CN111128157B - Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner - Google Patents
Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner Download PDFInfo
- Publication number
- CN111128157B CN111128157B CN201911270433.8A CN201911270433A CN111128157B CN 111128157 B CN111128157 B CN 111128157B CN 201911270433 A CN201911270433 A CN 201911270433A CN 111128157 B CN111128157 B CN 111128157B
- Authority
- CN
- China
- Prior art keywords
- intelligent household
- household appliance
- person
- wake
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
- G06V40/176—Dynamic expression
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention provides a wake-up-free voice recognition control method for intelligent household appliances, a computer readable storage medium and an air conditioner. Through binding the relation of object and intelligent household electrical appliances, the object can be equipment also can daily necessities, just look at certain object when the user and can correspond the intelligent household electrical appliances that speech control corresponds and bind, and the user can avoid awakening up the speech operation air conditioner, has promoted user's noninductive mutual experience, has also increased its interest of voice awakening simultaneously to a certain extent.
Description
Technical Field
The invention relates to the technical field of voice awakening, in particular to an awakening-free voice recognition control method of an intelligent household appliance, a computer readable storage medium and an air conditioner.
Background
At present, along with the rapid development of the field of artificial intelligence and the increasing demands of people on intelligent monitoring, intelligent home and novel human-computer interaction. At present, intelligent voice sound boxes on the market bloom all the time, voice interaction technology is mature, and voice interaction is applied to household appliances, such as voice air conditioners, gradually increasing. The application of the image-based non-inductive interaction technology in the household appliance industry is gradually appeared, and the image technology is combined with the control of voice control to meet new opportunities. Generally, a voice air conditioner (or a voice intelligent device) is controlled, an operation of waking up first is required before a voice control instruction is sent each time, a voice wake-up word control instruction is sent, a control instruction recognition operation is started after the voice control instruction is woken up, and the voice air conditioner (or the voice intelligent device) needs to be woken up each time.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the awakening-free voice recognition control method of the intelligent household appliance, the awakening-free direct voice air conditioner is carried out by combining the image recognition technology, the interaction experience of a user is improved, meanwhile, the device binding is realized, a certain device can be controlled by looking at the certain device, and the name of the device does not need to be awakened each time the device is operated.
In order to achieve the purpose, the invention adopts the following technical scheme:
a staring-free voice recognition control method for intelligent household appliances is characterized in that a staring-wakeup relationship between an object and the intelligent household appliances is preset, human body information of a person in the current environment is detected in real time through a visual sensor, whether the person intentionally starts the corresponding intelligent household appliance is analyzed and judged through a neural network algorithm, and if the person intentionally starts the corresponding intelligent household appliance is judged, the intelligent household appliance enters a wakeup-free state to acquire voice information. Through binding the relation of object and intelligent household electrical appliances, the object can be equipment also can daily necessities, just look at certain object when the user and can correspond the intelligent household electrical appliances that speech control corresponds and bind, and the user can avoid awakening up the speech operation air conditioner, has promoted user's noninductive mutual experience, has also increased its interest of voice awakening simultaneously to a certain extent.
Further, the real-time detection of the human body information of the person in the current environment by the visual sensor specifically includes: the binocular camera detects dynamic information of the face and the head of a person in a visual area in real time, and the dynamic information of the face specifically comprises eye state information and mouth dynamic information. The current intention of the user can be directly reflected visually through the detected eye state information and mouth dynamic information, the judgment accuracy is improved, and the probability of mistaken awakening is reduced.
Further, the analyzing and judging whether the person intentionally starts the corresponding intelligent household appliance by using the neural network algorithm specifically includes: detecting and identifying the head direction and the elevation angle of a person, the face direction and the elevation angle and the pupil-eyeball occupancy ratio, and identifying and judging whether the person is watching a target intelligent household appliance or not through a deep learning cyclic neural network; if the user is watching the target intelligent household appliance, judging whether the mouth of the person is in a motion sound production state, and if the mouth of the person is in the motion sound production state, judging that the person intentionally starts the target intelligent household appliance. Whether the intelligent household appliance is watched or not is judged through information of the head and the face, then mouth movement is detected, the awakening operation is started, the detection mouth state is immediately started when the binocular camera detects the face, and the mouth movement is identified through the circular memory neural network matching algorithm model, so that the equipment can accurately identify that a user is about to control the equipment, the awakening is avoided, and the misjudgment rate is reduced.
Further, the identifying and judging whether the person is gazing at the target intelligent household appliance through the deep learning recurrent neural network specifically comprises: carrying out smooth denoising pretreatment on the obtained figure face image, then carrying out image feature extraction, processing the image information through a template classifier, carrying out algorithm comparison processing on the image information and a preset front face image, judging whether the offset angle of the face image meets the requirement that the upper, lower, left and right offset angles are within positive and negative y degrees, and if so, determining that a user is watching a target intelligent household appliance, wherein y is a preset angle value. The set image offset angle can effectively solve the problem of the recognition rate of the front face recognition of the image, effectively avoid the problem of high false recognition rate and improve the recognition rate.
Further, the preset gazing awakening relationship between the object and the intelligent household appliance specifically comprises: and setting one-to-one corresponding binding relationship between a plurality of groups of target objects and the intelligent household appliances, and setting the corresponding wake-up-free voice-controlled intelligent household appliance A by watching the target object A. The user does not need to wake up the name of the device each time the device is operated, and can directly look at a certain target object to control a certain intelligent household appliance.
Further, the identifying and judging whether the person is watching the target intelligent household appliance through the deep learning recurrent neural network specifically comprises: and if the person is judged not to be watching the target intelligent household appliance, ending the awakening process. When the user does not watch the target intelligent household appliance, the intention of awakening the intelligent household appliance is not shown, the next judgment is not needed, and the awakening is directly finished, so that the condition of mistaken awakening is avoided.
Further, the judging whether the mouth of the person is in the movement sound production state specifically includes: and if the mouth of the person is in a closed state, ending the awakening process. On the basis that the user watches the target intelligent household appliance, if the mouth of the person is closed, the user does not have the intention of awakening the intelligent household appliance, and the two-step judgment ensures the accuracy of awakening.
Further, the judging that the person intentionally starts the target intelligent household appliance specifically includes: the person mouth is in a movement sound production state, voice information is collected and recognized, and if the detected voice is recognized as a control command, the person enters an intelligent household appliance voice control state; and if the detected voice is not the control instruction, ending the awakening process. The detected voice is accurately analyzed and judged, and the recognition rate can be effectively improved.
A computer readable storage medium for storing a computer program, which when invoked by a processor implements the wake-up free speech recognition control method for an intelligent appliance as claimed in any one of the preceding claims.
An air conditioner comprises a processor and a memory, wherein the memory is used for storing a computer program, and the computer program realizes the wake-up-free voice recognition control method of the intelligent household appliance when being called by the processor.
The awakening-free voice recognition control method of the intelligent household appliance, the computer readable storage medium and the air conditioner have the advantages that: the intelligent household appliance is provided with a binocular camera technology, the watching condition and the mouth-shaped action of a human face are detected through an image recognition technology, the air conditioner is judged to be controlled by a user through processing and predicting image data by using a recurrent neural network, the air conditioner is in an awakening-free state at the moment, the user can directly speak a voice command to control the intelligent household appliance, and the non-inductive interaction experience of the user is improved; the user does not need to wake up the name of the equipment each time the equipment is operated, and can directly control the equipment by looking at the equipment, so that the interestingness of the wake-up control is increased.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic diagram of the LSTM recurrent neural network model of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person skilled in the art without making any inventive step are within the scope of protection of the present invention.
Example 1: a wake-up-free voice recognition control method for intelligent household appliances.
As shown in fig. 1, a wake-up-free voice recognition control method for an intelligent household appliance, which is specifically applied to a voice air conditioner, includes the following specific steps:
s1, presetting a gazing awakening relation between an object and an intelligent household appliance, specifically, setting one-to-one corresponding binding relation between a plurality of groups of target objects and the intelligent household appliance, configuring a binocular camera by a voice air conditioner, wherein the binocular camera can effectively avoid static pictures, detecting the dynamic states of the face and the head of a user in a visual area in real time, identifying whether the focusing positions of the eyes of the user correspond to the target objects, rapidly detecting and identifying the direction and the elevation angle of the head and the face of the user and the occupancy ratio of pupillary eyeball, and identifying and judging whether the user gazes at a certain target object through a deep learning cyclic neural network; the method comprises the steps of carrying out smooth denoising pretreatment on an obtained figure face image, then carrying out image feature extraction, processing image information through a template classifier, carrying out algorithm comparison processing on the image information and a preset front face image, judging whether a human face image offset angle meets the condition that the upper offset angle, the lower offset angle, the left offset angle and the right offset angle are within plus or minus 5 degrees, and if so, determining that a user is watching a target object;
s2, if the user is watching the target object, judging whether the mouth of the user is in a moving and sounding state;
s3, if the person is judged not to be gazed at the target object, the awakening process is ended;
s4, if the mouth belongs to the movement sound production state, collecting the sound information in the current time period, and the voice recognition module acquires whether the sound information corresponds to an effective control instruction;
s5, if the mouth of the person is judged to be in a closed state, ending the awakening process;
s6, when the voice control instruction is recognized, the voice air conditioner enters a voice control state;
and S7, ending the awakening process when the voice control command is not recognized.
As shown in fig. 2, the deep learning recurrent neural network is an LSTM recurrent neural network module, which specifically includes: firstly, a 'forgetting gate' layer is controlled by a sigmoid function, and the 'forgetting gate' layer can be output h according to the previous momentt−1(hidden state) and current input xtTo produce a f of 0 to 1t(forget gate value) to decide whether to let the last time learn the information Ct−1Through or partially through; secondly, new information to be updated is generated, and the step comprises two parts, namely a first part of 'input gate' layer determines which values are used for updating through a sigmoid function, and a second part of generating a new candidate value C through a tanh functiont(state) that it may be added to the cell state as a candidate value generated by the current layer, and then the two generated values are combined for updating; finally, the output gate obtains an initial output through the sigmoid function, and then uses the tanh function to output CtThe value is zoomed to be between-1 and 1, and then the value is multiplied by the output obtained by sigmoid pair by pair, thereby obtaining the output h of the modelt。
A target watched by a user is preset in a visual range of the air-conditioning binocular camera (the target can be a certain object or specific equipment, and pictures of the target watched by the user are all in a visual area of the camera), and the target A is set to correspond to the awakening-free voice direct control equipment A; the target B sets corresponding wake-up-free voice directly-controlled equipment B; the target C is set to correspond to the wake-up-free voice directly-controlled device C, and the like, and multiple presets can be performed. When the user is detected to look at a certain target, the user can be judged to control a certain device, and at the moment, the user can directly control the certain device by voice. If the user is detected to watch the target A, the air conditioner is immediately awakened to pick up sound, and the control instruction is forwarded to control the corresponding equipment 1.
In the embodiment, an air conditioner is placed in a room, dehumidifier equipment is placed in a visual range of a binocular camera of the air conditioner, the camera can recognize pictures of users watching the dehumidifier equipment, the pictures are preset, the equipment is set to be normally powered on and bound with each other, when the camera of the air conditioner detects that the users watch the dehumidifier equipment, the air conditioner immediately enters a state of no-wakeup listening pickup, and the users can directly control the dehumidifier through voice instructions. For example, in a room, a user watches dehumidifier equipment, the air conditioner enters a sound pickup state after detection, waits for a control instruction to be forwarded to the dehumidifier, and controls the dehumidifier, so that the awakening-free interaction of who says about who is seen is achieved.
Example 2: an awakening-free voice recognition control method for intelligent household appliances.
The difference from the embodiment 1 is that the target object is a picture, a vase and the like, and the binocular camera can recognize the picture of the picture watched by the user and the picture of the vase watched by the user. The device is preset, and when the user watches the picture, the device is set to correspond to the controllable water heater device, and when the user watches the vase, the device is set to correspond to the controllable air purifier device. When the binocular camera of the air conditioner detects that the user is watching the picture image of the picture, the air conditioner immediately enters a state of avoiding awakening and intercepting pickup, and the water heater equipment can be directly controlled by the voice command of the user. When the air conditioner camera detects that the user is watching the picture image of the vase, the air conditioner immediately enters a state of avoiding waking up and listening, and the user voice command can directly control the air purifier equipment.
Example 3: a computer readable storage medium.
A computer-readable storage medium for storing a computer program, wherein when the computer program is called by a processor, the wake-up-free voice recognition control method of an intelligent appliance according to embodiment 1 or embodiment 2 is implemented.
Example 4: an air conditioner.
An air conditioner comprises a processor and a memory, wherein the memory is used for storing a computer program, and when the computer program is called by the processor, the wake-up-free voice recognition control method of the intelligent household appliance in the embodiment 1 or the embodiment 2 is realized.
The above description is only for the preferred embodiment of the present invention, but the present invention should not be limited to the embodiment and the disclosure of the drawings, and therefore, all equivalent or modifications that do not depart from the spirit of the present invention are intended to fall within the scope of the present invention.
Claims (6)
1. A wake-up-free voice recognition control method of an intelligent household appliance is characterized in that a watching wake-up relationship between an object and the intelligent household appliance is preset, human body information of a person in the current environment is detected in real time through a visual sensor, a neural network algorithm is utilized to analyze and judge whether the person intentionally starts the corresponding intelligent household appliance, and if the person intentionally starts the corresponding intelligent household appliance, the intelligent household appliance enters a wake-up-free state to acquire voice information; the preset gazing awakening relationship between the object and the intelligent household appliance is specifically as follows: setting a one-to-one corresponding binding relationship between a plurality of groups of target objects and the intelligent household appliances, setting a corresponding wake-up-free voice-controllable intelligent household appliance A by watching a target object A,
the human body information of the figure in the current environment detected in real time through the visual sensor is specifically as follows: the binocular camera detects the dynamic information of the face and the head of the person in the visible area in real time, the dynamic information of the face specifically comprises eye state information and mouth dynamic information,
the method for analyzing and judging whether the person intentionally starts the corresponding intelligent household appliance by utilizing the neural network algorithm specifically comprises the following steps: detecting and identifying the head direction and the elevation angle of a person, the face direction and the elevation angle and the pupil-eyeball occupancy ratio, and identifying and judging whether the person is watching a target intelligent household appliance or not through a deep learning cyclic neural network; if the user is watching the target intelligent household appliance, judging whether the human mouth is in a motion sound production state, if so, judging whether the human is intentionally starting the target intelligent household appliance, and identifying and judging whether the human is watching the target intelligent household appliance through a deep learning cyclic neural network specifically comprises the following steps: if the person is judged not to be gazed at the target intelligent household appliance, the awakening process is ended, and the deep learning cyclic neural network is an LSTM cyclic neural network module, and specifically comprises the following steps: firstly, a forgetting gate layer is controlled by a sigmoid function, and generates a forgetting gate value ft from 0 to 1 according to an output hidden state ht-1 and a current input xt at the last moment so as to determine whether to pass or partially pass information Ct-1 learned at the last moment; secondly, new information needing to be updated is generated, the step comprises two parts, the first part of an 'input gate' layer determines which values are used for updating through a sigmoid function, the second part is that a tanh function generates a new candidate value state Ct which is possibly added into a cell state as a candidate value generated by the current layer, and the two parts of generated values are combined for updating; and finally, obtaining an initial output by the aid of a sigmoid function, then scaling the Ct value to a range from-1 to 1 by the aid of a tanh function, and multiplying the Ct value by the output obtained by the sigmoid pair by pair to obtain the output ht of the model.
2. The wake-up-free speech recognition control method for intelligent home appliances according to claim 1, wherein the determining whether the person is watching the target intelligent home appliance through deep learning recurrent neural network recognition specifically comprises: carrying out smooth denoising pretreatment on the obtained figure face image, then carrying out image feature extraction, processing the image information through a template classifier, carrying out algorithm comparison processing on the image information and a preset front face image, judging whether the offset angle of the face image meets the requirement that the upper, lower, left and right offset angles are within positive and negative y degrees, and if so, determining that a user is watching a target intelligent household appliance, wherein y is a preset angle value.
3. The wake-up-free voice recognition control method for the intelligent household appliance according to claim 1, wherein the judging whether the mouth of the person is in the motion and sound production state specifically comprises: and if the mouth of the person is in a closed state, ending the awakening process.
4. The wake-up-free voice recognition control method for intelligent home appliances according to claim 1, wherein the judging that the person intentionally starts the target intelligent home appliance specifically comprises: the person mouth is in a movement sound production state, voice information is collected and recognized, and if the detected voice is recognized as a control command, the person enters an intelligent household appliance voice control state; and if the detected voice is not the control instruction, ending the awakening process.
5. A computer-readable storage medium for storing a computer program, wherein the computer program, when being invoked by a processor, implements the wake-up-free speech recognition control method for an intelligent appliance according to any one of claims 1 to 4.
6. An air conditioner comprising a processor and a memory, wherein the memory is used for storing a computer program, and when the computer program is called by the processor, the method for controlling the wake-up-free voice recognition of the intelligent household appliance is realized according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911270433.8A CN111128157B (en) | 2019-12-12 | 2019-12-12 | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911270433.8A CN111128157B (en) | 2019-12-12 | 2019-12-12 | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111128157A CN111128157A (en) | 2020-05-08 |
| CN111128157B true CN111128157B (en) | 2022-05-27 |
Family
ID=70499139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911270433.8A Active CN111128157B (en) | 2019-12-12 | 2019-12-12 | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111128157B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112420043A (en) * | 2020-12-03 | 2021-02-26 | 深圳市欧瑞博科技股份有限公司 | Intelligent awakening method and device based on voice, electronic equipment and storage medium |
| CN113138560A (en) * | 2021-04-12 | 2021-07-20 | 维沃移动通信有限公司 | Terminal control method, device, equipment and readable storage medium |
| CN113593544A (en) * | 2021-06-11 | 2021-11-02 | 青岛海尔科技有限公司 | Device control method and apparatus, storage medium, and electronic apparatus |
| CN115691485A (en) * | 2021-07-26 | 2023-02-03 | 华为技术有限公司 | Equipment awakening method, related device and communication system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423228A (en) * | 2002-10-17 | 2003-06-11 | 南开大学 | Apparatus and method for identifying gazing direction of human eyes and its use |
| CN107239139A (en) * | 2017-05-18 | 2017-10-10 | 刘国华 | Based on the man-machine interaction method and system faced |
| CN108519819A (en) * | 2018-03-30 | 2018-09-11 | 北京金山安全软件有限公司 | Intelligent device processing method and device, intelligent device and medium |
| CN109977811A (en) * | 2019-03-12 | 2019-07-05 | 四川长虹电器股份有限公司 | The system and method for exempting from voice wake-up is realized based on the detection of mouth key position feature |
| CN110136714A (en) * | 2019-05-14 | 2019-08-16 | 北京探境科技有限公司 | Natural interaction sound control method and device |
| CN110335600A (en) * | 2019-07-09 | 2019-10-15 | 四川长虹电器股份有限公司 | The multi-modal exchange method and system of household appliance |
| CN110531853A (en) * | 2019-08-23 | 2019-12-03 | 西安交通大学 | A kind of E-book reader control method and system based on human eye fixation point detection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6964023B2 (en) * | 2001-02-05 | 2005-11-08 | International Business Machines Corporation | System and method for multi-modal focus detection, referential ambiguity resolution and mood classification using multi-modal input |
-
2019
- 2019-12-12 CN CN201911270433.8A patent/CN111128157B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423228A (en) * | 2002-10-17 | 2003-06-11 | 南开大学 | Apparatus and method for identifying gazing direction of human eyes and its use |
| CN107239139A (en) * | 2017-05-18 | 2017-10-10 | 刘国华 | Based on the man-machine interaction method and system faced |
| CN108519819A (en) * | 2018-03-30 | 2018-09-11 | 北京金山安全软件有限公司 | Intelligent device processing method and device, intelligent device and medium |
| CN109977811A (en) * | 2019-03-12 | 2019-07-05 | 四川长虹电器股份有限公司 | The system and method for exempting from voice wake-up is realized based on the detection of mouth key position feature |
| CN110136714A (en) * | 2019-05-14 | 2019-08-16 | 北京探境科技有限公司 | Natural interaction sound control method and device |
| CN110335600A (en) * | 2019-07-09 | 2019-10-15 | 四川长虹电器股份有限公司 | The multi-modal exchange method and system of household appliance |
| CN110531853A (en) * | 2019-08-23 | 2019-12-03 | 西安交通大学 | A kind of E-book reader control method and system based on human eye fixation point detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111128157A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111128157B (en) | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner | |
| TWI646444B (en) | Method for waking up intelligent robot and intelligent robot | |
| CN110291489B (en) | Computationally efficient human identification intelligent assistant computer | |
| CN111145739A (en) | Vision-based awakening-free voice recognition method, computer-readable storage medium and air conditioner | |
| CN104102181B (en) | Intelligent home control method, device and system | |
| WO2020083110A1 (en) | Speech recognition and speech recognition model training method and apparatus | |
| CN112051743A (en) | Device control method, conflict processing method, corresponding devices and electronic device | |
| WO2022110564A1 (en) | Smart home multi-modal human-machine natural interaction system and method thereof | |
| CN109767769A (en) | A kind of audio recognition method, device, storage medium and air-conditioning | |
| CN102932212A (en) | Intelligent household control system based on multichannel interaction manner | |
| CN106203380B (en) | Ultrasonic wave gesture identification method and system | |
| CN112101219B (en) | Intention understanding method and system for elderly accompanying robot | |
| CN103220583A (en) | System and method for detecting user fatigue degree based on smart television | |
| WO2018006374A1 (en) | Function recommending method, system, and robot based on automatic wake-up | |
| WO2022227775A1 (en) | Method and device for controlling air conditioner, and air conditioner | |
| CN110822648B (en) | Air conditioner, control method thereof, and computer-readable storage medium | |
| CN110426962A (en) | A kind of control method and system of smart home device | |
| CN108536027B (en) | Intelligent home control method and device and server | |
| CN109595757B (en) | Control method and device of air conditioner and air conditioner with control device | |
| SE545310C2 (en) | Improved turn-taking | |
| CN110213663A (en) | Audio and video playing method, computer equipment and computer readable storage medium | |
| CN110154048B (en) | Robot control method and device and robot | |
| CN111402096A (en) | Online teaching quality management method, system, equipment and medium | |
| CN107452381B (en) | Multimedia voice recognition device and method | |
| CN104615252A (en) | Control method, control device, wearable electronic device and electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |