CN107291841A - A kind of method and system based on position and the social target of user's portrait intelligent Matching - Google Patents

A kind of method and system based on position and the social target of user's portrait intelligent Matching Download PDF

Info

Publication number
CN107291841A
CN107291841A CN201710401245.9A CN201710401245A CN107291841A CN 107291841 A CN107291841 A CN 107291841A CN 201710401245 A CN201710401245 A CN 201710401245A CN 107291841 A CN107291841 A CN 107291841A
Authority
CN
China
Prior art keywords
user
portrait
matching
index
characteristic
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.)
Withdrawn
Application number
CN201710401245.9A
Other languages
Chinese (zh)
Inventor
邓志雄
黄铿龙
梁永峰
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.)
Guangzhou Henghao Data Technology Co Ltd
Original Assignee
Guangzhou Henghao Data 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 Guangzhou Henghao Data Technology Co Ltd filed Critical Guangzhou Henghao Data Technology Co Ltd
Priority to CN201710401245.9A priority Critical patent/CN107291841A/en
Publication of CN107291841A publication Critical patent/CN107291841A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9537Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28Databases characterised by their database models, e.g. relational or object models
    • G06F16/284Relational databases
    • G06F16/285Clustering or classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01Social networking

Abstract

" a kind of method and system that the social target of intelligent Matching is carried out based on position and user's portrait ", using the system, terminal user can pass through related mobile phone application software(APP)Log in and search in certain position regional extent and oneself characteristic matching degree(Match index)It is high or complementary(Complementation index)High social target;Meanwhile, on the premise of user allows and ensures user information safety, system can be actively to user or social network sites recommended user's characteristic matching degree height or complementary high social target.The system main composition has:Autonomous service interaction interface, open interface, user's portrait intelligent Matching module, Generalization bounds repository, classification scoring define information bank, characteristic key analysis module, user's representation data platform etc..

Description

A kind of method and system based on position and the social target of user's portrait intelligent Matching
Technical field
Software development, mobile network, big data, proposed algorithm, data mining, user's portrait, behavioural analysis, tag library.
Background technology
User draws a portrait(User Profile)Also known as user role (Persona), is the virtual representations of real user, according to The investigation of the difference of the target of user, behavior and viewpoint is gone to understand user, and they are divided into different types, then per species Characteristic feature is extracted in type, the description such as name, photo, some demography key element, scenes is assigned, is formed a people Thing prototype, i.e. user role.
As a kind of effective tool for delineating targeted customer, contact user's demand and design direction, user draws a portrait in reality Often the attribute of user, behavior, custom are coupled with expecting with the most plain and closeness to life language during operation Get up, and the user model of the labeling taken out according to these information, i.e., labeled " " to user.It is fast by internet Fast influence on development, obtained user is analyzed by user's internet behavior and is drawn a portrait in precision marketing, user's statistics, data mining, production Product design, business applys in terms of managing, for example, apply on currently a popular sequencing advertisement is merchandised, and can allow enterprise Marketing is more accurate, effectively improve business conversion ratio.Generally, user behavior analysis to user behavior mainly by monitoring what is obtained Data are analyzed, can allow enterprise in further detail, the behavioural habits of user are well understood so that find out website, promote canal The problem of enterprise marketing environment such as road is present.
Substantial amounts of interaction data have recorded detailed user behavior characteristic information in common carrier network, particularly move , can be neatly from user's base attribute with reference to O domains and B numeric field datas in communication network(Subscriber Number, real-name authentication information Deng), business using, enliven the various dimensions such as position, terminal are used, focus is searched for, user perceives and build user full view and draw a portrait, have Effect is set up various dimensions user tag storehouse and periodically upgraded in time.
At present, global each common carrier or Internet firm all pay much attention to the construction in each dimension user tag storehouse, and Constantly utilize the efficiency and matter of the skill upgrading data acquisitions such as big data and data mining, storage, computing, analysis modeling and decision-making Amount, but precision marketing aspect is principally dedicated in application personal user's application in user tag storehouse at present, play in other respects It is less.To lift the data value in Mobile Network Operator user tag storehouse and answering scope, the present invention proposes a kind of based on position User's portrait carries out the method and system of the social target of intelligent Matching, can provide a kind of based on the band of position in real time for terminal user And the intelligent recommendation service of social targeted customer's characteristic matching, or the real-time user characteristics matching letter of friend-making sites offer Breath.
Because the user tag storehouse information that the system is used is by a large number of users behavioral data statistics fortune in real network Calculate and obtain, therefore possess the feature letter that user oneself uploads in certain objectivity, contrast friend-making sites to user feature analysis Breath is more for confidence level;In addition, the system conceals user's specific address, name, phone number during matching user characteristics The sensitive informations such as code, possess privacy of user protection security setting.
The content of the invention
The present invention proposes a kind of method and system that the social target of intelligent Matching is carried out based on position and user's portrait.Utilize The system, terminal user can pass through related mobile phone application software(APP)Log in and search in certain position regional extent with from Own characteristic matching degree(Match index)It is high or complementary(Complementation index)High social target;Meanwhile, allow and ensure in user On the premise of user information safety, system can be actively to user or social networking application(Website may some limitations)Recommend to use The social target that family label characteristics matching degree is high or complementarity is high.
System main composition has:Autonomous service interaction interface, open interface, user's portrait intelligent Matching module, recommendation plan Slightly repository, classification scoring define information bank, characteristic key analysis module, user's representation data platform.System main modular Fig. 1 referring to Figure of description is constituted, concrete operating principle is described as follows:
1. Self-Service interactive interface(Mobile phone terminal service software APP or Web page etc.)
(1)Service account is registered:To be ready that the user of turn up service provides registration login page, intelligent is provided to receive system Service with social target.
(2)Scope circle is selected:User can enclose the park feature selected certain geographic range and select friend-making target on map (Such as:Resident, visiting, all etc.).
(3)Feature selecting:User is provided the various features of portrait(Or label)Screening and filtering is carried out to user, also can be direct System help selection is given, is found and oneself characteristic matching degree height or the social targets of complementary high TopN.User can be big to 7 special Levy(Culture, economy, face value, health, reference, personality, hobby)Selected and by giving characteristic key analysis module to correlation The business of networking content and traffic volume measurement of feature calculate " intensity index " of the respective feature of two users.The expression of 7 big features Method and the following form of appraisal procedure:
Feature name Method for expressing Appraisal procedure
Culture It is high, medium higher, medium, general, It is low, or scale scoring etc. By distinguish occupation, career field, reading content, attentinal contents, APP carries out comprehensive descision using data such as durations
It is economical It is excellent, good, in, general, or scale scoring Deng Pass through communication cost set meal, brand concern, residence, consumption field The data such as institute, trip feature, terminal models carry out comprehensive descision
Face value It is excellent, good, in, general, or scale scoring Deng By the way that user's upload pictures are carried out with image recognition, and upload The data such as height and weight carry out comprehensive descision
Health It is excellent, good, in, general, or scale scoring Deng By accessing user's walking data of third-party application, ride APP Data, travelling APP data etc. carry out comprehensive descision
Reference Reference score value Registered, in net duration by user's set meal, arrearage record, real name Situations such as be estimated.
Personality Optimistic, gentle, festivals or holidays are active, save Holiday residence man APP uses liveness, trip liveness, dynamic operation track etc. Data carry out comprehensive descision
Hobby Such as main business tagging arrangements:Depending on Frequently, tourism, shopping, cuisines, motion, Game, music, reading, news, chess Board, financing, and show rulers scoring By the use duration for calculating user's all kinds of business for a period of time (Or portfolio)Threshold value contrast with setting is given a mark, or The average level contrast of person and the whole network user are given a mark
(4)Actively recommend:On the premise of user allows and ensures user information safety(Such as can be by user's selection when recommended Whether the sensitive informations such as cell-phone number, name are hidden), system provided to user terminal application(Or the third-party application of access)Recommend The social target information of matching, such as matching assessment result(7 big features " match index ", hobby " intensity index "), account name(Or The pet name), head portrait etc..
(5)Instant messaging:System be supplied to user with recommend social target engage in the dialogue, leave a message, send media file, For functions such as head portrait thumb ups.
(6)Recommendation score:System provides the user the result feedback function whether effective to the social target of recommendation.
2. open interface(Api, SDK etc.)
(1)Recommendation service:Open system recommendation service interface, third-party application can be called by the interface, incoming to work as Preceding customer location, Subscriber Number and circle select the parameters such as scope, you can obtain the social target recommendation list matched with the user.
(2)Application data access service:Open system data access service interface, third-party application can pass through the interface Application data is uploaded, in the social target of intelligent Matching third-party application data can be used to carry out comprehensive analysis matching.
3. characteristic key analysis module
The module is mainly provided to be identified by user(Such as:Subscriber phone number), call user's representation data platform interface to obtain To the user's portrait and characteristic of the user, load classification scoring defines the classifying rules and standards of grading of information bank, and ties Close business tine and traffic volume measurement data are calculated the intensity index of feature.
The intelligent Matching module 4. user draws a portrait
The module obtains the Figure Characteristics and intensity index data of active user by characteristic key analysis module, and circle selects model The Figure Characteristics and intensity index data of other interior targeted customers are enclosed, and combine both data and are analyzed, are directed to Match index, complementation index to portrait are calculated and association analysis matching, and combine the recommendation score result of user feedback Comprehensive analysis is carried out, the result of matching is according to specific rule(Rule is obtained by Generalization bounds repository)It was ranked up Filter, returns to interactive interface by matching result, suitable destination object is recommended into user.
5. Generalization bounds repository
The repository is mainly used to define and stores Generalization bounds rule, including:User's selection matching range configuration(As user can The matching range threshold value of selection), Generalization bounds(Similitude or complementarity), ordering rule, filtering rule, TopN set etc., and Comprehensive analysis is carried out for user's portrait intelligent Matching module Generalization bounds rule.
6. classification scoring defines information bank
The information bank mainly stores the classification information and standards of grading of feature.Such as culture:In the code of points of definition culture(High, In, it is low)When, it is necessary to amount of reading and content are estimated and classified, such as often access literary works, economic weekly, paper etc., It is classified as the high culture of judge and pays the utmost attention to factor;As liked:Defining the code of points of travel enthusiasts(Have deep love for, be interested in, it is relevant Note etc.)When classify, it is necessary to access content to it, such as often access tour site, trip ticket booking, access tourism magazine weekly Etc. information be classified as tourism have deep love for degree optimization Consideration..The information bank stores the assessment side for defining 7 big characteristic strength indexes Method.Such as " culture " feature accesses the frequency accounting of literature, economic class, news category, scientific and technological class website or column by calculating.
Standards of grading are as follows:
The frequency accounting 80% and the above for accessing literature website are 5 points, and 60%-80% is 4 points, and 40%-60% is 3 points, 20%-40% For 2 points, 0-20% is 1 point;
The frequency accounting 80% and the above for accessing economic class website are 5 points, and 60%-80% is 4 points, and 40%-60% is 3 points, 20%-40% For 2 points, 0-20% is 1 point.
Etc. these scoring definition as described above, these comprehensive regular scorings divide for the method for expressing of " culture " this attribute Class for it is high, medium it is higher, in, it is general, low.Characteristic key analysis module carries out the intensity of feature by loading the information base data Index is calculated.
7. user's representation data platform
User is drawn a portrait and characteristic is mainly derived from:Information resource database(Sex, age bracket etc.), user behavior and trace information Storehouse(Using set meal, behavior, longitude and latitude are accessed, user's running orbit resides position etc.), traffic statistics storehouse(ARPU, stream Amount distribution, access duration, access frequency etc.), mobile network's signaling platform(Single, location updating is single in detail in detail for calling and called signaling, switch The interface online such as detailed list, S1-U/GB/IUPS/ is single etc. in detail), third-party application database(Ride data, order data, walking number According to etc.).
Brief description of the drawings
Fig. 1 is feature intelligent matching system main modular composition schematic diagram.
Fig. 2 is the service application process schematic of feature intelligent matching system.
Embodiment
Below by example in detail embodiment.Here social target is applied to the system of the present invention to recommend The business processing flow of scene is illustrated, and selected example is only used for explaining the present invention, is not intended to limit the present invention's Scope.Feature intelligent matching system recommends the business processing flow of social target referring to Fig. 2 of Figure of description, and detailed process is said It is bright as follows:
Step 1:User submits matching request, and content includes subscriber phone number, and user's real-time position information encloses the geography of choosing Range information(Such as:5 km etc.), and user's social target signature of interest(Such as:Music interest, tourism hobby etc.).
Step 2:Characteristic key analysis module receives the matching condition of user's submission, can be divided into following two steps and enter Row retrieval:
A. according to active user's phone number, by user's representation data platform obtain Figure Characteristics that the user met and The traffic volume measurement situation of each feature.
B. according to the real-time position information of active user, the geographic range of circle choosing, obtained by user's representation data platform The information and Figure Characteristics of other users in the range of this, and each 7 big FEATURE service amount statistical conditions of user.
Characteristic key analysis module is by loading traffic volume measurement data, and load classification scoring defines the rule of information bank Then data, calculate " intensity index " of 7 big characteristic attributes of drawing a portrait, such as can analyze use from the statistics of business of networking classification There is principal character label in the hobby feature at family:Game, chess and card, motion, tourism, shopping, cuisines, music, video, photograph, read Reading, news, financing etc.;The label " intensity index " of music-lover can be according in the same period, and the user accesses music net The flow stood accounts for the accounting of user's total flow(Or duration accounting, clicking rate accounting)It is estimated;Can also be according to the user Music site average discharge is accessed with full dose user(Or average duration, average click-through rate)Difference be estimated.
The characteristic of user's representation data platform is answered from mobile network's signaling platform, information resource database, third party Use database.Wherein:
1)Mobile network's signaling platform is used for the interaction data bag for gathering each equipment room in mobile network(XDR)And carry out Packet analyzing (DPI), wherein XDR includes circuit domain(CS domains)And data field(Ps domain)Chain of command and user's plane signaling are single in detail(Such as:Calling and called Single, location updating is single in detail in detail, the online of the interface such as list, S1-U/GB/IUPS/ is detailed single in detail for switching for signaling), the significant data after parsing Deposit in the database in signaling platform, wherein important data include six key elements of each user behavior online, such as:When Between, place, terminal iidentification IMEI, cell-phone number, content, result;
2)Information resource database is mainly used in storage cell data base, end message storehouse, user information database and business identification storehouse.Cell Database:Including information such as cell ID, title, network type, cover type, longitude and latitude, covering scene, administrative area, districts and cities;
3)Third-party application database is mainly used in storing third-party application data, data of such as riding, order data, walking number According to the information such as tourism app data.
Step 3:The policy rule information in user's portrait intelligent Matching module loading Generalization bounds storehouse, is obtained using similar Property characteristic attribute and complementary characteristic attribute(Personality, hobby), and TopN configuration information.
User's portrait intelligent Matching module is matched by loading Step 1 with Step 2 retrieval with analysis result. The matching algorithm of the module can carry out matching primitives according to the intensity index of feature, obtain match index result(That is both phase Like degree).If matched using complementary strategy, need that equivalent conversion will be carried out with complementary feature(Such as: " active ", the equivalence of intensity index 5 is in " containing ", intensity index 5).Two object similarities use vector space cosine similarity Mode calculated, calculate the similarity degree between user, the value of measuring similarity is smaller, similarity is got between illustrating user Small, the bigger explanation user's difference of value of similarity is bigger.User is converted to the feature of user to the favorable rating of various things, so The characteristic vector between user calculates cosine similarity afterwards.Two vectorial angle cosine values in cosine similarity vector space It is used as the size for weighing two user's difference.Cosine value indicates that angle closer to 0 degree closer to 1, that is, two vectors are got over Similar, this is just cried " cosine similarity ".And the formula for calculating user's cosine similarity is:
Assuming that intensity indexs of the user a to physical culture(That is preference)For 2, to the intensity index of music for 3, i.e. a feature to Measure and be(2,3), i.e. X1=2, Y1=3.And user b is 5 to the intensity index of physical culture, the intensity index to music is 1, then b spy Levying vector is(5,1), i.e. X1=5, Y1=1, then substituting into formula above just can calculate user a and b cos (θ) value, that is, Match index(That is similarity).
By being obtained after calculating in active user and scope(Such as: 5 km)Other users all match indexes(It is similar Degree), then result is ranked up and obtains match index highest TopN, and returns result to user or social networking application.

Claims (6)

1. a kind of method and system that the social target of intelligent Matching is carried out based on position and user's portrait, it is characterised in that:This is System is main to be configured by autonomous service interaction interface, characteristic key analysis module, user's portrait intelligent Matching module, Generalization bounds Storehouse, open interface, classification scoring define the composition such as information bank, user's representation data platform, and the terminal user of the system can pass through Related mobile phone application software(APP)Log in and search in certain position regional extent and oneself characteristic matching degree(Match index) It is high or complementary(Complementation index)High social target;Meanwhile, on the premise of user allows and ensures user information safety, it is System can actively to user or(Social networking application, social network sites may limit to a little)Recommended user's label characteristics matching degree is high Or complementary high social target.
2. autonomous service interaction interface as claimed in claim 1, it is characterised in that:Can be by mobile phone terminal service software(APP)Or Web The interactive form of the page provides the user service account registration, the choosing of scope circle, actively feature selecting, the function such as recommendation, wherein:Model Enclosure choosing, which refers to enclose on map after the User logs in service software, to be selected certain geographic range and selects being resident for friend-making target Feature(Such as:Resident, visiting, all etc.);Feature selecting, which refers to user, can voluntarily select the various features of friend-making target(Or mark Label)Screening and filtering is carried out, Systematic selection also can be directly given, found and oneself characteristic matching degree height or complementary high TopN societies Hand over target;Actively recommend to refer on the premise of user allows and ensures user information safety(Hide the sensitive letter such as cell-phone number, name Breath), system provides a user(Or the third-party application of access)Recommend the social target information of matching, such as matching assessment result(7 Big feature " match index ", hobby " intensity index "), account name(Or the pet name), head portrait etc..
3. feature selecting as claimed in claim 2, it is characterised in that:User can be to 7 big features(It is culture, economy, face value, strong Health, reference, personality, hobby)Carry out business of networking content and industry of the selection Bing Jiao Give characteristic key analysis modules to correlated characteristic Business amount statistics calculates " intensity index " of the respective feature of two users.
4. characteristic key analysis module as claimed in claim 1, it is characterised in that:The module can be identified by user(Such as:With Family phone number)User's representation data platform interface is called to get the user's portrait and characteristic of the user, load classification Classifying rules and standards of grading that information bank is defined are defined, and combine the intensity of business tine and traffic volume measurement data to feature Index is calculated.
The intelligent Matching module 5. user as claimed in claim 1 draws a portrait, it is characterised in that:Obtained by characteristic key analysis module The Figure Characteristics and intensity of other targeted customers in the range of the Figure Characteristics and intensity index data of active user, and circle choosing Exponent data, and analyzed with reference to both data, it is directed to count " match index ", " complementation index " of portrait Calculate and association analysis, and combine the recommendation score result of user feedback and carry out comprehensive analysis, the result of matching is according to specific rule Then(Rule is obtained by Generalization bounds repository)Filtering is ranked up, interactive interface is returned result to.
6. Generalization bounds repository as claimed in claim 1, it is characterised in that:For defining and storing Generalization bounds rule, Including:The configuration of user's selection matching range, Generalization bounds(Similitude or complementarity), ordering rule, filtering rule, TopN set Deng, and carry out comprehensive analysis for user's portrait intelligent Matching module Generalization bounds rule.
CN201710401245.9A 2017-06-01 2017-06-01 A kind of method and system based on position and the social target of user's portrait intelligent Matching Withdrawn CN107291841A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710401245.9A CN107291841A (en) 2017-06-01 2017-06-01 A kind of method and system based on position and the social target of user's portrait intelligent Matching

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710401245.9A CN107291841A (en) 2017-06-01 2017-06-01 A kind of method and system based on position and the social target of user's portrait intelligent Matching

Publications (1)

Publication Number Publication Date
CN107291841A true CN107291841A (en) 2017-10-24

Family

ID=60095450

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710401245.9A Withdrawn CN107291841A (en) 2017-06-01 2017-06-01 A kind of method and system based on position and the social target of user's portrait intelligent Matching

Country Status (1)

Country Link
CN (1) CN107291841A (en)

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107807997A (en) * 2017-11-08 2018-03-16 北京奇虎科技有限公司 User's portrait building method, device and computing device based on big data
CN108228839A (en) * 2018-01-05 2018-06-29 湖南科技学院 A kind of colleges and universities' admission examinee's dating system and computer media
CN108846726A (en) * 2018-06-07 2018-11-20 深圳市惠群商业数据技术有限公司 It is a kind of to carry out social method and system by delivering books
CN108875069A (en) * 2018-07-04 2018-11-23 中国联合网络通信集团有限公司 A kind of marriage and making friend's matching process and device based on telecommunications big data
CN108920682A (en) * 2018-07-11 2018-11-30 厦门盈趣科技股份有限公司 Social user's recommended method and device based on machine learning and user's Portrait brand technology
CN109062938A (en) * 2018-06-15 2018-12-21 平安科技(深圳)有限公司 Orient the method, apparatus and storage medium, server of recommended user
CN109379733A (en) * 2018-11-27 2019-02-22 长安大学 A kind of non-contact short distance information real-time matching interactive system and method
CN109448186A (en) * 2018-10-28 2019-03-08 浙江新弘网络科技有限公司 A kind of visitor's system for prompting
CN109934273A (en) * 2019-03-01 2019-06-25 长沙理工大学 It is a kind of based on the fault characteristic of DML-KNN algorithm and active damage repair technology draw a portrait new method
CN110071818A (en) * 2018-01-22 2019-07-30 江苏迪纳数字科技股份有限公司 A kind of active safe driving householder method adapting to high speed traveling based on network communication
CN110111143A (en) * 2019-04-28 2019-08-09 上海二三四五移动科技有限公司 A kind of control method and control device for establishing mobile end subscriber portrait
CN110287425A (en) * 2019-05-09 2019-09-27 北京邮电大学 Save the periphery point of interest recommended method that net joins automobile mounted terminal computing resource
CN110428348A (en) * 2019-08-07 2019-11-08 北京百度网讯科技有限公司 Blind date object recommendation method and apparatus
CN110569435A (en) * 2019-08-29 2019-12-13 苏州华策网络科技有限公司 Intelligent dual-ended recommendation engine system and method
CN110650428A (en) * 2019-08-29 2020-01-03 惠州华阳通用电子有限公司 Interaction method and device based on content and vehicle position
CN110781374A (en) * 2018-07-13 2020-02-11 北京字节跳动网络技术有限公司 User data matching method and device, electronic equipment and computer readable medium
CN110852898A (en) * 2019-10-31 2020-02-28 上海动听网络科技有限公司 Friend making method, terminal, server and friend making system
CN110969535A (en) * 2018-09-30 2020-04-07 武汉斗鱼网络科技有限公司 Method, device, system and medium for matching between users
CN111314210A (en) * 2020-02-13 2020-06-19 上海掌门科技有限公司 Method and equipment for social interaction
CN111729319A (en) * 2020-08-10 2020-10-02 成都卓杭网络科技股份有限公司 Social contact recommendation method and device for game player
CN111729177A (en) * 2020-06-23 2020-10-02 马国英 Bedside fixing device is used in hemodialysis room nursing
CN112035756A (en) * 2020-08-27 2020-12-04 中国建设银行股份有限公司 Method and device for recommending friends of old people, electronic equipment and storage medium
CN111861174B (en) * 2020-07-09 2021-04-13 北京睿知图远科技有限公司 Credit assessment method for user portrait
CN113672777A (en) * 2021-08-30 2021-11-19 上海飞旗网络技术股份有限公司 User intention exploration method and system based on traffic correlation analysis
CN115186664A (en) * 2022-09-13 2022-10-14 深圳市爱聊科技有限公司 Method and system for measuring and calculating degree of coincidence between subjects based on multiple dimensions
CN116805255A (en) * 2023-06-05 2023-09-26 深圳市瀚力科技有限公司 Advertisement automatic optimizing throwing system based on user image analysis
CN116805255B (en) * 2023-06-05 2024-04-23 深圳市瀚力科技有限公司 Advertisement automatic optimizing throwing system based on user image analysis

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102867020A (en) * 2012-07-30 2013-01-09 成都西可科技有限公司 Personal character trait-based friend making matching method
US20140089132A1 (en) * 2012-09-26 2014-03-27 Wal-Mart Stores, Inc. System and method for making gift recommendations using social media data
CN104915861A (en) * 2015-06-15 2015-09-16 浙江经贸职业技术学院 An electronic commerce recommendation method for a user group model constructed based on scores and labels
CN106649509A (en) * 2016-10-12 2017-05-10 腾讯科技(北京)有限公司 User feature extraction method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102867020A (en) * 2012-07-30 2013-01-09 成都西可科技有限公司 Personal character trait-based friend making matching method
US20140089132A1 (en) * 2012-09-26 2014-03-27 Wal-Mart Stores, Inc. System and method for making gift recommendations using social media data
CN104915861A (en) * 2015-06-15 2015-09-16 浙江经贸职业技术学院 An electronic commerce recommendation method for a user group model constructed based on scores and labels
CN106649509A (en) * 2016-10-12 2017-05-10 腾讯科技(北京)有限公司 User feature extraction method and device

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107807997A (en) * 2017-11-08 2018-03-16 北京奇虎科技有限公司 User's portrait building method, device and computing device based on big data
CN108228839A (en) * 2018-01-05 2018-06-29 湖南科技学院 A kind of colleges and universities' admission examinee's dating system and computer media
CN110071818A (en) * 2018-01-22 2019-07-30 江苏迪纳数字科技股份有限公司 A kind of active safe driving householder method adapting to high speed traveling based on network communication
CN108846726A (en) * 2018-06-07 2018-11-20 深圳市惠群商业数据技术有限公司 It is a kind of to carry out social method and system by delivering books
WO2019237571A1 (en) * 2018-06-15 2019-12-19 平安科技(深圳)有限公司 Method for directionally recommending user, device and storage medium, and server
CN109062938A (en) * 2018-06-15 2018-12-21 平安科技(深圳)有限公司 Orient the method, apparatus and storage medium, server of recommended user
CN108875069A (en) * 2018-07-04 2018-11-23 中国联合网络通信集团有限公司 A kind of marriage and making friend's matching process and device based on telecommunications big data
CN108920682A (en) * 2018-07-11 2018-11-30 厦门盈趣科技股份有限公司 Social user's recommended method and device based on machine learning and user's Portrait brand technology
CN108920682B (en) * 2018-07-11 2021-08-31 厦门盈趣科技股份有限公司 Social user recommendation method and device based on machine learning and user portrait technology
CN110781374A (en) * 2018-07-13 2020-02-11 北京字节跳动网络技术有限公司 User data matching method and device, electronic equipment and computer readable medium
CN110969535A (en) * 2018-09-30 2020-04-07 武汉斗鱼网络科技有限公司 Method, device, system and medium for matching between users
CN109448186A (en) * 2018-10-28 2019-03-08 浙江新弘网络科技有限公司 A kind of visitor's system for prompting
CN109379733A (en) * 2018-11-27 2019-02-22 长安大学 A kind of non-contact short distance information real-time matching interactive system and method
CN109934273A (en) * 2019-03-01 2019-06-25 长沙理工大学 It is a kind of based on the fault characteristic of DML-KNN algorithm and active damage repair technology draw a portrait new method
CN110111143A (en) * 2019-04-28 2019-08-09 上海二三四五移动科技有限公司 A kind of control method and control device for establishing mobile end subscriber portrait
CN110287425B (en) * 2019-05-09 2021-05-11 北京邮电大学 Peripheral interest point recommendation method for saving calculation resources of vehicle-mounted terminal of internet automobile
CN110287425A (en) * 2019-05-09 2019-09-27 北京邮电大学 Save the periphery point of interest recommended method that net joins automobile mounted terminal computing resource
CN110428348A (en) * 2019-08-07 2019-11-08 北京百度网讯科技有限公司 Blind date object recommendation method and apparatus
CN110650428A (en) * 2019-08-29 2020-01-03 惠州华阳通用电子有限公司 Interaction method and device based on content and vehicle position
CN110569435A (en) * 2019-08-29 2019-12-13 苏州华策网络科技有限公司 Intelligent dual-ended recommendation engine system and method
CN110569435B (en) * 2019-08-29 2023-01-03 苏州华策网络科技有限公司 Intelligent dual-ended recommendation engine system and method
CN110650428B (en) * 2019-08-29 2021-06-29 惠州华阳通用电子有限公司 Interaction method and device based on content and vehicle position
CN110852898A (en) * 2019-10-31 2020-02-28 上海动听网络科技有限公司 Friend making method, terminal, server and friend making system
CN111314210A (en) * 2020-02-13 2020-06-19 上海掌门科技有限公司 Method and equipment for social interaction
CN111729177A (en) * 2020-06-23 2020-10-02 马国英 Bedside fixing device is used in hemodialysis room nursing
CN111729177B (en) * 2020-06-23 2022-09-30 马国英 Bedside fixing device is used in hemodialysis room nursing
CN111861174B (en) * 2020-07-09 2021-04-13 北京睿知图远科技有限公司 Credit assessment method for user portrait
CN111729319A (en) * 2020-08-10 2020-10-02 成都卓杭网络科技股份有限公司 Social contact recommendation method and device for game player
CN112035756A (en) * 2020-08-27 2020-12-04 中国建设银行股份有限公司 Method and device for recommending friends of old people, electronic equipment and storage medium
CN113672777A (en) * 2021-08-30 2021-11-19 上海飞旗网络技术股份有限公司 User intention exploration method and system based on traffic correlation analysis
CN113672777B (en) * 2021-08-30 2023-09-08 上海飞旗网络技术股份有限公司 User intention exploration method and system based on flow correlation analysis
CN115186664A (en) * 2022-09-13 2022-10-14 深圳市爱聊科技有限公司 Method and system for measuring and calculating degree of coincidence between subjects based on multiple dimensions
CN115186664B (en) * 2022-09-13 2023-01-13 深圳市爱聊科技有限公司 Method and system for measuring and calculating coincidence degree between subjects based on multiple dimensions
CN116805255A (en) * 2023-06-05 2023-09-26 深圳市瀚力科技有限公司 Advertisement automatic optimizing throwing system based on user image analysis
CN116805255B (en) * 2023-06-05 2024-04-23 深圳市瀚力科技有限公司 Advertisement automatic optimizing throwing system based on user image analysis

Similar Documents

Publication Publication Date Title
CN107291841A (en) A kind of method and system based on position and the social target of user's portrait intelligent Matching
US20210157869A1 (en) Information sending method, apparatus and system, and computer-readable storage medium
Thebault-Spieker et al. Toward a geographic understanding of the sharing economy: Systemic biases in UberX and TaskRabbit
CN209690978U (en) User data acquisition device
US10332150B2 (en) Location event advertising
JP5053283B2 (en) Prioritizing entity display in distributed geographic information systems
JP2018110010A (en) Consumer driven advertisement system
CN106503015A (en) A kind of method for building user's portrait
CN110110221A (en) Government data intelligent recommendation method and system
CN106504099A (en) A kind of system for building user's portrait
Berlingerio et al. The GRAAL of carpooling: GReen And sociAL optimization from crowd-sourced data
CN105122293A (en) Method and system for logging and processing data relating to an activity
CN107292463A (en) A kind of method and system that the project evaluation is carried out to application program
CN103177384A (en) Network advertisement putting method based on user interest spectrum
CN107086922A (en) A kind of user behavior recognition method and apparatus
CN110334293A (en) A kind of facing position social networks has Time Perception position recommended method based on fuzzy clustering
CN104620272A (en) Generating a point of interest profile based on third-party social comments
Höpken et al. The knowledge destination—a customer information-based destination management information system
CN109189959A (en) A kind of method and device constructing image data base
CN107292648A (en) A kind of user behavior analysis method and device
Dokuz et al. Discovering socially important locations of social media users
CN112765475B (en) Smart travel target matching method
CN108665083A (en) A kind of method and system for advertisement recommendation for dynamic trajectory model of being drawn a portrait based on user
JP2020537252A (en) Systems and methods for predicting similar mobile devices
Wang et al. Measuring urban vibrancy of residential communities using big crowdsourced geotagged data

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
CB02 Change of applicant information

Address after: 510000 B03, E-PARK Creative Park, yuzhuzhi Valley, 32, Keng Kong Street, Maogang village, Whampoa, Guangzhou, Guangdong

Applicant after: GUANGZHOU HENGHAO DATA TECHNOLOGY CO., LTD.

Address before: 510080 4, No. 3, Ho Group West Road, Yuexiu District, Guangzhou, Guangdong.

Applicant before: GUANGZHOU HENGHAO DATA TECHNOLOGY CO., LTD.

CB02 Change of applicant information
WW01 Invention patent application withdrawn after publication

Application publication date: 20171024

WW01 Invention patent application withdrawn after publication