CN105718576B - Personalized location recommender system relevant to geographical feature - Google Patents

Personalized location recommender system relevant to geographical feature Download PDF

Info

Publication number
CN105718576B
CN105718576B CN201610044328.2A CN201610044328A CN105718576B CN 105718576 B CN105718576 B CN 105718576B CN 201610044328 A CN201610044328 A CN 201610044328A CN 105718576 B CN105718576 B CN 105718576B
Authority
CN
China
Prior art keywords
user
geographic
module
preference
check
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.)
Active
Application number
CN201610044328.2A
Other languages
Chinese (zh)
Other versions
CN105718576A (en
Inventor
朱晓妍
郝日佩
池浩田
裴庆祺
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.)
Xidian University
Original Assignee
Xidian University
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 Xidian University filed Critical Xidian University
Priority to CN201610044328.2A priority Critical patent/CN105718576B/en
Publication of CN105718576A publication Critical patent/CN105718576A/en
Application granted granted Critical
Publication of CN105718576B publication Critical patent/CN105718576B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/9535Search customisation based on user profiles and personalisation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a kind of personalized location recommender systems relevant to geographical feature, mainly solve the deficiency of existing Collaborative Filtering Recommendation Algorithm performance difference in Sparse scene.Its technical solution is recommended by the different mutually coordinated realizations of functional module: database obtains module and obtains target information;Target information is stored in customer data base by user data library module;User preference excavates module and obtains the position candidate recommendation list to sort according to user preference from customer data base;Target information is stored in geographical data bank by geodata library module;Geographical feature excavates module and obtains the position candidate recommendation list to sort according to geographical feature from geographical data bank;Recommending module uses the recommendation list to sort according to user preference and influences the recommendation list of sequence according to geographical feature, obtains recommendation results.The present invention alleviates the sparsity problem of data, can be used in the place Push Service based on position social networks by considering geographical feature.

Description

Personalized position recommendation system related to geographic features
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a personalized recommendation technology related to geographic features, which can be used for location push service in a location-based social network.
Background
With the rapid development of database technology and the wide application of database management systems, data accumulation is increasing. In the face of the proliferation of data, it is desirable to mine out much of the important information hidden behind it so that it can be better used to serve people. The service provider has a great deal of personal information and historical records related to the user, and the data can be used for actively recommending related services to the user, so that the service provider is convenient for the user and beneficial to the service provider.
The traditional recommendation system algorithm mainly uses a recommendation algorithm based on collaborative filtering and a recommendation algorithm based on content. The advent and advancement of wireless networks and location-aware technologies has driven the explosion of mobile internet, and particularly location-based social networks, and users' geo-location data has begun to be acquired in large quantities via client GPS. The geographic context begins to be an important feature attribute for location recommendation, enabling some goods recommendation tasks based on the user's geographic location.
After collecting the geographic position data of the user, the user needs to be divided on the geographic position, and the dividing method is based on the longitude and latitude of the location where the user signs in. And then, calculating the prediction scores of the user and the region to the positions through a preset model by scanning the position history records of all the users in the region and all the history records of the users to be recommended, further obtaining candidate positions, and performing recommendation calculation based on model collaborative filtering.
In the currently existing recommendation calculation schemes based on collaborative filtering, one is based on the similarity degree between users and the other is based on the similarity degree between articles.
In the above methods, since no consideration is given to the influence of geographic features on the location recommendation for the user, the performance is poor in a data sparse scene, such as remote location recommendation, and the problem of cold start of a new user and a new article cannot be effectively solved.
Disclosure of Invention
The invention aims to provide a personalized position recommendation system related to geographic features aiming at the defects of the method, and the personalized position recommendation system uses a potential dirichlet allocation topic model in combination with the position category and the geographic features to provide interesting positions for users.
To achieve the above object, a recommendation system of the present invention includes:
the data acquisition module DC is used for capturing the sign-in record of the target website user and providing data for the user database module UD and the geographic database module DD;
the user database module UD is used for storing all information captured by the data capture module DC in a user database by taking the user ID as an index and providing user information for the user preference mining module UM;
the geographic database module DD is used for storing all information captured by the data capture module DC in a geographic database by taking a geographic city as an index and providing geographic information for the geographic feature mining module DM;
a user preference mining module UM for mining the preference of the user by using the data in the user database module UD to obtain a candidate position recommendation List sorted according to the preference of the user1
A geographic feature mining module DM, configured to mine geographic features using the data in the geographic database module DD to obtain a candidate position recommendation List sorted according to the geographic feature influence2
A recommendation module RD for recommending a List List based on the candidate locations sorted according to the user's preferences1And a List of candidate location recommendations sorted by geographic feature impact2And generating a final recommendation Result.
The invention has the advantages that:
according to the invention, the user preference mining module learns the personal interests of the user, so that personalized position recommendation is realized;
according to the invention, the geographic characteristic mining module is used for integrating the geographic characteristic influence, so that the problem of data sparsity is relieved, especially the problem of remote location recommendation.
Drawings
FIG. 1 is an overall framework diagram of the recommendation system of the present invention;
FIG. 2 is a block diagram of a user preference mining module framework in the present invention;
FIG. 3 is a block diagram of a geographic feature mining module of the present invention;
FIG. 4 is a diagram of a recommender framework in accordance with the present invention.
Embodiments and effects of the present invention are described in detail below with reference to the accompanying drawings.
Detailed description of the preferred embodiments
The core idea of the invention is to consider the influence of geographic features, combine position categories, use a potential Dirichlet allocation topic model, and provide a personalized position recommendation system related to the geographic features, so as to provide interested positions for users.
Referring to fig. 1, the present invention includes: the system comprises a data acquisition module DC, a user database module UD, a geographic database module DD, a user preference mining module UM, a geographic feature mining module DM and a recommendation module RD. The data acquisition module DC is used for capturing the sign-in record of the target website user and providing data for the user database module UD and the geographic database module DD; the user database module UD is used for storing all information acquired by the data acquisition module DC in a user database by taking the user ID as an index and providing user information for the user preference mining module UM; a user preference mining module UM which uses the user sign-in record in the user database module DC to mine the preference of the user to be recommended and obtain a candidate position recommendation List ordered according to the user preference1(ii) a The geographic database module DD is used for storing all information acquired by the data acquisition module DC in a geographic database by taking a geographic city as an index and providing geographic information for the geographic feature mining module DM; the geographic feature mining module DM uses user check-in records contained in different geographic cities in the geographic database module DD to mine the geographic features of the city to be recommended to obtain a candidate position recommendation List sorted according to the influence of the geographic features2(ii) a Recommendation module RD uses recommendation List List obtained by user preference mining module UM1And a recommendation List obtained by the geographic feature mining module DM2And obtaining a final recommendation result.
The data acquisition module DC acquires a check-in record of a target website user, wherein the check-in record comprises: user ID, semantic location, such as daylotus garden, category of semantic location, such as travel & traffic, and geographic city where the semantic location is, such as west' an. Wherein the category of the semantic location includes: art & entertainment, college & university, event, grocery store, night market, outdoor & leisure, residential, shop & service and travel & traffic.
Referring to fig. 2, the user preference mining module UM includes: subject model training unit UM1Three-layer graph model construction unit UM2And a location preference value calculation unit UM3
The topic model training Unit UM1The system comprises a user database module UD, a theme characteristic vector UV and a user database module UD, wherein the user database module UD is used for obtaining user check-in records and themes and generating theme characteristic vectors UV corresponding to the themes of each user;
the three-layer graph model construction unit UM2And the user sign-in record and topic model training unit UM is used for obtaining the user sign-in record and the topic model training unit UM according to the user database module UD1Constructing a three-layer graph structure of a user layer, a position layer and a theme layer which are composed of all users, all positions and all themes by using the obtained theme feature vector UV;
the position preference value calculating unit UM3The method is used for obtaining the prior knowledge of the user-subject probability distribution in the user database according to the three-layer graph structure of the user layer, the position layer and the subject layerAnd a priori knowledge β of the topic-location probability distributionvCalculating the preference value f of the user to the position not visiteduvWherein the preference value f of the user to the non-visited locationuvCalculated by the following formula:
wherein,representing user u versus topic zkIs estimated based on the degree of preference of the user,representing a topic z for a location v in a user databasekThe estimation of the probability of generation in (1),representing a topic zkThe number of times sampled in the user u check-in record,indicating that position v is on subject z in user u check-in recordkNumber of times of middle sampling, subscriptIndicating that the subject i, R is not includedrRepresenting the number of topics contained in the check-in record of the user u;
using user preference values f for locationuvThe inaccessible positions are sorted in a descending manner, the first k positions are selected to generate a candidate position recommendation List sorted according to the preference of the user1
Referring to fig. 3, the geographic feature mining module DM includes: topic model training unit DM1Three-layer graph model building unit DM2And a position preference value calculation unit DM3
The topic model training unit DM1The system comprises a geographic database module DD, a theme feature vector DV, a user name database module DD, a user name database module;
the three-layer graph model building unit DM2And a module DM for training the check-in records and topic models of all users in the geographic city contained in the geographic database module DD1Constructing a geographic layer consisting of all cities, all positions and all topics, and a three-layer graph structure of a position layer and a topic layer by the obtained topic feature vector DV;
the position preferenceValue calculation unit DM3The method is used for obtaining the prior knowledge of the probability distribution of the geographic city-subject in the geographic database according to the three-layer graph structure of the geographic layer, the position layer and the subject layerAnd a priori knowledge β 'of the topic-location probability distribution'vCalculating the preference value f of the geographic city to the positionlv', wherein the geographic city has a preference value f for locationlv', calculated by the formula:
wherein,representing a geographic city l vs. a topic zkIs estimated based on the degree of preference of the user,representing a location v in a geographic database on a topic zkThe estimation of the probability of generation in (1),representing a topic zkThe number of times sampled in all check-in records for geographic city l,indicating that the position v is on the subject zkNumber of times of middle sampling, subscriptIndicating that the subject i, R is not includedlRepresents the number of topics contained in all check-in records of the geographic city l, | V | represents the number of locations contained in all check-in records of the geographic city l.
Preference value f for location using geographic citieslv', to the positionDescending and sorting, selecting the first k positions to form a candidate position recommendation List sorted according to the influence of geographic features2
Referring to fig. 4, the recommendation module RD includes: weighting coefficient calculation submodule RD1And location recommendation submodule RD2
The weighting coefficient calculation submodule RD1Calculating the weight value omega occupied by the user's personal preference in making a decision by the useruAnd the weight ω occupied by the geographical influence in making the decision by the userlThe calculation formula is as follows:
wherein,mean value, P, representing user u preferenceuRepresents the check-in record for user u,represents the set of locations contained in the check-in record for user u,representing the collection of topics contained by the check-in record for user u,mean value, P, representing the preference of a geographic city llA check-in record representing all users in the geographic city l,represents the set of locations contained in the check-in records of all users in the geographic city l,the set of topics that the check-in records of all users in the geographic city l contain is represented.
The position recommendation submodule RD2For calculating said two recommendation lists List1And List2Weight R of medium position:
R=λufuvlf′lv
wherein,indicating a normalization of the weights taken up in making the decision on the user's personal preferences,representing the normalization of the weight that the geographic features occupy in making the user's decision.
And sorting the positions according to the height of the weighted value, selecting the first k positions to obtain a recommendation Result, wherein the numerical value of k is related to a specific recommendation scene, and if the position in the city to be recommended is more than 100, taking 20 as k is a reasonable choice.

Claims (6)

1. A personalized location recommendation system related to a geographic feature, comprising:
the data acquisition module DC is used for acquiring the sign-in record of the target website user and providing data for the user database module UD and the geographic database module DD;
the user database module UD is used for storing all information captured by the data capture module DC in a user database by taking the user ID as an index and providing user information for the user preference mining module UM;
the geographic database module DD is used for storing all information captured by the data capture module DC in a geographic database by taking a geographic city as an index and providing geographic information for the geographic feature mining module DM;
a user preference mining module UM for mining the preference of the user by using the data in the user database module UD to obtain a candidate position recommendation List sorted according to the preference of the user1
A geographic feature mining module DM, configured to mine geographic features using the data in the geographic database module DD to obtain a candidate position recommendation List sorted according to the geographic feature influence2
A recommendation module RD for recommending a List List based on the candidate locations sorted according to the user's preferences1And a List of candidate location recommendations sorted by geographic feature impact2Generating a final recommendation Result;
the user preference mining module UM comprises:
subject model training unit UM1The system comprises a user database module UD, a theme characteristic vector UV and a user database module UD, wherein the user database module UD is used for obtaining user check-in records and themes and generating theme characteristic vectors UV corresponding to the themes of each user;
three-layer graph model construction unit UM2And the user sign-in record and topic model training unit UM is used for obtaining the user sign-in record and the topic model training unit UM according to the user database module UD1Constructing a three-layer graph structure of a user layer, a position layer and a theme layer which are respectively composed of all users, all positions and all themes by using the obtained theme feature vector UV;
location preference value calculation unit UM3The method is used for obtaining the prior knowledge of the user-subject probability distribution in the user database according to the three-layer graph structure of the user layer, the position layer and the subject layerAnd a priori knowledge β of the topic-location probability distributionvAnd calculating the preference value of the user to the position which is not visited:
wherein,representing user u versus topic zkIs estimated based on the degree of preference of the user,representing a position v in a user database with respect to a topic zkIs determined based on the estimated probability of generation of,representing a topic zkThe number of times sampled in the check-in record for user u,indicating that location v is about topic z in user u's check-in recordkNumber of times sampled, subscriptIndicating that the subject i, R is not includedrRepresenting the number of topics contained in the check-in record of the user u, and N representing the number of positions contained in the check-in record of the user u;
using user preference values f for locationuvThe inaccessible positions are sorted in a descending manner, the first k positions are selected to generate a candidate position recommendation List sorted according to the preference of the user1
The geographic feature mining module DM comprises:
topic model training unit DM1The system comprises a geographic database module DD, a theme feature vector DV, a user name database module DD, a user name database module;
three-layer graph model construction unit DM2And a module DM for training the check-in records and topic models of all users in the geographic city contained in the geographic database module DD1The obtained theme feature vector DV constructs a geographic layer, a position layer and a theme layer which are composed of all cities, all positions and all themesA three-layer graph structure of a subject layer;
position preference value calculation unit DM3The method is used for obtaining the prior knowledge of the probability distribution of the geographic city-subject in the geographic database according to the three-layer graph structure of the geographic layer, the position layer and the subject layerAnd a priori knowledge β of the topic-location probability distributionv', calculating a geographic city preference value f for locationlv′:
Wherein,representing a geographic city l vs. a topic zkIs estimated based on the degree of preference of the user,representing a location v in a geographic database on a topic zkThe estimation of the probability of generation in (1),representing a topic zkThe number of times sampled in all check-in records for geographic city l,indicating that the position v is on the subject zkNumber of times of middle sampling, subscriptIndicating that the subject i, R is not includedlThe number of the topics contained in all check-in records of the geographic city l is represented, | V | represents the number of the positions contained in all check-in records of the geographic city l;
preference value f for location using geographic citieslv', to positionThe rows are sorted in a descending way, the first k positions are selected to form a candidate position recommendation List sorted according to the influence of the geographic features2
2. The system of claim 1, wherein the check-in record comprises: the user ID, the semantic location, the category of the semantic location and the geographic city in which the semantic location is located.
3. The system of claim 2, wherein the categories of semantic locations include art & entertainment, college & university, event, grocery store, night market, outdoor & leisure, residential, shop & service, and travel & traffic.
4. The system of claim 1, wherein said recommendation module RD comprises:
weighting coefficient calculation submodule RD1: for calculating the weight value omega occupied by the personal preference of the user when the user makes a decision according to the relative standard deviation formulauAnd the weight ω occupied by the geographical influence in making the decision by the userl
Position recommendation submodule RD2: for calculating the two recommendation lists List according to a weighting formula1And List2And (4) sorting the weighted values of the middle positions according to the height of the weighted values to obtain a recommendation Result.
5. System according to claim 4, wherein the weighting factor calculation submodule RD1Calculating a weight ω occupied by the user's personal preference in making the decisionuAnd the weight ω occupied by the geographical influence in making the decision by the userlCalculated by the following formula:
wherein,mean value, P, representing user u preferenceuRepresents the check-in record for user u,represents the set of locations contained in the check-in record for user u,representing the collection of topics contained by the check-in record for user u,mean value, P, representing the preference of a geographic city llA check-in record representing all users in the geographic city l,represents the set of locations contained in the check-in records of all users in the geographic city l,the set of topics that the check-in records of all users in the geographic city l contain is represented.
6. The system of claim 4, wherein the location recommendation submodule RD2Calculating two recommendation lists1And List2The weighted value of the middle position is calculated by the following formula:
R=λufuvlf′lv
wherein,to representThe weights that the user's personal preferences take in making the decision are normalized,representing the normalization of the weight that the geographic features occupy in making the user's decision.
CN201610044328.2A 2016-01-22 2016-01-22 Personalized location recommender system relevant to geographical feature Active CN105718576B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610044328.2A CN105718576B (en) 2016-01-22 2016-01-22 Personalized location recommender system relevant to geographical feature

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610044328.2A CN105718576B (en) 2016-01-22 2016-01-22 Personalized location recommender system relevant to geographical feature

Publications (2)

Publication Number Publication Date
CN105718576A CN105718576A (en) 2016-06-29
CN105718576B true CN105718576B (en) 2019-07-16

Family

ID=56153944

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610044328.2A Active CN105718576B (en) 2016-01-22 2016-01-22 Personalized location recommender system relevant to geographical feature

Country Status (1)

Country Link
CN (1) CN105718576B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108268519B (en) * 2016-12-30 2022-05-24 阿里巴巴集团控股有限公司 Method and device for recommending network object
CN106951572A (en) * 2017-04-12 2017-07-14 上海斐讯数据通信技术有限公司 A kind of food and drink commending system and dining recommending method
CN107180269B (en) * 2017-05-27 2021-07-16 维沃移动通信有限公司 Seat recommendation method and terminal equipment
CN107562798A (en) * 2017-08-02 2018-01-09 北京大学(天津滨海)新代信息技术研究院 A kind of real-time information recommendation method of the time geodata based on user
CN109558961B (en) * 2017-09-25 2023-05-02 阿里巴巴集团控股有限公司 Method and system for determining position information, storage medium, processor and device
CN109688178B (en) * 2017-10-19 2022-03-11 阿里巴巴集团控股有限公司 Recommendation method, device and equipment
CN108009877B (en) * 2017-11-24 2021-10-15 创新先进技术有限公司 Information mining method and device
CN108460101B (en) * 2018-02-05 2019-05-28 山东师范大学 Point of interest recommended method of the facing position social networks based on geographical location regularization
CN108958247A (en) * 2018-07-02 2018-12-07 深圳市益鑫智能科技有限公司 A kind of guided robot
CN109902222B (en) 2018-11-30 2022-05-13 华为技术有限公司 Recommendation method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010067175A (en) * 2008-09-12 2010-03-25 Toshiba Corp Hybrid content recommendation server, recommendation system, and recommendation method
CN102594905A (en) * 2012-03-07 2012-07-18 南京邮电大学 Method for recommending social network position interest points based on scene
CN103064924A (en) * 2012-12-17 2013-04-24 浙江鸿程计算机系统有限公司 Travel destination situation recommendation method based on geotagged photo excavation
CN105069717A (en) * 2015-07-29 2015-11-18 陕西师范大学 Personalized travel route recommendation method based on tourist trust

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010067175A (en) * 2008-09-12 2010-03-25 Toshiba Corp Hybrid content recommendation server, recommendation system, and recommendation method
CN102594905A (en) * 2012-03-07 2012-07-18 南京邮电大学 Method for recommending social network position interest points based on scene
CN103064924A (en) * 2012-12-17 2013-04-24 浙江鸿程计算机系统有限公司 Travel destination situation recommendation method based on geotagged photo excavation
CN105069717A (en) * 2015-07-29 2015-11-18 陕西师范大学 Personalized travel route recommendation method based on tourist trust

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
在线地图服务日志的大数据分析;陈迪等;《小型微型计算机系统》;20150131;第36卷(第1期);第33-38页
基于分层模型的位置推荐方法研究;孔晓笛等;《计算机与数字工程》;20150331;第43卷(第3期);第468-472页

Also Published As

Publication number Publication date
CN105718576A (en) 2016-06-29

Similar Documents

Publication Publication Date Title
CN105718576B (en) Personalized location recommender system relevant to geographical feature
JP6784308B2 (en) Programs that update facility characteristics, programs that profile facilities, computer systems, and how to update facility characteristics
Jiang et al. Author topic model-based collaborative filtering for personalized POI recommendations
CN109241454B (en) Interest point recommendation method fusing social network and image content
Zheng et al. Collaborative location and activity recommendations with gps history data
Jiang et al. Personalized travel sequence recommendation on multi-source big social media
CN104123398B (en) A kind of information-pushing method and device
Zheng et al. Recommending friends and locations based on individual location history
CN107291888B (en) Machine learning statistical model-based living recommendation system method near living hotel
US20190087072A1 (en) System and method for context enhanced mapping
Lee et al. Exploration of geo-tagged photos through data mining approaches
Zhao et al. Personalized recommendations of locally interesting venues to tourists via cross-region community matching
US20150112963A1 (en) Time and location based information search and discovery
US8612134B2 (en) Mining correlation between locations using location history
US20130268558A1 (en) Methods and Systems of Aggregating Information of Social Networks Based on Changing Geographical Locations of a Computing Device Via a Network
Falcone et al. What is this place? Inferring place categories through user patterns identification in geo-tagged tweets
CN105894089A (en) Method of establishing credit investigation model, credit investigation determination method and the corresponding apparatus thereof
CA2879685A1 (en) Methods and systems of aggregating information of social networks based on changing geographical locations of a computing device via a network
Peng et al. Perceiving Beijing’s “city image” across different groups based on geotagged social media data
US20140089343A1 (en) Methods and Systems for Monitoring and Controlling Social Network Communications Over a Network at a Secure Location
Waga et al. Recommendation of points of interest from user generated data collection
CN108897750B (en) Personalized place recommendation method and device integrating multiple contextual information
Liu et al. Where your photo is taken: Geolocation prediction for social images
Xia et al. Decision Tree‐Based Contextual Location Prediction from Mobile Device Logs
Waga et al. Context aware recommendation of location-based data

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