Emotional state evaluation method and device, electronic equipment and storage medium

Abstract

The application discloses an emotion state evaluation method and device, electronic equipment and a storage medium, comprising: collecting original data of a target object, determining a heart rate variability index and motion energy in each first time period based on the original data; determining an initial emotion index corresponding to each first time period based on the heart rate variability index corresponding to each first time period; for each initial emotion index, calibrating the initial emotion index to obtain a target emotion index according to the motion energy corresponding to the initial emotion index and the motion energy in a second time period corresponding to the initial emotion index; according to the target emotion indexes, a target emotion index sequence is formed, emotion evaluation parameters in at least one scene are determined according to the target emotion index sequence, and a target emotion state of the target object is determined based on the emotion evaluation parameters. The technical scheme of the embodiment of the application realizes long-time sustainable emotion state evaluation, improves the evaluation accuracy and the convenience effect.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a method, device, electronic device, and storage medium for assessing emotional state. Background Technology

[0002] The assessment and diagnosis of emotional state mainly rely on scales. The completion of scales is highly subjective, and users are prone to defensiveness when completing the scales, which may lead to answers that do not reflect the facts. Therefore, it is difficult to objectively and accurately reflect the user's true state.

[0003] Currently, there are methods for assessing emotional states by detecting users' resting-state brain function images, electroencephalograms, facial expressions, and voice information. However, these methods can only assess users' emotional states in real time or within a short period of time, and are difficult to reflect users' true emotional states in daily life. Summary of the Invention

[0004] This invention provides a method, device, electronic device, and storage medium for assessing emotional state, thereby achieving long-term, sustainable emotional state assessment and improving the accuracy and convenience of the assessment.

[0005] According to one aspect of the present invention, an emotional state assessment method is provided, the method comprising:

[0006] Collect raw data of the target object, and based on the raw data, determine the heart rate variability index and exercise energy in each first time period;

[0007] Based on the heart rate variability index corresponding to each first time period, the initial emotion index corresponding to each first time period is determined.

[0008] For each initial emotion index, the initial emotion index is calibrated based on the motion energy corresponding to the initial emotion index and the motion energy within a second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index; wherein, the second time period is longer than the first time period;

[0009] A target emotion index sequence is formed based on each target emotion index. An emotion assessment parameter for at least one scenario is determined based on the target emotion index sequence. The target emotion state of the target object is determined based on each emotion assessment parameter.

[0010] According to another aspect of the present invention, an emotional state assessment device is provided, the device comprising:

[0011] The raw data processing module is used to collect raw data of the target object and, based on the raw data, determine the heart rate variability index and exercise energy within each first time period.

[0012] The initial emotion index determination module is used to determine the initial emotion index corresponding to each first time period based on the heart rate variability index corresponding to each first time period.

[0013] The target emotion index determination module is used to calibrate each initial emotion index based on the motion energy corresponding to the initial emotion index and the motion energy within a second time period corresponding to the initial emotion index, thereby obtaining a target emotion index corresponding to the initial emotion index; wherein, the second time period is longer than the first time period.

[0014] The target emotional state determination module is used to form a target emotional index sequence based on each target emotional index, determine at least one emotional assessment parameter in a scenario based on the target emotional index sequence, and determine the target emotional state of the target object based on each emotional assessment parameter.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the emotional state assessment method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the emotional state assessment method according to any embodiment of the present invention.

[0020] The technical solution of this invention collects raw data of the target object and, based on the raw data, determines the heart rate variability index and exercise energy in each first time period. Based on the heart rate variability index corresponding to each first time period, an initial emotion index corresponding to each first time period is determined. For each initial emotion index, the initial emotion index is calibrated according to the exercise energy corresponding to the initial emotion index and the exercise energy in the second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index. A target emotion index sequence is formed based on each target emotion index. An emotion assessment parameter for at least one scenario is determined based on the target emotion index sequence. The target emotion state of the target object is determined based on each emotion assessment parameter. This solves the problems of low accuracy in emotion state assessment and difficulty in long-term and continuous emotion state assessment, achieving long-term sustainable emotion state assessment and improving the accuracy and convenience of assessment.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating an emotional state assessment method provided in Embodiment 1 of the present invention.

[0024] Figure 2 This is a schematic diagram of a 24-hour emotional state assessment process provided in Embodiment 1 of the present invention;

[0025] Figure 3 This is a flowchart illustrating an emotional state assessment method provided in Embodiment 2 of the present invention.

[0026] Figure 4 This is a schematic diagram of the structure of an emotional state assessment device provided in Embodiment 3 of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0031] Example 1

[0032] Figure 1 This is a flowchart illustrating an emotion state assessment method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a long-term and continuous emotion state assessment of a target object is performed. The method can be executed by an emotion state assessment device, which can be implemented in hardware and / or software and can be configured in an electronic device.

[0033] like Figure 1 As shown, the method includes:

[0034] S110. Collect raw data of the target object, and based on the raw data, determine the heart rate variability index and exercise energy in each first time period.

[0035] The target subject can be the individual undergoing an emotional state assessment. The raw data can be data acquired using detection devices, such as signals collected by wearable physiological signal detection devices. The raw data may include electrocardiogram (ECG) signals, pulse waves, and other data used to determine the heart rate sequence. The first time period can be a pre-set timeframe used to determine the target subject's emotional state over a short period, such as 0-5 minutes. Heart rate variability (HRV) refers to the phenomenon of continuously changing heart rate intervals; it is an indicator that reflects the activity of the autonomic nervous system and quantitatively assesses the tension and balance of the cardiac sympathetic and vagal nerves. Exercise energy can be an indicator used to measure the amount of exercise performed by the target subject.

[0036] Specifically, raw data of the target object is continuously collected, and the raw data in each first time period is analyzed and processed to extract heart rate variability indicators and exercise energy in the first time period.

[0037] It should be noted that the first time period can be determined by: determining each first time period based on the preset duration and preset interval. For example, if the preset duration is 5 minutes and the preset interval is 1 minute, then 0 minutes to 5 minutes, 1 minute to 6 minutes, 2 minutes to 7 minutes, etc. can be used as each first time period.

[0038] Based on the above example, the heart rate variability index for each first time period can be accurately determined using the following method:

[0039] Based on the raw data, determine the heart rate sequence in the raw data.

[0040] Among them, the heart rate sequence can be a sequence of heart rate data in the time dimension.

[0041] Specifically, the heart rate extraction algorithm can extract the heart rate sequence from the raw data.

[0042] For each first time period, the heart rate subsequence corresponding to the first time period is determined based on the heart rate sequence, and the heart rate variability index within the first time period is determined based on the heart rate subsequence.

[0043] The heart rate variability indicators include at least one of the following: mean heart rate, standard deviation, and low-frequency to high-frequency ratio. The heart rate subsequence can be the heart rate sequence corresponding to the first time period. The standard deviation and low-frequency to high-frequency ratio can be understood as indicators calculated based on the RR interval; the standard deviation can be understood as the standard deviation of the NN interval.

[0044] Specifically, heart rate subsequences corresponding to each time period are determined from the heart rate sequence. Then, the heart rate subsequences are analyzed and processed to extract heart rate variability indicators, which may be at least one of the following: mean heart rate, standard deviation, and low-frequency to high-frequency ratio.

[0045] It should be noted that the analysis of heart rate variability (HRV) indicators is actually the analysis of variability in the cardiac cycle (RR interval sequence). The analysis methods include time-domain analysis, frequency-domain analysis, and nonlinear (chaotic) analysis. HRV indicators can include time-domain, frequency-domain, and nonlinear indicators. Time-domain indicators include mean, standard deviation, root mean square of the difference, and the percentage of adjacent RR intervals with a difference greater than 50 ms. Frequency-domain indicators include total power, ultra-low frequency power, very low frequency power, low frequency power, high frequency power (HF), standardized low frequency power, standardized high frequency power, and low-frequency to high-frequency ratio. In this embodiment, at least one of the mean heart rate, standard deviation, and low-frequency to high-frequency ratio is selected. Other types of HRV indicators can be selected according to actual needs; no specific limitation is made in this embodiment.

[0046] Based on the above example, the kinetic energy within each first time period can be accurately determined using the following method:

[0047] Based on the original data, determine the triaxial acceleration sequence in the original data.

[0048] The triaxial acceleration sequence can be data from the raw data or data acquired using a triaxial accelerometer sensor or other data acquisition device. The triaxial acceleration sequence can include horizontal axis acceleration sequences, vertical axis acceleration sequences, and triaxial acceleration sequences.

[0049] Specifically, the three-axis acceleration sequences contained in the raw data are extracted. The horizontal axis acceleration sequence is the x-axis sequence, which can be represented by x_axis; the vertical axis acceleration sequence is the y-axis sequence, which can be represented by y_axis; and the vertical axis acceleration sequence is the z-axis sequence, which can be represented by z_axis.

[0050] The motion modulus sequence is determined based on the triaxial acceleration sequence corresponding to the first time period, and the motion power spectrum is determined based on the motion modulus sequence.

[0051] The motion modulus sequence can be obtained by taking the square root of the sum of the squares of the accelerations along each axis. The motion power spectrum can be the Fourier transform spectrum corresponding to the motion modulus sequence.

[0052] Specifically, the sum of the squares of the horizontal, vertical, and triaxial acceleration sequences in the triaxial acceleration sequence corresponding to the first time period is taken, followed by the square root, to obtain the motion modulus sequence corresponding to each first time period. Then, a Fourier transform is performed on the motion modulus sequence to obtain the Fourier transform spectrum, which is the motion power spectrum.

[0053] For example, the sequence of kinematic moduli can be determined using the following formula:

[0054]

[0055] Where x_axis represents the horizontal axis acceleration sequence, y_axis represents the vertical axis acceleration sequence, z_axis represents the vertical axis acceleration sequence, and xyz_sqrt represents the motion modulus sequence.

[0056] For each first time period, the motion energy within the first time period is determined based on the preset frequency band and motion power spectrum.

[0057] The preset frequency band can be a pre-set superimposed frequency band, such as 0.5 to 5 Hz.

[0058] Specifically, for each first time period, the power spectrum amplitudes of the motion power spectrum within the first time period in the preset frequency band are added together to obtain the motion energy within the first time period.

[0059] S120. Based on the heart rate variability index corresponding to each first time period, determine the initial emotion index corresponding to each first time period.

[0060] The initial sentiment index can be a preliminarily determined sentiment index, which can be understood as a sentiment index related to heart rate variability.

[0061] Specifically, for each first time period, the heart rate variability index within that time period is normalized to ensure that the initial emotion index falls within a preset range, such as 0-100, and conforms to a normal distribution. Then, the normalized heart rate variability indices are weighted and summed to obtain the initial emotion index corresponding to that first time period.

[0062] For example, taking heart rate variability indicators such as mean heart rate, standard deviation, and low-frequency / high-frequency ratio as examples, the normalization of these three indicators can be performed by normalizing the mean heart rate (HR) according to the correspondence in Table 1, obtaining the normalized mean heart rate, denoted as HRNorm; normalizing the standard deviation (SDNN) according to the correspondence in Table 2, obtaining the normalized standard deviation, denoted as SdnnNorm; and normalizing the low-frequency / high-frequency ratio (LF / HF) according to the correspondence in Table 3, obtaining the normalized low-frequency / high-frequency ratio, denoted as lfhfNorm. Of course, normalization can also be performed in other ways.

[0063] Table 1

[0064] HRNorm 0 0.4 0.6 0.8 1 1.5 2 HR (BMP) ≤80 ≤95 ≤120 ≤140 ≤160 ≤180 ＞180 HRNorm 2.5 2.8 3 3.2 3.5 3.8 4

[0065] Table 2

[0066]

[0067] Table 3

[0068]

[0069] Furthermore, weights can be defined for mean heart rate, standard deviation, and low-frequency / high-frequency ratio, for example: mean heart rate weight wHR = 12.5; standard deviation weight wSdnn = 5; low-frequency / high-frequency ratio weight wLFHFRatio = 7.5. Then, the initial mood index, fatigue_index, can be calculated using the following formula:

[0070] fatigue_index=wHR*HRNorm+wSdnn*SdnnNorm+wLFHFRatio*lfhfNorm

[0071] The initial sentiment index calculated using the above formula meets the requirement of being between 0 and 100 and exhibits a normal distribution.

[0072] The initial sentiment index can generally be calculated using the following formula:

[0073]

[0074] Where, fatigue_index represents the initial sentiment index, n represents the number of heart rate variability indicators, w(i) represents the weight of the i-th heart rate variability indicator, and valueNorm(i) represents the i-th heart rate variability indicator.

[0075] S130. For each initial emotion index, calibrate the initial emotion index based on the motion energy corresponding to the initial emotion index and the motion energy in the second time period corresponding to the initial emotion index to obtain the target emotion index corresponding to the initial emotion index.

[0076] The second time period can be the time span for determining continuous exercise. The second time period is longer than the first time period; for example, if the first time period is 65-70 minutes, the corresponding second time period is 40-70 minutes. The target emotion index can be the emotion index obtained after exercise calibration.

[0077] Specifically, the initial emotional index can be calibrated through exercise to correct for overly high initial emotional indices calculated during periods of high physical activity and underly low initial emotional indices calculated during periods of prolonged sitting. Since an excessively high emotional index indicates high stress levels and a state of high pressure, while an excessively low emotional index indicates low mood, correcting these factors yields a target emotional index that more closely reflects the target individual's actual stress level. For each initial emotional index, the corresponding exercise energy within a second time period is determined. Based on the exercise energy from the first and second time periods, the initial emotional index is calibrated, and this calibrated initial emotional index is used as the target emotional index.

[0078] S140. Form a target emotion index sequence based on each target emotion index, determine at least one emotion assessment parameter in a scenario based on the target emotion index sequence, and determine the target emotion state of the target object based on each emotion assessment parameter.

[0079] The scenarios can be used to measure different rhythms. For example, scenarios include at least one of the following: all-day average scenario, daytime average scenario, sleep-time average scenario, daytime-sleep-time average difference scenario, all-day-sleep-time average difference scenario, and preset time period-non-preset time period average difference scenario. Emotional assessment parameters can be assessment values ​​corresponding to each scenario. The target emotional state can be the emotional state corresponding to the emotional assessment parameters under each scenario. Optionally, the target emotional state includes at least one of the following: all-day emotional state, diurnal rhythm, emotional pattern, and depressive state. All-day emotional state can be used to assess the target's emotional state throughout the day, such as elevated, calm, or depressed. Diurnal rhythm can be used to assess the emotional state of the target's sleep, such as insomnia. Emotional pattern can be used to assess the emotional state of the target's emotional changes, such as elevated-depressed-elevated, continuously elevated, continuously depressed. Depressive state can be used to assess the target's depressive tendency, such as having a depressive tendency or not having a depressive tendency.

[0080] Specifically, at least one scenario to be evaluated is identified. A target emotion index sequence is constructed based on various target emotion indices, and the evaluation values ​​for these scenarios are determined, which are the emotion evaluation parameters. Then, based on a pre-defined correspondence between the emotion evaluation parameters and emotional states for each scenario, the emotional state corresponding to the emotion evaluation parameters is determined as the emotional state corresponding to the scenario to be evaluated. Finally, by combining the emotional states across all scenarios, the target emotional state of the target individual can be determined. For example, the 24-hour emotional state evaluation process is as follows: Figure 2 As shown, it can be done according to... Figure 2 The process shown is used to assess the target's emotional state.

[0081] It's important to note that a pre-established correspondence between emotional assessment parameters and emotional states can be established for different scenarios. For example, if the emotional assessment parameter is in the second range (e.g., 33-66), it indicates the target is in a calm state, which includes daily work and walks. If the parameter is in the first range (e.g., 66-100), the stress index is high, indicating the target is under stress. Emotional assessment parameters during sleep are generally at a lower level, i.e., in the third range (e.g., 0-33). Therefore, it can be determined that the first range corresponds to excitement, the second range to calmness, and the third range to sleep.

[0082] For example, during sleep, the target's emotional assessment parameters are generally low, usually falling within the third interval. Targets with sleep disorders or autonomic nervous system damage typically have emotional assessment parameters higher than normal during sleep, exceeding the maximum boundary value of the third interval. This may result in an overall emotional index throughout the night, meaning the average emotional assessment parameter corresponding to a specific scenario during sleep exceeds the maximum boundary value of the third interval. In such cases, the target's sleep quality is poor, easily leading to various physical and mental health problems. Therefore, this difference in the target's emotional index levels under specific scenarios can be used to predict the probability of having a certain disease.

[0083] The technical solution of this invention collects raw data of the target object and, based on the raw data, determines the heart rate variability index and exercise energy in each first time period. Based on the heart rate variability index corresponding to each first time period, an initial emotion index corresponding to each first time period is determined. For each initial emotion index, the initial emotion index is calibrated according to the exercise energy corresponding to the initial emotion index and the exercise energy in the second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index. A target emotion index sequence is formed based on each target emotion index. An emotion assessment parameter for at least one scenario is determined based on the target emotion index sequence. The target emotion state of the target object is determined based on each emotion assessment parameter. This solves the problems of low accuracy in emotion state assessment and difficulty in long-term and continuous emotion state assessment, achieving long-term sustainable emotion state assessment and improving the accuracy and convenience of assessment.

[0084] Example 2

[0085] Figure 3 This is a flowchart illustrating an emotion state assessment method provided in Embodiment 2 of the present invention. Based on the foregoing embodiments, the specific implementation method for calibrating the initial emotion index to determine the target emotion index can be found in the detailed description of this technical solution. Explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0086] like Figure 3 As shown, the method includes:

[0087] S210. Collect raw data of the target object, and based on the raw data, determine the heart rate variability index and exercise energy in each first time period.

[0088] S220. Based on the heart rate variability index corresponding to each first time period, determine the initial emotion index corresponding to each first time period.

[0089] S230. For each initial emotion index, if the motion energy corresponding to the initial emotion index does not exceed the preset first motion threshold, then the initial emotion index is calibrated according to the motion energy to obtain the emotion index to be processed; otherwise, the initial emotion index is used as the emotion index to be processed.

[0090] The first motion threshold can be a pre-set threshold used to determine whether there is vigorous motion energy within the first time period. The emotion index to be processed can be the result of calibrating the initial emotion index based on the motion energy within the first time period.

[0091] Specifically, for each initial emotion index, the same method can be used for the first calibration. Taking one initial emotion index as an example, the motion energy corresponding to the initial emotion index is compared with a preset first motion threshold. If the motion energy does not exceed the first motion threshold, the initial emotion index is calibrated based on the motion energy, and the calibrated initial emotion index is used as the emotion index to be processed. If the motion energy exceeds the first motion threshold, the initial emotion index is not calibrated, and the initial emotion index is used as the emotion index to be processed.

[0092] Based on the above example, if the motion energy corresponding to the initial emotion index does not exceed a preset first motion threshold, the initial emotion index can be calibrated according to the motion energy to obtain the emotion index to be processed in the following way:

[0093] Based on the preset correspondence between exercise energy and calibration value, a first calibration value corresponding to exercise energy is determined; based on the first calibration value and the initial emotion index, the emotion index to be processed is determined.

[0094] The preset correspondence between exercise energy and calibration values ​​can be a pre-established correspondence between the exercise energy corresponding to the first time period and the calibration value required to calibrate the initial emotion index. The first calibration value can be the calibration value required to calibrate the initial emotion index.

[0095] Specifically, a correspondence between exercise energy and calibration values ​​can be established in advance. Based on this correspondence, the calibration value corresponding to the exercise energy in the first time period can be determined, which is the first calibration value. The first calibration value is then calculated with the initial emotion index, for example, by adding them together, and the result is used as the emotion index to be processed.

[0096] For example, the pre-established correspondence between energy and calibration value is shown in Table 4.

[0097] Table 4

[0098] EnergyNorm 0 -3 -5 -10 -15 -20

[0099] Table 4 shows a negative correlation between exercise energy and the first calibration index. After determining the first calibration value corresponding to the exercise energy in the first time period, the first calibration value can be added to the initial emotion index to obtain the emotion index to be processed. That is, the emotion index to be processed is determined by the following formula.

[0100] fatigue_index'=fatigue_index+EnergyNorm

[0101] Where, fatigue_index is the initial sentiment index, EnergyNorm is the first calibration value, and fatigue_index' is the sentiment index to be processed.

[0102] S240. If the emotion index to be processed is greater than or equal to the preset first emotion threshold, and the motion energy in the first time period and the motion energy in the second time period are both less than the preset second motion threshold, then the target emotion index corresponding to the initial emotion index is determined according to the preset second calibration value and the emotion index to be processed; otherwise, the emotion index to be processed is used as the target emotion index corresponding to the initial emotion index.

[0103] The first emotion threshold can be a value used to determine whether the emotion index is too high, such as 70. The second movement threshold can be a value used to determine whether the movement energy is too low in the first and second time periods, such as 2. The second calibration value can be a pre-set value used to calibrate the emotion index to be processed, such as 5. It should be noted that the specific values ​​of the first emotion threshold, the second movement threshold, and the second calibration value are not specifically limited in this embodiment.

[0104] Specifically, when the emotion index to be processed is greater than or equal to the preset first emotion threshold, the motion energy in the first time period is less than the preset second motion threshold, and the motion energy in the second time period is less than the preset second motion threshold, the calculation is performed based on the preset second calibration value and the emotion index to be processed, and the calculation result is used as the target emotion index. In other cases, no second calibration is required. Therefore, the emotion index to be processed is used as the target emotion index corresponding to the initial emotion index.

[0105] For example, the formula can be used: "fatigue_index" = "fatigue_index' + EnergyNorm', where "fatigue_index'" is the sentiment index to be processed, "EnergyNorm'" is the second calibration value, and "fatigue_index" is the target sentiment index.

[0106] Optionally, if the target sentiment index is greater than the maximum preset sentiment index, the preset sentiment index can be used as the target sentiment index.

[0107] For example, the maximum preset sentiment index is 100, and the preset sentiment index is 99.59. When the target sentiment index exceeds 100, the target sentiment index is set to 99.59.

[0108] S250. Form a target emotion index sequence based on each target emotion index, determine at least one emotion assessment parameter in a scenario based on the target emotion index sequence, and determine the target emotion state of the target object based on each emotion assessment parameter.

[0109] The technical solution of this invention involves collecting raw data of the target object and determining the heart rate variability index and exercise energy within each first time period based on the raw data. Based on the heart rate variability index corresponding to each first time period, an initial emotion index corresponding to each first time period is determined. For each initial emotion index, if the exercise energy corresponding to the initial emotion index does not exceed a preset first exercise threshold, the initial emotion index is calibrated based on the exercise energy to obtain a processable emotion index. Otherwise, the initial emotion index is used as the processable emotion index for the first calibration. If the processable emotion index is greater than or equal to the preset first emotion threshold, and the exercise energy within the first time period and the exercise energy within the second time period... If the motion energy is less than the preset second motion threshold, then the target emotion index corresponding to the initial emotion index is determined according to the preset second calibration value and the emotion index to be processed; otherwise, the emotion index to be processed is used as the target emotion index corresponding to the initial emotion index for a second calibration. A target emotion index sequence is formed based on each target emotion index, and at least one emotion assessment parameter in at least one scenario is determined based on the target emotion index sequence. The target emotion state of the target object is determined based on each emotion assessment parameter. This solves the problems of low accuracy in emotion state assessment and difficulty in long-term and continuous emotion state assessment, and achieves long-term sustainable emotion state assessment, improving the accuracy and convenience of assessment.

[0110] Example 3

[0111] Figure 4 This is a schematic diagram of the structure of an emotional state assessment device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a raw data processing module 310, an initial emotion index determination module 320, a target emotion index determination module 330, and a target emotion state determination module 340.

[0112] The system includes the following modules: a raw data processing module 310, which collects raw data of the target object and determines the heart rate variability index and exercise energy within each first time period based on the raw data; an initial emotion index determination module 320, which determines the initial emotion index corresponding to each first time period based on the heart rate variability index; a target emotion index determination module 330, which calibrates the initial emotion index for each initial emotion index based on the exercise energy corresponding to the initial emotion index and the exercise energy within a second time period corresponding to the initial emotion index, to obtain the target emotion index corresponding to the initial emotion index; wherein the second time period is longer than the first time period; and a target emotion state determination module 340, which assembles a target emotion index sequence based on the target emotion indices, determines at least one emotion assessment parameter for a scenario based on the target emotion index sequence, and determines the target emotion state of the target object based on the emotion assessment parameters.

[0113] Optionally, the raw data processing module 310 is further configured to determine the heart rate sequence in the raw data based on the raw data; for each first time period, determine the heart rate subsequence corresponding to the first time period based on the heart rate sequence, and determine the heart rate variability index within the first time period based on the heart rate subsequence; wherein the heart rate variability index includes at least one of mean heart rate, standard deviation, and low-frequency to high-frequency ratio.

[0114] Optionally, the raw data processing module 310 is further configured to: determine the triaxial acceleration sequence in the raw data; determine the motion modulus sequence based on the triaxial acceleration sequence corresponding to the first time period; and determine the motion power spectrum based on the motion modulus sequence; and determine the motion energy within each first time period based on a preset frequency band and the motion power spectrum.

[0115] Optionally, the target emotion index determination module 330 is further configured to, for each initial emotion index, if the motion energy corresponding to the initial emotion index does not exceed a preset first motion threshold, calibrate the initial emotion index according to the motion energy to obtain a to-be-processed emotion index; otherwise, use the initial emotion index as the to-be-processed emotion index; and calibrate the to-be-processed emotion index according to the to-be-processed emotion index and the motion energy in the second time period corresponding to the initial emotion index to obtain a target emotion index corresponding to the initial emotion index.

[0116] Optionally, the target emotion index determination module 330 is further configured to determine a first calibration value corresponding to the exercise energy based on a preset correspondence between exercise energy and calibration value; and to determine the emotion index to be processed based on the first calibration value and the initial emotion index.

[0117] Optionally, the target emotion index determination module 330 is further configured to determine the target emotion index corresponding to the initial emotion index based on the preset second calibration value and the emotion index to be processed if the emotion index to be processed is greater than or equal to a preset first emotion threshold, and the motion energy in the first time period and the motion energy in the second time period are both less than a preset second motion threshold; otherwise, the emotion index to be processed is used as the target emotion index corresponding to the initial emotion index.

[0118] Optionally, the scenario includes at least one of the following: an all-day average scenario, a daytime average scenario, a sleep-time average scenario, a daytime-sleep-time average difference scenario, an all-day-sleep-time average difference scenario, and a preset time period-non-preset time period average difference scenario; the target emotional state includes at least one of the following: all-day emotional state, circadian rhythm, emotional pattern, and depressive state.

[0119] The technical solution of this invention collects raw data of the target object and, based on the raw data, determines the heart rate variability index and exercise energy in each first time period. Based on the heart rate variability index corresponding to each first time period, an initial emotion index corresponding to each first time period is determined. For each initial emotion index, the initial emotion index is calibrated according to the exercise energy corresponding to the initial emotion index and the exercise energy in the second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index. A target emotion index sequence is formed based on each target emotion index. An emotion assessment parameter for at least one scenario is determined based on the target emotion index sequence. The target emotion state of the target object is determined based on each emotion assessment parameter. This solves the problems of low accuracy in emotion state assessment and difficulty in long-term and continuous emotion state assessment, achieving long-term sustainable emotion state assessment and improving the accuracy and convenience of assessment.

[0120] The emotional state assessment device provided in the embodiments of the present invention can execute the emotional state assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] Example 4

[0122] Figure 5A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0123] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0124] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0125] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as emotional state assessment methods.

[0126] In some embodiments, the emotion state assessment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the emotion state assessment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the emotion state assessment method by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0131] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0132] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0133] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0134] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for assessing emotional state, characterized in that, include: Collect raw data of the target object, and based on the raw data, determine the heart rate variability index and exercise energy in each first time period; Based on the heart rate variability index corresponding to each first time period, the initial emotion index corresponding to each first time period is determined. For each initial emotion index, the initial emotion index is calibrated based on the motion energy corresponding to the initial emotion index and the motion energy within a second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index; wherein, the second time period is longer than the first time period; A target emotion index sequence is formed based on each target emotion index. An emotion assessment parameter for at least one scenario is determined based on the target emotion index sequence. The target emotion state of the target object is determined based on each emotion assessment parameter. For each initial emotion index, the initial emotion index is calibrated based on the motion energy corresponding to the initial emotion index and the motion energy within a second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index, including: For each initial emotion index, if the motion energy corresponding to the initial emotion index does not exceed a preset first motion threshold, the initial emotion index is calibrated based on the motion energy to obtain the emotion index to be processed; otherwise, the initial emotion index is used as the emotion index to be processed. Based on the emotion index to be processed and the motion energy in the second time period corresponding to the initial emotion index, the emotion index to be processed is calibrated to obtain the target emotion index corresponding to the initial emotion index. The step of calibrating the initial emotion index based on the kinetic energy to obtain the emotion index to be processed includes: Based on the preset correspondence between motion energy and calibration value, a first calibration value corresponding to the motion energy is determined; Based on the first calibration value and the initial emotion index, determine the emotion index to be processed; The step of calibrating the emotion index to be processed based on the emotion index to be processed and the motion energy within a second time period corresponding to the initial emotion index to obtain the target emotion index corresponding to the initial emotion index includes: If the emotion index to be processed is greater than or equal to a preset first emotion threshold, and the exercise energy in the first time period and the exercise energy in the second time period are both less than a preset second exercise threshold, then the target emotion index corresponding to the initial emotion index is determined according to the preset second calibration value and the emotion index to be processed. Otherwise, the emotion index to be processed is used as the target emotion index corresponding to the initial emotion index.

2. The method according to claim 1, characterized in that, The determination of heart rate variability indicators within each first time period based on the raw data includes: Based on the raw data, determine the heart rate sequence in the raw data; For each first time period, a heart rate subsequence corresponding to the first time period is determined based on the heart rate sequence, and a heart rate variability index within the first time period is determined based on the heart rate subsequence; wherein, the heart rate variability index includes at least one of mean heart rate, standard deviation, and low-frequency to high-frequency ratio.

3. The method according to claim 1, characterized in that, Based on the raw data, the motion energy within each first time period is determined, including: Based on the raw data, determine the triaxial acceleration sequence in the raw data; The motion modulus sequence is determined based on the triaxial acceleration sequence corresponding to the first time period, and the motion power spectrum is determined based on the motion modulus sequence. For each first time period, the motion energy within the first time period is determined based on the preset frequency band and the motion power spectrum.

4. The method according to claim 1, characterized in that, The scenario includes at least one of the following: all-day average scenario, daytime average scenario, sleep-time average scenario, daytime-sleep-time average difference scenario, all-day-sleep-time average difference scenario, and preset time period-time-non-preset time period average difference scenario; the target emotional state includes at least one of the following: all-day emotional state, diurnal rhythm, emotional pattern, and depressive state.

5. An emotional state assessment device, characterized in that, include: The raw data processing module is used to collect raw data of the target object and, based on the raw data, determine the heart rate variability index and exercise energy within each first time period. The initial emotion index determination module is used to determine the initial emotion index corresponding to each first time period based on the heart rate variability index corresponding to each first time period. The target emotion index determination module is used to calibrate each initial emotion index based on the motion energy corresponding to the initial emotion index and the motion energy within a second time period corresponding to the initial emotion index, thereby obtaining a target emotion index corresponding to the initial emotion index; wherein, the second time period is longer than the first time period. The target emotional state determination module is used to form a target emotional index sequence based on each target emotional index, determine at least one emotional assessment parameter in a scenario based on the target emotional index sequence, and determine the target emotional state of the target object based on each emotional assessment parameter. The target emotion index determination module is further configured to, for each initial emotion index, calibrate the initial emotion index based on the motion energy if the motion energy corresponding to the initial emotion index does not exceed a preset first motion threshold, to obtain a to-be-processed emotion index; otherwise, use the initial emotion index as the to-be-processed emotion index; and calibrate the to-be-processed emotion index based on the to-be-processed emotion index and the motion energy within a second time period corresponding to the initial emotion index, to obtain a target emotion index corresponding to the initial emotion index. The target emotion index determination module is further configured to determine a first calibration value corresponding to the exercise energy based on a preset correspondence between exercise energy and calibration value; and to determine the emotion index to be processed based on the first calibration value and the initial emotion index. The target emotion index determination module is further configured to determine the target emotion index corresponding to the initial emotion index based on the preset second calibration value and the emotion index to be processed if the emotion index to be processed is greater than or equal to a preset first emotion threshold, and the motion energy in the first time period and the motion energy in the second time period are both less than a preset second motion threshold; otherwise, the emotion index to be processed is used as the target emotion index corresponding to the initial emotion index.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the emotional state assessment method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the emotional state assessment method according to any one of claims 1-4.

Images