Device for monitoring a user's psycho-emotional state

Abstract

The invention relates to medical technology. A device for monitoring a user's psycho-emotional state comprises a photoplethysmography sensor, a microcontroller, an accelerometer, an electrodermal activity sensor, and an analytic unit for generating psycho-emotional state assessment data on the basis of signals from the sensors. The analytic unit is configured to be capable of performing a preliminary analysis of data from the accelerometer and the photoplethysmography sensor to determine periods and levels of physical activity by the user during an assessment of the user's psycho-emotional state. The invention addresses the problem of creating a compact wearable device that is capable of very accurately recording physiological parameters of the user and transmitting these data via a wireless connection. The problem is solved by the simultaneous use of several physiological parameter sensors, the data from which are analyzed and adjusted, making it possible to assess the user's psycho-emotional state even during periods of activity, as well as by the use of compact and energy-efficient sensors and other components in the device.

Description

DEVICE FOR MONITORING THE USER'S PSYCHOEMOTIONAL STATE Field of technology

[0001] The claimed invention relates to electronic devices that provide for the collection and processing of user data for the purpose of monitoring the psycho-emotional state. State of the art

[0002] Obtaining information about a person's condition, in particular based on objective physiological indicators that correlate with a person's psycho-emotional state, is of interest in many areas of life and industry, including medicine, social services, security systems, and many others. At the same time, one of the most critical for solving monitoring problems is identifying a stressful state.

[0003] Some devices for monitoring the psycho-emotional state of the user and their components known from the state of the art are based primarily on pulse oximetry sensors, which does not provide a complete picture of emotional arousal and stress levels, since pulse oximetry readings are sensitive not only to changes in emotional background, but also to physical activity.

[0004] To address this issue, such devices can be supplemented with other data, such as skin electrical activity data, human movement data, heartbeat data, and more.

[0005] Electrodermal activity (EDA) combines a number of indicators, such as galvanic skin response (GSR), skin potential level SPL, skin potential response SPR, spontaneous skin potential response SRP, skin resistance level SRL or skin conductivity level SRL, skin resistance response SRL or skin conductivity response SPR, spontaneous skin resistance response SRR or spontaneous skin conductivity response SRL. devices. There are a number of methods and devices that can record data on the level and change of potential, resistance and conductivity of the skin. Most of these devices contain electrodes that are in contact with or at a small distance from the body to create conductivity or potential difference between them, which makes it possible to create signals based on the above indicators. Data with The electrical activity of the skin can be obtained using galvanic skin response (GSR) sensors, which have a number of disadvantages such as polarization of contacts, skin adaptation to a constant current flow, the need to place them on certain areas of the body, and a possible allergic reaction to the chemical composition of the electrodes. Also, GSR does not cover the entire set of electrodermal activity (EDA) data.

[0006] An invention is known (US 20220304603 A1; published on September 29, 2016; IPC: A61B 5 / 16; A61B 5 / 00; A61B 5 / 0205; A61B 5 / 024; A61B 5 / 0533; A61B 5 / 08; A61B 5 / 33; G16H 20 / 70; G16H 50 / 20), disclosing: one or more physiological sensors configured to interact with the user's body, and a transmitter capable of transmitting and receiving data obtained by one or more physiological sensors, one or more processors connected with the ability to exchange data with an emotional state monitoring device and configured to receive data from the transmitter, wherein one or more processors have a memory in which instructions are stored that, when executed, cause one or more processors to: obtain, using one or more physiological sensors, data corresponding to one or more physiological parameters of the user;detect, by at least one of the one or more physiological sensors, a change in at least one of the one or more physiological parameters; request, via the emotional state monitoring device, an emotional state identifier corresponding to the change; and provide, via the emotional state monitoring device, a suggested response based on the emotional state identifier.

[0007] The disadvantages of this invention include the fact that it does not provide specific implementation options for the said sensors or their combinations in a form suitable for implementation in a compact wearable device and ensuring compliance with a number of requirements related to user convenience, the absence of significant instrumental errors, the ability to operate from a compact power source and the provision of opportunities for determining the user's psycho-emotional stress.

[0008] Electrodermal activity (EDA) sensors are also known from the prior art, for example, the application (RU 2022110240 A; published on 16.10.2023; IPC: A61B 5 / 16; A61B 5 / 053) discloses a sensor that discloses a single-electrode sensor of electrical activity of the surface layer of the user's body, comprising: one electrode containing a plurality of conductors and configured to be placed on the body the user or at a distance from him, providing a capacitive and / or inductive connection "electrode-body"; an analytical unit, made with the possibility of determining one or more indicators of the electrical activity of the surface layer of the body based on at least one of the following signals: leakage current of the capacitor "electrode-body", capacitance of the capacitor "electrode-body", inductance of the system "electrode-body", a signal formed by an external electromagnetic field and passing through the said capacitor, modulation of the phase, frequency and / or amplitude of this signal. The proposed sensor is based on reading the potential of a solitary conductor, which is performed by adjusting the pulse signal generator.

[0009] The disadvantages of this invention include the fact that such a sensor is not very responsive, i.e. it gives a relatively small change in frequency with a relatively small change in capacitance, which reduces the accuracy of measurements.

[0010] An invention is also known (US 2016262690 A1; published on September 15, 2016; IPC: A61B 5 / 00; A61B 5 / 0205) disclosing a sleep quality management device that includes a sensor module and a processing unit. The sensor module is configured to output a heart rate signal and a skin conductivity signal. The processing unit is connected to the sensor module. The processing unit is configured to determine the sleep stage and stress level in accordance with the heart rate signal and the skin conductivity signal in order to identify the occurrence of stressful sleep. The occurrence of a stressful dream is identified when the sleep stage corresponds to the rapid eye movement (REM) stage, and the stress level corresponds to the stress state. [OOP] Another disadvantage of this invention is that it does not describe the possibility of making the device wearable. Also, the operation of the device is described only for a user in a sleep state, and its ability to work in the case of user activity is not described.

[0012] The disadvantages of all the above-mentioned inventions are insufficient measurement accuracy or the impossibility of making the device compact enough to make it wearable. The essence of the invention

[0013] The objective of the present invention is to create a wearable compact device capable of recording the user's physiological indicators with high accuracy and transmitting these data wirelessly. The specific physiological indicators read by the device are at least EDA, ECG or plethysmogram and changes in body position, on the basis of which the user's psycho-emotional state can be assessed.

[0014] This task is solved by achieving a technical result by the present invention, consisting in expanding the capabilities of the device for monitoring the user's condition indicators. The expansion of capabilities is ensured by using several sensors of the user's physiological indicators at the same time, the data of which are analyzed and corrected, which allows assessing the user's condition even during periods of activity, as well as by using compact and energy-efficient sensors and other parts of the device, allowing the device to be made wearable.

[0015] According to one aspect of the invention, a wearable device for monitoring the user's condition is proposed, comprising a microcontroller, a photoplethysmogram sensor, an accelerometer, a skin electrical activity sensor, an analytical unit configured to generate data on assessing the user's condition based on signals from said sensors, wherein the analytical unit is configured to perform a preliminary analysis of data from the accelerometer and the photoplethysmogram sensor to determine the periods and levels of physical activity of the user when generating data on assessing the psycho-emotional state of the user, which makes it possible to increase the accuracy of determining not only the periods of physical activity and data on heart rate variability, but also the generated assessment data, which directly affects the achievement of the set technical result.

[0016] The device may additionally contain a muscle activity sensor, a light sensor, a temperature sensor, a humidity sensor, a sound recording device, and the analytical unit is designed with the ability to take into account data from the said sensors to adjust the results of the assessment of the psycho-emotional state.

[0017] These and other aspects of the invention will be understood and explained with reference to the embodiments of the invention described further in this application. Description of drawings

[0018] The subject matter of the present application is described in paragraphs and clearly stated in the claims. The above-mentioned objectives, features and advantages of the invention are apparent from the following detailed description, taken in conjunction with the accompanying drawings, which show:

[0019] Fig. 1 shows a schematic diagram of the implementation of a device for monitoring the psycho-emotional state of a user, according to the present invention.

[0020] Fig. 2 shows a schematic diagram of the implementation of a device for monitoring the psycho-emotional state of a user using a temperature sensor and a muscle activity sensor, according to the present invention.

[0021] Fig. 3 shows an embodiment of an EDA sensor with two electrodes based on reading the charge time formed by the electrodes, according to the present invention.

[0022] Fig. 4 shows an embodiment of an EDA sensor with two electrodes based on reading the average discharge current of the electrodes, according to the present invention.

[0023] Fig. 5 shows a variant of the implementation of interdigital electrodes.

[0024] Fig. 6 shows a functional diagram of a device with wireless data transmission according to the present invention.

[0025] Fig. 7 shows an example of the calculated acceleration data plotted against time, obtained over a thirty minute period, based on accelerometer data.

[0026] Fig. 8 shows an example of device data plotted as a function of time over a thirty minute period, including an EDA sensor, a photoplethysmogram sensor, and an accelerometer.

[0027] The specified drawings are explained by the following positions: Microcontroller (MCU) - 1; Photoplethysmogram Sensor (PPG Sensor) - 2; Accelerometer (MT) - 3; EDA Sensor - 4; Battery - 5; Memory Device - 6; Charging Circuit - 7; Temperature Sensor - 8; Muscle Activity Sensor - 9; Harness - 10; Electrode - I; Amplifier - 12; Filter - 13; Mobile Application - 14; Analytical Unit - 15; Stress Level - 16. Detailed description of the invention

[0028] In the following detailed description of the embodiment of the invention, numerous implementation details are provided in order to provide a clear understanding of the present invention. However, it will be obvious to one skilled in the art how the present invention can be used with or without these implementation details. In other instances, well-known methods, procedures, and components have not been described in detail in order not to unnecessarily obscure the features of the present invention.

[0029] In addition, it is clear from the above presentation that the invention is not limited to the given implementation. Numerous possible modifications, changes, variations and replacements, preserving the essence and form of the present invention, are obvious to specialists skilled in the subject area.

[0030] From here on, the term “sensor” refers to a set of sensors (devices for reading data from a person) and components that convert data from the sensors.

[0031] Ensuring an adequate response to stress is the basis for maintaining homeostasis in the human body. The main regulatory systems involved in the formation of the stress response are the hypothalamic-pituitary-adrenal axis (HPA), the autonomic nervous system (ANS), and the central nervous system (CNS). Heart rate (HR) and rhythm are largely under the control of the ANS, although the heart muscle also has the ability to independently control its contractions - automatism. HR is controlled by the combined balanced influence of the sympathetic (SNS) and parasympathetic (PNS) nervous systems. The parasympathetic effect on HR is mediated by the release of acetylcholine from the vagus nerve. Muscarinic acetylcholine receptors respond to this release by increasing the permeability of the cell membrane for the K+ ion. The sympathetic effect on heart rate is mediated by the release of adrenaline and noradrenaline.Beta-adrenergic receptors are activated by the release of these hormones, resulting in cAMP-mediated phosphorylation of membrane proteins. An increase in SNS activity or a decrease in PNS activity leads to an increase in HR, whereas a decrease in SNS activity or an increase in PNS activity causes a decrease in HR. The SNS primarily acts on the ventricular muscles of the heart and increases their contractility. In addition, the SNS increases the excitation rate, the conduction velocity of excitation, and the excitability of the sinoatrial (SA) node. With maximum stimulation of the SNS, the HR and contractility can triple and double, respectively. The PNS primarily acts on the sinoatrial and atrioventricular (AV) nodes, decreasing HR. Vagal and sympathetic activity are in constant interaction. Autonomic activity modulates HR, so the degree of HR variability provides information about the state and functioning of nervous regulation and the ability of the heart to respond to these stimuli.Since the heart is not a metronome and its beats are irregular, heart rate variability (HRV) is normal and expected. In addition, HRV indicates the heart's ability to respond to multiple events occurring. with the body (e.g. breathing, exercise, mental stress, hemodynamic and metabolic changes, sleep and orthostatism) and compensate for them.

[0032] Thus, heart rate variability (HRV) can be used as a valuable tool to measure the sympathetic and parasympathetic activity of the ANS, which in turn is directly involved in the formation of the stress response.

[0033] Within the framework of the proposed device, HRV data can be obtained from an ECG or plethysmogram, in particular, by calculating the intervals between the P-P peaks.

[0034] In this case, according to the proposed invention, it is also implied that the accelerometer readings located in the proposed device are taken into account, which allows not only to increase the accuracy of determining heartbeats, but also to determine periods of physical activity and, in turn, to make the determination of the emotional state more accurate due to the ability to take into account the specified data. In addition, based on the accelerometer readings, it is possible to determine a change in the nature of movements, in particular, to recognize changes that, in combination with the readings of the electrodermal activity sensor and ECG data, with a high probability indicate repetitive movements characteristic of a feeling of anxiety, or a decrease in activity associated with fatigue and apathy, which directly affects the achievement of the specified technical result.

[0035] To implement monitoring, the device can be made in the form of a variety of wearable accessories or clothing items, for example, in the form of a bracelet, ring, patch, device integrated into clothing or shoes, and other similar elements.

[0036] According to a preferred embodiment, the proposed device is a wearable device consisting of an electronics unit and a sensor unit. The electronics unit includes a processor, a power source capable of being recharged, antennas and their strapping, a memory device, a wireless communication device, and others, not limited to the named components.

[0037] The sensor unit contains at least one EDA sensor, a photoplethysmogram sensor, an accelerometer, and also, according to some embodiments, at least some of the following components: a temperature sensor, a muscle activity sensor (electromyograph), sound recording devices, light sensors: a UVA / UVB, RGB-IR and other light spectrum sensor, an ambient temperature sensor, a humidity sensor and others.

[0038] According to one of the variants of the minimal implementation of the proposed wearable device for monitoring the psycho-emotional state of the user, the device contains a photoplethysmogram sensor, an accelerometer and an EDA sensor.

[0039] Fig. 1 shows a block diagram of one embodiment of the device, including a minimum configuration. According to this embodiment, the device contains a photoplethysmogram sensor, an accelerometer, an EDA sensor, a microcontroller and an analytical unit. Fig. 1 also shows such elements as a battery, a memory device and a charging circuit - a specialist in the field of technology will understand that these elements are not the subject of the present invention and can be implemented in various ways without significantly affecting the solution of the above problems. For a certain specified period of time, the microcontroller reads data from the photoplethysmogram sensor, accelerometer and EDA sensor in the device, after which they are sent to the analytical unit, where they are pre-processed, which depends on the user's movement.According to the most general variant, the more active the user's movement is registered, the more powerful processing is required to obtain data on the user's psycho-emotional state based on the specified data from the device components. If the user moves actively, the sensor readings become noisier, and in this case, more resource-intensive processing methods are required, for example, using the Hampel filter. Then the signal is processed in time and the user's psycho-emotional state indicators are determined, for example, the stress level, such implementation directly affects the achievement of the set technical result. It should be noted here that structurally the analytical unit can be located both in the device body and be distributed, that is, have some remote computing power, the connection with which can be carried out wirelessly.According to some embodiments, the invention can also be used in conjunction with a third-party mobile application - that is, data from the analytical unit can also be sent to some remote device on which such an application is installed, which is capable of receiving data from the analytical unit.

[0040] Fig. 2 shows a diagram of an embodiment that additionally contains a temperature sensor and a muscle activity sensor. Although, due to the presence of additional sensors, this embodiment may have higher power consumption and larger dimensions compared to the minimum configuration described above, on the other hand, additional sensors allow for better filter the output data from the influence of the ambient temperature and muscle activity, which make it difficult to obtain objective data indicating the psycho-emotional state of the user and act as a source of noise when reading data. When the device is operating, according to this embodiment, data from the temperature sensor, the environment and the muscle activity sensor (myogram) are taken into account by the analytical unit at least at the pre-processing stage, as a result of which it is possible to compensate for distortions and noise introduced by temperature and movement, which also improves the technical result.

[0041] One of the embodiments of the EDA sensor shown in Fig. 3 is based on reading the charging time of the capacitor formed by the electrodes using a strapping that limits the charging current; a two-electrode sensor is used for this embodiment. To read the data, the sensor must be charged to a voltage level set in the microcontroller. In the microcontroller, in turn, there is a comparator that creates a software interrupt when the level is exceeded. Reading the data essentially consists of reading the charging time of the formed capacitor from 0 to a certain level. In this embodiment of the EDA sensor, the strapping consists of 1 element on the board, which makes this circuit relatively simple to implement. However, if charging occurs with low currents, noise induced currents can have a significant effect on the measuring signal - in this case, it is advisable to additionally provide shielding means in the device.

[0042] If the capacitance of the above-described sensor is small (on the order of pF units) and / or the capacitor formed in the device is charged with small currents, the sensor proposed above has a low reading resolution. The microcontroller has a timer time unit that is large enough for the method based on measuring the charge rate, so a resistor (strapping) is used to reduce the capacitor charge rate in this embodiment. In general, the greater the resistor resistance, the slower the capacitor is charged, and at the same time, the greater the influence of noise will be on the measuring signal according to this embodiment.

[0043] The second embodiment of the EDA sensor, shown in Fig. 4, is based on reading the average discharge current of the capacitor. For this purpose, a rectangular signal is fed to the sensor, limited in current by means of a strapping; during the positive edge of the signal, the capacitor is charged, then at a low the capacitor discharges at the front. During the discharge, the discharge current is averaged, amplified and transformed into voltage by an amplifier, after which the signal is filtered and fed to the ADC of the microcontroller.

[0044] There are also single-electrode contactless sensors, contact sensors, including galvanic skin sensors, and others that can read and transmit information on electrodermal activity. For example, there are contact sensors that, based on data on changes in the specific resistance or conductivity of the surface layer of the skin, determine quantitative characteristics of sweating in the area of ​​the sensor location. Contactless sensors that measure changes in electrode potentials are also known. The present invention is not limited to the given examples of implementation of electrodermal activity sensors and may include other embodiments of them, according to this field of technology and the use of which in the present invention is obvious to specialists.However, it is necessary to take into account the weight, dimensions and power consumption of such EDA sensors, in order to be able to make the device wearable, and also that in the case of using contact EDA sensors, it is necessary to ensure contact between the wearable device and the user's body.

[0045] In terms of achieving greater sensor responsiveness to changes in EDA readings (small changes), it is preferable to use two electrodes. In this case, the interdigital electrode shape is also preferable (one of the possible embodiments of this type of electrode is shown in Fig. 5), since such electrodes provide uniform electromagnetic field strength at some distance from the electrodes even in the presence of profuse sweating that has reached the electrode, whereas when using other types of electrodes, there is a higher probability of uneven and strong penetration of the electromagnetic field deep into the skin, which also affects the technical result. Sweating affects the capacity of the capacitor due to the fact that it changes the electrical permeability of the skin.

[0046] According to one embodiment, the device can be presented in the form of a bracelet attached to the user's wrist and containing an electronics unit (processor, charger, antenna and their harness) and a sensor unit, an EDA sensor (examples of which are given above), a photoplethysmogram sensor and an accelerometer. The proposed wearable device provides wireless data transmission, for example, in this embodiment it is implemented using the BLE (Bluetooth Low Energy) protocol (the functional diagram is shown in Fig. 6).

[0047] According to some embodiments, the ability to transmit physiological indicators of the user, such as EDA, plethysmogram and accelerometer data, to a mobile application is provided, after which this data is processed and the results are displayed to the user in real time through the mobile application.According to this embodiment, the full cycle of operation of the proposed device includes the following stages: data from the sensors arrive at the microcontroller, and are then sent wirelessly to the mobile application; data is sent from the mobile application to the analytical unit (which, according to various embodiments, can be located either directly near the housing with the sensors or on a remote server); in the analytical unit, pre-processing and processing of the available data is performed with the determination of the assessment of the psycho-emotional state of the user (according to some embodiments, this is, for example, the stress level on a certain universal scale (for example, low-medium-high), which can be adjusted during the use of the device by one user to his stress levels); then the resulting assessment is sent to the user on the mobile application.

[0048] It should be noted that the term “mobile application” used here means some means of displaying or indicating the assessment of the user’s psycho-emotional state and can be implemented as a program on a mobile device, computer or other device capable of receiving and displaying data from a device for assessing the user’s psycho-emotional state, and is obvious to specialists in this field of technology.

[0049] The first step in data analysis according to one of the preferred embodiments is pre-processing, which plays an important role in the analysis and modeling of biomarkers associated with psycho-emotional stress and includes a number of steps, such as:

[0050] Downsampling to match timestamps in data with different sampling rates;

[0051] Random sample reduction or sample drop for unbalanced samples (where non-stressed samples outnumber stressed ones);

[0052] Standardization and normalization;

[0053] Cleaning data from outliers and anomalies.

[0054] The process of feature engineering involves extracting useful information from raw data that can be used as input features for analytical and machine learning models (Feature extraction). For example, in In some embodiments, the EDA data are decomposed into phase and tonic components using a convex optimization approach with sliding windows in the range from 10 to 20 minutes. In another embodiment, the HRV calculated from the P-P intervals of the photoplethysmogram is additionally used to calculate the parameters of the time (such as SDNN, RMS-SD) and frequency (Total Power, Low / High Frequency) analysis of the BCP. According to another embodiment, for the accelerometer data, the vector of averaged accelerations within the observed time window or the deviation of the acceleration vectors relative to each other is additionally calculated.

[0055] The Machine Learning model or analytical model accepts the processed and selected features from the previous stages as input. The result of the work is a classification of psycho-emotional stress based on physiological parameters (Arousal Detection). An important part of solving the problem of determining and predicting the psycho-emotional state, as well as high-quality training of the model (in implementation options where it is used) is the collection of relevant data, as well as their labeling. Data sets can be labeled using at least one of the following methods:

[0056] By periodically labeling specific frames as stressful or non-stressful while the subject was in the corresponding state (e.g. relaxation, physiological stress, emotional stress, relaxation);

[0057] By completing a self-assessment questionnaire by the user;

[0058] Through observer assessment of stress level and / or emotional state during the data collection period.

[0059] The listed methods can be used both in binary (presence / absence of stress) or multi-class classification problems (e.g., emotion classification), and in regression problems (e.g., determining the stress level on a given scale).

[0060] Also often of great importance is the general level of anxiety and tension at the start of the experiment (data collection), for the assessment of which various methods can be used, such as the Spielberger-Khanin diagnostics or the determination of an individual minute.

[0061] The following is an example of processing a set of data from a device that includes an electrodermal activity sensor, a photoplethysmogram sensor, and an accelerometer, received over a 30-minute period of time with the following sequence of user activity:

[0062] First 6 minutes of slow walking (2 minutes of slow walking + 2 minutes with the Stroop test + 2 minutes of slow walking);

[0063] Then 5 minutes in a calm state;

[0064] Then 6 minutes of fast walking (2 minutes of fast walking + 2 minutes with the Stroop test + 2 minutes of fast walking);

[0065] Then again 5 minutes in a calm state;

[0066] Then 6 minutes standing (2 minutes standing + 2 minutes with Stroop test + 2 minutes standing);

[0067] And then 2 minutes in a calm state.

[0068] According to one of the preferred embodiments of the invention, the first stage of working with data will be their preliminary processing (Pre-processing). In the basic version of the implementation of this stage, it includes cleaning from noise, emissions and anomalies.

[0069] The next, second, stage of data processing by the analytical block is feature extraction. In the example under consideration, at this stage, the acceleration parameters are calculated for the accelerometer data (see Fig. 7); for the PPG data, the following parameters are calculated for each 5-minute window: counting the P-P intervals, then applying the Kalman filter, then obtaining the parameters (see Fig. 8); for the electrodermal activity sensor data, decomposition into phase / frequency components is applied over a 5-minute window to obtain a (p^) graph (see Fig. 8).

[0070] Then, at the third stage, the Motion Detection stage, the Motion Indication indicator is calculated - / D вижение ( см Fig. 8) based on the obtained acceleration parameters a к. If periods of physical activity are detected, it is necessary to perform calculations at the first stage again for the photoplethysmogram and electrodermal activity sensor data at time intervals corresponding to the activity periods, using more powerful data filtering algorithms (this allows minimizing the error in calculating features at the second stage), after which the calculation of features at the second stage is repeated and proceed to the third stage.

[0071] After carrying out the above processing according to the considered embodiment, proceed to the stage of determining the level of emotional arousal (Arousal Detection). Next, select the threshold value t, based on the classification based on the machine learning model or analytical model, the excess of which graphs indicate emotional arousal, and as a result we get the graph Fig. 8.

[0072] The reference signs enclosed in brackets and used in the present description and claims shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps other than those listed in the claim. The singular element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several individual elements and / or by means of a suitably programmed processor. In a claim listing several devices, some of these devices may be implemented by the same piece of equipment.The measures set forth in dependent claims that differ from one another may be advantageously used in combination, whereby a person skilled in the art will understand that the principle underlying the achievement of the claimed technical advantages and the solution of the technical difficulties mentioned herein remains relevant when combining the technical features of the claimed invention disclosed in the present description.

[0073] Thus, the mentioned elements directly influence the technical result, which consists in expanding the capabilities of the device for monitoring the psycho-emotional state of the user.

[0074] The present application materials present a preferred disclosure of the implementation of the claimed technical solution, which should not be used as limiting other, particular embodiments of its implementation that do not go beyond the requested scope of legal protection and are obvious to specialists in the relevant field of technology.

Claims

Invention formula 1. A wearable device for monitoring data indicating the psycho-emotional state of the user, including - photoplethysmogram sensor; - microcontroller; - accelerometer; - electrodermal activity (EDA) sensor; - an analytical unit capable of generating data for assessing the psycho-emotional state of the user based on signals from said sensors; wherein the analytical unit is capable of performing a preliminary analysis of data from the accelerometer and photoplethysmogram sensor, ensuring the determination of periods and levels of physical activity of the user during said generation of data for assessing the psycho-emotional state of the user.

2. A wearable device for monitoring data indicating the psycho-emotional state of a user, according to claim 1, characterized in that it contains at least one of the following sensors: an ECG, a muscle activity sensor, a light sensor, a temperature sensor, a humidity sensor, a sound recording device, and the analytical unit is configured to take into account the data obtained from said sensors during said preliminary analysis.

3. A wearable device for monitoring data indicating the psycho-emotional state of the user, according to paragraph 1, characterized in that the analytical unit is designed with the possibility of being located separately from the wearable device, and the analytical unit is designed with the possibility of providing communication with the wearable device wirelessly.

4. A wearable device for monitoring data indicating the psycho-emotional state of a user, according to claim 1, characterized in that the analytical unit is configured to perform at least one of the following: downsampling to ensure that the time stamps of the data match, randomly reducing or discarding samples for unbalanced samples, cleaning the data from outliers and anomalies.

5. A wearable device for monitoring data indicating the psycho-emotional state of the user, according to paragraph 1, characterized in that the analytical unit is configured to perform feature development, including at least the following: - decomposition into phase and tonic components using a convex optimization approach with sliding windows in the range from 10 to 20 minutes for electrodermal activity sensor data; - calculation of heart rate variability (HRV) based on P-P intervals of the photoplethysmogram and its use to calculate the parameters of time and frequency analysis of HRV; - calculation of the vector of average accelerations within the observed time window or the deviation of acceleration vectors from each other.

6. A wearable device for monitoring data indicating the psycho-emotional state of the user, according to paragraph 1, characterized in that the analytical unit contains a model trained on relevant labeled data.

7. A wearable device for monitoring data indicating the psycho-emotional state of the user, according to paragraph 1, characterized in that the EDA sensor is a two-electrode device, and the electrodes are of the interdigital type.

8. A wearable device for monitoring data indicating the psycho-emotional state of the user, according to paragraph 1, characterized in that during said preliminary analysis of data, the analytical unit is provided with down-sampling of the received signals.

9. A wearable device for monitoring data indicating the psycho-emotional state of the user, according to paragraph 1, characterized in that it contains a data transmission module.

10. A method for analyzing, processing and adjusting data received from a device for monitoring the psycho-emotional state of a user, in which: preliminary data processing (Pre-processing) is carried out using an analytical unit; - carry out the extraction of useful information from raw data (Feature extraction) using an analytical block; - determine periods of user movement (Motion Detection) using an analytical unit; - during periods of user movement, preliminary processing is repeated with more powerful data filtering algorithms using the analytical block; - re-extract useful information from raw data during periods of user movement using an analytical unit; - transfer the extracted information to a machine learning model or an analytical model using an analytical block; - classify the psycho-emotional state based on the extracted information using a machine learning model or an analytical model (Arousal Detection); - receive a graph of the user's psycho-emotional state.

11. A method for analyzing, processing and adjusting data received from a device for monitoring the psycho-emotional state of a user, according to item 10, characterized in that at the stage of preliminary data processing at least one of the following is performed: - downsampling while ensuring the coincidence of data time stamps; - random reduction or discard of samples for unbalanced samples; - cleaning data from outliers and anomalies.

12. A method for analyzing, processing and adjusting data received from a device for monitoring the psycho-emotional state of a user, according to clause 10, characterized in that at the stage of extracting useful information, features are developed that include at least the following: - decomposition into phase and tonic components using a convex optimization approach with sliding windows in the range from 10 to 20 minutes for electrodermal activity sensor data; - calculation of heart rate variability (HRV) based on P-P intervals of the photoplethysmogram and its use to calculate the parameters of time and frequency analysis of HRV; - calculation of the vector of average accelerations within the observed time window or the deviation of acceleration vectors from each other.

13. A method for analyzing, processing, and adjusting data obtained from a device for monitoring the psycho-emotional state of a user, according to claim 10, characterized in that the Hampel filter method is used for preliminary processing with more powerful data filtering algorithms.

14. A method for analyzing, processing, and adjusting data received from a device for monitoring the psycho-emotional state of a user, according to claim 10, characterized in that a graph of the user's psycho-emotional state is additionally transmitted to a mobile application using a data transmission module.

15. A method for analyzing, processing and adjusting data received from a device for monitoring the psycho-emotional state of a user, according to item 10, characterized in that, that in order to classify the user's psycho-emotional state, the collection and labeling of relevant data is performed.

16. A method for analyzing, processing, and adjusting data received from a device for monitoring the psycho-emotional state of a user, according to paragraph 15, characterized in that at least one of the following methods is used to mark up the relevant data: - periodic marking; - completion of a self-assessment questionnaire by the user; - observer's assessment of stress level and / or emotional state during the data collection period.

17. A method for analyzing, processing and adjusting data received from a device for monitoring the psycho-emotional state of a user, according to paragraph 15, characterized in that the general level of anxiety and tension at the time of the start of the experiment (data collection) is additionally determined by at least one of the methods: - Spielberger-Khanin diagnostic method; - by the method of determining the individual minute.

Images