CN107480129A - A kind of article position recognition methods and the system of view-based access control model identification and speech recognition - Google Patents
A kind of article position recognition methods and the system of view-based access control model identification and speech recognition Download PDFInfo
- Publication number
- CN107480129A CN107480129A CN201710584920.6A CN201710584920A CN107480129A CN 107480129 A CN107480129 A CN 107480129A CN 201710584920 A CN201710584920 A CN 201710584920A CN 107480129 A CN107480129 A CN 107480129A
- Authority
- CN
- China
- Prior art keywords
- article
- camera
- module
- access control
- speech recognition
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000000007 visual effect Effects 0.000 claims abstract description 30
- 230000001755 vocal effect Effects 0.000 claims description 11
- 238000004321 preservation Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses article position recognition methods and the system of a kind of identification of view-based access control model and speech recognition, the article position recognition methods of the identification of one of which view-based access control model and speech recognition includes step:S1:Identify voice keyword;S2:The voice keyword is compared with the default voice keyword preserved, matches corresponding article;S3:Image information is obtained by camera, and from described image acquisition of information asset position information;S4:Export the asset position information.The present invention utilizes visual identity and speech recognition system, when people bark out Classical correlation keyword, you can the physical location of Directory Enquiries article.Reduce the operation for finding article, improve Consumer's Experience.
Description
Technical field
The present invention relates to visual identity and technical field of voice recognition, more particularly to a kind of identification of view-based access control model and voice to know
Other article position recognition methods and system regions.
Background technology
Often have in daily life and can not find oneself or others loses the experience for putting thing position, typically pass through in the prior art
Either GPS looks for article or people to sound, specifically:Mobile phone is looked in interior, can not find mobile phone by another mobile phone dialing
Number, mobile phone plays incoming call music, and people judges particular location by music, and shortcoming can only exactly look for mobile phone, other things, example
Such as key, card etc. can not be realized;GPS looks for people, and in advance by GPS, 3G module is placed on the body of people to be looked for or on mobile object,
People can only can be just looked under this pattern in the case where there are GPS and 3G signals;Shortcoming is exactly can not indoors or no signal
Place uses.
Current vision identification location technology has had passes through specific algorithm compared with much progress, depth camera or binocular camera
The specific location information of article identified in visual range can be accomplished, accomplish to look for east in household rooms according to this technology can
The purpose in west;
Speech recognition technology has also obtained the lifting of matter in recent years, can reach the journey with people's normally interactive voice
Degree.
Publication No. 105872460A Chinese patent, there is provided it is related to a kind of Indoor Video technical field, more particularly to
A kind of invention of indoor article tracking location system, including RFID indoor positioning devices, computer and video camera, RFID indoor positionings
Equipment is connected with computer, and computer is connected with video camera, in the use of the present invention, to stick corresponding electricity on article indoors in advance
Subtab, after RFID indoor positioning devices read the label information on indoor article, label substance and positional information are uploaded
To computer, computer is handled and counted to information, then translates into the signal of video camera to send video camera to, control images
Machine turns to article position and taken pictures, and can so realize the real-time tracing positioning to indoor article, fast and accurately
Make an inventory Item Information, whole system uses more convenient.
Indoor article tracking location system can only realize indoor article tracing and positioning disclosed in above-mentioned patent, wherein following the trail of thing
Product also need to it is labelled to article in advance, it is cumbersome, and can not realize that voice and equipment intersection query article are current
The function of position.
In summary, it is necessary to propose that one kind can be interacted simply, the side of indoor general article or non-mobile phone article is accurately positioned
Method.
The content of the invention
The technical problem to be solved in the present invention purpose is to provide a kind of article position of view-based access control model identification and speech recognition
Recognition methods and system are put, for solving in the prior art by distinguishing sound that article sends or finding article by GPS
When can not be accurately positioned the problem of searching out article.
In order to solve the above technical problems, the technical solution adopted by the present invention is:1st, a kind of view-based access control model identification and voice are known
Other article position recognition methods, it is characterised in that:Including step:
S1:Identify voice keyword;
S2:The voice keyword is compared with the default voice keyword preserved, matches corresponding article;
S3:Image information is obtained by camera, and from described image acquisition of information asset position information;
S4:Export the asset position information.
The default preservation voice keyword specifically includes step:
Article is identified by camera and demarcated;
Identify goods attribute;
Demarcate the position of article;
Generate the voice keyword of article;
Preserve the goods attribute, asset position information and corresponding article voice keyword.
Further, the position of the demarcation article includes step:
Measure camera and the actual range on ground;
According to camera and the actual range of bottom surface, the relative distance for being identified article and another article is calculated.
Exporting the asset position information includes:
The article photo is sent to customer mobile terminal or mailbox, the article position is marked out in the described article photo
Put;Or by identifying the relative position of article and another article described in verbal announcement user.
The camera uses depth camera;
Or the camera uses binocular vision camera.
A kind of article position identifying system of view-based access control model identification and speech recognition, including:
Sound identification module, for identifying voice keyword;
Comparing module, for the voice keyword to be compared with the default voice keyword preserved, match pair
The article answered;
Acquisition module, image information is obtained by camera, and from described image acquisition of information asset position information;
Output module, for exporting the asset position information.Also include:Data acquisition module, for identifying article simultaneously
Demarcation and identification goods attribute, generate voice keyword.
The data acquisition module includes;
Visual identity module, for identifying article and goods attribute by camera;
Demarcating module, for demarcating article and demarcation article position;
Voice keyword module is generated, for generating the voice keyword of article.
Wherein demarcating module includes:
Laser range sensor, for measuring the actual range of camera and ground;
Computing module, for the actual range according to camera and bottom surface, calculate the phase for being identified article and another article
Adjust the distance.
Further, the output module also includes:
Photo module is sent, for sending the article photo to customer mobile terminal or mailbox, the described article photo
In mark out the article position;
Verbal announcement module, for the relative position by identifying article and another article described in verbal announcement user.
The beneficial effects of the invention are as follows:The article that the present invention can identify according to visual identifying system, and calculate by
The relative distance of object and other articles is identified, multiple different speech recognition keywords are generated, when people bark out Classical correlation
Keyword, you can the physical location of Directory Enquiries article.The present invention inquires article position by interactive voice, and can be known by vision
Other system or voice precisely inquire about the physical location of article, reduce operation, improve Consumer's Experience.
Brief description of the drawings
Fig. 1 is the method flow diagram one of the article position identification of view-based access control model of the present invention identification and speech recognition.
Fig. 2 is that data acquisition of the present invention preserves flow chart.
Fig. 3 is the method flow diagram two of the article position identification of view-based access control model of the present invention identification and speech recognition.
Fig. 4 is the system construction drawing of the article position identification of view-based access control model of the present invention identification and speech recognition.
Fig. 5 is data acquisition module of the present invention and notification module system construction drawing.
Embodiment
It is the specific embodiment of the present invention and with reference to accompanying drawing below, technical scheme is further described,
But the present invention is not limited to these embodiments.
Embodiment one
Present embodiments provide a kind of article position of view-based access control model identification and speech recognition and know method for distinguishing, such as Fig. 1 extremely
Shown in Fig. 3, it includes step:
S1:Identify voice keyword;
S2:The voice keyword is compared with the default voice keyword preserved, matches corresponding article;
S3:Image information is obtained by camera, and from described image acquisition of information asset position information;
S4:Export the asset position information.
Voice is the most natural, means of most convenient of progress exchange of information between people.Voice technology is as conventional people
Machine exchange method, allows the language of the machine recognition mankind;Wherein keyword identification, which can be used for detecting in voice flow, whether there is thing
First given order word.
In the technical program, wherein it is default preserve voice keyword include determining in advance article in visual identifying system,
Goods attribute, article position and generation article keyword.As shown in Fig. 2 data acquisition preservation flow charts of the present invention, it includes
Step:Identify goods attribute;Demarcate the position of article;Generate the voice keyword of article;Preserve the goods attribute, article position
Confidence ceases and corresponding article voice keyword.
Wherein meeting power-up initializing visual identifying system before identification article, advance power-up initializing visual identifying system,
It can prevent that forming repetition to the article stored afterwards stores up by the Item Information stored before in visual identifying system to removing
Deposit, cause storage information incorrect;Then visual identifying system is carried out from performing check self-test, judges that visual identifying system whether can
Normal work, after the completion of visual identifying system carries out self-test, that is, carry out data acquisition and preservation.
When user is come into the range of visual identity, and places an article, visual identifying system identification article, and to thing
Product are demarcated, and after article is demarcated successfully, visual identifying system identification goods attribute, after identification goods attribute success, vision is known
Other system, the position for demarcating article and the voice keyword for generating article, preserve the goods attribute, article position and article
Voice crux word.
The position of wherein visual identifying system demarcation article is surveyed by the laser range sensor in visual identifying system
Go out camera and the actual range on ground, the phase of identified object or article and another article is gone out according to actual distance calculation
Adjust the distance, wherein held ceiling middle position indoors, so that the visual measurement range of camera is whole room
Between, the maximum area that camera observed can be calculated according to the height with ground, by visual identity by the sight of camera
Survey area and be divided into the uniform equal grid of area by a certain percentage, thus measure the relative distance of article and article.
Wherein described camera uses depth camera;Or the camera uses binocular vision camera
The depth camera is also known as 3D sensors, and the difference of 3D depth cameras and common camera is, except
Plane picture can be obtained, the depth information of reference object, that is, three-dimensional positions and dimensions information can also be obtained, then
Whole computing system just obtains the three-dimensional stereo data of environment and object, and these information can be used in human body tracking, Three-dimensional Gravity
Build, man-machine interaction, the field such as SLAM.
Depth camera possesses advantages below:
1) relative two dimensional image, the position relationship more enriched between object can be obtained by range information, that is, before distinguishing
Scape and background;
2) depth information remains unchanged and can complete the tradition such as segmentation to target image, mark, identification, tracking and apply;
3) handled by further in-depth, the application such as three-dimensional modeling can be completed;
4) identification and tracking to target can be rapidly completed;
5) key fitment relative inexpensiveness, including CCD and common LED etc., have to universalness production from now on and use
Profit;
6) by CMOS characteristic, mass data and information can be obtained, extremely effective, nothing is judged to the posture of complex object
Need scanning device back work.
Wherein binocular camera is to belong to one kind of depth camera, and binocular camera is to use two or more
Camera simultaneously gather image, the difference of the image obtained by comparing these different cameras in synchronization, use calculation
Method calculates depth information, so as to polygonal three-dimensional imaging.Left and right stereopsis is obtained by using 2 video cameras, the image has
A little slight shifts, with the same sequence of human eye.Computer is by comparing the two images, so that it may obtains and corresponds to ohject displacement in image
Different images.The different images or map can be colored, or GTG, be specifically dependent upon the demand of particular system.
The advantages of binocular polygonal three-dimensional imaging scheme, is the interference for being not readily susceptible to ambient light, is adapted to outdoor environment, meets that 24 is small
When the requirement that works long hours, be hardly damaged.
Therefore depth camera and binocular camera are suitable as the identification in visual identifying system in the technical program
Function.
When user begins look for article, voice says the article of searching, the speech recognition system on camera immediately with
The default voice keyword preserved is compared, and the positional information of article corresponding to inquiry and article, matches corresponding thing
After the positional information of product and article, by the camera in visual identifying system, article position is confirmed, and judge article position
The article when upper also be present, if the article also exists, it will the article photo on one article position of shooting;Pass through nothing
Gauze network sends the photo article position to the mobile terminal of user or mailbox, notified where the article to be found of user
Put.
Article position where wherein notifying the article to be found of user also has another method, i.e., by camera upper
State in scheme, calculated by three dimensions, the relative position of each article and other articles, its relative position is preserved, by taking the photograph
As the voice module on head informs relative position of the consumer articles currently with other articles.
The present embodiment, there is provided a kind of article position of view-based access control model identification and speech recognition knows method for distinguishing, Neng Gougen
The article identified according to the depth camera in visual identifying system or binocular camera, and calculate identified object and its
The relative distance of his article, multiple different speech recognition keywords are generated, when people bark out Classical correlation keyword, you can look into
The physical location of article at inquiry.The present invention inquires article position by interactive voice, and can pass through visual identifying system or language
Sound precisely inquires about the physical location of article, reduces the operation for finding article, improves Consumer's Experience.
Embodiment two
The system that a kind of article position of view-based access control model identification and speech recognition identifies is present embodiments provided, such as Fig. 4 sheets
Shown in the system construction drawing that invention view-based access control model identifies and the article position of speech recognition identifies, it includes:
Sound identification module, for identifying voice keyword;
Comparing module, for the voice keyword to be compared with the default voice keyword preserved, match pair
The article answered;
Acquisition module, image information is obtained by camera, and from described image acquisition of information asset position information;
Output module, for exporting the asset position information.Wherein sound identification module is provided on camera,
Camera in the present embodiment is with embodiment one, and using depth camera or using binocular camera, when user starts
When finding certain article, after saying the Item Information to be found, wherein sound identification module, by speech analysis, determine that user will
The voice keyword of the article of searching.And voice key word information is sent to comparing module.
Comparing module, after receiving the article voice key word information to be found of user, by the voice keyword with presetting
The voice keyword of preservation is compared, and matches the positional information of corresponding article and article, and the correspondence that will be matched
Article and asset position information send to confirm module.
Acquisition module, after receiving the article that user finds article matching, pass through depth camera or binocular camera
Obtain image information, and from described image acquisition of information asset position information, this acquisition module confirm article whether place and
After data acquisition preserves, whether there is other people and move article position without being preserved to it;Reduce and find article mortality.
After confirming also to there are the article on the good article position, the notice output module output asset position information.
Output module, after the image information for receiving acquisition module, export the positional information of the article.
Wherein output module is transmitted by the wireless network where current system.
The present embodiment, there is provided the system that a kind of article position of view-based access control model identification and speech recognition identifies, pass through language
Sound identification module and comparing module in sound identifying system determine the Item Information and positional information that user to be found, and pass through
Visual identifying system, confirm that article position whether there is the article, and by shoot photo and send to customer mobile terminal with
Mailbox, notify consumer articles positional information.Realize by interactive voice and visual identity, and depth camera, simple side
Just the function of article position, is quickly determined.Improve Consumer's Experience.
Embodiment three
Present embodiments provide the data in the system that a kind of article position of view-based access control model identification and speech recognition identifies
Acquisition module and notification module;As shown in Fig. 5 data acquisition modules of the present invention and notification module system construction drawing:
Data acquisition module, for identifying article and demarcating article and identification goods attribute, generation article voice is crucial
Word;
Its data acquisition module also includes:Visual identity module, for identifying article and goods attribute by camera;
When user is come into range of video, and after placing an article, visual identity module identifies the article and the article immediately
Attribute.
Demarcating module, for demarcating article and demarcation article position;
Voice keyword module is generated, for generating the voice keyword of article.
Wherein demarcating module includes:Laser range sensor, for measuring the actual range of camera and ground;
Computing module, for the actual range according to camera and bottom surface, calculate the phase for being identified article and another article
Adjust the distance.
Wherein held ceiling middle position indoors, so that the visual measurement range of camera is whole room
Between, the maximum area that camera observed can be calculated according to the height with ground, by visual identity by the sight of camera
Survey area and be divided into the uniform equal grid of area by a certain percentage, thus measure the relative distance of article and article, preserve
The position of the article.
Further, output module includes:
Photo module is sent, for sending the article photo to customer mobile terminal or mailbox, the described article photo
In mark out the article position.The picture that user can receive according to mobile terminal or mailbox, judges the position where article
Put, then find the article.
Verbal announcement module, for the relative position by identifying article and another article described in verbal announcement user, when
User is after article is begun look for, and after saying Item Information, identifies voice keyword, and the voice keyword is protected with default
The voice keyword deposited is compared, and matches the positional information of corresponding article and article, confirms exist on article position
After the article;According to the relative distance of default preservation article and article, notify to identify article described in user by verbal announcement
With the relative position of another article.
The present embodiment, there is provided the system that a kind of article position of view-based access control model identification and speech recognition identifies, compared to reality
Apply in example two, add data acquisition module and verbal announcement module, asset position information is found by verbal announcement user, made
It is more simple and efficient to obtain user's searching article.
Specific embodiment described herein is only to spirit explanation for example of the invention.Technology belonging to the present invention is led
The technical staff in domain can be made various modifications or supplement to described specific embodiment or be replaced using similar mode
Generation, but without departing from the spiritual of the present invention or surmount scope defined in appended claims.
Claims (10)
1. a kind of view-based access control model identification and the article position recognition methods of speech recognition, it is characterised in that:Including step:
S1:Identify voice keyword;
S2:The voice keyword is compared with the default voice keyword preserved, matches corresponding article;
S3:Image information is obtained by camera, and from described image acquisition of information asset position information;
S4:Export the asset position information.
2. a kind of view-based access control model identification according to claim 1 and the article position recognition methods of speech recognition, its feature
It is, the default preservation voice keyword specifically includes step:
Article is identified by camera and demarcated;
Identify goods attribute;
Demarcate the position of article;
Generate the voice keyword of article;
Preserve the goods attribute, asset position information and corresponding article voice keyword.
3. a kind of view-based access control model identification according to claim 2 and the article position recognition methods of speech recognition, its feature
It is, the position of the demarcation article includes step:
Measure camera and the actual range on ground;
According to camera and the actual range of bottom surface, the relative distance for being identified article and another article is calculated.
4. a kind of view-based access control model identification according to claim 3 and the article position recognition methods of speech recognition, its feature
It is, exporting the asset position information includes:
The article photo is sent to customer mobile terminal or mailbox, the article position is marked out in the described article photo;
Or by identifying the relative position of article and another article described in verbal announcement user.
5. a kind of view-based access control model identification according to claim 4 and the article position recognition methods of speech recognition, its feature
It is:
The camera uses depth camera;
Or the camera uses binocular vision camera.
6. a kind of view-based access control model identification and the article position identifying system of speech recognition, it is characterised in that including:
Sound identification module, for identifying voice keyword;
Comparing module, for the voice keyword to be compared with the default voice keyword preserved, match corresponding
Article;
Acquisition module, image information is obtained by camera, and from described image acquisition of information asset position information;
Output module, for exporting the asset position information.
7. a kind of view-based access control model identification according to claim 6 and the article position identifying system of speech recognition, its feature
It is, including:
Data acquisition module, for identifying article and demarcating and identify goods attribute, generate voice keyword.
8. a kind of view-based access control model identification according to claim 7 and the article position identifying system of speech recognition, its feature
It is, the data acquisition module includes;
Visual identity module, for identifying article and goods attribute by camera;
Demarcating module, for demarcating article and demarcation article position;
Voice keyword module is generated, for generating the voice keyword of article.
9. a kind of view-based access control model identification according to claim 8 and the article position identifying system of speech recognition, its feature
It is, demarcating module includes:
Laser range sensor, for measuring the actual range of camera and ground;
Computing module, for the actual range according to camera and bottom surface, calculate identified article with another article it is relative away from
From.
10. a kind of view-based access control model identification according to claim 6 and the article position identifying system of speech recognition, its feature
It is, the output module also includes:
Photo module is sent, for sending the article photo to customer mobile terminal or mailbox, the article photo acceptance of the bid
Outpour the article position;
Verbal announcement module, for the relative position by identifying article and another article described in verbal announcement user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710584920.6A CN107480129A (en) | 2017-07-18 | 2017-07-18 | A kind of article position recognition methods and the system of view-based access control model identification and speech recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710584920.6A CN107480129A (en) | 2017-07-18 | 2017-07-18 | A kind of article position recognition methods and the system of view-based access control model identification and speech recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107480129A true CN107480129A (en) | 2017-12-15 |
Family
ID=60595251
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710584920.6A Pending CN107480129A (en) | 2017-07-18 | 2017-07-18 | A kind of article position recognition methods and the system of view-based access control model identification and speech recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107480129A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108769626A (en) * | 2018-07-25 | 2018-11-06 | 深圳市凯木金科技有限公司 | A kind of intelligent monitoring pick-up head |
CN109189885A (en) * | 2018-08-31 | 2019-01-11 | 广东小天才科技有限公司 | Real-time control method based on intelligent equipment camera and intelligent equipment |
CN109522811A (en) * | 2018-10-23 | 2019-03-26 | 中国人民解放军海军航空大学 | A kind of reaching materials system and method |
CN109599105A (en) * | 2018-11-30 | 2019-04-09 | 广州富港万嘉智能科技有限公司 | Dish method, system and storage medium are taken based on image and the automatic of speech recognition |
CN109848982A (en) * | 2018-11-30 | 2019-06-07 | 广州富港万嘉智能科技有限公司 | It is a kind of that dish method, system and storage medium are taken based on image recognition automatically |
CN109993045A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视***技术有限公司 | Articles seeking method and lookup device search system and machine readable storage medium |
JP2019129392A (en) * | 2018-01-24 | 2019-08-01 | 沖電気工業株式会社 | Home appliance and location search system |
WO2019154282A1 (en) * | 2018-02-08 | 2019-08-15 | 广东美的厨房电器制造有限公司 | Household appliance and voice recognition method, control method and control device thereof |
CN111048081A (en) * | 2019-12-09 | 2020-04-21 | 联想(北京)有限公司 | Control method, control device, electronic equipment and control system |
CN111476126A (en) * | 2020-03-27 | 2020-07-31 | 海信集团有限公司 | Indoor positioning method and system and intelligent equipment |
CN113095230A (en) * | 2021-04-14 | 2021-07-09 | 北京深睿博联科技有限责任公司 | Method and device for helping blind person to search for articles |
CN113488055A (en) * | 2020-04-28 | 2021-10-08 | 海信集团有限公司 | Intelligent interaction method, server and intelligent interaction equipment |
CN113936388A (en) * | 2020-07-13 | 2022-01-14 | 虫极科技(北京)有限公司 | Device and method for automatically selling food |
TWI781411B (en) * | 2020-04-21 | 2022-10-21 | 英華達股份有限公司 | System and method for quickly searching for object |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1682279A (en) * | 2002-09-16 | 2005-10-12 | 松下电器产业株式会社 | System and method of media file access and retrieval using speech recognition |
WO2014196038A1 (en) * | 2013-06-05 | 2014-12-11 | 三菱電機株式会社 | Device for processing information through line-of-sight detection and information processing method |
CN104219628A (en) * | 2014-08-29 | 2014-12-17 | 南京信息职业技术学院 | Blind person information service method and system based on augmented reality and smart phone |
US20150088833A1 (en) * | 2013-09-26 | 2015-03-26 | Samsung Electronics Co., Ltd. | Method for providing related information regarding retrieval place and electronic device thereof |
CN204856845U (en) * | 2015-06-22 | 2015-12-09 | 上海卓易科技股份有限公司 | Positioner and have positioner's article |
-
2017
- 2017-07-18 CN CN201710584920.6A patent/CN107480129A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1682279A (en) * | 2002-09-16 | 2005-10-12 | 松下电器产业株式会社 | System and method of media file access and retrieval using speech recognition |
WO2014196038A1 (en) * | 2013-06-05 | 2014-12-11 | 三菱電機株式会社 | Device for processing information through line-of-sight detection and information processing method |
US20150088833A1 (en) * | 2013-09-26 | 2015-03-26 | Samsung Electronics Co., Ltd. | Method for providing related information regarding retrieval place and electronic device thereof |
CN104219628A (en) * | 2014-08-29 | 2014-12-17 | 南京信息职业技术学院 | Blind person information service method and system based on augmented reality and smart phone |
CN204856845U (en) * | 2015-06-22 | 2015-12-09 | 上海卓易科技股份有限公司 | Positioner and have positioner's article |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109993045B (en) * | 2017-12-29 | 2021-02-26 | 杭州海康威视***技术有限公司 | Article searching method, article searching device, article searching system and machine-readable storage medium |
CN109993045A (en) * | 2017-12-29 | 2019-07-09 | 杭州海康威视***技术有限公司 | Articles seeking method and lookup device search system and machine readable storage medium |
JP2019129392A (en) * | 2018-01-24 | 2019-08-01 | 沖電気工業株式会社 | Home appliance and location search system |
WO2019154282A1 (en) * | 2018-02-08 | 2019-08-15 | 广东美的厨房电器制造有限公司 | Household appliance and voice recognition method, control method and control device thereof |
CN108769626A (en) * | 2018-07-25 | 2018-11-06 | 深圳市凯木金科技有限公司 | A kind of intelligent monitoring pick-up head |
CN109189885A (en) * | 2018-08-31 | 2019-01-11 | 广东小天才科技有限公司 | Real-time control method based on intelligent equipment camera and intelligent equipment |
CN109522811A (en) * | 2018-10-23 | 2019-03-26 | 中国人民解放军海军航空大学 | A kind of reaching materials system and method |
CN109599105A (en) * | 2018-11-30 | 2019-04-09 | 广州富港万嘉智能科技有限公司 | Dish method, system and storage medium are taken based on image and the automatic of speech recognition |
CN109848982A (en) * | 2018-11-30 | 2019-06-07 | 广州富港万嘉智能科技有限公司 | It is a kind of that dish method, system and storage medium are taken based on image recognition automatically |
CN111048081A (en) * | 2019-12-09 | 2020-04-21 | 联想(北京)有限公司 | Control method, control device, electronic equipment and control system |
CN111476126A (en) * | 2020-03-27 | 2020-07-31 | 海信集团有限公司 | Indoor positioning method and system and intelligent equipment |
CN111476126B (en) * | 2020-03-27 | 2024-02-23 | 海信集团有限公司 | Indoor positioning method, system and intelligent device |
TWI781411B (en) * | 2020-04-21 | 2022-10-21 | 英華達股份有限公司 | System and method for quickly searching for object |
CN113488055A (en) * | 2020-04-28 | 2021-10-08 | 海信集团有限公司 | Intelligent interaction method, server and intelligent interaction equipment |
CN113488055B (en) * | 2020-04-28 | 2024-03-08 | 海信集团有限公司 | Intelligent interaction method, server and intelligent interaction device |
CN113936388A (en) * | 2020-07-13 | 2022-01-14 | 虫极科技(北京)有限公司 | Device and method for automatically selling food |
CN113095230A (en) * | 2021-04-14 | 2021-07-09 | 北京深睿博联科技有限责任公司 | Method and device for helping blind person to search for articles |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107480129A (en) | A kind of article position recognition methods and the system of view-based access control model identification and speech recognition | |
CA3019224C (en) | Information display method, device, and system | |
CN105279750B (en) | It is a kind of that guide system is shown based on the equipment of IR-UWB and image moment | |
CN110017841A (en) | Vision positioning method and its air navigation aid | |
CN104936283B (en) | Indoor orientation method, server and system | |
EP2321953B1 (en) | Image annotation on portable devices | |
WO2021068356A1 (en) | User-to-exhibit-distance-based cooperative interaction method and system for augmented reality museum | |
CN106291517A (en) | Indoor cloud robot angle positioning method based on position and visual information optimization | |
CN107093171A (en) | A kind of image processing method and device, system | |
CN104641399A (en) | System and method for creating an environment and for sharing a location based experience in an environment | |
CN104838230B (en) | For identifying the equipment, system and method for the object in image and transponder | |
JPWO2009038149A1 (en) | Video provision system and video provision method | |
JP2023541619A (en) | Warehouse storage robot positioning and map creation method, robot and storage medium | |
CN110431378A (en) | Position signaling relative to autonomous vehicle and passenger | |
CN107977082A (en) | A kind of method and system for being used to AR information be presented | |
CN110168615A (en) | Information processing equipment, information processing method and program | |
CN106038183A (en) | Wearable device and navigation system for blind people | |
Feng et al. | Visual Map Construction Using RGB‐D Sensors for Image‐Based Localization in Indoor Environments | |
CN108318024A (en) | A kind of geo-positioning system and method based on image recognition cloud service | |
CN102946476B (en) | Rapid positioning method and rapid positioning device | |
CN113794872B (en) | Image recognition system based on AR intelligent glasses | |
WO2019127320A1 (en) | Information processing method and apparatus, cloud processing device, and computer program product | |
CN105847679B (en) | Image acquisition method and electronic equipment | |
CN109033164A (en) | A kind of panoramic map data acquisition system and its moving gathering termination | |
CN112055033B (en) | Interaction method and system based on optical communication device |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201102 Address after: 318015 no.2-3167, zone a, Nonggang City, no.2388, Donghuan Avenue, Hongjia street, Jiaojiang District, Taizhou City, Zhejiang Province Applicant after: Taizhou Jiji Intellectual Property Operation Co.,Ltd. Address before: 201616 Shanghai city Songjiang District Sixian Road No. 3666 Applicant before: Phicomm (Shanghai) Co.,Ltd. |