CN109472354A - A kind of sentiment analysis model and its training method - Google Patents
A kind of sentiment analysis model and its training method Download PDFInfo
- Publication number
- CN109472354A CN109472354A CN201811614564.9A CN201811614564A CN109472354A CN 109472354 A CN109472354 A CN 109472354A CN 201811614564 A CN201811614564 A CN 201811614564A CN 109472354 A CN109472354 A CN 109472354A
- Authority
- CN
- China
- Prior art keywords
- layer
- node
- reciprocation
- neuron
- training set
- 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.)
- Withdrawn
Links
Classifications
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
- G06N3/065—Analogue means
-
- 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
- A61B5/72—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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Molecular Biology (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Animal Behavior & Ethology (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Heart & Thoracic Surgery (AREA)
- Computational Linguistics (AREA)
- Veterinary Medicine (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- Surgery (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Social Psychology (AREA)
- Developmental Disabilities (AREA)
- Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Educational Technology (AREA)
- Child & Adolescent Psychology (AREA)
- Fuzzy Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Neurology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention provides a kind of sentiment analysis model and its training method, the sentiment analysis model includes receiving layer, reciprocation layer and output layer.The receiving layer is made of multiple input nodes, and the reciprocation layer is made of multiple interactive neuron nodes.Each input node is connect with all interaction neuron nodes.Inside reciprocation layer, adjacent neurons node is connected with each other.The present invention can be used in the acquisition of the automation for user emotion state, does not need excessive manual operation, can control the emotional state of client user at any time.
Description
Technical field
The present invention relates to intelligent medical field more particularly to a kind of sentiment analysis model and its training methods.
Background technique
Intelligent wearable device application wearable technology carries out intelligentized design to daily wearing, develops and can dress
The general name of equipment, such as wrist-watch, bracelet, glasses, dress ornament.Wearable intelligent equipment possesses the developing history of many years, thought and young bird
Shape has occurred in the 1960s, and the equipment for having wearable smart machine form then occurs in the 70-80 age.
The physiologic information of user more preferably more can be easily perceived by intelligent wearable device, but in the prior art but can not be effective
Acquisition user emotional state.
Research report shows that the emotional state of user and the physical condition of user have important relationship, therefore, how base
Achieve the purpose that concern user emotion state is current urgent problem to be solved at any time in the intelligent wearable device of modernization.
In addition, physiological parameter is related to privacy of user, therefore, the data interactive method that there is a need to research and develop high security is to reach
To the purpose of maintenance privacy of user.
Summary of the invention
In order to solve the above-mentioned technical problem, the invention proposes a kind of sentiment analysis model and its training methods.The present invention
Specifically realized with following technical solution:
A kind of sentiment analysis model, the sentiment analysis model include receiving layer, reciprocation layer and output layer.It is described to connect
Layer of receiving is made of multiple input nodes, and the reciprocation layer is made of multiple interactive neuron nodes.Each input node is equal
It is connect with all interaction neuron nodes.Inside reciprocation layer, adjacent neurons node is connected with each other.
A kind of sentiment analysis model training method, the above-mentioned sentiment analysis model of the training method, which comprises
Obtain training set X={ x1, x2..., xk..., xN, the sum of the training set is N, wherein every in training set
A element is all a P n dimensional vector n, and each element corresponds to a kind of physiological parameter, the member of each training set in the P n dimensional vector n
Element corresponds to a mood vector；
Each neuron node in the reciprocation layer is numbered, and each neuron node is one corresponding
P dimensional weight vector ωi={ ωi1, xi2..., xik..., xip}；
P dimensional weight vector corresponding to each neuron node assigns initial value；
Element in the training set is sequentially input into the reciprocation layer, to obtain the cluster knot to the training set
Fruit, and the weight of the neuron node in the reciprocation layer is modified in cluster process；In the cluster result
Element with identical output node is polymerized to one kind；
Analytical calculation cluster centre and the corresponding mood vector of cluster centre are carried out to each cluster result.
Further, during the element in the training set is sequentially input the reciprocation layer, the friendship
Interaction layer executes following logics:
Wherein uiFor each neuron node
It exports, wherein λiFor the adjustment frequency of the P dimensional weight vector of i-th of node, xkFor the element in training set, c is neuron node
Total quantity, wherein output valve be 1 neuron node be the corresponding output node of the training set element.
Further, the adjustment frequency is according to formula meterIt calculates and obtains, miIn be neuron node P right-safeguarding
The adjustment number of weight vector, c are the total quantity of neuron node.
Further, further includes:
After the neuron output of single, it can take advantage of a situation and the P dimensional weight vector of each neuron node is adjusted, adjust
Whole formula isWherein αi,βiRespectively learning rate and forgetting rate, can be according to actual needs
It is set, but it must be ensured that αi>0,βi<0。
Further, further includes:
The physiological parameter includes that eeg wave just analyzes result, heart rate, pulse, skin temperature, blood pressure, blood oxygen saturation
Degree, blood volume beating, palm sweat, respiratory intensity or respiratory rate；It includes α wave, β wave and θ wave that the electroencephalogram, which just analyzes result,
The frequency of occurrences；
There are multiple elements in the mood vector, each element corresponds to a kind of mood, and the value of element represents certain mood
Weight, weighted value is bigger, and mood is stronger；The mood includes tranquil, nervous, depressed, cheerful and light-hearted, frightened and exciting.
The embodiment of the present invention is provided for a kind of sentiment analysis model and its training method, and it can be used to for user emotion
The automation of state obtains, and does not need excessive manual operation, can control the emotional state of client user at any time.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of sentiment analysis method flow diagram provided in an embodiment of the present invention；
Fig. 2 be it is provided in an embodiment of the present invention sign according to preset rules to the encrypting traffic, signed
Data flow method flow chart；
Fig. 3 be server provided in an embodiment of the present invention according to preset rules verifying signature whether effective ways process
Figure；
Fig. 4 is a kind of training method flow chart provided in an embodiment of the present invention；
Fig. 5 is provided in an embodiment of the present invention the encoded data stream to be input to preparatory trained sentiment analysis model
To obtain sentiment analysis result flow chart.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
The embodiment of the present invention provides a kind of sentiment analysis method, as shown in Figure 1, which comprises
S101. client acquires physiological signal, and encodes to the physiological signal, obtains encoded data stream；It uses
Shared key carries out two add operation of mould to the encoded data stream to obtain encrypting traffic；According to preset rules to the encryption
Data flow is signed, and signed data stream is obtained；The encrypting traffic and the signed data stream are sent to server together.
In order to guarantee the agility of encryption, present invention uses shared keys to be encrypted and decrypted, and shared key
Quality just determines the safety of encryption, and the quality of shared key is too low, it is clear that will affect cipher round results, therefore, the present invention is real
Following characteristics must be had by applying the shared key in example:
(1) shared key is binaryzation cyclic sequence, and wherein the length of cycling element is greater than preset length M, circulation
The quantity of unit is greater than preset quantity N.If the period of the cyclic sequence is even number, 0 is identical with 1 quantity；Otherwise, 0 and 1 number
Amount difference 1.
(2) distance of swimming sum in the shared key is set as S, is the distance of swimming of t, first distance of swimming and second distance of swimming for length
Quantity in the shared key in all distances of swimming is allIn embodiments of the present invention, continuous 1 distance of swimming constituted claims
For first distance of swimming, the two sides of first distance of swimming are 0 or sky；Continuous 0 distance of swimming constituted is known as second distance of swimming, second trip
The two sides of journey are 1 or sky.
(3) the evaluation function P (t) of the shared key obtains maximum value when t=0, and functional value is rapid when t ≠ 0
Subtract.The shared key is sequence a0a1a2...,；It enablesAndThe then evaluation function
S102. whether the server is effective according to preset rules verifying signature, if effectively, using described shared
Encrypting traffic described in key pair carries out two add operation of mould to restore encoded data stream；The encoded data stream is input in advance
Trained sentiment analysis model is to obtain sentiment analysis result；The sentiment analysis result is transmitted to the client.
Further, described to sign according to preset rules to the encrypting traffic, obtain signed data stream such as Fig. 2
It is shown, comprising:
S1011. public keys p, g and y are obtained from server, wherein p is to be worth biggish prime number, and g is a primitive root of p.
Specifically, the value of the p is greater than 10000.
S1012. private key x, 2≤x≤p-1 and y=g are generated at randomx(mod p)。
S1013. the random positive integer k obtained with p-1 prime number each other.
S1014. the first serial data a and the second serial data b, the first serial data a for calculating the signed data stream are logical
Cross formula a ≡ gk(mod p) is calculated and is obtained, and the second serial data b passes through formula b ≡ k-1(m-ax) (mod (p-1)) calculate and
?.
S1015. the first serial data a and the second serial data b is connected using default dividing mark, constitutes signed data
Stream.
Correspondingly, whether the server is effectively as shown in Figure 3 according to preset rules verifying signature, comprising:
S1021. the first serial data a and the second serial data b are extracted from signed data stream according to default dividing mark.
S1022. encrypting traffic m is obtained.
S1023. judge congruence expression gm≡yaabIt is (modp) whether true, if so, then determine that signature effectively, is otherwise signed
In vain.
Further, it in order to accurately implement the sentiment analysis method in the embodiment of the present invention, needs to train emotion in advance
Analysis model designs the sentiment analysis model in the embodiment of the present invention first.Specifically, the sentiment analysis model includes
Receive layer, reciprocation layer and output layer.The receiving layer is made of multiple input nodes, and the reciprocation layer is by multiple friendships
Mutual neuron node is constituted.Each input node is connect with all interaction neuron nodes.It is adjacent inside reciprocation layer
Neuron node is connected with each other.
Based on the sentiment analysis model, the embodiment of the present invention further provides a kind of training method, as shown in figure 4,
The described method includes:
S10. training set X={ x is obtained1, x2..., xk..., xN, the sum of the training set is N, wherein in training set
Each element be a P n dimensional vector n, each element corresponds to a kind of physiological parameter, each training set in the P n dimensional vector n
Element correspond to a mood vector.
Specifically, the physiological parameter include but is not limited to eeg wave just analyze result, heart rate, pulse, skin temperature,
Blood pressure, blood oxygen saturation, blood volume beating, palm sweat, respiratory intensity or respiratory rate.
The electroencephalogram just analyzes the frequency of occurrences that result includes α wave, β wave and θ wave.Present invention discover that people is in relaxation state
When α wave the frequency of occurrences it is higher, when people occurs nervous and worried, the frequency of occurrences of β wave is higher, when pathologic mood occurs in people
When obstacle, the frequency of occurrences of θ wave is higher.Can be characterized in the extraction brain wave of novelty of the embodiment of the present invention emotional change α wave,
The frequency of occurrences of β wave and θ wave is picked as training content for being associated with little other contents in brain wave with emotional change
It removes, improves trained precision.
Specifically, there are multiple elements in the mood vector, each element corresponds to a kind of mood, and the value of element represents certain
The weight of mood, weighted value is bigger, and mood is stronger.The mood includes but is not limited to tranquil, nervous, depressed, cheerful and light-hearted, frightened
And excitement.
S20. each neuron node in the reciprocation layer is numbered, and each neuron node is corresponding
One P dimensional weight vector ωi={ ωi1, xi2..., xik..., xip}。
S30. P dimensional weight vector corresponding to each neuron node assigns initial value.
S40. the element in the training set is sequentially input into the reciprocation layer, to obtain gathering the training set
Class is as a result, and be modified the weight of the neuron node in the reciprocation layer in cluster process；The cluster knot
Element in fruit with identical output node is polymerized to one kind.
Specifically, during the element in the training set is sequentially input the reciprocation layer, the interaction
Active layer executes following logics:
Wherein uiFor each neuron node
It exports, wherein λiFor the adjustment frequency of the P dimensional weight vector of i-th of node, xkFor the element in training set, c is neuron node
Total quantity, wherein output valve be 1 neuron node be the corresponding output node of the training set element.
Specifically, the adjustment frequency is according to formula meterIt calculates and obtains, miIn be neuron node P dimensional weight
The adjustment number of vector, c are the total quantity of neuron node.
After the neuron output of single, it can take advantage of a situation and the P dimensional weight vector of each neuron node is adjusted, adjust
Whole formula isWherein αi,βiRespectively learning rate and forgetting rate, can according to actual needs into
Row setting, but it must be ensured that αi>0,βi<0。
S50. analytical calculation cluster centre and the corresponding mood vector of cluster centre are carried out to each cluster result.
It is described that the encoded data stream is input to preparatory trained sentiment analysis model to obtain based on above content
Sentiment analysis result is as shown in Figure 5, comprising:
S100. the encoded data stream is inputted into the sentiment analysis model, and obtains its corresponding output node.
S200. the corresponding cluster result of the output node is obtained, and exports the corresponding mood vector of its cluster centre.
The embodiment of the present invention is provided for a kind of sentiment analysis method, based on client-server system realize for
The long-range monitoring and automation of family emotional state obtain, and do not need excessive manual operation, can control client user at any time
Emotional state carried out whole height encryption in data transmission procedure, had and because be related to the physiological data of user
The remarkable advantage of high automaticity and high security.
It should be understood that referenced herein " multiple " refer to two or more."and/or", description association
The incidence relation of object indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A
And B, individualism B these three situations.Character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of sentiment analysis model, it is characterised in that:
The sentiment analysis model includes receiving layer, reciprocation layer and output layer.The receiving layer is by multiple input node structures
At the reciprocation layer is made of multiple interactive neuron nodes.Each input node interacts neuron node with whole
Connection.Inside reciprocation layer, adjacent neurons node is connected with each other.
2. a kind of sentiment analysis model training method, the training method based on the sentiment analysis model described in claim 1,
It is characterized in that, which comprises
Obtain training set X={ x1, x2..., xk..., xN, the sum of the training set is N, wherein each element in training set
It is all a P n dimensional vector n, each element corresponds to a kind of physiological parameter in the P n dimensional vector n, and the element of each training set is right
Answer a mood vector；
Each neuron node in the reciprocation layer is numbered, and the corresponding P dimension of each neuron node
Weight vector ωi={ ωi1, xi2..., xik..., xip}；
P dimensional weight vector corresponding to each neuron node assigns initial value；
Element in the training set is sequentially input into the reciprocation layer, to obtain the cluster result to the training set,
And the weight of the neuron node in the reciprocation layer is modified in cluster process；Have in the cluster result
The element of identical output node is polymerized to one kind；
Analytical calculation cluster centre and the corresponding mood vector of cluster centre are carried out to each cluster result.
3. according to the method described in claim 2, it is characterized by:
During the element in the training set is sequentially input the reciprocation layer, under the reciprocation layer executes
State logic:
Wherein uiFor the output of each neuron node,
Wherein λiFor the adjustment frequency of the P dimensional weight vector of i-th of node, xkFor the element in training set, c is the total of neuron node
Quantity, the neuron node that wherein output valve is 1 is the corresponding output node of the training set element.
4. according to the method described in claim 3, it is characterized by:
The adjustment frequency is according to formula meterIt calculates and obtains, miIn for neuron node P dimensional weight vector adjustment time
Number, c are the total quantity of neuron node.
5. according to the method described in claim 4, it is characterized by further comprising:
After the neuron output of single, it can take advantage of a situation and the P dimensional weight vector of each neuron node is adjusted, adjustment is public
Formula isWherein αi,βiRespectively learning rate and forgetting rate can be set according to actual needs
It is fixed, but it must be ensured that αi>0,βi<0。
6. the method according to claim 1, wherein further include:
The physiological parameter includes that eeg wave just analyzes result, heart rate, pulse, skin temperature, blood pressure, blood oxygen saturation, blood
Capacity beating, palm sweat, respiratory intensity or respiratory rate；The electroencephalogram just analyzes the appearance frequency that result includes α wave, β wave and θ wave
Rate；
There are multiple elements in the mood vector, each element corresponds to a kind of mood, and the value of element represents the weight of certain mood,
Weighted value is bigger, and mood is stronger；The mood includes tranquil, nervous, depressed, cheerful and light-hearted, frightened and exciting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811614564.9A CN109472354A (en) | 2018-12-27 | 2018-12-27 | A kind of sentiment analysis model and its training method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811614564.9A CN109472354A (en) | 2018-12-27 | 2018-12-27 | A kind of sentiment analysis model and its training method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109472354A true CN109472354A (en) | 2019-03-15 |
Family
ID=65677133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811614564.9A Withdrawn CN109472354A (en) | 2018-12-27 | 2018-12-27 | A kind of sentiment analysis model and its training method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109472354A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113853161A (en) * | 2019-05-16 | 2021-12-28 | 托尼有限责任公司 | System and method for identifying and measuring emotional states |
-
2018
- 2018-12-27 CN CN201811614564.9A patent/CN109472354A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113853161A (en) * | 2019-05-16 | 2021-12-28 | 托尼有限责任公司 | System and method for identifying and measuring emotional states |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10606353B2 (en) | Systems and methods for collecting, analyzing, and sharing bio-signal and non-bio-signal data | |
| US20230221801A1 (en) | Systems and methods for collecting, analyzing, and sharing bio-signal and non-bio-signal data | |
| CN110795477A (en) | Data training method, device and system | |
| El Saddik et al. | Dtwins: A digital twins ecosystem for health and well-being | |
| Yu et al. | A hybrid user experience evaluation method for mobile games | |
| CN108366732A (en) | Sleepy starting detection | |
| KR101793426B1 (en) | Virtual reality exposure theraphy apparatus | |
| KR102284266B1 (en) | Method for vr sickness assessment considering neural mismatch model and the apparatus thereof | |
| CN105664332A (en) | Psychological stress training system and method | |
| CN108108603A (en) | Login method and device and electronic equipment | |
| CN107427267A (en) | For the method and apparatus for the state of mind for exporting main body | |
| CN106821720A (en) | A kind of method for pushing of point massage, device and AR equipment | |
| CN114999237A (en) | Intelligent education interactive teaching method | |
| CN109472354A (en) | A kind of sentiment analysis model and its training method | |
| CN109688141A (en) | A kind of physiological parameter data encrypted transmission method | |
| Han et al. | Noise-Factorized Disentangled Representation Learning for Generalizable Motor Imagery EEG Classification | |
| CN108234130A (en) | Auth method and device and electronic equipment | |
| CN109683712A (en) | A kind of sentiment analysis method | |
| Garzón-Paredes et al. | Emotional and cognitive responses to cultural heritage: a neuromarketing experiment using virtual reality in the tourist destination image model context | |
| O’Neill et al. | The Mental Maxwell Relations: A Thermodynamic Allegory for Higher Brain Functions | |
| KR20200038743A (en) | System, computing device and method for analyzing sleep-related behavior patterns using multi-modal sensor data | |
| WO2021154532A1 (en) | Systems and methods to provide mental distress therapy through subject interaction with an interactive space | |
| KR102445134B1 (en) | System And Method For Generating An Avatar Based On A User's Information And Providing An NFT For Avatar | |
| Carr | Evaluating the Usability of Passthought Authentication | |
| CN111064616B (en) | Chain type perception quality evaluation system based on block chain |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190315 |
|
| WW01 | Invention patent application withdrawn after publication |