[go: up one dir, main page]

CN103699594A - Information push method and information push system - Google Patents

Information push method and information push system Download PDF

Info

Publication number
CN103699594A
CN103699594A CN201310675039.9A CN201310675039A CN103699594A CN 103699594 A CN103699594 A CN 103699594A CN 201310675039 A CN201310675039 A CN 201310675039A CN 103699594 A CN103699594 A CN 103699594A
Authority
CN
China
Prior art keywords
information
face image
user
behavior
image
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.)
Granted
Application number
CN201310675039.9A
Other languages
Chinese (zh)
Other versions
CN103699594B (en
Inventor
胡金星
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.)
Shenzhen Hongzhituoxin Venture Capital Enterprise LP
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
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 Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to CN201310675039.9A priority Critical patent/CN103699594B/en
Publication of CN103699594A publication Critical patent/CN103699594A/en
Application granted granted Critical
Publication of CN103699594B publication Critical patent/CN103699594B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour

Landscapes

  • Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本发明适用于大数据处理技术领域，提供了一种信息推送方法及系统，所述系统包括：采集人脸图像；获取所述人脸图像的特征信息；将所述人脸图像的特征信息与预先建立的人脸图像数据库中的人脸图像特征模板进行匹配，当匹配的相似度大于预设阈值时，获取与所述人脸图像相关的信息；根据所述人脸图像相关的信息，挖掘出所述人脸图像对应用户的行为信息；向所述用户所在客户端推送与所述行为信息相关的信息。本发明可以根据人脸图像挖掘出对应用户的行为习惯，根据所述行为习惯向用户推送相应的信息，提高信息推送的准确率和用户满意度。

Figure 201310675039

The present invention is applicable to the technical field of big data processing, and provides an information push method and system. The system includes: collecting face images; acquiring feature information of the face images; combining feature information of the face images with The face image feature templates in the pre-established face image database are matched, and when the matching similarity is greater than a preset threshold, information related to the face image is obtained; according to the information related to the face image, mining Obtain the behavior information of the user corresponding to the face image; push information related to the behavior information to the client where the user is located. The present invention can excavate the behavior habit of the corresponding user according to the face image, push corresponding information to the user according to the behavior habit, and improve the accuracy rate of information push and user satisfaction.

Figure 201310675039

Description

A kind of information-pushing method and system
Technical field
The invention belongs to large technical field of data processing, relate in particular to a kind of information-pushing method and system.
Background technology
The existing information advancing technique mainly static profile data based on user input pushes, and such as according to attributes such as user location, age, sex, school, hobbies, will have the people of identical or close attribute or information pushing to user.This information pushing mode too relies on the personal information that user fills in, and the personal information that user fills in is often too simple, true even not, is difficult to accurately reflect user's actual conditions, causes the accuracy of information pushing not high, affects user and experiences.
Summary of the invention
The object of the embodiment of the present invention is to provide a kind of information-pushing method and system, to generate pushed information according to user's behavioural habits and preference, improves the accuracy of information pushing.
The embodiment of the present invention is achieved in that a kind of information-pushing method, and described method comprises:
Gather facial image;
Obtain the characteristic information of described facial image;
The characteristic information of described facial image is mated with the facial image feature templates in the face database of setting up in advance, when the similarity of coupling is greater than predetermined threshold value, obtain the information relevant to described facial image;
The information relevant according to described facial image, excavates the behavioural information of described facial image respective user;
To the described user place client push information relevant to described behavioural information.
Another object of the embodiment of the present invention is to provide a kind of information transmission system, and described system comprises:
Image acquisition units, for gathering facial image;
Characteristic acquisition unit, for obtaining the characteristic information of described facial image;
Processing unit, for the characteristic information of described facial image is mated with the facial image feature templates of the face database of setting up in advance, when the similarity of coupling is greater than predetermined threshold value, obtains the information relevant to described facial image;
Behavioural information is excavated unit, for the information relevant according to described facial image, excavates the behavioural information of described facial image respective user;
Information pushing unit, for to the described user place client push information relevant to described behavioural information.
The beneficial effect that the embodiment of the present invention compared with prior art exists is: the embodiment of the present invention is by mating the facial image of collection with the facial image in the face database of setting up in advance, when the similarity of coupling is greater than predetermined threshold value, obtain the information relevant to described facial image, and the information relevant according to described facial image, excavate the behavioural information of described facial image respective user, and then to the described user place client push information relevant to described behavioural information.The embodiment of the present invention can be excavated the behavioural habits of respective user according to facial image, according to described behavioural habits, to user, push corresponding information, improves accuracy rate and the user satisfaction of information pushing, has stronger ease for use and practicality.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the realization flow figure of the information-pushing method that provides of first embodiment of the invention;
Fig. 2 is the composition structural drawing of the information transmission system that provides of second embodiment of the invention.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
For technical solutions according to the invention are described, below by specific embodiment, describe.
embodiment mono-:
Fig. 1 shows the realization flow of the information-pushing method that the first embodiment provides, and details are as follows for the method process:
In step S101, gather facial image.
In the present embodiment, can pass through camera collection image sequence, and detect in the image sequence gathering whether have people's face by people's face detection algorithm, while there is people's face in the image sequence gathering, extract described facial image.The present embodiment can also be further carry out a certain proportion of cutting to the facial image extracting, and makes image after cutting comprise some essential characteristic points (as shown in Figure 2) of people's face, such as: eyes, nose, mouth etc.Wherein, described people's face detection algorithm is including, but not limited to the Adaboost algorithm of class rectangular characteristic.
Specifically can comprise: the video data of the camera that A1, collection public place set up.A2, the facial image in the video data gathering is carried out to cross-matched.A3, the corresponding stored facial image that the match is successful and place and/or the time of obtaining described facial image.
The public place of the present embodiment comprises the places such as parking lot, megastore, road both sides, park.In the present embodiment, gather a large amount of citizen's of public place accumulation video data, then the facial image that comprises of the video data in each place of cross-matched, corresponding data finally stored.For example, after the facial image of first that obtains parking lot, the facial image of first is mated respectively with a plurality of facial images that the places such as megastore, road both sides, park obtain, to judge whether first appears at the places such as megastore, road both sides, park, if the match is successful, suppose that first appears at park, store the information such as place, time that first appears at parking lot and park simultaneously, otherwise, only store the information such as place, time that first appears at parking lot.Certainly, the place here can also be specific to certain camera in parking lot, park.
Further, the present embodiment, after gathering facial image, also comprises:
Described facial image is carried out to pre-service, and described pre-service comprises binarization of gray value, corrosion and the expansion of image.
In the present embodiment, described pretreated process is including, but not limited to binarization of gray value, corrosion and the expansion of image.The RGB image collecting is converted to gray level image, and binaryzation.
Corrosion treatment: use for example 3 * 3 structural element of structural element B(), scan each pixel of the image after described binaryzation, with the binary image of structural element and its covering, do AND-operation, if be all 1, this pixel of result images is 1, otherwise be 0, make binary image reduce a circle.
Expansion process: use structural element B, scan each pixel of the image after described corrosion, with the image after the corrosion of structural element and its covering, do AND-operation, if be all 0, this pixel of result images is 0, otherwise be 1, make image augmentation one circle after corrosion, obtain corresponding profile diagram.
In step S102, obtain the characteristic information of described facial image.
In the present embodiment, described characteristic information comprises histogram feature, color characteristic, template characteristic, architectural feature and Haar feature etc.
In step S103, the characteristic information of described facial image is mated with the facial image feature templates in the face database of setting up in advance, when the similarity of coupling is greater than predetermined threshold value, obtain the information relevant to described facial image.
In the present embodiment, described face database is the large data knowledge storehouse on basis for take the database of a plurality of government departments, and described face database comprises the video data (can adopt Adaboost algorithm to extract facial image from described video data) of each camera collection in facial image feature templates, resident's personal information and city etc.Wherein, described resident's personal information comprises the information such as name, ID (identity number) card No., residence, age, sex, school, hobby and individual human head picture.
In the present embodiment, for integral data base resource, the information association by user at disparate databases, can identify by unique identifier the same user of disparate databases; Or (be specifically as follows each item number in essential information according to a weight factor is set according to user's essential information, for example the weight factor of telephone number is 0.7) calculate the similarity between user, when two users' similarity is more than or equal to default similarity threshold, think that the two users in disparate databases are same user.For example default similarity threshold is 90%, user A and user B, there is identical telephone number, its similarity is 70%, user A has identical telephone number and the pet name with user B, and its similarity is 90%, determines that user A and user B are same user, user A is associated with the behavioural information of user B, and specific embodiment mode is not as limit.
The present embodiment obtains the information relevant to described facial image from the large data knowledge storehouse of resource consolidation, and for example described facial image respective user appears at the probability of certain camera, described facial image respective user user appears at the probability between certain several camera continuously.
In step S104, the information relevant according to described facial image, excavates the behavioural information of described facial image respective user.
Specifically comprise:
The information relevant according to described facial image, adopts statistical learning method to obtain model;
Model based on obtained is excavated the behavioural information of described facial image respective user.
Concrete is, the information relevant according to described facial image, (initial model of for example setting up is ax2+by+c to adopt statistical learning method first to set up initial model, a, b, c represent the parameter of model, x, y represent factor of influence), calculate the joint probability of described relevant information, maximize the parameter (obtaining the value of a, b, c) that described joint probability obtains described initial model, and then obtain final mask.Wherein, described statistical learning method includes but not limited to the statistical learning method of probability or non-probability.
It should be noted that, why the present embodiment is used statistical learning method to set up model, because statistical learning method does not rely on feature extraction technology (the existing feature extraction technology that can rely on concrete syntax based on semantic rules method) and the concrete network environment of concrete syntax, do not rely on specific user behavior yet, therefore the model that adopts statistical learning method to set up, can expand in various network environment and different user behavior prediction easily.
In step S105, to the described user place client push information relevant to described behavioural information.
For example, when excavating user behavior information when often strolling 4S shop, can purchase to its propelling movement the information relevant to vehicle such as car service or vehicle maintenance service; When excavating user behavior information for frequent discrepancy airport, can push to it information such as budget fare.
As a preferable examples of the present invention, to the described user place client push information relevant to described behavioural information, specifically comprise described in the present embodiment:
Model based on obtained, generates the list of user's probable behavior;
User's probable behavior in the list of described user's probable behavior is marked;
To the relevant information of the described user place client push front N item user probable behavior the highest to scoring, described N is more than or equal to 1.
In the present embodiment, when calculating scoring, can calculate according to default score calculation formula, the C=that for example marks forwards probability * 0.5+ and replys probability * 0.7-and do not pay close attention to probability * 1.3, and described forwarding probability, comment probability, not pay close attention to probability be the probability that described model prediction user reacts to described pushed information.Wherein, described user's probable behavior refers to the information that may trigger user's operation, and the described information that may trigger user's operation comprises the information that user's possibility is interested or want most to see.
By the embodiment of the present invention, make the information of propelling movement more targeted, accuracy rate is higher, more can meet consumers' demand, and improves user satisfaction.
embodiment bis-:
Fig. 2 shows the composition structure of the information transmission system that second embodiment of the invention provides, and for convenience of explanation, only shows the part relevant to the embodiment of the present invention.
This information transmission system comprises image acquisition units 21, characteristic acquisition unit 22, processing unit 23, behavioural information excavation unit 24 and information pushing unit 25.Wherein, each unit concrete function is as follows:
Image acquisition units 21, for gathering facial image;
Characteristic acquisition unit 22, for obtaining the characteristic information of described facial image;
Processing unit 23, for the characteristic information of described facial image is mated with the facial image feature templates of the face database of setting up in advance, when the similarity of coupling is greater than predetermined threshold value, obtains the information relevant to described facial image;
Behavioural information is excavated unit 24, for the information relevant according to described facial image, excavates the behavioural information of described facial image respective user;
Information pushing unit 25, for to the described user place client push information relevant to described behavioural information.
Further, described behavioural information excavation unit 24 comprises:
Model obtains module 241, for the information relevant according to described facial image, adopts statistical learning method to obtain model;
Behavioural information is excavated module 242, excavates the behavioural information of described facial image respective user for the model based on obtained.
Further, described information pushing unit 25 comprises:
Behavior list generation module 251, for the model based on obtained, generates the list of user's probable behavior;
Grading module 252, for marking to user's probable behavior of described user's probable behavior list;
Information pushing module 253, for to the described user place client push information relevant with the highest front N item user probable behavior of scoring, described N is more than or equal to 1.
Wherein, described face database is the large data knowledge storehouse on basis for take the database of a plurality of government departments, and described face database includes but not limited to video data, facial image feature templates and resident's personal information etc. of each camera collection in city.
Further, described system also comprises:
Pretreatment unit 26, for after gathering facial image, carries out pre-service to described facial image, and described pre-service comprises binarization of gray value, corrosion and the expansion of image.
Those skilled in the art can be well understood to, for convenience and simplicity of description, only the division with above-mentioned each functional unit is illustrated, in practical application, can above-mentioned functions be distributed and by different functional units, completed as required, the inner structure that is described system is divided into different functional units, to complete all or part of function described above.Each functional unit in embodiment can be integrated in a processing unit, also can be that the independent physics of unit exists, also can be integrated in a unit two or more unit, above-mentioned integrated unit both can adopt the form of hardware to realize, and also can adopt the form of SFU software functional unit to realize.In addition, the concrete title of each functional unit also, just for the ease of mutual differentiation, is not limited to the application's protection domain.
In sum, the embodiment of the present invention is by mating the facial image of collection with the facial image in the face database of setting up in advance, when the similarity of coupling is greater than predetermined threshold value, obtain the information relevant to described facial image, and the information relevant according to described facial image, excavate the behavioural information of described facial image respective user, and then to the described user place client push information relevant to described behavioural information.The embodiment of the present invention can be excavated according to facial image the behavioural habits of respective user, according to described behavioural habits, to it, push corresponding information, make the information of propelling movement more targeted, accuracy rate is higher, more can meet consumers' demand, improve user satisfaction, there is stronger ease for use and practicality.
Those of ordinary skills it is also understood that, the all or part of step realizing in above-described embodiment method is to come the hardware that instruction is relevant to complete by program, described program can be in being stored in a computer read/write memory medium, described storage medium, comprises ROM/RAM, disk, CD etc.
Above content is in conjunction with concrete preferred implementation further description made for the present invention, can not assert that specific embodiment of the invention is confined to these explanations.For general technical staff of the technical field of the invention; make without departing from the inventive concept of the premise some alternative or obvious modification that are equal to; and performance or purposes identical, all should be considered as belonging to the present invention by the definite scope of patent protection of submitted to claims.

Claims (10)

1.一种信息推送方法，其特征在于，所述方法包括：1. A method for pushing information, characterized in that the method comprises: 采集人脸图像；Collect face images; 获取所述人脸图像的特征信息；Obtain feature information of the face image; 将所述人脸图像的特征信息与预先建立的人脸图像数据库中的人脸图像特征模板进行匹配，当匹配的相似度大于预设阈值时，获取与所述人脸图像相关的信息；Matching the feature information of the face image with the face image feature template in the pre-established face image database, when the matching similarity is greater than a preset threshold, obtaining information related to the face image; 根据所述人脸图像相关的信息，挖掘出所述人脸图像对应用户的行为信息；Mining out the behavior information of the user corresponding to the face image according to the information related to the face image; 向所述用户所在客户端推送与所述行为信息相关的信息。Push information related to the behavior information to the client where the user is located. 2.如权利要求1所述的方法，其特征在于，根据所述人脸图像相关的信息，挖掘出所述人脸图像对应用户的行为信息具体包括：2. The method according to claim 1, wherein, according to the information related to the face image, digging out the behavior information of the user corresponding to the face image specifically includes: 根据所述人脸图像相关的信息，采用统计学习方法获得模型；According to the information related to the face image, a statistical learning method is used to obtain a model; 基于所获得的模型挖掘出所述人脸图像对应用户的行为信息。Based on the obtained model, the user's behavior information corresponding to the face image is mined. 3.如权利要求2所述的方法，其特征在于，向所述用户所在客户端推送与所述行为信息相关的信息具体包括：3. The method according to claim 2, wherein pushing the information related to the behavior information to the client where the user is located specifically comprises: 基于所获得的模型，生成用户可能行为列表；Based on the obtained model, generate a list of possible user behaviors; 对所述用户可能行为列表中的用户可能行为进行评分；scoring the user's possible behavior in the user's possible behavior list; 向所述用户所在客户端推送与评分最高的前N项用户可能行为相关的信息，所述N大于或等于1。Push the information related to the top N possible behaviors of users with the highest scores to the client where the user is located, where N is greater than or equal to 1. 4.如权利要求1所述的方法，其特征在于，所述人脸图像数据库为以多个政府部门的数据库为基础的大数据知识库，包括采集的视频数据、人脸图像特征模板及居民个人信息。4. The method according to claim 1, wherein the face image database is a large data knowledge base based on the databases of multiple government departments, including video data collected, face image feature templates and residents personal information. 5.如权利要求1至4任一项所述的方法，其特征在于，在采集人脸图像之后，还包括：5. The method according to any one of claims 1 to 4, further comprising: 对所述人脸图像进行预处理，所述预处理包括图像的灰度二值化、腐蚀以及膨胀。The face image is preprocessed, and the preprocessing includes image grayscale binarization, erosion and expansion. 6.一种信息推送系统，其特征在于，所述系统包括：6. An information push system, characterized in that the system comprises: 图像采集单元，用于采集人脸图像；An image acquisition unit, configured to acquire face images; 特征信息获取单元，用于获取所述人脸图像的特征信息；A feature information acquisition unit, configured to acquire feature information of the face image; 处理单元，用于将所述人脸图像的特征信息与预先建立的人脸图像数据库中的人脸图像特征模板进行匹配，当匹配的相似度大于预设阈值时，获取与所述人脸图像相关的信息；A processing unit, configured to match the feature information of the face image with the feature template of the face image in the pre-established face image database, and when the matching similarity is greater than a preset threshold, acquire the Related information; 行为信息挖掘单元，用于根据所述人脸图像相关的信息，挖掘出所述人脸图像对应用户的行为信息；A behavior information mining unit, configured to mine behavior information of the user corresponding to the face image according to information related to the face image; 信息推送单元，用于向所述用户所在客户端推送与所述行为信息相关的信息。An information push unit, configured to push information related to the behavior information to the client where the user is located. 7.如权利要求6所述的系统，其特征在于，所述行为信息挖掘单元包括：7. The system according to claim 6, wherein the behavior information mining unit comprises: 模型获得模块，用于根据所述人脸图像相关的信息，采用统计学习方法获得模型；A model obtaining module, used to obtain a model by using a statistical learning method according to information related to the face image; 行为信息挖掘模块，用于基于所获得的模型挖掘出所述人脸图像对应用户的行为信息。The behavior information mining module is used to mine the behavior information of the user corresponding to the face image based on the obtained model. 8.如权利要求7所述的系统，其特征在于，所述信息推送单元包括：8. The system according to claim 7, wherein the information pushing unit comprises: 行为列表生成模块，用于基于所获得的模型，生成用户可能行为列表；A behavior list generating module, configured to generate a list of possible user behaviors based on the obtained model; 评分模块，用于对所述用户可能行为列表中的用户可能行为进行评分；A scoring module, configured to score the possible user behaviors in the user possible behavior list; 信息推送模块，用于向所述用户所在客户端推送与评分最高的前N项用户可能行为相关的信息，所述N大于或等于1。An information push module, configured to push information related to the top N possible behaviors of users with the highest scores to the client where the user is located, where N is greater than or equal to 1. 9.如权利要求6所述的系统，其特征在于，所述人脸图像数据库为以多个政府部门的数据库为基础的大数据知识库，包括采集的视频数据、人脸图像特征模板及居民个人信息。9. system as claimed in claim 6, is characterized in that, described facial image database is the big data knowledge base based on the database of a plurality of government departments, comprises the video data of collection, facial image feature template and resident personal information. 10.如权利要求6至9任一项所述的系统，其特征在于，所述系统还包括：10. The system according to any one of claims 6 to 9, wherein the system further comprises: 预处理单元，用于在采集人脸图像之后，对所述人脸图像进行预处理，所述预处理包括图像的灰度二值化、腐蚀以及膨胀。A preprocessing unit is configured to perform preprocessing on the facial image after the facial image is collected, and the preprocessing includes grayscale binarization, erosion and dilation of the image.
CN201310675039.9A 2013-12-11 2013-12-11 A kind of information-pushing method and system Active CN103699594B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310675039.9A CN103699594B (en) 2013-12-11 2013-12-11 A kind of information-pushing method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310675039.9A CN103699594B (en) 2013-12-11 2013-12-11 A kind of information-pushing method and system

Publications (2)

Publication Number Publication Date
CN103699594A true CN103699594A (en) 2014-04-02
CN103699594B CN103699594B (en) 2017-09-26

Family

ID=50361122

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310675039.9A Active CN103699594B (en) 2013-12-11 2013-12-11 A kind of information-pushing method and system

Country Status (1)

Country Link
CN (1) CN103699594B (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104133845A (en) * 2014-06-30 2014-11-05 百度在线网络技术（北京）有限公司 Multimedia information display method and multimedia information display processing equipment
CN104317790A (en) * 2014-07-22 2015-01-28 翔傲信息科技(上海)有限公司 A method and system for controlling user behavior based on big data
CN104575339A (en) * 2014-07-21 2015-04-29 北京智膜科技有限公司 Media information pushing method based on face detection interface
CN104766080A (en) * 2015-05-06 2015-07-08 苏州搜客信息技术有限公司 Image multi-class feature recognizing and pushing method based on electronic commerce
CN105302812A (en) * 2014-06-16 2016-02-03 腾讯科技（深圳）有限公司 Image information processing method and apparatus
CN105320699A (en) * 2014-08-04 2016-02-10 中国科学院深圳先进技术研究院 Old age preferential treatment certificate service pushing method and system
CN105320698A (en) * 2014-08-04 2016-02-10 中国科学院深圳先进技术研究院 Method and system for pushing advanced age allowance service
CN105405048A (en) * 2014-09-09 2016-03-16 阿里巴巴集团控股有限公司 Method and device for recognizing periodic behavior
CN105678622A (en) * 2016-01-07 2016-06-15 平安科技（深圳）有限公司 Analysis method and system for vehicle insurance claim-settlement photos
CN106156144A (en) * 2015-04-13 2016-11-23 腾讯科技（深圳）有限公司 Information-pushing method and device
CN108197971A (en) * 2017-12-08 2018-06-22 北京天正聚合科技有限公司 Information collecting method, information processing method, apparatus and system
CN109299709A (en) * 2018-12-04 2019-02-01 中山大学 Data recommendation method, device, server and client based on face recognition
CN109344726A (en) * 2018-09-05 2019-02-15 顺丰科技有限公司 A kind of advertisement placement method and device
CN109902545A (en) * 2017-12-11 2019-06-18 日立楼宇技术（广州）有限公司 User characteristic analysis method and system
WO2021004137A1 (en) * 2019-07-05 2021-01-14 深圳壹账通智能科技有限公司 Information pushing method and apparatus based on face recognition and computer device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080059994A1 (en) * 2006-06-02 2008-03-06 Thornton Jay E Method for Measuring and Selecting Advertisements Based Preferences
US20080249987A1 (en) * 2007-04-06 2008-10-09 Gemini Mobile Technologies, Inc. System And Method For Content Selection Based On User Profile Data
CN102208088A (en) * 2010-03-31 2011-10-05 索尼公司 Server apparatus, client apparatus, content recommendation method, and program
CN103294800A (en) * 2013-05-27 2013-09-11 华为技术有限公司 Method and device for pushing information

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080059994A1 (en) * 2006-06-02 2008-03-06 Thornton Jay E Method for Measuring and Selecting Advertisements Based Preferences
US20080249987A1 (en) * 2007-04-06 2008-10-09 Gemini Mobile Technologies, Inc. System And Method For Content Selection Based On User Profile Data
CN102208088A (en) * 2010-03-31 2011-10-05 索尼公司 Server apparatus, client apparatus, content recommendation method, and program
CN103294800A (en) * 2013-05-27 2013-09-11 华为技术有限公司 Method and device for pushing information

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105302812A (en) * 2014-06-16 2016-02-03 腾讯科技（深圳）有限公司 Image information processing method and apparatus
CN104133845A (en) * 2014-06-30 2014-11-05 百度在线网络技术（北京）有限公司 Multimedia information display method and multimedia information display processing equipment
CN104575339A (en) * 2014-07-21 2015-04-29 北京智膜科技有限公司 Media information pushing method based on face detection interface
CN104317790A (en) * 2014-07-22 2015-01-28 翔傲信息科技(上海)有限公司 A method and system for controlling user behavior based on big data
CN105320699A (en) * 2014-08-04 2016-02-10 中国科学院深圳先进技术研究院 Old age preferential treatment certificate service pushing method and system
CN105320698A (en) * 2014-08-04 2016-02-10 中国科学院深圳先进技术研究院 Method and system for pushing advanced age allowance service
CN105405048B (en) * 2014-09-09 2020-02-11 阿里巴巴集团控股有限公司 Method and device for identifying periodic behaviors
CN105405048A (en) * 2014-09-09 2016-03-16 阿里巴巴集团控股有限公司 Method and device for recognizing periodic behavior
CN106156144A (en) * 2015-04-13 2016-11-23 腾讯科技（深圳）有限公司 Information-pushing method and device
CN104766080A (en) * 2015-05-06 2015-07-08 苏州搜客信息技术有限公司 Image multi-class feature recognizing and pushing method based on electronic commerce
CN105678622A (en) * 2016-01-07 2016-06-15 平安科技（深圳）有限公司 Analysis method and system for vehicle insurance claim-settlement photos
CN108197971A (en) * 2017-12-08 2018-06-22 北京天正聚合科技有限公司 Information collecting method, information processing method, apparatus and system
CN109902545A (en) * 2017-12-11 2019-06-18 日立楼宇技术（广州）有限公司 User characteristic analysis method and system
CN109344726A (en) * 2018-09-05 2019-02-15 顺丰科技有限公司 A kind of advertisement placement method and device
CN109299709A (en) * 2018-12-04 2019-02-01 中山大学 Data recommendation method, device, server and client based on face recognition
WO2021004137A1 (en) * 2019-07-05 2021-01-14 深圳壹账通智能科技有限公司 Information pushing method and apparatus based on face recognition and computer device

Also Published As

Publication number Publication date
CN103699594B (en) 2017-09-26

Similar Documents

Publication Publication Date Title
CN103699594A (en) Information push method and information push system
CN103744858A (en) Method and system for pushing information
US20210026910A1 (en) Expert Detection in Social Networks
US9762528B2 (en) Generating a conversation in a social network based on mixed media object context
CN112330455B (en) Method, device, equipment and storage medium for pushing information
US11100368B2 (en) Accelerated training of an image classifier
CN104376010B (en) User recommendation method and device
CN102722709B (en) Method and device for identifying garbage pictures
CN108388882A (en) Based on the gesture identification method that the overall situation-part is multi-modal RGB-D
CN103793697A (en) Identity labeling method of face images and face identity recognition method of face images
CN108959323B (en) Video classification method and device
CN113244627B (en) Method and device for identifying plug-in, electronic equipment and storage medium
EP2874102A2 (en) Generating models for identifying thumbnail images
US20240086457A1 (en) Attention aware multi-modal model for content understanding
CN110472057B (en) Topic label generation method and device
US20190163962A1 (en) Establishing personal identity based on multiple sub-optimal images
KR20200062761A (en) Metadata crowd sourcing system and method
CN116977692A (en) Data processing method, device and computer readable storage medium
CN112241704A (en) Method and device for judging portrait infringement, electronic equipment and storage medium
CN107368499A (en) A kind of client's tag modeling and recommendation method and device
US20170229118A1 (en) Linguistic model database for linguistic recognition, linguistic recognition device and linguistic recognition method, and linguistic recognition system
CN110717094A (en) Information recommendation method and device, computer equipment and storage medium
CN111198926B (en) Business handling management method and device, electronic equipment and storage medium
US11830270B1 (en) Machine learning systems for auto-splitting and classifying documents
CN112766997A (en) Picture delivery method, device, equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20230227

Address after: 518000 A-301, office building, Shenzhen Institute of advanced technology, No. 1068, Xue Yuan Avenue, Shenzhen University Town, Shenzhen, Guangdong, Nanshan District, China

Patentee after: Shenzhen shen-tech advanced Cci Capital Ltd.

Address before: 1068 No. 518055 Guangdong city in Shenzhen Province, Nanshan District City Xili University School Avenue

Patentee before: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230418

Address after: 518000 b402, blocks a and B, Nanshan medical device Industrial Park, No. 1019, Nanhai Avenue, Yanshan community, merchants street, Nanshan District, Shenzhen, Guangdong

Patentee after: Shenzhen hongzhituoxin venture capital enterprise (L.P.)

Address before: 518000 A-301, office building, Shenzhen Institute of advanced technology, No. 1068, Xue Yuan Avenue, Shenzhen University Town, Shenzhen, Guangdong, Nanshan District, China

Patentee before: Shenzhen shen-tech advanced Cci Capital Ltd.

TR01 Transfer of patent right