CN107844997A - Books embedded advertisements dissemination method - Google Patents

Books embedded advertisements dissemination method Download PDF

Info

Publication number
CN107844997A
CN107844997A CN201711210989.9A CN201711210989A CN107844997A CN 107844997 A CN107844997 A CN 107844997A CN 201711210989 A CN201711210989 A CN 201711210989A CN 107844997 A CN107844997 A CN 107844997A
Authority
CN
China
Prior art keywords
books
reader
picture
image
dissemination method
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
CN201711210989.9A
Other languages
Chinese (zh)
Inventor
马志杰
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.)
Beijing Yun Ying Technology Co Ltd
Original Assignee
Beijing Yun Ying Technology Co Ltd
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 Beijing Yun Ying Technology Co Ltd filed Critical Beijing Yun Ying Technology Co Ltd
Priority to CN201711210989.9A priority Critical patent/CN107844997A/en
Publication of CN107844997A publication Critical patent/CN107844997A/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
    • G06Q30/0255—Targeted advertisements based on user history
    • G06Q30/0256—User search
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • G06Q30/0242—Determining effectiveness of advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/757—Matching configurations of points or features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/413—Classification of content, e.g. text, photographs or tables

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Evolutionary Computation (AREA)
  • Multimedia (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a kind of books embedded advertisements dissemination method, including：First step：Every time when reader scans books picture, the extension information related to the books picture is obtained by pattern recognition technique；Second step：According to the extension information, the characteristic of the reader is collected；Third step：According to the characteristic of the reader, to reader's advertisement information.

Description

Books embedded advertisements dissemination method
Technical field
The present invention relates to a kind of books embedded advertisements dissemination method, wherein technology is identified and runed using figure, get through Publishing house, reader, the intrinsic barrier of advertiser three, reduce publishing house and publish and publicize cost, lifting targeted ads are launched Precisely and brand-new business valency is presented with converting in changing effect, continuously and effectively collection and operation user data, realization interaction Value.
Background technology
Conventional display class billboard (newspaper, magazine etc.) is the pattern by using one way propagation, and range covers audient, And certain advertising message is passed on to audient.The coverage rate of conventional display class billboard is wider, and arrival rate is higher, possesses certain Authority, advertisement putting that is a wide range of, concentrating region can be carried out short-term, advertisement letter is carried out to the consumer of target market Breath is passed on.But conventional display class billboard has the following disadvantages：
1. lack of targeted, the accurate reception and registration of advertising message can not be ensured, can not precise positioning to target group；
2. the advertisement putting of one way propagation can not directly obtain the feedback of audiences’perception, follow-up sales situation pair can only be passed through Effect is launched substantially to be assessed；
3. limited flexibility, advertiser is when running into market situation change, it is necessary to which to change ad content highly difficult.
The content of the invention
The technical problems to be solved by the invention are for drawbacks described above in the prior art be present, there is provided a kind of books insertion Formula advertisement compartment system, lifting user's books reading experience is identified by figure, promote user persistently to sweep books and obtain more Information, then using the natural classification dividing mode of books, commercial advertisement is accurately presented to the target group of demand, most Afterwards using the matrix system integrated, integration Reader Data, big data analysis and utilization are carried out.
According to the present invention, there is provided a kind of books embedded advertisements dissemination method, including：
First step：Every time when reader scans books picture, obtained and the books picture by pattern recognition technique Related extension information；
Second step：According to the extension information, the characteristic of the reader is collected；
Third step：According to the characteristic of the reader, to reader's advertisement information.
Preferably, obtaining the extension information related to the books picture by pattern recognition technique includes：By the figure The original image of book picture does convolution with Gaussian kernel and obtains the image of each different scale in metric space, and high by adjusting The scale factor of this core obtains the image of different scale；Then the image of predetermined quantity is extracted respectively after SIFT feature to extraction All SIFT features carry out k-means cluster to obtain k cluster centre as vision word table, finally to each image with list Vocabulary is that specification calculates each SIFT feature of the width image its distance with each word in word list, to be somebody's turn to do The code book of width image, the distance of the code book and training code book of the width image is finally calculated, by the training image of corresponding minimum distance The information extension information related as the books picture.
Preferably, in first step, the extension information related to the books picture is further presented for reader.
Preferably, extension information includes the one or more in Online Bibliography Classification, word, video, picture and voice.
Preferably, judge that the demand of the reader likes classification according to the extension information in second step.
Preferably, the books picture includes the picture page and the word page.
One aspect of the present invention solves publishing house's Books Marketing and returns this pain spot, assists publishing house to receive, collect, run Reader/bean vermicelli data, publishing house's enhancing readers ' reading experience is helped, is not limited by the transmission of diversification means by time, space Information, form good interactive closed loop with reader；On the other hand solve advertiser and launch advertising objective crowd not enough accurately Pain spot, using the Online Bibliography Classification advantage of books, labeling is carried out to the reader to buy books, while reader sweeps picture and obtains information Push corresponding marketing message to reader, obtain effectively, accurately changing effect.
Brief description of the drawings
With reference to accompanying drawing, and by reference to following detailed description, it will more easily have more complete understanding to the present invention And be more easily understood its with the advantages of and feature, wherein：
Fig. 1 schematically shows the flow of books embedded advertisements dissemination method according to the preferred embodiment of the invention Figure.
Fig. 2 schematically shows the signal of books embedded advertisements dissemination method according to the preferred embodiment of the invention Figure.
It should be noted that accompanying drawing is used to illustrate the present invention, it is not intended to limit the present invention.Pay attention to, represent that the accompanying drawing of structure can It can be not necessarily drawn to scale.Also, in accompanying drawing, same or similar element indicates same or similar label.
Embodiment
In order that present disclosure is more clear and understandable, with reference to specific embodiments and the drawings in the present invention Appearance is described in detail.
The present invention propose using the major publishing house in the whole nation publication bibliography and reader resources and/or wechat public number and/or The channels such as APP resources, readers ' reading is lifted by pattern recognition technique and experienced, so as to reach the mesh for promoting reader persistently to sweep books , and then set up core customer's management matrix；Simultaneously using the Online Bibliography Classification of books, label tube is carried out to reader and/or bean vermicelli Reason and data tracking analysis, so as to realize it is accurate, lasting, directionally to reader and/or bean vermicelli advertisement information, realize and convert With sale.
Specifically, Fig. 1 schematically shows books embedded advertisements dissemination method according to the preferred embodiment of the invention Flow chart.Fig. 2 schematically shows the signal of books embedded advertisements dissemination method according to the preferred embodiment of the invention Figure.
As depicted in figs. 1 and 2, books embedded advertisements dissemination method according to the preferred embodiment of the invention includes：
First step S1：Every time when reader scans books picture, obtained and the books figure by pattern recognition technique The related extension information of piece；
Preferably, in first step S1, the extension information related to the books picture is further presented for reader.
It should be noted that the books picture not only includes the picture page, and including the word page.
Specifically, lifting reader's books reading experience is identified by figure, promotes reader persistently to scan books, i.e. reader The picture that corresponding icon is carried in books can be scanned, it is more behind the picture will to be presented for reader automatically by picture recognition system Extension information, including the diversification information carrier such as Online Bibliography Classification, word, video, picture, voice.
Second step S2：According to the extension information, the characteristic of the reader is collected；
The demand that the reader can be judged according to the extension information in second step likes classification.For example, utilize books Online Bibliography Classification, books can embody the interest of user in itself, and the books of especially specialty subdivision can embody the demand of user, Such as the user of purchase tourist handbook has the plan for going to tourism in the recent period.
Tag control can be carried out and data tracking is analyzed, after reader's scanned picture, using the Online Bibliography Classification of books to reading Person's demand and hobby are classified automatically, and simultaneity factor records reader's picture interested by lasting, passes through tag control technology Readers ' Characteristics data (behavioral data) are collected and analyzed.
Third step S3：According to the characteristic of the reader, to reader's advertisement information.
The present invention can realize it is accurate, lasting, directionally push marketing message to reader/bean vermicelli, utilize the classification of books Advantage, advertiser can select the books that are consistent with its target group to carry out advertisement putting, reader sweep picture obtain information it is same When can also browse, click on the advertising message of implantation, the advertising message of advertiser's also sustainable renewal implantation, while also by this hair The wechat hard core control matrix and database of bright establishment persistently carry out maintenance operation to target group, monitor and track advertisement putting Effect.
In addition, in the present invention it is possible to set up core customer's management matrix, that is, develop the shared deployment system of the full platform of full account System, primary account number is developed on multiple publishing house's wechat public number/APP (sub- account), primary account number manages sub- account shared data, And supervise the independent operation of sub- account.
<The specific example of pattern recognition technique>
In the present invention, figure identification it is main by the way of BOW (bag ofwords) model is built by document representation into Characteristic vector.Its basic thought is assumed that for a text, is ignored its word order and grammer, syntax, is only regarded as The set of some vocabulary, and each vocabulary in text is independent.It is exactly briefly to say that every document all regards a bag as Son (because the inside dress is all vocabulary, referred to as therefore bag of words, Bag ofwords are), then sees in this sack Dress is all any vocabulary, is classified.If pig in document, horse, ox, sheep, mountain valley, soil, vocabulary as tractor It is some more, and bank, mansion, automobile, vocabulary is less as park, tends to judge that it is a description rural document, Rather than description cities and towns.
Basic recognition logic is to do convolution by original image and Gaussian kernel to obtain each different scale in metric space Image, and obtain the image of different scale by adjusting the scale factor of Gaussian kernel.Then SIFT is extracted respectively to n width images To the whole SIFT feature of extraction after (scale invariant feature is changed, Scale-invariantfeaturetransform) feature Carry out k-means and cluster to obtain k cluster centre as vision word table, be finally specification to this using word list to each image Distance of each SIFT feature of width image each word in calculating it with word list, nearest+1, the width can be obtained The code book of image, it is finally calculated with training the distance of code book, the training image of corresponding minimum distance is thought and test image Match somebody with somebody.
One aspect of the present invention solves publishing house's Books Marketing and returns this pain spot, assists publishing house to receive, collect, run Reader/bean vermicelli data, publishing house's enhancing readers ' reading experience is helped, is not limited by the transmission of diversification means by time, space Information, form good interactive closed loop with reader；On the other hand solve advertiser and launch advertising objective crowd not enough accurately Pain spot, using the Online Bibliography Classification advantage of books, labeling is carried out to the reader to buy books, while reader sweeps picture and obtains information Push corresponding marketing message to reader, obtain effectively, accurately changing effect.
Furthermore, it is necessary to explanation, unless otherwise indicated, the otherwise term in specification " first ", " second ", " the 3rd " Be used only for distinguishing each component in specification, element, step etc. Deng description, without be intended to indicate that each component, element, Logical relation or ordinal relation between step etc..
It is understood that although the present invention is disclosed as above with preferred embodiment, but above-described embodiment and it is not used to Limit the present invention.For any those skilled in the art, without departing from the scope of the technical proposal of the invention, Many possible changes and modifications are all made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as With the equivalent embodiment of change.Therefore, every content without departing from technical solution of the present invention, the technical spirit pair according to the present invention Any simple modifications, equivalents, and modifications made for any of the above embodiments, still fall within the scope of technical solution of the present invention protection It is interior.

Claims (6)

  1. A kind of 1. books embedded advertisements dissemination method, it is characterised in that including：
    First step：Every time when reader scans books picture, obtained by pattern recognition technique related to the books picture Extension information；
    Second step：According to the extension information, the characteristic of the reader is collected；
    Third step：According to the characteristic of the reader, to reader's advertisement information.
  2. 2. books embedded advertisements dissemination method according to claim 1, it is characterised in that obtained by pattern recognition technique The extension information related to the books picture is taken to include：The original image of the books picture is done into convolution with Gaussian kernel to obtain The image of each different scale in metric space, and obtain the image of different scale by adjusting the scale factor of Gaussian kernel； Then the image of predetermined quantity is extracted respectively and k-means is carried out to all SIFT features of extraction after SIFT feature clusters to obtain K cluster centre is as vision word table, finally to each image using each SIFT of word list as specification to the width image Characteristic point calculates its distance with each word in word list, to obtain the code book of the width image, finally calculates the width image The distance of code book and training code book, using the extension related as the books picture of the information of the training image of corresponding minimum distance Information.
  3. 3. books embedded advertisements dissemination method according to claim 1 or 2, it is characterised in that in first step, enter one Walk and the extension information related to the books picture is presented for reader.
  4. 4. books embedded advertisements dissemination method according to claim 1 or 2, it is characterised in that extension information includes book One or more in mesh classification, word, video, picture and voice.
  5. 5. books embedded advertisements dissemination method according to claim 1 or 2, it is characterised in that second step according to The extension information judges the demand hobby classification of the reader.
  6. 6. books embedded advertisements dissemination method according to claim 1 or 2, it is characterised in that the books picture bag Include the picture page and the word page.
CN201711210989.9A 2017-11-28 2017-11-28 Books embedded advertisements dissemination method Pending CN107844997A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711210989.9A CN107844997A (en) 2017-11-28 2017-11-28 Books embedded advertisements dissemination method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711210989.9A CN107844997A (en) 2017-11-28 2017-11-28 Books embedded advertisements dissemination method

Publications (1)

Publication Number Publication Date
CN107844997A true CN107844997A (en) 2018-03-27

Family

ID=61680502

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711210989.9A Pending CN107844997A (en) 2017-11-28 2017-11-28 Books embedded advertisements dissemination method

Country Status (1)

Country Link
CN (1) CN107844997A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102047280A (en) * 2008-05-30 2011-05-04 全浚浩 A method and system of personalized electronic direct sales and service linked with the printing and the publishing
JP2012150552A (en) * 2011-01-17 2012-08-09 Horiuchi Denki Seisakusho:Kk Object recognition processing device and object recognition processing method
CN103793419A (en) * 2012-10-31 2014-05-14 深圳市世纪光速信息技术有限公司 Information push method and device
CN106250909A (en) * 2016-07-11 2016-12-21 南京邮电大学 A kind of based on the image classification method improving visual word bag model
CN107153850A (en) * 2016-03-04 2017-09-12 上海阿法迪智能标签系统技术有限公司 The acquisition methods and system of books relevant information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102047280A (en) * 2008-05-30 2011-05-04 全浚浩 A method and system of personalized electronic direct sales and service linked with the printing and the publishing
JP2012150552A (en) * 2011-01-17 2012-08-09 Horiuchi Denki Seisakusho:Kk Object recognition processing device and object recognition processing method
CN103793419A (en) * 2012-10-31 2014-05-14 深圳市世纪光速信息技术有限公司 Information push method and device
CN107153850A (en) * 2016-03-04 2017-09-12 上海阿法迪智能标签系统技术有限公司 The acquisition methods and system of books relevant information
CN106250909A (en) * 2016-07-11 2016-12-21 南京邮电大学 A kind of based on the image classification method improving visual word bag model

Similar Documents

Publication Publication Date Title
Pike Brands and branding geographies
US9058619B2 (en) System and method for measurement, planning, monitoring, and execution of out-of-home media
Hiam Marketing for dummies
CN108694602A (en) Promotional literature generation method and device
CN105975581A (en) Media information display method, client and server
CN106651444A (en) Method and system for performing advertisement release by tagging users
CN104767830A (en) Information issuing management method and device
CN106688215A (en) Automated click type selection for content performance optimization
CN106164963A (en) For carrying out the system and method for advertisement based on analytic process
KR102213107B1 (en) O2o marketing platform system based on behavior pattern of visitor of offline store and building method thereof
CN103907137A (en) Virtual advertising platform
CN109886735A (en) A kind of method and device of advertisement pushing
Leung et al. Why passengers’ geo-demographic characteristics matter to airport marketing
CN110969480A (en) Multimedia backpack advertising information playing control method and device
Palmer et al. A deep learning approach to identify unhealthy advertisements in street view images
CN103337026A (en) Advertising systems and methods using embedded map
Turow The development of the modern advertising industry
Babin et al. Marketing research
Zahrádka et al. What is the price of outdoor advertising: A case study of the Czech republic?
Madleňák et al. Digital advertising system in urban transport system of Žilina town
KR20200097571A (en) Online to Offline marketing platform for data based in customer&#39;s pattern in a offline store
Holtzhausen Content analysis of roles portrayed by women in advertisements in selected South African media
CN107844997A (en) Books embedded advertisements dissemination method
Kishor Consumer behaviour towards consumer durable goods
TWM635233U (en) Advertising management 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

Application publication date: 20180327

RJ01 Rejection of invention patent application after publication