CN106022934A - Potential friend discovering method based on moving trajectory pattern and system - Google Patents
Potential friend discovering method based on moving trajectory pattern and system Download PDFInfo
- Publication number
- CN106022934A CN106022934A CN201610293497.XA CN201610293497A CN106022934A CN 106022934 A CN106022934 A CN 106022934A CN 201610293497 A CN201610293497 A CN 201610293497A CN 106022934 A CN106022934 A CN 106022934A
- Authority
- CN
- China
- Prior art keywords
- dwell point
- user
- semantic
- point
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a potential friend discovering method based on a moving trajectory pattern. The method comprises the steps that a semantic description model is established; the semantic information of each staying point is described according to a POI data set; each kind of service is weighted; according to the distribution of the staying points, the staying points are clustered into positions; the semantic information of each position is described to generate a continuous kind trajectory sequence; according to the generated kind trajectory sequence, the common kind trajectory sub sequence CTP of users is extracted; the similarity between users is calculated; and the first k similar users are selected for a target user. According to the invention, potential friends of the same life pattern as the user can be discovered for the user; the number of the candidate services is increased; the problem of data sparsity is effectively solved; the service experience quality of the user is improved; and useful solutions are provided for user personalized service recommendation in future location-based social networks.
Description
Technical field
The present invention relates to network communication field, send out particularly to a kind of potential good friend based on motion track pattern
Existing method and system.
Background technology
In recent years, along with extensively application and popularization, the location-based social networks of various mobile terminal devices
(LBSN) develop on an unprecedented scale as Foursquare, FacebookPlace, Twitter and side, street etc. also obtain.
Location-based social networks, is characterized in utilizing the information of registering of user, by online social networks and physics
Position combines, to realize the shared and propagation of location Based service resource in virtual world.Thus,
In a mobile environment, user can obtain network service, such as in time: multimedia service, weather forecasting,
News and transport information etc. in real time.Through CISCO predictive display: by 2016, mobile data traffic will
Exceeding several Chinese mugwort byte/moon, wherein flow produced by Video service will account for the 86% of overall consumption flow.Therefore,
Substantial amounts of Internet service is pushed to user side, to be supplied to the different types of services selection of user.But,
Due to the restriction of conventional communication mode, it is interested that user often receives the information that some are useless, even user
Service is flooded by substantial amounts of network service.In this case, service recommendation system gradually rises and draws
Play the concern of many scholars.Service recommendation system can find to meet user's request in a large amount of network services
Personalized service to recommend user, and provide the service in difference in functionality and performance.
Different from Web search engine, service recommendation system is not only concerned about the relation between Search Results and order,
And the personalization preferences that difference is serviced by concerned with user.Traditional service recommendation method relies on " user-entry "
Binary group information, including collaborative filtering recommending (CF) and content-based recommendation (CBR).While it is true,
Along with being continuously increased of users ' individualized requirement, only consider user and entry relation can not accurately to
Family provides suitably service.Therefore, when user asks service, contextual information is (such as: time, position
Put, social relations, environment, emotion and network state etc.) need to be taken into account, constituting " user-
Context-entry " triplet information.Further, along with the continuous change of contextual information, context-aware
Service recommendation system (CARS) automatic, personalized services selection can be provided the user.Such as:
User A likes browsing its novel interested on bus rather than in office；User B likes
When After Hours searching related promotion advertising message rather than be on duty.Therefore, how contextual information is passed through
The personalization preferences of digging user, becomes an important research target of service recommendation system.
Similar users is the discovery that a critical workflow of service recommendation system.In location-based social networks,
Server collected, by " check-in " service, the location history information that each user is daily, thus utilized ground
Relation between reason space and semantic space, extracts living habit and the pattern of user.For GPS track number
According to collection, due to its space complexity and time continuity, by traditional data mining technology (such as: hurricane
Wind is followed the tracks of and animal activity behavior) it is difficult to extract the living habit of user.The more important thing is, different visits
Ask that position sequence can reflect the wish that user is different, and the user of different geographic regions may have identical
Wish.Motion track pattern refers to be made up of in a certain order the semantic information of a series of positions
Group sequence, it can describe rule of life and the preference of user effectively.Such as: if the day of a user
Often activity command is " shopping " → " having a meal " → " seeing a film ", then his/her motion track pattern is permissible
It is extracted as " market " → " restaurant " → " cinema ".Therefore, from the angle of motion track pattern,
By comparing the trajectory model similarity between user, find its potential good friend for targeted customer, will be for future
In location-based social networks, user individual service recommendation provides useful resolving ideas.
Summary of the invention
In order to find the potential good friend identical with user's life pattern, increase the number of candidate service, improve and use
The service experience quality at family, the invention provides a kind of potential good friend based on motion track pattern and finds method
And system.Described technical scheme is as follows:
A kind of potential good friend based on motion track pattern finds that method, described method include:
Set up semantic description model, describe the semantic information of each dwell point according to POI data collection, and right
Each class service is weighted；
According to the distribution situation of dwell point, it is position by dwell point cluster, and describes the semanteme of each position
Information, generates continuous print kind track sets；
According to the kind track sets generated, extract kind trajectory model CTP common between user；
Calculate the similarity between user, user is ranked up by similarity, selects front k for targeted customer
Individual similar users.
Described semantic description model includes:
Represent the set of dwell point with S, calculate a dwell point siCoordinate, obtain the rail being made up of dwell point
Mark；
Calculate the kind weight of dwell point, obtain the dwell point characteristic vector about kind.
Described method also includes:
Initialize dwell point set, calculate the length of motion track；
Judge whether the distance between any two points is less than threshold values, and whether the time is more than threshold values, if it does not,
Then delete.
Calculate the coordinate of Centroid；
This Centroid is added to dwell point set.
Described kind track describes method and includes:
It is position by dwell point cluster, obtains location track sequence；
Utilize the number of the non-zero weight value of each type in dwell point, calculate the POI kind corresponding to position
Weight, obtain the position characteristic vector about kind；
The characteristic vector of cluster position, makes each position be divided into different kinds, obtains kind track
Sequence.
Described method also includes:
Initialized location set, calculates the element number in dwell point set；
Create a position, dwell point is joined in this position, and calculate position coordinates；
Judge whether dwell point is more than threshold values to the distance of position, if it is, create next position, will
Dwell point joins in this position, calculates position coordinates, if it is not, then dwell point to be joined this position,
Update position coordinates；
This position is added to location sets.
Described common locus schema extraction method includes:
Initialize trajectory model set, the length of definition subsequence；
Retrieve each node in two user semantic tracks；
Judge that two semantic points are the most identical, if it is not, then delete, continue retrieval, if it is, under carrying out
One step；
The position of this point of labelling, begins look for the subsequence whether having specific length threshold values from this point, if it does not,
Then delete, continue retrieval, if it is, this subsequence is added to trajectory model set.
Described similar users finds that method includes:
By the common locus pattern extracted, in terms of genre popularity and active sequences two, calculate user
Between similarity；
By user by similarity by sorting from big to small, thus pick out front k similar users for targeted customer.
A kind of potential good friend based on motion track pattern finds that system, described system include that dwell point detects mould
Block, dwell point semantic description module, position detecting module, position semantic description module, common locus pattern
Extraction module and similar users discovery module, wherein,
Described dwell point detection module, is used for detecting in original GPS track data, and existing having is certain
The point of resident behavior；
Described dwell point semantic description module, for carrying out the description of semantic information to the dwell point detected；
Described position detecting module, is used for detecting in dwell point data, existing reflection user's mobile behavior
Point；
Described position semantic description module, for carrying out the description of semantic information to the position detected；
Described common locus schema extraction module, for extracting rail common between user from semantic track
Mark pattern；
Described similar users discovery module, for calculating the similarity between user, and selects for targeted customer
Front k similar users.
The technical scheme that the embodiment of the present invention provides has the benefit that
Set up semantic description model, describe the semantic information of each dwell point according to POI data collection, and right
Each class service is weighted, and according to the distribution situation of dwell point, is position by dwell point cluster, and describes
The semantic information of each position, generates continuous print kind track sets, according to the kind track sets generated,
Extract kind track subsequence CTP common between user, calculate the similarity between user, use for target
Front k similar users is selected at family.The scheme that the embodiment of the present invention provides, can be to the user discover that to live with it
The potential good friend that pattern is identical, increases the number of candidate service, effectively solves Deta sparseness problem, simultaneously
Improve the service experience quality of user, for user individual service recommendation in following location-based social networks
Useful resolving ideas is provided.
Accompanying drawing explanation
Fig. 1 is that based on motion track pattern the potential good friend that the embodiment of the present invention one provides finds Method And Principle
Flow chart；
Fig. 2 is the dwell point detection algorithm schematic diagram that the embodiment of the present invention one provides；
Fig. 3 is the detection algorithm schematic diagram that the embodiment of the present invention one provides.
Fig. 4 is the common locus schema extraction algorithm schematic diagram that the embodiment of the present invention one provides.
Fig. 5 is that based on motion track pattern the potential good friend that the embodiment of the present invention two provides finds system structure
Schematic diagram.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Embodiment is described in further detail.
The present invention proposes a kind of potential good friend based on motion track pattern and finds method, by the geography of user
Positional information is mapped as semantic description information, the interest of digging user, preference and personal lifestyle custom, mesh
Be for the user discover that the potential good friend identical with its life pattern, increase candidate service number, efficient solution
Certainly Sparse sex chromosome mosaicism, improves the service experience quality of user, for following location-based social network simultaneously
In network, user individual service recommendation provides useful resolving ideas.
The semantic description model that the present invention provides, describes the semantic letter of each dwell point according to POI data collection
Breath, and each class service is weighted, further according to the distribution situation of dwell point, it is position by dwell point cluster
Put, and describe the semantic information of each position, generate continuous print kind track sets, further according to generate
Kind track sets, extracts kind track subsequence CTP common between user, calculates the phase between user
Like degree, select front k similar users for targeted customer.
Embodiment one
As it is shown in figure 1, based on motion track pattern the potential good friend side of discovery provided for the embodiment of the present invention
Method principle flow chart, wherein,
Step 10, sets up semantic description model, describes the semantic letter of each dwell point according to POI data collection
Breath, and each class service is weighted.
In the track data that user is original, each geographical position moved may be regarded as having through
The point of latitude information.The definition of dwell point is: dwell point represents a region, stops at this district's intra domain user
Stay a period of time, and do a significant activity.A kind of situation is that user enters into a satellite
In the building that signal is weak, such as: shopping center, cinema, theater or museum etc.；Another kind of situation
It is that user stays outside geographic area, but is not passed through this region, such as: sightseeing tour.
The set of dwell point, a dwell point s is represented with SiCan be expressed as:
Wherein pjAnd p (lon)j(lat) each original point p is represented respectivelyjLongitude and latitude, be made up of dwell point
Track is expressed as Tra_s=s1→s2→…→sn。
For interest and the preference of digging user, only know that user's event trace on geographical space is inadequate
, semantic space can describe the semantic information corresponding to each geographical position, and is got by utilization
Semantic information, the present invention can excavate live in different geographic regions, there is identical semantic information
Similar users.POI identifies service name, classification and the longitude and latitude that each geographical position point is had
Information, by TF-IDF algorithm, the weight of the POI kind corresponding to dwell point can be calculated as:
Wherein, N represents the total POI number existed in this region, niRepresent the POI number of type i, Si
Represent the dwell point set of type i.
The characteristic vector of each dwell point can be expressed as fs=＜ w1,w2,...,wn＞, thus dwell point is endowed
Certain semantic information.
Concrete dwell point detection algorithm as in figure 2 it is shown, wherein,
1) initialize dwell point set, calculate the length of motion track.
2) judge whether the distance between any two points is less than threshold values, and whether the time is more than threshold values, if it does not,
Then return to 1).
3) coordinate of Centroid is calculated.
4) this Centroid is added to dwell point set.
Step 20, according to the distribution situation of dwell point, is position by dwell point cluster, and describes each position
The semantic information put, generates continuous print kind track sets.
Dwell point can not distinguish the behavior that user is had in a semantic space sometimes completely, such as: two
Individual different dwell point, lays respectively at two different spaces for activities of Tsing-Hua University, but the two stops
Point belongs to identical semantic description category.In order to set up unified behavior description information to each user, this
Bright utilize following formula by dwell point cluster be position:
The location track sequence of one user can be expressed as Tra_L=L1→L2→…→Ln, each position
L represents a geographic area, comprises the dwell point in some semantic spaces in this region, such as: market,
Cinema etc..The similar dwell point of different user is assigned to identical position LiIn, thus be user behavior
Description method provides standard uniformly.
Concrete detection algorithm as it is shown on figure 3, wherein,
1) initialized location set, calculates the element number in dwell point set.
2) create a position, dwell point is joined in this position, and calculate position coordinates.
3) judge whether dwell point is more than threshold values to the distance of position, if it is, create next position,
Dwell point is joined in this position, calculate position coordinates, if it is not, then dwell point to be joined this position,
Update position coordinates.
4) this position is added to location sets.
Semantic information based on the dwell point calculated in step 10, position LiSemantic information can by its wrap
The semantic information integrative of the dwell point contained represents.Such as: containing type i and the stop of type j in a position
Point, more can accurately describe this position by the information of i and j.
Utilize the number of the non-zero weight value of each type in dwell point, the power of the POI kind corresponding to position
Weight can be calculated as:
Wherein, fsRepresenting the characteristic vector of dwell point, the characteristic vector of each position can be expressed as
FL=< W1,W2,...,Wk>。
By cluster feature vector, each position is divided into different kinds, and the kind of this user
Class track sets can be expressed as Tra_C=C1→C2→…→Cn, thus construct user's motion track model.
Step 30, according to the kind track sets generated, extracts kind trajectory model CTP common between user.
Utilizing user's motion track model that step 20 provides, the present invention can extract between each user jointly
Kind track subsequence CTP, it is contemplated that the sequence of one or two different kinds compositions cannot be fine
The activity pattern of ground user anyway, present invention provide that the length of subsequence is not less than 3.
Concrete common locus schema extraction algorithm as shown in Figure 4, wherein,
1) trajectory model set is initialized, the length of definition subsequence.
2) each node in two user semantic tracks of retrieval.
3) judge that two semantic points are the most identical, if it is not, then return to 2) continue retrieval, if it is,
Carry out next step.
4) position of this point of labelling, begins look for the subsequence whether having specific length threshold values from this point, if
No, then return to 2) continue retrieval, if it is, added to trajectory model set by this subsequence.
Step 40, calculates the similarity between user, user is ranked up by similarity, for targeted customer
Select front k similar users.
By common locus schema extraction algorithm, the CTP between user can be extracted, thus calculate
The similarity of user.Different from traditional similarity calculating method, present invention primarily contemplates two aspects:
First, genre popularity, the personalization preferences of its reflection user.Genre popularity is the highest, and institute can body
Existing user's similarity is the lowest.Therefore, each Type C in CTPkSimilarity can be calculated as:
Wherein, pop (Ck) represent Type CkPopularity, and the IDF that this value is referred in step 10
Value.
Second, active sequences, represent user and access the order of position.Based on the CTP extracted, each height
The similarity of sequence can be calculated as:
Wherein, m represents user u1And u2In the length of the longest CTP, am=2m-1。
Therefore, two user u1And u2Similarity may be calculated:
Wherein, N1And N2Represent user u respectively1And u2Access the number of position.
Finally, by sim (u1,2) value by sorting from big to small, the present invention can be that targeted customer picks out
Front k similar users.
Embodiment two
Find as it is shown in figure 5, embodiments provide a kind of potential good friend based on motion track pattern
System, including dwell point detection module 100, dwell point semantic description module 200, position detecting module 300,
Position semantic description module 400, common locus schema extraction module 500 and similar users discovery module 600,
Specific as follows:
Dwell point detection module 100, is used for detecting in original GPS track data, and existing having is certain
The point of resident behavior；
Dwell point semantic description module 200, for carrying out the description of semantic information to the dwell point detected；
Position detecting module 300, is used for detecting in dwell point data, existing reflection user's mobile behavior
Point；
Position semantic description module 400, for carrying out the description of semantic information to the position detected；
Common locus schema extraction module 500, for extracting track common between user from semantic track
Pattern；
Similar users discovery module 600, for calculating the similarity between user, and before selecting for targeted customer
K similar users.
It should be understood that based on motion track pattern the potential good friend that above-described embodiment provides finds system
When selecting similar users, only it is illustrated with the division of above-mentioned each functional module, in actual application,
As desired above-mentioned functions distribution can be completed by different functional modules, will the internal structure of device
It is divided into different functional modules, to complete all or part of function described above.It addition, above-mentioned reality
The data transmission device that executing example provides belongs to same design with data transmission method embodiment, and it implemented
Journey refers to embodiment of the method, repeats no more here.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
In sum, in embodiments of the present invention, set up semantic description model, describe according to POI data collection
The semantic information of each dwell point, and each class service is weighted, according to the distribution situation of dwell point,
It is position by dwell point cluster, and describes the semantic information of each position, generate continuous print kind track sequence
Row, according to the kind track sets generated, extract kind track subsequence CTP common between user, meter
Calculate the similarity between user, select front k similar users for targeted customer.The embodiment of the present invention provides
Scheme can be to the user discover that the potential good friend identical with its life pattern, increases the number of candidate service, has
Effect solves Sparse sex chromosome mosaicism, improves the service experience quality of user, for following location-based society simultaneously
User individual service recommendation in network is handed over to provide useful resolving ideas.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can be passed through
Hardware completes, it is also possible to instructing relevant hardware by program and complete, described program can be stored in
In a kind of computer-readable recording medium, storage medium mentioned above can be read only memory, disk or
CD etc..
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all the present invention's
Within spirit and principle, any modification, equivalent substitution and improvement etc. made, should be included in the present invention's
Within protection domain.
Claims (8)
1. a potential good friend based on motion track pattern finds method, it is characterised in that described method bag
Include:
Set up semantic description model, describe the semantic information of each dwell point according to POI data collection, and right
Each class service is weighted；
According to the distribution situation of dwell point, it is position by dwell point cluster, and describes the semanteme of each position
Information, generates continuous print kind track sets；
According to the kind track sets generated, extract kind trajectory model CTP common between user；
Calculate the similarity between user, user is ranked up by similarity, selects front k for targeted customer
Individual similar users.
2. the method for claim 1, it is characterised in that described semantic description model includes:
Represent the set of dwell point with S, calculate a dwell point siCoordinate, obtain the rail being made up of dwell point
Mark；
Calculate the kind weight of dwell point, obtain the dwell point characteristic vector about kind.
3. method as claimed in claim 2, it is characterised in that described method also includes:
Initialize dwell point set, calculate the length of motion track；
Judge whether the distance between any two points is less than threshold values, and whether the time is more than threshold values, if it does not,
Then delete；
Calculate the coordinate of Centroid；
This Centroid is added to dwell point set.
4. the method for claim 1, it is characterised in that described kind track describes method and includes:
It is position by dwell point cluster, obtains location track sequence；
Utilize the number of the non-zero weight value of each type in dwell point, calculate the POI kind corresponding to position
Weight, obtain the position characteristic vector about kind；
The characteristic vector of cluster position, makes each position be divided into different kinds, obtains kind track
Sequence.
5. method as claimed in claim 4, it is characterised in that described method also includes:
Initialized location set, calculates the element number in dwell point set；
Create a position, dwell point is joined in this position, and calculate position coordinates；
Judge whether dwell point is more than threshold values to the distance of position, if it is, create next position, will
Dwell point joins in this position, calculates position coordinates, if it is not, then dwell point to be joined this position,
Update position coordinates；
This position is added to location sets.
6. the method for claim 1, it is characterised in that described common locus schema extraction method bag
Include:
Initialize trajectory model set, the length of definition subsequence；
Retrieve each node in two user semantic tracks；
Judge that two semantic points are the most identical, if it is not, then delete, continue retrieval, if it is, under carrying out
One step；
The position of this point of labelling, begins look for the subsequence whether having specific length threshold values from this point, if it does not,
Then delete, continue retrieval, if it is, this subsequence is added to trajectory model set.
7. the method for claim 1, it is characterised in that described similar users finds that method includes:
By the common locus pattern extracted, in terms of genre popularity and active sequences two, calculate user
Between similarity；
By user by similarity by sorting from big to small, thus pick out front k similar users for targeted customer.
8. a potential good friend based on motion track pattern finds system, it is characterised in that described system bag
Include dwell point detection module, dwell point semantic description module, position detecting module, position semantic description module,
Common locus schema extraction module and similar users discovery module, wherein,
Described dwell point detection module, is used for detecting in original GPS track data, and existing having is certain
The point of resident behavior；
Described dwell point semantic description module, for carrying out the description of semantic information to the dwell point detected；
Described position detecting module, is used for detecting in dwell point data, existing reflection user's mobile behavior
Point；
Described position semantic description module, for carrying out the description of semantic information to the position detected；
Described common locus schema extraction module, for extracting rail common between user from semantic track
Mark pattern；
Described similar users discovery module, for calculating the similarity between user, and selects for targeted customer
Front k similar users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610293497.XA CN106022934A (en) | 2016-05-05 | 2016-05-05 | Potential friend discovering method based on moving trajectory pattern and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610293497.XA CN106022934A (en) | 2016-05-05 | 2016-05-05 | Potential friend discovering method based on moving trajectory pattern and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106022934A true CN106022934A (en) | 2016-10-12 |
Family
ID=57081791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610293497.XA Pending CN106022934A (en) | 2016-05-05 | 2016-05-05 | Potential friend discovering method based on moving trajectory pattern and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106022934A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106506705A (en) * | 2016-12-29 | 2017-03-15 | 平安科技（深圳）有限公司 | Listener clustering method and device based on location-based service |
| CN107784046A (en) * | 2016-11-14 | 2018-03-09 | 平安科技（深圳）有限公司 | POI treating method and apparatus |
| CN108108749A (en) * | 2017-12-12 | 2018-06-01 | 杭州电子科技大学 | A kind of friend recommendation method based on user's similarity |
| CN108170834A (en) * | 2018-01-12 | 2018-06-15 | 南京理工大学 | A kind of determining method of mobile target association co-occurrence pattern |
| CN108241630A (en) * | 2016-12-23 | 2018-07-03 | 武汉四维图新科技有限公司 | Recommend method and device in a kind of driving destination |
| 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 |
| CN109446186A (en) * | 2018-09-27 | 2019-03-08 | 江苏大学 | A kind of social relationships judgment method based on motion track |
| CN109558961A (en) * | 2017-09-25 | 2019-04-02 | 阿里巴巴集团控股有限公司 | Determine method and system, storage medium, processor and the device of location information |
| CN110515981A (en) * | 2018-05-21 | 2019-11-29 | 国家计算机网络与信息安全管理中心 | A kind of user identification method and device based on space-time trajectory |
| CN111104468A (en) * | 2019-09-25 | 2020-05-05 | 西安交通大学 | Method for deducing user activity based on semantic track |
| CN111368211A (en) * | 2020-02-20 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Relation chain determining method, device and storage medium |
| CN113032567A (en) * | 2021-03-29 | 2021-06-25 | 广东众聚人工智能科技有限公司 | Position embedding interpretation method and device, computer equipment and storage medium |
| CN113468194A (en) * | 2021-07-02 | 2021-10-01 | 广东蕾特恩科技发展有限公司 | Customer relationship management data updating system and method based on big data |
| WO2021259007A1 (en) * | 2020-06-24 | 2021-12-30 | 平安科技（深圳）有限公司 | Data pushing method and system based on behavior trajectory, and computer device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880719A (en) * | 2012-10-16 | 2013-01-16 | 四川大学 | User trajectory similarity mining method for location-based social network |
| CN104965913A (en) * | 2015-07-03 | 2015-10-07 | 重庆邮电大学 | GPS (global positioning system) geographic position data mining based user classification method |
| CN105243148A (en) * | 2015-10-25 | 2016-01-13 | 西华大学 | Checkin data based spatial-temporal trajectory similarity measurement method and system |
| CN105243128A (en) * | 2015-09-29 | 2016-01-13 | 西华大学 | Sign-in data based user behavior trajectory clustering method |
| CN105389332A (en) * | 2015-10-13 | 2016-03-09 | 广西师范学院 | Geographical social network based user similarity computation method |
-
2016
- 2016-05-05 CN CN201610293497.XA patent/CN106022934A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880719A (en) * | 2012-10-16 | 2013-01-16 | 四川大学 | User trajectory similarity mining method for location-based social network |
| CN104965913A (en) * | 2015-07-03 | 2015-10-07 | 重庆邮电大学 | GPS (global positioning system) geographic position data mining based user classification method |
| CN105243128A (en) * | 2015-09-29 | 2016-01-13 | 西华大学 | Sign-in data based user behavior trajectory clustering method |
| CN105389332A (en) * | 2015-10-13 | 2016-03-09 | 广西师范学院 | Geographical social network based user similarity computation method |
| CN105243148A (en) * | 2015-10-25 | 2016-01-13 | 西华大学 | Checkin data based spatial-temporal trajectory similarity measurement method and system |
Non-Patent Citations (1)
| Title |
|---|
| XIANGYE XIAO 等: "Finding Similar User Using Category-Based Location History", 《GIS"10》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784046A (en) * | 2016-11-14 | 2018-03-09 | 平安科技（深圳）有限公司 | POI treating method and apparatus |
| CN107784046B (en) * | 2016-11-14 | 2021-05-04 | 平安科技（深圳）有限公司 | POI information processing method and device |
| CN108241630A (en) * | 2016-12-23 | 2018-07-03 | 武汉四维图新科技有限公司 | Recommend method and device in a kind of driving destination |
| CN106506705B (en) * | 2016-12-29 | 2020-07-28 | 平安科技（深圳）有限公司 | Crowd classification method and device based on location service |
| CN106506705A (en) * | 2016-12-29 | 2017-03-15 | 平安科技（深圳）有限公司 | Listener clustering method and device based on location-based service |
| CN109558961A (en) * | 2017-09-25 | 2019-04-02 | 阿里巴巴集团控股有限公司 | Determine method and system, storage medium, processor and the device of location information |
| CN108108749B (en) * | 2017-12-12 | 2020-01-17 | 杭州电子科技大学 | Friend recommendation method based on user similarity |
| CN108108749A (en) * | 2017-12-12 | 2018-06-01 | 杭州电子科技大学 | A kind of friend recommendation method based on user's similarity |
| CN108170834A (en) * | 2018-01-12 | 2018-06-15 | 南京理工大学 | A kind of determining method of mobile target association co-occurrence pattern |
| CN108170834B (en) * | 2018-01-12 | 2022-03-25 | 南京理工大学 | Method for determining correlation co-occurrence mode of moving target |
| CN110515981A (en) * | 2018-05-21 | 2019-11-29 | 国家计算机网络与信息安全管理中心 | A kind of user identification method and device based on space-time trajectory |
| CN110515981B (en) * | 2018-05-21 | 2022-04-12 | 国家计算机网络与信息安全管理中心 | User identification method and device based on space-time trajectory |
| 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 |
| CN109446186B (en) * | 2018-09-27 | 2021-07-20 | 江苏大学 | Social relation judgment method based on movement track |
| CN109446186A (en) * | 2018-09-27 | 2019-03-08 | 江苏大学 | A kind of social relationships judgment method based on motion track |
| CN111104468A (en) * | 2019-09-25 | 2020-05-05 | 西安交通大学 | Method for deducing user activity based on semantic track |
| CN111104468B (en) * | 2019-09-25 | 2023-03-28 | 西安交通大学 | Method for deducing user activity based on semantic track |
| CN111368211A (en) * | 2020-02-20 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Relation chain determining method, device and storage medium |
| CN111368211B (en) * | 2020-02-20 | 2023-05-16 | 腾讯科技（深圳）有限公司 | Relation chain determining method, device and storage medium |
| WO2021259007A1 (en) * | 2020-06-24 | 2021-12-30 | 平安科技（深圳）有限公司 | Data pushing method and system based on behavior trajectory, and computer device |
| CN113032567A (en) * | 2021-03-29 | 2021-06-25 | 广东众聚人工智能科技有限公司 | Position embedding interpretation method and device, computer equipment and storage medium |
| CN113032567B (en) * | 2021-03-29 | 2022-03-29 | 广东众聚人工智能科技有限公司 | Position embedding interpretation method and device, computer equipment and storage medium |
| CN113468194A (en) * | 2021-07-02 | 2021-10-01 | 广东蕾特恩科技发展有限公司 | Customer relationship management data updating system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106022934A (en) | Potential friend discovering method based on moving trajectory pattern and system | |
| US11055325B2 (en) | System and method for context enhanced mapping | |
| Yin et al. | Modeling location-based user rating profiles for personalized recommendation | |
| Yin et al. | Joint modeling of user check-in behaviors for real-time point-of-interest recommendation | |
| Yin et al. | LCARS: A spatial item recommender system | |
| Li et al. | Multiple location profiling for users and relationships from social network and content | |
| US10332150B2 (en) | Location event advertising | |
| Zhao et al. | Personalized recommendations of locally interesting venues to tourists via cross-region community matching | |
| US8108778B2 (en) | System and method for context enhanced mapping within a user interface | |
| US20150112963A1 (en) | Time and location based information search and discovery | |
| Jiang et al. | Learning from contextual information of geo-tagged web photos to rank personalized tourism attractions | |
| CN106021305A (en) | Mode and preference sensing POI recommendation method and system | |
| US20110087685A1 (en) | Location-based service middleware | |
| Arain et al. | Intelligent travel information platform based on location base services to predict user travel behavior from user-generated GPS traces | |
| CN109918573A (en) | A kind of personalized circuit recommendation system and method based on position social networks | |
| CN106605418A (en) | Power management of mobile clients using location-based services | |
| Xu et al. | A dynamic topic model and matrix factorization-based travel recommendation method exploiting ubiquitous data | |
| KR20080007437A (en) | Virtual earth | |
| CN102939604A (en) | Method and apparatus for context-indexed network resources | |
| WO2009158168A2 (en) | System and method for determination and display of personalized distance | |
| Zhu et al. | SEM-PPA: A semantical pattern and preference-aware service mining method for personalized point of interest recommendation | |
| Liu et al. | Where your photo is taken: Geolocation prediction for social images | |
| Zhang et al. | A context-awareness personalized tourist attraction recommendation algorithm | |
| Umair et al. | Discovering personal places from location traces | |
| Reddy et al. | An enhanced travel package recommendation system based on location dependent social 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |
|
| RJ01 | Rejection of invention patent application after publication |