogram signal in the human physiological signal; determining the user's blood oxygen saturation by calculation based on the blood light reflection signal in the human physiological signal; The user's blood pressure is determined by calculation according to the pulse wave signal in the human physiological signal.

4. A psychological emotion insight analysis method according to claim 1, characterized in that: The second calculation group is determined in the following manner: Determine, through a volunteer data survey, a plurality of relative deviation values corresponding to a plurality of physiological indicators of a volunteer user under anger and a historical average value of the corresponding physiological indicators in a control group of the volunteer user with normal physiological indicators; Establishing a third calculation group according to the multiple relative deviation values corresponding to the multiple current physiological indicators of the volunteer user; A plurality of third calculation groups corresponding to the anger emotions of the plurality of volunteer users are determined, and corresponding mean calculations are performed on the data in the plurality of third calculation groups to obtain a second calculation group corresponding to the anger emotions.

5. The psychological emotion insight analysis method according to claim 1, characterized in that: The method of using multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm also includes: The multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected at the same time are divided into an indicator reference group; Pre-set upper and lower boundary values for each physiological indicator, and compare the user's current physiological indicators with their corresponding preset upper and lower boundary values; If a physiological indicator in a certain indicator reference group is higher than the preset upper boundary value or lower than the preset lower boundary value corresponding to the physiological indicator, it is determined that the indicator reference group has an abnormality, and it is determined whether the indicator reference group corresponding to multiple consecutive moments has the same abnormality, and the number of times the abnormality occurs is recorded; When the consecutive number of times exceeds the preset upper limit, it is determined that the user has emotional fluctuations, and multiple indicator reference groups are continuously extracted starting from the indicator reference group where the abnormality first occurs; The multiple physiological indicators in the extracted multiple indicator reference groups are classified according to the project category and arranged in order, and a trend change curve of each physiological indicator is established, and finally the trend change curves corresponding to the multiple physiological indicators are obtained, and the trend change curves corresponding to the multiple physiological indicators are used to establish a comparative data group; Retrieving from the cloud a comparison data template corresponding to each of the plurality of psychological emotions, performing a cosine similarity calculation on the comparison data template for each psychological emotion and the comparison data group, and determining a degree of match between the comparison data group and the comparison data template corresponding to each psychological emotion; The psychological emotion corresponding to the comparison data template with the greatest matching degree is output as the emotion judgment result.

6. A psychological emotion insight analysis method according to claim 5, characterized in that: The upper boundary value and the lower boundary value are determined by the following method: Obtain the first fluctuation range of a physiological indicator of the human body under normal emotional state through self-volunteer data survey or user group feedback; Obtain the second fluctuation range of a physiological indicator of the current user in a normal emotional state while using the wearable device; Determine a first fluctuation median value according to the first fluctuation range, where the first fluctuation median value is the average of the maximum value and the minimum value of the first fluctuation range; determining a second fluctuation median according to the second fluctuation range, where the second fluctuation median is the average of the maximum value and the minimum value of the second fluctuation range; determining an absolute difference between the first fluctuation median and the second fluctuation median, and multiplying the absolute difference by a preset proportional coefficient to obtain a correction value; taking the maximum value in the second fluctuation range as a first upper boundary value, and adding the correction value to the first upper boundary value to obtain an upper boundary value; The minimum value in the second fluctuation range is used as the first lower boundary value, and the correction value is added to the first lower boundary value to obtain the lower boundary value.

7. The psychological emotion insight analysis method according to claim 5, characterized in that: The step of performing cosine similarity calculation on the comparison data template of each psychological emotion and the comparison data group to determine the matching degree between the comparison data group and the comparison data template corresponding to each psychological emotion comprises: Select a comparison data template of a certain psychological emotion and perform similarity calculation between it and the comparison data group; When performing similarity calculation, cosine similarity calculation is performed on all trend change curves in the comparison data group and trend change template curves of corresponding physiological indicators in the comparison data template to obtain multiple first-class similarities, and each first-class similarity is respectively bound to its corresponding physiological indicator item; wherein, the cosine similarity calculation process includes: Determine two curves, the trend change curve and the trend change template curve; According to the length of the trend change curve, the trend change template curve is trimmed to equal length to obtain a second curve; quantizing the trend change curve and the second curve at equal distances to obtain a plurality of sequentially arranged quantified data points; determining slopes of a plurality of quantified data points on the trend change curve, and arranging the slopes of the plurality of quantified data points on the trend change curve to generate a first calculation sequence; determining slopes of a plurality of quantized data points on the second curve, and arranging the slopes of the plurality of quantized data points on the second curve to generate a second calculation sequence; Using the first calculation sequence and the second calculation sequence, calculating the similarity between the trend change curve and the second curve using a cosine similarity calculation formula as a first type of similarity; According to the weight coefficient preset for each physiological indicator corresponding to the comparison data template of the psychological emotion, a weighted calculation is performed based on multiple first-category similarities to obtain the degree of matching between the comparison data group and the comparison data template corresponding to the psychological emotion.

8. A psychological emotion insight analysis system, characterized in that: include: The signal acquisition and processing module is used to collect the user's blood light reflection signal, pulse wave signal and electrocardiogram signal through the wearable device, and pre-process the blood light reflection signal, pulse wave signal and electrocardiogram signal to obtain human physiological signals; A signal analysis module, configured to calculate and analyze the human physiological signal values to obtain a plurality of physiological indicators of the user; wherein the physiological indicators include heart rate, blood oxygen saturation, atrial fibrillation, and blood pressure; The emotion judgment module is used to use multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through the cosine similarity algorithm to obtain the emotion judgment result and display it in real time on the mobile terminal; The method in which the emotion judgment module uses multiple physiological indicators of the user to identify and judge the user's psychological and emotional state through a cosine similarity algorithm includes: Acquire multiple physiological indicators obtained by analyzing the blood light reflection signal, pulse wave signal and electrocardiogram signal collected from the user at the current moment; Determine the historical average values of each physiological indicator of the user based on the historical physiological indicator data of the user account stored in the cloud server, and establish a normal physiological indicator control group using multiple historical average values; Determine the relative deviation between each physiological indicator corresponding to the current moment and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group; If the relative deviation between a certain physiological indicator and the historical average value of the corresponding physiological indicator in the normal physiological indicator control group is greater than a preset deviation threshold, it is determined that the user's physiological indicator is abnormal; When it is determined that the physiological indicators of the user are abnormal, a first calculation group is established according to a plurality of relative deviation values corresponding to the plurality of current physiological indicators of the user; Performing cosine similarity calculations on the first calculation group and the plurality of second calculation groups stored in the cloud, respectively, to obtain similarity values between the first calculation group and the plurality of second calculation groups stored in the cloud; Output the emotion noun bound to the second calculation group corresponding to the highest similarity value as the emotion judgment result; While outputting the emotion judgment results, it is also necessary to calculate the intensity of the user's emotions using the following method: Determining a plurality of relative deviation values within the second calculation group corresponding to the highest similarity value; Calculating second relative deviation values between the plurality of relative deviation values in the first calculation group and the corresponding plurality of relative deviation values in the second calculation group; Calculate the average of the multiple second relative deviation values to obtain the intensity of the user's emotion; When the intensity of the user's emotions exceeds a preset fluctuation threshold, the user is reminded through the mobile terminal to pay attention to regulating his or her emotions.

Images