CN208335743U - A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain - Google Patents
A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain Download PDFInfo
- Publication number
- CN208335743U CN208335743U CN201820632770.1U CN201820632770U CN208335743U CN 208335743 U CN208335743 U CN 208335743U CN 201820632770 U CN201820632770 U CN 201820632770U CN 208335743 U CN208335743 U CN 208335743U
- Authority
- CN
- China
- Prior art keywords
- white light
- circuit
- semantic
- communication
- cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The intelligent robot Semantic interaction system based on white light communication and the cognition of class brain that the utility model discloses a kind of, realizes the physical positioning of robot, by white light communication to switch the situation mode under different scenes.The intelligent semantic interaction schemes that system has used offline and cloud to merge online simultaneously realize the class brain intelligent robot Semantic interaction that offline and cloud combines online.Wherein, the online class brain intelligent robot Semantic interaction system of cloud is made of versatile class brain speech recognition cognitive model, class brain Semantic interaction model and speech synthesis platform, it can be very good the application of expansion service robot, user experience is improved, while can targetedly be provided personalized service for different home.
Description
Technical field
The utility model relates to robot voice intelligent interaction fields, in particular to a kind of to be recognized based on white light communication and class brain
The intelligent robot Semantic interaction system known.
Background technique
With the continuous development of modern science and technology and computer technology, people no longer adhere rigidly in the information interchange with machine
Keyboard operation of the mankind to machine, but a kind of more convenient, natural interactive mode is needed, and language is that the mankind are most important
And most effective information source realizes that if the language interaction between man-machine allows robot to listen to understand people be also that the mankind dream of
Thing.The development of speech recognition technology, so that this ideal is achieved.
Auditory system is always the important component of intelligent robot sensory perceptual system, and its object is to preferably complete people
Information exchange between robot.With traditional keyboard, data interaction that mouse and display carry out is different, using the sense of hearing into
The transmission of row data enables robot more anthropomorphic and intelligent.Sense of hearing interactive system is related to the speech recognition in artificial intelligence, class
People's construction of knowledge base, the advanced technologies such as semantic retrieval, speech recognition and speech synthesis, with very wide application prospect and larger
Practical value.
Currently for the technical solution of robot voice identification, traditional way is using speech chip or using single-chip microcontroller
System realizes offline speech identifying function, and discrimination is not high, be generally only capable of identifying simple word and order.
Another method is exactly that long-range speech recognition is realized using communication module, robot voice controlling terminal into
Row voice collecting is identified by network transmission to remote computation generator terminal.
With the appearance of the platforms such as cloud computing and cloud storage, robot voice is carried out using cloud platform and knows method for distinguishing very
Improve that identified off-line precision is not high and the small problem in word library in big program.
Traditional intelligent interaction technology is often realized on service robot itself platform, for example simple speech recognition is calculated
Method, video acquisition and based process etc. have certain difficulty if realizing more complicated algorithm.Because they are to machine
The arithmetic speed requirement of people's control system is quite high, while the problems such as mass data storage of pattern recognition system equally limits
The further development of offline service robot.
The scheme practicability for carrying out speech recognition based on remote computer is not high, and extended capability is not strong, local with being used only
The effect that computer is identified is similar.
The speech recognition schemes for being currently based on cloud platform mostly use greatly universal phonetic library to be analyzed and identified, cannot embody
Personalized feature, is only analyzed and is identified to the voice signal for being transferred to cloud platform, cannot carry out man-machine chat well
The operation with certain semantic feature such as exchange (for example tells robot that you will listen a bent specific music, it is allowed to download and play
Deng), while the distinctive Semantic interaction under different situations can not be realized well, the semanteme of context cannot be made full use of
Information interacts.In addition, need robot system to keep network connection when carrying out speech recognition using cloud platform, it cannot be very
The offline intelligent robot interactive controlling of good realization.
Utility model content
In order to solve limitation existing for current speech recognition, the utility model provides what one kind can occur according to voice
Scene to carry out the intelligent robot Semantic interaction system and method based on white light communication and the cognition of class brain of identification interaction automatically.
In order to achieve the above technical purposes, the technical solution of the utility model is,
It is a kind of based on white light communication and class brain cognition intelligent robot Semantic interaction system, including offline voice collecting and
Identify hardware system, class brain semantics recognition and cognition hardware system and white light communication and indoor situation positioning system, it is described
Offline voice collecting and identification hardware system be communicatively connected to respectively class brain semantics recognition cognition hardware system and white light communication and
Indoor situation positioning system,
The offline voice collecting and identification hardware system includes embedded control system, speech recognition module and audio
Processing circuit, the embedded control system communicate to connect speech recognition module and audio frequency processing circuit respectively, in each need
The place for carrying out scene Recognition is provided with a speech recognition module and an audio frequency processing circuit;
The class brain semantics recognition cognition hardware system includes device for embedded control, remote communication module and long-range language
Adopted identification device, the device for embedded control is communicatively connected to remote speech by remote communication module and semantics recognition fills
It sets, device for embedded control is also communicatively connected to offline voice collecting and identification hardware system;
The described white light communication and interior situation positioning system include multiple LED white light circuits and with LED white light circuit number
Equal white light identification circuit is measured, needs the place for carrying out scene Recognition to be provided with a LED white light circuit and one each
The luminous white light identification circuit of a white light circuit of LED for identification, each white light identification circuit are communicatively connected to offline voice collecting
With identification hardware system.
A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain, the offline language
The embedded control system of sound acquisition and identification hardware system includes STM32 embedded system, the speech recognition module packet
LD3320 speech recognition module is included, the audio frequency processing circuit includes audio filter circuit, audio amplifier circuit, multiple microphones
Array and multiple audio playing circuits, it is each that the place for carrying out scene Recognition is needed to be mounted on a microphone array and logical
Cross audio amplifier circuit and audio filter circuit be connected to STM32 embedded system, the LD3320 speech recognition module and
Multiple audio playing circuits are respectively connected to STM32 embedded system, each that the place for carrying out scene Recognition is needed to be mounted on
One audio playing circuit.
A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain, the class brain language
Justice cognition hardware system includes device for embedded control, remote communication module and remote speech semantic recognition device, and described is embedding
Entering formula control device includes ARM11 embedded system, and the remote communication module includes WiFi communication module, 4G mobile communication
Module and WLan router, the long-range semantic recognition device include cloud voice semantics recognition platform, cloud intelligence machine
Mankind's brain Semantic interaction platform and cloud speech synthesis platform, the ARM11 embedded system by WiFi communication module or
4G mobile communication module is connected to WLan router, and cloud voice semantics recognition platform is sequentially connected cloud intelligence machine mankind's brain
Semantic interaction platform and cloud speech synthesis platform, cloud Semantic interaction platform and cloud speech synthesis platform respectively with the road WLan
It is communicated to connect by device, ARM11 embedded system is connected to offline voice collecting and identifies the device for embedded control of hardware system.
A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain, the white light are logical
Letter and the LED white light circuit of indoor situation positioning system include white light LED array, LED array driving circuit, the communication of LED white light
Signal modulation and demodulator circuit, white light driving and communication system STM32 controller, the white light LED array are set to accordingly
The place for needing to carry out scene Recognition at, the described white light driving and communication system STM32 controller pass through LED array driving
Circuit and LED white light signal of communication modulation and demodulation circuit to communicate to connect with white light LED array, the white light identification circuit
Including high-speed photodiode sensor array and LED white light demodulator circuit, the high-speed photodiode sensor array
It is set to and needs to irradiate at the place for carrying out scene Recognition and by white light LED array accordingly, the LED white light demodulator circuit
Input terminal communicate to connect high-speed photodiode sensor array, output end is communicatively connected to offline voice collecting and identification is hard
Part system.
A kind of intelligent robot Semantic interaction method based on white light communication and the cognition of class brain, using described based on white light
The intelligent robot Semantic interaction system of communication and the cognition of class brain, comprising the following steps:
Step 1: simulating bionical human brain hierarchical structure using Cerebral cortex learning algorithm, building class brain speech recognition recognizes mould
Type;Network is fought by production, in voice input terminal, changes primary voice data length, increase interfering noise and artificial system
It makes shortage of data mode and expands voice training data, to enhance the robustness of speech recognition cognitive model;
Step 2: using the corpus under different situations locating for different location, in conjunction with the sparse term vector coding staff of class brain
Class brain Semantic interaction system is trained by interrogation reply system and constructed to method and the real-time memory models of level;
It needs to carry out field Step 3: receiving using the embedded system that STM32 is core by photoelectric receiving transducer
The LED white light sensor array position that sends over of coding and contextual information on the place of scape identification, by decoded positions and
Context data, speech recognition and class brain Semantic interaction system correspond to the selection of semantic base on guide line;
Step 4: offline voice collecting and identifying system realize acquisition and front-end processing to voice, and judge that system is
No networking is online, and offline speech recognition and output are realized when system is non-online;When system is online, voice data is transmitted
To varieties of clouds brain voice semantics recognition platform, and it will identify that the voice semantic text information come is sent to class brain Semantic interaction platform
It is analyzed, predicts optimum answer with its knowledge base for corresponding to situation, return again to and carry out voice number to speech synthesis platform
According to synthesis, finally synthesis voice is played out to complete intelligent human-machine interaction.
The method, the step 1 the following steps are included:
1) it chooses level and remembers basis of the Cerebral cortex learning algorithm as voice semantics recognition system model in real time;
2) on the basis of Cerebral cortex algorithm, bionical human brain structure constructs the class brain speech recognition cognitive model of multi-layer
Structure realizes that the level includes primary voice data sensing layer, middle diencephalon to the class brain deep learning of voice semantic sequence
Cortex learning layer, semantic feature space layer and timing layer;The primary voice data sensing layer input is digital audio-frequency data,
Audio data after exporting speech terminals detection is to Cerebral cortex learning layer;The intermediate Cerebral cortex learning layer identification inputs true
The real or imaginary voice data being fitted to exports as binary word vector;The semantic feature space layer input is middle diencephalon skin
The single term vector of matter learning layer output, exports as term vector set;The timing layer, by the language in semantic feature space layer
Words vector set constitutes the sentence and text data with temporal aspect, is carried out with contextual information to voice data pre-
It surveys and identifies;
3) in primary voice data sensing layer one end, access production fights network, for synthesizing virtual data, expands instruction
Practice sample, the production confrontation network includes the discrimination model for generating model and generating model for training, generates model
The distribution of sample data is captured, discrimination model is two classifiers, differentiates that input is the sample of truthful data or generation, model training
When fixed party, update the parameter of another model, alternating iteration finally estimates sample so that the mistake of other side maximizes
The distribution of data, so that the virtual data for generating model synthesis completes the training for generating model close to authentic specimen data;
4) above-mentioned trained generation model is used, K group dummy synthesis sample { Y is generatedv 1,...,Yv K, extend to voice
In training data, training is participated in;
5) after the completion of the building of voice semantics recognition system model, system is trained using the audio data of recording, mistake
Journey is as follows:
Firstly, collect the voice dialogue text fragments under public mandarin corpus and different situations, containing different native places and
Property others Mandarin Chinese recording data, the voice quantity collected in total is N;
Then, word cutting is carried out as unit of sentence to recording corpus, i.e., individually split the word in sentence, owned
After the completion of sentence word cutting, it is classified as M word in total;
To the word that N primary voice data and M word cutting generate, instructed using class brain voice semanteme learning model
Practice, when training, voice data is inputted from primary voice data sensing layer, generates corresponding binary system semantic text language from timing layer
Expect data, while to original language material data, in primary voice data sensing layer, fighting network using above-mentioned production, carrying out empty
The synthesis of quasi- sample, I voice data of dummy synthesis are trained together;
6) voice semantics recognition system model training input is voice data sin, trained prediction output is the semantic text of voice
This sequence is Tpredict, corresponding real speech semantic text sequence is Ttrue, it is to be indicated in the form of term vector in timing layer
Text sequence, the residual error of the two be δ=| | Tpredict-Ttrue||2, enable all parameters in model be expressed as W, utilize optimization
Method iterative model parameter keeps residual error δ value minimum, and iteration stopping condition isIt completes to class brain speech recognition
The training of cognitive model.
The method, the step 3) include following procedure:
1) the generation model described in is realized using multi-layer perception (MLP), according to voice data S=[s to be trained1,...,
sn,...,sN], wherein N is voice sum, snFor the nth voice binary features data and s after normalizationnIt is tieed up for l, wherein
The integer that l=0,1,2...L, L are > 0 passes through timing, increase interfering noise and artificial manufacture before and after variation primary voice data
The missing mode of voice data obtains three groups and virtually generates voice data collectionWithWhereinIt is virtually closed for timing nth generated before and after variation voice data
At voice binary features data,It makes an uproar to increase interference to voice data
Sound nth dummy synthesis voice binary features data generated,
Nth dummy synthesis voice binary features data generated are lacked artificially to manufacture voice data, are enabledSvIt indicates
WithThree dummy synthesis data total collections;
2) fixed to generate model parameter, every voice data that three groups virtually generate is differentiated respectively, discrimination model
It is realized using including the convolutional neural networks of two layers of convolutional layer, two layers of maximum sub-sampling layer and one layer of output diagnostic horizon;First
The convolution kernel of layer convolutional layer is i × i dimension, and the second layer is the maximum sub-sampling layer of j × j, and third layer is the volume that k × k ties up convolution kernel
Lamination, the 4th layer of maximum sub-sampling layer for p × q, the last layer are that output differentiates probability layer, whereinWherein l=0,1,2...L, L are positive real number, and l is the voice binary features number after normalization
According to dimension,For integer, the convolution operation at matrix (i, j) pixel is expressed assv
∈SvIndicate that the voice data of 1 l dimension virtually generated, Z indicate two-dimensional convolution nuclear matrix, j × j maximum sub-sampling is by matrix
Become from original l × l dimensionDimension, i.e., any region j × j reserved volume product value maximal term, therefore, matrix
Pixel is reduced to originalIt is then p × q using the 4th layer using third layer convolutional layer after maximum sub-sampling
Maximum sub-sampling layer, svAfter above-mentioned nonlinear transformation, two-dimensional space is finally projected toWhereinIndicate 2-D data space, two dimensional characterProbability layer is differentiated by finally exporting, i.e., output is as a result, order isIt indicates to generation sample svDifferentiated, result is " to generate sample
This " differentiate correct probability,It indicates to differentiate that result is the probability that " initial data " differentiates mistake, adds up and differentiate knot
The correct probability of fruit:As largest optimization objective function, iteration updates the parameter of discrimination model, makes this
The value of objective function is maximum;
3) parameter of fixed discrimination model, the parameter of the more newly-generated model of iteration regenerate virtual sampleEqually makeThe value of objective function is maximum;
4) continue alternating iteration, minimize the value of objective function, stopping criterion for iteration is
The method, the step 2 the following steps are included:
1) collecting includes parlor leisure corpus, bedroom sleep corpus, and study learns corpus, and sanitation park or square moves corpus, online shopping
Customer service corpus, health medical treatment corpus, the elderly accompany and attend to corpus, and child nurses corpus, and information inquires the different situations including corpus
Under text corpus, generate the corpus under different situations, and word cutting is carried out to all corpus, generate word question-answering mode;
2) the sparse term vector coding method of class brain and the real-time memory models of level are combined, are trained by interrogation reply system and structure
Build the class brain Semantic interaction system under different corpus situations;The sparse term vector coding of the class brain is with binary sparse vector
Mode indicate the word in text, specific coding method is as follows:
The binary sparse term vector x=[a for enabling n tie up1,...,an], element a in vectornValue be 0 or 1, when being 0
Quantity is rarefaction representation when being much larger than 1 quantity;
Define two binary sparse term vector x1And x2Overlapping degree calculate function overlap (x1,x2)=x1·x2,
And with this come judge two words close to program, given threshold λ, when overlay programme is more than that threshold value then indicates two word phases
Match: match (x1,x2)=overlap (x1,x2)≥λ;
3) training method of the real-time memory models of level is as follows in step 2):
Semantic word after question and answer corpus word cutting is formed by way of the sparse term vector coding of class brain with timing spy
The semantic text of sign enables text vector be expressed as y=[x1,...,xt,...,xT],xtIndicate wherein t moment
The binary sparse term vector of n dimension;
According to the successive of timing, the training input using as unit of binary sparse word vectors as model is enabled as inputt
=xt, output is exported using the binary sparse word vectors at t+1 moment as trainingt=xt+1, chronologically input completes one
Question and answer are the question and answer knowledge training for completing a text sequence, finally train the model for having semantic forecast function;
4) when testing and using trained model, first according to specific scene location information, corresponding contextual model is selected
Corpus training pattern, wherein scene location information is true by directly reading the scene location information that comes transmitted by white light communication
It is fixed;If being unable to get the scene location information to come transmitted by white light communication, the corpus model under all scenes is utilized, according to
It is secondary that analysis prediction is carried out to speech text currently entered, contextual model and final defeated is determined with the prediction of maximum probability output
Out, predict that contextual model locating for the maximum training model of output probability is current context mode;Again to class brain voice
The text that identifies of identification cognitive model carries out word cutting, and the semantic word cut is carried out the sparse term vector of class brain and is encoded, according to when
Sequence is successively sent in the real-time memory models of trained level;When having inputted the last one problem word inputN=xNWhen, it is right
The prediction output answered is first semantic word output of answerN=z1, z1For the binary system of the N+1 moment n dimension of prediction output
Sparse term vector;Again by z1Term vector feeds back to input terminal, the input input as the N+1 momentN+1=z1, fed back by circulation
Afterwards, the corresponding prediction text answers of final question and answer are obtained, probability r%, wherein r is the probability value of prediction result confidence level, 0
≤r≤100。
The method, the step 3 the following steps are included:
1) it is modulated by the way of Binary Frequency Shift Keying as the LED white light sensor array of transmitting terminal, number
The modulated optical signal for emitting 200KHz when signal 1, is the modulated optical signal of 0Hz when digital signal is 0;And it is infrared logical using NEC
Letter agreement realizes the digital data transmission between transmitting terminal and receiving end by frequency shift keying;
2) optical signal received as the photoelectric receiving transducer of receiving end passes through conversion of photoelectric sensor into electric signal, electricity
Signal is decoded by the decoder being made of phase discriminator, low-pass filter and AD analog-digital converter;Receiving terminal receives
When the modulated signal of 200KHz, other interference signals are filtered out by bandpass filter, and the modulated signal of 200KHz is carried out
Coherent demodulation, then demodulation amount is obtained by low-pass filter, and compared with 0V carries out voltage, when receiving 200KHz optical signal,
Demodulate output level 1, output level 0 when not receiving modulated optical signal;3) for the interior space of different situations, it is mounted on day
White light LEDs on card have independent position and context token information, and constantly send to region and carry context token
The white light of data then decodes its position and contextual information when receiving end, which receives, enters corresponding white light, to realize room
The extraction of interior positioning and context data.
The method, the step 4 the following steps are included:
1) ARM11 embedded system 14 is once communicated at interval of 6s clock time with server, if receiving cloud clothes
Business device response then indicates that networking is online, is otherwise off-line state, and sound-light alarm prompts;
2) if it is off-line state, speech recognition is realized by LD3320 module, when carrying out offline speech recognition,
Serial communication mode is first passed through, the voice data that will be identified downloads in LD3320 speech recognition module, completes crucial repertorie
Building;
3) when identified off-line, by being sent into audio data stream, voice recognition chip detects to use by end-point detecting method
Family pipes down, and after voice data user to be loquitured between piping down carries out operational analysis, provides recognition result;
4) it if it is presence, is held by voice data of the robot control system based on ARM11 to acquisition
Point detection, and by the raw audio file of primary voice data, voice to be identified is sent to speech recognition platforms as unit of sentence
Data;
5) after cloud class brain voice semantics recognition system receives voice data, it is decoded and speech pattern recognition,
Optimal recognition result is obtained, is sent to class brain Semantic interaction platform in a text form, while white light communication being received
Location information and contextual model send the past;
6) intelligence machine mankind brain Semantic interaction platform carries out class brain according to the contextual model and contextual information received
Semantic analysis by choosing corresponding situation semantic base, and therefrom matches optimal feedback semantic data, by it with text
Form is sent to cloud speech synthesis platform;
7) speech synthesis platform in cloud carries out speech synthesis according to the text received, generates voice document, and be returned to base
In the robot control system of ARM11, after robot control system receives voice, voice is carried out by external audio output circuit
Output is played, and continues to acquire and receive the voice signal of next step, completes lasting class brain intelligent semantic interaction.
The utility model has technical effect that solve semantic analysis ability existing for current speech interaction robot
The problems such as weak, Personalized service is not strong, it is poor to lack context recognition function, user experience and limited by network, can
By its application service old machine people, household robot, the related fieldss such as the elderly's monitoring have good economy and society effect
Benefit.
The utility model is described in further detail with reference to the accompanying drawing.
Detailed description of the invention
Fig. 1 is system construction drawing;
Fig. 2 is that white light communicates transmit circuit schematic diagram;
Fig. 3 is white light communications reception circuit diagram;
Fig. 4 is implementation flow chart;
Fig. 5 is offline speech recognition schematic diagram;
Fig. 6 is class brain voice semantics recognition system schematic;
Fig. 7 is class brain Semantic interaction systematic training schematic diagram;
Fig. 8 is that class brain Semantic interaction system uses schematic diagram.
Wherein, 1STM32 embedded system;2 audio filter circuits;3 audio amplifier circuits;4 microphone arrays;5LD3320 language
Sound identification module;6LED white light demodulator circuit;7 high-speed photodiode sensor arrays;8 different situations spaces;9 white light LEDs
Array;10LED array drive circuit;11LED white light signal of communication modulation and demodulation circuit;The driving of 12 white lights and communication system
STM32 controller;13 audio playing circuits;14ARM11 embedded system;15Wifi communication module;16 4G mobile communication moulds
Block;17WLan router;18 cloud voice semantics recognition platforms;19 cloud intelligence machine mankind's brain Semantic interaction platforms;20 clouds
Hold speech synthesis platform.
Specific embodiment
The present embodiment include offline voice collecting and identification hardware system, class brain semantics recognition and cognition hardware system and
White light communication and indoor situation positioning system, offline voice collecting and identification hardware system are communicatively connected to the knowledge of class brain semanteme respectively
It Ren Zhi not hardware system and white light communication and indoor situation positioning system.
Offline voice collecting and identification hardware system include embedded control system, speech recognition module and audio processing electricity
Road, embedded control system communicate to connect speech recognition module and audio frequency processing circuit respectively, need to carry out scene knowledge each
Other place is provided with a speech recognition module and an audio frequency processing circuit.
It includes device for embedded control, remote communication module and long-range semantics recognition that class brain semantics recognition, which recognizes hardware system,
Device, the device for embedded control are communicatively connected to remote speech and semantic recognition device by remote communication module, insertion
Formula control device is also communicatively connected to offline voice collecting and identification hardware system.
White light communication and interior situation positioning system include multiple LED white light circuits and equal with LED white light circuit quantity
White light identification circuit, need that the place for carrying out scene Recognition is provided with a LED white light circuit and one is used for each
Identify that the luminous white light identification circuit of LED white light circuit, each white light identification circuit are communicatively connected to offline voice collecting and identification
Hardware system.
In order to further expand usage mode, the place for carrying out scene Recognition is needed to be provided with a voice knowledge each
The mode of the white light identification circuit that LED white light circuit shines for identification of other module, an audio frequency processing circuit and one, can also
It is interpreted as that speech recognition module and audio frequency processing circuit are mounted on the same moveable intelligence machine respectively by above-mentioned 3 circuits
On people, which is moved to different scenes as needed, and identifies shining for LED white light circuit in scene, then
Carry out phonetic incepting, the voice broadcast finally fed back.
The present embodiment is the embedded system of core, LD3320 signer-independent sign language recognition module, microphone battle array using STM32
Column, speech front-end processing circuit, voice playing module construct offline voice collecting and identifying system;It is grasped using Linux is loaded
Make the ARM embedded system of system, wireless WIFI module, 4G mobile communication module, cloud speech recognition platforms, cloud speech synthesis is flat
Platform, intelligence machine mankind brain Semantic interaction platform construct on-line speech identification, semantic analysis and interactive system;It is white using LED
Photosensor array, LED drive circuit, LED communication control circuit communicate and indoor situation positioning system to construct white light.It is first
First, determine whether to be connected to network by ARM embedded system, so that it is determined that using on speech recognition mode under line or line
The online speech recognition of cloud and semantic analysis mode.Then, pass through photoelectric receiving transducer by the embedded system of core of STM32
Receive the position and contextual information that the coding of LED white light sensor array on indoor roof sends over, by decoded positions and
Context data carrys out the selection of speech recognition and class brain Semantic interaction system to certain semantic library on guide line.Offline voice collecting
The acquisition and front-end processing to voice are realized with identifying system, and system realizes offline speech recognition and output when non-online;System
When online, the class brain speech recognition cognition platform that voice data is transmitted to cloud is identified, then will identify that
Voice semantic text information is sent to intelligence machine mankind's brain Semantic interaction platform and analyzes, with the knowledge base of corresponding situation
Optimum answer is obtained, returns again to and carries out voice data synthesis to cloud speech synthesis platform, final intelligent robot is to lift up one's voice
Mode by synthesize voice play out to complete intelligent human-machine interaction.
The embedded control system of offline voice collecting and identification hardware system includes STM32 embedded system, described
Speech recognition module includes LD3320 speech recognition module, and the audio frequency processing circuit includes that audio filter circuit, audio are put
Big circuit, multiple microphone arrays and multiple audio playing circuits, it is each that the place for carrying out scene Recognition is needed to be mounted on one
Microphone array, and STM32 embedded system, the LD3320 are connected to by audio amplifier circuit and audio filter circuit
Speech recognition module and multiple audio playing circuits are respectively connected to STM32 embedded system, each to need to carry out scene Recognition
Place be mounted on an audio playing circuit.
Referring to Fig. 1-8, include: based on offline voice collecting and identification hardware system constructed by the present embodiment
1) offline voice collecting and identification hardware system are by STM32 embedded system 1, audio filter circuit 2, audio amplification
Circuit 3, microphone array 4 and LD3320 speech recognition module are constituted;
2) audio filter circuit is made of six rank analogue low pass filtering circuits and 64 rank FIR digital band pass filter circuits.
Building is by ARM embedded system, wireless WIFI module, 4G mobile communication module, the online semantics recognition of cloud, semantic friendship
The class brain semantic knowledge software and hardware system of mutual and speech synthesis system composition:
1) on-line speech identification and interactive system are by ARM11 embedded system 14, Wifi communication module 15,4G mobile communication
Module 16, WLAN router 17, cloud speech recognition platforms 18, cloud intelligence machine mankind's brain Semantic interaction platform 19 and cloud
Speech synthesis platform 20 is constituted.
2) wherein ARM11 uses (SuSE) Linux OS, carries out terminal App programming using Python, programs in Python
In, it is specifically used to carry out the relevant operation (mp3 file generated, mp3 file play etc.) of voice to PyAudio component, it with
Offline speech collecting system STM32 controller carries out data communication by serial ports;
3) cloud semantics recognition and interactive system hardware, which are used, can be carried out what parallel acceleration calculated with GPU (graphics processor)
Server has Python development platform.
4) speech synthesis platform in cloud synthesizes interface using Baidu's cloud voice online, and platform uses REST api interface, adopts
It is requested with Http mode, is applicable to the speech recognition of any platform, in Python environment programming, use urllib, urllib2
Http protocol data transmission and parsing are completed with pycurl component.
Construct white light communication and indoor situation positioning system:
1) white light communication and positioning system are by white light LED array 9,11 He of LED drive circuit 10 and LED communication control circuit
STM32 controller 12 is constituted.
2) white light LED array uses the astigmatism LED 160-180LM of 36 3W power, is combined company according to parallel mode
It connects, driving circuit is driven using IRFP4468 power MOS switch tube;
3) the digital communication control of white light LEDs is modulated by PWM, and PWM frequency is led in 200KHz, duty ratio 25%
The timer for crossing STM32 generates.
4) sophisticated signals such as audio using carrier modulation technique, are modulated to carrier wave by the complicated simulation letter such as white light LEDs audio
Upper (200KHz carrier wave) controls white light LEDs by driving circuit and shines, send eventually by optical signal, used herein
Fundamental modulation chip is CD4046.
Construct cloud class brain speech recognition cognitive system:
1) it chooses level and remembers basis of the Cerebral cortex learning algorithm as voice semantics recognition system model in real time;
2) on the basis of Cerebral cortex algorithm, bionical human brain structure constructs the class brain speech recognition cognitive model of multi-layer
Structure realizes that the level includes: primary voice data sensing layer to the class brain deep learning of voice semantic sequence, intermediate
Cerebral cortex learning layer, semantic feature space layer and timing layer;The primary voice data sensing layer input is digital audio number
According to the audio data after exporting speech terminals detection is to Cerebral cortex learning layer;The intermediate Cerebral cortex learning layer identifies input
True or dummy synthesis voice data, export as binary word vector;The semantic feature space layer input is centre
The single term vector of Cerebral cortex learning layer output, exports as term vector set;The timing layer, will be in semantic feature space layer
Language term vector set constitute have temporal aspect sentence and text data, with contextual information to voice data into
Row prediction and identification.
3) in primary voice data sensing layer one end, access production fights network, for synthesizing virtual data, expands instruction
Practice sample.The production confrontation network includes the discrimination model for generating model and generating model for training, generates model
It is a kind of Game Relationship with discrimination model, discrimination model effect can be generated more to preferably improve generation model
Close to the data of authentic specimen.The distribution that model captures sample data is generated, discrimination model is two classifiers, differentiates that input is true
Real data or the sample of generation, fixed party when model training, update the parameter of another model, alternating iteration, so that other side
Mistake maximize, the distribution of sample data is finally estimated, so that generating the virtual data of model synthesis close to authentic specimen
Data complete the training for generating model.
4) the production model described in is realized using multi-layer perception (MLP), according to voice data S=to be trained
[s1,...,sn,...,sN], wherein N is voice sum, sn(s is enabled for the nth voice binary features data after normalizationnFor
L=43681 dimension data), by variation primary voice data front and back timing, increases interfering noise and artificially manufacture voice data
Missing mode obtains three groups and virtually generates voice data collectionWithWhereinIt is virtually closed for timing nth generated before and after variation voice data
At voice binary features data, It makes an uproar to increase interference to voice data
Sound nth dummy synthesis voice binary features data generated,
Nth dummy synthesis voice binary features data generated are lacked artificially to manufacture voice data, are enabledSvIt indicatesWithThree dummy synthesis data total collections;
5) fixed to generate model parameter, every voice data that three groups virtually generate is differentiated respectively, discrimination model
It is realized using the convolutional neural networks containing two layers of convolutional layer, two layers of maximum sub-sampling layer and output diagnostic horizon.First layer volume
The convolution kernel of lamination is the dimension of i × i=10 × 10, and the second layer is the maximum sub-sampling layer of j × j=20 × 20, and third layer is k × k
The convolutional layer of=5 × 5 dimension convolution kernels, the 4th layer of maximum sub-sampling layer for p × q=6 × 3, the last layer are that output differentiates general
Rate layer.Wherein, the convolution operation at matrix (i, j) pixel is expressed assvIt indicatesDimension virtually generate voice data (since voice is one-dimensional data, l=43681 dimension it is one-dimensional to
Amount need to be transformed intoThe matrix-vector of dimension), Z indicates two-dimensional convolution nuclear matrix, and j × j=20 × 20 is maximum
Sub-sampling is to become matrix from 200 × 200 dimensions after first layer convolutionDimension, i.e., any j ×
The region j=20 × 20 reserved volume product value maximal term, therefore, matrix pixel point is reduced to originalMaximum son
After sampling, the convolutional layer of convolution kernel is tieed up using third layer k × k=5 × 5, becomes 6 × 6 dimensions, is then p using the 4th layer
The maximum sub-sampling layer of × q=6 × 3 becomes 1 × 2 dimension, svAfter above-mentioned nonlinear transformation, two-dimensional space is finally projected toWhereinIndicate 2-D data space, two dimensional characterBy finally exporting differentiation probability
Layer, i.e. output are as a result, order isIt indicates to generation sample svIt carries out
Differentiating, result is the probability of " generating sample " (differentiating correct),It indicates to differentiate that result is that " initial data " (differentiates wrong
Probability accidentally).It is cumulative to differentiate the correct probability of result:As largest optimization objective function, iteration updates
The parameter of discrimination model keeps the value of this objective function maximum.
6) parameter of fixed discrimination model, the parameter of the more newly-generated model of iteration regenerate virtual sampleEqually makeThe value of objective function is maximum.
7) continue alternating iteration, change the value of objective function most, stopping criterion for iteration is
8) above-mentioned trained generation model is used, K=2 group dummy synthesis sample is generatedLanguage when extending to
In sound training data, training is participated in.
9) after the completion of model construction, system is trained using the audio data of recording, process is as follows:
Firstly, collecting public mandarin corpus, using 2600 people's Mandarin Chinese mobile phone speech databases, contain different nationalitys
The Mandarin Chinese recording data with gender speaker is passed through, enabling the voice quantity collected in total is N1=800409;
Then, word cutting is carried out as unit of sentence to mandarin recording corpus, i.e., be individually partitioned into the word in sentence
Come, after the completion of enabling all sentence word cuttings, is classified as M in total1A word;
(voice quantity is N to voice several pieces sections for collecting under X=1000 Y=10 class difference situations2=200000), 10 class
Different contextual models specifically include that parlor leisure situation, bedroom sleep situation, study Studying Situntion, sanitation park or square movement situation, net
Interaction context, health medical treatment situation are purchased, the elderly accompanies and attends to situation, and child nurses situation, and information inquires situation and general situation, together
Sample carries out word cutting as unit of sentence, is classified as M in total2A word;
To N=N1+N2The word that primary voice data and M word cutting generate, using class brain voice semanteme learning model into
Row training, when training, voice data is inputted from primary voice data sensing layer, generates the semantic text of corresponding binary system from timing layer
This corpus data, while to original language material data, in primary voice data sensing layer, network is fought using above-mentioned production, into
I=2 × 3 × N=6002454 voice data of the synthesis of row virtual sample, dummy synthesis is trained together.
10) model training input is voice data (audio data) sin, trained prediction output is voice semantic text sequence
It is classified as Tpredict(timing layer, indicated in the form of term vector), corresponding real speech semantic text sequence are Ttrue(timing layer,
Indicated in the form of term vector), the residual error of the two isAll parameters in model are enabled to be expressed as W, using most
Optimization method iterative model parameter keeps residual error δ value minimum, and iteration stopping condition isClass brain voice
After the completion of identifying cognitive model training, to any audio data of input, corresponding language text can be identified.
Construct cloud Semantic interaction system:
1) Python web crawlers is utilized, (lie fallow the text corpus under online collection difference situation corpus in parlor, crouches
Room is slept corpus, and study learns corpus, and sanitation park or square moves corpus, online shopping customer service corpus, health medical treatment corpus, and the elderly accompanies and attends to language
Material, child nurse corpus, and information inquires corpus etc.), the corpus under different situations is generated, and word cutting is carried out to all corpus,
Generate word question-answering mode;
2) the sparse term vector coding method of class brain and the real-time memory models of level are combined, are trained by interrogation reply system and structure
Build the class brain Semantic interaction system under different situations;
3) it is above-mentioned 2) in class brain sparse term vector coding be exactly to be indicated in text with the mode of binary sparse vector
Word (word), specific coding method are as follows:
The binary sparse term vector x=[a for enabling n=1024 tie up1,...,an], element a in vectornQuantity for 1 is w=
40, it is much larger than 1 quantity for 0 quantity at this time, meets class brain rarefaction representation mode.Neuron is represented by signal stimulus for 1
It is activated, is not activated for 0 expression, respond and indicate different by once activating w=40 neuron of different location
Phrase pattern, such as x1=[0 1000 1... 001110 0] and x2=[1 10011 ... 000
110 1] different word vectors are indicated.
The overlapping degree for defining two binary sparse term vectors calculates function overlap (x, y)=xy, and is come with this
Judge two words close to program, set threshold values λ=40*80%=32, then indicate two when overlay programme is more than threshold values 32
A word matches: match (x, y)=overlap (x, y) >=32.
4) it is above-mentioned 2) in the training methods of the real-time memory models of level see Fig. 7, the specific steps are as follows:
Semantic word after question and answer corpus word cutting is formed by way of the sparse term vector coding of class brain with timing spy
The semantic text of sign enables y=[x1,...,xt,...,xT],xtThe wherein binary sparse word of t moment n dimension
Vector.In the corpus formed such as " turning in a report " this word, " submission " is the word at t=1 moment, and " report " is the t=2 moment
Word, x can be used respectivelyT=1And xT=2Binary sparse term vector indicate the two words.
According to the successive of timing, the training input using as unit of binary sparse word vectors as model is enabled as inputt
=xt, output is exported using the binary sparse word vectors at t+1 moment as trainingt=xt+1, i.e., above-mentioned " submission " is as instruction
Practice input, corresponding output is " report ", trains next model in this way and just has semantic forecast function, when chronologically inputting
As soon as after completing a question and answer, completing the question and answer training an of text sequence.
5) it tests and uses trained model process as shown in Figure 8, fed back contextual model is first communicated according to white light
Information selects different contextual models;Word cutting is carried out to the text that class brain speech recognition cognitive model identifies again, by what is cut
Semantic word carries out the sparse term vector coding of class brain, is successively sent in the real-time memory models of trained level according to timing.When
The last one problem word input is inputtedN=xNWhen, corresponding prediction output is first semantic word output of answerN
=z1, z1For the binary sparse term vector of the N+1 moment n dimension of prediction output.Again by z1Term vector feeds back to input terminal, as N
The input input at+1 momentN+1=z1, after circulation feedback, the corresponding prediction text answers of available final question and answer, than
Such as " what day is it today? " enter model as input after word cutting, prediction output is " Friday ", and probability r%, wherein r is pre-
Survey the probability value of result credibility, 0≤r≤100.
White light LEDs on indoor roof are received by photoelectric receiving transducer using the embedded system that STM32 is core
The position and contextual information that array code sends over, by decoded positions and context data, speech recognition, class brain on guide line
Semantic analysis and interactive system correspond to the selection of semantic base:
1) position and contextual information receive system by high speed SFH203P PIN photodiode array 7, STM32 controller
1, signal demodulating circuit 6 is constituted.
2) transmitting terminal is modulated by the way of Binary Frequency Shift Keying, and the modulation light of 200Kz is emitted when digital signal 1
Signal is the modulated optical signal of 0Hz when digital signal is 0.
3) in demodulating end, circuit is mainly the bandpass filter of center frequency, amplifier and voltage comparator by 200KHz
It constitutes, when receiving the modulated signal of 200KHz, is filtered out other interference signals by bandpass filter, and by the tune of 200KHz
Signal processed carries out coherent demodulation, then obtains demodulation amount by low-pass filter, and compared with 0V progress voltage, when receiving 200KHz
When optical signal, output level 1, output level 0 when not receiving modulated optical signal are demodulated;
4) on the basis of frequency shift keying, the transmission of digital signal is realized using NEC infrared communication protocol;
5) in demodulating end, by conversion of photoelectric sensor at the electric signal for carrying audio, electric signal passes through by reflecting optical signal
The decoder that phase device, low-pass filter and AD analog-digital converter are constituted is decoded, and the phase demodulation frequency of phase discriminator is set in
200KHz, it is consistent with the carrier frequency of transmitting terminal.What low-pass filter came out seeks to received analog signal, is turned by modulus
Parallel operation is converted into digital signal.The demodulation chip being used herein as based on CD4046.
6) for the interior space of different situations, the white light LEDs being ceiling mounted carry out independent position and situation
(two position situations: study and dining room are arranged) in mark information in implementation process, and constantly send its situation to region
Flag data and suggestion voice information can decode its position, situation when receiving end enters its light source overlay area
It, can benefit when being unable to get situation feedback information to extract indoor positioning and context data with suggestion voice information
With all training models, analysis prediction successively is carried out to speech text currently entered, it is defeated with the prediction of maximum probability
Contextual model and final output are determined out, predict that contextual model locating for the maximum training model of output probability is to work as
Preceding contextual model.
Offline voice collecting and identifying system realize acquisition and front-end processing to voice, and judge whether system networks
Line realizes that offline speech recognition and output process are as follows when system is non-online:
1) ARM11 embedded system 14 is once communicated at interval of 6s clock time with server, if receiving cloud clothes
Business device response then indicates that networking is online, is otherwise off-line state, and sound-light alarm prompts.
2) if it is off-line state, speech recognition is realized by LD3320, when carrying out offline speech recognition, is first led to
Serial communication mode is crossed, the voice data that will be identified downloads in LD3320 speech recognition module, completes the structure of crucial repertorie
It builds.
3) when identified off-line, by being sent into audio data stream, voice recognition chip detects to use by end-point detecting method
Family pipes down, and after voice data user to be loquitured between piping down carries out operational analysis, provides recognition result.
When system is online, cloud speech recognition platforms are sent speech data to, and will identify that the speech text information come
It is sent to intelligence machine mankind's brain Semantic interaction platform to analyze, obtains optimum answer with its knowledge base for corresponding to situation,
It returns again to and carries out voice data synthesis to cloud speech synthesis platform, final intelligent robot will synthesize language in a manner of lifting up one's voice
Sound is played out to complete intelligent human-machine interaction:
1) end-point detection is carried out to the voice data of acquisition based on the robot control system of ARM11, and by raw tone
Data generate mp3 file format, send voice data to be identified to speech recognition platforms as unit of sentence;
2) after cloud class brain voice semantics recognition system receives voice data, it is decoded and speech recognition, is obtained
Optimal recognition result is sent to intelligence machine mankind's brain Semantic interaction platform in a text form, while white light is communicated institute
The location information and contextual model received sends the past;
3) intelligence machine mankind brain Semantic interaction platform carries out class brain according to the contextual model and contextual information received
Semantic analysis, by choosing corresponding situation semantic base, and optimal feedback semantic data is therefrom matched, by it with text
Form be sent to cloud speech synthesis platform;
4) speech synthesis platform in cloud carries out speech synthesis according to the text received, generates mp3 formatted voice file, and pass
Back to the robot control system based on ARM11, after robot control system receives voice, by external audio output circuit into
Row voice plays output, and continues to acquire and receive the voice signal of next step, completes lasting class brain intelligent semantic interaction.
Claims (4)
1. a kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain, which is characterized in that including offline
Voice collecting and identification hardware system, class brain semantics recognition and cognition hardware system and white light communication and indoor situation positioning system
System, the offline voice collecting and identification hardware system are communicatively connected to class brain semantics recognition cognition hardware system and white respectively
Optic communication and indoor situation positioning system,
The offline voice collecting and identification hardware system includes embedded control system, speech recognition module and audio processing
Circuit, the embedded control system communicate to connect speech recognition module and audio frequency processing circuit respectively, it is each need into
The place of row scene Recognition is provided with a speech recognition module and an audio frequency processing circuit;
The class brain semantics recognition cognition hardware system includes device for embedded control, remote communication module and long-range semantic knowledge
Other device, the device for embedded control is communicatively connected to remote speech and semantic recognition device by remote communication module, embedding
Enter formula control device and is also communicatively connected to offline voice collecting and identification hardware system;
The described white light communication and interior situation positioning system include multiple LED white light circuits and with LED white light circuit quantity phase
Deng white light identification circuit, need the place for carrying out scene Recognition to be provided with a LED white light circuit and a use each
In the luminous white light identification circuit of identification LED white light circuit, each white light identification circuit is communicatively connected to offline voice collecting and knowledge
Other hardware system.
2. a kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain according to claim 1,
It is characterized in that, the embedded control system of the offline voice collecting and identification hardware system includes the embedded system of STM32
System, the speech recognition module includes LD3320 speech recognition module, and the audio frequency processing circuit includes audio filtered electrical
Road, audio amplifier circuit, multiple microphone arrays and multiple audio playing circuits, it is each that the place for carrying out scene Recognition is needed to pacify
STM32 embedded system is connected to by audio amplifier circuit and audio filter circuit equipped with a microphone array, and, it is described
LD3320 speech recognition module and multiple audio playing circuits be respectively connected to STM32 embedded system, it is each to need to carry out
The place of scene Recognition is mounted on an audio playing circuit.
3. a kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain according to claim 1,
It is characterized in that, the class brain semantic knowledge hardware system includes device for embedded control, remote communication module and long-range language
Sound semantic recognition device, the device for embedded control include ARM11 embedded system, and the remote communication module includes
WiFi communication module, 4G mobile communication module and WLan router, the long-range semantic recognition device include cloud voice language
Adopted identifying platform, cloud intelligence machine mankind brain Semantic interaction platform and cloud speech synthesis platform, the ARM11 are embedded
System is connected to WLan router by WiFi communication module or 4G mobile communication module, and cloud voice semantics recognition platform is successively
Connect cloud intelligence machine mankind brain Semantic interaction platform and cloud speech synthesis platform, cloud Semantic interaction platform and cloud language
Sound synthesis platform is connect with WLan router communication respectively, and ARM11 embedded system is connected to offline voice collecting and identification is hard
The device for embedded control of part system.
4. a kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain according to claim 1,
It is characterized in that, the LED white light circuit of the white light communication and indoor situation positioning system includes white light LED array, LED gusts
Column drive circuit, LED white light signal of communication modulation and demodulation circuit, white light driving and communication system STM32 controller, it is described
White light LED array is set to be needed to carry out at the place of scene Recognition accordingly, the white light driving and communication system STM32
Controller by LED array driving circuit and LED white light signal of communication modulation and demodulation circuit come with white light LED array communication link
It connects, the white light identification circuit includes high-speed photodiode sensor array and LED white light demodulator circuit, the high speed
Photodiode sensor array is set to be needed to irradiate at the place for carrying out scene Recognition and by white light LED array accordingly,
The input terminal of the LED white light demodulator circuit communicates to connect high-speed photodiode sensor array, output end communication connection
To offline voice collecting and identification hardware system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820632770.1U CN208335743U (en) | 2018-04-28 | 2018-04-28 | A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820632770.1U CN208335743U (en) | 2018-04-28 | 2018-04-28 | A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain |
Publications (1)
Publication Number | Publication Date |
---|---|
CN208335743U true CN208335743U (en) | 2019-01-04 |
Family
ID=64779506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201820632770.1U Active CN208335743U (en) | 2018-04-28 | 2018-04-28 | A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN208335743U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108717852A (en) * | 2018-04-28 | 2018-10-30 | 湖南师范大学 | A kind of intelligent robot Semantic interaction system and method based on white light communication and the cognition of class brain |
CN110174105A (en) * | 2019-06-14 | 2019-08-27 | 西南科技大学 | Intelligent body Autonomous Navigation Algorithm and system under a kind of complex environment |
-
2018
- 2018-04-28 CN CN201820632770.1U patent/CN208335743U/en active Active
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108717852A (en) * | 2018-04-28 | 2018-10-30 | 湖南师范大学 | A kind of intelligent robot Semantic interaction system and method based on white light communication and the cognition of class brain |
CN108717852B (en) * | 2018-04-28 | 2024-02-09 | 湖南师范大学 | Intelligent robot semantic interaction system and method based on white light communication and brain-like cognition |
CN110174105A (en) * | 2019-06-14 | 2019-08-27 | 西南科技大学 | Intelligent body Autonomous Navigation Algorithm and system under a kind of complex environment |
CN110174105B (en) * | 2019-06-14 | 2022-02-11 | 西南科技大学 | Intelligent agent autonomous navigation algorithm and system in complex environment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108717852A (en) | A kind of intelligent robot Semantic interaction system and method based on white light communication and the cognition of class brain | |
CN104700829B (en) | Animal sounds Emotion identification system and method | |
CN107030691B (en) | Data processing method and device for nursing robot | |
CN108000526B (en) | Dialogue interaction method and system for intelligent robot | |
CN108877801A (en) | More wheel dialog semantics based on multi-modal Emotion identification system understand subsystem | |
CN108805087A (en) | Semantic temporal fusion association based on multi-modal Emotion identification system judges subsystem | |
CN108899050A (en) | Speech signal analysis subsystem based on multi-modal Emotion identification system | |
CN108805089A (en) | Based on multi-modal Emotion identification method | |
CN106997243B (en) | Speech scene monitoring method and device based on intelligent robot | |
CN108805088A (en) | Physiological signal analyzing subsystem based on multi-modal Emotion identification system | |
CN106790628A (en) | Smart home house keeper central control system and its control method with body-sensing function | |
CN108108340A (en) | For the dialogue exchange method and system of intelligent robot | |
CN102932212A (en) | Intelligent household control system based on multichannel interaction manner | |
CN106773766A (en) | Smart home house keeper central control system and its control method with learning functionality | |
CN108202334A (en) | A kind of Dancing Robot that can identify music beat and style | |
CN106896767A (en) | One kind can Xie Dai formulas robot | |
CN105744434A (en) | Intelligent loudspeaker box control method and system based on gesture recognition | |
CN104134060A (en) | Sign language interpreting, displaying and sound producing system based on electromyographic signals and motion sensors | |
CN105139450B (en) | A kind of three-dimensional personage construction method and system based on face simulation | |
CN109176535A (en) | Exchange method and system based on intelligent robot | |
CN208335743U (en) | A kind of intelligent robot Semantic interaction system based on white light communication and the cognition of class brain | |
CN107942695A (en) | emotion intelligent sound system | |
CN114926837B (en) | Emotion recognition method based on human-object space-time interaction behavior | |
CN108197123A (en) | A kind of cloud translation system and method based on smartwatch | |
CN110457661A (en) | Spatial term method, apparatus, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |