CN108694942A - A kind of smart home interaction question answering system based on home furnishings intelligent service robot - Google Patents
A kind of smart home interaction question answering system based on home furnishings intelligent service robot Download PDFInfo
- Publication number
- CN108694942A CN108694942A CN201810284175.8A CN201810284175A CN108694942A CN 108694942 A CN108694942 A CN 108694942A CN 201810284175 A CN201810284175 A CN 201810284175A CN 108694942 A CN108694942 A CN 108694942A
- Authority
- CN
- China
- Prior art keywords
- intended
- service robot
- smart home
- question answering
- answering system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003993 interaction Effects 0.000 title abstract description 9
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000004378 air conditioning Methods 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005057 refrigeration Methods 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/197—Probabilistic grammars, e.g. word n-grams
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of, and the smart home based on home furnishings intelligent service robot interacts question answering system, it is equipped with smart home backstage question answering system in household service robot, smart home backstage question answering system is intended to filling module by intent classifier module, intention acquisition module, more wheels, intention realizes module and dialogue generation module is constituted.The system can be directed to user speech and instruct, text is segmented and is identified, it is intended to classify, template is intended to using default corresponding classification and carries out intent information acquisition, user demand is realized using corresponding api interface in realization module is intended to, and dialog text is generated, it is back to household service robot.Smart home interaction question answering system in the present invention passes through the combination with home furnishings intelligent service robot, previous smart home interaction/dependence of the control system to remote controler/mobile phone or other-end is overcome, user is facilitated to complete the interworking with intelligent domestic system at home anywhere or anytime.
Description
Technical field
The invention belongs to smart home fields, and in particular to a kind of smart home friendship based on home furnishings intelligent service robot
Mutual question answering system.
Background technology
In the intelligent domestic system of the prior art, often by remote controler, the equipment such as mobile phone carry out the interaction with user.
But the equipment such as these remote controlers can be not necessarily consistently placed on hand by user, be caused inconvenient for use.It will interaction mould in the present invention
Block is arranged on household intellect service robot, and voice is carried out in the home furnishings intelligent service robot of user at one's side by following
Interaction realizes that the demand of user is realized.
Invention content
It is an object of the invention in view of the deficienciess of the prior art, providing a kind of based on home furnishings intelligent service robot
Smart home interact question answering system.
The technical solution adopted in the present invention is:
A kind of smart home interaction question answering system based on home furnishings intelligent service robot, is in household service robot
Equipped with smart home backstage question answering system, the smart home backstage question answering system by intent classifier module, be intended to acquisition module,
More wheels are intended to filling module, are intended to realize that module and dialogue generation module are constituted, and household service robot receives user speech and refers to
It enables, it is intended that corresponding text is segmented and identified by sort module to be intended to classify to it, is preset with being intended to acquisition module
Various classifications are intended to masterplate, and being intended to template using corresponding classification carries out intent information acquisition, corresponding in module using being intended to realize
Api interface realize user demand, and generate dialog text, be back to household service robot.
The step of smart home backstage question answering system realization interacts question and answer with user is as follows:
Step 1:User, which says, presets wake-up word, and the microphone array on household service robot captures wake-up word,
User location coordinate is judged, before marching to user plane, starts persistently to receive voice signal v1;
Step 2:The language of the airborne embedding assembly computer of household service robot is passed through to collected audio signal v1
Sound conversion module is carried out voice and is converted to the corresponding character string s1 of audio signal v1, and the use provided using intelligent domestic system
Family scene information corrects character string s1 by scene correct algorithm, generates character string s2, generates encrypted service request
Q1 is sent to smart home backstage question answering system;
Step 3:Smart home backstage question answering system receive after the request q1 that household service robot is sent to ask into
Row parsing, character string s2 is segmented, and names Entity recognition, part-of-speech tagging processing, and send to intent classifier module;
Step 4:Intent classifier module receives user version will by the good model c1 of pre-training using classification and identification algorithm
The intent information of text is classified, and is divided into:Control is inquired, dialogue, and electric business is gone on a journey, and is stayed;
Step 5:According to the classification information obtained in step 4, intent information acquisition is carried out using the corresponding masterplate that is intended to, if
Single-wheel can not fill up the intent data being intended in masterplate, then be intended to filling module using more wheels, until filling up;
Step 6:According to the data for being intended to masterplate and providing in step 5, connect using realization mould corresponding A PI in the block is intended to
Cause for gossip shows user demand;
Step 7:API return informations in step 6 are obtained, dialog text is produced, returns to household service-delivery machine
People;
Step 8:Household service robot receives the text that smart home backstage question answering system returns, and turns language by text
Sound module converter is that voice returns to user, and next round is waited for talk with;
User's scene information that intelligent domestic system described in step 2 provides includes:Current time, date, home wear
Business robot position, weather, electric operation state;
The scene correct algorithm is a kind of sequence probability computational methods:Sequence s=(w1,w2,w3,…,wt) sequence
Row probability P (s) is calculated with following formula:
P (s)=P (w1)×P(w2|w1)×P(w3|w1,w2)×…×P(wt|w1,w2,…,wt-1)
Wherein:waFor a-th of word of the sequence after participle;
P(wb) it is the probability that b-th of word occurs;
P(wc|wd) it is that c-th of word occurs cutting in the subsequent probability of d-th of word;
T is the length of sequence s, that is, includes the number of word;
The scene correct algorithm is unfolded in accordance with the following steps:
Step 1:Character string s1 to be corrected is received, is segmented, formation sequence s=(w1,w2,w3,…,wt), calculate P
(s), if P (s) is more than the threshold value P preset, without correcting, sequence s is directly returned to;
Step 2:The stop words in s and inessential word are removed, sequence to be replaced is generated
Ss=(w1,w2,w3,…,wu), wherein u is the length of sequence ss;
Step 3:Calculate the probability of e-th of word in sequence ss to be replacedIt calculates as follows:
Wherein:w′vFor v-th of word in the high frequency dictionary of replacement preset;
For weTo v-th of word w ' in the high frequency dictionary for the corresponding scene of replacement preset1
Phonetic editing distance inverse;
Step 4:By weIt is substituted for w 'vThe sequence probability P (sss) of formation sequence sss, sequence of calculation sss, if P (sss)
E-th of word in s is replaced with w ' by > P (s)v, otherwise s is without modification;
Step 5:Step 3 step 4 is repeated, until the word in ss has all been handled, returns to sequence s
Beneficial effects of the present invention:
Smart home in the present invention interacts question answering system by the combination with home furnishings intelligent service robot, overcomes
Previous smart home interaction/dependence of the control system to remote controler/mobile phone or other-end, facilitates user to exist anywhere or anytime
The interworking with intelligent domestic system is completed in family.
Description of the drawings
Fig. 1 is part-of-speech tagging processing schematic diagram.
Specific implementation mode
The smart home based on home furnishings intelligent service robot of the present invention interacts question answering system, is in household service-delivery machine
Equipped with smart home backstage question answering system in people, the household service robot hardware includes movement chassis, motion control
Device, embedding assembly computer, microphone array, loud speaker, display screen, depth of field camera, laser radar, software systems include:
Voice conversion module, text-to-speech module, high frequency question and answer are to cache module, machine vision module, positioning navigation module, data
Trunk module and by intent classifier module, be intended to acquisition module, more wheel is intended to filling module, is intended to realize module and dialogue
The smart home backstage question answering system that generation module is constituted.Household service robot receives user speech instruction, it is intended that classification mould
Corresponding text is segmented and identified by block to be intended to classify to it, and various classifications intention moulds are preset with being intended to acquisition module
Version is intended to template using corresponding classification and carries out intent information acquisition, is used using being intended to realize in module that corresponding api interface is realized
Family demand, and dialog text is generated, it is back to household service robot.
The step of smart home backstage question answering system realization interacts question and answer with user is as follows:
Step 1:User, which says, presets wake-up word, and the microphone array on household service robot captures wake-up word,
User location coordinate is judged, before marching to user plane, starts persistently to receive voice signal v1;
Step 2:The language of the airborne embedding assembly computer of household service robot is passed through to collected audio signal v1
Sound conversion module is carried out voice and is converted to the corresponding character string s1 of audio signal v1, and the use provided using intelligent domestic system
Family scene information corrects character string s1 by scene correct algorithm, generates character string s2, generates encrypted service request
Q1 is sent to smart home backstage question answering system;
Step 3:Smart home backstage question answering system receive after the request q1 that household service robot is sent to ask into
Row parsing, character string s2 is segmented, and names Entity recognition, part-of-speech tagging processing, and send to intent classifier module;
Step 4:Intent classifier module receives user version will by the good model c1 of pre-training using classification and identification algorithm
The intent information of text is classified, and is divided into:Control is inquired, dialogue, and electric business is gone on a journey, and is stayed;
Step 5:According to the classification information obtained in step 4, intent information acquisition is carried out using the corresponding masterplate that is intended to, if
Single-wheel can not fill up the intent data being intended in masterplate, then be intended to filling module using more wheels, until filling up;
Step 6:According to the data for being intended to masterplate and providing in step 5, connect using realization mould corresponding A PI in the block is intended to
Cause for gossip shows user demand;
Step 7:API return informations in step 6 are obtained, dialog text is produced, returns to household service-delivery machine
People;
Step 8:Household service robot receives the text that smart home backstage question answering system returns, and turns language by text
Sound module converter is that voice returns to user, and next round is waited for talk with;
User's scene information that intelligent domestic system described in step 2 provides includes:Current time, date, home wear
Business robot position, weather, electric operation state;
The scene correct algorithm is a kind of sequence probability computational methods:Sequence s=(w1,w2,w3,…,wt) sequence
Row probability P (s) is calculated with following formula:
P (s)=P (w1)×P(w2|w1)×P(w3|w1,w2)×…×P(wt|w1,w2,…,wt-1)
Wherein:waFor a-th of word of the sequence after participle;
P(wb) it is the probability that b-th of word occurs;
P(wc|wd) it is that c-th of word occurs cutting in the subsequent probability of d-th of word;
T is the length of sequence s, that is, includes the number of word;
The scene correct algorithm is unfolded in accordance with the following steps:
Step 1:Character string s1 to be corrected is received, is segmented, formation sequence s=(w1,w2,w3,…,wt), calculate P
(s), if P (s) is more than the threshold value P preset, without correcting, sequence s is directly returned to;
Step 2:The stop words in s and inessential word are removed, sequence to be replaced is generated
Ss=(w1,w2,w3,…,wu), wherein u is the length of sequence ss;
Step 3:Calculate the probability of e-th of word in sequence ss to be replacedIt calculates as follows:
Wherein:w′vFor v-th of word in the high frequency dictionary of replacement preset;
For weTo v-th of word w ' in the high frequency dictionary for the corresponding scene of replacement preset1
Phonetic editing distance inverse;
Step 4:By weIt is substituted for w 'vThe sequence probability P (sss) of formation sequence sss, sequence of calculation sss, if P (sss)
E-th of word in s is replaced with w ' by > P (s)v, otherwise s is without modification;
Step 5:Step 3 step 4 is repeated, until the word in ss has all been handled, returns to sequence s.
It is illustrated below with two examples:
1. controlling API embodiments:Word is waken up to be preset as " little Bai ".
User sends out instruction:" little Bai helps me that air-conditioning is transferred to 25 degree ".Robot listen to wake up word " little Bai " start into
Row voice is converted, and is generated character string s1=' little Bai, is helped me that air-conditioning is transferred to 5 degree of childhood ', it is corrected by scene correct algorithm
To character string s2=' little Bai, help me that air-conditioning is transferred to 25 degree '.
To the participle of character string s2, name Entity recognition, part-of-speech tagging handling result as shown in Figure 1.:
S2 is obtained by the good model c1 operations classification and identification algorithm of pre-training and belongs to control intention, and information in s2 is carried out
Extraction, it is " air-conditioning " to extract target control electric appliance, and control is called to be intended to correspond to the masterplate of air-conditioning, air-conditioning masterplate packet in template library
It includes:Switch is adjusted, and periodically, is analyzed and is currently intended to belong to adjusting intention.Obtain t1=30 degrees Celsius of current indoor temperature, analysis
It is to open air-conditioning and cryogenic temperature is arranged is 25 degrees Celsius to go out user view.Air-conditioning is set by Intelligent housing gateway
It sets.The feedback information that control is completed is sent to home furnishings intelligent service robot, home furnishings intelligent service robot is broadcast:" owner, it is empty
Tune has been set to 25 degree of refrigeration, will cool off oneself a little while ".
2. a pair wheel dialogue is intended to filling embodiment:It wakes up word to be preset as " little Bai ", at 2018 on date
User sends out phonetic order:" little Bai helps me to order a train ticket ".
Home furnishings intelligent service robot:Voice is converted to character string s1, and corrects and obtain character string s2=" little Bai, side
I orders a train ticket ".
Smart home backstage question answering system:Character string s2 is classified to obtain " trip is intended to ", parsing s2 is obtained " train ticket "
Keyword is booked tickets masterplate using train ticket, masterplate be " departure place-destination-when m- train type ", do not include such in s2
Information judges loss of learning, enables and is intended to filling module to wheel, generate filling problematic character string ss1=" owner, from which to which
, when go ", problematic character string ss1 is sent to home furnishings intelligent service robot.
Home furnishings intelligent service robot playback problem character string ss1:" when owner goes from which to which " is used
It answers at family:" tomorrow morning goes to Shanghai from Hangzhou ", home furnishings intelligent service robot carry out speech recognition by identical flow and will
As a result it is sent to smart home backstage question answering system.
Smart home backstage question answering system receives return string s3, is filled to template information, i.e. " departure place:
Hangzhou-destination:Shanghai-time:10 days 6 March in 2018:00 to 2018 on March 10,12:00- train types:It is unknown ", lead to
Crossing the related remaining ticket of ticketing website's inquiry, " period shares high ferro 1, and ordinary passenger express train 2 is asked as a result, generating answer character string ss2=
Ask that owner takes high ferro or ordinary passenger express train",
User answers:" high ferro ", home furnishings intelligent service robot carry out speech recognition by identical flow and send out result
It send to smart home backstage question answering system.Smart home backstage question answering system judges that masterplate filling finishes, and calls trip API in phase
It closes ticketing website and completes ticket booking task.
Claims (5)
1. a kind of smart home based on home furnishings intelligent service robot interacts question answering system, which is characterized in that be in home wear
It is engaged in robot equipped with smart home backstage question answering system, the smart home backstage question answering system is by intent classifier module, meaning
Figure acquisition module, more wheels are intended to filling module, are intended to realize that module and dialogue generation module are constituted, and household service robot connects
Receive user speech instruction, it is intended that corresponding text is segmented and identified by sort module to be intended to classify to it, is being intended to obtain
Modulus block is preset with various classifications and is intended to masterplate, and being intended to template using corresponding classification carries out intent information acquisition, real using being intended to
Corresponding api interface realizes user demand in existing module, and generates dialog text, is back to household service robot.
2. the smart home according to claim 1 based on home furnishings intelligent service robot interacts question answering system, feature
It is, the smart home backstage question answering system realizes that the step of interacting question and answer with user is as follows:
Step 1:User, which says, presets wake-up word, and the microphone array on household service robot captures wake-up word, to
Family position coordinates are judged, before marching to user plane, start persistently to receive voice signal v1;
Step 2:Collected audio signal v1 is turned by the voice of the airborne embedding assembly computer of household service robot
Mold changing block is carried out voice and is converted to the corresponding character string s1 of audio signal v1, and the user provided using intelligent domestic system
Scape information corrects character string s1 by scene correct algorithm, generates character string s2, generates encrypted service request q1, sends out
Give smart home backstage question answering system;
Step 3:Smart home backstage question answering system solves request after receiving the request q1 that household service robot is sent
Analysis, character string s2 is segmented, and names Entity recognition, part-of-speech tagging processing, and send to intent classifier module;
Step 4:Intent classifier module receive user version using classification and identification algorithm by the good model c1 of pre-training by text
Intent information classify, be divided into:Control is inquired, dialogue, and electric business is gone on a journey, and is stayed;
Step 5:According to the classification information obtained in step 4, intent information acquisition is carried out using the corresponding masterplate that is intended to, if single-wheel
The intent data being intended in masterplate can not be filled up, then be intended to filling module using more wheels, until filling up;
Step 6:According to the data for being intended to masterplate and providing in step 5, realized using realization mould corresponding A PI interfaces in the block are intended to
User demand;
Step 7:API return informations in step 6 are obtained, dialog text is produced, returns to household service robot;
Step 8:Household service robot receives the text that smart home backstage question answering system returns, and passes through text-to-speech mould
Block is converted into voice and returns to user, and next round is waited for talk with.
3. the smart home according to claim 2 based on home furnishings intelligent service robot interacts question answering system, feature
It is, the user's scene information provided for intelligent domestic system described in step 2 includes:Current time, date, home wear
Robot position, weather, electric operation state.
4. the smart home according to claim 2 based on home furnishings intelligent service robot interacts question answering system, feature
It is, the scene correct algorithm described in step 2 is a kind of sequence probability computational methods, sequence s=(w1,w2,w3,…,wt)
Sequence probability P (s) is calculated with following formula:
P (s)=P (w1)×P(w2|w1)×P(w3|w1,w2)×…×P(wt|w1,w2,…,wt-1)
Wherein:waFor a-th of word of the sequence s after participle;
P(wb) it is the probability that b-th of word occurs;
P(wc|wd) it is that c-th of word occurs and in the subsequent probability of d-th of word;
T is the length of sequence s, that is, includes the number of word.
5. the smart home according to claim 2 based on home furnishings intelligent service robot interacts question answering system, feature
It is, the scene correct algorithm described in step 2 is unfolded in accordance with the following steps:
Step 1:Character string s1 to be corrected is received, is segmented, formation sequence s=(w1,w2,w3,…,wt), P (s) is calculated, if
P (s) is more than the threshold value P preset, without correcting, directly returns to sequence s;
Step 2:The stop words in s and inessential word are removed, sequence to be replaced is generated
Ss=(w1,w2,w3,…,wu), wherein u is the length of sequence ss;
Step 3:Calculate the probability of e-th of word in sequence ss to be replacedIt calculates as follows:
Wherein:w′vFor v-th of word in the high frequency dictionary of replacement preset;
For weTo v-th of word w ' in the high frequency dictionary for the corresponding scene of replacement preset1Phonetic editing distance
Inverse;
Step 4:By weIt is substituted for w 'vThe sequence probability P (sss) of formation sequence sss, sequence of calculation sss, if P (sss)s >P
(s), e-th of word in s is replaced with into w 'v, otherwise s is without modification;
Step 5:Step 3 and step 4 are repeated, until the word in ss has all been handled, returns to sequence s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810284175.8A CN108694942A (en) | 2018-04-02 | 2018-04-02 | A kind of smart home interaction question answering system based on home furnishings intelligent service robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810284175.8A CN108694942A (en) | 2018-04-02 | 2018-04-02 | A kind of smart home interaction question answering system based on home furnishings intelligent service robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108694942A true CN108694942A (en) | 2018-10-23 |
Family
ID=63844766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810284175.8A Pending CN108694942A (en) | 2018-04-02 | 2018-04-02 | A kind of smart home interaction question answering system based on home furnishings intelligent service robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108694942A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109471925A (en) * | 2018-10-26 | 2019-03-15 | 北京智能优学科技有限公司 | The method and system and computer readable storage medium of foreign language teaching semantic analysis, dialog process and interaction |
| CN109839110A (en) * | 2019-01-09 | 2019-06-04 | 浙江大学 | A kind of multiple target point path planning method based on quick random search tree |
| CN109949803A (en) * | 2019-02-11 | 2019-06-28 | 特斯联（北京）科技有限公司 | Building service facility control method and system based on semantic instructions intelligent recognition |
| CN110171005A (en) * | 2019-06-10 | 2019-08-27 | 杭州任你说智能科技有限公司 | A kind of tourism robot system based on intelligent sound box |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN110335595A (en) * | 2019-06-06 | 2019-10-15 | 平安科技（深圳）有限公司 | Slotting based on speech recognition asks dialogue method, device and storage medium |
| CN110473521A (en) * | 2019-02-26 | 2019-11-19 | 北京蓦然认知科技有限公司 | A kind of training method of task model, device, equipment |
| CN111048079A (en) * | 2019-10-09 | 2020-04-21 | 深圳软通动力信息技术有限公司 | Man-machine conversation method, system, electronic device and storage medium |
| CN111211953A (en) * | 2020-03-02 | 2020-05-29 | 深圳市瑞凡微电子科技有限公司 | Intelligent home cloud service system based on natural language processing and Internet of things technology |
| CN111210824A (en) * | 2018-11-21 | 2020-05-29 | 深圳绿米联创科技有限公司 | Voice information processing method and device, electronic equipment and storage medium |
| CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
| CN111666396A (en) * | 2020-06-05 | 2020-09-15 | 北京百度网讯科技有限公司 | User intention understanding satisfaction evaluation method, device, equipment and storage medium |
| CN111899763A (en) * | 2020-07-18 | 2020-11-06 | 浙江长护信息技术有限公司 | Nursing identification and evaluation method based on audio analysis |
| CN112017654A (en) * | 2020-07-17 | 2020-12-01 | 武汉赛思云科技有限公司 | Method and system for realizing non-interface office based on human-computer voice interaction |
| WO2021135561A1 (en) * | 2019-12-31 | 2021-07-08 | 思必驰科技股份有限公司 | Skill voice wake-up method and apparatus |
| CN113407692A (en) * | 2021-06-17 | 2021-09-17 | 重庆大牛认知科技有限公司 | Internet Protocol Television (IPTV) -terminal-based government affair consultation method and system |
| CN113407691A (en) * | 2021-06-17 | 2021-09-17 | 重庆大牛认知科技有限公司 | Legal consultation method and system based on intelligent interaction |
| CN114882885A (en) * | 2022-07-11 | 2022-08-09 | 广州小鹏汽车科技有限公司 | Voice interaction method, server, vehicle and storage medium |
| CN117059074A (en) * | 2023-10-08 | 2023-11-14 | 四川蜀天信息技术有限公司 | Voice interaction method and device based on intention recognition and storage medium |
| CN117809657A (en) * | 2024-02-29 | 2024-04-02 | 国网山东省电力公司东营供电公司 | Self-answering intelligent auxiliary telephone robot |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464736A (en) * | 2014-12-15 | 2015-03-25 | 北京百度网讯科技有限公司 | Error correction method and device for voice recognition text |
| CN106796787A (en) * | 2014-05-20 | 2017-05-31 | 亚马逊技术有限公司 | The linguistic context carried out using preceding dialog behavior in natural language processing is explained |
-
2018
- 2018-04-02 CN CN201810284175.8A patent/CN108694942A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106796787A (en) * | 2014-05-20 | 2017-05-31 | 亚马逊技术有限公司 | The linguistic context carried out using preceding dialog behavior in natural language processing is explained |
| CN104464736A (en) * | 2014-12-15 | 2015-03-25 | 北京百度网讯科技有限公司 | Error correction method and device for voice recognition text |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109471925A (en) * | 2018-10-26 | 2019-03-15 | 北京智能优学科技有限公司 | The method and system and computer readable storage medium of foreign language teaching semantic analysis, dialog process and interaction |
| CN111210824A (en) * | 2018-11-21 | 2020-05-29 | 深圳绿米联创科技有限公司 | Voice information processing method and device, electronic equipment and storage medium |
| CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
| CN109839110A (en) * | 2019-01-09 | 2019-06-04 | 浙江大学 | A kind of multiple target point path planning method based on quick random search tree |
| CN109839110B (en) * | 2019-01-09 | 2020-07-24 | 浙江大学 | Multi-target point path planning method based on rapid random search tree |
| CN109949803A (en) * | 2019-02-11 | 2019-06-28 | 特斯联（北京）科技有限公司 | Building service facility control method and system based on semantic instructions intelligent recognition |
| CN110473521A (en) * | 2019-02-26 | 2019-11-19 | 北京蓦然认知科技有限公司 | A kind of training method of task model, device, equipment |
| CN110335595A (en) * | 2019-06-06 | 2019-10-15 | 平安科技（深圳）有限公司 | Slotting based on speech recognition asks dialogue method, device and storage medium |
| CN110171005A (en) * | 2019-06-10 | 2019-08-27 | 杭州任你说智能科技有限公司 | A kind of tourism robot system based on intelligent sound box |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN111048079A (en) * | 2019-10-09 | 2020-04-21 | 深圳软通动力信息技术有限公司 | Man-machine conversation method, system, electronic device and storage medium |
| WO2021135561A1 (en) * | 2019-12-31 | 2021-07-08 | 思必驰科技股份有限公司 | Skill voice wake-up method and apparatus |
| US11721328B2 (en) | 2019-12-31 | 2023-08-08 | Ai Speech Co., Ltd. | Method and apparatus for awakening skills by speech |
| CN111211953A (en) * | 2020-03-02 | 2020-05-29 | 深圳市瑞凡微电子科技有限公司 | Intelligent home cloud service system based on natural language processing and Internet of things technology |
| CN111666396A (en) * | 2020-06-05 | 2020-09-15 | 北京百度网讯科技有限公司 | User intention understanding satisfaction evaluation method, device, equipment and storage medium |
| CN111666396B (en) * | 2020-06-05 | 2023-10-31 | 北京百度网讯科技有限公司 | User intention understanding satisfaction evaluation method, device, equipment and storage medium |
| CN112017654A (en) * | 2020-07-17 | 2020-12-01 | 武汉赛思云科技有限公司 | Method and system for realizing non-interface office based on human-computer voice interaction |
| CN111899763A (en) * | 2020-07-18 | 2020-11-06 | 浙江长护信息技术有限公司 | Nursing identification and evaluation method based on audio analysis |
| CN113407692A (en) * | 2021-06-17 | 2021-09-17 | 重庆大牛认知科技有限公司 | Internet Protocol Television (IPTV) -terminal-based government affair consultation method and system |
| CN113407691A (en) * | 2021-06-17 | 2021-09-17 | 重庆大牛认知科技有限公司 | Legal consultation method and system based on intelligent interaction |
| CN114882885A (en) * | 2022-07-11 | 2022-08-09 | 广州小鹏汽车科技有限公司 | Voice interaction method, server, vehicle and storage medium |
| CN117059074A (en) * | 2023-10-08 | 2023-11-14 | 四川蜀天信息技术有限公司 | Voice interaction method and device based on intention recognition and storage medium |
| CN117059074B (en) * | 2023-10-08 | 2024-01-19 | 四川蜀天信息技术有限公司 | Voice interaction method and device based on intention recognition and storage medium |
| CN117809657A (en) * | 2024-02-29 | 2024-04-02 | 国网山东省电力公司东营供电公司 | Self-answering intelligent auxiliary telephone robot |
| CN117809657B (en) * | 2024-02-29 | 2024-05-24 | 国网山东省电力公司东营供电公司 | Self-answering intelligent auxiliary telephone robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108694942A (en) | A kind of smart home interaction question answering system based on home furnishings intelligent service robot | |
| CN106201424B (en) | A kind of information interacting method, device and electronic equipment | |
| CN107240398B (en) | Intelligent voice interaction method and device | |
| CN110648553B (en) | Site reminding method, electronic equipment and computer readable storage medium | |
| US20190027148A1 (en) | Method and apparatus for recognizing speech by lip reading | |
| WO2021147041A1 (en) | Semantic analysis method and apparatus, device, and storage medium | |
| US10580407B1 (en) | State detection and responses for electronic devices | |
| CN109074806A (en) | Distributed audio output is controlled to realize voice output | |
| CN108304890B (en) | Generation method and device of classification model | |
| CN107819929A (en) | It is preferred that the identification and generation of emoticon | |
| CN102543071A (en) | Voice recognition system and method used for mobile equipment | |
| CN109410911A (en) | Artificial intelligence learning method based on speech recognition | |
| CN111261151A (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN102760431A (en) | Intelligentized voice recognition system | |
| CN114267345B (en) | Model training method, voice processing method and device | |
| CN105653709A (en) | Intelligent home voice text control method | |
| CN112017670B (en) | Target account audio identification method, device, equipment and medium | |
| JP2017192091A (en) | IOT system with voice control function and information processing method thereof | |
| CN104361311A (en) | Multi-modal online incremental access recognition system and recognition method thereof | |
| WO2023273749A1 (en) | Broadcasting text generation method and apparatus, and electronic device | |
| CN112579031A (en) | Voice interaction method and system and electronic equipment | |
| CN103927006A (en) | Robot based information interaction system and method | |
| CN110809796B (en) | Speech recognition system and method with decoupled wake phrases | |
| CN109471977A (en) | Meteorological service system | |
| CN111460373A (en) | Arrival reminding method and device, storage medium and terminal equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181023 |
|
| WD01 | Invention patent application deemed withdrawn after publication |