CN109493885A - Psychological condition assessment and adjusting method, device and storage medium, server - Google Patents
Psychological condition assessment and adjusting method, device and storage medium, server Download PDFInfo
- Publication number
- CN109493885A CN109493885A CN201811348241.XA CN201811348241A CN109493885A CN 109493885 A CN109493885 A CN 109493885A CN 201811348241 A CN201811348241 A CN 201811348241A CN 109493885 A CN109493885 A CN 109493885A
- Authority
- CN
- China
- Prior art keywords
- user
- psychological
- key message
- real
- information
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
Abstract
Semantic, technical field of voice interaction that the present invention relates to voices, a kind of psychological condition assessment provided by the embodiments of the present application and adjusting method, it include: the real-time behavior characteristic information for acquiring user, pretreatment is carried out to real-time behavior characteristic information and obtains key message, real-time behavior characteristic information includes the first voice messaging；Default behavioural characteristic classifying rules is obtained, is classified based on default behavioural characteristic classifying rules and key message to user psychology feature, psychological classification results are obtained；Based on the incidence relation between default psychological classification results and feedback regulation information, determines the corresponding feedback regulation information of the real-time behavior characteristic information of user, send feedback regulation information in real time to user.In this application by being acquired to user behavior characteristics information and analyzing in time, quickly determine the psychological characteristics classification of user, and send Real-time Feedback associated with the category to user and adjust information, user psychology pressure is relieved when realizing Intelligent dialogue, guarantees the privacy of user.
Description
Technical field
The present invention relates to information technologies, technical field of data processing, and in particular to a kind of assessment of psychological condition and adjusting side
Method, device and storage medium, server.
Background technique
Currently, worldwide, Psychological Health Problem, which has become, leads to individual " disability " (disability)
First cause, passivity consequence account for the 37% of all disease harm, in conjunction with its " global " (global), " chronicity "
(chronic) and from the point of view of the development trend of " popularity " (prevalent), the presence of Psychological Health Problem not only results in society
The huge consumption and waste of resource, exacerbate the burden of entire society, and directly threaten the daily life quality of individual
And Subjective Sense of Happiness.It specific to the actual conditions in China, is shown according to he result of investigation, the integral level of common people's mental health
It equally allows of no optimist, the whole incidence of Psychological Health Problem reaches 17.5%.
In addition, in order to adapt to the development of computer industry, programmer needs to grow since computer industry updates comparatively fast
Phase is in self-teaching, and also needs to face larger operating pressure simultaneously, so that modern metropolitan cities programmer's psychological pressure compares
Greatly, it works overtime more, pressure can not discharge, and easily lead to more mental disease, can not dredge in time；Shrink is at high cost, and
And a lot of programmers are reluctant actively to go to carry out psychological counseling due to self reason (such as introverted, concerning the pride).
Summary of the invention
To overcome the above technical problem, especially programmer's pressure is larger, is unable to get release, while certainly based on programmer
Body reason is reluctant actively to go the problem of carrying out psychological counseling, and spy proposes following technical scheme:
A kind of psychological condition assessment provided in an embodiment of the present invention and adjusting method, comprising:
The real-time behavior characteristic information for acquiring user carries out pretreatment to the real-time behavior characteristic information and obtains crucial letter
Breath, the real-time behavior characteristic information include the first voice messaging；
Default behavioural characteristic classifying rules is obtained, the default behavioural characteristic classifying rules and the key message pair are based on
User psychology feature is classified, and psychological classification results are obtained；
Based on the incidence relation between default psychological classification results and feedback regulation information, real-time behavior described in user is determined
The corresponding feedback regulation information of characteristic information, the feedback regulation information is sent to user in real time.
Optionally, the default behavioural characteristic classifying rules includes the multilayer feedforward based on the training of error backpropagation algorithm
Neural network.
It is optionally, described that pretreatment acquisition key message is carried out to the real-time behavior characteristic information, comprising:
First voice messaging is cleaned based on default voice messaging cleaning rule, obtains the second voice messaging；
Second voice messaging is handled according to mel cepstrum coefficients operation rule, obtains the key message.
Optionally, it is described based on the default behavioural characteristic classifying rules and the key message to user psychology feature into
Row classification, comprising:
According to the key message and it is described based on error backpropagation algorithm training multilayer feedforward neural network to
Family psychological characteristics is classified.
Optionally, it is described based on the default behavioural characteristic classifying rules and the key message to user psychology feature into
Row classification, comprising:
Optimize the default behavioural characteristic classifying rules according to the psychological classification results；
Based on after optimization the default behavioural characteristic classifying rules and the key message determine that the user psychology is special
The classification of sign.
Optionally, described in the default behavioural characteristic classifying rules based on after optimization and the key message determine
After the classification of user psychology feature, comprising:
The classification of the default behavioural characteristic classifying rules after optimization is determined according to the classification of the user psychology feature
Error；
The error in classification is judged whether within default error threshold, if so, the classification of the user psychology feature
It is determined as the psychological classification results；
If it is not, then based on the default behavioural characteristic classifying rules and the key message again to user psychology feature into
Row classification.
It is optionally, described to obtain default behavioural characteristic classifying rules, comprising:
Key message and its classification of sample of users are obtained based on block chain technology；
Key message and its classification using sample of users, based on error backpropagation algorithm training multilayer feedforward nerve net
Network；
The multilayer feedforward neural network is used to characterize the incidence relation of key message and classification.
The embodiment of the invention also provides a kind of assessment of psychological condition and regulating devices, comprising:
Acquisition module carries out the real-time behavior characteristic information pre- for acquiring the real-time behavior characteristic information of user
Processing obtains key message, and the real-time behavior characteristic information includes the first voice messaging；
Analysis module, for obtaining default behavioural characteristic classifying rules, based on the default behavioural characteristic classifying rules and
The key message classifies to user psychology feature, obtains psychological classification results；
Feedback module, for determining and using based on the incidence relation between default psychological classification results and feedback regulation information
The corresponding feedback regulation information of real-time behavior characteristic information described in family, the feedback regulation information is sent to user in real time.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is contained, which realizes the assessment of psychological condition described in any technical solution and adjusting side when being executed by processor
Method.
The embodiment of the invention also provides a kind of servers, comprising:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and quilt
It is configured to be executed by one or more of processors, one or more of application programs are configured to carry out according to any skill
The step of assessment of psychological condition described in art scheme and adjusting method.
A kind of computer readable storage medium is additionally provided in the embodiment of the present invention, on the computer readable storage medium
It is stored with computer program, which realizes the assessment of psychological condition described in any technical solution and adjust when being executed by processor
Method.
A kind of server is additionally provided in the embodiment of the present invention includes:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and quilt
It is configured to be executed by one or more of processors, one or more of application programs are configured to carry out according to any skill
The assessment of psychological condition described in art scheme and adjusting method.
Compared with the prior art, the present invention has the following beneficial effects:
1, a kind of psychological condition assessment provided by the embodiments of the present application and adjusting method, comprising: acquire the real-time row of user
It is characterized information, pretreatment is carried out to the real-time behavior characteristic information and obtains key message, the real-time behavior characteristic information
Including the first voice messaging；Default behavioural characteristic classifying rules is obtained, based on the default behavioural characteristic classifying rules and described
Key message classifies to user psychology feature, obtains psychological classification results；It is adjusted based on default psychological classification results and feedback
The incidence relation between information is saved, determines the corresponding feedback regulation information of real-time behavior characteristic information described in user, Xiang Yong
Family sends the feedback regulation information in real time.In this application by being acquired to user behavior characteristics information and timely dividing
Analysis in order to determine the psychological characteristics classification of user, and sends feedback regulation information to user based on the category, realizes to user
Psychological pressure relieves, and process user can carry out when alone, ensure that the privacy of user, the process
In feedback regulation information be Real-time Feedback, realize the process that can only talk with.
2, a kind of psychological condition assessment provided by the embodiments of the present application and adjusting method, the default behavioural characteristic classification gauge
Then include the multilayer feedforward neural network based on the training of error backpropagation algorithm, improves user psychology tagsort result
Accuracy, in order to be able to propose more accurately solution for the psychological characteristics of user.
3, a kind of psychological condition assessment provided in an embodiment of the present invention and adjusting method, it is described to obtain default behavioural characteristic point
Rule-like, comprising: the key message of user is obtained based on block chain technology；Optimize the default behavior according to the key message
Tagsort rule.It, can be according to the multistage voice messaging of active user in order to guarantee the accuracy of default behavior classifying rules
Calculating is optimized to default behavioural characteristic classifying rules, guarantees the accuracy of default behavior classifying rules；It can also be in conjunction with every
The used record of one user optimizes behavior characteristic information classifying rules.In order to effectively utilize big data, may be used also
To obtain the key message of other users by block chain technology, and behavioural characteristic classifying rules is carried out based on the key message
Optimization improves the precision of default behavior classifying rules.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is a kind of process signal of embodiment in the exemplary embodiments of psychological condition of the present invention assessment and adjusting method
Figure；
Fig. 2 is that the process of another embodiment in the exemplary embodiments of psychological condition of the present invention assessment and adjusting method is shown
It is intended to；
Fig. 3 is the structural schematic diagram of the exemplary embodiments of psychological condition of the present invention assessment and regulating device；
Fig. 4 is an example structure schematic diagram of server of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refers to that there are the feature, integer, step, operations, but it is not excluded that in the presence of or addition it is one or more other
Feature, integer, step, operation.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
It will be appreciated by those skilled in the art that so-called " application ", " application program ", " application software " and class of the invention
It is same concept well known to those skilled in the art like the concept of statement, refers to and instructed by series of computation machine and related data
The computer software for being suitable for electronics operation of the organic construction of resource.Unless specified, this name itself is not by programming language
Type, rank, the operating system of operation of also not rely by it or platform are limited.In the nature of things, this genus also not by appoint
The terminal of what form is limited.
Since programmer is usually in high-pressure work state in daily work, if things go on like this lead to the psychology of programmer
Pressure is larger, while programmer is also easy to appear biggish negative emotions so that programmer can not work carefully, programmer
Suitable people can not be found to oneself psychological pressure to pour out, and then psychological pressure can not be released, and journey is caused
Sequence person can only wallow in work, but also will continue to increase the psychological burden of programmer, form vicious circle.The application is implemented
A kind of assessment of psychological condition and adjusting method that example provides are mainly used for adjusting the psychological pressure of programmer, enable a programmer to
Oneself thinking that suitable space pours out the psychological pressure of oneself, and to its psychological problems information of programmer's feedback regulation, it can
Guarantee the privacy of programmer, while can also help and relieve pressure.
A kind of psychological condition assessment provided by the embodiments of the present application and adjusting method, as shown in Figure 1, comprising: S100,
S200、S300。
S100: acquiring the real-time behavior characteristic information of user, carries out pretreatment acquisition to the real-time behavior characteristic information
Key message, the real-time behavior characteristic information include the first voice messaging；
S200: default behavioural characteristic classifying rules is obtained, the default behavioural characteristic classifying rules and the key are based on
Information classifies to user psychology feature, obtains psychological classification results；
S300: it based on the incidence relation between default psychological classification results and feedback regulation information, determines real described in user
When the corresponding feedback regulation information of behavior characteristic information, send the feedback regulation information in real time to user.
In embodiments herein, when programmer pours out the difficulty oneself faced, during acquiring this in real time
The behavior characteristic information of programmer, wherein behavior characteristic information mainly includes the first voice messaging of voice acquisition device acquisition,
The voice messaging is the speech content for the programmer that voice device acquires in time, comprising: specific word content, sound decibel
Deng.Simultaneously in order to realize the current emotional and psychological characteristics that more accurately determine programmer, photographic device can also be passed through
Acquire the image information of face feature and/or limb action of the user during pouring out.Further, user can also be obtained
Characteristic information, this feature information includes the personal preference etc. of user, when user enters system, based on user input individual
The personal preference etc. of acquisition of information user.It can also be obtained and be used based on block chain technology after subscriber identity information has been determined
The personal preference at family.Collected user behavior characteristics information is pre-processed, to obtain key message.For example, for the
One voice messaging can be denoised to voice messaging by lamprophonia rule, avoid the semanteme of influence of noise voice, together
When can also be to avoid the decibel of influence of noise voice.The image information of face feature and/or limb action for user can incite somebody to action
The continuous part frame of acquisition or the image for being spaced frame carry out the noise of image preprocessing removal image, obtain user's face feature
The main frame image of variation of variation and/or limb action, as key message.Like for individual subscriber, due to getting
User information may have more label or text, in order to more accurate determination user hobby so that be convenient for
The psychological characteristics that user is determined based on the hobby, by content deletion burdensome in label or text or the text unrelated with hobby
It deletes, obtains the key message of individual subscriber hobby.On the basis of above-mentioned, in order to determine user psychological characteristics or
Psychological characteristics obtains default behavioural characteristic classifying rules, and optionally, the default behavioural characteristic classifying rules includes being based on error
The multilayer feedforward neural network (BP neural network) of backpropagation algorithm training.Classified based on key message and default behavioural characteristic
Rule classifies to the psychological characteristics of user, obtains psychological classification results.Optionally, BP neural network is used in the application,
The main frame of voice key information above-mentioned, personal preference key message, face feature and/or limb action changing features is defeated
Enter BP neural network, by the calculating of BP neural network, the psychological classification results of user is obtained, specifically, personal preference is crucial
The main frame of information, face feature and/or limb action changing features can also not have to input neural network, pass through preset feelings
Thread recognition rule determines the mood of user, and the mood and voice messaging classification results are compared, and various features combine altogether
With the psychological characteristics for determining user, the accuracy of user psychology tagsort is improved.BP algorithm is exactly with network error square
For objective function, using gradient descent method come the minimum value of calculating target function, which can be determined as the psychology of user
Classification results.During user pours out, in order to timely solve the psychological problems of user, the psychology pressure of user is relieved
Power, the psychological classification results based on user, to the real-time feedback regulation information of user, which includes text information
With one of voice messaging or two kinds.Wherein, psychological classification results and when feedback regulation information, are deposited with incidence relation
Storage, after determining psychological classification results, then feedback associated with the classification results can be searched based on the classification results
Information is adjusted, and the feedback regulation information is sent to user, in order to solve the psychological problems of user.For example, based on key
Information determines that user has Depressive, judges the grade of user's Depressive (in such as slightly, in conjunction with key message above-mentioned
Degree, severe etc.), slightly associated feedback regulation information includes: to listen easily that (program can be with base for music with the Depressive
The music that user likes type is obtained by network in the hobby of user, and segment or whole can be carried out based on the selection of user
The broadcasting of song), be proposed to be used in the direction of diet, and enumerate part fruits and vegetables etc.；Incentive message etc. is sent to user.Before
The process of stating can also be applied to the process that other psychological classification results determine feedback regulation information, can be obtained by user preferences
Specific feedback regulation information is simultaneously sent to user, such as aforementioned music, dietary recommendations continued, allows users to be easier to connect
Feedback regulation information above-mentioned is received, realizes the purpose for relieving user psychology pressure.
Optionally, in a kind of wherein embodiment, as shown in Fig. 2, described carry out the real-time behavior characteristic information
Pretreatment obtains key message, comprising: S110 and S120.
S110: cleaning first voice messaging based on default voice messaging cleaning rule, obtains the second voice
Information；
S120: second voice messaging is handled according to mel cepstrum coefficients operation rule, obtains the key
Information.
It is capable of the parameter of dialectical mood due to enough having contained in voice messaging, is closed so carrying out processing to voice messaging
Before key information, needs to carry out pre-processing to collected voice messaging, reduce calculation amount, improve the accurate of Emotion identification
Property.In embodiments herein, in conjunction with process above-mentioned, the mistake that pretreatment obtains key message is carried out to the first voice messaging
Cheng Zhong, in order to make the content of voice messaging more coherent accurate, first by default voice messaging cleaning rule to the
One voice messaging is cleaned, to obtain the second voice messaging.Default voice messaging cleaning rule includes carrying out to voice messaging
Quantization, then the voice messaging such as denoises by preemphasis, adding window, framing etc..Specifically, treatment process is voice messaging
After incoming, it is based on preset period and frequency abstraction voice messaging.And the variation based on voltage value when sampling, voice is believed
Breath is quantified, and such as several sections is divided by the amplitude peak of entire voltage change, the sample sampled for falling in certain section
Performance number returns into one kind, and provides corresponding quantized value.Preemphasis processing is carried out to the voice messaging in same class later, removes language
Noise in message breath is handled the speech message after removal noise by preset function, and carry out endpoint later
Detection, to obtain sectional continuous whole speech message.
After obtaining the second voice messaging by aforementioned process, the second voice is believed by mel cepstrum coefficients operation rule
Breath is handled to obtain key message, wherein mel cepstrum coefficients (Mel-scale Frequency Cepstral
Coefficients, abbreviation MFCC) it is the cepstrum parameter extracted in Mel scale frequency domain.Second voice messaging is passed through
Square of spectrum amplitude is sought in Fast Fourier Transform (FFT) later, is calculated by Mel frequency filter group and Log logarithmic energy
And DCT asks cepstrum to obtain MFCC, detailed process can be indicated by following form:
Log X [k]=log (Mel-Spectrum).
Cepstral analysis is carried out on log X [k]:
1) logarithm is taken: log X [k]=log H [k]+log E [k].
2) inverse transformation: x [k]=h [k]+e [k] is carried out.
Mel frequency cepstral coefficient, abbreviation MFCC are known as in the previously obtained cepstrum coefficient h [k] of Mel frequency spectrum.It can obtain
The key message of the second voice messaging into the embodiment of the present application.
Optionally, it is described based on the default behavioural characteristic classifying rules and the key message to user psychology feature into
Row classification, comprising:
According to the key message and it is described based on error backpropagation algorithm training multilayer feedforward neural network to
Family psychological characteristics is classified.
It,, will in order to be accurately determined the psychological characteristics of user after determining key message on the basis of above-mentioned
Key message inputs BP neural network, i.e., inputs key message in input layer, true in output layer by the calculating of BP neural network
Determine the psychological characteristics of user.In BP neural network, it need to be calculated by successive ignition, so that the error calculated is lower, psychology
Tagsort result is more accurate, is detailed in and is explained later.
Optionally, it is described based on the default behavioural characteristic classifying rules and the key message to user psychology feature into
Row classification, comprising:
Optimize the default behavioural characteristic classifying rules according to the psychological classification results；
Based on after optimization the default behavioural characteristic classifying rules and the key message determine that the user psychology is special
The classification of sign.
During calculating classification based on key message and BP neural network, mel-frequency cepstrum system is inputted in input layer
Number (Mel frequency cepstral coefficient) is simultaneously calculated, and the error of the result adjustment classification results based on calculating is based on the error transfer factor
Classified calculating result threshold value realizes the optimization to default behavioural characteristic classifying rules.Optimization complete and then it is secondary in input layer
Input mel-frequency cepstrum coefficient (Mel frequency cepstral coefficient) is simultaneously calculated, and the psychological characteristics classification results of user are obtained.It is logical
It is calculated again after first optimization behavioural characteristic classifying rules, so that the calculated minimum value of BP neural network is smaller, psychological characteristics
Classification results it is more accurate, reduce and calculate error, improve the accuracy rate of calculating.
Optionally, described in the default behavioural characteristic classifying rules based on after optimization and the key message determine
After the classification of user psychology feature, comprising:
The classification of the default behavioural characteristic classifying rules after optimization is determined according to the classification of the user psychology feature
Error；
The error in classification is judged whether within default error threshold, if so, the classification of the user psychology feature
It is determined as the psychological classification results；
If it is not, then based on the default behavioural characteristic classifying rules and the key message again to user psychology feature into
Row classification.
On the basis of above-mentioned, in order to ensure the accuracy of calculated result, the result based on aforesaid class feature is (i.e. psychological
The classification of feature) error of the result, the i.e. error in classification of the application are calculated, the error and preset error threshold are carried out pair
Than judging that error in classification whether within the error threshold, that is, determines whether to meet required precision, when error in classification is in the error
Within threshold value, then the classification results of user psychology feature above-mentioned can be determined as psychological classification results above-mentioned.When classification misses
When difference is not within the error threshold, in order to improve the precision of calculating, judge that BP neural network obtains changing for this calculated result
Whether reach the upper limit for calculation times, if reaching iterative calculation maximum number of times, illustrates that this calculated result meets the requirements；If not
Reach the upper limit of iterative calculation number, then in order to guarantee calculated result accuracy, repeats to determine user mentioned by key message
The calculating process of psychological characteristics classification optimizes behavioural characteristic classifying rules at this and calculates classification results.
It is optionally, described to obtain default behavioural characteristic classifying rules, comprising:
Key message and its classification of sample of users are obtained based on block chain technology；
Key message and its classification using sample of users, based on error backpropagation algorithm training multilayer feedforward nerve net
Network；
The multilayer feedforward neural network is used to characterize the incidence relation of key message and classification.
It,, can be in order to guarantee the accuracy of default behavior classifying rules in embodiments herein in conjunction with aforementioned process
Multistage voice messaging according to active user optimizes calculating to default behavioural characteristic classifying rules, guarantees default behavior classification
The accuracy of rule；Behavior characteristic information classifying rules can also be optimized in conjunction with each user used record.
In order to effectively utilize big data, the key message of other users can also be obtained by block chain technology, and is based on the key
Information optimizes behavioural characteristic classifying rules, the precision of default behavior classifying rules is improved, in implementation provided by the present application
In example, it can be combined with error backpropagation algorithm above-mentioned and determine default behavioural characteristic classifying rules above-mentioned, due to acquisition
Sample data it is more so that obtain behavioural characteristic classification it is more accurate, be also convenient for the result based on classification and provide a user
More accurate feedback regulation information achievees the purpose that adjusting so that user is easier to receive feedback information.In addition, aforementioned
On the basis of, in order to enable training pattern is more accurate, it is described send the feedback regulation information in real time to user after, also wrap
It includes: the real-time behavior characteristic information after preset time period, after acquisition user's adjusting；The real-time behavior for comparing the user is special
Reference breath and the real-time behavior characteristic information after user adjusting, obtain the regulating effect to the user.Regulating effect compared with
When poor, convenient for automatically further being corrected to behavior classifying rules based on the regulating effect, while can also be by the tune
Section effect is researched and developed as research staff or the foundation of recovery actions tagsort rule.
The embodiment of the invention also provides a kind of assessment of psychological condition and regulating devices, in a kind of wherein embodiment,
As shown in Figure 3, comprising: acquisition module 100, analysis module 200, feedback module 300.
Acquisition module 100 carries out the real-time behavior characteristic information for acquiring the real-time behavior characteristic information of user
Pretreatment obtains key message, and the real-time behavior characteristic information includes the first voice messaging；
Analysis module 200 is based on the default behavioural characteristic classifying rules for obtaining default behavioural characteristic classifying rules
Classify with the key message to user psychology feature, obtains psychological classification results；
Feedback module 300, for determining based on the incidence relation between default psychological classification results and feedback regulation information
The corresponding feedback regulation information of real-time behavior characteristic information described in user sends the feedback regulation letter to user in real time
Breath.
Further, as shown in figure 3, a kind of psychological condition assessment provided in the embodiment of the present invention and regulating device are also wrapped
Include: cleaning unit 110 obtains for cleaning based on default voice messaging cleaning rule to first voice messaging
Two voice messagings；Voice key information obtaining unit 120, for foundation mel cepstrum coefficients operation rule to second voice
Information is handled, and the key message is obtained.Behavior characteristic information taxon 210, for according to the key message and
The multilayer feedforward neural network based on the training of error backpropagation algorithm classifies to user psychology feature.Optimize unit
220, for optimizing the default behavioural characteristic classifying rules according to the psychological classification results；Psychological characteristics classification determination unit
230, for based on after optimization the default behavioural characteristic classifying rules and the key message determine that the user psychology is special
The classification of sign.Error in classification determination unit 240, it is described pre- after optimizing for being determined according to the classification of the user psychology feature
If the error in classification of behavioural characteristic classifying rules；Judging unit 250, for judging the error in classification whether in default error threshold
Within value, if so, the classification of the user psychology feature is determined as the psychological classification results；Unit 260 is reseted, if for
It is no, then classified again to user psychology feature based on the default behavioural characteristic classifying rules and the key message.It closes
Key information acquiring unit 130, for obtaining key message and its classification of sample of users based on block chain technology；Training unit
140, for using key message and its classification of sample of users, based on error backpropagation algorithm training multilayer feedforward nerve net
Network；The multilayer feedforward neural network is used to characterize the incidence relation of key message and classification.
Above-mentioned psychological condition assessment may be implemented in a kind of psychological condition assessment provided in an embodiment of the present invention and regulating device
And the embodiment of adjusting method, concrete function realize the explanation referred in embodiment of the method, details are not described herein.
A kind of computer readable storage medium provided in an embodiment of the present invention stores on the computer readable storage medium
There is computer program, psychological condition assessment and adjusting side described in any one technical solution are realized when which is executed by processor
Method.Wherein, the computer readable storage medium includes but is not limited to any kind of disk (including floppy disk, hard disk, CD, CD-
ROM and magneto-optic disk), ROM (Read-Only Memory, read-only memory), RAM (Random AcceSS Memory, immediately
Memory), EPROM (EraSable Programmable Read-Only Memory, Erarable Programmable Read only Memory),
(Electrically EraSable Programmable Read-Only Memory, electric erazable programmable is read-only to be deposited EEPROM
Reservoir), flash memory, magnetic card or light card.It is, storage equipment includes by equipment (for example, computer, mobile phone) with energy
Any medium for the form storage or transmission information enough read can be read-only memory, disk or CD etc..
A kind of computer readable storage medium provided in an embodiment of the present invention is, it can be achieved that the assessment of above-mentioned psychological condition and adjusting
The embodiment of method, in this application by being acquired to user behavior characteristics information and timely analyzing, in order to determination
The psychological characteristics classification of user, and feedback regulation information is sent based on category phase user, realization relaxes to user psychology pressure
Solution, and process user can carry out when alone, ensure that the privacy of user；It is provided by the embodiments of the present application
A kind of assessment of psychological condition and adjusting method, comprising: the real-time behavior characteristic information for acquiring user, to the real-time behavioural characteristic
Information carries out pretreatment and obtains key message, and the real-time behavior characteristic information includes the first voice messaging；Obtain default behavior
Tagsort rule, divides user psychology feature based on the default behavioural characteristic classifying rules and the key message
Class obtains psychological classification results；Based on the incidence relation between default psychological classification results and feedback regulation information, user is determined
The corresponding feedback regulation information of the real-time behavior characteristic information, the feedback regulation information is sent to user in real time.?
In embodiments herein, when programmer pours out the difficulty oneself faced, the row of the programmer during this is acquired in real time
It is characterized information, wherein behavior characteristic information mainly includes the first voice messaging of voice acquisition device acquisition, the voice messaging
The as speech content of programmer that acquires in time of voice device, comprising: specific word content, sound decibel etc..It is simultaneously
It realizes the current emotional and psychological characteristics for more accurately determining programmer, user can also be acquired by photographic device and existed
The image information of face feature and/or limb action during pouring out.Further, the feature letter of user can also be obtained
Breath, this feature information includes the personal preference etc. of user, and when user enters system, the personal information based on user's input is obtained
The personal preference etc. of user can also obtain the individual of user based on block chain technology after subscriber identity information has been determined
Hobby.Optionally, the application becomes voice key information, personal preference key message, face feature and/or limb action feature
Change main frame calculated, obtain the psychological classification results of user, specifically, personal preference key message, face feature and/
Or the main frame of limb action changing features can also determine the mood of user by preset Emotion identification rule, and by the feelings
Thread is compared with voice messaging classification results, and various features combine the common psychological characteristics for determining user, improves user's heart
Manage the accuracy of tagsort.During user pours out, in order to timely solve the psychological problems of user, use is relieved
The psychological pressure at family, the psychological classification results based on user, to the real-time feedback regulation information of user, wherein psychological classification results
With stored when feedback regulation information with incidence relation, after determining psychological classification results, then can be based on the classification
As a result feedback regulation information associated with the classification results is searched, and the feedback regulation information is sent to user, in order to
The psychological problems for solving user can be combined with user preferences and obtain specific feedback regulation information and be sent to user, in turn
User can more receive aforementioned feedback and adjust information, realize the purpose meter provided in an embodiment of the present invention for relieving user psychology pressure
The embodiment of above-mentioned psychological condition assessment and adjusting method may be implemented in calculation machine readable storage medium storing program for executing, and concrete function realization refers to
Explanation in embodiment of the method, details are not described herein.
In addition, the present invention also provides a kind of servers, as shown in figure 4, the server process in another embodiment
The devices such as device 503, memory 505, input unit 507 and display unit 509.It will be understood by those skilled in the art that Fig. 4 shows
Structure devices out do not constitute the restriction to Servers-all, may include than illustrating more or fewer components or group
Close certain components.Memory 505 can be used for storing application program 501 and each functional module, and the operation of processor 503 is stored in
The application program 501 of reservoir 505, thereby executing the various function application and data processing of equipment.Memory 505 can be interior
Memory or external memory, or including both built-in storage and external memory.Built-in storage may include read-only memory
(ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash
Device or random access memory.External memory may include hard disk, floppy disk, ZIP disk, USB flash disk, tape etc..It is disclosed in this invention to deposit
Reservoir includes but is not limited to the memory of these types.Memory 505 disclosed in this invention is only used as example rather than as limit
It is fixed.
Input unit 507 is used to receive the input and user's input behavior characteristic information and/or personal information of signal.
Input unit 507 may include touch panel and other input equipments.Touch panel collects the touching of client on it or nearby
Touching operation, (for example client is attached on touch panel or in touch panel using any suitable object or attachment such as finger, stylus
Close operation), and corresponding attachment device is driven according to a pre-set procedure；Other input equipments can include but is not limited to
One of physical keyboard, function key (such as broadcasting control button, switch key etc.), trace ball, mouse, operating stick etc. are more
Kind.Display unit 509 can be used for showing client input information or be supplied to client information and computer equipment it is various
Menu.The forms such as liquid crystal display, Organic Light Emitting Diode can be used in display unit 509.Processor 503 is computer equipment
Control centre is stored in memory by running or executing using the various pieces of various interfaces and the entire computer of connection
Software program and/or module in 503, and the data being stored in memory are called, perform various functions and handle data.
One or more processors 503 shown in Fig. 4 are able to carry out, realize the function of acquisition module 100 shown in Fig. 3, analysis
The function of the function of module 200, the function of feedback module 300, the function of cleaning unit 110, voice key information obtaining unit 120
Can, the function of behavior characteristic information taxon 210, the function of optimizing unit 220, psychological characteristics classification determination unit 230
Function, the function of error in classification determination unit 240, the function of judging unit 250, the function of reseting unit 260, key message obtain
Take the function of unit 130, the function of training unit 140.
In one embodiment, the server includes one or more processors 503, and one or more storages
Device 505, one or more application program 501, wherein one or more of application programs 501 are stored in memory 505
And be configured as being executed by one or more of processors 503, one or more of application programs 301 are configured to carry out
The assessment of psychological condition described in above embodiments and adjusting method.
A kind of server provided in an embodiment of the present invention is, it can be achieved that the assessment of above-mentioned psychological condition and the implementation of adjusting method
Example, in this application by being acquired to user behavior characteristics information and timely analyzing, in order to determine the psychology of user
Feature classification, and feedback regulation information is sent based on category phase user, realization relieves user psychology pressure, and the process
User can carry out when alone, ensure that the privacy of user；A kind of psychological shape provided by the embodiments of the present application
State assessment and adjusting method, comprising: the real-time behavior characteristic information for acquiring user carries out the real-time behavior characteristic information pre-
Processing obtains key message, and the real-time behavior characteristic information includes the first voice messaging；Obtain default behavioural characteristic classification gauge
Then, classified based on the default behavioural characteristic classifying rules and the key message to user psychology feature, obtain psychology
Classification results；Based on the incidence relation between default psychological classification results and feedback regulation information, real-time row described in user is determined
It is characterized the corresponding feedback regulation information of information, sends the feedback regulation information in real time to user.In the reality of the application
It applies in example, when programmer pours out the difficulty oneself faced, acquires the behavior characteristic information of the programmer during this in real time,
Wherein behavior characteristic information mainly includes the first voice messaging of voice acquisition device acquisition, which is voice device
The speech content of the programmer acquired in time, comprising: specific word content, sound decibel etc..It is more smart in order to realize simultaneously
The current emotional and psychological characteristics of programmer are determined quasi-ly, and user can also be acquired by photographic device during pouring out
The image information of face feature and/or limb action.Further, the characteristic information of user, this feature information can also be obtained
Personal preference etc. including user, when user enters system, the personal information based on user's input obtains the personal happiness of user
OK etc., the personal preference of user can also be obtained based on block chain technology after subscriber identity information has been determined.Optionally,
The application by the main frame of voice key information, personal preference key message, face feature and/or limb action changing features into
Row calculates, and obtains the psychological classification results of user, specifically, personal preference key message, face feature and/or limb action are special
The main frame of sign variation can also determine the mood of user by preset Emotion identification rule, and by the mood and voice messaging
Classification results compare, and various features combine the common psychological characteristics for determining user, improve user psychology tagsort
Accuracy.During user pours out, in order to timely solve the psychological problems of user, the psychology pressure of user is relieved
Power, the psychological classification results based on user, to the real-time feedback regulation information of user, wherein psychological classification results and feedback regulation
Stored when information with incidence relation, after determining psychological classification results, then can be searched based on the classification results with
The associated feedback regulation information of the classification results, and the feedback regulation information is sent to user, in order to solve user's
Psychological problems can be combined with user preferences and obtain specific feedback regulation information and be sent to user, and then user more can
It receives aforementioned feedback and adjusts information, realize the purpose for relieving user psychology pressure.
The psychological condition assessment and the reality of adjusting method of above-mentioned offer may be implemented in server provided in an embodiment of the present invention
Example is applied, concrete function realizes the explanation referred in embodiment of the method, and details are not described herein.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of psychological condition assessment and adjusting method characterized by comprising
The real-time behavior characteristic information for acquiring user carries out pretreatment to the real-time behavior characteristic information and obtains key message,
The real-time behavior characteristic information includes the first voice messaging；
Default behavioural characteristic classifying rules is obtained, based on the default behavioural characteristic classifying rules and the key message to user
Psychological characteristics is classified, and psychological classification results are obtained；
Based on the incidence relation between default psychological classification results and feedback regulation information, real-time behavioural characteristic described in user is determined
The corresponding feedback regulation information of information, the feedback regulation information is sent to user in real time.
2. psychological condition assessment according to claim 1 and adjusting method, which is characterized in that the default behavioural characteristic point
Rule-like includes the multilayer feedforward neural network based on the training of error backpropagation algorithm.
3. psychological condition assessment according to claim 2 and adjusting method, which is characterized in that described to the real-time behavior
Characteristic information carries out pretreatment and obtains key message, comprising:
First voice messaging is cleaned based on default voice messaging cleaning rule, obtains the second voice messaging；
Second voice messaging is handled according to mel cepstrum coefficients operation rule, obtains the key message.
4. psychological condition assessment according to claim 3 and adjusting method, which is characterized in that described to be based on the default row
It is characterized classifying rules and the key message classifies to user psychology feature, comprising:
According to the key message and the multilayer feedforward neural network based on the training of error backpropagation algorithm to user's heart
Reason feature is classified.
5. psychological condition assessment according to any one of claims 1 to 4 and adjusting method, which is characterized in that described to be based on
The default behavioural characteristic classifying rules and the key message classify to user psychology feature, comprising:
Optimize the default behavioural characteristic classifying rules according to the psychological classification results；
Based on after optimization the default behavioural characteristic classifying rules and the key message determine the user psychology feature
Classification.
6. psychological condition assessment according to claim 5 and adjusting method, which is characterized in that the institute based on after optimization
State default behavioural characteristic classifying rules and after the key message determines the classification of the user psychology feature, comprising:
The error in classification of the default behavioural characteristic classifying rules after optimization is determined according to the classification of the user psychology feature；
The error in classification is judged whether within default error threshold, if so, the classification of the user psychology feature determines
For the psychological classification results；
If it is not, then being divided again user psychology feature based on the default behavioural characteristic classifying rules and the key message
Class.
7. psychological condition assessment according to claim 2 and adjusting method, which is characterized in that described to obtain default behavior spy
Levy classifying rules, comprising:
Key message and its classification of sample of users are obtained based on block chain technology；
Key message and its classification using sample of users, based on error backpropagation algorithm training multilayer feedforward nerve net
Network；
The multilayer feedforward neural network is used to characterize the incidence relation of key message and classification.
8. a kind of psychological condition assessment and regulating device characterized by comprising
Acquisition module pre-processes the real-time behavior characteristic information for acquiring the real-time behavior characteristic information of user
Key message is obtained, the real-time behavior characteristic information includes the first voice messaging；
Analysis module, for obtaining default behavioural characteristic classifying rules, based on the default behavioural characteristic classifying rules and described
Key message classifies to user psychology feature, obtains psychological classification results；
Feedback module, for determining user institute based on the incidence relation between default psychological classification results and feedback regulation information
The corresponding feedback regulation information of real-time behavior characteristic information is stated, sends the feedback regulation information in real time to user.
9. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the described in any item psychological condition assessments of claim 1 to 7 and adjusting method when the program is executed by processor.
10. a kind of server characterized by comprising
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors, one or more of application programs are configured to carry out according to claim 1
To the step of 7 described in any item psychological condition assessments and adjusting method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811348241.XA CN109493885A (en) | 2018-11-13 | 2018-11-13 | Psychological condition assessment and adjusting method, device and storage medium, server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811348241.XA CN109493885A (en) | 2018-11-13 | 2018-11-13 | Psychological condition assessment and adjusting method, device and storage medium, server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109493885A true CN109493885A (en) | 2019-03-19 |
Family
ID=65695682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811348241.XA Pending CN109493885A (en) | 2018-11-13 | 2018-11-13 | Psychological condition assessment and adjusting method, device and storage medium, server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109493885A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751950A (en) * | 2019-10-25 | 2020-02-04 | 武汉森哲地球空间信息技术有限公司 | Police conversation voice recognition method and system based on big data |
| CN110767290A (en) * | 2019-10-12 | 2020-02-07 | 山东省立医院 | Interactive emotion persuasion and psychological counseling robot |
| CN111312282A (en) * | 2020-02-18 | 2020-06-19 | 北京声智科技有限公司 | Health state determination method and device based on voice information |
| CN111326234A (en) * | 2020-01-21 | 2020-06-23 | 浙江连信科技有限公司 | Psychological puzzle scene matching method and device based on deep learning algorithm |
| CN111599472A (en) * | 2020-05-14 | 2020-08-28 | 重庆大学 | Method and device for recognizing psychological states of students and computer |
| CN112071386A (en) * | 2020-08-19 | 2020-12-11 | 深圳市医贝科技有限公司 | Active mental health early warning method and system |
| CN116578731A (en) * | 2023-07-05 | 2023-08-11 | 之江实验室 | Multimedia information processing method, system, computer device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715129A (en) * | 2013-12-13 | 2015-06-17 | 中国科学院心理研究所 | Mental health state assessment system and method based on mobile equipment using behavior |
| CN106528538A (en) * | 2016-12-07 | 2017-03-22 | 竹间智能科技（上海）有限公司 | Method and device for intelligent emotion recognition |
| CN107003997A (en) * | 2014-12-04 | 2017-08-01 | 微软技术许可有限责任公司 | Type of emotion for dialog interaction system is classified |
| CN107066514A (en) * | 2017-01-23 | 2017-08-18 | 深圳亲友科技有限公司 | The Emotion identification method and system of the elderly |
| CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
| CN108095740A (en) * | 2017-12-20 | 2018-06-01 | 姜涵予 | A kind of user emotion appraisal procedure and device |
| WO2018151628A1 (en) * | 2017-02-17 | 2018-08-23 | Георгий Игоревич ПЛИЕВ | Algorithm for complex remote non-contact multichannel analysis of a psycho-emotional and physiological condition of a subject from audio and video content |
| CN108629313A (en) * | 2018-05-04 | 2018-10-09 | 河北省科学院应用数学研究所 | Emotion adjustment method, device, system and computer storage media |
| CN108734096A (en) * | 2018-04-11 | 2018-11-02 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and the device for data processing |
-
2018
- 2018-11-13 CN CN201811348241.XA patent/CN109493885A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715129A (en) * | 2013-12-13 | 2015-06-17 | 中国科学院心理研究所 | Mental health state assessment system and method based on mobile equipment using behavior |
| CN107003997A (en) * | 2014-12-04 | 2017-08-01 | 微软技术许可有限责任公司 | Type of emotion for dialog interaction system is classified |
| CN106528538A (en) * | 2016-12-07 | 2017-03-22 | 竹间智能科技（上海）有限公司 | Method and device for intelligent emotion recognition |
| CN107066514A (en) * | 2017-01-23 | 2017-08-18 | 深圳亲友科技有限公司 | The Emotion identification method and system of the elderly |
| WO2018151628A1 (en) * | 2017-02-17 | 2018-08-23 | Георгий Игоревич ПЛИЕВ | Algorithm for complex remote non-contact multichannel analysis of a psycho-emotional and physiological condition of a subject from audio and video content |
| CN107799165A (en) * | 2017-09-18 | 2018-03-13 | 华南理工大学 | A kind of psychological assessment method based on virtual reality technology |
| CN108095740A (en) * | 2017-12-20 | 2018-06-01 | 姜涵予 | A kind of user emotion appraisal procedure and device |
| CN108734096A (en) * | 2018-04-11 | 2018-11-02 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and the device for data processing |
| CN108629313A (en) * | 2018-05-04 | 2018-10-09 | 河北省科学院应用数学研究所 | Emotion adjustment method, device, system and computer storage media |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110767290A (en) * | 2019-10-12 | 2020-02-07 | 山东省立医院 | Interactive emotion persuasion and psychological counseling robot |
| CN110751950A (en) * | 2019-10-25 | 2020-02-04 | 武汉森哲地球空间信息技术有限公司 | Police conversation voice recognition method and system based on big data |
| CN111326234A (en) * | 2020-01-21 | 2020-06-23 | 浙江连信科技有限公司 | Psychological puzzle scene matching method and device based on deep learning algorithm |
| CN111312282A (en) * | 2020-02-18 | 2020-06-19 | 北京声智科技有限公司 | Health state determination method and device based on voice information |
| CN111599472A (en) * | 2020-05-14 | 2020-08-28 | 重庆大学 | Method and device for recognizing psychological states of students and computer |
| CN111599472B (en) * | 2020-05-14 | 2023-10-24 | 重庆大学 | Method and device for identifying psychological state of student and computer |
| CN112071386A (en) * | 2020-08-19 | 2020-12-11 | 深圳市医贝科技有限公司 | Active mental health early warning method and system |
| CN116578731A (en) * | 2023-07-05 | 2023-08-11 | 之江实验室 | Multimedia information processing method, system, computer device and storage medium |
| CN116578731B (en) * | 2023-07-05 | 2023-09-29 | 之江实验室 | Multimedia information processing method, system, computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109493885A (en) | Psychological condition assessment and adjusting method, device and storage medium, server | |
| Lauraitis et al. | Detection of speech impairments using cepstrum, auditory spectrogram and wavelet time scattering domain features | |
| Pawar et al. | Convolution neural network based automatic speech emotion recognition using Mel-frequency Cepstrum coefficients | |
| CN108197115A (en) | Intelligent interactive method, device, computer equipment and computer readable storage medium | |
| US20140052448A1 (en) | System and method for recognizing emotional state from a speech signal | |
| Benba et al. | Voice assessments for detecting patients with Parkinson’s diseases using PCA and NPCA | |
| CN110070888A (en) | A kind of Parkinson's audio recognition method based on convolutional neural networks | |
| EP2862169A2 (en) | Cepstral separation difference | |
| CN109584904A (en) | The sightsinging audio roll call for singing education applied to root LeEco identifies modeling method | |
| Usman et al. | Heart rate detection and classification from speech spectral features using machine learning | |
| Soumaya et al. | A hybrid method for the diagnosis and classifying parkinson's patients based on time–frequency domain properties and K-nearest neighbor | |
| CN110136726A (en) | A kind of estimation method, device, system and the storage medium of voice gender | |
| Thirumuru et al. | Novel feature representation using single frequency filtering and nonlinear energy operator for speech emotion recognition | |
| Fernandes et al. | Speech emotion recognition using mel frequency cepstral coefficient and SVM classifier | |
| Benba et al. | Voice assessments for detecting patients with neurological diseases using PCA and NPCA | |
| Kumar et al. | Speech emotion recognition using CNN-LSTM and vision transformer | |
| Sandulescu et al. | Mobile app for stress monitoring using voice features | |
| CN116687410B (en) | Method and system for evaluating dysfunctions of chronic patients | |
| Usman et al. | Dataset of raw and pre-processed speech signals, Mel Frequency Cepstral Coefficients of Speech and Heart Rate measurements | |
| Natarajan et al. | Longitudinal investigation of work stressors using human voice features | |
| Nirjon et al. | sMFCC: exploiting sparseness in speech for fast acoustic feature extraction on mobile devices--a feasibility study | |
| Muhammad et al. | Spectro-temporal directional derivative based automatic speech recognition for a serious game scenario | |
| CN116486840A (en) | Depression automatic evaluation system based on natural voice | |
| Akinrinmade et al. | Creation of a Nigerian voice corpus for indigenous speaker recognition | |
| Upadhya et al. | Multitaper perceptual linear prediction features of voice samples to discriminate healthy persons from early stage Parkinson diseased persons |
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 |