CN115670460A

CN115670460A - Mood state monitoring method and device and storage medium

Info

Publication number: CN115670460A
Application number: CN202211054297.0A
Authority: CN
Inventors: 温万惠; 刘光远
Original assignee: Southwest University
Current assignee: Southwest University
Priority date: 2022-08-31
Filing date: 2022-08-31
Publication date: 2023-02-03

Abstract

The application provides a mood state monitoring method, a mood state monitoring device and a storage medium. The method comprises the steps of acquiring an autonomic nerve activity signal of a target individual; wherein the autonomic neural activity signals comprise a plurality of time-phased autonomic neural activity signals; respectively extracting target sequences from a plurality of time-interval autonomic nervous activity signals to obtain a plurality of time-interval physiological data; calculating and comparing the physiological data of a plurality of time intervals according to a preset characteristic space to determine the mood state of the target individual; wherein, predetermine the feature space and include: the preset pressure grade evaluation feature space, the preset parasympathetic forced regulation state detection feature space and the preset mood state evaluation feature space realize all-weather mood state monitoring on crowds, so that the mood state of the crowds can be effectively and completely inferred.

Description

Mood state monitoring method and device and storage medium

Technical Field

The application relates to the technical field of mood state monitoring, in particular to a mood state monitoring method, a mood state monitoring device and a storage medium.

Background

The state of the coordinated balance between the mental and physical aspects in which the mood corresponds well is the mood in a healthy state, and the state of the imbalance between the mental and physical aspects in which the mood corresponds poorly is the mood in a sub-healthy state, so the mood state is closely related to the health of a person. In addition, the literature clearly indicates that the emotion in a short time changes the activity rule of sympathetic nerves and parasympathetic nerves, so that the detection of the mood state of the human promotes the application value of research on the health of the human.

Currently, detection techniques for emotional states are mainly aimed at short and intense emotions, such as: the research results of the second classification and the third classification of the stress level also relate to the technology of stress scoring, but the stress level and the scoring result given by the existing research and technology are lack of experience and validity for verification, so that the stress level and the scoring lack of transverse comparability, and the all-weather and diffuse mood state cannot be detected, so that the mood state of the crowd cannot be effectively and completely inferred according to the stress level and the scoring result.

Disclosure of Invention

Embodiments of the present invention provide a method, an apparatus, and a storage medium for monitoring mood states, which are capable of accurately inferring mood states of a crowd by calculating and comparing sequences extracted from autonomic nervous activity signals of a plurality of time periods around the clock of a person using a plurality of preset feature spaces.

In a first aspect, an embodiment of the present application provides a mood state monitoring method, where the method includes:

acquiring an autonomic nerve activity signal of a target individual; wherein the autonomic neural activity signals comprise a plurality of time-phased autonomic neural activity signals;

respectively extracting target sequences from the time-interval autonomic nervous activity signals to obtain a plurality of time-interval physiological data;

calculating and comparing the physiological data of the plurality of time intervals according to a preset feature space to determine the mood state of the target individual; wherein the preset feature space includes: the method comprises the steps of presetting a pressure grade evaluation characteristic space, presetting a parasympathetic forced regulation state detection characteristic space and presetting a mood state evaluation characteristic space.

According to the mood state monitoring method, the mood state of the target individual is determined by calculating and comparing the target sequence extracted from the autonomic nerve activity signals of the target individual in a plurality of time intervals through the preset pressure level evaluation characteristic space, the preset parasympathetic forced regulation state detection characteristic space and the preset mood state evaluation characteristic space. The physiological data in the preset characteristic space has universal applicability and transverse comparability, and the physiological data in a plurality of time intervals are subjected to distributed joint detection, so that the integrity of the mood state detection result is ensured, and the mood state of an individual can be effectively and completely detected when the physiological data of the individual collected in real time is detected.

Optionally, the acquiring the autonomic nerve activity signal of the target individual comprises:

acquiring physiological signals of the target individual acquired by a medical sensor; wherein the physiological signals comprise autonomic nerve activity signals and human body three-dimensional acceleration signals;

carrying out segmentation calculation on the autonomic nerve activity signals and the human body three-dimensional acceleration signals to obtain a plurality of time-divided human body three-dimensional acceleration signals and autonomic nerve activity signals;

judging whether the plurality of time-sharing human body three-dimensional acceleration signals are larger than a preset human body three-dimensional acceleration signal or not;

if so, determining the autonomic nerve activity signals corresponding to the human body three-dimensional acceleration signals of the multiple time intervals as autonomic nerve activity signals of non-target individuals;

and if not, determining the autonomic nerve activity signals corresponding to the human body three-dimensional acceleration signals of the multiple time intervals as the autonomic nerve activity signals of the target individual.

According to the mood state monitoring method, the autonomic nerve activity signals and the autonomic nerve activity signals of a target individual, which are acquired by a medical sensor, are segmented to obtain a plurality of time-segmented human body three-dimensional acceleration signals and autonomic nerve activity signals, whether the autonomic nerve activity is influenced by a plurality of time-segmented body activities (human body three-dimensional acceleration signals) is distinguished by presetting the human body three-dimensional acceleration signals, and the time-segmented human body three-dimensional acceleration signals and autonomic nerve activity signals which are larger than the preset human body three-dimensional acceleration signals are removed to obtain the target autonomic nerve activity signals. The human body three-dimensional acceleration signals of the time period which are greater than the preset human body three-dimensional acceleration signals can interfere the detection of the mood state, and the validity of the mood state detection result can be further ensured by removing the human body three-dimensional acceleration signals of the time period which are greater than the preset human body three-dimensional acceleration signals.

Optionally, the calculating and comparing the plurality of time-interval physiological data according to a preset feature space to determine the mood state of the target individual includes:

according to the preset pressure rating characteristic space, respectively performing pressure rating on the physiological data of the plurality of time intervals to obtain the physiological data of the plurality of time intervals after the pressure rating, and calculating the physiological data of the plurality of time intervals according to a preset pressure rating method to obtain pressure ratings of the physiological data of the plurality of time intervals;

performing parasympathetic forced regulation detection on the physiological data of the plurality of time intervals according to the preset parasympathetic forced regulation state detection feature space to obtain parasympathetic forced regulation time distribution and frequency of the physiological data of the plurality of time intervals;

analyzing and comparing the pressure scores and the parasympathetic forced modulation time distribution and frequency of the physiological data of the plurality of time intervals according to the preset mood state evaluation feature space to determine the mood state of the target individual.

According to the mood state monitoring method, the characteristic space of preset pressure level evaluation is used for carrying out pressure scoring on physiological data of a plurality of time intervals, the characteristic space of preset parasympathetic forced regulation state detection is used for carrying out parasympathetic forced regulation time distribution and frequency detection on the physiological data of the plurality of time intervals, and the characteristic space of preset mood state evaluation is used for carrying out mood state analysis and comparison on the pressure scoring of the physiological data of the plurality of time intervals and the parasympathetic forced regulation time and frequency, so that the mood state of an individual is determined. The calibration of the physiological data samples of the preset pressure grade evaluation space, the preset parasympathetic forced regulation state detection characteristic space and the preset mood state evaluation characteristic space adopts various effective experience effect targets and selects various physiological indexes capable of revealing key characteristics of mental pressure and parasympathetic forced regulation, so that the universal applicability and transverse comparability of the physiological data samples are ensured, and then the mood state is monitored by combining the pressure grading of the physiological data in multiple time periods and the parasympathetic forced regulation, and the integrity of the mood state detection result is ensured, so that the mood state of an individual can be effectively and completely detected when the physiological data of the individual collected in real time are detected.

Optionally, the preset pressure rating feature space is constructed by:

performing pressure grade calibration on preset physiological data according to preset pressure grade experience calibration to obtain preset physiological data of a plurality of pressure grades;

and calculating the preset physiological data of the multiple pressure levels according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms to obtain the calculation result of the preset physiological data of the multiple pressure levels, and constructing the preset pressure level evaluation feature space according to the calculation result.

According to the mood state monitoring method, the preset physiological data are subjected to pressure grade calibration through the preset pressure grade experience effect scale, and then the preset physiological data after the pressure grade calibration are represented by the periodic function of the target sequence rhythm reflecting the key characteristics of the autonomic nervous activity rule and the average fluctuation function of the two target sequence rhythms, so that the regular distribution of the preset physiological data in the characteristic space is obtained and used as the preset pressure grade evaluation characteristic space. The pressure grade calibration is carried out on the preset physiological data by adopting the effective preset pressure grade experience effect scale to obtain the preset physiological data of a plurality of pressure grades, and then the scatter distribution of the preset physiological data of the plurality of pressure grades in the preset pressure grade evaluation space is supported according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms, so that the effectiveness, the universality applicability and the transverse comparability of the pressure grade calibration of the preset physiological data are ensured, and the constructed preset pressure grade evaluation characteristic space can effectively carry out the pressure grade evaluation on the physiological data acquired in real time.

Optionally, the preset pressure scoring method includes a formula one:

score is the stress Score of the time-sliced physiological data; x is the physiological data of the time interval; x1 is a class center of preset physiological data corresponding to the pressure level of the physiological data of the time intervals; s is the standard deviation in the class of the preset physiological data; j is the stress level of the physiological data of the time interval;

the pressure rating of the physiological data of the plurality of time intervals is respectively carried out according to the preset pressure rating characteristic space to obtain the physiological data of the plurality of time intervals after the pressure rating is carried out, and the pressure rating of the physiological data of the plurality of time intervals is obtained by calculating the physiological data of the plurality of time intervals according to a preset pressure rating method, and the method comprises the following steps:

calculating the physiological data of the plurality of time intervals according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms to obtain the calculation results of the physiological data of the plurality of time intervals;

mapping the calculation results of the physiological data of the plurality of time intervals to the preset pressure level evaluation feature space respectively, and calculating the distance between the class center of the calculation results of the preset physiological data of the plurality of pressure levels and the calculation results respectively to obtain the distance between the calculation results of the physiological data of the plurality of time intervals and the class center of the calculation results of the preset physiological data of the plurality of pressure levels respectively;

determining a plurality of minimum distances from the distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the preset physiological data of the plurality of pressure levels, and taking the pressure levels of the preset physiological data corresponding to the minimum distances as the pressure levels of the physiological data of the plurality of time intervals;

and obtaining the stress scores of the physiological data of the plurality of time intervals according to the formula I, the physiological data of the plurality of time intervals, the class center of preset physiological data of the corresponding stress grade of the physiological data of the plurality of time intervals, the class standard deviation of the preset physiological data and the stress grade of the physiological data of the plurality of time intervals.

According to the mood state monitoring method, scattered point distribution in a preset pressure level evaluation characteristic space is represented by a periodic function of target sequence rhythms and an average fluctuation function of two target sequence rhythms according to physiological data of a plurality of time intervals, then the distance between the physiological data of the plurality of time intervals and the preset physiological data of the plurality of pressure levels is observed, the pressure level of the preset physiological data which is respectively closest to the physiological data of the plurality of time intervals is used as the pressure level of the physiological data of the plurality of time intervals, and finally, the physiological data of the plurality of time intervals with the evaluated pressure levels are scored according to a preset scoring method to obtain the pressure scores of the physiological data of the plurality of time intervals. The preset stress grading characteristic space can effectively carry out stress grading on the physiological data, so that the raw stress score calculated when the physiological data with the graded stress is subjected to stress grading is also effective, and an effective basis is provided for the mood state detection in the aspect of stress grading.

Optionally, the preset parasympathetic-forced-regulation-state detection feature space is constructed by:

calibrating preset physiological data according to a preset pressure level experience effect scale, a preset fatigue theoretical model, a preset work and rest and a diet irregularity effect scale to obtain a plurality of first physiological data and second physiological data; wherein the first physiological data is designated as parasympathetic forced modulation;

respectively carrying out continuous wavelet transformation on the plurality of first physiological data and the plurality of second physiological data according to a wavelet basis function of a preset transformation scale interval to obtain a geometric form approximation degree measurement index of the plurality of first physiological data and the plurality of second physiological data and the plurality of time-interval physiological data;

respectively carrying out average difference calculation on the plurality of first physiological data and the second physiological data and the adjacent first physiological data and second physiological data to obtain the average difference of the plurality of first physiological data and second physiological data;

acquiring power values of the plurality of first physiological data and the plurality of second physiological data under a preset frequency;

obtaining a calculation result of the plurality of first physiological data and second physiological data based on the maximum transformation scale, the average difference and the power value under the preset frequency of the plurality of first physiological data and second physiological data;

and constructing the parasympathetic forced regulation state detection feature space according to the calculation results of the plurality of first physiological data and second physiological data.

The mood state monitoring method comprises the steps of evaluating preset physiological data through a preset pressure level experience significance and a preset fatigue theoretical model to obtain first physiological data and second physiological data, and then representing the first physiological data and the second physiological data by using a wavelet approximation degree measurement index of a preset transformation scale interval reflecting key features of autonomic nerve activity rules, an index of target sequence variation and a relative activation degree index in a preset frequency, so that regular distribution of the preset physiological data in a feature space is obtained to be used as a preset parasympathetic forced regulation state detection feature space. The preset physiological data are calibrated by adopting effective preset pressure level experience effect, a preset fatigue theoretical model and other preset special events causing the forced adjustment of the parasympathetic nerves, so that the physiological data with the forced adjustment of the parasympathetic nerves and without the forced adjustment of the parasympathetic nerves are obtained, secondly, the scatter distribution of the physiological data with the forced adjustment of the parasympathetic nerves and without the forced adjustment of the parasympathetic nerves in a preset parasympathetic nerve forced adjustment state detection characteristic space is supported according to a wavelet approximation degree measurement index of a preset transformation scale interval, an index of target sequence variation and a relative activation degree index in a preset frequency, so that the effectiveness, universality and transverse comparability of the forced adjustment detection of the parasympathetic nerves of the preset physiological data are ensured, and the constructed preset parasympathetic nerve forced adjustment state detection characteristic space can effectively carry out the forced adjustment detection of the parasympathetic nerves on the physiological data collected in real time.

Optionally, the detecting, according to the preset parasympathetic forced modulation state detection feature space, performing parasympathetic forced modulation detection on the physiological data of the plurality of time segments to obtain a parasympathetic forced modulation time distribution and a frequency of the physiological data of the plurality of time segments includes:

performing wavelet transformation on the physiological data of the plurality of time intervals to obtain geometric form approximation degree measurement indexes of the physiological data of the plurality of time intervals;

carrying out average difference calculation on the physiological data of the plurality of time intervals and the adjacent physiological data of the time intervals to obtain the average difference of the physiological data of the plurality of time intervals;

acquiring power values of the physiological data of the plurality of time intervals under the preset frequency;

obtaining a calculation result of the physiological data of the plurality of time intervals based on the geometric shape approximation degree metric indexes of the plurality of time intervals, the average difference and the power value under the preset frequency;

mapping the calculation results of the physiological data of the plurality of time intervals to the preset parasympathetic forced regulation state detection feature space respectively, and performing distance calculation on class centers of the calculation results of the plurality of first physiological data and the plurality of second physiological data and the calculation results respectively to obtain distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the plurality of first physiological data and the plurality of second physiological data respectively;

determining a plurality of minimum distances from the distances between the calculation results of the plurality of time-interval physiological data and the class centers of the calculation results of the plurality of first physiological data and second physiological data respectively;

if the preset physiological data corresponding to the minimum distances is the first physiological data, marking the time-interval physiological data corresponding to the minimum distances as parasympathetic forced adjustment, and recording the times of parasympathetic forced adjustment of the time-interval physiological data to obtain the forced adjustment frequency of the time-interval physiological data.

The mood state monitoring method comprises the steps of expressing scatter distribution of a detection feature space in a preset parasympathetic nerve forced regulation state by adopting wavelet basis functions of preset transformation scale intervals, indexes of target sequence variation and relative activation degree indexes in preset frequencies through physiological data of a plurality of time intervals, observing the far and near degree of the physiological data of the plurality of time intervals and the preset physiological data with and without parasympathetic nerve forced regulation, respectively marking the physiological data of the plurality of time intervals closest to the parasympathetic nerve forced regulation distance as parasympathetic nerve forced regulation, recording the times of the parasympathetic nerve forced regulation, and finally determining the forced regulation frequency of parasympathetic nerves of the physiological data of the plurality of time intervals according to the time length of the time intervals and the times of occurrence of the parasympathetic nerve forced regulation. The preset parasympathetic forced regulation state detection feature space can effectively detect the parasympathetic forced regulation of the physiological data, so that an effective basis is provided for the mood state detection in the aspect of parasympathetic forced regulation frequency.

Optionally, the preset mood state assessment feature space is constructed by:

calibrating the mood state of the preset physiological data according to a preset self-evaluation table to obtain the preset physiological data of the calibrated mood state;

calculating pressure scores and parasympathetic forced regulation time distribution and frequency of the preset physiological data of the calibrated mood state to obtain preset pressure scores, preset duration ratio and preset parasympathetic forced regulation time distribution and frequency of good mood state and bad mood state;

and constructing the preset mood state evaluation feature space according to the preset pressure score, the preset duration ratio and the preset parasympathetic forced regulation time distribution and frequency of the good mood state and the bad mood state.

The mood state monitoring method comprises the steps of calibrating the mood state of preset physiological data through a preset self-evaluation table, obtaining a preset pressure score, a preset duration ratio and preset parasympathetic mandatory regulation time distribution and frequency of good mood state and bad mood state through pressure scoring and parasympathetic mandatory regulation detection of the physiological data of the determined mood state, and constructing a preset mood state characteristic space according to the pressure score and the parasympathetic mandatory regulation time distribution and frequency. Because the preset self-evaluation table is adopted to calibrate the mood state of the preset physiological data, the pressure score and the parasympathetic forced regulation of the physiological data with the calibrated mood state are analyzed, and the preset pressure score, the preset duration ratio and the preset forced regulation frequency of the good mood state and the bad mood state are obtained, the effectiveness of each index of the mood state of the preset physiological data is ensured, and the mood state detection can be effectively carried out on the physiological data collected in real time by the preset mood state characteristic space.

Optionally, the analyzing and comparing the pressure scores and the forced adjustment frequencies of the plurality of time-interval physiological data according to the preset mood state assessment feature space to determine the mood state of the target individual includes:

grouping the pressure scores of the physiological data of the plurality of time intervals according to the work and rest time of the target individual to obtain a plurality of pressure scores of the physiological data of the arousal state and the sleep state;

grouping the parasympathetic nerve forced regulation time distribution and frequency of the physiological data of the plurality of time intervals according to a preset pressure level experience effect scale and a preset fatigue theoretical model to obtain the parasympathetic nerve forced regulation time distribution and frequency of a plurality of physiological fatigue-prone times and physiological fatigue-insusceptible times;

determining a pressure score of the physiological data of the arousal state, which is smaller than a preset pressure score of good mood state, from the pressure scores of the physiological data of the arousal states to obtain a pressure score of the physiological data of the first arousal state;

determining a stress score of the physiological data of the sleep state with the stress score of zero from the stress scores of the physiological data of the sleep state to obtain a stress score of the physiological data of the first sleep state;

and if the ratio of the duration corresponding to the pressure score of the physiological data of the first wake state to the durations of the plurality of time intervals is greater than the preset duration ratio of good mood state, the ratio of the duration corresponding to the pressure score of the physiological data of the first sleep state to the durations of the plurality of time intervals is greater than the preset duration ratio of good mood state, and the forced adjustment frequency of the plurality of physiological fatigue-prone times is less than the preset adjustment frequency of good mood state, determining that the mood state is good.

The method for monitoring the mood state comprises the steps of grouping the pressure scores and the parasympathetic forced regulation of the physiological data of a plurality of time intervals according to the work and rest time of a target individual, the preset pressure level empirical indicators and the preset fatigue theoretical model to obtain the pressure scores of the physiological data of the wakeful state and the sleep state and the parasympathetic forced regulation frequency of the physiological data of the physiological fatigue-prone state and the physiological fatigue-insurmountable time, and determining that the mood state of the individual is good if the pressure score of the physiological data of the wakeful state is less than the preset ratio of the good mood pressure score for a longer time than the preset ratio of the good mood state, the pressure score of the sleep state is zero for a longer time than the preset ratio of the good mood state, and the parasympathetic forced regulation frequency of the physiological data of the physiological fatigue-prone state is less than the preset forced regulation frequency of the good mood state. The pressure scores of physiological data of the wakefulness state and the sleep state and the parasympathetic forced regulation frequency of physiological fatigue-free time are judged through the preset mood state characteristic space, so that the good detection result of the mood state of the target individual has effectiveness and integrity.

Optionally, the analyzing and comparing the pressure scores and the forced adjustment frequencies of the plurality of time-sliced physiological data according to the feature space assessed by the preset mood state to determine the mood state comprises:

determining a pressure score of the physiological data of the arousal state which is larger than the preset pressure score of the bad mood state from the pressure scores of the physiological data of the arousal states to obtain a pressure score of the physiological data of a second arousal state;

determining a pressure score of the physiological data in the sleep state, which is greater than a preset pressure score of poor mood state, from the pressure scores of the physiological data in the sleep state to obtain a pressure score of the physiological data in a second sleep state;

and if the ratio of the duration corresponding to the pressure score of the physiological data of the second arousal state to the durations of the plurality of time intervals is greater than the preset duration ratio of the bad mood state, the ratio of the duration corresponding to the pressure score of the physiological data of the second sleep state to the durations of the plurality of time intervals is greater than the preset duration ratio of the bad mood state, and the forced adjusting frequency of the plurality of physiological fatigue-resistant times is greater than the preset adjusting frequency of the bad mood state, determining that the mood state is bad.

In the mood state monitoring method, when the proportion duration of the pressure score of the physiological data in the arousal state, which is greater than the preset proportion duration of the bad mood, the proportion duration of the pressure score of the physiological data in the sleep state, which is greater than the preset proportion duration of the bad mood, and the parasympathetic forced regulation frequency of the physiological data in the physiological fatigue-free time, which is greater than the preset forced regulation frequency of the bad mood, the mood state of the individual is determined to be bad. The pressure scores of physiological data of the wakefulness state and the sleep state and the parasympathetic forced regulation frequency of the physiological fatigue-free time are judged through the preset mood state characteristic space, so that the detection result that the mood state of the target individual is poor has effectiveness and integrity.

In a second aspect, an embodiment of the present application further provides a mood state monitoring device, where the device includes:

the acquisition module is used for acquiring an autonomic nervous activity signal of a target individual; wherein the autonomic neural activity signals comprise a plurality of time-phased autonomic neural activity signals;

the extraction module is used for respectively extracting target sequences from the plurality of time-interval autonomic nerve activity signals to obtain a plurality of time-interval physiological data;

the analysis module is used for calculating and comparing the physiological data of the plurality of time intervals according to a preset feature space so as to determine the mood state of the target individual; wherein the preset feature space comprises: the method comprises the following steps of presetting a pressure grade evaluation characteristic space, presetting a parasympathetic forced regulation state detection characteristic space and presetting a mood state evaluation characteristic space.

In the foregoing embodiment, the mood state monitoring device provided has the same beneficial effects as those of the first aspect or the mood state monitoring method provided in any optional implementation manner of the first aspect, and details are not described herein.

In a third aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the above-described method.

In the foregoing embodiment, a computer-readable storage pool medium is provided, which has the same beneficial effects as those of the first aspect described above, or the mood state monitoring method provided in any optional implementation manner of the first aspect, and is not described herein again.

In summary, the present application provides a mood state monitoring method, device and storage medium. The method comprises the steps of obtaining an autonomic nerve activity signal of a target individual; wherein the autonomic neural activity signals comprise a plurality of time-phased autonomic neural activity signals; respectively extracting target sequences from a plurality of time-interval autonomic nervous activity signals to obtain a plurality of time-interval physiological data; calculating and comparing the physiological data of a plurality of time intervals according to a preset characteristic space to determine the mood state of the target individual; wherein, predetermine the feature space and include: the preset pressure grade evaluation feature space, the preset parasympathetic forced regulation state detection feature space and the preset mood state evaluation feature space realize all-weather mood state monitoring on crowds, so that the mood state of the crowds can be effectively and completely inferred.

Drawings

To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is a schematic block diagram of an electronic device according to an embodiment of the present application;

fig. 2 is a first flowchart of a mood state monitoring method according to an embodiment of the present disclosure;

fig. 3 is a second flowchart of the mood state monitoring method according to the embodiment of the present application;

fig. 4 is a schematic waveform diagram of a human body three-dimensional acceleration signal provided in an embodiment of the present application;

FIG. 5 is a waveform diagram illustrating a significant change in autonomic nervous activity caused by a three-dimensional acceleration signal of a human body according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a preset pressure rating feature space provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of the stress score, the heart rate sequence, the parasympathetic forced modulation mark and the human body three-dimensional acceleration signal of the human subject under a good mood;

fig. 8 is a schematic diagram of an all-weather stress score, a heart rate sequence, a parasympathetic forced modulation mark and a human body three-dimensional acceleration signal of a subject under bad mood according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a mood state monitoring device according to an embodiment of the present application.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only used to illustrate the technical solutions of the present application more clearly, and therefore are only used as examples, and the protection scope of the present application is not limited thereby.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

In the description of the embodiments of the present application, the technical terms "first", "second", and the like are used only for distinguishing different objects, and are not to be construed as indicating or implying relative importance or to implicitly indicate the number, specific order, or primary-secondary relationship of the technical features indicated. In the description of the embodiments of the present application, "a plurality" means two or more unless specifically defined otherwise.

To facilitate understanding of the present embodiment, first, an electronic device for performing the mood state monitoring method disclosed in the embodiments of the present application will be described in detail.

FIG. 1 is a block diagram of an embodiment of an electronic device. The electronic device 100 may include a memory 111, a memory controller 112, a processor 113, a peripheral interface 114, an input-output unit 115, and a display unit 116. It will be understood by those of ordinary skill in the art that the structure shown in fig. 1 is merely exemplary and is not intended to limit the structure of the electronic device 100. For example, electronic device 100 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

The above-mentioned elements of the memory 111, the memory controller 112, the processor 113, the peripheral interface 114, the input/output unit 115 and the display unit 116 are electrically connected to each other directly or indirectly, so as to implement data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The processor 113 is used to execute the executable modules stored in the memory.

The Memory 111 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 111 is used for storing a program, the processor 113 executes the program after receiving an execution instruction, and the method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present application may be applied to the processor 113, or implemented by the processor 113.

The processor 113 may be an integrated circuit chip having signal processing capability. The Processor 113 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The peripheral interface 114 couples various input/output devices to the processor 113 and memory 111. In some embodiments, the peripheral interface 114, the processor 113, and the memory controller 112 may be implemented in a single chip. In other examples, they may be implemented separately from the individual chips.

The input/output unit 115 is used for providing data input to the user. The input/output unit 115 may be, but is not limited to, a mouse, a keyboard, and the like.

The display unit 116 provides an interactive interface (e.g., a user operation interface) between the electronic device 100 and the user or is used for displaying image data to the user for reference. In this embodiment, the display unit may be a liquid crystal display or a touch display. In the case of a touch display, the display can be a capacitive touch screen or a resistive touch screen, which supports single-point and multi-point touch operations. Supporting single-point and multi-point touch operations means that the touch display can sense touch operations simultaneously generated from one or more positions on the touch display, and the sensed touch operations are sent to the processor for calculation and processing.

The electronic device 100 in this embodiment may be configured to perform each step in each method provided in this embodiment. The following describes in detail the implementation of the mood state monitoring method by means of several embodiments.

The principle of the mood state monitoring method provided by the embodiment of the application is as follows:

from the biological point of view, the autonomic nervous system is mainly divided into sympathetic nervous system and parasympathetic nervous system, which are restricted to each other and maintain the balance of the body's regulatory function, i.e. when the crowd encounters a special event (i.e. the mood changes), the human sympathetic and parasympathetic nerves are antagonized to maintain the body's balance (i.e. there is forced regulation of the parasympathetic nerves), and the forced regulation of the parasympathetic nerves is reflected on the change rule of the autonomic nervous activity signal.

From the psychological point of view, when a person encounters a special event (i.e. when the mood state changes), the person will show different physiological responses, behavioral manifestations under stress, psychological experiences of stress response, and the like, so the mental stress is also required to be graded, and the change rules of corresponding autonomic nervous activity signals also exist in different grades of mental stress.

In conclusion, the mood state of the crowd is determined according to the mental stress score, duration and occurrence time of the crowd, the frequency of parasympathetic forced regulation and the occurrence time of the crowd, and the like. Therefore, in order to determine the mood state of the population, the mental stress score and the forced regulation frequency of parasympathetic nerves of the population are required to be clear, and the forced regulation frequency and the mental stress level of the parasympathetic nerves of the population correspond to the change rule of the autonomic nervous activity signal.

The mood state monitoring method provided by the embodiment of the application is characterized in that the mental stress level calibration and the parasympathetic forced regulation state calibration are carried out on the crowd in advance, and then the change rule of the autonomic nerve activity signal corresponding to the crowd is found, namely the change rule of the autonomic nerve activity signal under different mental stress levels and the change rule of the autonomic nerve activity signal under the parasympathetic forced regulation are determined. Therefore, in the course of subsequent practical applications, it is only necessary to determine the level of mental stress and whether parasympathetic regulation is present by observing whether the autonomic nervous activity signal satisfies the law of change.

Please refer to fig. 2, which illustrates a first flowchart of a mood state monitoring method according to an embodiment of the present application.

Step S100: acquiring an autonomic nerve activity signal of a target individual; wherein the autonomic nervous activity signal comprises a plurality of time-phased autonomic nervous activity signals;

the target individual refers to a person to be subjected to mood state monitoring.

The autonomic nervous activity signal includes, but is not limited to, electrocardiogram, pulse wave, heart rate, pulse rate, heart rate, and the like, and the embodiments of the present application are not limited thereto.

It should be noted that, in the embodiment of the present application, all-weather mood monitoring is performed on the target individual, so that a 24-hour autonomic nervous activity signal is collected, and the 24 hours are divided into a plurality of time periods, so that the autonomic nervous signal of the target individual is divided into a plurality of time-divided autonomic nervous activity signals.

Step S200: respectively extracting target sequences from a plurality of time-interval autonomic nervous activity signals to obtain a plurality of time-interval physiological data;

the plurality of time-interval physiological data refers to a set of time-interval target sequences.

The target sequence is a rhythm time sequence extracted from the autonomic nerve activity signal, such as an electrocardiogram extracted sequence, and an electrocardiogram rhythm time sequence is obtained; the sequence extracted from the heart rate is a heart rate rhythm time sequence.

In addition, different autonomic nerve activity signals have different display states, and different autonomic nerve activity signals can be extracted from the autonomic nerve activity signals to sequences only by performing corresponding signal processing on the different autonomic nerve activity signals.

Step S300: calculating and comparing the physiological data of a plurality of time intervals according to a preset characteristic space to determine the mood state of the target individual; wherein, predetermine the feature space and include: the method comprises the steps of presetting a pressure grade evaluation characteristic space, presetting a parasympathetic forced regulation state detection characteristic space and presetting a mood state evaluation characteristic space.

The preset pressure rating feature space is used for performing pressure rating judgment and pressure scoring on the physiological data of the multiple time intervals to obtain pressure scores of the physiological data of the multiple time intervals.

The preset parasympathetic forced regulation state monitoring feature space is used for detecting parasympathetic forced regulation frequency of the physiological data of a plurality of time intervals so as to obtain the parasympathetic forced regulation frequency of the physiological data of the plurality of time intervals.

The preset mood state feature space is used for analyzing the physiological data pressure scores and the parasympathetic forced regulation frequency of a plurality of time intervals so as to determine the mood state of the target individual.

Specifically, after acquiring a plurality of time-interval autonomic nerve activity signals of the target individual, extracting a target sequence from the plurality of time-interval autonomic nerve activity signals, and then calculating and comparing the target according to a preset pressure level evaluation feature space, a preset parasympathetic forced regulation state detection feature space and a preset mood state evaluation feature space to determine the mood state of the target individual.

In the present embodiment, the mood state of the target individual is determined by calculating and comparing the target sequence extracted from the multiple time-divisional autonomic nervous activity signals of the target individual through the preset pressure level assessment feature space, the preset parasympathetic forced regulation state detection feature space, and the preset mood state assessment feature space. The physiological data in the preset characteristic space has universal applicability and transverse comparability, and the physiological data in a plurality of time intervals are subjected to distributed joint detection, so that the integrity of the mood state detection result is ensured, and the mood state of an individual can be effectively and completely detected when the physiological data of the individual collected in real time is detected.

Optionally, the step S100 may specifically include: steps S110-S150.

Please refer to fig. 3, which is a second flow chart of the mood state monitoring method according to the embodiment of the present application.

Step S110: acquiring physiological signals of a target individual acquired by a medical sensor; wherein, the physiological signal comprises an autonomic nerve activity signal and a human body three-dimensional acceleration signal;

please refer to fig. 4 for a schematic diagram of a waveform of a human body three-dimensional acceleration signal provided by the embodiment of the present application.

Please refer to fig. 5, which illustrates a waveform diagram of a three-dimensional acceleration signal of a human body causing a significant change in autonomic nervous activity provided by an embodiment of the present application.

It should be noted that, when the human body three-dimensional acceleration exceeds the preset human body three-dimensional acceleration, a significant change of the autonomic nerve activity signal is caused, and the significant change is abnormal, and the autonomic nerve activity signal corresponds to a situation that antagonism between sympathetic and parasympathetic nerves is reflected, so that the autonomic nerve activity signal in the abnormal state is subjected to parasympathetic nerve forced regulation, and the detected result is definitely inaccurate, and inaccurate parasympathetic nerve regulation detection will certainly interfere with the judgment of the monitoring of the mood state, so when the collected human body three-dimensional acceleration signal in a certain time interval exceeds the preset human body three-dimensional acceleration, the target autonomic nerve activity signal in the time interval should be discarded at this time to ensure the accuracy of the mood state monitoring.

It can be understood that the medical sensor is arranged on the crowd to be subjected to mood state detection, the carrier of the medical sensor can be equipment capable of being carried such as a smart watch, and the carrier of the medical sensor is not limited in the embodiment of the application, and can be specifically arranged according to actual requirements.

The human body three-dimensional acceleration signal refers to the acceleration of a human body in three dimensions of X, Y and Z and is used for reflecting the situation of determining physical activity. When the human body three-dimensional acceleration signal exceeds the preset human body three-dimensional acceleration, the obvious change of the autonomic nerve activity is shown, and the situation that the collected autonomic nerve activity signal cannot represent the antagonistic state between the sympathetic nerve and the parasympathetic nerve is shown.

In one embodiment, because the human body three-dimensional acceleration signal which is not subjected to the detrending processing has a plurality of high frequencies and low frequencies, the human body three-dimensional acceleration signal needs to be detrended (denoised), so that on the premise of a sampling rate of 512Hz, a low-frequency coefficient of 6-layer wavelet decomposition is set to zero, and then the signal is reconstructed to obtain the human body three-dimensional acceleration signal with high frequency fluctuation.

Step S120: carrying out segmentation calculation on the autonomic nerve activity signal and the human body three-dimensional acceleration signal to obtain a plurality of time-divided human body three-dimensional acceleration signals and autonomic nerve activity signals;

the segmentation calculation method may be a preset sliding time window, or may be other methods capable of segmenting time, and the embodiment of the present application is not limited herein.

Step S130: judging whether the time-sharing human body three-dimensional acceleration signals are larger than preset human body three-dimensional acceleration signals or not;

step S140: if so, determining the autonomic nervous activity signals corresponding to the human body three-dimensional acceleration signals of a plurality of time intervals as autonomic nervous activity signals of non-target individuals;

step S150: and if not, determining the autonomic nervous activity signals corresponding to the human body three-dimensional acceleration signals of a plurality of time intervals as the autonomic nervous activity signals of the target individual.

The preset three-dimensional acceleration signal is a threshold value of the three-dimensional acceleration signal which is enough to cause a significant change of the autonomic nervous activity, namely, when the preset three-dimensional acceleration signal is exceeded, the autonomic nervous activity signal causes a significant change of the autonomic nervous activity.

An autonomic nervous activity signal of a non-target individual is one that does not normally characterize the state of antagonism between sympathetic and parasympathetic nerves. Conversely, an autonomic nervous activity signal of a target individual refers to an autonomic nervous activity signal that is capable of normally characterizing a state of antagonism between sympathetic and parasympathetic nerves.

Specifically, a human body three-dimensional acceleration signal and an autonomic nerve activity signal which are acquired by a medical sensor are acquired, then the human body three-dimensional acceleration signal and the autonomic nerve activity signal are segmented to obtain a plurality of time-divided human body three-dimensional acceleration signals and autonomic nerve activity signals, and finally the human body three-dimensional acceleration signal is preset by using a three-dimensional acceleration trend-removing fluctuation signal to distinguish whether the body activity obviously affects the autonomic nerve activity or not, so that the autonomic nerve activity signal capable of representing the antagonistic state between sympathetic and parasympathetic nerves is obtained, and the preprocessing and acquisition of the autonomic nerve activity are also finished.

In this embodiment, the mood state monitoring method performs segmentation processing on the autonomic nervous activity signal and the human body three-dimensional acceleration signal of the target individual acquired by the medical sensor to obtain a plurality of time-divided human body three-dimensional acceleration signals and autonomic nervous activity signals, distinguishes whether the plurality of time-divided body activities (the human body three-dimensional acceleration signals) influence the autonomic nervous activity by presetting the human body three-dimensional acceleration signals, and eliminates the time-divided human body three-dimensional acceleration signals and the autonomic nervous activity signals larger than the preset human body three-dimensional acceleration signals to obtain the target autonomic nervous activity signals. Because the human body three-dimensional acceleration signals of the time intervals which are greater than the preset human body three-dimensional acceleration signals can interfere the detection of the mood state, the validity of the mood state detection result can be further ensured by eliminating the human body three-dimensional acceleration signals of the time intervals which are greater than the preset human body three-dimensional acceleration signals.

Optionally, the step S300 may specifically include: steps S310-S330.

Step S310: according to a preset pressure grade evaluation feature space, respectively carrying out pressure grade evaluation on the physiological data of a plurality of time intervals to obtain the physiological data of the plurality of time intervals after the pressure grade evaluation, and calculating the physiological data of the plurality of time intervals according to a preset pressure grading method to obtain the pressure grades of the physiological data of the plurality of time intervals;

step S320: carrying out parasympathetic forced regulation detection on the physiological data of a plurality of time intervals according to a preset parasympathetic forced regulation state detection feature space to obtain parasympathetic forced regulation time distribution and frequency of the physiological data of the time intervals;

step S330: and analyzing and comparing the pressure scores of the physiological data of a plurality of time intervals and the distribution and frequency of the parasympathetic forced regulation time according to the preset mood state evaluation feature space so as to determine the mood state of the target individual.

In this embodiment, the preset pressure level evaluation feature space is used for performing pressure scoring on the physiological data of a plurality of time intervals, the preset parasympathetic forced regulation state detection feature space is used for performing regulation time distribution and frequency detection on the physiological data of the plurality of time intervals in a parasympathetic forced regulation manner, and the preset mood state evaluation feature space is used for performing mood state analysis and comparison on the pressure scoring and the parasympathetic forced regulation time distribution and frequency of the physiological data of the plurality of time intervals, so as to determine the mood state of the individual. The calibration of the physiological data samples in the preset pressure level evaluation space, the preset parasympathetic forced regulation state detection characteristic space and the preset mood state evaluation characteristic space adopts various effective experience effect criteria and selects various physiological indexes capable of revealing key characteristics of mental pressure and parasympathetic forced regulation, so that the universal applicability and transverse comparability of the physiological data samples are ensured, and secondly, the mood state is monitored by combining the pressure scoring of the physiological data in multiple time periods and the parasympathetic forced regulation, so that the completeness of the mood state detection result is ensured, and the mood state of an individual can be effectively and completely detected when the physiological data of the individual collected in real time are detected.

Optionally, the preset pressure rating feature space is constructed by:

please refer to fig. 6, which illustrates a schematic diagram of a preset pressure rating feature space provided in an embodiment of the present application

1) Performing pressure grade calibration on preset physiological data according to preset pressure grade experience effect calibration to obtain preset physiological data of a plurality of pressure grades;

the preset pressure level experience indicators include, but are not limited to, prior knowledge of the pressure source, psychological experience of the pressure response, physiological response and behavioral performance, and the embodiments of the present application are not limited thereto.

The plurality of pressure levels include, but are not limited to, four pressure levels of no pressure, weak pressure, medium pressure and strong pressure, and other classification levels are also possible, and embodiments of the present application are not specifically limited herein.

2) And calculating the preset physiological data of a plurality of pressure levels according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms to obtain the calculation results of the preset physiological data of the plurality of pressure levels, and constructing a preset pressure level evaluation characteristic space according to the calculation results.

The periodic function of the target sequence rhythm is a metric that reflects the state of balance of sympathetic and parasympathetic activity.

The mean fluctuation function of the rhythms of the two target sequences is a measure reflecting the competition of sympathetic and parasympathetic activity.

The following are specifically exemplified:

example 1: under the action of the answers and the strong pressure sources of the Master graduate paper (pressure source prior knowledge), the pressure level of the tested self-describing is strong pressure (psychological experience of pressure reaction), the heartbeat of the tested self-describing is obviously faster than usual (pressure physiological reaction), the tested self-describing cannot answer the questions of experts correctly in behavior, even cannot pass the answers and the answers (behavior expression of pressure), and the physiological data of the crowd in the answers and the answers situation of the graduate paper are marked as the strong pressure.

Example 2: during nap, the subject's body and spirit are in a relaxed state (prior knowledge of the stress source), self-wording is stress-free (psychological experience), the heartbeat is significantly slower than before nap (physiological response), and the relaxation in nap state (behavioral performance) can be seen from body posture and facial expression, so the physiological data of the crowd in nap situation is marked as stress-free.

And for the pressure marking mode in other real life situations, the grade label of the pressure physiological data is calibrated by combining the prior knowledge of the pressure source, the pressure response psychological experience, the physiological response and the behavioral performance.

Specifically, through experience validation of various pressure levels, pressure level calibration can be effectively performed on physiological data under different real life situations, in addition, the two physiological indexes are key characteristics for reflecting parasympathetic forced regulation, so that the change of autonomic nervous activity signals of the physiological data of different pressure levels can be effectively reflected by adopting a periodic function of a target sequence rhythm and an average fluctuation function of two times of target sequence rhythms, for the subsequently and actually acquired physiological data, after the acquired physiological data are mapped to a preset pressure level evaluation space, the pressure level of the acquired physiological data can be directly determined according to the autonomic nervous activity signals, and meanwhile, the effectiveness of the physiological data pressure level evaluation is also ensured.

In this embodiment, the preset physiological data is subjected to pressure level calibration by a preset pressure level experience validation, and then the preset physiological data after pressure level calibration is represented by a periodic function of a target sequence rhythm reflecting key characteristics of the autonomic nervous activity rule and an average fluctuation function of two times of the target sequence rhythm, so that the regular distribution of the preset physiological data in the feature space is obtained and used as a preset pressure level evaluation feature space. The pressure grade calibration is carried out on the preset physiological data by adopting the effective preset pressure grade experience effect scale to obtain the preset physiological data of a plurality of pressure grades, and then the scatter distribution of the preset physiological data of the plurality of pressure grades in the preset pressure grade evaluation space is supported according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms, so that the effectiveness, the universality applicability and the transverse comparability of the pressure grade calibration of the preset physiological data are ensured, and the constructed preset pressure grade evaluation characteristic space can effectively carry out the pressure grade evaluation on the physiological data acquired in real time.

Optionally, the preset pressure scoring method includes formula one:

score is the stress Score of the time-phased physiological data; x is physiological data of time intervals; x1 is a class center of preset physiological data corresponding to the pressure level of the physiological data of the time period; s is the standard deviation in class of the preset physiological data; j is the pressure level of the physiological data of the time period, and the step 310 may specifically include: steps S311-S314.

It should be noted that the essence of the preset pressure scoring formula is to map the physiological data subjected to experience validation of the preset pressure levels equally into the interval of [0-100], and since the preset pressure level evaluation feature space only contains the physiological data of four pressure levels, the pressure scoring interval of each pressure level is: no pressure: [0-25], weak pressure: [25-50], moderate pressure [50-75], strong pressure [75-100], that is, when there are 5 pressure levels in the physiological data, the corresponding pressure scoring interval becomes: no pressure: [0-20], weak pressure: 20-40, 40-60 middle pressure, 60-80 strong pressure and 80-100 super strong pressure. Therefore, the division of the pressure grade in the embodiment of the present application is not specifically limited herein, and may be specifically set according to actual requirements.

In addition, the numerical value 25 in the formula one is obtained by dividing 4 pressure classes adopted in the embodiment of the present application, and then mapping the four pressure classes to the interval of [0-100] for uniform division, that is, 100/4=25, if the pressure classes are divided into 5, then 100/5=20, and so on.

In addition, j in the formula one does not refer to 4 levels of no pressure, weak pressure, medium level pressure and strong pressure, but refers to a specific numerical value obtained by sorting the 4 levels of no pressure, weak pressure, medium level pressure and strong pressure, wherein the larger j indicates that the pressure is stronger, and since the scoring interval of no pressure is [0-25] is the minimum, the level of no pressure is 0, the scoring interval of weak pressure is [25-50] is located at the second, the level of weak pressure is 1, and so on, the level of medium pressure is 2, and the level of strong pressure is 3.

In an embodiment, when the preset pressure level assessment feature space is constructed, after the physiological data is represented by two indexes, namely a periodic function of a target sequence rhythm and an average fluctuation function of two target sequence rhythms, the physiological data is not distributed in non-pressure scatter points or not distributed in strong pressure scatter points, so that a score value of less than 0 or more than 100 may exist when the pressure score is calculated, and at this time, a value of 0 or 100 should be selected, and the value of not less than 0 or more than 100 should be selected.

Step S311: calculating physiological data of a plurality of time intervals according to a periodic function of a target sequence rhythm and an average fluctuation function of two target sequence rhythms to obtain a calculation result of the physiological data of the plurality of time intervals;

step S312: mapping the calculation results of the physiological data of a plurality of time intervals to a preset pressure level evaluation feature space respectively, and performing distance calculation on class centers of the calculation results of the preset physiological data of a plurality of pressure levels and the calculation results respectively to obtain the distance between the calculation results of the physiological data of a plurality of time intervals and the class centers of the calculation results of the preset physiological data of a plurality of pressure levels respectively;

step S313: respectively determining a plurality of minimum distances from the distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the preset physiological data of the plurality of pressure levels, and respectively taking the pressure levels of the preset physiological data corresponding to the minimum distances as the pressure levels of the physiological data of the plurality of time intervals;

step S314: and obtaining the pressure scores of the physiological data of the multiple time intervals according to the formula I, the physiological data of the multiple time intervals, the class center of the preset physiological data of the pressure grades corresponding to the physiological data of the multiple time intervals, the standard deviation in the class of the preset physiological data and the pressure grades of the physiological data of the multiple time intervals.

It can be understood that the preset pressure level assessment feature space comprises physiological data of a plurality of pressure levels, when the physiological data of a plurality of time intervals are represented by a periodic function of a target sequence rhythm and an average fluctuation function of two target sequence rhythms in the scatter distribution of the preset pressure level assessment feature space, the distribution relation between the scatter distribution of the physiological data of the plurality of time intervals and the scatter distribution of the physiological data of the plurality of pressure levels can be observed, then the pressure level of the physiological data of the pressure level closest to the physiological data of the time intervals is used as the pressure level of the physiological data of the time intervals, and finally the physiological data of the determined pressure level is calculated according to a formula I to obtain the pressure score of the physiological data.

In this embodiment, the periodic function of the target sequence rhythm and the average fluctuation function of two target sequence rhythms are used to represent the scatter distribution in the preset pressure level assessment feature space for the physiological data of multiple time intervals, then the distance between the physiological data of multiple time intervals and the preset physiological data of multiple pressure levels is observed, the pressure level of the preset physiological data respectively closest to the physiological data of multiple time intervals is used as the pressure level of the physiological data of multiple time intervals, and finally, the physiological data of multiple time intervals with the assessed pressure levels are scored according to a preset scoring method, so as to obtain the pressure scores of the physiological data of multiple time intervals. The preset stress grading characteristic space can effectively carry out stress grading on the physiological data, so that the raw stress score calculated when the physiological data with the graded stress is subjected to stress grading is also effective, and an effective basis is provided for the mood state detection in the aspect of stress grading.

Optionally, the preset parasympathetic forced regulation state detection feature space is constructed by:

it should be noted that the embodiment of the present application uses three types of indicators, wherein the first type is a key indicator describing forced regulation of parasympathetic nerves. The other two types of indexes are classic indexes for analyzing autonomic nervous activity rules by using visceral rhythm time series. When the first type of index and the other two types of indexes form a high-dimensional feature space, the information complementation between the features better describes the distribution rule of the two types of data samples whether parasympathetic nerves are forcibly regulated or not in the feature space. Therefore, the present invention detects whether parasympathetic forced modulation occurs by monitoring the distribution of the feature space in the preset parasympathetic forced modulation state by the first physiological data and the second physiological data.

1) Calibrating preset physiological data according to a preset pressure level experience effect standard, a preset fatigue theoretical model, a preset work and rest effect standard and a diet irregularity effect standard to obtain a plurality of first physiological data and second physiological data; wherein the first physiological data is designated as parasympathetic forced modulation;

the first physiological data is a physiological signal which is high in mental alertness within a physiological non-tired time and contains autonomic nervous activity information in a mental and physical relaxation state, and is calibrated to be forcedly regulated by parasympathetic nerves.

The second physiological data is physiological signals containing autonomic nervous activity information under strong stress and low mental alertness in physiological fatigue-prone time in special life events deviating from a balance state.

The physiological fatigue-free time refers to the time beginning by taking the morning getting up as timing after normal night sleep, and 3 hours later, the physiological fatigue-free time is obtained according to a preset fatigue theoretical model.

In one embodiment, the physiological data is graded for fatigue by fatigue grade (0-10 grade, 0 means no fatigue at all, 10 means exhausted by muscle for higher score, and then the level of mental alertness is judged according to the fatigue grade.

The physiological fatigue-prone time is obtained according to a preset fatigue theoretical model after the physiological fatigue-prone time is 6 hours after the normal sleep and waking up.

The strong pressure is judged whether to be the strong pressure according to four experience significances of pressure source prior knowledge, psychological experience, physiological response and behavior.

2) Respectively carrying out continuous wavelet transformation on the plurality of first physiological data and the plurality of second physiological data according to a wavelet basis function of a preset transformation scale interval to obtain a plurality of first physiological data and second physiological data and a plurality of geometric form approximation degree measurement indexes of physiological data of different time intervals;

the preset transformation scale interval refers to a numerical range of wavelet coefficients of a wavelet basis function, and is not limited herein in the embodiments of the present application.

In one embodiment, key indicators reflecting parasympathetic forced modulation are employed: and then selecting a maximum transformation scale from the plurality of transformation scales which can most approximate the first physiological data and the second physiological data, wherein the reason for selecting the maximum transformation scale is that the maximum transformation scale can represent forced regulation of parasympathetic nerves.

3) Respectively carrying out average difference calculation on the plurality of first physiological data and the second physiological data and the adjacent first physiological data and second physiological data to obtain the average difference of the plurality of first physiological data and second physiological data;

in one embodiment, a first class of classical indicators that reflect the laws of autonomic nervous activity is employed: and (4) taking an index Tn for describing the small-scale heart rate variation in the time domain. The subscript n represents more than one such optional indicator, such as the mean of adjacent heart rate difference values, etc. Such indicators are used to reveal the relative degree of gambling of the sympathetic and parasympathetic nerves. The index has a large value, which represents that the game of sympathetic and parasympathetic nerves is violent, and vice versa represents the inhibition of one autonomic nerve branch.

4) Acquiring power values of a plurality of first physiological data and second physiological data under a preset frequency;

in one embodiment, a first class of classical indicators reflecting autonomic nervous activity rules is employed: 3. an index Fn in the frequency domain describing the relative activation degree of parasympathetic nerves is taken. The index n represents more than one such alternative indicator, such as the total power of the sub-bands at 0.15Hz-0.4Hz for the heart rate series.

5) Obtaining a plurality of calculation results of the first physiological data and the second physiological data based on the maximum transformation scale, the average difference and the power value under the preset frequency of the plurality of first physiological data and the second physiological data;

6) And constructing a parasympathetic forced regulation state detection feature space according to the calculation results of the plurality of first physiological data and the second physiological data.

In this embodiment, the preset physiological data is evaluated through a preset pressure level experience effect scale, a preset fatigue theoretical model, a preset work and rest effect scale and a diet irregularity effect scale to obtain first physiological data and second physiological data, and then the first physiological data and the second physiological data are represented by a wavelet approximation degree measurement index of a preset transformation scale interval reflecting key features of autonomic nervous activity rules, an index of target sequence variation and a relative activation degree index within a preset frequency, so that regular distribution of the preset physiological data in a feature space is obtained to serve as a preset parasympathetic nerve forced regulation state detection feature space. The method comprises the steps of calibrating preset physiological data by adopting effective preset pressure level experience effect and a preset fatigue theoretical model and other preset special events causing forced parasympathetic regulation to obtain physiological data with forced parasympathetic regulation and without forced parasympathetic regulation, and then supporting scatter distribution of the physiological data with forced parasympathetic regulation and without forced parasympathetic regulation in a preset parasympathetic regulation state detection characteristic space according to a wavelet approximation degree measurement index of a preset transformation scale interval, an index of target sequence variation and a relative activation degree index in a preset frequency, so that the effectiveness, universality and transverse comparability of forced parasympathetic regulation detection of the preset physiological data are ensured, and the constructed preset parasympathetic regulation state detection characteristic space can effectively carry out forced parasympathetic regulation detection on real-time collected physiological data.

Optionally, step S320 may specifically include: steps S321-S327.

Step S321: performing wavelet transformation on the physiological data of the plurality of time intervals to obtain geometric form approximation degree measurement indexes of the physiological data of the plurality of time intervals;

step S322: calculating the average difference of the physiological data of a plurality of time intervals and the physiological data of the adjacent time intervals to obtain the average difference of the physiological data of the plurality of time intervals;

step S323: acquiring power values of a plurality of time-interval physiological data under a preset frequency;

step S324: obtaining a calculation result of the physiological data of a plurality of time intervals based on the geometric form approximation degree measurement index, the average difference and the power value under the preset frequency of the physiological data of the plurality of time intervals;

step S325: respectively mapping the calculation results of the physiological data of a plurality of time intervals to a preset parasympathetic forced regulation state detection characteristic space, and respectively carrying out distance calculation on class centers of the calculation results of the first physiological data and the second physiological data and the calculation results to obtain the distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the first physiological data and the second physiological data;

it should be noted that the time-interval-divided physiological data refers to a time-interval-divided target sequence of the autonomic nervous activity signals, and the target sequence is a wavelength similar to the first physiological data and the second physiological data, so that the time-interval-divided physiological data can be directly compared with the transformation scale of the first physiological data and the second physiological data without any calculation.

It can be understood that, since the first physiological data is the physiological data in which the parasympathetic nerve appears, which is determined in advance through the preset pressure level experience significances and the preset fatigue model, the first physiological data in the preset parasympathetic nerve forced regulation state detection feature space meets the three indexes, and the parasympathetic nerve forced regulation can be reflected. Therefore, when the calculation result of the time-interval physiological data is similar to the index of the first physiological data, the time-interval physiological data shows that the parasympathetic forced regulation occurs.

Step S326: determining a plurality of minimum distances from the distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the first physiological data and the second physiological data respectively;

step S327: if the preset physiological data corresponding to the minimum distances is the first physiological data, marking the time-interval physiological data corresponding to the minimum distances as parasympathetic forced adjustment, and recording the times of parasympathetic forced adjustment of the time-interval physiological data to obtain the time distribution and frequency of parasympathetic forced adjustment of the time-interval physiological data.

Specifically, physiological data of a plurality of time intervals, average differences and power under a preset frequency are mapped to a preset parasympathetic forced regulation state detection feature space, then the relation between the physiological data of the time intervals and the scatter point distribution of first physiological data and the scatter point distribution of second physiological data is observed, the physiological data of the time intervals distributed close to the scatter point of the first physiological data are marked as parasympathetic forced regulation, finally, the times of marking of the parasympathetic forced regulation are recorded, and the regulation frequency in the time intervals is calculated according to the regulation times.

In the embodiment, the scatter distribution of the characteristic space in the preset parasympathetic forced regulation state is expressed by the wavelet basis function of the preset transformation scale interval, the index of the target sequence variation and the relative activation degree index in the preset frequency through the physiological data of the plurality of time segments, then the far and near degrees of the physiological data of the plurality of time segments and the preset physiological data with and without parasympathetic forced regulation are observed, the physiological data of the time segments closest to the parasympathetic forced regulation are respectively marked as parasympathetic forced regulation, then the times of the parasympathetic forced regulation are recorded, and finally the forced regulation frequency of the parasympathetic of the physiological data of the plurality of time segments is determined according to the time length of the time segments and the times of the parasympathetic forced regulation. The preset parasympathetic forced regulation state detection feature space can effectively detect the parasympathetic forced regulation of the physiological data, so that an effective basis is provided for the mood state detection in the aspect of parasympathetic forced regulation frequency.

Optionally, the preset mood state assessment feature space is constructed by:

1) Calibrating the mood state of the preset physiological data according to a preset self-evaluation table to obtain the preset physiological data of the calibrated mood state;

2) Calculating the pressure score and the parasympathetic forced regulation time distribution and frequency of the preset physiological data with the calibrated mood state to obtain the preset pressure score and the preset parasympathetic forced regulation time distribution and frequency with good mood state and bad mood state;

the preset self-rating scale includes, but is not limited to, various scales such as daytime fatigue time-of-day self-rating, nighttime sleep time and quality self-rating, anxiety self-rating, stress self-rating, and depression self-rating, and all scales capable of rating the mood state of the population are within the protection scope of the embodiment of the present application, and the embodiment of the present application is not particularly limited herein.

The following detailed description is made for the self-rating tables: for example, the testee participates in graduation answer within a certain time period of the day, self-evaluation is anxious before and during answer, stress is great, anxiety and stress are generated in the process of waiting for answer results after answer is finished, and fatigue grades are reported once an hour within the whole day of wakefulness; stress, anxiety and depression in the past 1 week or more are measured with an anxiety self-rating scale SAS, a depression self-rating scale SDS, a life event scale LES, a perceived stress scale PSS, etc., and the test self-reports the time to fall asleep, the time to get up, the presence or absence of wakefulness in the middle of the night, the self-sensory sleep quality, etc. for the first day and the same day.

It can be understood that the preset pressure scores, the preset time proportion and the preset forced adjustment frequency of the good mood state and the bad mood state are obtained by carrying out a plurality of preset self-evaluation table tests on the people with the good mood state and the bad mood state, and combining the preset pressure grade evaluation characteristic space and the preset parasympathetic forced adjustment state detection characteristic space, and then obtaining the pressure scores, the time proportion, the occurrence time and the situations of the parasympathetic forced adjustment and the occurrence time of the two types of people in all weather and a plurality of time intervals.

3) And constructing a preset mood state evaluation characteristic space according to preset pressure scores, preset parasympathetic forced regulation time distribution and preset frequency for good mood states and bad mood states.

Specifically, self-evaluation reports of the crowd are collected according to a plurality of preset self-evaluation tables, fatigue grades and work and rest time of a plurality of time intervals are analyzed, then pressure grades and parasympathetic forced regulation times of the plurality of time intervals detected by a characteristic space and a preset parasympathetic forced regulation state are evaluated according to the preset pressure grades, and corresponding pressure grades, time ratio and parasympathetic forced regulation frequencies under the conditions of good mood states and bad mood states are obtained finally.

In this embodiment, the preset physiological data is subjected to mood state calibration through a preset self-evaluation table, a preset pressure score, a preset duration ratio and a preset parasympathetic forced regulation time distribution and frequency of a good mood state and a bad mood state are obtained through pressure scoring and parasympathetic forced regulation detection of the physiological data of which the mood state is determined, and a preset mood state feature space is constructed according to the pressure score, the parasympathetic forced regulation time distribution and the frequency. Because the preset self-evaluation table is adopted to calibrate the mood state of the preset physiological data, the pressure score and the parasympathetic forced regulation of the physiological data with the calibrated mood state are analyzed, and the preset pressure score, the preset duration ratio and the preset forced regulation frequency of the good mood state and the bad mood state are obtained, the effectiveness of each index of the mood state of the preset physiological data is ensured, and the mood state detection can be effectively carried out on the physiological data collected in real time by the preset mood state characteristic space.

Optionally, the step S330 may specifically include: 331-S335.

For example, the index of judgment of the mood state of the embodiment of the present application: the mental pressure is higher than the scoring result of 50 points, the duration time of the scoring is a sensitive index of the poor mood, and the occurrence time (whether the scoring occurs at the sleep time) is a sensitive and specific index of the poor mood; the forced regulation frequency and time distribution of parasympathetic nerves are sensitive and specific indexes of bad mood. The combination of the mental stress and the parasympathetic forced regulation indexes is a key technical index for detecting bad mind.

Step S331: grouping the pressure scores of the physiological data of a plurality of time intervals according to the work and rest time of the target individual to obtain the pressure scores of the physiological data of a plurality of arousal states and sleeping states;

the work and rest time of the target individual refers to the time when the crowd sleeps and the time when the crowd does not sleep, and due to the fact that the work and rest time of each person is different, the physiological data of the time intervals can be grouped according to actual requirements.

Step S332: grouping the parasympathetic nerve forced regulation time distribution and frequency of the physiological data of a plurality of time intervals according to a preset pressure level experience effect scale and a preset fatigue theoretical model to obtain the parasympathetic nerve forced regulation time distribution and frequency of a plurality of physiological fatigue-prone times and physiological fatigue-prone times;

step S333: determining a pressure score of the physiological data of the arousal state, which is smaller than a preset pressure score of good mood state, from the pressure scores of the physiological data of the arousal states to obtain a pressure score of the physiological data of the first arousal state;

step S334: determining a stress score of the physiological data in the sleep state with the stress score of zero from the stress scores of the physiological data in the sleep states to obtain a stress score of the physiological data in the first sleep state;

step S335: and if the ratio of the duration corresponding to the pressure score of the physiological data in the first wake state to the durations in the plurality of time intervals is greater than the preset duration ratio of the good mood state, the ratio of the duration corresponding to the pressure score of the physiological data in the first sleep state to the durations in the plurality of time intervals is greater than the preset duration ratio of the good mood state, and the forced regulation frequency of the physiological fatigue-prone time is less than the preset regulation frequency of the good mood state, determining that the mood state is good.

Specifically, if the duration occupancy ratio of the time-interval mental pressure score lower than the mood good experience threshold in the full-day awake state is higher than the mood good experience threshold, the duration occupancy ratio of the time-interval mental pressure score zero in the sleep state is higher than the mood good experience threshold, the number of times of forced parasympathetic nerve adjustment in the awake state and the sleep state is lower than the mood good experience threshold, and the majority of times are distributed in the physiological fatigue-prone time, the mood state is judged to be good.

The following are exemplified:

please refer to fig. 7, which illustrates a schematic diagram of the pressure score, the heart rate sequence, the parasympathetic forced modulation mark and the human body three-dimensional acceleration signal of the subject in all weather under a good mood.

Figure 7 shows the mental stress scores and parasympathetic forced regulation markers of the subjects in a good state of the mind. The data samples have been validated through a variety of empirical criteria for mood well: on the data acquisition day and in the week before and after the data acquisition, no pressure source and behavior inducement inducing bad mood exist. An embodiment of the method of the present invention for detecting the mood state of the subject on the day through physiological signal processing is shown in fig. 7. As can be seen from the stress score of 7, the test was at the lowest stress level for most of the day, the score was below 25 points for most of the time, parasympathetic forced modulation was only occasionally observed during periods of physiological indefatigability, and parasympathetic forced modulation by fatigue occurred during periods of physiological indefatigability of about 18 to 21. Thus, the mood well-being detected from the frequency and temporal distribution of mental stress and parasympathetic forced regulation coincides with a real mood well-being label.

In this embodiment, the pressure scores and parasympathetic forced regulation of the physiological data of a plurality of time intervals are grouped according to the work and rest time of the target individual and the preset pressure level empirical criteria and the preset fatigue theoretical model, so as to obtain the pressure scores of the physiological data of the awake state and the sleep state and the parasympathetic forced regulation frequency of the physiological data of the physiologically fatigable state and the physiologically non-fatigable time, and then if the ratio of the pressure score of the physiological data of the awake state to the preset pressure score of the mood state is longer than the preset ratio of the mood state, and the ratio duration of the pressure score to zero in the sleep state is longer than the preset ratio of the mood state, and the parasympathetic forced regulation frequency of the physiological data of the physiologically fatigable state to the mood state is less than the preset forced regulation frequency of the mood state, the mood state of the individual is determined to be good. The pressure scores of physiological data of the wakefulness state and the sleep state and the parasympathetic forced regulation frequency of physiological fatigue-free time are judged through the preset mood state characteristic space, so that the good detection result of the mood state of the target individual has effectiveness and integrity.

Optionally, the step S330 may specifically further include: 331'-S333'.

Step S331': determining a pressure score of the physiological data of the arousal state which is larger than a preset pressure score of bad mood state from the pressure scores of the physiological data of the arousal states to obtain a pressure score of the physiological data of a second arousal state;

step S332': determining a pressure score of the physiological data of the sleep state which is larger than a preset pressure score of poor mood state from the pressure scores of the physiological data of the sleep states to obtain a pressure score of the physiological data of a second sleep state;

step S333': and if the ratio of the duration corresponding to the pressure score of the physiological data in the second wake state to the durations in the plurality of time intervals is greater than the preset duration ratio of the poor mood state, the ratio of the duration corresponding to the pressure score of the physiological data in the second sleep state to the durations in the plurality of time intervals is greater than the preset duration ratio of the poor mood state, and the forced adjusting frequency of the plurality of physiological fatigue-resistant times is greater than the preset adjusting frequency of the poor mood state, determining that the mood state is poor.

Specifically, if the duration occupancy rate of the time-interval mental pressure score higher than the poor-heart-context experience threshold value in the all-day awake state is higher than the poor-heart-context experience threshold value, the duration occupancy rate of the time-interval mental pressure score higher than the poor-heart-context experience threshold value in the sleep state is higher than the poor-heart-context experience threshold value, and the number of times of forced adjustment of the parasympathetic nerves in the awake state and the sleep state is higher than the poor-heart-context experience threshold value, and the parasympathetic nerves are distributed not only in the physiological fatigue-prone time, but also in the physiological fatigue-prone time, the mind state is determined to be poor.

The following are exemplified:

please refer to fig. 8, which illustrates a schematic diagram of the pressure score, the heart rate sequence, the parasympathetic forced modulation mark and the human body three-dimensional acceleration signal of the subject in all weather under bad mood.

Fig. 8 shows the day-to-day mental stress scores and parasympathetic forced modulation markers for a trial of dysthymia due to graduation answers. The data sample has been validated through a variety of experience to identify a poor state of mind and the cause that induced the state: in the afternoon of the day, 14-16% of the subjects were asked for graduation answers, a restlessness expectation with unknown results before the answers, a state of uneasiness in the process of stating work for experts, and a ruminal recall and a large consumption of physical and mental resources for events after the answers, resulting in an insecure mood throughout the day. Fig. 8 shows an embodiment of the method for monitoring a mood state of a subject on the day by processing a physiological signal. As can be seen from the stress score of fig. 8, the trial traced back to the beginning of morning data collection (about 8; after the answer, mental stress was relieved, but most of the time was still in a state of weak stress (greater than 25 cents, less than 50 cents), and was still accompanied by intensive parasympathetic forced regulation, revealing that events that easily lead to poor mood continued; during the evening sleep of the day, the subject mental stress rarely appears a score of 0 in a state of good sleep. Therefore, the bad mood detected from the frequency and time distribution of the mental stress and the parasympathetic forced regulation coincides with the real bad mood label, that is, the mood state is determined to be bad.

In one embodiment, the mood state is determined to be normal if the time-phased mental stress score, the time-length ratio and the parasympathetic forced modulation frequency in the full-day arousal state are between the two judgment indexes.

In this embodiment, when the ratio duration of the pressure score of the physiological data in the wakefulness state being greater than the preset ratio duration of the poor mood is greater than the preset ratio duration of the poor mood, the ratio duration of the pressure score of the physiological data in the sleep state being greater than the preset ratio duration of the poor mood is greater than the preset ratio duration of the poor mood, and the parasympathetic forced modulation frequency of the physiological data in the physiological non-fatigability time being greater than the preset forced modulation frequency of the poor mood, the mood state of the individual is determined to be poor. The pressure scores of physiological data of the wakefulness state and the sleep state and the parasympathetic forced regulation frequency of the physiological fatigue-free time are judged through the preset mood state characteristic space, so that the detection result that the mood state of the target individual is poor has effectiveness and integrity.

Please refer to fig. 9 for a schematic structural diagram of a mood state monitoring device according to an embodiment of the present application.

The embodiment of the present application provides a mood state monitoring device 200, including:

an obtaining module 210, configured to obtain an autonomic nerve activity signal of a target individual; wherein the autonomic neural activity signals comprise a plurality of time-phased autonomic neural activity signals;

an extracting module 220, configured to extract a target sequence from the multiple time-interval autonomic nervous activity signals respectively, so as to obtain multiple time-interval physiological data;

the analysis module 230 is configured to calculate and compare the plurality of time-sliced physiological data according to a preset feature space to determine a mood state of the target individual; wherein the preset feature space comprises: the method comprises the steps of presetting a pressure grade evaluation characteristic space, presetting a parasympathetic forced regulation state detection characteristic space and presetting a mood state evaluation characteristic space.

Optionally, the obtaining module 210 is further configured to: acquiring physiological signals of the target individual acquired by a medical sensor; wherein the physiological signals comprise autonomic nerve activity signals and human body three-dimensional acceleration signals; carrying out segmentation calculation on the autonomic nerve activity signals and the human body three-dimensional acceleration signals to obtain a plurality of time-divided human body three-dimensional acceleration signals and autonomic nerve activity signals; judging whether the plurality of time-sharing human body three-dimensional acceleration signals are larger than a preset human body three-dimensional acceleration signal or not; if so, determining the autonomic nerve activity signals corresponding to the human body three-dimensional acceleration signals of the multiple time intervals as autonomic nerve activity signals of non-target individuals; and if not, determining the autonomic nerve activity signals corresponding to the human body three-dimensional acceleration signals of the multiple time intervals as the autonomic nerve activity signals of the target individual.

Optionally, the analysis module 230 is further configured to: according to the preset pressure rating characteristic space, respectively performing pressure rating on the physiological data of the plurality of time intervals to obtain the physiological data of the plurality of time intervals after the pressure rating, and calculating the physiological data of the plurality of time intervals according to a preset pressure rating method to obtain pressure ratings of the physiological data of the plurality of time intervals; carrying out parasympathetic forced regulation detection on the physiological data of the plurality of time intervals according to the preset parasympathetic forced regulation state detection feature space to obtain the parasympathetic forced regulation time distribution and frequency of the physiological data of the plurality of time intervals; analyzing and comparing the pressure scores and the parasympathetic forced modulation time distribution and frequency of the physiological data of the plurality of time intervals according to the preset mood state evaluation feature space to determine the mood state of the target individual.

Optionally, the analysis module 230 is further configured to: performing pressure grade calibration on preset physiological data according to preset pressure grade experience effect calibration to obtain preset physiological data of a plurality of pressure grades; and calculating the preset physiological data of the multiple pressure levels according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms to obtain the calculation result of the preset physiological data of the multiple pressure levels, and constructing the preset pressure level evaluation feature space according to the calculation result.

Optionally, the analysis module 230 is further configured to: calculating the physiological data of the plurality of time intervals according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms to obtain the calculation results of the physiological data of the plurality of time intervals; mapping the calculation results of the physiological data of the plurality of time intervals to the preset pressure level evaluation feature space respectively, and calculating the distance between the class center of the calculation results of the preset physiological data of the plurality of pressure levels and the calculation results respectively to obtain the distance between the calculation results of the physiological data of the plurality of time intervals and the class center of the calculation results of the preset physiological data of the plurality of pressure levels respectively; determining a plurality of minimum distances from the distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the preset physiological data of the plurality of pressure levels respectively, and taking the pressure levels of the preset physiological data corresponding to the minimum distances as the pressure levels of the physiological data of the plurality of time intervals respectively; and obtaining the stress scores of the physiological data of the plurality of time intervals according to the formula I, the physiological data of the plurality of time intervals, the class center of preset physiological data of the corresponding stress grade of the physiological data of the plurality of time intervals, the class standard deviation of the preset physiological data and the stress grade of the physiological data of the plurality of time intervals.

Optionally, the analysis module 230 is further configured to: calibrating preset physiological data according to a preset pressure level experience effect standard, a preset fatigue theoretical model, a preset work and rest effect standard and a diet irregularity effect standard to obtain a plurality of first physiological data and second physiological data; wherein the first physiological data is designated as parasympathetic-forced modulation; respectively carrying out continuous wavelet transformation on the plurality of first physiological data and the plurality of second physiological data according to a wavelet basis function of a preset transformation scale interval to obtain a geometric form approximation degree measurement index of the plurality of first physiological data and the plurality of second physiological data and the plurality of sub-period physiological data; respectively carrying out average difference calculation on the plurality of first physiological data and the plurality of second physiological data and the adjacent first physiological data and second physiological data to obtain average differences of the plurality of first physiological data and the plurality of second physiological data; acquiring power values of the plurality of first physiological data and the plurality of second physiological data under a preset frequency; obtaining a calculation result of the plurality of first physiological data and second physiological data based on the maximum transformation scale, the average difference and the power value under the preset frequency of the plurality of first physiological data and second physiological data; and constructing the parasympathetic forced regulation state detection feature space according to the calculation results of the plurality of first physiological data and second physiological data.

Optionally, the analysis module 230 is further configured to: performing wavelet transformation on the physiological data of the plurality of time intervals to obtain geometric form approximation degree measurement indexes of the physiological data of the plurality of time intervals; calculating the average difference of the physiological data of the plurality of time intervals and the adjacent physiological data of the time intervals to obtain the average difference of the physiological data of the plurality of time intervals; acquiring power values of the physiological data of the plurality of time intervals under the preset frequency; obtaining a calculation result of the physiological data of the plurality of time intervals based on the geometric shape approximation degree measurement index, the average difference and the power value under the preset frequency of the physiological data of the plurality of time intervals; mapping the calculation results of the physiological data of the plurality of time intervals to the preset parasympathetic forced regulation state detection feature space respectively, and performing distance calculation on class centers of the calculation results of the plurality of first physiological data and the plurality of second physiological data and the calculation results respectively to obtain distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the plurality of first physiological data and the plurality of second physiological data respectively; determining a plurality of minimum distances from the distances between the calculation results of the plurality of time-interval physiological data and the class centers of the calculation results of the plurality of first physiological data and second physiological data respectively; if the preset physiological data corresponding to the minimum distances is the first physiological data, marking the time-division physiological data corresponding to the minimum differences as parasympathetic forced adjustment, and recording the times of parasympathetic forced adjustment of the time-division physiological data to obtain the time distribution and frequency of parasympathetic forced adjustment of the time-division physiological data.

Optionally, the analysis module 230 is further configured to: calibrating the mood state of the preset physiological data according to a preset self-evaluation table to obtain the preset physiological data with the calibrated mood state; calculating pressure scores and parasympathetic mandatory regulation time distribution and frequency of the preset physiological data with the calibrated mood state to obtain preset pressure scores, preset time occupation ratios and preset mandatory regulation frequencies of good mood state and bad mood state; and constructing the preset mood state evaluation feature space according to the preset pressure score, the preset parasympathetic forced regulation time distribution and the preset frequency of the good mood state and the bad mood state.

Optionally, the analysis module 230 is further configured to: grouping the pressure scores of the physiological data of the plurality of time intervals according to the work and rest time of the target individual to obtain a plurality of pressure scores of the physiological data of the arousal state and the sleep state; grouping the parasympathetic nerve forced regulation time distribution and frequency of the physiological data of the plurality of time intervals according to a preset pressure level experience effect scale and a preset fatigue theoretical model to obtain the parasympathetic nerve forced regulation time distribution and frequency of a plurality of physiological fatigue-prone times and physiological fatigue-insusceptible times; determining a pressure score of the physiological data of the arousal state, which is smaller than a preset pressure score of good mood state, from the pressure scores of the physiological data of the arousal states, and obtaining a pressure score of the physiological data of the first arousal state; determining a stress score of the physiological data in the sleep state with the stress score of zero from the stress scores of the physiological data in the sleep state to obtain a stress score of the physiological data in the first sleep state; and if the ratio of the time length corresponding to the pressure score of the physiological data of the first wakefulness state to the time lengths of the plurality of time intervals is greater than the preset time length ratio of the good mood state, the ratio of the time length corresponding to the pressure score of the physiological data of the first sleep state to the time lengths of the plurality of time intervals is greater than the preset time length ratio of the good mood state, and the forced adjusting frequency of the plurality of physiological fatigue-prone time states is less than the preset adjusting frequency of the good mood state, determining that the mood state is good.

Optionally, the analysis module 230 is further configured to: determining a pressure score of the physiological data of the arousal state which is larger than the preset pressure score of the bad mood state from the pressure scores of the physiological data of the arousal states to obtain a pressure score of the physiological data of a second arousal state; determining a pressure score of the physiological data in the sleep state, which is greater than a preset pressure score of poor mood state, from the pressure scores of the physiological data in the sleep state to obtain a pressure score of the physiological data in a second sleep state; and if the ratio of the duration corresponding to the pressure score of the physiological data of the second arousal state to the durations of the plurality of time intervals is greater than the preset duration ratio of the bad mood state, the ratio of the duration corresponding to the pressure score of the physiological data of the second sleep state to the durations of the plurality of time intervals is greater than the preset duration ratio of the bad mood state, and the forced adjusting frequency of the plurality of physiological fatigue-resistant times is greater than the preset adjusting frequency of the bad mood state, determining that the mood state is bad.

It should be understood that the device corresponds to the above-mentioned mood state monitoring method embodiment, and can perform the steps involved in the above-mentioned method embodiment, and the specific functions of the device can be referred to the above description, and the detailed description is appropriately omitted here to avoid redundancy. The device includes at least one software function that can be stored in memory in the form of software or firmware (firmware) or solidified in the Operating System (OS) of the device.

The embodiment of the application also provides a storage medium, wherein the storage medium is stored with a computer program, and the computer program is executed by a processor to execute the method.

The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The above description is only an alternative embodiment of the embodiments of the present application, but the scope of the embodiments of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present application, and all the changes or substitutions should be covered by the scope of the embodiments of the present application.

Claims

1. A method of mood state monitoring, the method comprising:

respectively extracting target sequences from the plurality of time-interval autonomic nervous activity signals to obtain a plurality of time-interval physiological data;

2. The mood state monitoring method according to claim 1, wherein the obtaining of the autonomic nervous activity signals of the target individual comprises:

3. The mood state monitoring method as recited in claim 1, wherein the calculating and comparing the plurality of time-sliced physiological data according to a preset feature space to determine the mood state of the target individual comprises:

according to the preset pressure grade evaluation feature space, respectively carrying out pressure grade evaluation on the physiological data of the plurality of time intervals to obtain the physiological data of the plurality of time intervals after the pressure grade evaluation, and calculating the physiological data of the plurality of time intervals according to a preset pressure grading method to obtain the pressure grades of the physiological data of the plurality of time intervals;

carrying out parasympathetic forced regulation detection on the physiological data of the plurality of time intervals according to the preset parasympathetic forced regulation state detection feature space to obtain the parasympathetic forced regulation time distribution and frequency of the physiological data of the plurality of time intervals;

4. The mood state monitoring method according to claim 3, wherein the preset pressure rating feature space is constructed by:

5. The method according to claim 4, wherein the predetermined stress score is given by the formula one:

score is the stress Score of the time-sliced physiological data; x is the physiological data of the time interval; x1 is a class center of preset physiological data corresponding to the pressure level of the physiological data of the time intervals; s is a class standard deviation of preset physiological data; j is the stress level of the physiological data of the time interval;

the pressure rating of the physiological data of the plurality of time intervals is respectively carried out according to the preset pressure rating characteristic space to obtain the physiological data of the plurality of time intervals after the pressure rating, and the pressure rating of the physiological data of the plurality of time intervals is obtained by calculating the physiological data of the plurality of time intervals according to a preset pressure rating method, which comprises the following steps:

calculating the physiological data of a plurality of time intervals according to the periodic function of the target sequence rhythm and the average fluctuation function of the two target sequence rhythms to obtain the calculation results of the physiological data of the plurality of time intervals;

mapping the calculation results of the physiological data of the plurality of time intervals to the preset pressure level evaluation feature space respectively, and performing distance calculation on class centers of the calculation results of the preset physiological data of the plurality of pressure levels and the calculation results respectively to obtain distances between the calculation results of the physiological data of the plurality of time intervals and the class centers of the calculation results of the preset physiological data of the plurality of pressure levels respectively;

6. The mood state monitoring method as recited in claim 3, wherein the preset parasympathetic forced modulation state detection feature space is constructed by:

calibrating preset physiological data according to a preset pressure level experience effect scale, a preset fatigue theoretical model, a preset work and rest and a diet irregularity effect scale to obtain a plurality of first physiological data and second physiological data; wherein the first physiological data is designated as parasympathetic-forced modulation;

respectively carrying out average difference calculation on the plurality of first physiological data and the plurality of second physiological data and the adjacent first physiological data and second physiological data to obtain average differences of the plurality of first physiological data and the plurality of second physiological data;

and constructing the parasympathetic forced regulation state detection feature space according to the calculation results of the plurality of first physiological data and the plurality of second physiological data.

7. The method for monitoring the mood state according to claim 6, wherein the detecting the parasympathetic forced modulation of the physiological data of the plurality of time segments according to the preset parasympathetic forced modulation state detection feature space to obtain the time distribution and the frequency of the parasympathetic forced modulation of the physiological data of the plurality of time segments comprises:

performing wavelet transformation on the physiological data of the plurality of time segments to obtain geometric form approximation degree measurement indexes of the physiological data of the plurality of time segments;

obtaining a calculation result of the physiological data of the plurality of time intervals based on the geometric shape approximation degree measurement index, the average difference and the power value under the preset frequency of the physiological data of the plurality of time intervals;

if the preset physiological data corresponding to the minimum distances is the first physiological data, marking the time-division physiological data corresponding to the minimum distances as parasympathetic forced adjustment, and recording the times of parasympathetic forced adjustment of the time-division physiological data to obtain the time distribution and frequency of parasympathetic forced adjustment of the time-division physiological data.

8. The method according to claim 3, wherein the predetermined mood state assessment feature space is constructed by:

calculating the pressure score and the parasympathetic forced regulation time distribution and frequency of the preset physiological data with the calibrated mood state to obtain the preset pressure score and the preset parasympathetic forced regulation time distribution and frequency with good mood state and bad mood state;

and constructing the preset mood state evaluation feature space according to the preset pressure score, the preset parasympathetic forced regulation time distribution and the preset frequency of the good mood state and the bad mood state.

9. The method for monitoring the mood state according to claim 8, wherein the analyzing and comparing the stress scores and the forced adjustment time distribution and frequency of the plurality of time-interval physiological data according to the preset mood state assessment feature space to determine the mood state of the target individual comprises:

grouping the pressure scores of the physiological data of the plurality of time intervals according to the work and rest time of the target individual to obtain a plurality of pressure scores of the physiological data of the wakefulness state and the sleep state;

determining a pressure score of the physiological data of the arousal state, which is smaller than a preset pressure score of good mood state, from the pressure scores of the physiological data of the arousal states, and obtaining a pressure score of the physiological data of the first arousal state;

and if the ratio of the time length corresponding to the pressure score of the physiological data of the first wakefulness state to the time lengths of the plurality of time intervals is greater than the preset time length ratio of the good mood state, the ratio of the time length corresponding to the pressure score of the physiological data of the first sleep state to the time lengths of the plurality of time intervals is greater than the preset time length ratio of the good mood state, and the forced regulation frequency of the plurality of physiological fatigue-prone times is less than the preset regulation frequency of the good mood state, determining that the mood state is good.

10. The mood state monitoring method as recited in claim 9, wherein the analyzing and comparing the stress scores and the forced adjustment frequencies of the plurality of time-spaced physiological data according to a feature space assessed according to a preset mood state to determine the mood state comprises:

determining a pressure score of the physiological data of the arousal state, which is greater than the preset pressure score of the bad mood state, from the pressure scores of the physiological data of the arousal states to obtain a pressure score of the physiological data of a second arousal state;

11. A mood state monitoring device, the device comprising:

the analysis module is used for calculating and comparing the physiological data of the plurality of time intervals according to a preset feature space so as to determine the mood state of the target individual; wherein the preset feature space comprises: the method comprises the steps of presetting a pressure grade evaluation characteristic space, presetting a parasympathetic forced regulation state detection characteristic space and presetting a mood state evaluation characteristic space.

12. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 10.