CN117045253A - AI psychological consultation method and system - Google Patents
AI psychological consultation method and system Download PDFInfo
- Publication number
- CN117045253A CN117045253A CN202311115827.2A CN202311115827A CN117045253A CN 117045253 A CN117045253 A CN 117045253A CN 202311115827 A CN202311115827 A CN 202311115827A CN 117045253 A CN117045253 A CN 117045253A
- Authority
- CN
- China
- Prior art keywords
- user
- text information
- state
- heart rate
- consultation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000008451 emotion Effects 0.000 claims abstract description 52
- 238000003058 natural language processing Methods 0.000 claims abstract description 49
- 230000002996 emotional effect Effects 0.000 claims description 58
- 239000006185 dispersion Substances 0.000 claims description 24
- 238000002560 therapeutic procedure Methods 0.000 claims description 16
- 208000019901 Anxiety disease Diseases 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 14
- 230000036506 anxiety Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 12
- 238000009225 cognitive behavioral therapy Methods 0.000 claims description 6
- 230000001788 irregular Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013542 behavioral therapy Methods 0.000 claims description 2
- 230000001149 cognitive effect Effects 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 claims 1
- 201000010099 disease Diseases 0.000 description 7
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 230000008909 emotion recognition Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000001020 rhythmical effect Effects 0.000 description 3
- 206010027940 Mood altered Diseases 0.000 description 2
- 208000013738 Sleep Initiation and Maintenance disease Diseases 0.000 description 2
- 210000003403 autonomic nervous system Anatomy 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 206010022437 insomnia Diseases 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 210000002820 sympathetic nervous system Anatomy 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000018522 Gastrointestinal disease Diseases 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013019 agitation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007510 mood change Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 210000005037 parasympathetic nerve Anatomy 0.000 description 1
- 210000001002 parasympathetic nervous system Anatomy 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002889 sympathetic effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
Abstract
The application provides an AI psychological consultation method and system, comprising the steps of acquiring physiological signals and voice signals of a user through wearing equipment, wherein a voice recognition module and a sensor for collecting human physiological signals are arranged on the wearing equipment, the physiological signals are converted into state text information corresponding to the emotion states of the user according to the corresponding relation between the physiological signals and the emotion states, the voice signals of the user are converted into voice text information, and an AI consultation mode matched with the emotion states of the user is selected by a natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user; according to the method, the emotion signs of the user are obtained in real time through the intelligent wearable equipment, and the psychological consultation is carried out on the user by combining the emotion signs of the user and the AI consultation mode matched with the emotion state of the user through voice information selection, so that the accuracy and the effectiveness of the psychological consultation can be improved.
Description
Technical Field
The application relates to the technical field of AI, in particular to an AI psychological consultation method and system.
Background
At present, psychological diseases are increasingly prominent, physiological diseases and psychological diseases are mutually influenced, the psychological diseases can cause a plurality of physiological diseases, such as anxiety, depression and other bad moods can cause gastrointestinal disturbance, insomnia and the like, and the physiological diseases can also cause psychological diseases, such as insomnia can aggravate depression and anxiety.
When people encounter some psychological problems, they do not seek the help of psychological doctors or psychological consultants immediately, and there are general situations that are bad or worry about revealing individual privacy without seeking psychological assistance. With the increase of demands, some AI psychological consultation robots can interact with people in some voice to help adjust the emotion of people, but the accuracy of the AI psychological consultation robots is still to be improved.
Disclosure of Invention
The application provides an AI psychological consultation method and system, which aim to conduct more accurate psychological dispersion on a user and help the user to walk out of psychological trouble.
In one aspect, the present application provides an AI psychological consulting method, including:
the method comprises the steps that physiological signals and voice signals of a user are obtained through wearing equipment, and a voice collector and a sensor for collecting physiological signals of a human body are arranged on the wearing equipment;
converting the physiological signals into state text information corresponding to the emotional state of the user according to the corresponding relation between the physiological signals and the emotional state;
converting the voice signal of the user into voice text information;
and selecting an AI consultation mode matched with the emotion state of the user by the natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user.
In one embodiment, the wearable device is provided with a heart rate sensor, an acceleration sensor and a skin electric sensor, wherein the heart rate sensor is used for detecting heart rate and heart rate variability of a user, the acceleration sensor is used for detecting limb movement changes of the user, and the skin electric sensor is used for detecting skin electric signals of the user; before the physiological signal is converted into the state text information corresponding to the emotional state of the user according to the corresponding relation between the physiological signal and the emotional state, the method further comprises the following steps:
and comprehensively judging the emotional state of the user according to the heart rate, heart rate variability, limb movement variation and skin electric signals of the user.
In one embodiment, the comprehensively judging the emotional state of the user according to the heart rate, the heart rate variability, the limb movement variation and the skin electric signal of the user includes:
if the heart rate of the user is stable, the heart rate variability is normal, the skin electric signal is normal, the moving steps are stable and regular, and the user is judged to be in a calm emotion state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and regular, and the user is judged to be in an anxiety emotional state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and irregular, and the user is judged to be in a fear or panic emotional state;
if the heart rate of the user becomes smaller, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the number of moving steps is reduced, and the user is judged to be in a sad emotion state.
In one embodiment, before the converting the physiological signal into the state text information corresponding to the emotional state of the user according to the correspondence between the physiological signal and the emotional state, the method further includes:
and the cloud server receives the physiological signals and the voice signals of the user sent by the wearable equipment.
In one embodiment, the selecting, by the natural language processing model, the AI consultation mode matching the emotional state of the user according to the state text information and the voice text information, and performing psychological consultation on the user includes:
if the natural language processing model receives that the state text information of the user is anxiety or fear, an AI cognitive behavior therapy module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives that the state text information of the user is anger, an AI psychodynamic therapy module is adopted to psychologically dredge the user based on the voice text information of the user acquired in real time;
if the natural language processing model receives the state text information of the user as sadness, an AI humanization therapy module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives the state text information of the user as calm, the AI solution direction short-term treatment method module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time.
In one embodiment, the selecting, by the natural language processing model, the AI consultation mode matching the emotional state of the user according to the state text information and the voice text information to perform psychological consultation on the user further includes:
if the emotion state of the user changes in the consultation process, the natural language processing model adjusts the AI consultation mode according to the emotion state change of the user.
In one embodiment, if the emotional state of the user changes during the consultation, adjusting the AI consultation mode of the user includes:
if the state text information of the user is changed from calm to sadness, continuously based on the voice text information of the user obtained in real time, converting the AI consultation mode from an AI solution direction short-term treatment method module to an AI humanism treatment method module, and performing psychological dispersion on the user;
if the state text information of the user is converted from sadness to anger, continuously converting the AI consultation mode from the AI personage treatment therapy module to the AI psychodynamic treatment method module based on the voice text information of the user obtained in real time, and performing psychological dispersion on the user;
if the state text information of the user is converted from anger to fear, continuously converting the AI consultation mode from the AI psychodynamic therapy module to the AI cognitive behavioral therapy module based on the voice text information of the user acquired in real time, and conducting psychological dispersion on the user.
On the other hand, the application provides an AI psychological consultation system, which comprises a wearable device, wherein the wearable device is provided with a voice collector, a sensor for collecting physiological signals of a human body, a cloud server and a cloud server, the voice collector is used for collecting physiological signals and voice signals of a user, the wearable device is in wireless connection with the cloud server, and the cloud server is used for:
converting the physiological signals into state text information corresponding to the emotional state of the user according to the corresponding relation between the physiological signals and the emotional state;
converting the voice signal of the user into voice text information;
and selecting an AI consultation mode matched with the emotion state of the user by the natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user.
In one embodiment, the wearable device further includes a display interface for displaying feedback information and a man-machine interaction operation menu in the AI psychological consultation process.
In one embodiment, the wearable device is provided with a heart rate sensor, an acceleration sensor and a skin electric sensor, wherein the heart rate sensor is used for detecting heart rate and heart rate variability of a user, the acceleration sensor is used for detecting limb movement changes of the user, and the skin electric sensor is used for detecting skin electric signals of the user; the cloud server stores a computer program, and the computer program is further configured to execute the method of any one of the above when running.
The application relates to an AI psychological consultation method and system, comprising the steps of acquiring physiological signals and voice signals of a user through wearing equipment, wherein a voice recognition module and a sensor for collecting human physiological signals are arranged on the wearing equipment, the physiological signals are converted into state text information corresponding to the emotion states of the user according to the corresponding relation between the physiological signals and the emotion states, the voice signals of the user are converted into voice text information, and an AI consultation mode matched with the emotion states of the user is selected by a natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user; according to the method, the emotion signs of the user are obtained in real time through the intelligent wearable equipment, and the psychological consultation is carried out on the user by combining the emotion signs of the user and the AI consultation mode matched with the emotion state of the user through voice information selection, so that the accuracy and the effectiveness of the psychological consultation can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required in the embodiments are briefly described below, and the drawings in the following description are only drawings corresponding to some embodiments of the present application, and it is possible for a person skilled in the art to obtain drawings of other embodiments according to these drawings without inventive effort.
FIG. 1 is a flow chart of an AI psychological consulting method according to one embodiment of the application;
FIG. 2 is a flow chart showing a method of AI psychological consultation according to another embodiment of the present application;
FIG. 3 is a diagram showing a variation of AI psychological consultation modes according to an embodiment of the present application;
FIG. 4 is a block diagram showing the structure of an AI psychological consulting system in one embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
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.
Referring to fig. 1, an AI psychological consulting method of the present application, in one embodiment, includes:
step S101, physiological signals and voice signals of a user are obtained through a wearable device, and a voice collector and a sensor for collecting physiological signals of a human body are arranged on the wearable device.
Specifically, the wearable device may be a smart bracelet, a smart watch, a smart eye shield, or other wearable device.
In one embodiment, the wearable device is provided with a heart rate sensor, an acceleration sensor and a skin electric sensor, wherein the heart rate sensor is used for detecting heart rate and heart rate variability of a user, the acceleration sensor is used for detecting limb movement variation of the user, and the skin electric sensor is used for detecting skin electric signals of the user.
Step S102, converting the physiological signals into state text information corresponding to the emotional states of the user according to the corresponding relation between the physiological signals and the emotional states.
The human body has corresponding reactions in different emotional states, and the emotional states of the human body can be judged by collecting physiological signals of the human body and identifying the reactions.
Wherein, the heart rate rise generally represents the emotional change toward the excited and strong direction, and the heart rate fall generally represents the emotional change toward the flat and relaxed direction. In relaxed and calm states, heart rate variability is generally high, indicating that the autonomic nervous system is more flexible and adaptable in this state, and the balance of sympathetic and parasympathetic nerves is relatively good. While heart rate variability tends to decrease under stress and stress conditions, indicating increased activity in the sympathetic nervous system and decreased activity in the parasympathetic nervous system, resulting in an imbalance in the autonomic nervous system.
The acceleration sensor can collect the change degree of limbs, is a language of the limbs, rapidly walks back and forth in rhythms and is an anxiety expression; rapid rhythmic back and forth ambulation is a panic manifestation; severe swing of the extremities is an angry manifestation.
Galvanic skin is a physiological indicator that measures the conductivity of skin, also known as conductivity or resistance. It reflects the electrical conductivity of the skin surface, an indicator that is usually associated with mood changes. Upon emotional activation, the activity of the sympathetic nervous system increases, resulting in an increase in skin conductance, which is often associated with emotional agitation (e.g., excitement, anger, or fear), whereas when tension or anxiety is felt, the galvanic skin activity may become more unstable.
The emotional state of the user can be accurately identified by comprehensively judging the emotional state of the user according to the heart rate, heart rate variability, limb movement variation and skin electric signals of the user.
Step S103, converting the voice signal of the user into voice text information.
And step S104, selecting an AI consultation mode matched with the emotion state of the user by the natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user.
The emotional state of the user is converted into text information, the text information and the text information of the voice signals are input into a natural language model, and the natural language model selects an AI consultation mode matched with the emotional state of the user according to the emotional state of the user and the voice information of the user to carry out psychological consultation on the user. The method of the embodiment can select the AI consultation mode suitable for the emotion state of the user at the moment to psychologically dredge the user on the basis of knowing the emotion state of the user, and can improve the accuracy and effect of psychological consultation.
Among them, the field of natural language processing models has a wide range of applications, which mimics the language capabilities of humans and exhibits very excellent performance in many tasks. After the pre-training is completed, the natural language processing model may be used for various NLP tasks (Natural Language Processing ) for generating natural dialogs, chat, or questions and answers. According to the natural language processing model, model training is carried out based on the state text information and the voice text information of the user, and a knowledge base is constructed, so that personalized psychological consultation and advice are provided for the user, the accurate grasp of psychological and emotional changes of the user is improved, the psychological consultation process is closer to the actual emotion and requirement of the user, and the psychological consultation effectiveness is improved.
Referring to fig. 2, in another embodiment, the AI psychological consultation method includes:
step S201, physiological signals and voice signals of a user are obtained through a wearable device, and a voice recognition module and a sensor for collecting physiological signals of a human body are arranged on the wearable device.
Step S202, a cloud server receives physiological signals and voice signals of a user sent by a wearable device.
Referring to fig. 4, after acquiring the physiological signal and the voice signal of the user, the wearable device sends the physiological signal and the voice signal to the cloud server through the wireless network, and the cloud server receives the physiological signal and the voice signal of the user and performs subsequent signal processing.
Step S203, comprehensively judging the emotion state of the user according to the heart rate, heart rate variability, limb movement variation and skin electric signals of the user.
Specifically, if the heart rate of the user is stable, the heart rate variability is normal, the skin electric signal is normal, the moving steps are stable and regular, and the user is judged to be in a calm emotion state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and regular, and the user is judged to be in an anxiety emotional state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and irregular, and the user is judged to be in a fear or panic emotional state;
if the heart rate of the user becomes smaller, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the number of moving steps is reduced, and the user is judged to be in a sad emotion state.
The emotion state determination method is a preferable real method, and the present embodiment is not limited to this, and if there is better emotion state determination in practical application, it is also within the concept protected by the present embodiment.
Specifically, after the cloud server receives the physiological signal of the user, the calculation and emotion state judgment processes of the physiological parameter of the user are as follows:
in one embodiment, the heart rate sensor can collect pulse waves by adopting an optical sensor and an electrocardio sensor, and analyze the heart rate and the heart rate variability degree. The heart rate and the change trend calculating method thereof comprise the following steps:
1. a time series of output data of the heart rate sensor is acquired and is denoted as { x 1, x 2, x 3, …, x n }, where x i represents the heart rate value at the ith time point.
2. The trend of rising and falling of heart rate is detected using the difference. The difference Deltax [ i ] = x [ i ] -x [ i-1] between heart rate values at adjacent time points is calculated. If Deltax [ i ] > ε (a set threshold), it indicates that the heart rate is rising at the nth time point. A duration limit may be set, i.e. the heart rate continues to rise for a certain period of time to be considered valid.
The difference Deltax [ i ] = x [ i ] -x [ i-1] between heart rate values at adjacent time points is calculated. If Deltax [ i ] < - ε (a set threshold), it indicates that heart rate was decreasing at the nth time point. Also, a duration limit may be set, i.e. the heart rate continuously decreases for a certain time period to be considered valid.
The heart rate variability calculation method comprises the following steps:
1. calculating the difference between adjacent heart rate intervals: Δx [ i ] =x [ i ] -x [ i-1].
2. The sum of squares of the differences is calculated: Σ (Δx [ i ] 2).
3. The square of the average difference is calculated: mean (ΔxI2).
4. Calculating standard deviation: hrv=sqrt (mean (Δx [ i ] 2)).
The HRV value obtained by calculation reflects the variability of heart rate over a period of time. Higher HRV values indicate greater heart rate variability, while lower HRV values indicate less heart rate variability. It should be noted that other methods for calculating heart rate variability may be used, such as frequency domain analysis, time domain analysis, etc. Each method has its characteristics and application range, and the selection of the appropriate method depends on the specific requirements.
Judging the emotion state of the corresponding user:
1. in a relaxed and calm state, heart rate variability is typically high, and the output text "user in relaxed and calm state" is fed back to the natural language processing module.
2. In the stress and stress state, the heart rate variability tends to decrease, and the output text "the user is stressed or in stress state" is fed back to the natural language processing module.
In one embodiment, the acceleration sensor may be a triaxial acceleration sensor, and the method for calculating the trend of the moving steps includes:
1. let the Step number sequence be { Step [1], step [2], step [3], …, step [ k ] }, wherein Step [ k ] represents the number of steps in the kth time period, calculate the average value of the Step number sequence: mean= (Step [1] +step [2] +step [3] + … +step [ n ])/n. n represents the total observed time window number.
2. Calculating the difference between the step number and the average value in each time period in the step number sequence: d, d 1 =Step[1]-mean,d 2 =Step[2]-mean,…,dn=Step[n]-mean。
3. Calculating standard deviation of the difference sequence: std=sqrt ((d) 1 2 +d 2 2 +d 3 2 +…+dn 2 )/n)。
4. Calculating the degree of step number: vm=std/mean.
The higher the degree of dispute, the greater the variability and irregularity of the step sequence, while the lower the degree of dispute, the higher the stability and regularity of the step sequence. It should be noted that, in calculating the degree of step count, the length of the time period may be selected according to the specific situation, for example, every second, every minute, or every hour. Other statistical methods, such as variance, discrete coefficient, etc., can also be used for calculating the degree of dispute, depending on the specific needs and characteristics of the pace rules.
Judging the emotion state of the corresponding user:
mean is greater than a threshold α, VM is less than a threshold β, representing rapid rhythmic back and forth ambulation, which is a manifestation of anxiety, outputting the word "the user is in an emotional state of anxiety" and feeding back to the natural language processing module.
And 2. When mean is larger than a threshold value alpha, VM is larger than a threshold value beta, and the fast and rhythmic walk back and forth is a panic expression, and the text of 'the user is in a panic emotional state' is output and fed back to the natural language processing module.
Abs (mi-1) above a threshold value gamma, represents that severe swing of the extremities is an angry manifestation. abs represents a function that takes absolute value, outputs the word "the user is in an angry emotional state" and feeds back to the natural language processing module.
In one embodiment, a method for calculating a skin electrical signal includes:
let the output data of the skin sensor be a time series, denoted as { SK ] 1 ,SK 2 ,SK 3 …, SKn }, where xi represents the skin electrical value at the i-th time point.
1. Calculating a baseline value: a baseline period of time is selected from the electrodermal sensor data, typically data in a resting state or in a non-stimulated state. The baseline value was calculated as the average or median of the skin electrical values over the period of time and recorded as baseline.
2. Calculating a change value: for each time point the galvanic skin value SKi is calculated as the difference from the baseline value baseline: Δski=ski-baseline. This difference represents the degree of galvanic skin change at the current time point.
3. Optional normalization process: the galvanic skin change values may be normalized, for example by dividing by the baseline value baseline, to obtain the relative rate of change, according to particular needs: relative_change= (Δskip/baseine) ×100.
Judging the emotion state of the corresponding user:
the skin conductivity rises, and the text of 'the user is in a state with large emotion fluctuation' is output and fed back to the natural language processing module.
Step S204, converting the physiological signals into state text information corresponding to the emotional states of the user according to the corresponding relation between the physiological signals and the emotional states.
Step S205, the voice signal of the user is converted into voice text information.
And S206, selecting an AI consultation mode matched with the emotion state of the user by the natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user.
Specifically, referring to fig. 3, if the natural language processing model receives that the state text information of the user is anxiety or fear, the AI cognitive behavioral therapy module is adopted to psychologically dredge the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives that the state text information of the user is anger, an AI psychodynamic therapy module is adopted to psychologically dredge the user based on the voice text information of the user acquired in real time;
if the natural language processing model receives the state text information of the user as sadness, an AI humanization therapy module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives the state text information of the user as calm, the AI solution direction short-term treatment method module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time.
The above consultation mode corresponding to a certain emotional state is a preferred consultation mode, and the present embodiment is not limited thereto, and if a better consultation mode is also included in the practical application, the present embodiment is also within the concept protected by the present embodiment.
In one embodiment, the user is likely to experience emotion change in a complete psychological consultation process, and when the wearable device recognizes that the emotion of the user changes, the natural language model changes the AI consultation strategy to continue psychological mediation for the user, so that the AI psychological consultation is close to the consultation process of the experienced psychological consultant, and the effectiveness of the AI psychological consultation is ensured.
Specifically, if the state text information of the user is converted from calm to sadness, continuously converting the AI consultation mode from an AI solution direction short-term treatment method module to an AI humanization treatment method module based on the real-time acquired voice text information of the user, and performing psychological dispersion on the user;
if the state text information of the user is converted from sadness to anger, continuously converting the AI consultation mode from the AI personage treatment therapy module to the AI psychodynamic treatment method module based on the voice text information of the user obtained in real time, and performing psychological dispersion on the user;
if the state text information of the user is converted from anger to fear, continuously converting the AI consultation mode from the AI psychodynamic therapy module to the AI cognitive behavioral therapy module based on the voice text information of the user acquired in real time, and conducting psychological dispersion on the user.
According to the AI psychological consultation method, physiological signals and voice signals of a user are collected in real time through the wearable device, the cloud server receives the physiological signals and voice signals of the user and then converts the physiological signals and voice signals into state text information and voice text information, the state text information and the voice text information are input into the natural language processing model, the natural language processing model selects an AI consultation mode matched with the emotion state of the user to carry out psychological consultation on the user based on the emotion state of the user, and if the emotion state of the user changes in the consultation process, the AI consultation mode is adjusted to continue carrying out psychological consultation on the user, so that the AI psychological consultation process is attached to the consultation process of an experienced psychological consultation operator, and the effectiveness of the AI psychological consultation is guaranteed.
Referring to fig. 4, the embodiment of the present application further provides an AI psychological consultation system, including a wearable device 10, where the wearable device 10 is provided with a voice collector 11 and a sensor for collecting physiological signals of a human body, and is used for collecting physiological signals and voice signals of a user, and a cloud server 20, where the wearable device 10 and the cloud server 20 are wirelessly connected through a communication module 15, and the cloud server 20 includes:
the emotion recognition module 22 is configured to convert the physiological signal into state text information corresponding to the emotional state of the user according to the corresponding relationship between the physiological signal and the emotional state;
a voice recognition module 21 for converting a voice signal of a user into voice text information;
and the natural voice model 23 is used for selecting an AI consultation mode matched with the emotion state of the user according to the state text information and the voice text information to carry out psychological consultation on the user.
In one embodiment, the wearable device further includes a display interface 16 for displaying feedback information and a man-machine interaction operation menu during AI psychological consultation.
Specifically, the feedback information includes physiological signals of the user detected by the wearable device 10, emotional states of the user fed back to the wearable device 10 by the cloud server 20, real-time dialogue information between the cloud server 20 and the user, and the like. The man-machine interaction operation menu comprises a consultation start menu, a consultation pause menu, a consultation end menu, a text dialog box input menu, a consultation record review menu and the like. The user can conveniently know the psychological condition of the user, choose to receive psychological consultation in a text or voice mode, control the psychological consultation process and the like, and the experience of the user is improved.
In one embodiment, the wearable device 10 further includes a speaker, which is configured to play the consultation information fed back by the cloud server 20 to the user for listening.
In one embodiment, the wearable device 10 is provided with a heart rate sensor 12, an acceleration sensor 13 and a skin electric sensor 14, wherein the heart rate sensor 12 is used for detecting heart rate and heart rate variability of a user, the acceleration sensor 13 is used for detecting limb movement variation of the user, and the skin electric sensor 14 is used for detecting skin electric signals of the user.
The emotion recognition module 22 is specifically configured to comprehensively determine an emotional state of the user according to the heart rate, heart rate variability, limb movement variation and skin electric signals of the user.
Further, the emotion recognition module 22 is configured to determine that the user is in a calm emotion state if the heart rate of the user is stable, the heart rate variability is normal, the skin electrical signal is normal, the limb movement is stable and regular;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and regular, and the user is judged to be in an anxiety emotional state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and irregular, and the user is judged to be in a fear or panic emotional state;
if the heart rate of the user becomes smaller, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the number of moving steps is reduced, and the user is judged to be in a sad emotion state.
In one embodiment, the natural language processing model 23 is specifically configured to, if the natural language processing model receives that the state text information of the user is anxiety or fear, use the AI cognitive behavioral therapy module to psychologically dredge the user based on the speech text information of the user obtained in real time;
if the natural language processing model receives that the state text information of the user is anger, an AI psychodynamic therapy module is adopted to psychologically dredge the user based on the voice text information of the user acquired in real time;
if the natural language processing model receives the state text information of the user as sadness, an AI humanization therapy module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives the state text information of the user as calm, the AI solution direction short-term treatment method module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time.
In one embodiment, the natural language processing model 23 is further configured to:
if the emotion state of the user changes in the consultation process, the natural language processing model adjusts the AI consultation mode according to the emotion state change of the user.
Specifically, the natural language processing model 23 is configured to continuously convert the AI consultation mode from the AI solution short-term treatment method module to the AI humanization treatment module based on the real-time acquired voice text information of the user if the state text information of the user is converted from calm to sad, and perform psychological dispersion on the user;
if the state text information of the user is converted from sadness to anger, continuously converting the AI consultation mode from the AI personage treatment therapy module to the AI psychodynamic treatment method module based on the voice text information of the user obtained in real time, and performing psychological dispersion on the user;
if the state text information of the user is converted from anger to fear, continuously converting the AI consultation mode from the AI psychodynamic therapy module to the AI cognitive behavioral therapy module based on the voice text information of the user acquired in real time, and conducting psychological dispersion on the user.
The AI psychological consultation system of this embodiment gathers physiological signals and voice signals of the user through wearing equipment, and sends to the cloud server through wireless communication module, and the cloud server converts the physiological signals and voice signals of the user into state word information and voice word information after they are converted, and inputs to the natural language processing model, and the natural language processing model selects the AI consultation mode that matches with the emotion state of the user based on the emotion state of the user to carry out psychological consultation on the user. The wearing equipment can be portable equipment commonly used such as watches, is convenient for users to timely accept relatively effective psychological dispersion at any time, relieves the trouble brought by various psychological problems to people, and has positive value and significance for life of people.
In the foregoing embodiments of the present application, it should be understood that the disclosed systems, devices and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium.
Based on such understanding, the technical solution of the present application may be embodied in essence or contributing part or all or part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a mobile terminal, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In summary, although the present application has been described with reference to the preferred embodiments, the scope of the application is not limited thereto, and any person skilled in the art who is skilled in the art should make equivalent substitutions or modifications according to the technical scheme of the present application within the scope of the present application.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
Claims (10)
1. An AI psychological consultation method, characterized by comprising:
the method comprises the steps that physiological signals and voice signals of a user are obtained through wearing equipment, and a voice collector and a sensor for collecting physiological signals of a human body are arranged on the wearing equipment;
converting the physiological signals into state text information corresponding to the emotional state of the user according to the corresponding relation between the physiological signals and the emotional state;
converting the voice signal of the user into voice text information;
and selecting an AI consultation mode matched with the emotion state of the user by the natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user.
2. The AI psychological consultation method according to claim 1, characterized in that the wearable device is provided with a heart rate sensor, an acceleration sensor and a skin electric sensor, wherein the heart rate sensor is used for detecting heart rate and heart rate variability of a user, the acceleration sensor is used for detecting limb movement changes of the user, and the skin electric sensor is used for detecting skin electric signals of the user; before the physiological signal is converted into the state text information corresponding to the emotional state of the user according to the corresponding relation between the physiological signal and the emotional state, the method further comprises the following steps:
and comprehensively judging the emotional state of the user according to the heart rate, heart rate variability, limb movement variation and skin electric signals of the user.
3. The AI psychological consulting method of claim 2, wherein comprehensively determining the emotional state of the user based on the heart rate, heart rate variability, limb movement variation, and skin electrical signals of the user comprises:
if the heart rate of the user is stable, the heart rate variability is normal, the skin electric signal is normal, the moving steps are stable and regular, and the user is judged to be in a calm emotion state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and regular, and the user is judged to be in an anxiety emotional state;
if the heart rate of the user becomes large, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the moving steps are rapid and irregular, and the user is judged to be in a fear or panic emotional state;
if the heart rate of the user becomes smaller, the heart rate variability is reduced, the amplitude of the skin electric signal is increased, the number of moving steps is reduced, and the user is judged to be in a sad emotion state.
4. The AI psychological consulting method of claim 1, further comprising, prior to converting the physiological signal into the state text information corresponding to the emotional state of the user according to the correspondence of the physiological signal to the emotional state:
and the cloud server receives the physiological signals and the voice signals of the user sent by the wearable equipment.
5. The AI psychological consulting method of claim 1, wherein the selecting, by the natural language processing model, an AI consultation mode matching the emotional state of the user based on the state text information and the phonetic text information, comprises:
if the natural language processing model receives that the state text information of the user is anxiety or fear, an AI cognitive behavior therapy module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives that the state text information of the user is anger, an AI psychodynamic therapy module is adopted to psychologically dredge the user based on the voice text information of the user acquired in real time;
if the natural language processing model receives the state text information of the user as sadness, an AI humanization therapy module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time;
if the natural language processing model receives the state text information of the user as calm, the AI solution direction short-term treatment method module is adopted to conduct psychological dispersion on the user based on the voice text information of the user obtained in real time.
6. The AI psychological consultation method of claim 5, wherein the selecting, by the natural language processing model, an AI consultation mode that matches the user's emotional state based on the state literal information and the phonetic literal information, further comprises:
if the emotion state of the user changes in the consultation process, the natural language processing model adjusts the AI consultation mode according to the emotion state change of the user.
7. The AI psychological consulting method of claim 6, wherein if the emotional state of the user changes during the course of the consultation, adjusting the AI consultation mode of the user comprises:
if the state text information of the user is changed from calm to sadness, continuously based on the voice text information of the user obtained in real time, converting the AI consultation mode from an AI solution direction short-term treatment method module to an AI humanism treatment method module, and performing psychological dispersion on the user;
if the state text information of the user is converted from sadness to anger, continuously converting the AI consultation mode from the AI personage treatment therapy module to the AI psychodynamic treatment method module based on the voice text information of the user obtained in real time, and performing psychological dispersion on the user;
if the state text information of the user is converted from anger to fear, continuously converting the AI consultation mode from the AI psychodynamic therapy module to the AI cognitive behavioral therapy module based on the voice text information of the user acquired in real time, and conducting psychological dispersion on the user.
8. The utility model provides an AI psychological consultation system, its characterized in that, including wearing equipment, be provided with the voice acquisition ware on the wearing equipment and be used for gathering human physiological signal's sensor for gather user's physiological signal and voice signal, and high in the clouds server, wearing equipment with high in the clouds server wireless connection, high in the clouds server is used for:
converting the physiological signals into state text information corresponding to the emotional state of the user according to the corresponding relation between the physiological signals and the emotional state;
converting the voice signal of the user into voice text information;
and selecting an AI consultation mode matched with the emotion state of the user by the natural language processing model according to the state text information and the voice text information to carry out psychological consultation on the user.
9. The AI psychological consultation system of claim 8, wherein the wearable device further includes a display interface for displaying feedback information and a man-machine interactive operation menu during AI psychological consultation.
10. The AI psychological consultation system of claim 8, wherein the wearable device is provided with a heart rate sensor for detecting heart rate and heart rate variability of the user, an acceleration sensor for detecting limb movement changes of the user, and a skin electric sensor for detecting skin electric signals of the user; the cloud server stores a computer program which, when run, is further configured to perform the method of any of claims 2-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311115827.2A CN117045253A (en) | 2023-08-31 | 2023-08-31 | AI psychological consultation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311115827.2A CN117045253A (en) | 2023-08-31 | 2023-08-31 | AI psychological consultation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117045253A true CN117045253A (en) | 2023-11-14 |
Family
ID=88664416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311115827.2A Pending CN117045253A (en) | 2023-08-31 | 2023-08-31 | AI psychological consultation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117045253A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117379021A (en) * | 2023-12-13 | 2024-01-12 | 深圳市光速时代科技有限公司 | Old person health index monitoring system based on intelligent wearing equipment |
-
2023
- 2023-08-31 CN CN202311115827.2A patent/CN117045253A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117379021A (en) * | 2023-12-13 | 2024-01-12 | 深圳市光速时代科技有限公司 | Old person health index monitoring system based on intelligent wearing equipment |
CN117379021B (en) * | 2023-12-13 | 2024-03-08 | 深圳市光速时代科技有限公司 | Old person health index monitoring system based on intelligent wearing equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10885800B2 (en) | Human performance optimization and training methods and systems | |
US11185281B2 (en) | System and method for delivering sensory stimulation to a user based on a sleep architecture model | |
Nirjon et al. | Musicalheart: A hearty way of listening to music | |
EP3007755B1 (en) | Sound-induced sleep method and a system therefor | |
CN100558290C (en) | Electrophysiologicalintuition intuition indicator | |
RU2415642C1 (en) | Method of classification of electroencephalographic signals in interface brain-computer | |
US20150011842A1 (en) | Method and device for stuttering alleviation | |
CN102525412A (en) | Method and equipment for promoting emotion balance, evaluating emotion state and evaluating emotion regulating effect | |
CN105615901A (en) | Emotion monitoring method and system | |
CN117045253A (en) | AI psychological consultation method and system | |
CN104367306A (en) | Physiological and psychological career evaluation system and implementation method | |
Mijić et al. | MMOD-COG: A database for multimodal cognitive load classification | |
CA3106402A1 (en) | Multiple frequency neurofeedback brain wave training techniques, systems, and methods | |
AU2021101097A4 (en) | A system and method for automatic playlist generation by analysing human emotions through physiological signals | |
Scherer et al. | Automatic verification of emotionally stressed speakers: The problem of individual differences | |
WO2021070456A1 (en) | Earphone, information processing device, and information processing method | |
Chyan et al. | A deep learning approach for stress detection through speech with audio feature analysis | |
Yiu et al. | Fatigue-Related change in surface electromyographic activities of the perilaryngeal muscles | |
Majumder et al. | A smart cyber-human system to support mental well-being through social engagement | |
Hossain et al. | Cognitive load measurement using galvanic skin response for listening tasks | |
Gebhard et al. | Towards heart rate categorisation from speech in outdoor running conditions | |
Kinjo et al. | Patient stress estimation for using deep learning with RRI data sensed by WBAN | |
Redekar et al. | Heart Rate Prediction from Human Speech using Regression Models | |
WO2023058200A1 (en) | Fatigue degree calculation device, fatigue degree calculation method, and storage medium | |
WO2022079758A1 (en) | Information processing device, control method, and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |