CN107798560A - A kind of retail shop's individual character advertisement intelligent method for pushing and system - Google Patents

A kind of retail shop's individual character advertisement intelligent method for pushing and system Download PDF

Info

Publication number
CN107798560A
CN107798560A CN201710994886.XA CN201710994886A CN107798560A CN 107798560 A CN107798560 A CN 107798560A CN 201710994886 A CN201710994886 A CN 201710994886A CN 107798560 A CN107798560 A CN 107798560A
Authority
CN
China
Prior art keywords
mrow
commodity
advertisement
customer
index
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
Application number
CN201710994886.XA
Other languages
Chinese (zh)
Inventor
胡雪婷
徐望明
伍世虔
柳龙飞
郑超兵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University of Science and Engineering WUSE
Wuhan University of Science and Technology WHUST
Original Assignee
Wuhan University of Science and Engineering WUSE
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University of Science and Engineering WUSE filed Critical Wuhan University of Science and Engineering WUSE
Priority to CN201710994886.XA priority Critical patent/CN107798560A/en
Publication of CN107798560A publication Critical patent/CN107798560A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • 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
    • 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 present invention provides a kind of retail shop's individual character advertisement intelligent method for pushing and system, including：Obtain the face image of customer in the viewing areas of advertisement delivery device；Feature extraction is carried out to face image, obtains the sex of the face of customer and age characteristics information in viewing areas；Advertisement delivery device push comprehensive concern index highest Commdity advertisement corresponding with customer face characteristic information.The advertisement concern index fusion that comprehensive concern index is paid close attention to index and commodity by commodity conclusion of the business index, merchandise classification is formed, and each index is updated at regular intervals by being obtained after the camera collection image of many places through Image analysis.Age-based and sex of the invention is divided customer group, attention rate highest Commdity advertisement is launched according to consumer type, launch strategy and combine the long-term Shopping Behaviors of customer, to the much information such as commodity and the interest-degree of advertisement, advertisement delivery effect is effectively increased, and can be according to the comprehensive concern index of customer behavior more new commodity.

Description

A kind of retail shop's individual character advertisement intelligent method for pushing and system
Technical field
The present invention relates to personalized recommendation field, more particularly to a kind of retail shop's individual character advertisement intelligent method for pushing and it is System.
Background technology
Retail shop is directly facing ultimate consumer, in order to boost consumption, consumption guidance function, and the advertisement in retail trade Publicity can arouse potential consumption demand, guide the consumption propensity, mode and fashion of consumer., can in terms of advertising To pass through poster, banner, the dispensing and push of the intelligent advisement player progress advertisement of LED display and a new generation.
The push of advertisement is carried out first it is to be understood that the hobby of customer, different colonies is for different type product Interest-degree is different, such as women may more like clothes, skincare product, and male more likes electronic product.In addition, all ages and classes The crowd of section also has different demands to product, and teenager more likes the recreational strong product such as toy, comic books, the elderly couple Health products may be interested.So the advertisement of corresponding attribute is launched after being drawn accordingly to customer group, to cater to difference The hobby and demand of crowd, the push effect of advertisement can be improved.It is entitled " for individual character such as the A of publication No. CN 103493068 The document of change ad selection system and method ", by " based on consumer characteristic and the advertising database for including multiple advertisement profiles Comparison, be identified to present to one or more advertisements of consumer " technical scheme carry out targetedly advertisement.This is special Although profit divides to customer group, corresponding advertisement is then targetedly launched, is launched to what colony assorted The advertisement of sample is determined by manually rule, and the rule manually formulated lacks the support of data, is supported even if there is data Lack ageing, it is understood that there may be deviation, that is, the advertisement launched may not be that corresponding colony most pays close attention to currently, be most interested 's.Therefore need to integrate the long-term Shopping Behaviors of customer, the information to commodity and the interest-degree of advertisement during advertisement launching.
The content of the invention
It is an object of the invention to provide a kind of retail shop's individual character advertisement intelligent method for pushing and system, for being sold Shop precisely pushes the advertisement of attention rate highest commodity to customer.
To achieve these goals, its technical solution is：
A kind of retail shop's individual character advertisement intelligent method for pushing, including：
Step 1：The face image of customer in the viewing areas of advertisement delivery device is obtained using human face detection tech；
Step 2：Feature extraction is carried out to the face image, obtains the face feature letter of customer in the viewing areas Breath；
Step 3：The advertisement delivery device pushes comprehensive concern index highest corresponding with customer face characteristic information The advertisement of commodity, the comprehensive concern index of the commodity are paid close attention to the advertisement of index and commodity by commodity conclusion of the business index, merchandise classification Concern index fusion forms.
In above-mentioned retail shop's individual character advertisement intelligent method for pushing, the facial feature information of the customer includes customer's Sex and place age bracket, the age bracket include children, youth, middle age and old age.
In above-mentioned retail shop's individual character advertisement intelligent method for pushing, the commodity conclusion of the business index includes commodity category or business The conclusion of the business buying policy index of product kind, and the conclusion of the business buying policy index of the commodity in commodity detailed catalogue.
In above-mentioned retail shop's individual character advertisement intelligent method for pushing, the merchandise classification concern index is the category of commodity Or kind concern index.
In above-mentioned retail shop's individual character advertisement intelligent method for pushing, the Commdity advertisement concern index is in commodity detailed catalogue Commodity advertisement concern index, the index is that the viewing areas of the advertisement delivery device is looked after home or domestic affairs the objective duration for seeing advertisement With the ratio of the total duration of the advertisement, the duration of wherein customer's viewing advertisement is obtained by catching the duration of face tracking advertisement.
Have in above-mentioned retail shop's individual character advertisement intelligent method for pushing, the viewing areas of the advertisement delivery device to During few two customers, the priority of customer is formulated according to sales tactics, is had at least in the viewing areas of the advertisement delivery device During two customers, the priority of customer is formulated according to sales tactics, the high customer's of the advertisement delivery device push priority The advertisement of comprehensive concern index highest commodity corresponding to facial feature information.
A kind of retail shop's individual character advertisement intelligent supplying system, including：
First image collection module, the image in viewing areas for obtaining advertisement delivery device；
Face detection module, for detecting customer's face, obtain the face of customer in the advertisement delivery device viewing areas Portion's image；
Face feature extraction module, for carrying out feature extraction to the face image, obtain the viewing areas and look after home or domestic affairs The facial feature information of visitor；
Advertisement provides module, for pushing comprehensive concern corresponding with customer face characteristic information by advertisement delivery device The advertisement of index highest commodity, the comprehensive concern indexs of the commodity by commodity conclusion of the business index, merchandise classification pay close attention to index and The advertisement concern index fusion of commodity forms.
In above-mentioned retail shop's individual character advertisement intelligent supplying system, the facial feature information of the customer includes customer's Sex and place age bracket, the age bracket include children, youth, middle age and old age.
In above-mentioned retail shop's individual character advertisement intelligent supplying system, the commodity conclusion of the business index includes commodity category or business The conclusion of the business buying policy index of product kind, and the conclusion of the business buying policy index of the commodity in commodity detailed catalogue；The merchandise classification pays close attention to index Category or kind concern index for commodity；The Commdity advertisement concern index is that the advertisement concern of the commodity in commodity detailed catalogue refers to Mark, the index are that the viewing areas of the advertisement delivery device is looked after home or domestic affairs the total duration of the objective duration and the advertisement for seeing advertisement The duration of ratio, wherein customer viewing advertisement is obtained by catching the duration of face tracking advertisement.
It is base that index is paid close attention in the advertisement of the conclusion of the business index, merchandise classification concern index and commodity of the commodity being related in the present invention Carry out counting calculating in a period, have higher reference value and science so as to make obtained data.Each index By the concern time of camera collection facial image and customer to the concern time of certain class I goods and to advertisement in shop etc. Obtain through Image analysis after information, and be updated at regular intervals.Of the invention age-based and sex is by customer Colony is divided, and the advertisement of attention rate highest commodity is launched according to the particular type of customer, is launched advertisement and is combined customer Long-term Shopping Behaviors, to the much information such as commodity and the interest-degree of advertisement, be effectively improved advertisement delivery effect, and can be with According to the comprehensive concern index of customer behavior more new commodity.
Brief description of the drawings
Fig. 1 is a kind of retail shop's individual character advertisement intelligent method for pushing flow chart according to an exemplary embodiment.
Fig. 2 is the commodity conclusion of the business indicator-specific statistics flow chart according to an exemplary embodiment.
Fig. 3 is that the merchandise classification according to an exemplary embodiment pays close attention to indicator-specific statistics flow chart.
Fig. 4 is that the Commdity advertisement according to an exemplary embodiment pays close attention to indicator-specific statistics flow chart.
Fig. 5 is a kind of system frame of retail shop's individual character advertisement intelligent supplying system according to an exemplary embodiment Figure.
Embodiment
The present invention is further detailed explanation with reference to the accompanying drawings and detailed description.
As shown in figure 1, a kind of retail shop's individual character advertisement intelligent method for pushing, including：
Step 1：The face image of customer in the viewing areas of advertisement delivery device is obtained using human face detection tech；
Step 2：Feature extraction is carried out to the face image, obtains the face feature letter of customer in the viewing areas Breath；
Step 3：The advertisement delivery device pushes comprehensive concern index highest corresponding with customer face characteristic information The advertisement of commodity.
The advertisement delivery device of embodiment can be the advertisement machine with camera, and camera is obtained in advertisement machine viewing areas Customer face image, the extraction of characteristic information is then further carried out to human face region, obtains sex and the place of customer Age attribute, age attribute are place age section, and age bracket includes children, youth, middle age and old age, can also use it certainly His age criteria for classification, the advertisements of different attribute crowds are adapted to according to different launched in advertisement machine of customer characteristic information.
The front of face is detected using Face datection algorithm, while according to face feature point information, to detecting The front of face corrected, so as to avoid face from deflecting the influence to follow-up identification process, to improve the sex to customer With the accuracy rate of age attribute identification.
Sex and age attribute are obtained by facial feature information and then use depth convolutional neural networks The method of (Convolutional Neural Networks, CNN), used convolutional neural networks include 3 convolutional layers, and 2 Individual full articulamentum and 1 output layer.By in the model that trains of the face detected input, by obtained by the model that trains Parameter carry out convolution algorithm, the age of the customer and the characteristic information of sex can be directly obtained.
The problem of inaccurate is differentiated caused by during in order to prevent that customer from moving before camera, by pretreated face figure When piece is sent into the differentiation of the network progress face character trained, the time-space relationship of video multiple image can be utilized, sets one Individual rational threshold value, when continuous three two field pictures Attribute Recognition result is identical and is more than threshold value, system just determines the customer most Whole attribute is this result, this that sex and age attribute recognition correct rate are can ensure that by way of multiple image is identified.
Commodity in embodiment are mainly classified by following level：
1st, major class：The specialization of commodity production and the field of circulation is embodied, such as hardware class, chemical, foodstuff, aquatic product Deng；
2nd, middle class (commodity category)：The general name with some common properties or feature commodity is embodied, such as food commodity again Vegetables and fruit, meat and meat products, breast and dairy products, egg and egg products etc. can be divided into；
3rd, group (range of goods)：The further division of centering class commodity, embodies specific trade name.Such as alcoholic commercial articles It is divided into white wine, beer, grape wine, fruit wine etc.；
4th, commodity detailed catalogue：Detailed differentiation to range of goods, including the specification of commodity, pattern, grade etc., more specifically body The feature of existing commodity, such as 60 ° high cup board five-Grain Liquor.
Commodity in commodity category, range of goods and commodity detailed catalogue are relative concept, specific classifying rules according to Market actual conditions and statistical demand can be adjusted.
Wherein, the comprehensive concern index of commodity is paid close attention to the advertisement pass of index and commodity by commodity conclusion of the business index, merchandise classification Note index fusion forms.
Wherein, commodity conclusion of the business index includes commodity p conclusion of the business buying policy index xICategory corresponding to (i, j, p) and commodity p or Kind Q (p) conclusion of the business buying policy index xC(i, j, Q (p)) is respectively：
I is the age attribute of customer, i ∈ { 1,2,3,4 }, and order of elements in set represents children, youth, middle age And old age；J is the gender attribute of customer, j ∈ { 1,2 }, and order of elements in set represents women and male；P is the wide of dispensing Corresponding commodity are accused, the commodity are the commodity in the detailed catalogue under category or kind level, and p ∈ { 1,2 ..., m }, m are just whole Number；Q (p) is category or Breed property corresponding to commodity p；Q is the category or kind of commodity, and q ∈ { 1,2 ..., n }, n are just whole Number；For purchase commodity category or kind q number；To buy commodity p number；Business is corresponded to for purchase commodity p Product attribute is Q (p) number.
Example below conveniently understands present disclosure：Assuming that the suncream of certain brand its volume in all commodity in market Number be 5, its conclusion of the business buying policy index in the customer group that attribute is young women is xI(2,1,5)；The suncream of the brand Corresponding cosmetics category is expressed as Q (5), in the customer group that attribute is young women, the conclusion of the business buying policy index of cosmetics For xC(2,1, Q (5)), are also assumed that under same criteria for classification, and it is 1 that cosmetics Q (5) is numbered in all middle class levels, Then xC(2,1, Q (5)) are also referred to as xC(2,1,1)。
xC(i, j, Q (p)) numerical value is bigger to be represented such crowd and is more likely to buy Q (p) class product, xI(i, j, p) numerical value is got over It is big to represent that customer is more likely to buy commodity p in Q (p) class commodity.
As shown in Fig. 2 classification Q (p) number is by the second of cashier corresponding to purchase commodity p number and commodity p Image collection module and the bar code scanner comprehensive analysis of commodity statistics, the second image collection module are used to gather at cashier Current customer image, it is easy to subsequently identify and count the attributes such as sex and the age of customer, bar code scanner records the second figure The information such as the commodity p that the current customer caught as acquisition module is bought quantity and price.
As shown in figure 3, merchandise classification concern index is the concern index x of category corresponding to commodity p or kindA(Q(p))
In formula, p is the commodity corresponding to the advertisement launched, and the commodity are the business in the detailed catalogue under category or kind level Product, p ∈ { 1,2 ..., m }, m is positive integer；Q (p) is category or Breed property corresponding to commodity p；AQ(p)For corresponding to commodity p The concern number of category or Breed property Q (p)；Q is the category or kind of commodity, and q ∈ { 1,2 ..., n }, n is positive integer；Aq The number of the concern of category or kind q for commodity.
Because what is typically displayed on same shelf is category or kind identical commodity, therefore customer is in each category Or residence time is adopted by that can capture the 3rd image collection module of the people of shelf and its surrounding at the commodity of kind Obtained after collection through analysis.By setting the judgment mode of threshold value to exclude simply to pass by the customer of shelf.Herein can not be right Customer's age, sex are judged, only analyze whole customer group to each category or the degree of concern of the commodity of kind.
As shown in figure 4, Commdity advertisement concern index xT(p) viewing areas for advertisement delivery device, which is looked after home or domestic affairs, objective sees advertisement Duration and the advertisement total duration ratio, wherein customer watches the duration of advertisement by catching the duration of face tracking advertisement Obtain.It is not required to detect human face region in every two field picture, saves run time so that system real time is stronger, subtracts simultaneously Few issuable erroneous judgement so that the system is more sane.
Index is paid close attention in the advertisement of the conclusion of the business index, merchandise classification concern index and commodity of commodity to be entered based on a period Row statistics calculates, for example, can using one week, one month or 1 year as one timing statisticses section, so as to make obtained data have compared with High reference value and science.Interest of the higher expression crowd of overall target that the fusion of these three indexs forms to commodity p Degree is bigger, there is bigger probability selection purchase, comprehensive concern index f (p；I, j) calculated by following formula：
f(p；I, j)=w1xC(i,j,Q(p))+w2xI(i,j,p)+w3xA(Q(p))+w4xT(p)+b
In formula, i is the age attribute of customer, i ∈ { 1,2,3,4 }, and order of elements in set represents children, green grass or young crops Year, middle age and old age；J is the gender attribute of customer, j ∈ { 1,2 }, and order of elements in set represents women and male；P is throwing The commodity corresponding to advertisement put, the commodity are the commodity in the detailed catalogue under category or kind level, p ∈ { 1,2 ..., m }, m For positive integer；Q (p) is category or Breed property corresponding to commodity p；xC(i, j, Q (p)) is category or kind corresponding to commodity p Conclusion of the business buying policy index；xI(i, j, p) is commodity p conclusion of the business buying policy index；xA(Q (p)) is category or kind corresponding to commodity p Concern index；xT(p) index is paid close attention to for commodity p advertisement；w1、w2、w3、w4, b take real number.Following example conveniently understands Q (p) category or kind corresponding to the 3rd commodity of numbering of complete quotient field are represented with p relation, Q (3), it is assumed that in the classification gauge of formulation The commodity of the 3rd sequence number are certain brand mobile phone in then, then Q (3) represents mobile phone productses class.
Commodity overall target f (p；I, j) mainly by specific in customer's age attribute, gender attribute, commodity detailed catalogue level Commodity p influence.X in expression formulaC、xICommodity conclusion of the business index, reflect customer more favor purchase category or kind and Specific commodity under detailed catalogue level, can be by w1、w2Larger weights are set.xAIt is the category of commodity or the concern index of kind, Reflect customer's type of merchandise interested that may be bought, w3Value can be slightly below w1、w2.Commdity advertisement concern index xT Customer is reflected to playing the interest of advertisement either to the level of interest of advertised product, w4Value can be with w3Quite.Initial When changing parameter, 4 weight distribution identical values can be modified by traffic-operating period.In addition, can be square by parameter b Just the index of a certain bar advertisement is changed, such as new advertisement thinks that preferential old advertisement plays, then can set the parameter b of new advertisement It is larger, it can avoid always playing several fixed advertisements.
In a kind of preferable mode, when having at least two customers in the viewing areas of advertisement delivery device, according to sale The priority of policy development customer, the advertisement delivery device push comprehensive corresponding to the facial feature information of the high customer of priority Close the advertisement of concern index highest commodity.
Can be for priority：Children's priority is higher than youth, and youth is higher than adult, and adult is higher than old age People；When the customer detected is in same age bracket, then sex priority is determined, can be that women priority is higher than male. Certain priority orders are not limited to the above situation, can be adjusted as the case may be.
Play currently launch advertisement when, only track record have been subjected to Attribute Recognition customer watch advertisement it is accumulative when Between, no longer other customer groups are identified, even if occur before the camera of advertisement machine the higher customer of priority also not in The broadcasting of disconnected Current ad.If the camera of advertisement machine loses currently playing advertisement targeted customer, continue to work as The broadcasting of preceding advertisement, through being detected again to the face of customer after a period of time, if detecting the customer that previously lost falls, Continue the broadcasting of Current ad, if detecting other customers, play the ad content being consistent with customer's age, sex.
A kind of retail shop's individual character advertisement intelligent supplying system, including：
First image collection module, the image in viewing areas for obtaining advertisement delivery device；
Face detection module, for detecting customer's face, obtain the face of customer in the advertisement delivery device viewing areas Portion's image；
Face feature extraction module, for carrying out feature extraction to the face image, obtain the viewing areas and look after home or domestic affairs The facial feature information of visitor；
Advertisement provides module, for pushing comprehensive concern corresponding with customer face characteristic information by advertisement delivery device The advertisement of index highest commodity.
The extracting method of facial feature information in a kind of retail shop's individual character advertisement intelligent supplying system of embodiment and The computational methods of the comprehensive concern index of commodity are implemented in a kind of foregoing retail shop's individual character advertisement intelligent method for pushing Introduce in example, repeat no more here.
For extracting the image at customer's age and sex character information by positioned at cashier when counting commodity conclusion of the business index The second image collection module collection.Buy commodity category or kind q numberBuy commodity p numberBuy business Product p corresponding goods attribute is Q (p) numberObtained by the bar code scanner of cashier.Computer analyzes the second image The commodity for customer's purchase that customer characteristic information is obtained after the custom image of acquisition module collection and is obtained with bar code scanner Information is associated integration.Concern number in merchandise classification concern index per class commodity is obtained by the 3rd image near shelf Obtained after module collection image through analysis.After advertisement pays close attention to the time by described first image acquisition module and subsequent analysis processing The duration for obtaining face tracking advertisement in the viewing areas of advertisement delivery device obtains.Wherein, the first image collection module is Camera in advertisement delivery device, the second image collection module at cashier, monitor shelf the 3rd image collection module, article The equipment such as code scanner and computer can be entered by existing camera, computer system, bar code scanner in market Row transformation, system block diagram is referring to Fig. 5.
It is as follows that the strategy of advertisement is launched using above-mentioned advertisement intelligent method for pushing and system, reference can be made to Fig. 1：
1st, when user distance advertisement machine camera is unidentified farther out arrive customer face feature when, calculate commodity synthesis concern Can be by weight w during index1、w20 is set to, at this moment only considers the shadow of merchandise classification concern index and Commdity advertisement concern index Ring, choose the product advertising that most of customer families are more favored, the size of concern index is integrated successively according to commodity from advertisement base Play advertisement；
2nd, after advertisement machine detects a certain customer, its face image is obtained, extracts the sex and age segment information of user, The commodity synthesis concern index highest business according to corresponding to the sex of customer and age bracket extract attribute crowd out of database The advertisement of product simultaneously plays out；
3rd, after advertisement machine detects that multiple customers are watching advertisement, the excellent of user's characteristic information is formulated according to sales tactics First level, the advertisement of the maximum commodity of corresponding commodity synthesis concern desired value is played for the customer of highest priority；
4th, Commdity advertisement concern indication information is updated during customer purchase and viewing advertisement.
Method and system provided by the invention can not only be used in advertisement putting field, presentation, rush to commodity Pin and buying are also helpful.Noticeable position can be displayed in for the commodity favored by consumers in general so that production The promotion of product has more specific aim.

Claims (10)

  1. A kind of 1. retail shop's individual character advertisement intelligent method for pushing, it is characterised in that including：
    Step 1：The face image of customer in the viewing areas of advertisement delivery device is obtained using human face detection tech；
    Step 2：Feature extraction is carried out to the face image, obtains the facial feature information of customer in the viewing areas, institute Stating facial feature information includes sex and age, and the age is age segment information, including children, youth, middle age and old Year；
    Step 3：The advertisement delivery device pushes comprehensive concern index highest commodity corresponding with customer face characteristic information Advertisement, the comprehensive concern index f (p；I, j) be：
    f(p；I, j)=w1xC(i,j,Q(p))+w2xI(i,j,p)+w3xA(Q(p))+w4xT(p)+b
    In formula, i is the age attribute of customer, i ∈ { 1,2,3,4 }, order of elements in set represent children, youth, in Year and old age；J is the gender attribute of customer, j ∈ { 1,2 }, and order of elements in set represents women and male；P is what is launched Commodity corresponding to advertisement, the commodity are the commodity in the detailed catalogue under category or kind level, and p ∈ { 1,2 ..., m }, m is just Integer；Q (p) is category or Breed property corresponding to commodity p；xC(i, j, Q (p)) be category corresponding to commodity p or kind into Hand over buying policy index；xI(i, j, p) is commodity p conclusion of the business buying policy index；xA(Q (p)) is the pass of category or kind corresponding to commodity p Note index；xT(p) index is paid close attention to for commodity p advertisement；w1、w2、w3、w4, b take real number.
  2. 2. retail shop's individual character advertisement intelligent method for pushing according to claim 1, it is characterised in that the commodity p's Conclusion of the business buying policy index xIThe conclusion of the business buying policy index x of category corresponding to (i, j, p) and commodity p or kind Q (p)C(i, j, Q (p)) difference For：
    <mrow> <msub> <mi>x</mi> <mi>I</mi> </msub> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>j</mi> <mo>,</mo> <mi>p</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <msubsup> <mi>N</mi> <mi>p</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> <msubsup> <mi>N</mi> <mrow> <mi>Q</mi> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> </mrow> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> </mfrac> </mrow>
    <mrow> <msub> <mi>x</mi> <mi>C</mi> </msub> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>j</mi> <mo>,</mo> <mi>Q</mi> <mo>(</mo> <mi>p</mi> <mo>)</mo> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <msubsup> <mi>N</mi> <mrow> <mi>Q</mi> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> </mrow> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>q</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msubsup> <mi>N</mi> <mi>q</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> </mrow> </mfrac> </mrow>
    In formula, q is the category or kind of commodity, and q ∈ { 1,2 ..., n }, n is positive integer；For purchase commodity category or kind Q number；To buy commodity p number；The number for being Q (p) for purchase commodity p corresponding goods attributes.
  3. 3. retail shop's individual character advertisement intelligent method for pushing according to claim 1, it is characterised in that p pairs of the commodity The category or the concern index x of kind answeredA(Q (p)) is：
    <mrow> <msub> <mi>x</mi> <mi>A</mi> </msub> <mrow> <mo>(</mo> <mi>Q</mi> <mo>(</mo> <mi>p</mi> <mo>)</mo> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <msub> <mi>A</mi> <mrow> <mi>Q</mi> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> </mrow> </msub> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>q</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>A</mi> <mi>q</mi> </msub> </mrow> </mfrac> </mrow>
    In formula, AQ(p)For category corresponding to commodity p or Breed property Q (p) concern number；Q be commodity category or kind, q ∈ { 1,2 ..., n }, n is positive integer；AqThe number of the concern of category or kind q for commodity, category or product of the customer in commodity Effective concern number is designated as when residence time exceedes threshold value at kind q.
  4. 4. retail shop's individual character advertisement intelligent method for pushing according to claim 1, it is characterised in that the Commdity advertisement Pay close attention to index xT(p) viewing areas for advertisement delivery device is looked after home or domestic affairs the ratio of the total duration of the objective duration for seeing advertisement and the advertisement The duration that value, wherein customer watch advertisement is obtained by catching the duration of face tracking advertisement.
  5. 5. retail shop's individual character advertisement intelligent method for pushing according to claim 1, it is characterised in that the advertisement putting When having at least two customers in the viewing areas of device, the priority of customer, the advertisement putting dress are formulated according to sales tactics Put the advertisement of comprehensive concern index highest commodity corresponding to the facial feature information of the high customer of push priority.
  6. A kind of 6. retail shop's individual character advertisement intelligent supplying system, it is characterised in that including：
    First image collection module, the image in viewing areas for obtaining advertisement delivery device；
    Face detection module, for detecting customer's face, obtain face's figure of customer in the advertisement delivery device viewing areas Picture；
    Face feature extraction module, for carrying out feature extraction to the face image, obtain customer in the viewing areas Facial feature information, the facial feature information include sex and age, and the age is age segment information, including juvenile youngster Virgin, young, middle age and old age；
    Advertisement provides module, for pushing comprehensive concern index corresponding with customer face characteristic information by advertisement delivery device The advertisement of highest commodity, the comprehensive concern index f (p；I, j) be：
    f(p；I, j)=w1xC(i,j,Q(p))+w2xI(i,j,p)+w3xA(Q(p))+w4xT(p)+b
    In formula, i is the age attribute of customer, i ∈ { 1,2,3,4 }, order of elements in set represent children, youth, in Year and old age；J is the gender attribute of customer, j ∈ { 1,2 }, and order of elements in set represents women and male；P is what is launched Commodity corresponding to advertisement, the commodity are the commodity in the detailed catalogue under category or kind level, and p ∈ { 1,2 ..., m }, m is just Integer；Q (p) is category or Breed property corresponding to commodity p；xC(i, j, Q (p)) be category corresponding to commodity p or kind into Hand over buying policy index；xI(i, j, p) is commodity p conclusion of the business buying policy index；xA(Q (p)) is the pass of category or kind corresponding to commodity p Note index；xT(p) index is paid close attention to for commodity p advertisement；w1、w2、w3、w4, b take real number.
  7. 7. retail shop's individual character advertisement intelligent supplying system according to claim 6, it is characterised in that the commodity p's Conclusion of the business buying policy index xIThe conclusion of the business buying policy index x of category corresponding to (i, j, p) and commodity p or kind Q (p)C(i, j, Q (p)) difference For：
    <mrow> <msub> <mi>x</mi> <mi>I</mi> </msub> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>j</mi> <mo>,</mo> <mi>p</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <msubsup> <mi>N</mi> <mi>p</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> <msubsup> <mi>N</mi> <mrow> <mi>Q</mi> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> </mrow> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> </mfrac> </mrow>
    <mrow> <msub> <mi>x</mi> <mi>C</mi> </msub> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>j</mi> <mo>,</mo> <mi>Q</mi> <mo>(</mo> <mi>p</mi> <mo>)</mo> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <msubsup> <mi>N</mi> <mrow> <mi>Q</mi> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> </mrow> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>q</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msubsup> <mi>N</mi> <mi>q</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>j</mi> </mrow> </msubsup> </mrow> </mfrac> </mrow>
    In formula, q is the category or kind of commodity, and q ∈ { 1,2 ..., n }, n is positive integer；For purchase commodity category or kind Q number；To buy commodity p number；The number for being Q (p) for purchase commodity p corresponding goods attributes.
  8. 8. retail shop's individual character advertisement intelligent supplying system according to claim 6, it is characterised in that p pairs of the commodity The category or the concern index x of kind answeredA(Q (p)) is：
    <mrow> <msub> <mi>x</mi> <mi>A</mi> </msub> <mrow> <mo>(</mo> <mi>Q</mi> <mo>(</mo> <mi>p</mi> <mo>)</mo> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <msub> <mi>A</mi> <mrow> <mi>Q</mi> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> </mrow> </msub> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>q</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>A</mi> <mi>q</mi> </msub> </mrow> </mfrac> </mrow>
    In formula, AQ(p)For category corresponding to commodity p or Breed property Q (p) concern number；Q be commodity category or kind, q ∈ { 1,2 ..., n }, n is positive integer；AqThe number of the concern of category or kind q for commodity, category or product of the customer in commodity Effective concern number is designated as when residence time exceedes threshold value at kind q.
  9. 9. retail shop's individual character advertisement intelligent supplying system according to claim 6, it is characterised in that the Commdity advertisement Pay close attention to index xT(p) viewing areas for advertisement delivery device is looked after home or domestic affairs the ratio of the total duration of the objective duration for seeing advertisement and the advertisement The duration that value, wherein customer watch advertisement is obtained by catching the duration of face tracking advertisement.
  10. 10. retail shop's individual character advertisement intelligent supplying system according to claim 6, it is characterised in that the advertisement is thrown Put in the viewing areas of device when having at least two customers, the priority of customer, the advertisement putting are formulated according to sales tactics The advertisement of comprehensive concern index highest commodity corresponding to the facial feature information of the high customer of device push priority.
CN201710994886.XA 2017-10-23 2017-10-23 A kind of retail shop's individual character advertisement intelligent method for pushing and system Pending CN107798560A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710994886.XA CN107798560A (en) 2017-10-23 2017-10-23 A kind of retail shop's individual character advertisement intelligent method for pushing and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710994886.XA CN107798560A (en) 2017-10-23 2017-10-23 A kind of retail shop's individual character advertisement intelligent method for pushing and system

Publications (1)

Publication Number Publication Date
CN107798560A true CN107798560A (en) 2018-03-13

Family

ID=61533508

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710994886.XA Pending CN107798560A (en) 2017-10-23 2017-10-23 A kind of retail shop's individual character advertisement intelligent method for pushing and system

Country Status (1)

Country Link
CN (1) CN107798560A (en)

Cited By (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108648338A (en) * 2018-04-12 2018-10-12 广州杰赛科技股份有限公司 The shopping saving system method, apparatus and vending machine of automatic vending machine
CN108711072A (en) * 2018-05-10 2018-10-26 西安万像电子科技有限公司 Data processing method and data processing system
CN108766278A (en) * 2018-05-15 2018-11-06 三星电子（中国）研发中心 A kind of electronic guide board method for information display and device
CN108876430A (en) * 2018-04-28 2018-11-23 广东智媒云图科技股份有限公司 A kind of advertisement sending method based on crowd characteristic, electronic equipment and storage medium
CN108921585A (en) * 2018-05-15 2018-11-30 北京七鑫易维信息技术有限公司 A kind of advertisement sending method, device, equipment and storage medium
CN108961005A (en) * 2018-07-06 2018-12-07 北京旷视科技有限公司 Information-pushing method, device, electronic equipment and medium
CN108985835A (en) * 2018-07-09 2018-12-11 上海小蚁科技有限公司 Target group determines method and device, storage medium, terminal
CN108985853A (en) * 2018-07-27 2018-12-11 优信拍（北京）信息科技有限公司 A kind of promotion method of transaction, apparatus and system
CN109003135A (en) * 2018-07-20 2018-12-14 云南航伴科技有限公司 Intelligent advertisement matching supplying system and method based on recognition of face
CN109003134A (en) * 2018-07-20 2018-12-14 云南航伴科技有限公司 Intelligent advertisement delivery system and method based on recognition of face
CN109064214A (en) * 2018-07-09 2018-12-21 河南深实科技有限公司 A kind of advertisement Redirectional system based on customer's off-line data
CN109102336A (en) * 2018-08-09 2018-12-28 安徽爱依特科技有限公司 Robot advertisement sending method and its system based on image analysis
CN109165992A (en) * 2018-07-16 2019-01-08 北京旷视科技有限公司 A kind of intelligent shopping guide method, apparatus, system and computer storage medium
CN109525866A (en) * 2018-12-06 2019-03-26 安徽海豚新媒体产业发展有限公司 A kind of advertisement sending method based on viewing duration
CN109583972A (en) * 2018-12-19 2019-04-05 中新智擎科技有限公司 A kind of advertisement demonstration method, device, advertisement robot and storage medium
CN109816434A (en) * 2019-01-04 2019-05-28 四川虹美智能科技有限公司 A kind of vending machine advertisement control method for playing back, apparatus and system
CN109840810A (en) * 2019-03-19 2019-06-04 深圳创维－Rgb电子有限公司 Data analyze method for pushing, device, background server and readable storage medium storing program for executing
CN109934633A (en) * 2019-03-15 2019-06-25 广州溯源信息技术有限公司 A kind of precision marketing display rack system and method based on RFID technique
CN110415733A (en) * 2019-07-18 2019-11-05 乐播新瑞(北京)文化传媒有限公司 Audio-frequence player device, central control system, the update of audio and playback method and system
CN110413096A (en) * 2019-08-02 2019-11-05 梁彩连 A kind of advertisement intelligent display system based on big data
CN110517094A (en) * 2019-08-30 2019-11-29 软通动力信息技术有限公司 A kind of visitor's data analysing method, device, server and medium
CN111598600A (en) * 2019-02-21 2020-08-28 虹软科技股份有限公司 Multimedia information pushing method and system and terminal equipment
CN111738749A (en) * 2019-06-18 2020-10-02 北京京东尚科信息技术有限公司 Information display method and device, electronic equipment and storage medium
CN112070546A (en) * 2020-09-10 2020-12-11 浪潮软件股份有限公司 Advertisement putting method based on big data and face recognition
WO2020253577A1 (en) * 2019-06-19 2020-12-24 京东方科技集团股份有限公司 Resource display method and device, and storage medium thereof
CN112163888A (en) * 2020-09-30 2021-01-01 成都新潮传媒集团有限公司 Advertisement matching method, device and storage medium
CN112651793A (en) * 2021-02-09 2021-04-13 广东天正计算机服务有限公司 Intelligent retail system based on face recognition
CN112805739A (en) * 2018-10-05 2021-05-14 三星电子株式会社 Electronic device and control method thereof
CN112823363A (en) * 2019-08-29 2021-05-18 利妍控股有限公司 System and method for retail display of cosmetics
CN113129047A (en) * 2019-12-31 2021-07-16 上海依图信息技术有限公司 Advertisement putting method and device for escalator robot
CN113222642A (en) * 2021-04-15 2021-08-06 南京有物信息科技有限公司 Special television marketing system for stores
CN113378765A (en) * 2021-06-25 2021-09-10 四川启睿克科技有限公司 Intelligent statistical method and device for advertisement attention crowd and computer readable storage medium
CN113421130A (en) * 2021-07-20 2021-09-21 重庆京东方智慧科技有限公司 Advertisement pushing method and device, electronic equipment and readable storage medium
CN114067397A (en) * 2021-11-16 2022-02-18 浙大城市学院 Advertisement analysis and delivery method based on machine vision
CN114141132A (en) * 2022-01-30 2022-03-04 广州长嘉电子有限公司 Advertising machine and advertising directional display method
CN115099866A (en) * 2022-07-07 2022-09-23 悦诚智慧(厦门)科技有限公司 Advertisement delivery system based on AI glasses
WO2022222051A1 (en) * 2021-04-20 2022-10-27 京东方科技集团股份有限公司 Method, apparatus and system for customer group analysis, and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102722842A (en) * 2012-06-11 2012-10-10 姚明东 Commodity recommendation optimizing method based on customer behavior
CN103493068A (en) * 2011-04-11 2014-01-01 英特尔公司 Personalized advertisement selection system and method
CN104573619A (en) * 2014-07-25 2015-04-29 北京智膜科技有限公司 Method and system for analyzing big data of intelligent advertisements based on face identification
CN105825390A (en) * 2015-01-05 2016-08-03 上海通路快建网络服务外包有限公司 Commodity recommendation method, commodity recommendation device, and commodity recommendation system
CN106408377A (en) * 2016-08-31 2017-02-15 广东华邦云计算股份有限公司 Shopping recommended method and system
CN106899646A (en) * 2015-12-21 2017-06-27 美的集团股份有限公司 Information-pushing method, system, intelligent member card and Cloud Server
CN107103487A (en) * 2017-03-02 2017-08-29 浙江兰德纵横网络技术股份有限公司 A kind of advertisement sending method based on big data

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103493068A (en) * 2011-04-11 2014-01-01 英特尔公司 Personalized advertisement selection system and method
CN102722842A (en) * 2012-06-11 2012-10-10 姚明东 Commodity recommendation optimizing method based on customer behavior
CN104573619A (en) * 2014-07-25 2015-04-29 北京智膜科技有限公司 Method and system for analyzing big data of intelligent advertisements based on face identification
CN105825390A (en) * 2015-01-05 2016-08-03 上海通路快建网络服务外包有限公司 Commodity recommendation method, commodity recommendation device, and commodity recommendation system
CN106899646A (en) * 2015-12-21 2017-06-27 美的集团股份有限公司 Information-pushing method, system, intelligent member card and Cloud Server
CN106408377A (en) * 2016-08-31 2017-02-15 广东华邦云计算股份有限公司 Shopping recommended method and system
CN107103487A (en) * 2017-03-02 2017-08-29 浙江兰德纵横网络技术股份有限公司 A kind of advertisement sending method based on big data

Cited By (43)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108648338A (en) * 2018-04-12 2018-10-12 广州杰赛科技股份有限公司 The shopping saving system method, apparatus and vending machine of automatic vending machine
CN108876430A (en) * 2018-04-28 2018-11-23 广东智媒云图科技股份有限公司 A kind of advertisement sending method based on crowd characteristic, electronic equipment and storage medium
CN108876430B (en) * 2018-04-28 2021-02-02 广东智媒云图科技股份有限公司 Advertisement pushing method based on crowd characteristics, electronic equipment and storage medium
CN108711072A (en) * 2018-05-10 2018-10-26 西安万像电子科技有限公司 Data processing method and data processing system
CN108766278A (en) * 2018-05-15 2018-11-06 三星电子（中国）研发中心 A kind of electronic guide board method for information display and device
CN108921585A (en) * 2018-05-15 2018-11-30 北京七鑫易维信息技术有限公司 A kind of advertisement sending method, device, equipment and storage medium
CN108766278B (en) * 2018-05-15 2020-06-05 三星电子（中国）研发中心 Electronic guideboard information display method and device
CN108961005A (en) * 2018-07-06 2018-12-07 北京旷视科技有限公司 Information-pushing method, device, electronic equipment and medium
CN108985835A (en) * 2018-07-09 2018-12-11 上海小蚁科技有限公司 Target group determines method and device, storage medium, terminal
CN109064214A (en) * 2018-07-09 2018-12-21 河南深实科技有限公司 A kind of advertisement Redirectional system based on customer's off-line data
CN109165992A (en) * 2018-07-16 2019-01-08 北京旷视科技有限公司 A kind of intelligent shopping guide method, apparatus, system and computer storage medium
CN109003134A (en) * 2018-07-20 2018-12-14 云南航伴科技有限公司 Intelligent advertisement delivery system and method based on recognition of face
CN109003135A (en) * 2018-07-20 2018-12-14 云南航伴科技有限公司 Intelligent advertisement matching supplying system and method based on recognition of face
CN108985853A (en) * 2018-07-27 2018-12-11 优信拍（北京）信息科技有限公司 A kind of promotion method of transaction, apparatus and system
CN109102336A (en) * 2018-08-09 2018-12-28 安徽爱依特科技有限公司 Robot advertisement sending method and its system based on image analysis
CN112805739A (en) * 2018-10-05 2021-05-14 三星电子株式会社 Electronic device and control method thereof
CN109525866A (en) * 2018-12-06 2019-03-26 安徽海豚新媒体产业发展有限公司 A kind of advertisement sending method based on viewing duration
CN109583972A (en) * 2018-12-19 2019-04-05 中新智擎科技有限公司 A kind of advertisement demonstration method, device, advertisement robot and storage medium
CN109816434A (en) * 2019-01-04 2019-05-28 四川虹美智能科技有限公司 A kind of vending machine advertisement control method for playing back, apparatus and system
CN111598600A (en) * 2019-02-21 2020-08-28 虹软科技股份有限公司 Multimedia information pushing method and system and terminal equipment
CN109934633A (en) * 2019-03-15 2019-06-25 广州溯源信息技术有限公司 A kind of precision marketing display rack system and method based on RFID technique
CN109840810A (en) * 2019-03-19 2019-06-04 深圳创维－Rgb电子有限公司 Data analyze method for pushing, device, background server and readable storage medium storing program for executing
CN111738749A (en) * 2019-06-18 2020-10-02 北京京东尚科信息技术有限公司 Information display method and device, electronic equipment and storage medium
WO2020253577A1 (en) * 2019-06-19 2020-12-24 京东方科技集团股份有限公司 Resource display method and device, and storage medium thereof
CN110415733B (en) * 2019-07-18 2021-09-17 乐播新瑞(北京)文化传媒有限公司 Audio playing equipment, central control system, audio updating and playing method and system
CN110415733A (en) * 2019-07-18 2019-11-05 乐播新瑞(北京)文化传媒有限公司 Audio-frequence player device, central control system, the update of audio and playback method and system
CN110413096B (en) * 2019-08-02 2021-12-14 深圳市米优文化网络有限公司 Advertisement intelligent display system based on big data
CN110413096A (en) * 2019-08-02 2019-11-05 梁彩连 A kind of advertisement intelligent display system based on big data
CN112823363A (en) * 2019-08-29 2021-05-18 利妍控股有限公司 System and method for retail display of cosmetics
CN110517094A (en) * 2019-08-30 2019-11-29 软通动力信息技术有限公司 A kind of visitor's data analysing method, device, server and medium
CN113129047A (en) * 2019-12-31 2021-07-16 上海依图信息技术有限公司 Advertisement putting method and device for escalator robot
CN112070546A (en) * 2020-09-10 2020-12-11 浪潮软件股份有限公司 Advertisement putting method based on big data and face recognition
CN112163888A (en) * 2020-09-30 2021-01-01 成都新潮传媒集团有限公司 Advertisement matching method, device and storage medium
CN112651793A (en) * 2021-02-09 2021-04-13 广东天正计算机服务有限公司 Intelligent retail system based on face recognition
CN113222642A (en) * 2021-04-15 2021-08-06 南京有物信息科技有限公司 Special television marketing system for stores
WO2022222051A1 (en) * 2021-04-20 2022-10-27 京东方科技集团股份有限公司 Method, apparatus and system for customer group analysis, and storage medium
CN113378765A (en) * 2021-06-25 2021-09-10 四川启睿克科技有限公司 Intelligent statistical method and device for advertisement attention crowd and computer readable storage medium
CN113421130A (en) * 2021-07-20 2021-09-21 重庆京东方智慧科技有限公司 Advertisement pushing method and device, electronic equipment and readable storage medium
CN114067397A (en) * 2021-11-16 2022-02-18 浙大城市学院 Advertisement analysis and delivery method based on machine vision
CN114067397B (en) * 2021-11-16 2024-03-29 浙大城市学院 Advertisement analysis and delivery method based on machine vision
CN114141132A (en) * 2022-01-30 2022-03-04 广州长嘉电子有限公司 Advertising machine and advertising directional display method
CN114141132B (en) * 2022-01-30 2022-05-03 广州长嘉电子有限公司 Advertising machine and advertising directional display method
CN115099866A (en) * 2022-07-07 2022-09-23 悦诚智慧(厦门)科技有限公司 Advertisement delivery system based on AI glasses

Similar Documents

Publication Publication Date Title
CN107798560A (en) A kind of retail shop&#39;s individual character advertisement intelligent method for pushing and system
Inoue et al. Predicting behavioral loyalty through corporate social responsibility: The mediating role of involvement and commitment
CN103390238B (en) System and method for configuring advertisement
CN106791901B (en) Live broadcast channel ordering method and device
CN108073671A (en) Business object recommends method, apparatus and electronic equipment
US20200320576A1 (en) Targeted Advertising Based On Demographic Features Extracted From Persons
CN107146096A (en) A kind of intelligent video advertisement methods of exhibiting and device
Cox Retail Analytics: The Secret Weapon
CN108876430B (en) Advertisement pushing method based on crowd characteristics, electronic equipment and storage medium
CN111028029A (en) Offline commodity recommendation method and device and electronic equipment
Nassis et al. The effect of fans’ attitudes on sponsorship outcomes: Evidence from an exploratory study in Greece
Popovic Contemporary sports product and making a brand
Streletskaya et al. How information leads consumers to select specialty foods when tasting is not an option
CN112163880A (en) Intelligent advertisement putting method and system based on image processing
Wu et al. Effects of product scarcity: The mediating role of consumer need for uniqueness and conformity
Schulz Effects of branding on restaurants’ image: A case of selected restaurants in Nairobi, Kenya
CN113421130A (en) Advertisement pushing method and device, electronic equipment and readable storage medium
Parganas Fans, spectators, consumers in football
CN112330369A (en) Online trading system for agricultural and sideline products
Gholipour et al. The relationship between sport event quality, satisfaction, perceive value, loyalty and behavior intention: a meta-analysis
CN110807665A (en) Method and device for improving conversion rate of marketing commodities
JP5466097B2 (en) Consumer attribute information acquisition system and consumer attribute information acquisition method
US11210705B1 (en) System and method for transmitting direct advertising information to an augmented reality device
Tokunaga et al. System to Induce Accepting Unconsidered Information by Connecting Current Interests: Proof of Concept in Snack Purchasing Scenarios
CN116894699B (en) Self-adaptive video advertisement putting 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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180313