CN107086041A - Speech emotional analysis method and device based on computations - Google Patents
Speech emotional analysis method and device based on computations Download PDFInfo
- Publication number
- CN107086041A CN107086041A CN201710188827.3A CN201710188827A CN107086041A CN 107086041 A CN107086041 A CN 107086041A CN 201710188827 A CN201710188827 A CN 201710188827A CN 107086041 A CN107086041 A CN 107086041A
- Authority
- CN
- China
- Prior art keywords
- voice messaging
- session
- server
- key
- user
- 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 TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
- H04L63/0442—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload wherein the sending and receiving network entities apply asymmetric encryption, i.e. different keys for encryption and decryption
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- Psychiatry (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Hospice & Palliative Care (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention belongs to field of artificial intelligence, there is provided a kind of speech emotional analysis method based on computations and device.The speech emotional analysis method based on computations that the present invention is provided includes：Step S1, user terminal and server exchange key；Step S2, user terminal obtains the voice messaging of user's input, is sent after being encrypted using key to voice messaging to server；Step S3, server receives the voice messaging after encryption, and voice messaging is obtained using secret key decryption, the voice messaging after decryption is stored in the corresponding memory cell of user, the voice messaging in memory cell passes through the affective state of contextual analysis user.Methods and apparatus of the present invention, can prevent third party from robbing the personal information for obtaining user, provide feasibility to carry out sentiment analysis based on context, be favorably improved the accuracy rate of sentiment analysis；Cipher mode is simple, reduces the complexity and volume of transmitted data of communication two party calculating, it is ensured that the real-time of sentiment analysis.
Description
Technical field
The present invention relates to field of artificial intelligence, and in particular to a kind of speech emotional analysis method based on computations
And device.
Background technology
Existing speech emotional analytical technology is the simple sentence top layer sentiment analysis for simple dialog mostly, and actually talks with field
Jing Zhong, the emotion of people is all continuous-stable, can increase the essence of affection computation by the context emotion of these continuous-stables
Accuracy and real-time.But, the sentiment analysis based on context needs complicated substantial amounts of data, complicated computing, in order to carry
The efficiency and precision of high touch analysis, are often required for being handled by the server of rear end.For user terminal, by original
Beginning data sharing easily causes privacy leakage to third party, therefore communication security and data traffic turn into subject matter.
The content of the invention
For defect of the prior art, speech emotional analysis method based on computations and dress that the present invention is provided
Put, the voice messaging of transmission be encrypted using symmetric encryption method, can prevent third party from robbing the personal information for obtaining user,
Feasibility is provided to carry out sentiment analysis based on context, the accuracy rate of sentiment analysis has been favorably improved；Cipher mode letter
It is single, reduce the complexity and volume of transmitted data of communication two party calculating, it is ensured that the real-time of sentiment analysis.
In a first aspect, a kind of speech emotional analysis method based on computations that the present invention is provided includes：Step S1, is used
Family end and server exchange key；Step S2, the user terminal obtains the voice messaging of user's input, using the key to institute
Sent after predicate message encryption for information to the server；Step S3, the server receives the voice messaging after encryption, uses institute
State secret key decryption and obtain the voice messaging, the voice messaging after decryption is stored in the corresponding memory cell of user, according to institute
The voice messaging in memory cell is stated, passes through the affective state of contextual analysis user.
Preferably, the step S1 includes：User terminal obtains the public key and Pseudo-Random Number of server, generates meeting
ID is talked about, the session id is encrypted by the public key, the session id and ID after encryption are sent to the server；Institute
State server and receive after the session id after encryption and obtain the session id using private key decryption, and store the session id to institute
Under the account for stating ID；The step S2 includes：The user terminal obtains the voice messaging of user's input, by the session id
Input the Pseudo-Random Number generation key；The voice messaging is encrypted using the key, and will be described
Voice messaging after ID and encryption is sent to the server；The step S3, including：The server is locally being searched
The session id of the ID, obtains the key by session id input Pseudo-Random Number, uses the key
Decryption obtains the voice messaging, the voice messaging after decryption is stored in the corresponding memory cell of the ID, according to institute
The voice messaging in memory cell is stated, passes through the affective state of contextual analysis user.
Preferably, the step S2 includes：The user terminal obtains the voice messaging of user's input, by current time and institute
State the session id input Pseudo-Random Number and obtain key；The voice messaging is encrypted using the key,
And the voice messaging after the ID and encryption is sent to the server；The step S3 includes：The server exists
The session id of the ID is locally searched, current time and session id input Pseudo-Random Number are obtained described
Key, the voice messaging is obtained using the secret key decryption, and it is corresponding that the voice messaging after decryption is stored in into the ID
In memory cell, according to the voice messaging in the memory cell, pass through the affective state of contextual analysis user.
Preferably, in addition to：The user terminal starts timing when generating the session id, when timing reaches effective time
When, new session id is generated, by being sent to the server after the public key encryption；Server receives new session id
Afterwards, replaced with new session id in the session id being locally stored.
Preferably, in addition to：The server is sent in the information of the user terminal and carries authentication information, described
Authentication information is encrypted using the private key of server；The user terminal is received after the authentication information of encryption, passes through the public affairs
Key is decrypted, according to the authentication information after decryption to server authentication.
Second aspect, a kind of speech emotional analytical equipment based on computations that the present invention is provided, including：Exchange key
Module, for user terminal and server exchange key；Information encrypting module, the voice of user's input is obtained for the user terminal
Information, is sent to the server after being encrypted using the key to the voice messaging；Information deciphering module, for the clothes
Business device receives the voice messaging after encryption, the voice messaging is obtained using the secret key decryption, by the voice messaging after decryption
It is stored in the corresponding memory cell of user, according to the voice messaging in the memory cell, passes through the feelings of contextual analysis user
Sense state.
Preferably, it is described exchange cipher key module specifically for：User terminal obtains public key and the pseudo random number generation of server
Algorithm, generates session id, the session id is encrypted by the public key, and the session id after ID and encryption is sent into institute
State server；The server, which receives to decrypt using private key after the session id after encryption, obtains the session id, and stores institute
Session id is stated under the account of the ID；Described information encrypting module specifically for：The user terminal obtains user's input
Voice messaging, the session id is inputted into the Pseudo-Random Number and generates key；Using the key to institute's predicate
Message breath is encrypted, and the voice messaging after the ID and encryption is sent into the server；Described information is decrypted
Module specifically for：The server is locally searching the session id of the ID, and the session id is inputted into pseudo random number
Generating algorithm obtains the key, and the voice messaging is obtained using the secret key decryption, and the voice messaging after decryption is stored in
In the corresponding memory cell of the ID, according to the voice messaging in the memory cell, pass through contextual analysis user's
Affective state.
Preferably, described information encrypting module specifically for：The user terminal obtains the voice messaging of user's input, ought
Preceding time and the session id input the Pseudo-Random Number and obtain key；Using the key to the voice messaging
It is encrypted, and the voice messaging after the ID and encryption is sent to the server；Described information deciphering module has
Body is used for：The server is locally searching the session id of the ID, by current time and the session id input it is pseudo- with
Machine number generating algorithm obtains the key, and the voice messaging is obtained using the secret key decryption, by the voice messaging after decryption
It is stored in the corresponding memory cell of the ID, according to the voice messaging in the memory cell, is used by contextual analysis
The affective state at family.
Preferably, in addition to the dynamic update module of session id, the dynamic update module of the session id is used for：The user terminal
Start timing when generating the session id, when timing reaches effective time, generate new session id, added by the public key
The server is sent to after close；Server is received after new session id, is replaced with new session id and is being locally stored
Session id.
Preferably, in addition to authentication module, the authentication module is used for：The server is sent to the letter of the user terminal
Authentication information is carried in breath, the authentication information is encrypted using the private key of server；The user terminal, which is received, to be added
After close authentication information, it is decrypted by the public key, according to the authentication information after decryption to server authentication.
Brief description of the drawings
A kind of flow for speech emotional analysis method based on computations that Fig. 1 is provided by the embodiment of the present invention one is shown
It is intended to；
A kind of structural frames for speech emotional analytical equipment based on computations that Fig. 2 is provided by the embodiment of the present invention four
Figure.
Embodiment
The embodiment of technical solution of the present invention is described in detail below in conjunction with accompanying drawing.Following examples are only used for
Clearly illustrate technical scheme, therefore be intended only as example, and the protection of the present invention can not be limited with this
Scope.
It should be noted that unless otherwise indicated, technical term or scientific terminology used in this application should be this hair
The ordinary meaning that bright one of ordinary skill in the art are understood.
Embodiment one
As shown in figure 1, a kind of speech emotional analysis method based on computations that the present embodiment is provided, including：
Step S1, user terminal and server exchange key.
Step S2, user terminal obtains the voice messaging of user's input, is extremely taken to transmission after voice messaging encryption using key
Business device.
Step S3, server receives the voice messaging after encryption, voice messaging is obtained using secret key decryption, after decryption
In the corresponding memory cell of voice messaging deposit user, the voice messaging in memory cell passes through contextual analysis user
Affective state.
Wherein, memory cell is used for storing all voice messagings of user, and is stored in chronological order, by reading
Voice messaging in user's memory cell can be carried out contextual analysis, improve the accuracy rate of user feeling state analysis.
The speech emotional analysis method based on computations that the present embodiment is provided, using symmetric encryption method to transmission
Voice messaging is encrypted, and can prevent third party from robbing the personal information for obtaining user, is carried to carry out sentiment analysis based on context
Feasibility has been supplied, the accuracy rate of sentiment analysis has been favorably improved；Cipher mode is simple, reduces the complexity of communication two party calculating
Degree and volume of transmitted data, it is ensured that the real-time of sentiment analysis.
Embodiment two
In order to ensure the security of user terminal and server when exchanging key, prevent key from being stolen by third party, this reality
Example is applied there is provided another speech emotional analysis method based on computations, including：
Step S10, user terminal obtains the public key and Pseudo-Random Number of server, generates session id, passes through public key
Session id is encrypted, the session id after ID and encryption is sent to server.
Wherein, session id is that client is generated at random.ID is the unique encodings of user terminal, and server leans on ID
Different user terminals are distinguished, all information of user terminal are stored under the account of ID.
Step S20, server, which receives to decrypt using private key after the session id after encryption, obtains session id, and stores session
ID is under the account of ID.
Step S30, user terminal obtains the voice messaging of user's input, it will words ID input Pseudo-Random Number generations
Key.
Voice messaging is encrypted using key for step S40, user terminal, and by ID and encryption after voice messaging
It is sent to server.
Wherein, the method encrypted using key is had a lot, for example, voice messaging=key ^ voice messagings after encryption, its
In " ^ " represent XOR calculate.
Step S50, server is locally searching the session id of ID, it will words ID input Pseudo-Random Numbers are obtained
To key, voice messaging is obtained using secret key decryption, the voice messaging after decryption is stored in the corresponding memory cell of ID,
Voice messaging in memory cell, passes through the affective state of contextual analysis user.
Wherein, memory cell is stored with all voice messagings of user, and is stored in chronological order, passes through to read and uses
Voice messaging in the memory cell of family can be carried out contextual analysis, improve the accuracy rate of user feeling state analysis.
In step S10 and S20, session id is encrypted using RSA public key encryption algorithms, it is ensured that session id can not
By Brute Force, the security for exchanging cipher key processes is improved.
On the basis of embodiment one, the speech emotional analysis method based on computations of embodiment two ensure that
Key is not cracked, and improves the security that speech emotional analyzes process, protects the individual privacy of user.
In order to reduce the risk that session id leakage is brought, the speech emotional analysis method based on computations also includes：With
Family end starts timing when generating session id, when timing reaches effective time, new session id is generated, after public key encryption
It is sent to server；Server is received after new session id, is replaced with new session id in the session id being locally stored.This
Sample, session id is only effective within effective time, and such as two hours, after effective time, user terminal can generate new session
ID, and server is sent to using public key encryption, it is encrypted afterwards between user terminal and server using new session id logical
Letter.The dynamic renewal of session id, further ensures the communication security between user terminal and server.
In order to which the identity to server end is verified, server, which is sent in the information of user terminal, carries certification letter
Breath, authentication information is encrypted using the private key of server.User terminal is received after the authentication information of encryption, is carried by server
The public key of confession is decrypted, and according to the authentication information after decryption to being communicated again after server authentication, further increases use
Communication security between family end and server.
Embodiment three
Another speech emotional analysis method based on computations is present embodiments provided, including：
Step S100, user terminal obtains the public key and Pseudo-Random Number of server, generates session id, passes through public key
Session id is encrypted, the session id after ID and encryption is sent to server.
Wherein, ID is the unique encodings of user terminal, and server distinguishes different user terminals by ID, user terminal
All information are stored under the account of ID.
Step S200, server, which receives to decrypt using private key after the session id after encryption, obtains session id, and stores meeting
ID is talked about under the account of ID.
Step S300, user terminal obtains the voice messaging of user's input, and current time and session id are inputted into pseudo random number
Generating algorithm obtains key.
Wherein it is possible to using input of the session id * current times as Pseudo-Random Number, in order to improve complexity
Other combination session ids and the algorithm of current time can be used.
Step S400, voice messaging is encrypted using key, and the voice messaging after ID and encryption is sent to
Server.
Wherein, the method encrypted using key is had a lot, for example, voice messaging=key ^ voice messagings after encryption, its
In " ^ " represent XOR calculate.
Step S500, server is locally searching the session id of ID, and current time and session id are inputted into pseudorandom
Number generating algorithm obtains key, and voice messaging is obtained using secret key decryption, by the voice messaging deposit ID correspondence after decryption
Memory cell in, the voice messaging in memory cell passes through the affective state of contextual analysis user.
Wherein, the time synchronized of server and user terminal.Memory cell is stored with all voice messagings of user, and on time
Between sequentially stored, can be carried out contextual analysis by reading the voice messaging in user's memory cell, improve user
The accuracy rate of affective state analysis.
On the basis of embodiment one, two, the speech emotional analysis method based on computations that embodiment three is provided,
When generating key using Pseudo-Random Number, add current time so that the key of generation also with time correlation, can be with
The difficulty of third party's decryption is effectively increased, information content is increased significantly increases while data encryption amount of calculation and transmission will not be brought
Plus, it is ensured that the real-time of sentiment analysis.
In order to reduce the risk that session id leakage is brought, the speech emotional analysis method based on computations also includes：With
Family end starts timing when generating session id, when timing reaches effective time, new session id is generated, after public key encryption
It is sent to server；Server is received after new session id, is replaced with new session id in the session id being locally stored.This
Sample, session id is only effective within effective time, and such as two hours, after effective time, user terminal can generate new session
ID, and server is sent to using public key encryption, it is encrypted afterwards between user terminal and server using new session id logical
Letter.The dynamic renewal of session id, further ensures the communication security between user terminal and server.
In order to which the identity to server end is verified, server, which is sent in the information of user terminal, carries certification letter
Breath, authentication information is encrypted using the private key of server.User terminal is received after the authentication information of encryption, is carried by server
The public key of confession is decrypted, and according to the authentication information after decryption to being communicated again after server authentication, further increases use
Communication security between family end and server.
Example IV
Based on the above-mentioned speech emotional analysis method identical inventive concept based on computations, present embodiments provide
A kind of speech emotional analytical equipment based on computations, as shown in Fig. 2 including：Exchange cipher key module 101, information encryption mould
Block 102 and information deciphering module 103.
Cipher key module 101 is exchanged, for user terminal and server exchange key.
Information encrypting module 102, the voice messaging of user's input is obtained for user terminal, is added using key to voice messaging
Sent after close to server.
Information deciphering module 103, the voice messaging after encryption is received for server, and obtaining voice using secret key decryption believes
Breath, the voice messaging after decryption is stored in the corresponding memory cell of user, the voice messaging in memory cell, by upper
Hereafter analyze the affective state of user.
The speech emotional analytical equipment based on computations that the present embodiment is provided, using symmetric encryption method to transmission
Voice messaging is encrypted, and can prevent third party from robbing the personal information for obtaining user, is carried to carry out sentiment analysis based on context
Feasibility has been supplied, the accuracy rate of sentiment analysis has been favorably improved；Cipher mode is simple, reduces the complexity of communication two party calculating
Degree and volume of transmitted data, it is ensured that the real-time of sentiment analysis.
Further, in order to ensure the security of user terminal and server when exchanging key, prevent key by third party
Steal, exchange cipher key module 101 specifically for：User terminal obtains the public key and Pseudo-Random Number of server, generates meeting
ID is talked about, session id is encrypted by public key, the session id after ID and encryption is sent to server；Server, which is received, to be added
Session id is obtained using private key decryption, and store session id under the account of ID after session id after close.
Information encrypting module 102 specifically for：User terminal obtains the voice messaging of user's input, it will words ID inputs it is pseudo- with
Machine number generating algorithm generates key；Voice messaging is encrypted using key, and by ID and encryption after voice messaging
It is sent to server；
Information deciphering module 103 specifically for：Server is locally searching the session id of ID, it will words ID inputs are pseudo-
Generating Random Number obtains key, and voice messaging is obtained using secret key decryption, and the voice messaging after decryption is stored in into ID
In corresponding memory cell, the voice messaging in memory cell passes through the affective state of contextual analysis user.
Further, in order to improve the difficulty that cracks of key, information encrypting module 102 specifically for：User terminal is obtained
The voice messaging of user's input, key is obtained by current time and session id input Pseudo-Random Number；Use key pair
Voice messaging is encrypted, and the voice messaging after ID and encryption is sent into server.
Information deciphering module 103 specifically for：Server is locally searching the session id of ID, by current time and meeting
Words ID input Pseudo-Random Numbers obtain key, voice messaging are obtained using secret key decryption, by the voice messaging after decryption
It is stored in the corresponding memory cell of ID, the voice messaging in memory cell passes through the emotion of contextual analysis user
State.
Speech emotional analytical equipment based on computations also includes the dynamic update module of session id, and session id dynamically updates
Module is used for：User terminal starts timing when generating session id, when timing reaches effective time, generates new session id, leads to
Cross and server is sent to after public key encryption；Server is received after new session id, is replaced and locally deposited with new session id
The session id of storage.
Speech emotional analytical equipment based on computations also includes authentication module, and authentication module is used for：Server is sent
To authentication information is carried in the information of user terminal, authentication information is encrypted using the private key of server.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extent
The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that：Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.
Claims (10)
1. a kind of speech emotional analysis method based on computations, it is characterised in that including：
Step S1, user terminal and server exchange key；
Step S2, the user terminal obtains the voice messaging of user's input, after being encrypted using the key to the voice messaging
Send to the server；
Step S3, the server receives the voice messaging after encryption, the voice messaging is obtained using the secret key decryption, will
In the corresponding memory cell of voice messaging deposit user after decryption, according to the voice messaging in the memory cell, by upper
Hereafter analyze the affective state of user.
2. according to the method described in claim 1, it is characterised in that
The step S1 includes：
User terminal obtains the public key and Pseudo-Random Number of server, session id is generated, by the public key to the meeting
ID encryptions are talked about, the session id and ID after encryption are sent to the server；
The server, which receives to decrypt using private key after the session id after encryption, obtains the session id, and stores the session
ID is under the account of the ID；
The step S2 includes：
The user terminal obtains the voice messaging of user's input, and the session id is inputted into the Pseudo-Random Number generates
Key；
The voice messaging is encrypted using the key, and the voice messaging after the ID and encryption is sent to
The server；
The step S3, including：
The server is locally searching the session id of the ID, and session id input Pseudo-Random Number is obtained
To the key, the voice messaging is obtained using the secret key decryption, the voice messaging after decryption is stored in the ID
In corresponding memory cell, according to the voice messaging in the memory cell, pass through the affective state of contextual analysis user.
3. method according to claim 2, it is characterised in that
The step S2 includes：
The user terminal obtains the voice messaging of user's input, and current time and the session id are inputted into the pseudo random number gives birth to
Key is obtained into algorithm；
The voice messaging is encrypted using the key, and the voice messaging after the ID and encryption is sent to
The server；
The step S3 includes：
The server is locally searching the session id of the ID, and current time and the session id are inputted into pseudo random number
Generating algorithm obtains the key, and the voice messaging is obtained using the secret key decryption, and the voice messaging after decryption is stored in
In the corresponding memory cell of the ID, according to the voice messaging in the memory cell, pass through contextual analysis user's
Affective state.
4. according to the method in claim 2 or 3, it is characterised in that also include：The user terminal is generating the session id
When start timing, when timing reaches effective time, new session id is generated, by being sent to the clothes after the public key encryption
Business device；Server is received after new session id, is replaced with new session id in the session id being locally stored.
5. according to the method in claim 2 or 3, it is characterised in that also include：
The server, which is sent in the information of the user terminal, carries authentication information, and the authentication information uses server
Private key be encrypted；
The user terminal is received after the authentication information of encryption, is decrypted by the public key, is believed according to the certification after decryption
Breath is to server authentication.
6. a kind of speech emotional analytical equipment based on computations, it is characterised in that including：
Cipher key module is exchanged, for user terminal and server exchange key；
Information encrypting module, the voice messaging of user's input is obtained for the user terminal, and the voice is given using the key
Sent after information encryption to the server；
Information deciphering module, the voice messaging after encryption is received for the server, obtains described using the secret key decryption
Voice messaging, the voice messaging after decryption is stored in the corresponding memory cell of user, according to the voice in the memory cell
Information, passes through the affective state of contextual analysis user.
7. device according to claim 6, it is characterised in that
It is described exchange cipher key module specifically for：
User terminal obtains the public key and Pseudo-Random Number of server, session id is generated, by the public key to the meeting
ID encryptions are talked about, the session id and ID after encryption are sent to the server；
The server, which receives to decrypt using private key after the session id after encryption, obtains the session id, and stores the session
ID is under the account of the ID；
Described information encrypting module specifically for：
The user terminal obtains the voice messaging of user's input, and the session id is inputted into the Pseudo-Random Number generates
Key；
The voice messaging is encrypted using the key, and the voice messaging after the ID and encryption is sent to
The server；
Described information deciphering module specifically for：
The server is locally searching the session id of the ID, and session id input Pseudo-Random Number is obtained
To the key, the voice messaging is obtained using the secret key decryption, the voice messaging after decryption is stored in the ID
In corresponding memory cell, according to the voice messaging in the memory cell, pass through the affective state of contextual analysis user.
8. device according to claim 7, it is characterised in that
Described information encrypting module specifically for：
The user terminal obtains the voice messaging of user's input, and current time and the session id are inputted into the pseudo random number gives birth to
Key is obtained into algorithm；
The voice messaging is encrypted using the key, and the voice messaging after the ID and encryption is sent to
The server；
Described information deciphering module specifically for：
The server is locally searching the session id of the ID, and current time and the session id are inputted into pseudo random number
Generating algorithm obtains the key, and the voice messaging is obtained using the secret key decryption, and the voice messaging after decryption is stored in
In the corresponding memory cell of the ID, according to the voice messaging in the memory cell, pass through contextual analysis user's
Affective state.
9. the device according to claim 7 or 8, it is characterised in that also including the dynamic update module of session id, the session
ID dynamic update modules are used for：The user terminal starts timing when generating the session id, when timing reaches effective time,
The new session id of generation, by being sent to the server after the public key encryption；Server is received after new session id, is used
New session id is replaced in the session id being locally stored.
10. the device according to claim 7 or 8, it is characterised in that also including authentication module, the authentication module is used for：
The server, which is sent in the information of the user terminal, carries authentication information, and the authentication information uses the private of server
Key is encrypted；The user terminal is received after the authentication information of encryption, is decrypted by the public key, after decryption
Authentication information is to server authentication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710188827.3A CN107086041A (en) | 2017-03-27 | 2017-03-27 | Speech emotional analysis method and device based on computations |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710188827.3A CN107086041A (en) | 2017-03-27 | 2017-03-27 | Speech emotional analysis method and device based on computations |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107086041A true CN107086041A (en) | 2017-08-22 |
Family
ID=59614349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710188827.3A Pending CN107086041A (en) | 2017-03-27 | 2017-03-27 | Speech emotional analysis method and device based on computations |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107086041A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920639A (en) * | 2018-07-02 | 2018-11-30 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108920640A (en) * | 2018-07-02 | 2018-11-30 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108986825A (en) * | 2018-07-02 | 2018-12-11 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN111105777A (en) * | 2018-10-25 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Voice data acquisition and playing method and device, key packet updating method and device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1448861A (en) * | 2002-04-01 | 2003-10-15 | 微软公司 | Automatic re-authentication |
| CN101789934A (en) * | 2009-11-17 | 2010-07-28 | 北京飞天诚信科技有限公司 | Method and system for online security trading |
| CN103003824A (en) * | 2010-07-14 | 2013-03-27 | 桑迪士克科技股份有限公司 | Storage device and method for providing partially encrypted content files to a host device |
| CN103763308A (en) * | 2013-12-31 | 2014-04-30 | 北京明朝万达科技有限公司 | Method and device for having access to webpage safely and downloading data through intelligent terminal |
| US20160337413A1 (en) * | 2015-05-11 | 2016-11-17 | Citrix Systems, Inc. | Conducting online meetings using natural language processing for automated content retrieval |
| CN106297826A (en) * | 2016-08-18 | 2017-01-04 | 竹间智能科技（上海）有限公司 | Speech emotional identification system and method |
-
2017
- 2017-03-27 CN CN201710188827.3A patent/CN107086041A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1448861A (en) * | 2002-04-01 | 2003-10-15 | 微软公司 | Automatic re-authentication |
| CN101789934A (en) * | 2009-11-17 | 2010-07-28 | 北京飞天诚信科技有限公司 | Method and system for online security trading |
| CN103003824A (en) * | 2010-07-14 | 2013-03-27 | 桑迪士克科技股份有限公司 | Storage device and method for providing partially encrypted content files to a host device |
| CN103763308A (en) * | 2013-12-31 | 2014-04-30 | 北京明朝万达科技有限公司 | Method and device for having access to webpage safely and downloading data through intelligent terminal |
| US20160337413A1 (en) * | 2015-05-11 | 2016-11-17 | Citrix Systems, Inc. | Conducting online meetings using natural language processing for automated content retrieval |
| CN106297826A (en) * | 2016-08-18 | 2017-01-04 | 竹间智能科技（上海）有限公司 | Speech emotional identification system and method |
Non-Patent Citations (1)
| Title |
|---|
| 胡配祥: "《ASP.NET程序设计项目教程》", 31 July 2016, 中国科学技术大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920639A (en) * | 2018-07-02 | 2018-11-30 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108920640A (en) * | 2018-07-02 | 2018-11-30 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108986825A (en) * | 2018-07-02 | 2018-12-11 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108920640B (en) * | 2018-07-02 | 2020-12-22 | 北京百度网讯科技有限公司 | Context acquisition method and device based on voice interaction |
| CN111105777A (en) * | 2018-10-25 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Voice data acquisition and playing method and device, key packet updating method and device and storage medium |
| CN111105777B (en) * | 2018-10-25 | 2023-10-31 | 阿里巴巴集团控股有限公司 | Voice data acquisition and playing method and device, key package updating method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259443B (en) | PSI (program specific information) technology-based method for protecting privacy of federal learning prediction stage | |
| CN108063752B (en) | Credible gene detection and data sharing method based on block chain and agent re-encryption | |
| CN106779707B (en) | Block chain-based digital currency transaction information supervision method, device and system | |
| CN116383865B (en) | Privacy protection method and system in federated learning prediction stage | |
| CN113193948B (en) | Multi-participant joint privacy data statistical analysis method, information data processing terminal | |
| EP3673609A1 (en) | Method and apparatus for obtaining input of secure multiparty computation protocol | |
| CN106961336A (en) | A kind of key components trustship method and system based on SM2 algorithms | |
| CN107086041A (en) | Speech emotional analysis method and device based on computations | |
| JP2022528925A (en) | Computer-implemented methods and systems for encrypting data | |
| CN110061957A (en) | Data encryption, decryption method, user terminal, server and data management system | |
| CN107360002B (en) | Application method of digital certificate | |
| CN115358387B (en) | Method and device for joint updating model | |
| CN115913537B (en) | Data intersection method, system and related equipment based on privacy protection | |
| US20240143795A1 (en) | Method and device for intersecting unbalanced private sets | |
| CN109981290A (en) | The communication system and method close based on no certificate label under a kind of intelligent medical environment | |
| CN117195972A (en) | A CKKS-based ciphertext neural network construction method and system | |
| WO2022068358A1 (en) | Encryption method and apparatus for generating keys on basis of attributes of information, and device | |
| CN114697019B (en) | A user account privacy protection method and system | |
| CN110266483A (en) | Based on unsymmetrical key pond to and the quantum communications service station cryptographic key negotiation method of QKD, system, equipment | |
| CN101150399A (en) | Generation method for share secret key | |
| CN111368271A (en) | Method and system for realizing password management based on multiple encryption | |
| Gowri et al. | Secured machine learning using approximate homomorphic scheme for healthcare | |
| Maragathavalli et al. | Cloud data security model using modified decoy technique in fog computing for E-healthcare | |
| Mancy et al. | Protection of encrypted medical image using consent based access control | |
| CN114154185A (en) | Data encryption storage method based on national cryptographic algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170822 |
|
| RJ01 | Rejection of invention patent application after publication |