CN110473015A - A kind of smart ads system and advertisement placement method - Google Patents
A kind of smart ads system and advertisement placement method Download PDFInfo
- Publication number
- CN110473015A CN110473015A CN201910734391.2A CN201910734391A CN110473015A CN 110473015 A CN110473015 A CN 110473015A CN 201910734391 A CN201910734391 A CN 201910734391A CN 110473015 A CN110473015 A CN 110473015A
- Authority
- CN
- China
- Prior art keywords
- data
- pedestrian
- advertisement
- equipment
- processing
- 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
- 238000012545 processing Methods 0.000 claims abstract description 80
- 238000011282 treatment Methods 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000011221 initial treatment Methods 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 abstract description 8
- 238000013527 convolutional neural network Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000007906 compression Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F9/00—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements
- G09F9/30—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements in which the desired character or characters are formed by combining individual elements
- G09F9/33—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements in which the desired character or characters are formed by combining individual elements being semiconductor devices, e.g. diodes
Abstract
The invention discloses a kind of smart ads systems, comprising: edge end equipment, processing locality equipment, cloud device and advertisement dispensing device；The edge end equipment is for acquiring pedestrian's data and carrying out preliminary treatment to data；The processing locality equipment is used for that treated that data are further analyzed processing to marginal end equipment, controls the dispensing advertisement of advertisement dispensing device according to processing result；The cloud device is to handle the data exceeded other than processing locality equipment disposal ability; and processing result is returned into processing locality equipment; marginal end equipment and advertisement dispensing device are controlled by processing locality equipment again; corresponding advertisement can be played for audient crowd; and it ensure that the safety in data transmission procedure, protect pedestrian's privacy.
Description
Technical field
The invention belongs to field of artificial intelligence more particularly to a kind of smart ads systems and advertisement placement method.
Background technique
Existing entity advertisements putting mode is all in fixed or mobile place, and the rolling that is set for temporally is broadcast
It puts.Compared to that can push targeted advertisement according to known customer information on the internet, traditional mode can not be protected
Hinder user's specific aim that advertisement is launched.Generally to a certain specific place or region only by modes such as questionnaire surveys come really
Surely by information such as gender, age, the occupations of personnel.The information obtained in this way is i.e. bothersome and inaccurate.And that takes at present arranges
Applying all is the play time for directly setting advertisement, is rolling broadcasting always later.Advertisement play when can not determine either with or without by
Everybody group, or even sometimes all without passerby.Such mode is inefficient and not environmentally.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of smart ads system and advertisement placement method, energy
Corresponding advertisement enough is played for audient crowd, the technical solution adopted in the present invention is as follows:
In a first aspect, providing a kind of smart ads system, comprising: edge end equipment, processing locality equipment, cloud device and
Advertisement dispensing device；
For acquiring pedestrian's data and carrying out preliminary treatment to data, the data after preliminary treatment do not include the edge end equipment
Pedestrian image is the characteristics of image and behavioural characteristic of some pedestrians, and identification as subsequent in this way, which provides the foundation, also substantially drops
Low data volume；
The processing locality equipment is used for that treated that data are further analyzed processing to marginal end equipment, according to processing
As a result control advertisement dispensing device launches advertisement；
The cloud device returns to processing result to handle the data exceeded other than processing locality equipment disposal ability
Processing locality equipment, then marginal end equipment and advertisement dispensing device are controlled by processing locality equipment.
Further, the edge end equipment includes pedestrian's data acquisition equipment and is used to carry out at primary pedestrian's data
The primary processing equipment of reason, pedestrian's data acquisition equipment includes camera and infrared sensor, and camera is set to advertisement
The top center and advertisement for launching region are launched at two sides and each entrance in region, and infrared sensor is set to advertisement throwing
Put the top center position in area.
Second aspect provides a kind of intelligent advertisement put-on method, includes the following steps:
Pedestrian's data in advertisement dispensing region are acquired, and preliminary treatment is carried out to pedestrian's data；
Processing locality equipment is further processed pedestrian's data after the preliminary treatment received, if processing locality equipment performance meets
Demand then its pedestrian's data after preliminary treatment are handled completely and according to processing result directly control advertisement launch, if its
Performance be unsatisfactory for demand then its to after preliminary treatment pedestrian's data carry out part processing, data that treated send out cloud device；
When complete judgement can not be made by communicating unsmooth and local device, local device is made according to existing incomplete processing result to be sentenced
It is disconnected.Though precision is declined compared to background process, the uninterrupted of live play can guarantee.
Cloud device receives and processes that (cloud connects in processing locality capacity of equipment deficiency from the data of processing locality equipment
What is received is untreated complete data, will be continued with), and by treated, result returns to processing locality equipment, then leads to
It crosses processing locality equipment control advertisement dispensing device and carries out advertisement dispensing.
Further, described includes the portrait that pedestrian is extracted according to pedestrian's data to the progress preliminary treatment of pedestrian information data
Feature and behavioural characteristic, in this way in the process of transmission, because being free of image information, the data transmitted all are by coding
Characteristic information, on the one hand substantially reduce data volume, on the other hand ensure that the privacy of data pedestrian in transmission process
It will not reveal.
Further, processing locality equipment is further processed pedestrian's data after the preliminary treatment received specifically: logical
It crosses CNN network model and higher level feature is gradually extracted to pedestrian's data after preliminary treatment；It can further reduce in this way
The volume of data, subsequent data transmission is more efficient, and the availability of data is higher.
Further, it includes: to launch number in area that pedestrian's data in area are launched in acquisition advertisement, and each pedestrian is in different advertisements
The preceding residence time.It, can be with subsequent targetedly to different rows by recording pedestrian's residence time before different advertisements
People launches different advertisements.
Further, when monitoring in front of advertisement dispensing device without pedestrian, the control advertisement dispensing of processing locality equipment is set
It is standby to enter dormant state or shutdown；The energy can be largely saved in this way, reduce unnecessary waste.
Beneficial effect mainly includes the following:
1. advertisement is launched with strong points.The specific aim that advertisement is launched compared with traditional approach substantially enhances, can be according to different
Flow of the people flexibly launches different advertisements.There is clearly classification capacity to mixed crowd, there can be needle in the suitable time
To the most suitable advertisement of the dispensing of property.
2. can also be provided because background server can send instructions down and control the broadcasting of local device for client
The service content of customization meets the needs of different.Compare traditional broadcast mode more flexibly and have diversity, can
Preferably externally to promote.
3. can be provided for client it is specific launch efficiency data, when play, when broadcasting how many people and this
The information such as the age of a little people and gender.And the information such as the stop of pedestrian before advertisement is further acquired by camera and is checked, it searches
Background system is fed back to after collection.
4. judging that currently controlling advertisement as idle processing locality equipment throws when live camera and sensor are by monitoring
It puts equipment and enters dormant state or shutdown.Unnecessary electricity charge expense can be saved in this way, also contributed for low-carbon environment-friendly.
5. most data is all calculated in marginal end and intermediate ends when calculation amount is little, does not depend on backstage and take
Business device handles data, can obtain a result in time, non-delay.
6. can ensure personal privacy during transmission and data processing.All information all exists in this project
Processing, only one group of compress coding data of upload had been done in local device.Even if can not by lawless people acquisition yet
Therefrom make a profit.
7. not straight to the requirement of bandwidth during transmission similarly since processed data packet will not be very big in 6
The image transmitting connect is high, so part scene can dispose wireless device directly to mitigate the wiring difficulty at scene and be routed to
This.
8. the reliability of whole system is also mentioned similarly since local device has certain data-handling capacity in 5
Height is not in the case where can not connecting background server and cause field device that can not work.
9. the identification function based on this system can form good linkage with the police.Such as in local device in advance
Photo is placed, the auxiliary police lock suspicious people or runaway convict.Or field monitoring to exception when to police's PUSH message.
Detailed description of the invention
Fig. 1 is system architecture diagram of the invention.
Specific embodiment
With reference to the accompanying drawings of the specification, the present invention is further illustrated.
A kind of smart ads system, comprising: edge end equipment, processing locality equipment, cloud device and advertisement dispensing are set
It is standby；The edge end equipment is for acquiring pedestrian's data and carrying out preliminary treatment to data；The processing locality equipment for pair
Treated that data are further analyzed processing for edge end equipment, according to processing result control advertisement dispensing device launch it is wide
It accuses；The cloud device returns to processing result to handle the data exceeded other than processing locality equipment disposal ability
Processing locality equipment, processing locality equipment are controlled, then are set by processing locality equipment to marginal end equipment and advertisement dispensing
It is standby to be controlled.
Edge end equipment: edge end equipment includes data acquisition equipment and primary processing equipment, acquisition equipment by camera,
Infrared sensor.Data are acquired in marginal end and make by primary processing equipment preliminary processing, then to upper level, to being originally located in
Equipment is managed to send.Marginal end carries out raw data acquisition, the i.e. acquisition of pedestrian image first when specific works, will treated knot
Fruit (such as face frame, characteristic etc.) is sent to the further depth analysis of the stronger processing equipment of local operational capability.
Processing locality equipment: processing locality equipment can carry out further depth analysis, utilize CNN(volumes of different frameworks
Product nerve) network model gradually extracts higher level feature, and it, then directly can be in local if local device can satisfy calculating demand
It completes data processing (judging present period region one skilled in the art's information, targetedly play advertisement)；Here higher level
Feature, which refers to, has more accurate extraction relative to data (primary processing equipment treated data) before, filters out useless letter
Breath, and the scrambling relative to information before, data that treated will have higher availability.And by structured result
(such as interest level of pedestrian's gender, age, movement tendency and different crowd to different advertisements) uploads background server
(cloud), background server back up these structured results, for 1, in case intra-company is inquired；It 2, can be periphery quotient
Family provides basic data information；3, flow of the people data service is provided for security authority；4, it is mentioned for other clients that need to launch advertisement
For data analysis service.Here structuring refers to after handling layer by layer, forms and retouches with reference format and standard
State the data of mode.If local device cannot fully meet calculating demand, (operand is larger, and local device performance can not expire
Foot) it then can be in the processing work for locally carrying out a part, (principle according to CNN, it is ensured that the output knot obtained in treatment process
Fruit volume is smaller and smaller) and by treated, less amount data are sent to cloud, carry out the complex calculation of last part, operation knot
Fruit returns again to local device.This way increases the flexibility of information processing system, safety, and volume of transmitted data is smaller also to protect
Communication stability and low cost are demonstrate,proved.
Cloud device (background server): the complex calculation that processing locality equipment is not handled is sent to backstage, by rear
Platform server completes operation, and returns result to processing locality equipment, and what it is due to transmission is compress coding data rather than figure
As (data after the feature of extraction image after calculation process, compression later, which is packaged, to be uploaded), so the requirement to bandwidth is low.
Structured result that background server is collected such as pedestrian's gender, age, movement tendency etc. will be saved as company data data,
In case searching from now on.Background server, which also possesses priority more higher than processing locality equipment, (can control local device, setting is existing
Field parameters etc.).It can send instructions under to control processing locality equipment and live other equipment.Such as send specific identification
Picture gives processing locality equipment, or controls by processing locality equipment the angular adjustment of live camera and update newest
Program.
Advertisement dispensing device: LED display is used, is connected with processing locality equipment, processing locality equipment can control
The advertisement that advertisement screen is played, and enter screen protection state or directly shutdown in idle.Broadcasting point of advertisement or less is several
Kind situation: 1. when processing locality equipment can be judged directly, and local device directly judges, and control advertisement plays.
Judge partial information uploading background server completely 2. local device can not be made, returns operation result to background server
Also, then control advertisement broadcasting.3. local device can not make complete judgement, but communicate unsmooth.Local device is according to existing at this time
The incomplete processing result having judges, and guarantees to play uninterrupted.
System passes through the entrance (two, every side) totally four before and after region arrangement is launched in advertisement before this when running
Flake camera shooting right above in a gunlock camera (more cameras can also be set according to the actual situation) and region
The information that head and infrared sensor (for the number in induction region, as assist data) acquisition comes, processing locality equipment are come
Next period is judged in advance, can how many people of the inlet and outlet of how many people and front and back be in overlay area in advertisement
Into, and it is to be about to away which, which has, judges the efficiently individual quantity in region.And the letter such as gender, age, occupation of these people
Breath.Within the effective time that an advertisement plays, it is suitable to be played on the screen according to the conclusion that processing locality equipment obtains
Advertisement, and the information such as the time of these advertisements played and effective crowd are sent to backstage together, it is launched as advertisement
The foundation of efficiency.And the information such as the stop of pedestrian before advertisement is further acquired by camera and is checked, after being fed back to after collection
Platform system.These data are backed up in unified database simultaneously as data information.These data informations can be used as increment industry
Business be supplied to other want launch advertisements client, for they provide it is comprehensive, conveniently and targetedly consulting and data clothes
Business.
This set system can also cooperate with police.When local system has determined person's movements and expression questionable person, can control existing
The automatic screenshotss of field shooting head, picture are sent directly to relevant departments and enclose alarm content, pass through relevant departments' artificial nucleus' truth
Decide whether responding after condition again.Similarly the system can also pass through scene by the photo placed in advance in local device
It is compared in real time to assist the police to position and track some runaway convicts and escaped convict.If there are also clients to propose that it is hoped that there will be the clothes of customization
Business, can also detect that specific people realized later, and client also can choose right place in screen by above method
Upper transmission particular advertisement, or directly completed by Background control local device.
Local device and cloud device are mainly pedestrian's identification to the processing of pedestrian's data, and identification is mainly using following several
Algorithm:
Algorithm 1: region pedestrian's recognizer.This algorithm is dedicated to carrying out the audience size statistics that region is launched in advertisement, passes through
Based on Deep CNN extensible architecture design, meet the later period further stop crowd capture demand, algorithm support terminal fortune
Capable or end-cloud synthetic operation.It realizes step: 1, based on the camera collection image data being largely deployed on the spot, using
The mode of crowdsourcing carries out the configuration of pedestrian's label (making a mark to pedestrian in figure), in combination with ImageNet, COCO, Pascal
Networks pedestrian's database such as VOC, building pedestrian identify data set.2, based on existing yolov3 network, CNN network is changed
Output is 1 class target (people)+position frame, while additional 2 tie up vacant vector, is used for later period Function Extension.3, using transfer learning
Theory puts into ready pedestrian and identifies that data set carries out CNN network training, and Statistical error parameter guarantees CNN network
(revisedyolov3) identify that the AP (Average Precison) under data set reaches 0.7 or more (evaluation index) in pedestrian.
4, to trained network model, the model compression optimization based on PocketFlow is done, guarantees that its number of parameters reduces 2 times, meter
It calculates speed and promotes 2 times, while AP maintains 0.85 or more, guarantee that algorithm model is run in terminal higher efficiency.5, step 2 is pre-
The 2 vacant vectors of dimension stayed, can be according to later period functional requirement, and (such as: whether pedestrian is watching addition label in data set label
Advertisement), it is made by the accumulation of mass data and growth data collection, realizes the demands such as pedestrian determination of stopping.
Algorithm 2: pedestrian is towards recognizer.This algorithm is used to judge the disengaging situation of pedestrian, matches hop algorithm 1, realizes more
Accurately pedestrian's quantity statistics.It realizes step: 1, by the deployment of algorithm 1, can carry out calculating the quantity for obtaining pedestrian in image
And location information, each pedestrian can be split from image by location information.2, image is obtained, high number of row is partitioned into
People's set carries out generating data set towards label for labelling using modes such as crowdsourcings.3, due to the clear simplicity of task object, design
The classification cnn of shallow-layer 2, such as 7 layers of structure, every layer respectively uses 3*3 convolution kernel, and every layer of multiple of convolution nuclear volume is incremented by, and is superimposed connection entirely
After layer, output layer is 2 dimensional vectors, and loss function is binary cross entropy.4, investment data are trained, and are guaranteed quasi-
True rate is higher than 95%, storage model parameter.5, it is passed in and out and is differentiated by trained model realization pedestrian.
Algorithm 3: pedestrian's Attribute Recognition algorithm.Based on high-definition image, for judging pedestrian's age, gender, professional attribute etc.
Characteristic information, auxiliary accurate advertisement push.Realize step: 1, it is with algorithm 2 similar, it is based on algorithm 1 and image segmentation, is gone
People's image collection.2, by manually marking (information such as gender, age bracket, clothing), pedestrian's attribute data collection is generated.3, due to appointing
Business is complicated, is based on 30 layers of resnet+inception network architecture design or more depth convolutional neural networks (DCNN), will export
It is limited to (2+6+n) dimension, i.e. (gender+age bracket+n kind wears attribute clothes), the corresponding loss function of Aided design.4, data set is put into
Network model training is carried out, guarantees that result accuracy rate is higher than 90%.5, algorithm can be used when necessary for guarantee terminal operating efficiency
Model compression technology in 1, reduced-order models operand.6, Deployment Algorithm, system come into operation.
Embodiment is merely illustrative of the invention's technical idea, and this does not limit the scope of protection of the present invention, it is all according to
Technical idea proposed by the present invention, any changes made on the basis of the technical scheme are fallen within the scope of the present invention.
Claims (8)
1. a kind of smart ads system characterized by comprising edge end equipment, processing locality equipment, cloud device and wide
Accuse dispensing device；
The edge end equipment is for acquiring pedestrian's data and carrying out preliminary treatment to data；
The processing locality equipment is used for that treated that data are further analyzed processing to marginal end equipment, according to processing
As a result control advertisement dispensing device launches advertisement；
The cloud device returns to processing result to handle the data exceeded other than processing locality equipment disposal ability
Processing locality equipment, then marginal end equipment and advertisement dispensing device are controlled by processing locality equipment.
2. a kind of smart ads system according to claim 1, it is characterised in that: the edge end equipment includes pedestrian's number
Primary processing equipment according to acquisition equipment and for pedestrian's data to be carried out with primary treatment, pedestrian's data acquisition equipment include
Camera and infrared sensor, camera be set to advertisement launch region top center and advertisement launch region two sides with
And at each entrance, infrared sensor is set to the top center position that area is launched in advertisement.
3. a kind of smart ads system according to claim 1, it is characterised in that: pedestrian's data after preliminary treatment are not wrapped
Include pedestrian image.
4. a kind of intelligent advertisement put-on method characterized by comprising
Pedestrian's data in advertisement dispensing region are acquired, and preliminary treatment is carried out to pedestrian's data；
Processing locality equipment is further processed pedestrian's data after the preliminary treatment received, if processing locality equipment performance meets
Demand then its pedestrian's data after preliminary treatment are handled completely and according to processing result directly control advertisement launch, if its
Performance be unsatisfactory for demand then its to after preliminary treatment pedestrian's data carry out part processing, data that treated send out cloud device；
Cloud device receives and processes the data from processing locality equipment, and result is set back to processing locality by treated
It is standby, then advertisement dispensing device is controlled by processing locality equipment and carries out advertisement dispensing.
5. a kind of intelligent advertisement put-on method according to claim 4, which is characterized in that it is described to pedestrian information data into
Row preliminary treatment includes that the portrait feature and behavioural characteristic of pedestrian are extracted according to pedestrian's data.
6. a kind of intelligent advertisement put-on method according to claim 4, which is characterized in that processing locality equipment is to receiving
Pedestrian's data after preliminary treatment are further processed specifically: by CNN network model to pedestrian's data after preliminary treatment by
Step extracts higher level feature.
7. a kind of intelligent advertisement put-on method according to claim 4, which is characterized in that the row in area is launched in acquisition advertisement
Personal data includes: to launch number in area, residence time of each pedestrian before different advertisements.
8. a kind of intelligent advertisement put-on method according to claim 4, which is characterized in that when monitoring advertisement dispensing device
When front is without pedestrian, processing locality equipment control advertisement dispensing device enters dormant state or shutdown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910734391.2A CN110473015A (en) | 2019-08-09 | 2019-08-09 | A kind of smart ads system and advertisement placement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910734391.2A CN110473015A (en) | 2019-08-09 | 2019-08-09 | A kind of smart ads system and advertisement placement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110473015A true CN110473015A (en) | 2019-11-19 |
Family
ID=68510576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910734391.2A Pending CN110473015A (en) | 2019-08-09 | 2019-08-09 | A kind of smart ads system and advertisement placement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110473015A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889726A (en) * | 2019-11-26 | 2020-03-17 | 上海新储集成电路有限公司 | Device and method for customizing advertisement delivery |
| CN112468854A (en) * | 2020-11-27 | 2021-03-09 | 湖南众益文化传媒股份有限公司 | Variable-frequency playing method for outdoor building advertisement media machine |
| CN113127184A (en) * | 2019-12-31 | 2021-07-16 | 浙江宇视科技有限公司 | Data analysis method, device, equipment and medium |
Citations (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1193778A (en) * | 1997-02-12 | 1998-09-23 | 松下电器产业株式会社 | Data transmission apparatus, data reception apparatus, and medium |
| CN1985762A (en) * | 2005-12-22 | 2007-06-27 | 国际商业机器公司 | Device for monitoring a user's posture |
| CN101924791A (en) * | 2010-08-06 | 2010-12-22 | 百度在线网络技术（北京）有限公司 | Method, device and system for displaying multimedia information |
| CN102236860A (en) * | 2011-07-01 | 2011-11-09 | Tcl集团股份有限公司 | Automatic advisement releasing system and method |
| CN102881239A (en) * | 2011-07-15 | 2013-01-16 | 鼎亿数码科技(上海)有限公司 | Advertisement playing system and method based on image identification |
| US20140143804A1 (en) * | 2012-11-16 | 2014-05-22 | Institute For Information Industry | System and method for providing advertisement service |
| US20140310097A1 (en) * | 2011-12-16 | 2014-10-16 | Nec Corporation | Information processing system, information processing method, communications terminals and control method and control program thereof |
| CN104317860A (en) * | 2014-10-16 | 2015-01-28 | 中航华东光电（上海）有限公司 | Evaluation device of stereoscopic advertisement player and evaluation method of evaluation device |
| CN105095120A (en) * | 2015-07-03 | 2015-11-25 | 惠州Tcl移动通信有限公司 | Terminal control method and accessory device |
| CN105610944A (en) * | 2015-12-29 | 2016-05-25 | 北京物联远信息技术有限公司 | IOT-oriented fog computing architecture |
| CN105598972A (en) * | 2016-02-04 | 2016-05-25 | 北京光年无限科技有限公司 | Robot system and interactive method |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN107045461A (en) * | 2017-04-13 | 2017-08-15 | 宇龙计算机通信科技(深圳)有限公司 | The method and device of data processing |
| US20170270593A1 (en) * | 2016-03-21 | 2017-09-21 | The Procter & Gamble Company | Systems and Methods For Providing Customized Product Recommendations |
| CN107455004A (en) * | 2015-04-17 | 2017-12-08 | 瑞典爱立信有限公司 | Dynamic wrapper network based on ABR distribution of media and conveying |
| CN107948129A (en) * | 2017-10-16 | 2018-04-20 | 北京邮电大学 | Internet of Things mist calculating network system and its control method based on SDN |
| CN107959708A (en) * | 2017-10-24 | 2018-04-24 | 北京邮电大学 | A kind of car networking service collaboration computational methods and system based on high in the clouds-marginal end-car end |
| CN108154406A (en) * | 2018-02-09 | 2018-06-12 | 合肥莫高雷网络科技有限责任公司 | A kind of elevator audio advertisement jettison system based on Internet of Things |
| CN108297098A (en) * | 2018-01-23 | 2018-07-20 | 上海大学 | The robot control system and method for artificial intelligence driving |
| CN108667936A (en) * | 2018-05-10 | 2018-10-16 | Oppo广东移动通信有限公司 | Data processing method, terminal, mobile edge calculations server and storage medium |
| CN109614238A (en) * | 2018-12-11 | 2019-04-12 | 深圳市网心科技有限公司 | A kind of recongnition of objects method, apparatus, system and readable storage medium storing program for executing |
| CN109684083A (en) * | 2018-12-11 | 2019-04-26 | 北京工业大学 | A kind of multilevel transaction schedule allocation strategy towards under edge-cloud isomery |
| CN109727376A (en) * | 2018-12-29 | 2019-05-07 | 北京沃东天骏信息技术有限公司 | Generate the method, apparatus and selling apparatus of configuration file |
| CN109756572A (en) * | 2018-12-27 | 2019-05-14 | 驭势科技（北京）有限公司 | A kind of distributed computing network System and method for |
| CN109934625A (en) * | 2019-03-01 | 2019-06-25 | 统云信息科技有限公司 | A kind of artificial intelligence display screen advertisement dynamic throwing system and method |
| CN109936619A (en) * | 2019-01-18 | 2019-06-25 | 中国科学院空间应用工程与技术中心 | A kind of Information Network framework, method and readable storage medium storing program for executing calculated based on mist |
-
2019
- 2019-08-09 CN CN201910734391.2A patent/CN110473015A/en active Pending
Patent Citations (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1193778A (en) * | 1997-02-12 | 1998-09-23 | 松下电器产业株式会社 | Data transmission apparatus, data reception apparatus, and medium |
| CN1985762A (en) * | 2005-12-22 | 2007-06-27 | 国际商业机器公司 | Device for monitoring a user's posture |
| CN101924791A (en) * | 2010-08-06 | 2010-12-22 | 百度在线网络技术（北京）有限公司 | Method, device and system for displaying multimedia information |
| CN102236860A (en) * | 2011-07-01 | 2011-11-09 | Tcl集团股份有限公司 | Automatic advisement releasing system and method |
| CN102881239A (en) * | 2011-07-15 | 2013-01-16 | 鼎亿数码科技(上海)有限公司 | Advertisement playing system and method based on image identification |
| US20140310097A1 (en) * | 2011-12-16 | 2014-10-16 | Nec Corporation | Information processing system, information processing method, communications terminals and control method and control program thereof |
| US20140143804A1 (en) * | 2012-11-16 | 2014-05-22 | Institute For Information Industry | System and method for providing advertisement service |
| CN104317860A (en) * | 2014-10-16 | 2015-01-28 | 中航华东光电（上海）有限公司 | Evaluation device of stereoscopic advertisement player and evaluation method of evaluation device |
| CN107455004A (en) * | 2015-04-17 | 2017-12-08 | 瑞典爱立信有限公司 | Dynamic wrapper network based on ABR distribution of media and conveying |
| CN105095120A (en) * | 2015-07-03 | 2015-11-25 | 惠州Tcl移动通信有限公司 | Terminal control method and accessory device |
| CN105610944A (en) * | 2015-12-29 | 2016-05-25 | 北京物联远信息技术有限公司 | IOT-oriented fog computing architecture |
| CN105598972A (en) * | 2016-02-04 | 2016-05-25 | 北京光年无限科技有限公司 | Robot system and interactive method |
| US20170270593A1 (en) * | 2016-03-21 | 2017-09-21 | The Procter & Gamble Company | Systems and Methods For Providing Customized Product Recommendations |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN107045461A (en) * | 2017-04-13 | 2017-08-15 | 宇龙计算机通信科技(深圳)有限公司 | The method and device of data processing |
| CN107948129A (en) * | 2017-10-16 | 2018-04-20 | 北京邮电大学 | Internet of Things mist calculating network system and its control method based on SDN |
| CN107959708A (en) * | 2017-10-24 | 2018-04-24 | 北京邮电大学 | A kind of car networking service collaboration computational methods and system based on high in the clouds-marginal end-car end |
| CN108297098A (en) * | 2018-01-23 | 2018-07-20 | 上海大学 | The robot control system and method for artificial intelligence driving |
| CN108154406A (en) * | 2018-02-09 | 2018-06-12 | 合肥莫高雷网络科技有限责任公司 | A kind of elevator audio advertisement jettison system based on Internet of Things |
| CN108667936A (en) * | 2018-05-10 | 2018-10-16 | Oppo广东移动通信有限公司 | Data processing method, terminal, mobile edge calculations server and storage medium |
| CN109614238A (en) * | 2018-12-11 | 2019-04-12 | 深圳市网心科技有限公司 | A kind of recongnition of objects method, apparatus, system and readable storage medium storing program for executing |
| CN109684083A (en) * | 2018-12-11 | 2019-04-26 | 北京工业大学 | A kind of multilevel transaction schedule allocation strategy towards under edge-cloud isomery |
| CN109756572A (en) * | 2018-12-27 | 2019-05-14 | 驭势科技（北京）有限公司 | A kind of distributed computing network System and method for |
| CN109727376A (en) * | 2018-12-29 | 2019-05-07 | 北京沃东天骏信息技术有限公司 | Generate the method, apparatus and selling apparatus of configuration file |
| CN109936619A (en) * | 2019-01-18 | 2019-06-25 | 中国科学院空间应用工程与技术中心 | A kind of Information Network framework, method and readable storage medium storing program for executing calculated based on mist |
| CN109934625A (en) * | 2019-03-01 | 2019-06-25 | 统云信息科技有限公司 | A kind of artificial intelligence display screen advertisement dynamic throwing system and method |
Non-Patent Citations (2)
| Title |
|---|
| 徐耀林等: "基于树莓派的智能视频监控终端系统的设计和实现", 《科技风》 * |
| 郑雅羽等: "基于受众兴趣识别的智能广告展示系统设计", 《浙江工业大学学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889726A (en) * | 2019-11-26 | 2020-03-17 | 上海新储集成电路有限公司 | Device and method for customizing advertisement delivery |
| CN113127184A (en) * | 2019-12-31 | 2021-07-16 | 浙江宇视科技有限公司 | Data analysis method, device, equipment and medium |
| CN112468854A (en) * | 2020-11-27 | 2021-03-09 | 湖南众益文化传媒股份有限公司 | Variable-frequency playing method for outdoor building advertisement media machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| CN109271554B (en) | Intelligent video identification system and application thereof | |
| Ren et al. | Distributed and efficient object detection in edge computing: Challenges and solutions | |
| CN110473015A (en) | A kind of smart ads system and advertisement placement method | |
| CN104504112B (en) | Movie theatre information acquisition system | |
| CN104200466B (en) | A kind of method for early warning and video camera | |
| US20020038456A1 (en) | Method and system for the automatic production and distribution of media content using the internet | |
| CN109934625A (en) | A kind of artificial intelligence display screen advertisement dynamic throwing system and method | |
| CN103283226A (en) | Searching recorded video | |
| CN110198456A (en) | Video pushing method, device and computer readable storage medium based on live streaming | |
| CN110263613A (en) | Monitor video processing method and processing device | |
| TW202018594A (en) | People flow condition estimation method and device for designated area | |
| CN108920995A (en) | Intelligent security guard video monitoring method and its system and monitor terminal | |
| CN108270999A (en) | A kind of object detection method, image recognition server and system | |
| CN106844492A (en) | A kind of method of recognition of face, client, server and system | |
| CN108920577A (en) | Television set intelligently recommended method | |
| CN112347941A (en) | Motion video collection intelligent generation and distribution method based on 5G MEC | |
| CN108287910B (en) | A kind of wisdom garden service system and management system | |
| CN106559645A (en) | Based on the monitoring method of video camera, system and device | |
| CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
| CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
| CN109784260A (en) | A kind of zone flow real-time statistical method and system based on video structural | |
| CN103888731A (en) | Structured description device and system for mixed video monitoring by means of gun-type camera and dome camera | |
| CN110909195A (en) | Picture labeling method and device based on block chain, storage medium and server | |
| CN111274884A (en) | Intelligent advertisement pushing system based on integration of face recognition and behavior 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 |
Application publication date: 20191119 |
|
| RJ01 | Rejection of invention patent application after publication |