CN108922512A - A kind of personalization machine people phone customer service system - Google Patents
A kind of personalization machine people phone customer service system Download PDFInfo
- Publication number
- CN108922512A CN108922512A CN201810726770.2A CN201810726770A CN108922512A CN 108922512 A CN108922512 A CN 108922512A CN 201810726770 A CN201810726770 A CN 201810726770A CN 108922512 A CN108922512 A CN 108922512A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- information
- customer service
- service system
- voice
- 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- Withdrawn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
- 238000004891 communication Methods 0.000 claims abstract description 15
- 230000008451 emotion Effects 0.000 claims abstract description 14
- 230000005540 biological transmission Effects 0.000 claims abstract description 4
- 230000002996 emotional effect Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 13
- 230000008909 emotion recognition Effects 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 5
- 230000005236 sound signal Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 210000004556 brain Anatomy 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 4
- 238000001228 spectrum Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 11
- 238000005452 bending Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- 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
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- General Health & Medical Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of personalization machine people phone customer service system, including:Communication device:For receiving the first voice signal of user terminal transmission, and user terminal is sent by the second voice signal generated by intelligent robot;Intelligent robot:It is connect with the communication device, for receiving first voice signal, searches corresponding return information after identifying first voice signal, and generate corresponding second voice signal and replied;Database:It is communicated to connect with intelligent robot, for storing the return information and related data that are used for reply.Robot phone customer service system of the present invention can accurately identify user voice signal and its subsidiary emotion information, and personalized reply is provided for user, adaptable, and the intelligent interaction for improving system is horizontal.
Description
Technical field
The present invention relates to customer service robotic technology field, especially a kind of personalization machine people phone customer service system.
Background technique
Communication between customer service and user is the follow-up service of business to customer, but between current enterprise and client
Link up all is line to be carried out with artificial customer service after client's progress dialing, due to the limitation of telephone connection using manual service
Property, cause many clients just to will appear and cannot link up in time when carrying out with enterprise communication, causes problem that cannot solve in time
Certainly, problem maximum at present is exactly that a problem needs to wait and is lot more time to be handled, often client waiting when
Time just will appear dislike mood, influences subsequent communication, influences corporate image.
In the prior art, there are also customer service robots to start to come into operation, by receiving the instruction of user to depanning
The feedback of formula, but such customer service robot often can only unilaterally receive the instruction of user, it can not be as " natural person " one
The emotion or behavior of sample " understanding " user, and it is humanized provide response, interaction performance need to be improved.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of personalization machine people phone customer service system.
The purpose of the present invention is realized using following technical scheme:
A kind of personalization machine people phone customer service system, including:
Communication device:For receiving the first voice signal of user terminal transmission, and the will generated by intelligent robot
Two voice signals are sent to user terminal;
Intelligent robot:It is connect with the communication device, for receiving first voice signal, identifies first language
Corresponding return information is searched after sound signal, and is generated corresponding second voice signal and replied;
Database:It is communicated to connect with intelligent robot, for storing the return information and related data that are used for reply;
Wherein the intelligent robot includes:
Control processing module:For controlling the operation of modules;
Speech recognition module:For received first voice signal to be changed into corresponding text, and obtain the first voice
Speech emotional information in signal;
Semantics recognition module differentiates the morpheme of participle, and for segmenting to the text of acquisition to text
Sentence type differentiated;
Reply module:For according to the participle morpheme of the acquisition, sentence type and speech emotional information from database
The return information of middle match query;
Voice synthetic module:For the text organizational of the return information found at natural language, and to be changed into corresponding
The second voice signal.
Preferably, the database includes event base, maneuver library, emotion library, knowledge base, think tank, phrase library and dictionary,
Be respectively used to the storage simulation event information of human brain, action message, emotion information, knowledge information, concept information, phrase with
Corresponding relationship and standard word between standard speech.
Preferably, the system also includes modified modules, for modifying or increasing newly the information stored in the database.
Preferably, the speech recognition module further comprises:
Pretreatment unit denoises first voice signal, framing, windowing process;
Feature extraction unit carries out feature extraction processing to pretreated first voice signal, obtains the first voice letter
Number affective characteristics parameter;
Emotion recognition unit obtains the speech emotional information of the first voice signal according to the affective characteristics parameter.
Beneficial effects of the present invention are:Robot phone customer service system of the present invention, by carrying out communication link with user terminal
It connects, receives the voice signal of user terminal, by handling the voice signal of acquisition, the semanteme and language of recognition of speech signals
Sound emotion information, and this is analyzed, the return information for matching response replys user, can accurately identify user's language
Sound signal and its subsidiary emotion information provide personalized reply for user, adaptable, improve the intelligent interaction of system
It is horizontal.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is frame construction drawing of the invention;
Fig. 2 is the frame construction drawing of intelligent robot of the present invention;
Fig. 3 is the frame construction drawing of database of the present invention;
Fig. 4 is the frame construction drawing of speech recognition module of the present invention.
Appended drawing reference:
Communication device 1, intelligent robot 2, database 3, control processing module 21, speech recognition module 22, semantics recognition
Module 23 replys module 24, voice synthetic module 25, event base 31, maneuver library 32, emotion library 33, knowledge base 34, think tank
35, phrase library 36, dictionary 37, pretreatment unit 221, feature extraction unit 222, emotion recognition unit 223
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, Fig. 2, a kind of personalization machine people phone customer service system is shown, including:
Communication device 1:For receiving the first voice signal of user terminal transmission, and will be generated by intelligent robot 2
Second voice signal is sent to user terminal
Intelligent robot 2:It is connect with the communication device 1, for receiving first voice signal, identification described first
Corresponding return information is searched after voice signal, and is generated corresponding second voice signal and replied;
Database 3:It is communicated to connect with intelligent robot 2, for storing the return information and related data that are used for reply;
Wherein the intelligent robot 2 includes:
Control processing module 21:For controlling the operation of modules;
Speech recognition module 22:For received first voice signal to be changed into corresponding text, and obtain the first language
Speech emotional information in sound signal;
Semantics recognition module 23 differentiates the morpheme of participle, and for segmenting to the text of acquisition to text
This sentence type is differentiated;
Reply module 24:For according to the participle morpheme of the acquisition, sentence type and speech emotional information from data
The return information of match query in library 3;
Voice synthetic module 25:For the text organizational of the return information found at natural language, and to be changed into phase
The second voice signal answered.
Above embodiment of the present invention receives the voice signal of user terminal by being communicatively coupled with user terminal,
By handling the voice signal of acquisition, the semanteme and speech emotional information of recognition of speech signals, and this is analyzed,
The return information of matching response replys user, can accurately identify user voice signal and its subsidiary emotion information,
Personalized reply is provided for user, adaptable, the intelligent interaction for improving system is horizontal.
Preferably, wherein morpheme includes subject, from language, movement language and thought expression language.
Preferably, the communication device is connect with user terminal communication.
It preferably, include event base 31, maneuver library 32, emotion library 33, knowledge base 34, thought referring to database 3 described in Fig. 3
Library 35, phrase library 36 and dictionary 37 are respectively used to the event information of storage simulation human brain, action message, emotion information, know
Know the corresponding relationship and standard word between information, concept information, phrase and standard speech.
Preferably, the system also includes modified modules, for modifying or increasing newly the information stored in the database 3.
Preferably, referring to fig. 4, the speech recognition module 22 further comprises:
Pretreatment unit 221 denoises first voice signal, framing, windowing process;
Feature extraction unit 222 carries out feature extraction processing to pretreated first voice signal, obtains the first voice
The affective characteristics parameter of signal;
Emotion recognition unit 223 obtains the speech emotional information of the first voice signal according to the affective characteristics parameter.
Above embodiment of the present invention obtains voice signal by carrying out feature extraction processing to the voice signal of acquisition
Affective characteristics parameter and according to the speech emotional information of the affective characteristics parameter accurately recognition of speech signals be system
Corresponding reply is made according to the speech emotional information in user voice signal to lay a good foundation.
Preferably, the pretreatment unit 221 further comprises:
Sub-frame processing is carried out to received first voice signal, obtains voice sequence δc(τ), c=1,2 ..., C, wherein τ
Indicate the index of frame, frame number C.
Above embodiment of the present invention carries out sub-frame processing to voice signal, and the feature extraction after being lays the foundation.
Preferably, the feature extraction unit 222 further comprises:
(1) STFT is converted:Short Time Fourier Transform (STFT) is carried out according to the voice sequence of acquisition, wherein the STFT used
Function is:
In formula, δc(τ) indicates c frame voice sequence, λ (τ0- τ) indicate Hamming window function;Sc(ι) indicates δcThe STFT of (τ)
Coefficient, l=0,1 ..., L, L indicate Hamming window length, and j indicates orthogonality relation coefficient;
(2) logarithmic energy spectrum is obtained:The logarithmic energy spectrum for obtaining voice sequence STFT coefficient, wherein the logarithmic energy used
Function is:
In formula, Melc(μ) indicates Mel filter function, whereinμl, μtTable respectively
Showing the lower and upper limit of Mel frequency spectrum, 0≤g < G, G indicate the quantity of Mel filter,Indicate logarithmic energy, Melc(μ)
Indicate the filter result of Mel filter group, wherein all framesConstitute logarithmic energy spectrumγ indicates Dynamic gene;
(3) Gabor spectrum is obtained:Obtain the Gabor spectrum of voice signalWherein use Gabor spectrum obtain function for:
In formula, conv () indicates convolution operator,Indicate logarithmic energy spectrum, ξxyIndicate Gabor wavelet kernel function,
Wherein:
In formula, x indicates the core direction of Gabor wavelet, x=1,2 ..., X, and X indicates Gabor wavelet core direction quantity, y table
Show that the core scale of Gabor wavelet, y=1,2 ..., Y, Y indicate Gabor wavelet core scale quantity, k=(u, v) indicates pixel
Spatial position, σ indicate the radius of Gaussian function, ιyIndicate the corresponding scale parameter of core scale y,Indicate kernel function direction.
(4) local energy distribution profile is obtained:The local energy distribution profile of the Gabor spectrum is obtained, including:
Gabor is composedIt is divided into (C-d+1) (G/d) a fritter φuv;
Wherein, u=1 ..., C-d+1, v=1 ..., G/d, d indicate block size;
Each fritter φ is obtained respectivelyuvGabor single order not bending moment parameter, wherein bending moment parameter does not obtain the single order used
Function is:
β1=γ1y20+γ2y02+γ3y11
Wherein,
In formula, β1Indicate single order not bending moment parameter, dL, dHRespectively represent the width and height of block, ymnIt indicates in the normalization of m+n rank
Heart square, fmnIndicate m+n rank central moment,Indicate m+n rank square,Indicate energy barycenter, wherein Wherein, y20That is ymnMiddle m=2, n=0, γ1, γ2, γ3Indicate setting adjustment because
Son;
Through above-mentioned processing, by the Gabor single order obtained from each fritter, bending moment parameter combination does not obtain the part Gabor energy
Measure distribution profile;
(5) affective characteristics parameter is obtained:The phase of coefficient between Gabor local energy distribution profile is eliminated using discrete cosine transform
Guan Xing to obtain the cepstrum coefficient of Gabor local energy distribution profile, and is denoted as ρx,y, by different scale, different directions
Gabor local energy distribution profile cepstrum coefficient ρx,yIt combines, constitutes the affective characteristics parameter of voice signal.
Preferably, the feature extraction unit 222 further includes:From cepstrum coefficient ρx,yMiddle extraction statistical nature, is denoted as
ωx,y, meanwhile, also from ρx,ySingle order, extract statistical nature in second differnce, be denoted asWithCombine obtained language
Sound signal affective characteristics parameter is:
Preferably, Gabor wavelet core the scale quantity Y=5, core direction quantity X=8 of use.
Above embodiment of the present invention adopts the affective characteristics parameter for extracting voice signal with the aforedescribed process, firstly, using
Customized logarithmic energy function obtains the logarithmic energy spectrum of voice signal, can effectively represent the energy point of voice signal
Cloth, accuracy are high;Then the Gabor spectrum of voice signal is obtained, wherein the Gabor wavelet kernel function used can amplify voice letter
Number emotion local message, and the original information of stick signal improves the robustness of emotion recognition;Then by Gabor spectrum point
Obtain single order not bending moment parameter at different fritter, according to the single order of acquisition not bending moment parameter combination at local energy distribution profile,
The local energy change information of amplified energy spectrum, can protrude the characteristic of speech emotional in voice signal, improve voice
The accuracy and adaptability of affective characteristics parameter extraction;Finally use the cepstrum coefficient and one of Gabor local energy distribution profile
The feelings of the composition voice signal such as rank, the mean value of second differnce, standard value, maximum value, minimum value, peak value, the degree of bias, range, intermediate value
Feel characteristic parameter, the redundancy of affective characteristics parameter acquisition can be effectively reduced, improves the recognition performance of affective characteristics parameter.
Preferably, emotion recognition unit 223 further comprises:The affective characteristics parameter and preset different phonetic that will acquire
The affective characteristics parameter of emotional semantic classification is matched, and obtains corresponding speech emotional classification as speech emotional information;
Wherein, the speech emotional, which is classified, includes:It is neutral, happy, it is angry and sad.
In a kind of scene, when the speech emotional that emotion recognition unit 223 recognizes user is classified as anger, mould is replied
Block 24 will obtain the relevant return information for being used to pacify user emotion from database 3, and generate corresponding second voice letter
Number.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as analysis, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (4)
1. a kind of personalization machine people phone customer service system, which is characterized in that including:
Communication device:For receiving the first voice signal of user terminal transmission, and the second language that will be generated by intelligent robot
Sound signal is sent to user terminal;
Intelligent robot:It is connect with the communication device, for receiving first voice signal, identifies the first voice letter
Corresponding return information is searched after number, and is generated corresponding second voice signal and replied;
Database:It is communicated to connect with intelligent robot, for storing the return information and related data that are used for reply;
Wherein the intelligent robot includes:
Control processing module:For controlling the operation of modules;
Speech recognition module:For received first voice signal to be changed into corresponding text, and obtain the first voice signal
In speech emotional information;
Semantics recognition module differentiates the morpheme of participle, and for segmenting to the text of acquisition to the sentence of text
Subtype is differentiated;
Reply module:For being looked into from database according to the participle morpheme of the acquisition, sentence type and speech emotional information
Ask matched return information;
Voice synthetic module:For the text organizational of the return information found at natural language, and to be changed into corresponding
Two voice signals.
2. a kind of personalization machine people phone customer service system according to claim 1, which is characterized in that the database packet
Event base, maneuver library, emotion library, knowledge base, think tank, phrase library and dictionary are included, storage simulation human brain is respectively used to
Corresponding relationship and standard between event information, action message, emotion information, knowledge information, concept information, phrase and standard speech
Word.
3. a kind of personalization machine people phone customer service system according to claim 1, which is characterized in that the system is also wrapped
Modified module is included, for modifying or increasing newly the information stored in the database.
4. a kind of personalization machine people phone customer service system according to claim 2, which is characterized in that the speech recognition
Module further comprises:
Pretreatment unit denoises first voice signal, framing, windowing process;
Feature extraction unit carries out feature extraction processing to pretreated first voice signal, obtains the first voice signal
Affective characteristics parameter;
Emotion recognition unit obtains the speech emotional information of the first voice signal according to the affective characteristics parameter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810726770.2A CN108922512A (en) | 2018-07-04 | 2018-07-04 | A kind of personalization machine people phone customer service system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810726770.2A CN108922512A (en) | 2018-07-04 | 2018-07-04 | A kind of personalization machine people phone customer service system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108922512A true CN108922512A (en) | 2018-11-30 |
Family
ID=64423959
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810726770.2A Withdrawn CN108922512A (en) | 2018-07-04 | 2018-07-04 | A kind of personalization machine people phone customer service system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108922512A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109003364A (en) * | 2018-07-04 | 2018-12-14 | 深圳市益鑫智能科技有限公司 | A kind of Gate-ban Monitoring System of Home House based on speech recognition |
CN109712645A (en) * | 2019-01-10 | 2019-05-03 | 上海言通网络科技有限公司 | Autonomous phone system and autonomous call method |
CN110047517A (en) * | 2019-04-24 | 2019-07-23 | 京东方科技集团股份有限公司 | Speech-emotion recognition method, answering method and computer equipment |
CN111590610A (en) * | 2020-04-30 | 2020-08-28 | 南京智音云数字科技有限公司 | Novel intelligent dialogue robot control system and method thereof |
-
2018
- 2018-07-04 CN CN201810726770.2A patent/CN108922512A/en not_active Withdrawn
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109003364A (en) * | 2018-07-04 | 2018-12-14 | 深圳市益鑫智能科技有限公司 | A kind of Gate-ban Monitoring System of Home House based on speech recognition |
CN109712645A (en) * | 2019-01-10 | 2019-05-03 | 上海言通网络科技有限公司 | Autonomous phone system and autonomous call method |
CN110047517A (en) * | 2019-04-24 | 2019-07-23 | 京东方科技集团股份有限公司 | Speech-emotion recognition method, answering method and computer equipment |
CN111590610A (en) * | 2020-04-30 | 2020-08-28 | 南京智音云数字科技有限公司 | Novel intelligent dialogue robot control system and method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108922512A (en) | A kind of personalization machine people phone customer service system | |
CN111445903B (en) | Enterprise name recognition method and device | |
WO2023273170A1 (en) | Welcoming robot conversation method | |
KR101901920B1 (en) | System and method for providing reverse scripting service between speaking and text for ai deep learning | |
CN111967224A (en) | Method and device for processing dialog text, electronic equipment and storage medium | |
CN106847279A (en) | Man-machine interaction method based on robot operating system ROS | |
CN111598485A (en) | Multi-dimensional intelligent quality inspection method, device, terminal equipment and medium | |
CN112614510B (en) | Audio quality assessment method and device | |
DE60214850T2 (en) | FOR A USER GROUP, SPECIFIC PATTERN PROCESSING SYSTEM | |
CN111429157A (en) | Method, device and equipment for evaluating and processing complaint work order and storage medium | |
CN110225210A (en) | Based on call abstract Auto-writing work order method and system | |
CN111858854A (en) | Question-answer matching method based on historical dialogue information and related device | |
CN101505328A (en) | Network data retrieval method applying speech recognition and system thereof | |
CN111128240B (en) | Voice emotion recognition method based on anti-semantic-erasure | |
CN116737883A (en) | Man-machine interaction method, device, equipment and storage medium | |
CN111091826A (en) | Intelligent voice robot system based on deep learning and finite-state machine | |
CN111354377A (en) | Method and device for recognizing emotion through voice and electronic equipment | |
CN111625636B (en) | Method, device, equipment and medium for rejecting man-machine conversation | |
CN113726942A (en) | Intelligent telephone answering method, system, medium and electronic terminal | |
CN112347788A (en) | Corpus processing method, apparatus and storage medium | |
CN112836053A (en) | Man-machine conversation emotion analysis method and system for industrial field | |
CN117150338A (en) | Task processing, automatic question and answer and multimedia data identification model training method | |
CN116468048A (en) | Internet electronic commerce complaint intelligent processing method based on big data knowledge graph | |
CN114049875A (en) | TTS (text to speech) broadcasting method, device, equipment and storage medium | |
CN107066567B (en) | Topic detection-based user portrait modeling method and system in text conversation |
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: 20181130 |
|
WW01 | Invention patent application withdrawn after publication |