CN110189179A - A kind of precision advertisement broadcast method - Google Patents
A kind of precision advertisement broadcast method Download PDFInfo
- Publication number
- CN110189179A CN110189179A CN201910470142.7A CN201910470142A CN110189179A CN 110189179 A CN110189179 A CN 110189179A CN 201910470142 A CN201910470142 A CN 201910470142A CN 110189179 A CN110189179 A CN 110189179A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- man
- age bracket
- video
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06Q30/0257—User requested
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Abstract
The invention belongs to internet media technology fields, disclose a kind of precision advertisement broadcast method.The present invention includes: the In vivo detection information that S1. obtains human body in real time;S2. triggering face acquisition carries out image and/or video acquisition to the face of current human;S3. the face characteristic in present image and/or video is extracted, present image and/or the corresponding face age bracket of video are obtained;S4. it loads and exports the corresponding promotional literature of current face's age bracket to man-machine interface;S5. real-time judge In vivo detection information whether there is, and then persistently otherwise output promotional literature such as stops exporting and repeat step S1 to man-machine interface in this way.The invention allows to carry out specific aim advertisement broadcasting to the different age group of viewing advertisement, the precision for realizing advertisement plays, avoid advertising resource waste, and then improve the coverage rate for the validated user being directed to when advertisement plays, the Optimal improvements further played for advertisement provide data basis, are suitable for promoting the use of.
Description
Technical field
The invention belongs to internet media technology fields, and in particular to a kind of precision advertisement broadcast method.
Background technique
Internet has been greatly developed in recent years, and audient and covering surface can compare favourably with traditional media,
Online Media business also rapidly develops therewith, compared to traditional media, has the advantage of itself in terms of interacting marketing.Swashing
In strong competition, online Media can neatly adjust its ad content, can satisfy different customer demands, have covering model
Enclose the advantages such as wide, initiative and enthusiasm are strong, expense is relatively low, cost performance is high;And traditional media launches link still in advertisement
A large amount of artificial participations are needed, the popularization and development of advertising business are unfavorable for.
The mode that technology takes circulating rolling to play mostly is launched in existing online advertisement Internet-based, subway station,
The mobility of peoples such as bus station are big, personnel's age bracket does not lack fixed region, and this mode played that rolls can make each disappear
Expense group can cover corresponding ad content;But it is opposite for the consumer group of the personnel such as cell, office building, market
Fixed region, the mode that circulating rolling plays advertisement will lead to advertisement and play no specific aim, cover to advertisement validated user
Spend lower, to easily lead to, advertising results are bad, cause the waste of advertising resource.
Summary of the invention
In order to solve the above problems existing in the present technology, it is an object of that present invention to provide a kind of precision advertisement broadcasting sides
Method, so that advertisement more has specific aim when playing, to improve the spreadability of advertisement validated user.
The technical scheme adopted by the invention is as follows:
A kind of precision advertisement broadcast method, comprising the following steps:
S1. the In vivo detection information of human body is obtained in real time;
S2. triggering face acquires after obtaining In vivo detection information, carries out image to the face of current human and/or video is adopted
Collection;
S3. the face characteristic in present image and/or video is extracted, current face's feature is then loaded onto the face age
Section identification model in, obtain present image and/or the corresponding face age bracket of video, wherein face characteristic include textural characteristics,
Brightness and color characteristic;
S4. it loads and exports the corresponding promotional literature of current face's age bracket to man-machine interface;
S5. real-time judge In vivo detection information whether there is, as judging result be it is yes, then persistently output promotional literature to people
Machine interface, as judging result be it is no, then stop exporting promotional literature to man-machine interface, and repeat step S1.
Preferably, above-mentioned precision advertisement broadcast method is further comprising the steps of:
S6. the ambient brightness data around real-time detection man-machine interface, and man-machine interface is adjusted according to ambient brightness data
Luminance parameter.
Preferably, above-mentioned precision advertisement broadcast method is further comprising the steps of:
S7. the trigger action from man-machine interface is obtained in real time, then by the face characteristic in present image and/or video
It is compared with registration user's face characteristic in database, such as compares and unanimously then push the advertisement that current man-machine interface plays
File such as compares inconsistent to the corresponding account of current registration user, then exports prompt registration information to man-machine interface.
Preferably, in the step S1, obtaining the In vivo detection information of human body, specific step is as follows:
S101. real-time judge emits to whether the microwave signal power in front of current man-machine interface changes, and such as judges
As a result be it is yes, then obtain microwave signal power and change the initial image information in region;
S102. judge whether current preliminary image information includes face, as judging result be it is yes, then acquire microwave signal function
Rate changes the anticipation image information and infrared array temperature profile information in region, as judging result be it is no, then repeat to walk
Rapid S101;
S103. the anticipation image information of acquisition is subjected to piecemeal according to resolution ratio, prejudges human face region institute in image information
Including image subblock be labeled as head block, prejudge the image subblock in image outside human face region and be labeled as background block;
S104. each head block and the corresponding position of each background block in infrared array temperature profile information are found out
It sets, then obtains each head block and the corresponding temperature data of each background block;
S105. judge the average value of the temperature data of each head block whether within the scope of face temperature threshold, then
Judge the average value of the average value of the temperature data of each head block and the temperature data of each background block ratio whether
Within the scope of fractional threshold, such as twice judging result be or in which a judging result be it is yes, then export In vivo detection believe
Breath, such as judging result is no, then repeatedly step S101 twice.
Preferably, in the step S3, before the face characteristic for extracting present image and/or video, to present image
And/or video carries out pretreatment operation;The pretreatment operation includes light compensation, greyscale transformation, histogram equalization, returns
At least one of one change, geometric correction, filtering and sharpening.
Preferably, the training step of face age bracket identification model is as follows in the step S3:
S3a. using multiple include face pictures as training library, and by the plurality of pictures in trained library according to age bracket according to
Secondary arrangement obtains multiple picture groups;
S3b. a variety of face characteristics for extracting every picture in each picture group respectively, then extract each picture group respectively
In every picture every kind of face characteristic initial characteristics vector, and to every kind of face characteristic of all pictures in each picture group
Initial characteristics vector be weighted and average, using current average as the feature of this kind of face characteristic of current age section
Vector;
S3c. step S3b is repeated until obtaining the feature vector of all face characteristics in all picture groups, by each picture
Feature vector in group is gathered as one, successively sorts according to the corresponding age bracket of picture group to get to having multiple groups face
The face age bracket identification model of feature vector.
Preferably, obtaining the specific step of present image and/or the corresponding face age bracket of video in the step S3
It is rapid as follows:
S301. it is cut the region for the face for including in present image and/or video to obtain image-region;
S302. the feature vector to be sentenced for extracting every kind of face characteristic in image-region, then by every kind of feature vector to be sentenced
Similarity mode is carried out with the feature vector of face age bracket identification model respectively;
S302. the age bracket where the corresponding feature vector of feature vector to be sentenced in image-region is weighted averaging
Value, obtains the corresponding age bracket in present image area;
S304. the corresponding age bracket in present image area is obtained into the face corresponding age in present image and/or video
Section;
Preferably, when the face for including in present image and/or video is multiple, then to present image and/or video
In include each region of face cut to obtain multiple images region, step S302 is then carried out respectively to multiple images
And S303.
Preferably, in the step S4, when the corresponding promotional literature of load current age section, the specific steps are as follows:
S401. judge whether the corresponding age bracket in multiple images region in present image and/or video is consistent, such as judge
As a result be it is yes, then load the promotional literature of corresponding age bracket, as judging result be it is no, then count the corresponding figure of each age bracket
As the quantity in region is formed wait sentence set;
S402. judge currently wait sentence in set with the presence or absence of maximum value, as judging result be it is yes, then load maximum value correspondence
Age bracket promotional literature, as judging result be it is no, then it is corresponding according to the main consumer group in region where current man-machine interface
Age bracket promotional literature.
Preferably, when exporting Current ad file to man-machine interface, while exporting Current ad in the step S4
Then it is in place to obtain current man-machine interface institute to the corresponding voice playback terminal of current man-machine interface for the corresponding audio files of file
The clock time set, and according to the output volume of current clock time adjustment voice playback terminal.
The invention has the benefit that
By the identification to In vivo detection and face age bracket, make it possible to carry out needle to the different age group of viewing advertisement
Property advertisement is played, the precision for realizing advertisement plays, and plays the wasting of resources caused by advertisement during avoiding nobody, in turn
The coverage rate for the validated user being directed to when advertisement plays is improved, the Optimal improvements further played for advertisement provide data base
Plinth is suitable for promoting the use of.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
With reference to the accompanying drawing and specific embodiment does further explaination to the present invention.
Embodiment 1:
As shown in Figure 1, the present embodiment provides a kind of precision advertisement broadcast methods, it is characterised in that: the following steps are included:
S1. the In vivo detection information of human body is obtained in real time;It is possible thereby to when someone appearing in front of man-machine interface first
Between sense and triggering following step.
In the present embodiment, obtaining the In vivo detection information of human body, specific step is as follows:
S101. real-time judge emits to whether the microwave signal power in front of current man-machine interface changes, and such as judges
As a result be it is yes, then obtain microwave signal power and change the initial image information in region;Emit microwave signal can with but not only
It is limited to thus to effectively prevent erroneous judgement using microwave remote sensor.
S102. judge whether current preliminary image information includes face, as judging result be it is yes, then acquire microwave signal function
Rate changes the anticipation image information and infrared array temperature profile information in region, as judging result be it is no, then repeat to walk
Rapid S101;Acquisition initial image information and anticipation image information can with but be not limited only to acquire infrared array temperature using camera
Degree profile information can with but be not limited only to using MEMs infrared sensor array unit, camera and MEMs infrared array sensing
Device unit visual angle is similar, and the two can cover Face datection region, so that infrared region and shooting area lap reach
80% or more;Microwave signal power in front of man-machine interface changes, and exports In vivo detection information, and then trigger camera
And MEMs infrared sensor array unit.
S103. the anticipation image information of acquisition is subjected to piecemeal according to resolution ratio, prejudges human face region institute in image information
Including image subblock be labeled as head block, prejudge the image subblock in image outside human face region and be labeled as background block;Point
Block, which carries out subsequent step, can effectively improve the accuracy rate of identification living body, and background environment is avoided to impact living body judgement.
S104. each head block and the corresponding position of each background block in infrared array temperature profile information are found out
It sets, then obtains each head block and the corresponding temperature data of each background block;In normal usage scenario, header area
Temperature data between block and background block is different, it is possible to prevente effectively from some advertisements of triggering in special circumstances play,
There is the case where influencing other people and waste of resource, special circumstances have found one piece of man-shaped advertisement board before such as there is man-machine interface.
S105. judge the average value of the temperature data of each head block whether within the scope of face temperature threshold, then
Judge the average value of the average value of the temperature data of each head block and the temperature data of each background block ratio whether
Within the scope of fractional threshold, such as twice judging result be or in which a judging result be it is yes, then export In vivo detection believe
Breath, such as judging result is no, then repeatedly step S101 twice;Using MEMs infrared sensor array unit combination camera into
Pedestrian's face In vivo detection, structure is simple, and sensor price is low, reduces costs, and operating process is simple, it is only necessary to once have
Effect is shot with video-corder, that is, may identify whether to greatly reduce the complexity of living body determination for true man's face.
S2. triggering face acquires after obtaining In vivo detection information, carries out image to the face of current human and/or video is adopted
Collection;The acquisition of image and/or video can with but be not limited only to using above-mentioned camera or special camera, image and/or video
Acquisition function triggers after living body judges successfully.
S3. the face characteristic in present image and/or video is extracted, current face's feature is then loaded onto the face age
Section identification model in, obtain present image and/or the corresponding face age bracket of video, wherein face characteristic include textural characteristics,
Brightness and color characteristic;Textural characteristics, brightness and color characteristic are adjustable age parameters, it is possible thereby to sharp
The age bracket that current persons are finally determined with multiple features fusion realizes accurate age bracket identification.
In the present embodiment, before the face characteristic for extracting present image and/or video, present image and/or video are carried out
Pretreatment operation;Pretreatment operation includes light compensation, greyscale transformation, histogram equalization, normalization, geometric correction, filtering
At least one of and sharpen;Pretreatment can not meet pre-set image processing requirement to avoid acquired image and/or video
The case where, improve subsequent Face datection accuracy.
In the present embodiment, the training step of face age bracket identification model is as follows:
S3a. using multiple include face pictures as training library, and by the plurality of pictures in trained library according to age bracket according to
Secondary arrangement obtains multiple picture groups;It should be noted that each age bracket corresponds to unique picture group.
S3b. a variety of face characteristics for extracting every picture in each picture group respectively, then extract each picture group respectively
In every picture every kind of face characteristic initial characteristics vector, and to every kind of face characteristic of all pictures in each picture group
Initial characteristics vector be weighted and average, using current average as the feature of this kind of face characteristic of current age section
Vector;The extraction of feature vector quantizes different face characteristics, is convenient for subsequent calculating, the extraction of feature vector is for difference
Face characteristic can be realized using the different prior art, such as textural characteristics can be using by the quantity and shade depth of texture
The mode to quantize obtains, then then brightness can be compared by setting Benchmark brightness with the brightness of picture
The mode of numeralization obtains, and color characteristic can be by the colour of skin on face being compared with the benchmark colour of skin or will be on face
The mode that the quantity of age spot quantizes obtains.
S3c. step S3b is repeated until obtaining the feature vector of all face characteristics in all picture groups, by each picture
Feature vector in group is gathered as one, successively sorts according to the corresponding age bracket of picture group to get to having multiple groups face
The face age bracket identification model of feature vector.It should be noted that the identification model of each age bracket includes minimum 3 spies
Vector set is levied, thus precisely to identify that age bracket provides reliable technical foundation.
In the present embodiment, obtaining present image and/or the corresponding face age bracket of video, specific step is as follows:
S301. it is cut the region for the face for including in present image and/or video to obtain image-region;
S302. the feature vector to be sentenced for extracting every kind of face characteristic in image-region, then by every kind of feature vector to be sentenced
Similarity mode is carried out with the feature vector of face age bracket identification model respectively;
S302. the age bracket where the corresponding feature vector of feature vector to be sentenced in image-region is weighted averaging
Value, obtains the corresponding age bracket in present image area;
S304. the corresponding age bracket in present image area is obtained into the face corresponding age in present image and/or video
Section;
In the present embodiment, when the face for including in present image and/or video is multiple, then to present image and/or view
The each region for the face for including in frequency is cut to obtain multiple images region, then carries out step respectively to multiple images
S302 and S303.
S4. it loads and exports the corresponding promotional literature of current face's age bracket to man-machine interface.
In the present embodiment, when the load corresponding promotional literature of current age section, the specific steps are as follows:
S401. judge whether the corresponding age bracket in multiple images region in present image and/or video is consistent, such as judge
As a result be it is yes, then load the promotional literature of corresponding age bracket, as judging result be it is no, then count the corresponding figure of each age bracket
As the quantity in region is formed wait sentence set;
S402. judge currently wait sentence in set with the presence or absence of maximum value, as judging result be it is yes, then load maximum value correspondence
Age bracket promotional literature, as judging result be it is no, then it is corresponding according to the main consumer group in region where current man-machine interface
Age bracket promotional literature.It should be noted that the corresponding age bracket of the main consumer group in region where current man-machine interface
It is that advertisement putting business is preset in systems.
In the present embodiment, when exporting Current ad file to man-machine interface, while the corresponding sound of Current ad file is exported
Sound file is to the corresponding voice playback terminal of current man-machine interface, when then obtaining the clock of current man-machine interface position
Between, and according to the output volume of current clock time adjustment voice playback terminal, it is possible thereby to be arranged according to the different periods
Different volumes prevents from disturbing residents.
S5. real-time judge In vivo detection information whether there is, as judging result be it is yes, then persistently output promotional literature to people
Machine interface, as judging result be it is no, then stop exporting promotional literature to man-machine interface, and repeat step S1.It is possible thereby to effectively
Waste caused by avoiding nobody period advertisement from playing
In the present embodiment, above-mentioned precision advertisement broadcast method is further comprising the steps of:
S6. the ambient brightness data around real-time detection man-machine interface, and man-machine interface is adjusted according to ambient brightness data
Luminance parameter;So that user watches the experience sense of advertisement more preferably, effective broadcasting rate of advertisement is further increased.
In the present embodiment, above-mentioned precision advertisement broadcast method is further comprising the steps of:
S7. the trigger action from man-machine interface is obtained in real time, then by the face characteristic in present image and/or video
It is compared with registration user's face characteristic in database, such as compares and unanimously then push the advertisement that current man-machine interface plays
File such as compares inconsistent to the corresponding account of current registration user, then exports prompt registration information to man-machine interface.
The present invention is not limited to above-mentioned optional embodiment, anyone can show that other are each under the inspiration of the present invention
The product of kind form.Above-mentioned specific embodiment should not be understood the limitation of pairs of protection scope of the present invention, protection of the invention
Range should be subject to be defined in claims, and specification can be used for interpreting the claims.
Claims (10)
1. a kind of precision advertisement broadcast method, it is characterised in that: the following steps are included:
S1. the In vivo detection information of human body is obtained in real time;
S2. triggering face acquires after obtaining In vivo detection information, carries out image and/or video acquisition to the face of current human;
S3. the face characteristic in present image and/or video is extracted, current face's feature is then loaded onto face age bracket and is known
In other model, present image and/or the corresponding face age bracket of video are obtained, wherein face characteristic includes textural characteristics, brightness
Feature and color characteristic;
S4. it loads and exports the corresponding promotional literature of current face's age bracket to man-machine interface;
S5. real-time judge In vivo detection information whether there is, as judging result be it is yes, then persistently output promotional literature to man-machine boundary
Face, as judging result be it is no, then stop exporting promotional literature to man-machine interface, and repeat step S1.
2. precision advertisement broadcast method according to claim 1, it is characterised in that: further comprising the steps of:
S6. the ambient brightness data around real-time detection man-machine interface, and the bright of man-machine interface is adjusted according to ambient brightness data
Spend parameter.
3. precision advertisement broadcast method according to claim 2, it is characterised in that: further comprising the steps of:
S7. the trigger action from man-machine interface is obtained in real time, then by the face characteristic and number in present image and/or video
It is compared according to registration user's face characteristic in library, such as compares and unanimously then push the promotional literature that current man-machine interface plays
It to the corresponding account of current registration user, such as compares inconsistent, then exports prompt registration information to man-machine interface.
4. precision advertisement broadcast method according to claim 1 to 3, it is characterised in that: in the step S1,
Specific step is as follows for the In vivo detection information of acquisition human body:
S101. real-time judge emits to whether the microwave signal power in front of current man-machine interface changes, such as judging result
Be it is yes, then obtain microwave signal power and change the initial image information in region;
S102. judge whether current preliminary image information includes face, as judging result be it is yes, then acquire microwave signal power hair
The anticipation image information and infrared array temperature profile information of raw region of variation, if judging result is no, then repeatedly step
S101;
S103. the anticipation image information of acquisition is subjected to piecemeal according to resolution ratio, prejudged in image information included by human face region
Image subblock be labeled as head block, prejudge the image subblock in image outside human face region and be labeled as background block;
S104. each head block and the corresponding position of each background block in infrared array temperature profile information are found out, so
After obtain each head block and the corresponding temperature data of each background block;
S105. judge that the average value of the temperature data of each head block whether within the scope of face temperature threshold, then judges
The ratio of the average value of the temperature data of the average value of the temperature data of each head block and each background block whether than
Be worth threshold range in, such as twice judging result be or in which a judging result be it is yes, then export In vivo detection information, such as
Judging result is no twice, then repeatedly step S101.
5. precision advertisement broadcast method according to claim 4, it is characterised in that: in the step S3, extraction is worked as
Before the face characteristic of preceding image and/or video, pretreatment operation is carried out to present image and/or video;The pretreatment behaviour
Make to include at least one of light compensation, greyscale transformation, histogram equalization, normalization, geometric correction, filtering and sharpening.
6. precision advertisement broadcast method according to claim 5, it is characterised in that: in the step S3, face year
The age training step of section identification model is as follows:
S3a. the picture that multiple include face is successively arranged as training library, and by the plurality of pictures in training library according to age bracket
Column, obtain multiple picture groups;
S3b. a variety of face characteristics of every picture in each picture group are extracted respectively, are then extracted respectively every in each picture group
The initial characteristics vector of every kind of face characteristic of picture, and in each picture group every kind of face characteristic of all pictures just
Beginning feature vector, which is weighted, averages, using current average as the feature of this kind of face characteristic of current age section to
Amount;
S3c. repeatedly step S3b, will be in each picture group up to obtaining the feature vector of all face characteristics in all picture groups
Feature vector gather as one, successively sort according to the corresponding age bracket of picture group to get to having multiple groups face characteristic
The face age bracket identification model of vector.
7. precision advertisement broadcast method according to claim 6, it is characterised in that: in the step S3, worked as
Specific step is as follows for preceding image and/or the corresponding face age bracket of video:
S301. it is cut the region for the face for including in present image and/or video to obtain image-region;
S302. the feature vector to be sentenced of every kind of face characteristic in image-region is extracted, then distinguishes every kind of feature vector to be sentenced
Similarity mode is carried out with the feature vector of face age bracket identification model;
S303. the age bracket where the corresponding feature vector of feature vector to be sentenced in image-region is weighted and is averaged,
Obtain the corresponding age bracket in present image area;
S304. using the corresponding age bracket in present image area as the corresponding age bracket of face in present image and/or video.
8. precision advertisement broadcast method according to claim 7, it is characterised in that: wrapped in present image and/or video
When the face contained is multiple, then each region for the face for including in present image and/or video is cut to obtain multiple
Then image-region carries out step S302 and S303 respectively to multiple images.
9. precision advertisement broadcast method according to claim 8, it is characterised in that: in the step S4, load is worked as
When the corresponding promotional literature of preceding age bracket, the specific steps are as follows:
S401. judge whether the corresponding age bracket in multiple images region in present image and/or video is consistent, such as judging result
Be it is yes, then load the promotional literature of corresponding age bracket, as judging result be it is no, then count the corresponding image district of each age bracket
The quantity in domain is formed wait sentence set;
S402. judge currently wait sentence in set with the presence or absence of maximum value, as judging result be it is yes, then load maximum value corresponding year
Age section promotional literature, as judging result be it is no, then according to the main consumer group in the region corresponding year where current man-machine interface
The promotional literature of age section.
10. precision advertisement broadcast method according to claim 1, it is characterised in that: in the step S4, output is worked as
When preceding promotional literature to man-machine interface, while it is corresponding to current man-machine interface to export the corresponding audio files of Current ad file
Then voice playback terminal obtains the clock time of current man-machine interface position, and adjusts language according to current clock time
The output volume of sound playback terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910470142.7A CN110189179A (en) | 2019-05-31 | 2019-05-31 | A kind of precision advertisement broadcast method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910470142.7A CN110189179A (en) | 2019-05-31 | 2019-05-31 | A kind of precision advertisement broadcast method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110189179A true CN110189179A (en) | 2019-08-30 |
Family
ID=67719428
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910470142.7A Pending CN110189179A (en) | 2019-05-31 | 2019-05-31 | A kind of precision advertisement broadcast method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110189179A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113253841A (en) * | 2021-05-17 | 2021-08-13 | 南京林业大学 | Intelligent control method and device for advertisement screen |
CN113743984A (en) * | 2021-08-13 | 2021-12-03 | 苏州伊伯菲信息科技有限公司 | Big data identification method and system |
CN116347124A (en) * | 2023-03-29 | 2023-06-27 | 上海枭柯文化传播有限公司 | Advertisement loading method based on video playing state |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
CN105374306A (en) * | 2015-12-17 | 2016-03-02 | 英业达科技有限公司 | Advertisement device and advertisement playing method with identity recognition function |
CN106921893A (en) * | 2015-12-25 | 2017-07-04 | 苏州工业园区洛加大先进技术研究院 | A kind of advertisement sending method based on age bracket |
CN107995987A (en) * | 2017-03-21 | 2018-05-04 | 深圳市欸阿技术有限公司 | Advertisement show window and its display methods |
WO2018190773A1 (en) * | 2017-04-10 | 2018-10-18 | Garini Technologies Corporation Pte. Ltd. | Method and system for targeted advertising based on personal physical characteristics |
-
2019
- 2019-05-31 CN CN201910470142.7A patent/CN110189179A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101584575A (en) * | 2009-06-19 | 2009-11-25 | 无锡骏聿科技有限公司 | Age assessment method based on face recognition technology |
CN105374306A (en) * | 2015-12-17 | 2016-03-02 | 英业达科技有限公司 | Advertisement device and advertisement playing method with identity recognition function |
CN106921893A (en) * | 2015-12-25 | 2017-07-04 | 苏州工业园区洛加大先进技术研究院 | A kind of advertisement sending method based on age bracket |
CN107995987A (en) * | 2017-03-21 | 2018-05-04 | 深圳市欸阿技术有限公司 | Advertisement show window and its display methods |
WO2018190773A1 (en) * | 2017-04-10 | 2018-10-18 | Garini Technologies Corporation Pte. Ltd. | Method and system for targeted advertising based on personal physical characteristics |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113253841A (en) * | 2021-05-17 | 2021-08-13 | 南京林业大学 | Intelligent control method and device for advertisement screen |
CN113743984A (en) * | 2021-08-13 | 2021-12-03 | 苏州伊伯菲信息科技有限公司 | Big data identification method and system |
CN116347124A (en) * | 2023-03-29 | 2023-06-27 | 上海枭柯文化传播有限公司 | Advertisement loading method based on video playing state |
CN116347124B (en) * | 2023-03-29 | 2024-03-29 | 上海枭柯文化传播有限公司 | Advertisement loading method based on video playing state |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108322788B (en) | Advertisement display method and device in live video | |
CN110189179A (en) | A kind of precision advertisement broadcast method | |
CN108769801B (en) | Synthetic method, device, equipment and the storage medium of short-sighted frequency | |
KR102195922B1 (en) | Internet-based facial beautification system | |
KR101271483B1 (en) | Smart digital signage using customer recognition technologies | |
US8762419B2 (en) | Lexical classification system with dynamic modifiers | |
CN108269128B (en) | Advertisement putting method, device, equipment and storage medium | |
CN102467661B (en) | Multimedia device and method for controlling the same | |
CN103902973B (en) | Electronic bill-board pageview analytic statistics system and its operation method | |
CN105007395A (en) | Privacy processing method for continuously recording video | |
CN110460899A (en) | Methods of exhibiting, terminal device and the computer readable storage medium of barrage content | |
CN107292223A (en) | A kind of online verification method and system of real-time gesture detection | |
CN108764973A (en) | A kind of advertisement broadcast method, device, equipment and storage medium | |
CN108419115A (en) | A kind of advertisement method for implantation | |
CN108509856A (en) | Audio regulation method, device and stereo set | |
CN110415023A (en) | A kind of elevator card recommended method, device, equipment and storage medium | |
CN111724199A (en) | Intelligent community advertisement accurate delivery method and device based on pedestrian active perception | |
CN110188703A (en) | A kind of information push and drainage method based on recognition of face | |
CN117135370B (en) | AIGC-based live broadcasting room operation regulation and control method and system | |
CN110296448A (en) | A kind of smog recognition effect modification method, system and the kitchen ventilator of kitchen ventilator | |
CN112235602A (en) | Personalized screen protection system and method of smart television and smart television | |
CN109002785A (en) | Gait recognition method based on movement timing energy diagram | |
CN109034101A (en) | One-to-many sound state advertisement broadcast method | |
CN106530013A (en) | Advertisement push method and apparatus | |
CN208013969U (en) | A kind of content reproduction terminal and system |
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 |
Effective date of registration: 20200422 Address after: 201499 1st floor, No. 1990, Jinbi Road, Fengxian District, Shanghai Applicant after: Shanghai Haoyun Technology Co., Ltd Address before: 510000 Room 1005, East 8 Pazhou Avenue, Haizhu District, Guangzhou City, Guangdong Province Applicant before: Guangzhou Soft Ying Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190830 |
|
WD01 | Invention patent application deemed withdrawn after publication |