CN116548971B - Psychological crisis auxiliary monitoring system based on physiological parameters of object - Google Patents
Psychological crisis auxiliary monitoring system based on physiological parameters of object Download PDFInfo
- Publication number
- CN116548971B CN116548971B CN202310556104.XA CN202310556104A CN116548971B CN 116548971 B CN116548971 B CN 116548971B CN 202310556104 A CN202310556104 A CN 202310556104A CN 116548971 B CN116548971 B CN 116548971B
- Authority
- CN
- China
- Prior art keywords
- information
- psychological
- user
- data
- physiological
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 38
- 230000003340 mental effect Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000008859 change Effects 0.000 claims description 92
- 238000001514 detection method Methods 0.000 claims description 17
- 238000012937 correction Methods 0.000 claims description 9
- 230000006399 behavior Effects 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 230000008921 facial expression Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 description 5
- 230000002996 emotional effect Effects 0.000 description 3
- 230000004630 mental health Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000000638 stimulation Effects 0.000 description 2
- 206010012289 Dementia Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention relates to the field of data processing, in particular to a psychological crisis auxiliary monitoring system based on physiological parameters of a subject. The system comprises: the input terminal is used for generating reference psychological information according to the input information of the input terminal in a first preset time based on a user; a comparison unit for acquiring the correlation degree between each element data and the psychological information based on the similarity between each element reference data and the reference psychological information; the storage unit is used for storing the physiological information of the user, the corresponding psychological information and the user history information; the training unit is configured to: training a learning model based on the first training data and the second training data; a determining unit, configured to determine whether a psychological crisis occurs according to the psychological information variation and the variation trend of the element with the greatest correlation with the reference psychological information in the corresponding physiological information; the invention solves the problem of insufficient monitoring precision of the mental crisis, and improves the monitoring precision of the mental crisis through the scheme.
Description
Technical Field
The invention relates to the field of data processing, in particular to a psychological crisis auxiliary monitoring system based on physiological parameters of a subject.
Background
With the acceleration of life pace and the pursuit of people for improving quality of life of substances, the life pressure of people is increased gradually, and the number of people who live in high-pressure environment for a long time is increased, therefore, it is necessary to propose a method and a system for periodically monitoring the emotional state of a subject, which can detect and take certain measures in time before the mental crisis of a user, to prevent the dangerous behavior of the user, in the prior art, for example, in US10617351B2, by providing a method and a system for periodically monitoring the emotional state of the subject, comprising the following steps: subjecting the subject to a plurality of stimuli during the session; obtaining objective data from a plurality of monitoring sensors, wherein at least one sensor measures a physiological parameter; transmitting the data to a database; the data is processed to extract objective information about the emotional state of the subject. Also, for example, in US patent No. 10617351B2, the invention is to reduce the burden of evaluation of mental health of an evaluator, and to evaluate the mental health of the evaluator more accurately. A primary question selection for understanding at least one of personal personality, lifestyle, and social relationship of a subject is provided to a terminal of the subject through a transceiver, and a primary evaluation result generation unit that receives a response evaluator terminal to the primary question from an institution that generates a primary evaluation result through the transceiver, and based on the result of the diagnosis evaluation, a primary evaluation result of various factors necessary for not only directly improving cognitive ability but also maintaining mental health of the subject has an effect of preventing the subject from developing dementia. Both patents do not calculate the correlation between the elements in the collected physiological information and the corresponding psychological information, but correct the data in the physiological information according to the correlation and the data characteristics, and consider the change of the reference psychological information of the user to make the monitoring result inaccurate, and re-acquire the reference physiological information and the reference psychological information according to the psychological information change amount and retrain the learning model, and accurately assist in monitoring whether the psychological crisis occurs or not based on the psychological information change amount and the change trend of the element with the highest correlation with the psychological information in the physiological information.
Disclosure of Invention
In order to better solve the above problems, the present invention provides a mental crisis auxiliary monitoring system based on physiological parameters of a subject, the system comprising:
the input terminal is used for generating reference psychological information according to the input information of the input terminal in a first preset time based on a user;
the detection unit is used for acquiring user reference physiological information in the first preset time and extracting reference data of each element in the reference physiological information;
a comparison unit, configured to obtain a correlation between each element data and the psychological information based on a similarity between the reference data of each element and the reference psychological information;
the storage unit is used for storing the physiological information of the user, the corresponding psychological information and the user history information;
the training unit is configured to: training a learning model based on first training data and second training data, wherein the first training data comprises user physiological information and corresponding psychological information stored in the storage unit, and the second training data comprises the reference physiological information and corresponding reference psychological information;
a determining unit, configured to determine whether a psychological crisis occurs according to the psychological information variation and the variation trend of the element with the greatest correlation with the reference psychological information in the corresponding physiological information;
the physiological information comprises element data including pulse data, heart rate data, facial expression image data and limb behavior data.
As a more preferable technical solution, the input information is an answer to a question or image information set by a user for the input terminal, and the input terminal is configured to obtain reference psychological information by answering the question within the first preset time, where the question may cause a psychological change of the user, where the reference psychological information reflects the psychological change of the user, and at the same time, obtain, by the detection unit, physiological information of the user during the answer period within the first preset time, where the physiological information includes a plurality of element data, and each element data corresponds to the psychological change in time sequence.
As a more preferable aspect, the comparing unit is configured to: comparing the reference data of each element with the reference psychological information, obtaining the similarity between each element and the reference psychological information, obtaining the correlation between each element and the reference psychological information based on the similarity, and sequencing each element according to the correlation.
As a more preferable aspect, the system further includes a correction unit configured to:
acquiring physiological information and corresponding psychological information of a user by reading the storage unit, wherein the physiological information and the corresponding psychological information of the user are arranged according to time sequence;
the validity of each group of user physiological information is identified through the correlation degree and the data characteristics of each element in the physiological information, and when each element data in the ith group of user physiological information is valid, the processing is not needed; when one element data is invalid in the i-th group of user physiological information, determining the range of the element in the i-th group of physiological information through a first value of the element in the i-1-th group of physiological information and a second value of the element in the i+1-th group of physiological information, and correcting the value of the element according to the correlation degree of the element data and the psychological information; completing correction of the numerical value of each element corresponding to the physiological information, wherein the numerical range of i is a positive integer ranging from 1 to N, and N is the total amount of the physiological information of the user;
and training the learning model by taking the corrected user physiological information and the corresponding psychological information as first training data and taking the reference physiological information and the reference psychological information as second training data.
As a more preferable technical solution, the correction unit is further configured to determine whether each element data is valid according to a data range, a data format, and a data feature of each element data in the physiological information and the corresponding detection unit or the sensor of each element, where the data is valid when the data is consistent, and invalid when the data is inconsistent.
As a more preferable aspect, the determining unit is configured to: the method comprises the steps of correcting physiological information acquired by a user in real time, inputting the physiological information into a learning model to obtain psychological variation of the user, wherein the psychological variation is relative to reference psychological information, recording time as first time when the psychological variation is larger than a first threshold value, searching second time corresponding to the psychological variation being smaller than a third threshold value before the first time, and judging whether psychological crisis occurs according to time difference between the second time and the first time and variation trend of elements with highest psychological information correlation degree in the physiological information;
determining that a psychological crisis does not occur for the user when the time difference between the first time and the second time is greater than or equal to a first time length or an average rate of change of the highest correlation element within the time difference is less than a second threshold;
when the time difference is smaller than the first time length and the average change rate of the element with the highest correlation degree is larger than the second threshold value, determining that the mental crisis occurs to the user, and sending the mental crisis information to a user side;
and when the psychological change is negative and the accumulated time length is greater than a preset time length or the time length between the first time and the second time is greater than or equal to a first time length and the change rate of the element with the highest correlation is smaller than a second threshold value, acquiring updated reference physiological information and corresponding reference psychological information through the input terminal again, otherwise, updating is not needed.
As a more preferable aspect, the user history information includes physiological information of the user and a psychological change monitoring value for inputting the physiological information into the learning model.
As a more preferable technical solution, the reference physiological information and the physiological information are both obtained by a wearable device, and the wearable device includes a sensor or a detection unit corresponding to each physiological element in the physiological information.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, through calculating the relativity of element data in the acquired reference physiological information and corresponding reference psychological information, training data in the physiological information is corrected according to the relativity and the data characteristics, the accuracy of the training data is improved, psychological crisis is estimated based on the psychological information variation and each element variation trend in the physiological information, and when the time from the third threshold value to the first threshold value of the psychological variation of the user is smaller than the first time and the element variation rate with the highest relativity of the psychological information variation in the physiological information is larger than the second threshold value, the psychological crisis can be determined to occur and the psychological crisis information is sent to the user side, and the user side can take corresponding measures to relieve the psychological crisis of the user; when the time length between the first time and the second time is greater than or equal to the first time length and the change rate of the element with the highest correlation degree is smaller than the second threshold value, as the change time of the psychological change amount from the third threshold value to the first threshold value is longer and the change rate of the element with the highest correlation degree is smaller, the psychological information is not changed according to psychological reasons, and when the psychological change amount is negative and the accumulated time length is greater than the preset time length, the psychological state of a user is changed, the psychological fluctuation of the surrounding environment or an event is reduced, if the psychological change amount is judged based on the original reference physiological information and the corresponding reference psychological information, the monitoring result is inaccurate, and therefore the reference physiological information and the corresponding reference psychological information are required to be acquired again in the two conditions, the reference information with more accurate dynamic change is provided, the prediction precision of the learning model is improved by re-acquiring the reference physiological information and the reference psychological information and retraining the learning model, the psychological behavior of the user can be monitored more accurately through the mutual cooperation of the scheme, and dangerous events can be prevented from happening of dangerous events.
Drawings
FIG. 1 is a block diagram of a mental crisis auxiliary monitoring system based on physiological parameters of a subject in accordance with the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a psychological crisis auxiliary monitoring system based on physiological parameters of a subject, as shown in fig. 1, the system comprises:
the input terminal is used for generating reference psychological information according to the input information of the input terminal in a first preset time based on a user;
the detection unit is used for acquiring user reference physiological information in the first preset time and extracting reference data of each element in the reference physiological information;
specifically, the reference psychological information can be in the form of a question or a questionnaire which is set by answering, the answer of the question corresponds to the psychological information of the response, the psychological information and the psychological change information of the user can be quantified through the score of the answer question, the change of the physiological information caused by the psychological change can be obtained through a detection unit in the process of answering the question, the detection unit comprises a sensor in the wearable device, element data corresponding to each sensor in the physiological information is obtained through the sensor, the element data comprises pulse data, blood flow data, heart rate data and facial expression data set behavior limb data, and a basis is provided for evaluating the psychological change of the user through the scheme.
A comparison unit, configured to obtain a correlation between each element data and the psychological information based on a similarity between the reference data of each element and the reference psychological information;
specifically, the influence of each element on the reference psychological information and the change relation between the reference psychological information and the reference psychological information can be obtained through the similarity between the reference data of each element and the change of the reference psychological information along with time, main elements influencing the reference psychological information can be obtained through sorting according to the relativity between each element and the reference psychological information, and whether psychological crisis occurs or not can be accurately judged according to the change of the main elements when the psychological information is changed.
The storage unit is used for storing the physiological information of the user, the corresponding psychological information and the user history information;
the training unit is configured to: training a learning model based on first training data and second training data, wherein the first training data comprises user physiological information and corresponding psychological information stored in the storage unit, and the second training data comprises the reference physiological information and corresponding reference psychological information;
specifically, similarity verification is performed on each element in the physiological information of the user and the corresponding psychological information according to the relevance of each element in the physiological information and the corresponding psychological information, for example: the similarity between the pulse information and the corresponding psychological information is the largest, whether the pulse information and the corresponding psychological information are matched or not is verified through the similarity between the pulse information and the corresponding psychological information, when the pulse information and the corresponding psychological information are not matched, the value range of the element in the group of physiological information is determined through the values of the element in the group of physiological information before the group of physiological information and the element in the group of physiological information after the group of physiological information according to the time sequence, the numerical value of the element is corrected according to the correlation between the element and the reference psychological information, so that the accuracy of the first training data is ensured, the first training data and the second training data are used as training data of a learning model, and therefore the psychological change of a user can be accurately obtained when the learning model inputs the detected physiological information of the user, and the psychological change of the user is relative to the change of the reference psychological information.
A determining unit, configured to determine whether a psychological crisis occurs according to the psychological information variation and the variation trend of the element with the greatest correlation with the reference psychological information in the corresponding physiological information;
specifically, the relative reference psychological information change amount of the user can be obtained by inputting the physiological information of the user into the learning model, the larger the psychological information change amount is, the larger the psychological fluctuation of the user is, the larger the psychological information change possibility is, the smaller the psychological information change is, the smaller the psychological fluctuation of the user is, the more psychological information is related to the change trend of the element with the highest psychological information relativity, the longer the duration of the psychological fluctuation from small to large fluctuation is, the change rate of the element is smaller, the physiological cause possibly causes the change of the element, the psychological fluctuation is influenced by the stimulation of an event, the shorter the duration of the psychological fluctuation from small to large fluctuation is, and the change rate of the element is larger, so that whether the psychological crisis of the user can be estimated through the psychological information change amount of the user and the change rate of the element with the highest psychological information relativity; when the change amount of the psychological information is negative and the duration time is longer than the preset time, the sensitivity of the user to surrounding events and environments is reduced, which means that the psychological quality of the user is changed, and the psychological fluctuation of the user is smaller for the same environment or events, so that the reference value of the learning model, namely the reference psychological information, is also changed, or if the reference psychological information is not updated in time, the psychological change amount of the user cannot be accurately predicted through the learning model, and therefore, the corresponding relation between the reference physiological information of the user and the reference psychological information and between the reference psychological information of the user and the reference psychological information needs to be obtained again through an input terminal, a detection unit and a comparison unit, and a good foundation is provided for ensuring the accuracy of the learning model.
The physiological information comprises element data including pulse data, heart rate data, facial expression image data and limb behavior data.
Further, the input information is an answer of a user to the input terminal setting a question or an image information, and the input terminal is used for enabling the user to generate reference psychological information in a mode of setting the question or the image at the first preset time, wherein the question or the image can cause the user to generate psychological changes, and the reference psychological information reflects the psychological changes of the user;
the detection unit is used for acquiring physiological information of the user during answering in a first preset time, wherein the physiological information comprises a plurality of element data, and each element data corresponds to the psychological change in time sequence.
Specifically, the reference psychological information and the corresponding physiological information are obtained by a way that the user answers questions in a preset first time, the physiological information comprises a plurality of element data, the element data corresponds to the psychological information in time sequence, the reference physiological information and the reference psychological information reflect the corresponding relation between the psychological fluctuation of the user in a normal state and the physiological information, and the reference physiological information and the reference psychological information are used as reference information, so that a reference basis is provided for predicting psychological change of the user through the physiological information of the user.
Further, the comparing unit is configured to: comparing the reference data of each element with the reference psychological information, obtaining the similarity between each element and the reference psychological information, obtaining the correlation between each element and the reference psychological information based on the similarity, and sequencing each element according to the correlation.
Specifically, each element in the reference physiological information and the trend of the reference psychological information changing along with time are compared, the change similarity of each element and the reference psychological information is obtained through a comparison result, the correlation degree of each element and the reference psychological information is obtained, the higher the similarity is, the higher the correlation degree of the corresponding element and the psychological information is, and the element with the highest correlation degree is obtained according to the sorting of the similarity of each element, so that the change trend of the element with the highest correlation degree is combined when the psychological change amount is detected later, and whether the psychological crisis occurs is judged more accurately.
Further, the system further comprises a correction unit configured to:
acquiring physiological information and corresponding psychological information of a user by reading the storage unit, wherein the physiological information and the corresponding psychological information of the user are arranged according to time sequence;
the validity of each group of user physiological information is identified through the correlation degree and the data characteristics of each element in the physiological information, and when each element data in the ith group of user physiological information is valid, the processing is not needed; when one element data is invalid in the i-th group of user physiological information, determining the range of the element in the i-th group of physiological information through a first value of the element in the i-1-th group of physiological information and a second value of the element in the i+1-th group of physiological information, and correcting the value of the element according to the correlation degree of the element data and the psychological information; completing correction of the numerical value of each element corresponding to the physiological information, wherein the numerical range of i is a positive integer ranging from 1 to N, and N is the total amount of the physiological information of the user;
and training the learning model by taking the corrected user physiological information and the corresponding psychological information as first training data and taking the reference physiological information and the reference psychological information as second training data.
Specifically, the validity of each element data is determined by extracting the characteristic of each element data, and the corresponding element data can be acquired by a sensor, wherein the data acquisition range, format and characteristic of the sensor are determined, the data exceeding the data acquisition range of the sensor are invalid, and meanwhile, the validity of each element data in each group of physiological information is determined according to the relation between the time change trend of each element data and the time change trend of psychological information.
Further, the correction unit is further configured to determine whether each element data is valid according to a data range, a data format, and a data characteristic of each element data in the physiological information and the corresponding detection unit or the sensor of each element, and valid when the element data is consistent, and invalid when the element data is inconsistent.
Further, the determining unit is configured to: the method comprises the steps of correcting physiological information acquired by a user in real time, inputting the physiological information into a learning model to obtain psychological variation of the user, wherein the psychological variation is relative to reference psychological information, recording time as first time when the psychological variation is larger than a first threshold value, searching second time corresponding to the psychological variation being smaller than a third threshold value before the first time, and judging whether psychological crisis occurs according to time difference between the second time and the first time and variation trend of elements with highest psychological information correlation degree in the physiological information;
determining that a psychological crisis does not occur for the user when the time difference between the first time and the second time is greater than or equal to a first time length or an average rate of change of the highest correlation element within the time difference is less than a second threshold;
when the time difference is smaller than the first time length and the average change rate of the element with the highest correlation degree is larger than the second threshold value, determining that the mental crisis occurs to the user, and sending the mental crisis information to a user side;
and when the psychological change is negative and the accumulated time length is greater than a preset time length or the time length between the first time and the second time is greater than or equal to a first time length and the change rate of the element with the highest correlation is smaller than a second threshold value, acquiring updated reference physiological information and corresponding reference psychological information through the input terminal again, otherwise, updating is not needed.
Specifically, the psychological change of the user can be obtained in real time by correcting the physiological information acquired in real time and inputting the physiological information into the learning model, when the psychological change is larger than a first threshold value, the time at the moment is recorded as a first time, and a second time corresponding to a third threshold value is calculated, wherein the psychological change closest to the first time is smaller than a second time corresponding to the third threshold value, when the time difference between the first time and the second time is larger, the change rate of the element with the largest degree of relevance to the psychological information is judged, and the change of the numerical value of the element with the largest degree of relevance is possibly caused by the physiological cause or the psychological cause, but the physiological cause is characterized in that the change is slower and is the change of the accumulation of the daily period, and the psychological crisis caused by the stimulation of a certain event, so that the change rate of the element with the largest degree of relevance is larger, and the time is shorter, so that whether the physiological information is caused by the psychological crisis can be judged through the change of the psychological crisis; when the duration between the first time and the second time is smaller than the first time or the change rate of the element with the highest correlation degree is larger than the second threshold, namely, the time from the third threshold to the first threshold of the psychological change amount is shorter and the change rate of the element with the highest correlation degree with the psychological change amount in the physiological information is larger, determining that psychological crisis occurs, and sending psychological crisis information to a user side, wherein the user side can take corresponding measures to relieve the psychological crisis of the user; when the duration between the first time and the second time is greater than or equal to the first time or the change rate of the element with the highest correlation is smaller than the second threshold, as the change time of the psychological change amount from the third threshold to the first threshold is longer or the change rate of the element with the highest correlation is smaller and does not accord with the characteristics of physiological information change caused by psychological reasons, similarly, when the psychological change amount is negative and the accumulated duration is greater than the preset duration, the psychological state of the user is indicated to change, the psychological fluctuation of the surrounding environment or the event is reduced, and if the psychological change amount is judged based on the original reference physiological information and the corresponding reference psychological information, the prediction result is inaccurate, so that the reference physiological information and the corresponding reference psychological information are required to be acquired again through the input terminal, the detection unit and the comparison unit in both cases, and the reference information with more accurate dynamic change is provided.
Further, the training unit is further configured to: based on the updated user reference physiological information and the reference psychological information, acquiring the correlation degree of each element in the updated physiological information and the updated reference psychological information, correcting the user history information by using the correlation degree, and retraining the learning model according to the corrected history information, the updated physiological information and the corresponding updated reference psychological information.
Specifically, the reference physiological information and the corresponding reference psychological information are obtained through the input terminal and the detection unit, a new correlation degree is obtained through the comparison unit, the user history information is corrected according to the new correlation degree, the history information comprises the user physiological information and the corresponding psychological information, the learning model is retrained according to the corrected history information, the updated reference physiological information and the corresponding updated reference psychological information, and a more accurate prediction model is obtained.
Further, the user history information includes physiological information of the user and a psychological change amount predicted value of inputting the physiological information into the learning model.
Further, the reference physiological information and the physiological information are both acquired by a wearable device, which includes a sensor or a detection unit corresponding to each physiological element in the physiological information.
In summary, according to the invention, through calculating the correlation degree between the element data in the collected reference physiological information and the corresponding reference psychological information, the training data in the physiological information is corrected according to the correlation degree and the data characteristics, the accuracy of the training data is improved, the psychological crisis is estimated based on the psychological information variation and each element variation trend in the physiological information, and the psychological crisis of the user can be relieved by adopting corresponding measures when the time from the third threshold value to the first threshold value of the psychological variation of the user is smaller than the first time and the element variation rate with the highest correlation degree with the psychological information variation in the physiological information is larger than the second threshold value; when the time length between the first time and the second time is longer than or equal to the first time length or the change rate of the element with the highest correlation degree is smaller than the second threshold value, as the change time of the psychological change amount from the third threshold value to the first threshold value is longer and the change rate of the element with the highest correlation degree is smaller, the psychological information is changed due to the fact that the psychological cause is not met, and when the psychological change amount is negative and the accumulated time length is longer than the preset time length, the psychological state of a user is changed, the psychological fluctuation of the surrounding environment or an event is reduced, if the psychological change amount is judged based on the original reference physiological information and the corresponding reference psychological information, the prediction result is inaccurate, therefore, the reference physiological information and the corresponding reference psychological information are required to be acquired again in the two conditions, more accurate reference information for dynamic change is provided, the prediction accuracy of a learning model is improved by retraining the reference physiological information and the reference psychological information, and the prediction accuracy of the learning model is improved, and the psychological behavior of the user can be monitored in a more accurate auxiliary manner through the mutual cooperation of the scheme, so that dangerous events can be prevented.
The technical features of the foregoing embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the foregoing embodiments are not described, however, they should be considered as the scope of the disclosure as long as there is no contradiction between the combinations of the technical features.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (6)
1. A mental crisis auxiliary monitoring system based on physiological parameters of a subject, the system comprising:
the input terminal is used for generating reference psychological information according to the input information of the input terminal in a first preset time according to a user;
the detection unit is used for acquiring user reference physiological information in the first preset time and extracting reference data of each element in the reference physiological information;
a comparison unit, configured to obtain a correlation between each element data and the psychological information based on a similarity between the reference data of each element and the reference psychological information;
the storage unit is used for storing the physiological information of the user, the corresponding psychological information and the user history information;
the correction unit is configured to: acquiring physiological information and corresponding psychological information of a user by reading the storage unit, wherein the physiological information and the corresponding psychological information of the user are arranged according to time sequence;
the validity of each group of user physiological information is identified through the correlation degree and the data characteristics of each element in the physiological information, and when each element data in the ith group of user physiological information is valid, the processing is not needed; when one element data is invalid in the i-th group of user physiological information, determining the range of the element in the i-th group of physiological information through a first value of the element in the i-1-th group of physiological information and a second value of the element in the i+1-th group of physiological information, and correcting the value of the element according to the correlation degree of the element data and the psychological information; completing correction of the numerical value of each element corresponding to the physiological information, wherein the numerical range of i is a positive integer ranging from 1 to N, and N is the group number of the physiological information of the user;
the training unit is configured to: training a learning model based on corrected first training data and second training data, wherein the first training data comprises user physiological information and corresponding psychological information stored in the storage unit, the second training data comprises the reference physiological information and the corresponding reference psychological information, and real-time psychological variation is obtained by inputting physiological information acquired in real time into the learning model;
the determining unit is used for determining whether a psychological crisis occurs according to the change amount of the psychological information in the preset time and the change trend and time of the element with the maximum correlation degree with the reference psychological information in the corresponding physiological information;
the physiological information comprises element data including pulse data, heart rate data, facial expression image data and limb behavior data;
the determination unit is configured to: the method comprises the steps of correcting physiological information acquired by a user in real time, inputting the physiological information into a learning model to obtain psychological variation of the user, wherein the psychological variation is relative to reference psychological information, recording time as first time when the psychological variation is larger than a first threshold value, searching second time corresponding to the psychological variation being smaller than a third threshold value before the first time, and judging whether psychological crisis occurs according to time difference between the second time and the first time and variation trend of elements with highest psychological information correlation degree in the physiological information;
determining that a psychological crisis does not occur for the user when the time difference between the first time and the second time is greater than or equal to a first time length or an average rate of change of the highest correlation element within the time difference is less than a second threshold;
when the time difference is smaller than the first time length and the average change rate of the element with the highest correlation degree is larger than the second threshold value, determining that the mental crisis occurs to the user, and sending the mental crisis information to a user side;
when the psychological change is negative and the accumulated time length is greater than a preset time length or the time length between the first time and the second time is greater than or equal to a first time length and the change rate of the element with the highest correlation is smaller than a second threshold value, acquiring updated reference physiological information and corresponding reference psychological information through the input terminal again, otherwise, updating is not needed;
the training unit is further configured to: based on the updated user reference physiological information and the reference psychological information, acquiring the correlation degree of each element in the updated physiological information and the updated reference psychological information, correcting the user history information by using the correlation degree, and retraining the learning model according to the corrected history information, the updated physiological information and the corresponding updated reference psychological information.
2. The mental crisis auxiliary monitoring system based on physiological parameters of a subject according to claim 1, wherein the input information is an answer to a question or image information set by a user for the input terminal, the input terminal is used for acquiring reference mental information by answering the question within the first preset time, the question can cause the user to generate mental change, the reference mental information reflects the mental change of the user, and physiological information of the user during the answer period is acquired by a detection unit within the first preset time, and the physiological information comprises a plurality of element data, and each element data corresponds to the mental change in time sequence.
3. The mental crisis aid monitoring system based on physiological parameters of a subject according to claim 1, wherein the comparison unit is configured to: comparing the reference data of each element with the reference psychological information, obtaining the similarity between each element data and the reference psychological information, obtaining the correlation between each element data and the reference psychological information based on the similarity, and sorting the element data according to the correlation.
4. The mental crisis auxiliary monitoring system based on physiological parameters of a subject according to claim 1, wherein the correction unit is further configured to determine whether each element data is valid according to a data range, a data format and a data characteristic of the detection unit or the sensor corresponding to each element in the physiological information, and valid when the element data is consistent and invalid when the element data is inconsistent.
5. The mental crisis aid monitoring system based on physiological parameters of a subject according to claim 1, wherein the user history information includes physiological information of a user and a mental change amount monitoring value for inputting the physiological information into the learning model.
6. The mental crisis aid monitoring system based on physiological parameters of a subject according to claim 1, wherein the baseline physiological information and the physiological information are both obtained by a wearable device comprising a sensor or a detection unit corresponding to each physiological element in the physiological information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310556104.XA CN116548971B (en) | 2023-05-17 | 2023-05-17 | Psychological crisis auxiliary monitoring system based on physiological parameters of object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310556104.XA CN116548971B (en) | 2023-05-17 | 2023-05-17 | Psychological crisis auxiliary monitoring system based on physiological parameters of object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116548971A CN116548971A (en) | 2023-08-08 |
| CN116548971B true CN116548971B (en) | 2023-10-13 |
Family
ID=87487669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310556104.XA Active CN116548971B (en) | 2023-05-17 | 2023-05-17 | Psychological crisis auxiliary monitoring system based on physiological parameters of object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116548971B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117414135A (en) * | 2023-10-20 | 2024-01-19 | 郑州师范学院 | Behavioral and psychological abnormality detection method, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110013261A (en) * | 2019-05-24 | 2019-07-16 | 京东方科技集团股份有限公司 | Method, apparatus, electronic equipment and the storage medium of mood monitoring |
| CN110507335A (en) * | 2019-08-23 | 2019-11-29 | 山东大学 | Inmate's psychological health states appraisal procedure and system based on multi-modal information |
| CN112806994A (en) * | 2021-01-27 | 2021-05-18 | 首都师范大学 | System and method for predicting individual stress coping mode based on physiological signal |
| CN114601463A (en) * | 2022-03-08 | 2022-06-10 | 深圳领悟智能网络科技有限公司 | Psychological crisis monitoring system and method |
| CN115177253A (en) * | 2022-08-02 | 2022-10-14 | 河南牧业经济学院 | Student psychological crisis early warning system based on multi-mode data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200294670A1 (en) * | 2019-03-13 | 2020-09-17 | Monsoon Design Studios LLC | System and method for real-time estimation of emotional state of user |
-
2023
- 2023-05-17 CN CN202310556104.XA patent/CN116548971B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110013261A (en) * | 2019-05-24 | 2019-07-16 | 京东方科技集团股份有限公司 | Method, apparatus, electronic equipment and the storage medium of mood monitoring |
| CN110507335A (en) * | 2019-08-23 | 2019-11-29 | 山东大学 | Inmate's psychological health states appraisal procedure and system based on multi-modal information |
| CN112806994A (en) * | 2021-01-27 | 2021-05-18 | 首都师范大学 | System and method for predicting individual stress coping mode based on physiological signal |
| CN114601463A (en) * | 2022-03-08 | 2022-06-10 | 深圳领悟智能网络科技有限公司 | Psychological crisis monitoring system and method |
| CN115177253A (en) * | 2022-08-02 | 2022-10-14 | 河南牧业经济学院 | Student psychological crisis early warning system based on multi-mode data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116548971A (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11562222B2 (en) | Systems and methods of identity analysis of electrocardiograms | |
| RU2292839C2 (en) | Method and device for analyzing human behavior | |
| KR20170061222A (en) | The method for prediction health data value through generation of health data pattern and the apparatus thereof | |
| CN116548971B (en) | Psychological crisis auxiliary monitoring system based on physiological parameters of object | |
| US20240074698A1 (en) | Method, Computing Device And Wearable Device For Sleep Stage Detection | |
| CN108888277B (en) | Psychological test method, psychological test system and terminal equipment | |
| Mengoudi et al. | Augmenting dementia cognitive assessment with instruction-less eye-tracking tests | |
| CN111657890A (en) | Sleep state monitoring method and device, intelligent mattress and medium | |
| CN113871015B (en) | Man-machine interaction scheme pushing method and system for improving cognition | |
| Thorey et al. | AI vs Humans for the diagnosis of sleep apnea | |
| CN112908481A (en) | Automatic personal health assessment and management method and system | |
| US11568979B1 (en) | Adaptive artificial intelligence system for identifying behaviors associated with mental illness and modifying treatment plans based on emergent recognition of aberrant reactions | |
| CN111297327A (en) | Sleep analysis method, system, electronic equipment and storage medium | |
| US20200321082A1 (en) | Confidence evaluation to measure trust in behavioral health survey results | |
| Walker et al. | Beyond percent correct: Measuring change in individual picture naming ability | |
| JP4631464B2 (en) | Physical condition determination device and program thereof | |
| WO2021165498A1 (en) | Neurodevelopmental/cognitive assessment and cognitive training on a digital device and identification and measurement of digital cognitive biomarkers | |
| CN112914536A (en) | Motion state detection method and device, computer equipment and storage medium | |
| CN115497621A (en) | Old person cognitive status evaluation system | |
| KR102432275B1 (en) | Data processing method For Depressive disorder diagnosis method using artificial intelligence based on multi-indicator | |
| CN112806967B (en) | Teenager sleep quality monitoring method and device, computer equipment and storage medium | |
| CN115472312A (en) | Medical health management system and method based on medical defense fusion service | |
| CN114388089A (en) | Personal health management method and system based on artificial intelligence | |
| CN112957018A (en) | Heart state detection method and device based on artificial intelligence | |
| CN111436939A (en) | Health monitoring method, system, computer equipment and readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |