CN109920404A - Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect - Google Patents
Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect Download PDFInfo
- Publication number
- CN109920404A CN109920404A CN201910096982.1A CN201910096982A CN109920404A CN 109920404 A CN109920404 A CN 109920404A CN 201910096982 A CN201910096982 A CN 201910096982A CN 109920404 A CN109920404 A CN 109920404A
- Authority
- CN
- China
- Prior art keywords
- module
- audio
- frequency characteristics
- audio frequency
- 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.)
- Pending
Links
Landscapes
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
Abstract
The invention discloses a kind of information collecting devices of automatic selling Advertising Management System for possessing Intellisense effect, including microphone array, audio feature extraction module, auditory localization module, voice identification module and voice feature database, the microphone array is located at the two sides of Self-help vending machine, the audio feature extraction module is connected with each microphone respectively, the auditory localization module, the corresponding sound source position of all kinds of audio frequency characteristics is calculated, and is sent to the voice identification module after sound source position to be met to the audio feature extraction of identification of sound source range;The voice identification module, for making further sampling to the audio frequency characteristics within the scope of identification of sound source and extracting to identify and meet the audio frequency characteristics of voice feature and issue recognition result.The present invention can improve the communication effect of advertisement video, and accuracy is higher not vulnerable to environmental noise influence, can be used in more complex environment, use scope is wider.
Description
Technical field
The present invention relates to Self-help vending machine fields, and in particular to possesses the automatic selling advertising management system of Intellisense effect
The information collecting device and acquisition method of system.
Background technique
Now, automatic vending machine is to be widely popularized to come in China.With the development of science and technology, automatic vending machine industry
It is moving towards information-based and is further realizing rationalization.Currently, automatic vending machine can not only carry out beverage, food, lottery ticket etc.)
The transaction of commodity, and in order to further increase income, automatic vending machine also carries out advertisement dispensing simultaneously, wide by playing video
It accuses, preferable effect can be obtained.
Currently, automatic vending machine mostly uses greatly list mode to play advertisement, i.e., both according to locally or remotely server end
The continual progress advertisement broadcasting of fixed sequence or start by set date and closing play different advertisements according to the time, although having
A little advertisement delivery systems can be restarted extensively using acquisition modes such as cameras to whether someone carries out identification before Self-help vending machine
Playback equipment is accused, reduces unnecessary energy waste and equipment loss to a certain degree, but camera acquisition has certain lag
Property, and can not being identified for the people not in camera acquisition range, and in advertisement video acoustic information can also attract it is potential
Consumer, therefore in order to further increase the communication effect of advertisement potential is disappeared by what voice identified not within the scope of camera
The person of expense is also critically important, when the information collecting device for lacking voice near energy effectively perceive in the prior art.
Summary of the invention
The purpose of the present invention is to provide a kind of information of automatic selling Advertising Management System for possessing Intellisense effect
Acquisition device, to solve the prior art can not accurately identify whether someone is close to self-service by sound effectively in more complex environment
The problem of vending machine.
The information collecting device of the automatic selling Advertising Management System for possessing Intellisense effect, including microphone
Array, audio feature extraction module, auditory localization module, voice identification module and voice feature database,
The microphone array is located at the two sides of Self-help vending machine, obtains external sound and is converted into audio-frequency information;
The audio feature extraction module is connected with each microphone respectively, the audio letter issued for receiving each microphone
Similar audio frequency characteristics are classified after number being sampled and are extracted, and send auditory localization for the audio frequency characteristics of each microphone of correspondence
Module;
The auditory localization module stores the location information and identification of sound source range of microphone, according to audio frequency characteristics
The positional information calculation of time of origin and microphone goes out the corresponding sound source position of all kinds of audio frequency characteristics, and sound source position is met sound
The voice identification module is sent to after the audio feature extraction of identifing source range;
The voice identification module, within the scope of identification of sound source audio frequency characteristics make further sampling and extract and from
The voice feature database transfers voice feature and is compared identification with audio frequency characteristics, when identifying that the audio for meeting voice feature is special
Corresponding identification signal is issued when sign to control module.
Preferably, noise reduction process module is equipped between the audio feature extraction module and the microphone array, it is described
Noise reduction process module is the good depth noise reduction autocoder of preparatory off-line training.
It preferably, further include temperature inductor, the temperature inductor is connected to the auditory localization module, the sound source
It is equipped in locating module and is stored with the storage unit that different temperatures corresponds to velocity of sound, the auditory localization module is selected according to environment temperature
It selects corresponding velocity of sound and calculates sound source position.
Preferably, the present apparatus further includes noise determination module and the secondary dry module of drop, and the noise discrimination module connects respectively
It is connected to the audio feature extraction module, auditory localization module and secondary noise reduction module, the secondary noise reduction module is also connected to
The audio feature extraction module, the noise determination module are used for the noise accounting after Detection and Extraction in audio frequency characteristics, according to
The given threshold of signal-to-noise ratio judges whether that, to the secondary noise reduction of audio frequency characteristics progress, the secondary dry module of drop is used for audio frequency characteristics
Audio feature extraction module is re-send to after carrying out secondary noise reduction.
The present invention also provides the information collecting methods for the automatic selling Advertising Management System for possessing Intellisense effect, adopt
With the information collecting device of the above-mentioned automatic selling Advertising Management System for possessing Intellisense effect, specific method includes following
Step:
S1, the microphone array are converted into audio signal and are separately sent to respective correspondence after obtaining the sound of ambient enviroment
Noise reduction process module;
S2, the audio signal after noise reduction carry out sampling in audio feature extraction module and divide similar audio frequency characteristics
Class extracts;
The correspondence wheat of S3, audio frequency characteristics that are similar but belonging to different microphone acquisitions in auditory localization module according to storage
The location information of gram wind carries out analytical calculation, obtains the position for corresponding to each sound source, and the audio that will meet identification of sound source range is special
Sign is extracted and is sent to voice identification module;
The audio frequency characteristics of S4, voice identification module after transferring various voice features in voice feature database and further extracting
It is compared identification, the audio frequency characteristics of identification signal and the different sound sources of correspondence for meeting voice feature are issued according to recognition result.
Preferably, in the step S1, to audio signal by being re-send to after noise reduction process modular filtration environmental noise
The audio feature extraction module.
Preferably, after the step S2 sound intermediate frequency feature extraction through noise discrimination module by signal-to-noise ratio and given threshold ratio
Compared with audio frequency characteristics are directly sent to the auditory localization module when greater than given threshold, are otherwise sent audio frequency characteristics to secondary
Noise reduction module re-sends to audio feature extraction module after secondary noise reduction, carries out sending after audio frequency characteristics classification is extracted again
To noise discrimination module.
The present invention has the advantage that by extracting, by noise reduction, sampling with the corresponding velocity of sound of temperature after acquisition ambient sound
The sound source position for measuring different audio frequency characteristics can accurately obtain the audio frequency characteristics that environmental noise is not belonging in setting range, then pass through
The further detections of audio frequency characteristics is determined and voice identification, can more accurately detect nearby whether someone, and than general
The range that logical image capture module obtains information is wider, and can perceive the personnel in video in acoustic information energy spread scope.
Therefore the communication effect of advertisement video can be improved, and accuracy is higher not vulnerable to environmental noise influence, can be used for more complex
In environment, use scope is wider.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the embodiment of the present invention.
Specific embodiment
Below against attached drawing, by the description of the embodiment, making further details of theory to the specific embodiment of the invention
It is bright, to help those skilled in the art to have more complete, accurate and deep reason to inventive concept of the invention, technical solution
Solution.
Embodiment 1:
As shown in Figure 1, the present invention provides a kind of automatic selling advertising management systems for possessing Intellisense effect
The information collecting device of system, including microphone array, audio feature extraction module, auditory localization module, voice identification module, people
Acoustic signature library, temperature inductor, noise reduction process module, noise determination module and the secondary dry module of drop, in which:
The microphone array is located at the two sides of Self-help vending machine, obtains external sound and is converted into audio-frequency information.
Noise reduction process module have it is multiple, be located between the audio feature extraction module and the microphone array, often
A noise reduction process module is connected with corresponding microphone, and is connected to the same audio feature extraction module.The noise reduction process
Module is the good depth noise reduction autocoder of preparatory off-line training.
Autocoder (DeepDenoisingAutoEncoder, DeepDAE) is to the speech characteristic parameter with noise
MFCC carries out noise reduction, and dedicated deep neural network algorithm can learn how to distinguish useless make an uproar from a large amount of voice data automatically
Sound and useful voice, and noise is separated from voice, restore clearly voice.
The audio feature extraction module is connected through noise reduction process module with each microphone, for receiving each microphone hair
Audio signal out, which classifies similar audio frequency characteristics after being sampled, to be extracted, and the audio frequency characteristics of each microphone of correspondence are sent
To auditory localization module;After the received similar audio feature of different microphones is corresponded to microphone number by audio feature extraction module
One group of audio feature information is extracted in classification, to facilitate auditory localization module to carry out localization process.Audio frequency characteristics include after extraction
May meet the requirements voice information, be both not belonging to voice also different from other acoustic informations and noise reduction of conventional environment noise after
Still remaining a small amount of noise information.
The noise discrimination module is connected respectively to the audio feature extraction module, auditory localization module and secondary noise reduction
Module, the noise determination module is for the noise accounting in audio frequency characteristics after Detection and Extraction, according to the given threshold of signal-to-noise ratio
Judge whether to carry out secondary noise reduction to audio frequency characteristics.Signal-to-noise ratio meets the requirements, and is sent to auditory localization module.
The secondary noise reduction module is also connected to the audio feature extraction module, and the secondary dry module of drop is used for sound
Frequency feature re-sends to audio feature extraction module after carrying out secondary noise reduction.Enter lower than the audio frequency characteristics of snr threshold secondary
Noise reduction module is decomposed into the audio frequency characteristics of corresponding each microphone again and carries out secondary noise reduction with the judgement of more high threshold, and will obtain
The audio frequency characteristics of the different microphones of correspondence be sent to audio feature extraction module, the latter will do it classification again and extract.The mistake
The signal-to-noise ratio that journey is recycled to audio frequency characteristics meets the requirements.
The auditory localization module stores the location information and identification of sound source range of microphone, according to audio frequency characteristics
The positional information calculation of time of origin and microphone goes out the corresponding sound source position of all kinds of audio frequency characteristics, and sound source position is met sound
The voice identification module is sent to after the audio feature extraction of identifing source range.Temperature inductor can issue temperature in the process
Information is spent, is equipped in auditory localization module and is stored with the storage unit that different temperatures corresponds to velocity of sound, the auditory localization module root
It selects corresponding velocity of sound to calculate sound source position according to environment temperature, more accurate sound source position information can be obtained in this way.
The voice identification module, within the scope of identification of sound source audio frequency characteristics make further sampling and extract and from
The voice feature database transfers voice feature and is compared identification with audio frequency characteristics, when identifying that the audio for meeting voice feature is special
Corresponding identification signal is issued when sign to control module.
The present invention also provides the information collecting methods for the automatic selling Advertising Management System for possessing Intellisense effect, adopt
With the information collecting device of the above-mentioned automatic selling Advertising Management System for possessing Intellisense effect, specific method includes following
Step:
S1, the microphone array obtain ambient enviroment sound after be converted into audio signal, drop is passed through to audio signal
The audio feature extraction module is re-send to after processing module of making an uproar filtering environmental noise.
S2, the audio signal after noise reduction carry out sampling in audio feature extraction module and divide similar audio frequency characteristics
Class extracts, after audio feature extraction through noise discrimination module by signal-to-noise ratio compared with given threshold, be greater than given threshold when
Audio frequency characteristics are directly sent to the auditory localization module, otherwise send secondary noise reduction module by secondary drop for audio frequency characteristics
Audio feature extraction module is re-send to after making an uproar, and carries out being sent to noise discrimination module after audio frequency characteristics classification is extracted again;
Above-mentioned secondary noise reduction process can be repeated when its signal-to-noise ratio of the audio frequency characteristics of extraction is lower than threshold value until noise
Than reaching requirement.Since audio frequency characteristics are the information of extracted mistake, noise reduction threshold value used in secondary noise reduction can be high
In noise reduction process module.
The correspondence wheat of S3, audio frequency characteristics that are similar but belonging to different microphone acquisitions in auditory localization module according to storage
The location information of gram wind carries out analytical calculation, obtains the position for corresponding to each sound source, and the audio that will meet identification of sound source range is special
Sign is extracted and is sent to voice identification module.
The audio frequency characteristics of S4, voice identification module after transferring various voice features in voice feature database and further extracting
It is compared identification, the audio frequency characteristics of identification signal and the different sound sources of correspondence for meeting voice feature are issued according to recognition result.
The present invention can improve the communication effect of advertisement video, and accuracy is higher not vulnerable to environmental noise influence, can use
In more complex environment, use scope is wider.
In the present invention unless specifically defined or limited otherwise, term " installation ", " connected ", " connection ", " fixation " etc.
Term shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral;It can be mechanical connect
It connects, is also possible to be electrically connected;It can be directly connected, can also can be in two elements indirectly connected through an intermediary
The interaction relationship of the connection in portion or two elements.It for the ordinary skill in the art, can be according to specific feelings
Condition understands the concrete meaning of above-mentioned term in the present invention.
In the present invention unless specifically defined or limited otherwise, fisrt feature in the second feature " on " or " down " can be with
It is that the first and second features directly contact or the first and second features pass through intermediary mediate contact.Moreover, fisrt feature exists
Second feature " on ", " top " and " above " but fisrt feature be directly above or diagonally above the second feature, or be merely representative of
First feature horizontal height is higher than second feature.Fisrt feature can be under the second feature " below ", " below " and " below "
One feature is directly under or diagonally below the second feature, or is merely representative of first feature horizontal height less than second feature.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
The present invention is exemplarily described above in conjunction with attached drawing, it is clear that the present invention implements not by aforesaid way
Limitation, it is or not improved as long as using the improvement for the various unsubstantialities that the method for the present invention conception and technical scheme carry out
Present inventive concept and technical solution are directly applied into other occasions, within that scope of the present invention.
Claims (7)
1. possessing the information collecting device of the automatic selling Advertising Management System of Intellisense effect, it is characterised in that: including wheat
Gram wind array, audio feature extraction module, auditory localization module, voice identification module and voice feature database,
The microphone array is located at the two sides of Self-help vending machine, obtains external sound and is converted into audio-frequency information;
The audio feature extraction module is connected with each microphone respectively, for receive audio signal that each microphone issues into
Similar audio frequency characteristics are classified after row sampling and are extracted, and send auditory localization mould for the audio frequency characteristics of each microphone of correspondence
Block;
The auditory localization module stores the location information and identification of sound source range of microphone, according to the generation of audio frequency characteristics
The positional information calculation of time and microphone goes out the corresponding sound source position of all kinds of audio frequency characteristics, and sound source position is met sound source and is known
The voice identification module is sent to after the audio feature extraction of other range;
The voice identification module, for making further sampling to the audio frequency characteristics within the scope of identification of sound source and extracting and from described
Voice feature database transfers voice feature and is compared identification with audio frequency characteristics, when identifying the audio frequency characteristics for meeting voice feature
Corresponding identification signal is issued to control module.
2. the information collection dress of the automatic selling Advertising Management System according to claim 1 for possessing Intellisense effect
It sets, it is characterised in that: noise reduction process module, the drop are equipped between the audio feature extraction module and the microphone array
Processing module of making an uproar is the good depth noise reduction autocoder of preparatory off-line training.
3. the information collection of the automatic selling Advertising Management System according to claim 1 or 2 for possessing Intellisense effect
Device, it is characterised in that: further include temperature inductor, the temperature inductor is connected to the auditory localization module, the sound
It is equipped in the locating module of source and is stored with the storage unit that different temperatures corresponds to velocity of sound, the auditory localization module is according to environment temperature
Corresponding velocity of sound is selected to calculate sound source position.
4. the information collection dress of the automatic selling Advertising Management System according to claim 2 for possessing Intellisense effect
It sets, it is characterised in that: further include noise determination module and the secondary dry module of drop, the noise discrimination module is connected respectively to described
Audio feature extraction module, auditory localization module and secondary noise reduction module, the secondary noise reduction module are also connected to the audio
Characteristic extracting module, the noise determination module is for the noise accounting in audio frequency characteristics after Detection and Extraction, according to signal-to-noise ratio
Given threshold judges whether that, to the secondary noise reduction of audio frequency characteristics progress, the secondary dry module of drop is used to carry out audio frequency characteristics secondary
Audio feature extraction module is re-send to after noise reduction.
5. possessing the information collecting method of the automatic selling Advertising Management System of Intellisense effect, it is characterised in that: using such as
The information collecting device of any automatic selling Advertising Management System for possessing Intellisense effect in claim 1-4,
Specific method includes the following steps:
S1, the microphone array are converted into audio signal and are separately sent to corresponding drop after obtaining the sound of ambient enviroment
It makes an uproar processing module;
S2, the audio signal after noise reduction carry out sampling in audio feature extraction module and propose the classification of similar audio frequency characteristics
It takes out;
The correspondence microphone of S3, audio frequency characteristics that are similar but belonging to different microphone acquisitions in auditory localization module according to storage
Location information carry out analytical calculation, obtain the position for corresponding to each sound source, and the audio frequency characteristics for meeting identification of sound source range are mentioned
It takes and is sent to voice identification module;
The audio frequency characteristics of S4, voice identification module after transferring various voice features in voice feature database and further extracting carry out
Compare identification, the audio frequency characteristics of identification signal and the different sound sources of correspondence for meeting voice feature are issued according to recognition result.
6. the information collection side of the automatic selling Advertising Management System according to claim 5 for possessing Intellisense effect
Method, it is characterised in that: in the step S1, to audio signal by re-sending to institute after noise reduction process modular filtration environmental noise
State audio feature extraction module.
7. the information collection side of the automatic selling Advertising Management System according to claim 6 for possessing Intellisense effect
Method, it is characterised in that: after the step S2 sound intermediate frequency feature extraction through noise discrimination module by signal-to-noise ratio compared with given threshold,
Audio frequency characteristics are directly sent to the auditory localization module when greater than given threshold, otherwise send secondary noise reduction for audio frequency characteristics
Module re-sends to audio feature extraction module after secondary noise reduction, carries out being sent to after audio frequency characteristics classification is extracted again and make an uproar
Sound discrimination module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910096982.1A CN109920404A (en) | 2019-01-31 | 2019-01-31 | Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910096982.1A CN109920404A (en) | 2019-01-31 | 2019-01-31 | Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109920404A true CN109920404A (en) | 2019-06-21 |
Family
ID=66961177
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910096982.1A Pending CN109920404A (en) | 2019-01-31 | 2019-01-31 | Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109920404A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110503975A (en) * | 2019-08-02 | 2019-11-26 | 广州长嘉电子有限公司 | Smart television speech enhan-cement control method and system based on multi-microphone noise reduction |
CN110570852A (en) * | 2019-08-09 | 2019-12-13 | 阿里巴巴集团控股有限公司 | service assisting method and device and electronic equipment |
CN110931011A (en) * | 2020-01-07 | 2020-03-27 | 杭州凯旗科技有限公司 | AI intelligent voice interaction method applied to intelligent retail equipment |
CN111047776A (en) * | 2020-02-21 | 2020-04-21 | 广州市历杰科技有限公司 | Novel voice control vending machine |
CN111883160A (en) * | 2020-08-07 | 2020-11-03 | 上海茂声智能科技有限公司 | Method and device for picking up and reducing noise of directional microphone array |
CN112446718A (en) * | 2019-08-28 | 2021-03-05 | 南京深视光点科技有限公司 | Voice advertisement system capable of being placed in specific personnel and implementation method thereof |
CN112884975A (en) * | 2021-01-22 | 2021-06-01 | 李习平 | Scenic spot commodity selling system based on solar street lamp |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1217608A2 (en) * | 2000-12-19 | 2002-06-26 | Hewlett-Packard Company | Activation of voice-controlled apparatus |
US20080312918A1 (en) * | 2007-06-18 | 2008-12-18 | Samsung Electronics Co., Ltd. | Voice performance evaluation system and method for long-distance voice recognition |
CN101819758A (en) * | 2009-12-22 | 2010-09-01 | 中兴通讯股份有限公司 | System of controlling screen display by voice and implementation method |
CN203288177U (en) * | 2013-06-14 | 2013-11-13 | 成都智元汇数码科技有限公司 | Information releasing internet of things terminal with human body induction function |
CN105938657A (en) * | 2016-06-27 | 2016-09-14 | 常州加美科技有限公司 | Auditory perception and intelligent decision making system of unmanned vehicle |
CN106356061A (en) * | 2016-10-24 | 2017-01-25 | 合肥华凌股份有限公司 | Voice recognition method and system based on sound source localization and intelligent household appliance |
CN106970356A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技(杭州)有限公司 | Auditory localization tracking under a kind of complex environment |
CN106998517A (en) * | 2016-01-22 | 2017-08-01 | 联发科技股份有限公司 | The method that electronic installation and audio are focused on again |
CN107450390A (en) * | 2017-07-31 | 2017-12-08 | 绵阳美菱软件技术有限公司 | A kind of intelligent electrical appliance control device, control method and control system |
CN107578537A (en) * | 2017-08-25 | 2018-01-12 | 深圳市维冠视界科技股份有限公司 | A kind of data push method of Self-help vending machine and Self-help vending machine |
CN107767867A (en) * | 2017-10-12 | 2018-03-06 | 深圳米唐科技有限公司 | Implementation method, device, system and storage medium based on Voice command network |
CN108269133A (en) * | 2018-03-23 | 2018-07-10 | 深圳悠易阅科技有限公司 | A kind of combination human bioequivalence and the intelligent advertisement push method and terminal of speech recognition |
CN108305627A (en) * | 2018-03-30 | 2018-07-20 | 合肥惠科金扬科技有限公司 | A kind of intelligent display and system |
-
2019
- 2019-01-31 CN CN201910096982.1A patent/CN109920404A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1217608A2 (en) * | 2000-12-19 | 2002-06-26 | Hewlett-Packard Company | Activation of voice-controlled apparatus |
US20080312918A1 (en) * | 2007-06-18 | 2008-12-18 | Samsung Electronics Co., Ltd. | Voice performance evaluation system and method for long-distance voice recognition |
CN101819758A (en) * | 2009-12-22 | 2010-09-01 | 中兴通讯股份有限公司 | System of controlling screen display by voice and implementation method |
CN203288177U (en) * | 2013-06-14 | 2013-11-13 | 成都智元汇数码科技有限公司 | Information releasing internet of things terminal with human body induction function |
CN106970356A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技(杭州)有限公司 | Auditory localization tracking under a kind of complex environment |
CN106998517A (en) * | 2016-01-22 | 2017-08-01 | 联发科技股份有限公司 | The method that electronic installation and audio are focused on again |
CN105938657A (en) * | 2016-06-27 | 2016-09-14 | 常州加美科技有限公司 | Auditory perception and intelligent decision making system of unmanned vehicle |
CN106356061A (en) * | 2016-10-24 | 2017-01-25 | 合肥华凌股份有限公司 | Voice recognition method and system based on sound source localization and intelligent household appliance |
CN107450390A (en) * | 2017-07-31 | 2017-12-08 | 绵阳美菱软件技术有限公司 | A kind of intelligent electrical appliance control device, control method and control system |
CN107578537A (en) * | 2017-08-25 | 2018-01-12 | 深圳市维冠视界科技股份有限公司 | A kind of data push method of Self-help vending machine and Self-help vending machine |
CN107767867A (en) * | 2017-10-12 | 2018-03-06 | 深圳米唐科技有限公司 | Implementation method, device, system and storage medium based on Voice command network |
CN108269133A (en) * | 2018-03-23 | 2018-07-10 | 深圳悠易阅科技有限公司 | A kind of combination human bioequivalence and the intelligent advertisement push method and terminal of speech recognition |
CN108305627A (en) * | 2018-03-30 | 2018-07-20 | 合肥惠科金扬科技有限公司 | A kind of intelligent display and system |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110503975A (en) * | 2019-08-02 | 2019-11-26 | 广州长嘉电子有限公司 | Smart television speech enhan-cement control method and system based on multi-microphone noise reduction |
CN110503975B (en) * | 2019-08-02 | 2022-02-01 | 广州长嘉电子有限公司 | Smart television voice enhancement control method and system based on multi-microphone noise reduction |
CN110570852A (en) * | 2019-08-09 | 2019-12-13 | 阿里巴巴集团控股有限公司 | service assisting method and device and electronic equipment |
CN112446718A (en) * | 2019-08-28 | 2021-03-05 | 南京深视光点科技有限公司 | Voice advertisement system capable of being placed in specific personnel and implementation method thereof |
CN110931011A (en) * | 2020-01-07 | 2020-03-27 | 杭州凯旗科技有限公司 | AI intelligent voice interaction method applied to intelligent retail equipment |
CN111047776A (en) * | 2020-02-21 | 2020-04-21 | 广州市历杰科技有限公司 | Novel voice control vending machine |
CN111047776B (en) * | 2020-02-21 | 2020-10-09 | 杭州必灵网络科技有限公司 | Novel voice control vending machine |
CN111883160A (en) * | 2020-08-07 | 2020-11-03 | 上海茂声智能科技有限公司 | Method and device for picking up and reducing noise of directional microphone array |
CN111883160B (en) * | 2020-08-07 | 2024-04-16 | 上海茂声智能科技有限公司 | Directional microphone array pickup noise reduction method and device |
CN112884975A (en) * | 2021-01-22 | 2021-06-01 | 李习平 | Scenic spot commodity selling system based on solar street lamp |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109920404A (en) | Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect | |
CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
CN109299683B (en) | Security protection evaluation system based on face recognition and behavior big data | |
EP2249288A2 (en) | Object detection | |
CN101095149B (en) | Image comparison apparatus and method | |
CN109657624A (en) | Monitoring method, the device and system of target object | |
CN110472870A (en) | A kind of cashier service regulation detection system based on artificial intelligence | |
CN111597999A (en) | 4S shop sales service management method and system based on video detection | |
CN102915638A (en) | Surveillance video-based intelligent parking lot management system | |
CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
CN108710827B (en) | A kind of micro- police service inspection in community and information automatic analysis system and method | |
CN110276265A (en) | Pedestrian monitoring method and device based on intelligent three-dimensional solid monitoring device | |
CN111814510B (en) | Method and device for detecting legacy host | |
CN107315993A (en) | A kind of peephole system and its face identification method based on recognition of face | |
CN111339927B (en) | Intelligent recognition system for working state of personnel in electric power business hall | |
CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
CN107566790A (en) | With reference to REID and the real time monitoring apparatus and method of Video Supervision Technique | |
CN113115229A (en) | Personnel trajectory tracking method and system based on Beidou grid code | |
CN111724199A (en) | Intelligent community advertisement accurate delivery method and device based on pedestrian active perception | |
CN111795716A (en) | Pipe gallery maintenance validity judgment method based on city perception microgrid | |
CN114067403A (en) | Old people self-help money depositing and withdrawing obstacle recognition method and device | |
CN109214320A (en) | People's vehicle correlating method and device based on video analysis | |
CN102184409A (en) | Machine-vision-based passenger flow statistics method and system | |
CN107705370A (en) | A kind of BRT bus rapid transits automatic ticket checker intelligence ticket card ticket checking system | |
CN109033999B (en) | Subway charge platform based on face recognition |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190621 |