CN107798557A - Electronic installation, the service location based on LBS data recommend method and storage medium - Google Patents
Electronic installation, the service location based on LBS data recommend method and storage medium Download PDFInfo
- Publication number
- CN107798557A CN107798557A CN201710916517.9A CN201710916517A CN107798557A CN 107798557 A CN107798557 A CN 107798557A CN 201710916517 A CN201710916517 A CN 201710916517A CN 107798557 A CN107798557 A CN 107798557A
- Authority
- CN
- China
- Prior art keywords
- user
- predetermined
- data
- service location
- lbs
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
-
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0261—Targeted advertisements based on user location
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Signal Processing (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of service location based on LBS data to recommend method.This method includes：Each user corresponding LBS data in preset time are obtained from predetermined database, cluster analysis are carried out to the LBS data of acquisition, to analyze at least one action trail data corresponding to each user respectively；The action trail data of each user are analyzed, the similarity between each user is obtained with analysis；Based on the similarity between each user, each user is clustered, to obtain different user groups；Analyze the LBS data of all users in same user group, to analyze the action trail of all user preferences in the user group, and the service location that the action trail based on all user preferences analyzed is sent to predetermined terminal on the action trail for the user being directed in the user group recommends instruction.The present invention, which can provide the user, more accurately to be recommended, while improves the accuracy of LBS data applications.
Description
Technical field
The present invention relates to internet data process field, more particularly to a kind of electronic installation, the service field based on LBS data
Recommended method and storage medium.
Background technology
With the development of internet, the interest of user is more and more extensive, and with user's local environment and living standard
Change, the demand of user is also changing.Therefore, the behavior of user how is more fully understood and analyzed, provides the user pin
Service to its demand becomes most important.
At present, the application based on LBS (Location Based Services, location Based service) data is only limitted to
The geography information around the place where judging user is analyzed according to the current LBS data of the mobile terminal user got,
And combine the geography information around user and recommend the corresponding commodity of surrounding to user.For example, find the current geographic of cellphone subscriber
Position is certain street in Shanghai City, then fixed in the street square kilometre in the range of it is 1 public at searching mobile phone user current location
In the service location such as hotel in scope, movie theatre, library, gas station title and address, and recommend the user.It is this to push away
It is very convenient to recommend mode, but for application is upper, it is impossible to the demand of user is fully met, and the service location recommended is not necessarily
It is that user is badly in need of.Therefore, there is certain limitation.
The content of the invention
In view of this, the present invention proposes that a kind of electronic installation, the service location based on LBS data recommend method and storage to be situated between
Matter, the LBS data analyses of magnanimity can be utilized to draw the action trail of user preference, and the action trail based on user preference enters
Row service location is recommended, and improves the accuracy of recommendation, and improve the limitation to LBS data applications.
First, to achieve the above object, the present invention proposes a kind of electronic installation, and the electronic installation includes memory, place
Reason device and the service location based on LBS data that is stored on the memory and can run on the processor recommend system
System, it is described based on the service location commending system of LBS data by the computing device when realize following steps：
A, service location recommendation if desired is carried out to each predetermined user, or, if receiving one in advance really
The service location recommendation request that the terminal of fixed user is sent, then obtained from predetermined database each predetermined
User's corresponding LBS data in preset time, the LBS using predetermined first clustering algorithm to each user of acquisition
Data carry out cluster analysis, to analyze at least one action trail data corresponding to each user respectively；
B, according to the action trail data of the predetermined each user of similarity analysis rule analysis, obtained with analysis each
Similarity between individual user；
C, based on the similarity between each user, each user is gathered using predetermined second clustering algorithm
Class, to obtain different user groups, the similarity is more than the user point of predetermined threshold value to same user group, described similar
User point extremely different user group of the degree less than or equal to predetermined threshold value；
D, the user group belonging to each predetermined user is analyzed using predetermined service location recommended models
In all users LBS data, analyze the action trail of each predetermined user preference, and to predetermined terminal
Send the service location on the action trail of each predetermined user preference recommendation instruction, or, using predefine
The analysis of service location recommended models send the LBS numbers of all users in user group belonging to the user of the recommendation request
According to determining the action trail of the user preference, and send on the action trail of the user preference to predetermined terminal
The recommendation instruction of service location.
Further, the predetermined database includes obtaining from the positioning service system of all mobile terminal users
The running fix data and the service data related to position of offer got, the LBS data include geographical location information number
According to and all kinds of service datas related to the geographical location information data that provide, the action trail data include stroke
Type track data and/or, types of entertainment track data；The travel type track data includes journey time and stroke mark
Know, the types of entertainment track data includes playtime and address identifies.
Further, predetermined first clustering algorithm includes density-based algorithms；It is described true in advance
Fixed similarity analysis rule includes cosine angle analogue method, euclidean distance metric method or Pearson correlation coefficient method；Institute
State predetermined second clustering algorithm include the object function clustering algorithm based on original shape, density-based algorithms or
Clustering algorithm based on level.
Further, the predetermined service location recommended models are collaborative filtering recommending model.
Further, it is described also to be realized such as during the computing device based on the service location commending system of LBS data
Lower step：
Tracking receives the LBS data for the user for recommending instruction, and analyzes the LBS data of the user traced into being recommended
The user preference action trail on service location between matching degree, if the LBS data of the user traced into are with being pushed away
The matching degree between service location on the action trail for the user preference recommended is less than or equal to default matching threshold, then weighs
Step B and step C is performed again.
In addition, to achieve the above object, the present invention also provides a kind of service location based on LBS data and recommends method, should
Method comprises the following steps：
S1, service location recommendation is if desired carried out to each predetermined user, or, if receiving one in advance really
The service location recommendation request that the terminal of fixed user is sent, then obtained from predetermined database each predetermined
User's corresponding LBS data in preset time, the LBS using predetermined first clustering algorithm to each user of acquisition
Data carry out cluster analysis, to analyze at least one action trail data corresponding to each user respectively；
S2, the action trail data according to the predetermined each user of similarity analysis rule analysis, obtained with analysis
Similarity between each user；
S3, based on the similarity between each user, each user is carried out using predetermined second clustering algorithm
Cluster, to obtain different user groups, the similarity is more than the user point extremely same user group of predetermined threshold value, the phase
Like user point extremely different user group of the degree less than or equal to predetermined threshold value；
S4, the user group belonging to using each predetermined user of predetermined service location recommended models analysis
In all users LBS data, analyze the action trail of each predetermined user preference, and to predetermined terminal
Send the service location on the action trail of each predetermined user preference recommendation instruction, or, using predefine
The analysis of service location recommended models send the LBS numbers of all users in user group belonging to the user of the recommendation request
According to determining the action trail of the user preference, and send on the action trail of the user preference to predetermined terminal
The recommendation instruction of service location.
Further, the predetermined database includes obtaining from the positioning service system of all mobile terminal users
The running fix data and the service data related to position of offer got, the LBS data include geographical location information number
According to and all kinds of service datas related to the geographical location information data that provide, the action trail data include stroke
Type track data and/or, types of entertainment track data；The travel type track data includes journey time and stroke mark
Know, the types of entertainment track data includes playtime and address identifies.
Further, predetermined first clustering algorithm includes density-based algorithms；It is described true in advance
Fixed similarity analysis rule includes cosine angle analogue method, euclidean distance metric method or Pearson correlation coefficient method；Institute
State predetermined second clustering algorithm include the object function clustering algorithm based on original shape, density-based algorithms or
Clustering algorithm based on level.
Further, the predetermined service location recommended models are collaborative filtering recommending model.
Further, to achieve the above object, the present invention also provides a kind of computer-readable recording medium, the computer
Readable storage medium storing program for executing is stored with the service location commending system based on LBS data, and the service location based on LBS data is recommended
System can be by least one computing device, so that clothes of at least one computing device described above based on LBS data
The step of place recommendation method of being engaged in.
Compared to prior art, method and meter are recommended in electronic installation proposed by the invention, the individual character family based on LBS data
Calculation machine readable storage medium storing program for executing, first, each user corresponding LBS numbers in preset time are obtained from predetermined database
According to the LBS data progress cluster analysis to acquisition, to analyze at least one action trail corresponding to each user's difference respectively
Data；Secondly, the action trail data of each user are analyzed, the similarity between each user is obtained with analysis；Again, it is based on
Similarity between each user, each user is clustered, to obtain different user groups；Finally, same use is analyzed
The LBS data of all users in the colony of family, to analyze the action trail of all user preferences in the user group, and it is based on dividing
The action trail of all user preferences separated out, the behavior for the user being directed in the user group is sent to predetermined terminal
Service location on track recommends instruction.So, the disadvantage of the limitation to LBS data applications in the prior art can both be avoided
End, the accuracy of recommendation can also be improved.
Brief description of the drawings
Fig. 1 is each optional application environment schematic diagram of embodiment one of the present invention；
Fig. 2 is the schematic diagram of one optional hardware structure of electronic installation in Fig. 1；
Fig. 3 is the program module schematic diagram of service location commending system one embodiment of the invention based on LBS data；
Fig. 4 is the program module schematic diagram of service location commending system another embodiment of the invention based on LBS data；
Fig. 5 is the implementation process diagram that service location of the present invention based on LBS data recommends the embodiment of method one；
Fig. 6 is the implementation process diagram that service location of the present invention based on LBS data recommends another embodiment of method.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.Based on the embodiment in the present invention, those of ordinary skill in the art are not before creative work is made
The every other embodiment obtained is put, belongs to the scope of protection of the invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is only used for describing purpose, and can not
It is interpreted as indicating or implies its relative importance or imply the quantity of the technical characteristic indicated by indicating.Thus, define " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical scheme
With reference to occurring conflicting or will be understood that the combination of this technical scheme is not present when can not realize, also not in application claims
Protection domain within.
As shown in fig.1, it is each optional application environment schematic diagram of embodiment one of the present invention.
In the present embodiment, present invention can apply to include but not limited to, mobile terminal 1, electronic installation 2, network 3
Application environment in.
Wherein, mobile terminal 1 can be mobile phone, smart phone, notebook computer, digit broadcasting receiver, PDA
The removable of (personal digital assistant), PAD (tablet personal computer), PMP (portable media player), guider etc. sets
It is standby, and the fixed terminal of such as digital TV, desktop computer, notebook, server etc..
Electronic installation 2 can be the meter such as rack-mount server, blade server, tower server or Cabinet-type server
Equipment is calculated, and electronic installation 2 can be the server cluster that independent server or multiple servers are formed.
Network 3 can be intranet (Intranet), internet (Internet), global system for mobile communications
(Global System of Mobile communication, GSM), WCDMA (Wideband Code
Division Multiple Access, WCDMA), 4G networks, 5G networks, bluetooth (Bluetooth), Wi-Fi etc. is wireless or has
Gauze network.
As shown in fig.2, it is the schematic diagram of 2 one optional hardware structure of electronic installation in Fig. 1.In the present embodiment, electronics
Device 2 may include, but be not limited only to, and connection memory 11, processor 12, network interface can be in communication with each other by system bus
13.It is pointed out that Fig. 2 illustrate only the electronic installation 2 with component 11-13, it should be understood that being not required for reality
All components shown are applied, the more or less component of the implementation that can be substituted.
Wherein, memory 11 comprises at least a type of readable storage medium storing program for executing, and readable storage medium storing program for executing includes flash memory, hard
Disk, multimedia card, card-type memory (for example, SD or DX memories etc.), random access storage device (RAM), static random-access
Memory (SRAM), read-only storage (ROM), Electrically Erasable Read Only Memory (EEPROM), programmable read-only storage
Device (PROM), magnetic storage, disk, CD etc..In certain embodiments, memory 11 can be deposited with the inside of electronic installation 2
Storage unit, such as the hard disk or internal memory of electronic installation 2.In further embodiments, memory 11 can also be electronic installation 2
The plug-in type hard disk being equipped with External memory equipment, such as electronic installation 2, intelligent memory card (Smart Media Card,
SMC), secure digital (Secure Digital, SD) blocks, flash card (Flash Card) etc..Certainly, memory 11 can also be both
Internal storage unit including electronic installation 2 also includes its External memory equipment.In the present embodiment, memory 11 is generally used for depositing
Storage is installed on the operating system and types of applications software of electronic installation 2, such as the service location commending system based on LBS data
200 program code etc..In addition, memory 11 can be also used for temporarily storing all kinds of numbers that has exported or will export
According to.
Processor 12 can be in certain embodiments central processing unit (Central Processing Unit, CPU),
Controller, microcontroller, microprocessor or other data processing chips.Processor 12 is generally used for controlling the total of electronic installation 2
Gymnastics is made, such as performs the control related to the progress data interaction of mobile terminal 1 or communication and processing etc..In the present embodiment,
Processor 12 is used for the program code that stores or processing data in run memory 11, for example, operation based on LBS data
Service location commending system 200 etc..
Network interface 13 may include radio network interface or wired network interface, and network interface 13 is generally used for filling in electronics
Put and communication connection is established between 2 and other electronic equipments.In the present embodiment, network interface 13 is mainly used in electricity by network 3
Sub-device 2 is connected with one or more mobile terminals 1, and number is established between electronic installation 2 and one or more mobile terminals 1
According to transmission channel and communication connection.
So far, oneself is through describing the application environment of each embodiment of the present invention and the hardware configuration and work(of relevant device in detail
Energy.Below, above-mentioned application environment and relevant device will be based on, proposes each embodiment of the present invention.
First, the present invention proposes a kind of service location commending system 200 based on LBS data.
As shown in fig.3, it is the program mould of service location commending system 200 1 embodiment of the invention based on LBS data
Block figure.In the present embodiment, the service location commending system 200 based on LBS data can be divided into one or more modules, and one
Individual or multiple modules are stored in memory 11, and by one or more processors (being processor 12 in the present embodiment) institute
Perform, to complete the present invention.For example, in figure 3, the service location commending system 200 based on LBS data, which can be divided into, to be obtained
Modulus block 201, the first analysis module 202, the analysis module 204 of cluster module 203 and second.Program mould alleged by the present invention
Block is the series of computation machine programmed instruction section for referring to complete specific function, and LBS data are based on more suitable for description than program
Implementation procedure of the service location commending system 200 in electronic installation 2.Each program module 201-204 function is put up with below
It is described in detail.
Acquisition module 201, for if desired carrying out service location recommendation to each predetermined mobile terminal user,
Or if receiving the service location recommendation request that a predetermined mobile terminal is sent, from predetermined database
It is middle to obtain each predetermined user corresponding LBS data in preset time, utilize predetermined first clustering algorithm
Cluster analysis is carried out to the LBS data of each user of acquisition, to analyze at least one behavior corresponding to each user respectively
Track data.
Wherein, LBS data include geographical location information data and provided related to geographical location information data all kinds of
Service information data, action trail data include travel type track data and/or, types of entertainment track data；Travel type
Track data includes journey time and stroke mark (for example, some period at noon often goes to certain restaurant to have lunch), amusement
Type track data includes playtime and address mark (for example, weekend goes the place tourism determined).
Generally, Mobile positioning service system is used for finding the current geographic position of mobile terminal user, and searches for from current
The title in a range of service available place in geographical position and address are (for example, hotel, movie theatre, library, gas station
Deng title and address), then recommend the related names that search and address to mobile terminal user, so that mobile terminal user
The service according to corresponding to the title and address choice of recommendation.Wherein, after mobile terminal user selects to service, Location based service
System can record user current geographic position (i.e. described geographical location information data) and selected service it is (i.e. described related
Service information data), and be stored in database.Therefore in the present embodiment, the acquisition module 201 can be from the data
Obtained in storehouse the mobile terminal user LBS data (i.e. described geographical location information data and provide with the geographical position
Put the related service information data of information data).
Then, cluster analysis is carried out to the LBS data of each user of acquisition using predetermined first clustering algorithm,
To analyze at least one action trail data corresponding to each user respectively, in the present embodiment, predetermined first cluster
Algorithm is density-based algorithms (for example, DBSCAN clustering algorithms).
Further, specific process of cluster analysis is illustrated with the user A of acquisition LBS data instances, firstly, it is necessary in advance
Core point, the reachable region of core dot density, and the boundary point of density range coverage are defined, in the present embodiment, to obtain
To a certain geographical position that often positioned within a preset time interval of user A be core point, for example, user A was at one month
Inherent 12 noon clock positioning dining room E first number has exceeded default number (20 times), then with dining room B geographical position
For core point, if if second number that geographical position F was positioned by user A is more than or waited (in one month) within the default time
In first number, then geographical position F is the point in core point B density range coverages, by each core dot density range coverage
In the region that forms of point be the reachable region of core dot density, if if geographical position G is positioned by user A within the default time
The third time number crossed is equal to first number, then geographical position G is the boundary point of density range coverage, in this manner it is possible to achieve
The place that user A was frequently positioned in preset time, and then user A action trail is obtained according to the place frequently positioned
Data, for example, some period at noon often go to certain restaurant to have lunch, or, weekend go determine place tourism etc..
First analysis module 202, for the behavior rail according to the predetermined each user of similarity analysis rule analysis
Mark data, the similarity between each user is obtained with analysis.
Wherein, predetermined similarity analysis rule can be cosine angle analogue method, Europe in various embodiments
A few Reed Distance Scaling Methods or Pearson correlation coefficient method.
For example, in one embodiment, illustrate by taking euclidean distance metric method as an example, wherein, Euclidean distance degree
Amount method calculates similarity using equation below：
It should be noted that the x and y in above-mentioned formula are respectively the vector after normalizing, the result of above-mentioned formula is
For vector x and vectorial y similarity, in the present embodiment, for example, analyzing the similarity between user A and user B, then will use
Family A action trail data obtain the primary vector in above-mentioned formula after being normalized according to default normalization mode
X, after user B action trail data are normalized according to default normalization mode, obtain in above-mentioned formula
Secondary vector y, then primary vector x and secondary vector y are substituted into the calculation formula of above-mentioned similarity respectively, user is calculated
Similarity between A and user B.
Cluster module 203, for based on the similarity between each user, utilizing predetermined second clustering algorithm pair
Each user is clustered, and to obtain different user groups, similarity is more than the user point extremely same user group of predetermined threshold value,
Similarity is less than or equal to the user point extremely different user group of predetermined threshold value.
Wherein, predetermined second clustering algorithm includes the object function clustering algorithm based on original shape (for example, k-
Means), density-based algorithms (for example, DBSCAN) or based on level clustering algorithm (for example,
Hiearchical)。
Second analysis module 204, it is each predetermined for being analyzed using predetermined service location recommended models
The LBS data of all users in user group belonging to user, the action trail of each predetermined user preference is analyzed,
And the recommendation that the service location on the action trail of each predetermined user preference is sent to predetermined terminal instructs,
Or sent in the user group belonging to the user of recommendation request and owned using the analysis of predetermined service location recommended models
The LBS data of user, the action trail of the user preference is determined, and the row of the user preference is sent to predetermined terminal
Instructed for the recommendation of the service location on track.
Wherein, predetermined service location recommended models are collaborative filtering recommending model, and service location recommended models
Foundation include the training process of model and the test process of model.
Specifically, the training process of model includes：
The LBS data samples of the similar users of predetermined number (for example, 100) are obtained, by the LBS numbers of each similar users
It is divided into the corresponding training set of first ratio and the test set of the second ratio according to sample；
Using the LBS data training service place recommendation model of each similar users in training set, to be trained
Service location recommended models；
Service location recommended models are tested using the LBS data of each similar users in test set, if test is logical
To cross, then training terminates, or, if test is not by increasing the LBS data samples of the similar users in training set and holding again
The step of above-mentioned training of row services place recommendation model.
The test process of model includes：
The LBS data of each similar users in test set are divided using the service location recommended models trained
Analysis, to draw the action trail of each similar users preference；
By the action trail of each similar users preference drawn and the action trail of the frequent activity of each similar users
Contrasted, if the action trail of corresponding preference consistent number of users corresponding with the action trail of frequent activity is more than default
Percentage threshold (for example, 70%), it is determined that the test to service location recommended models passes through, or, if the row of corresponding preference
It is less than or equal to preset percentage threshold value for track consistent number of users corresponding with the action trail of frequent activity, it is determined that right
The test of service location recommended models does not pass through.
As shown in fig.4, it is the functional module of service location commending system another embodiment of the invention based on LBS data
Figure.As shown in Figure 4, the present embodiment is compared to the embodiment shown in Fig. 3, in the present embodiment, the service location based on LBS data
Commending system can be also divided into including tracking module 205, and the tracking module 205 is used to track the use for receiving and recommending instruction
The LBS data at family, and analyze the service in the LBS data of the user traced into and the action trail for the user preference recommended
Matching degree between place, if the clothes on the action trail of the LBS data of the user traced into and the user preference recommended
Matching degree between business place is less than or equal to default matching threshold, then for the first analysis module 202 and cluster module 203
Send restarting order.
Specifically, the second analysis module 204 sends the service location behavior rail for the user to predetermined terminal
After mark recommends instruction, start-up trace module 205 tracks the LBS data of the user, and according to the LBS data of predetermined user
Mapping relations between action trail, analyze the LBS data of the user traced into and the service location behavior rail recommended
Matching degree between mark, further determine that the accuracy that service location recommended models are recommended.
It is to be appreciated that if analysis draws the LBS data of the user traced into and the service location behavior rail recommended
Matching degree between mark is more than default matching threshold, it is determined that the service location recommended models are directed to the service location of the user
It is accurate to recommend, and further a pair service location related to the other users progress that the user belongs to same customer group can push away
Recommend.
It should be noted that in other embodiments of the present invention, in addition to the 3rd analysis module (is to show in figure
Go out), before the similarity between each user is analyzed, using predetermined frequent item set algorithm to each user's
Action trail data are analyzed, and the habits and customs feature of each user is obtained with analysis.
Wherein, predetermined frequent item set analysis rule includes FP-tree the matching analysis algorithms.Specifically, FP-tree
The matching analysis algorithm includes the construction process of FP-tree Matching Models and the process of Mining Frequent Patterns.
The construction process of FP-tree Matching Models includes, and first, builds what is be made up of the action trail data of each user
Database D B (also crying condition data for projection storehouse) and a default minimum support, secondly, according to database D B and minimum support
Degree output projection FP-tree, constantly to the FP-tree of output by the above-mentioned construction step of iteration, until the new FP- of construction
Tree is empty set, or new FP-tree only includes a paths (for example, an only action trail data), then explanation is to FP-
The construction process of tree Matching Models terminates, and the process of Mining Frequent Patterns is, when the FP-tree of construction is space-time, its prefix
As frequent mode；When only including a paths, can obtain by enumerating to be possible to combine to be connected with the prefix of this book
Frequent mode.It is to be appreciated that after the habits and customs feature of each user is analyzed, the first analysis module 202 is using in advance
The habits and customs feature of each user of similarity analysis rule analysis first determined is (for example, user A custom weekends go specifically
Point is taken exercises, and user B custom weekends remove specific market shopping etc.), the similarity between each user is obtained with analysis.
As shown in fig.5, it is implementing procedure signal of the present invention based on the embodiment of LBS data, services place recommendations method one
Figure.As shown in Figure 5, in the present embodiment, step S301 to step S304 is included based on LBS data, services place recommendations method.
S301, for if desired carrying out service location recommendation to each predetermined mobile terminal user, or, if
The service location recommendation request that a predetermined mobile terminal is sent is received, then is obtained from predetermined database each
Individual predetermined user corresponding LBS data in preset time, using predetermined first clustering algorithm to acquisition
The LBS data of each user carry out cluster analysis, to analyze at least one action trail data corresponding to each user respectively.
Wherein, LBS data include geographical location information data and provided related to geographical location information data all kinds of
Service information data, action trail data include travel type track data and/or, types of entertainment track data；Travel type
Track data includes journey time and stroke mark (for example, some period at noon often goes to certain restaurant to have lunch), amusement
Type track data includes playtime and address mark (for example, weekend goes the place tourism determined).
Generally, Mobile positioning service system is used for finding the current geographic position of mobile terminal user, and searches for from current
The title in a range of service available place in geographical position and address are (for example, hotel, movie theatre, library, gas station
Deng title and address), then recommend the related names that search and address to mobile terminal user, so that mobile terminal user
The service according to corresponding to the title and address choice of recommendation.Wherein, after mobile terminal user selects to service, Location based service
System can record user current geographic position (i.e. described geographical location information data) and selected service it is (i.e. described related
Service information data), and be stored in database.Therefore in the present embodiment, the acquisition module 201 can be from the data
Obtained in storehouse the mobile terminal user LBS data (i.e. described geographical location information data and provide with the geographical position
Put the related service information data of information data).
Then, cluster analysis is carried out to the LBS data of each user of acquisition using predetermined first clustering algorithm,
To analyze at least one action trail data corresponding to each user respectively, in the present embodiment, predetermined first cluster
Algorithm is density-based algorithms (for example, DBSCAN clustering algorithms).
Further, specific process of cluster analysis is illustrated with the user A of acquisition LBS data instances, firstly, it is necessary in advance
Core point, the reachable region of core dot density, and the boundary point of density range coverage are defined, in the present embodiment, to obtain
To a certain geographical position that often positioned within a preset time interval of user A be core point, for example, user A was at one month
Inherent 12 noon clock positioning dining room E first number has exceeded default number (20 times), then with dining room B geographical position
For core point, if if second number that geographical position F was positioned by user A is more than or waited (in one month) within the default time
In first number, then geographical position F is the point in core point B density range coverages, by each core dot density range coverage
In the region that forms of point be core dot density range coverage, if geographical position G was positioned by user A within the default time
Third time number is equal to first number, then geographical position G is the boundary point of density range coverage, in this manner it is possible to achieve user A
The place frequently positioned in preset time, and then user A action trail data are obtained according to the place frequently positioned,
For example, some period at noon often goes to certain restaurant to have lunch, or, weekend goes place tourism determined etc..
S302, according to the action trail data of the predetermined each user of similarity analysis rule analysis, to analyze
Similarity between each user.
Wherein, predetermined similarity analysis rule can be cosine angle analogue method, Europe in various embodiments
A few Reed Distance Scaling Methods or Pearson correlation coefficient method.
For example, in one embodiment, illustrate by taking euclidean distance metric method as an example, wherein, Euclidean distance degree
Amount method calculates similarity using equation below：
It should be noted that the x and y in above-mentioned formula are respectively the vector after normalizing, the result of above-mentioned formula is
For vector x and vectorial y similarity, in the present embodiment, for example, analyzing the similarity between user A and user B, then will use
Family A action trail data obtain the primary vector in above-mentioned formula after being normalized according to default normalization mode
X, after user B action trail data are normalized according to default normalization mode, obtain in above-mentioned formula
Secondary vector y, then primary vector x and secondary vector y are substituted into the calculation formula of above-mentioned similarity respectively, user is calculated
Similarity between A and user B.
S303, based on the similarity between each user, each user is entered using predetermined second clustering algorithm
Row cluster, to obtain different user groups, the user point that similarity is more than predetermined threshold value is small to same user group, similarity
In or equal to predetermined threshold value user point to different user groups.
Wherein, predetermined second clustering algorithm includes the object function clustering algorithm based on original shape (for example, k-
Means), density-based algorithms (for example, DBSCAN) or based on level clustering algorithm (for example,
Hiearchical)。
S304, the customer group belonging to each predetermined user is analyzed using predetermined service location recommended models
The LBS data of all users in body, analyze the action trail of each predetermined user preference, and to predetermined end
End sends the recommendation instruction of the service location on the action trail of each predetermined user preference.
Wherein, predetermined service location recommended models are collaborative filtering recommending model, and service location recommended models
Foundation include the training process of model and the test process of model.
Specifically, the training process of model includes：
The LBS data samples of the similar users of predetermined number (for example, 100) are obtained, by the LBS numbers of each similar users
It is divided into the corresponding training set of first ratio and the test set of the second ratio according to sample；
Using the LBS data training service place recommendation model of each similar users in training set, to be trained
Service location recommended models；
Service location recommended models are tested using the LBS data of each similar users in test set, if test is logical
To cross, then training terminates, or, if test is not by increasing the LBS data samples of the similar users in training set and holding again
The step of above-mentioned training of row services place recommendation model.
The test process of model includes：
The LBS data of each similar users in test set are divided using the service location recommended models trained
Analysis, to draw the action trail of each similar users preference；
By the action trail of each similar users preference drawn and the action trail of the frequent activity of each similar users
Contrasted, if the action trail of corresponding preference consistent number of users corresponding with the action trail of frequent activity is more than default
Percentage threshold (for example, 70%), it is determined that the test to service location recommended models passes through, or, if the row of corresponding preference
It is less than or equal to preset percentage threshold value for track consistent number of users corresponding with the action trail of frequent activity, it is determined that right
The test of service location recommended models does not pass through.
As shown in fig.6, the service location for being the present invention based on LBS data recommends the implementing procedure of another embodiment of method
Schematic diagram.It will be appreciated from fig. 6 that compared to the embodiment shown in Fig. 5, the service location recommendation side based on LBS data of the present embodiment
Method includes step S401 to step S403.
Step S401, if receiving the service location that a predetermined terminal user sends recommends instruction, from advance
It is predetermined that each predetermined user corresponding LBS data, utilization in preset time are obtained in the database of determination
First clustering algorithm carries out cluster analysis to the LBS data of each user of acquisition, to analyze respectively corresponding to each user
At least one action trail data.
Step S402, according to the action trail data of the predetermined each user of similarity analysis rule analysis, to divide
Analysis obtains the similarity between each user.
Step S403, based on the similarity between each user, using predetermined second clustering algorithm to each use
Family is clustered, and to obtain different user groups, similarity is more than the user point of predetermined threshold value to same user group, similar
User point extremely different user group of the degree less than or equal to predetermined threshold value.
Step S404, the use belonging to the user of recommendation request is sent using the analysis of predetermined service location recommended models
The LBS data of all users in the colony of family, the action trail of the user preference is analyzed, and send and be somebody's turn to do to predetermined terminal
The recommendation instruction of service location on the action trail of user preference.
It should be noted that in some other embodiment of the present invention, in addition to step S405 (not shown)s, with
Track receives the LBS data for the user for recommending instruction, and analyzes the LBS data of user traced into and the user recommended is inclined
The matching degree between service location on good action trail, if the LBS data of the user traced into and the user recommended
The matching degree between service location on the action trail of preference is less than or equal to default matching threshold, then repeats step
S402 and step S403.
Specifically, performed to predetermined terminal send for the user service location action trail recommend refer to
After order, the instruction for tracking the LBS data of the user is sent, and analyze the LBS data of the user traced into and the clothes recommended
Matching degree between business place action trail, further determines that whether the recommendation of service location recommended models is accurate.
It is to be appreciated that if analysis draws the LBS data of the user traced into and the service location behavior rail recommended
Matching degree between mark is more than default matching threshold, it is determined that the service location recommended models are directed to the service location of the user
It is accurate to recommend, and further a pair service location related to the other users progress that the user belongs to same customer group can push away
Recommend.
Explanation is needed further exist for, it is similar between each user is analyzed in other embodiments of the present invention
Before the step of spending, in addition to step is carried out using predetermined frequent item set algorithm to the action trail data of each user
Analysis, the habits and customs feature (being to show in figure) of each user is obtained with analysis.
Wherein, predetermined frequent item set analysis rule includes FP-tree the matching analysis algorithms.Specifically, FP-tree
The matching analysis algorithm includes the construction process of FP-tree Matching Models and the process of Mining Frequent Patterns.
The construction process of FP-tree Matching Models includes, and first, builds what is be made up of the action trail data of each user
Database D B (also crying condition data for projection storehouse) and a default minimum support, secondly, according to database D B and minimum support
Degree output projection FP-tree, constantly to the FP-tree of output by the above-mentioned construction step of iteration, until the new FP- of construction
Tree is empty set, or new FP-tree only includes a paths (for example, an only action trail data), then explanation is to FP-
The construction process of tree Matching Models terminates, and the process of Mining Frequent Patterns is, when the FP-tree of construction is space-time, its prefix
As frequent mode；When only including a paths, can obtain by enumerating to be possible to combine to be connected with the prefix of this book
Frequent mode.
It is to be appreciated that after the habits and customs feature of each user is analyzed, predetermined similarity point is utilized
The habits and customs feature for analysing each user of rule analysis (goes to specific place to take exercises, user B is practised for example, user A is accustomed to weekend
Used weekend removes specific market shopping etc.), the similarity between each user is obtained with analysis.
By above-mentioned each embodiment, electronic installation of the invention, the service location based on user's LBS data are recommended
Method and storage medium, first, by obtaining each user corresponding LBS in preset time from predetermined database
Data, cluster analysis is carried out to acquired LBS data using predetermined first clustering algorithm, to analyze each user
At least one action trail data corresponding to respectively；Then, according to the predetermined each user of similarity analysis rule analysis
Action trail data, with analysis obtain the similarity between each user；Then, between each user analysis obtained
Similarity substitutes into predetermined second clustering algorithm and carries out cluster analysis, to define the difference being made up of respectively acquainted users
User group；Finally, the user belonging to the user of identification information is carried using the analysis of predetermined service location recommended models
The LBS data of each user in colony, to analyze the action trail of the user preference, and the behavior rail based on the user preference
Mark sends the service location action trail recommendation instruction for the user to predetermined terminal.So, can both avoid existing
There is in technology the drawbacks of limitation to LBS data applications, the accuracy of recommendation can also be improved.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of electronic installation, it is characterised in that the electronic installation includes memory, processor, is stored on the memory
There are the service location commending system based on LBS data that can be run on the processor, the service field based on LBS data
Following steps are realized when institute's commending system is by the computing device：
A, service location recommendation if desired is carried out to each predetermined user, or, if receiving a predetermined use
The service location recommendation request that the terminal at family is sent, then each predetermined user is obtained from predetermined database and is existed
Corresponding LBS data in preset time, the LBS data of each user of acquisition are entered using predetermined first clustering algorithm
Row cluster analysis, to analyze at least one action trail data corresponding to each user respectively；
B, according to the action trail data of the predetermined each user of similarity analysis rule analysis, each use is obtained with analysis
Similarity between family；
C, based on the similarity between each user, each user is clustered using predetermined second clustering algorithm,
To obtain different user groups, the similarity is more than the user point extremely same user group of predetermined threshold value, the similarity
Less than or equal to the user point extremely different user group of predetermined threshold value；
D, institute in the user group belonging to each predetermined user of predetermined service location recommended models analysis is utilized
There are the LBS data of user, analyze the action trail of each predetermined user preference, and send to predetermined terminal
The recommendation instruction of service location on the action trail of each predetermined user preference, or, utilize predetermined clothes
Business place recommendation model analysis sends the LBS data of all users in user group belonging to the user of the recommendation request, really
The action trail of the user preference is made, and the service field on the action trail of the user preference is sent to predetermined terminal
Recommendation instruction.
2. electronic installation as claimed in claim 1, it is characterised in that the predetermined database is included from all movements
The running fix data and the service data related to position of offer got in the positioning service system of terminal user, it is described
LBS data include geographical location information data and all kinds of service datas related to the geographical location information data provided,
The action trail data include travel type track data and/or, types of entertainment track data；The travel type track
Data include journey time and stroke identifies, and the types of entertainment track data includes playtime and address identifies.
3. electronic installation as claimed in claim 1, it is characterised in that predetermined first clustering algorithm includes being based on
The clustering algorithm of density；The predetermined similarity analysis rule includes cosine angle analogue method, Euclidean distance degree
Amount method or Pearson correlation coefficient method；Predetermined second clustering algorithm includes the object function cluster based on prototype
Algorithm, density-based algorithms or the clustering algorithm based on level.
4. electronic installation as claimed in claim 1, it is characterised in that the predetermined service location recommended models are association
With filtered recommendation model.
5. the electronic installation as described in claim any one of 1-4, it is characterised in that the service location based on LBS data
Following steps are also realized when commending system is by the computing device：
The LBS data for receiving the user for recommending instruction are tracked, and the LBS data for analyzing the user traced into are somebody's turn to do with what is recommended
The matching degree between service location on the action trail of user preference, if the LBS data of the user traced into and being recommended
The matching degree between service location on the action trail of the user preference is less than or equal to default matching threshold, then repeats to hold
Row step B and step C.
6. a kind of service location based on LBS data recommends method, it is characterised in that methods described comprises the following steps：
S1, service location recommendation if desired is carried out to each predetermined user, or, if receiving a predetermined use
The service location recommendation request that the terminal at family is sent, then each predetermined user is obtained from predetermined database and is existed
Corresponding LBS data in preset time, the LBS data of each user of acquisition are entered using predetermined first clustering algorithm
Row cluster analysis, to analyze at least one action trail data corresponding to each user respectively；
S2, the action trail data according to the predetermined each user of similarity analysis rule analysis, obtained with analysis each
Similarity between user；
S3, based on the similarity between each user, each user is clustered using predetermined second clustering algorithm,
To obtain different user groups, the similarity is more than the user point extremely same user group of predetermined threshold value, the similarity
Less than or equal to the user point extremely different user group of predetermined threshold value；
S4, utilize institute in the user group belonging to each predetermined user of predetermined service location recommended models analysis
There are the LBS data of user, analyze the action trail of each predetermined user preference, and send to predetermined terminal
The recommendation instruction of service location on the action trail of each predetermined user preference, or, utilize predetermined clothes
Business place recommendation model analysis sends the LBS data of all users in user group belonging to the user of the recommendation request, really
The action trail of the user preference is made, and the service field on the action trail of the user preference is sent to predetermined terminal
Recommendation instruction.
7. the service location based on LBS data recommends method as claimed in claim 6, it is characterised in that described to predefine
Database include the running fix data that are got from the positioning service system of all mobile terminal users and offer with
The related service data in position, the LBS data include geographical location information data and providing with the geographical location information
The related all kinds of service datas of data, the action trail data include travel type track data and/or, types of entertainment rail
Mark data；The travel type track data includes journey time and stroke identifies, and the types of entertainment track data includes joy
Happy time and address mark.
8. the service location based on LBS data recommends method as claimed in claim 6, it is characterised in that described to predefine
The first clustering algorithm include density-based algorithms；The predetermined similarity analysis rule includes cosine angle
Analogue method, euclidean distance metric method or Pearson correlation coefficient method；Predetermined second clustering algorithm includes base
In the object function clustering algorithm of original shape, density-based algorithms or clustering algorithm based on level.
9. the service location based on LBS data recommends method as claimed in claim 6, it is characterised in that described to predefine
Service location recommended models be collaborative filtering recommending model.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has the service field based on LBS data
Institute's commending system, the service location commending system based on LBS data can by least one computing device so that it is described extremely
Service location based on LBS data of few computing device as any one of claim 6-9 recommends the step of method
Suddenly.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710916517.9A CN107798557B (en) | 2017-09-30 | 2017-09-30 | Electronic device, service place recommendation method based on LBS data and storage medium |
| PCT/CN2017/108738 WO2019061656A1 (en) | 2017-09-30 | 2017-10-31 | Electronic apparatus, service place recommendation method based on lbs data, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710916517.9A CN107798557B (en) | 2017-09-30 | 2017-09-30 | Electronic device, service place recommendation method based on LBS data and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107798557A true CN107798557A (en) | 2018-03-13 |
| CN107798557B CN107798557B (en) | 2020-09-25 |
Family
ID=61533085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710916517.9A Active CN107798557B (en) | 2017-09-30 | 2017-09-30 | Electronic device, service place recommendation method based on LBS data and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107798557B (en) |
| WO (1) | WO2019061656A1 (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985950A (en) * | 2018-07-13 | 2018-12-11 | 平安科技（深圳）有限公司 | Electronic device, user's insurance fraud method for prewarning risk and storage medium |
| CN109614556A (en) * | 2018-10-31 | 2019-04-12 | 拉卡拉支付股份有限公司 | Access path prediction, information-pushing method and device |
| CN109829020A (en) * | 2018-12-20 | 2019-05-31 | 平安科技（深圳）有限公司 | Place resource data push method, device, computer equipment and storage medium |
| CN110348990A (en) * | 2019-06-19 | 2019-10-18 | 北京淇瑀信息科技有限公司 | Line of credit method of adjustment, device and electronic equipment based on user's trip track |
| CN110730432A (en) * | 2019-10-21 | 2020-01-24 | 深圳市名通科技股份有限公司 | Proximity user identification method, terminal and readable storage medium |
| CN110753102A (en) * | 2019-10-15 | 2020-02-04 | 浙江口碑网络技术有限公司 | Service information pushing method and device based on geomagnetism |
| CN110750603A (en) * | 2019-09-06 | 2020-02-04 | 日立楼宇技术（广州）有限公司 | Building service prediction method, building service prediction device, building service prediction system, computer equipment and storage medium |
| CN110874609A (en) * | 2018-09-04 | 2020-03-10 | 武汉斗鱼网络科技有限公司 | User clustering method, storage medium, device and system based on user behaviors |
| CN110895588A (en) * | 2018-09-13 | 2020-03-20 | 中国移动通信有限公司研究院 | Data processing method and equipment |
| CN111209487A (en) * | 2020-01-02 | 2020-05-29 | 平安科技（深圳）有限公司 | User data analysis method, server, and computer-readable storage medium |
| CN111222686A (en) * | 2019-11-21 | 2020-06-02 | 施甸县保施高速公路投资开发有限公司 | Method for optimizing state of service area of highway |
| CN111523058A (en) * | 2020-04-21 | 2020-08-11 | 北京嘀嘀无限科技发展有限公司 | Service area analysis processing method, device, equipment and storage medium |
| CN111949891A (en) * | 2020-10-09 | 2020-11-17 | 广州斯沃德科技有限公司 | Personalized information recommendation method and system based on vehicle track clustering |
| CN112085099A (en) * | 2020-09-09 | 2020-12-15 | 西南大学 | Distributed student clustering integration method and system |
| CN112231392A (en) * | 2020-10-29 | 2021-01-15 | 广东机场白云信息科技有限公司 | Civil aviation customer source data analysis method, electronic equipment and computer readable storage medium |
| CN113254570A (en) * | 2021-07-15 | 2021-08-13 | 浙江网商银行股份有限公司 | Data identification method and device |
| CN113310495A (en) * | 2021-06-08 | 2021-08-27 | 湖南师范大学 | Indoor positioning method and system, electronic equipment and readable storage medium |
| CN113379454A (en) * | 2021-06-09 | 2021-09-10 | 北京房江湖科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN114282126A (en) * | 2022-03-01 | 2022-04-05 | 阿里健康科技(中国)有限公司 | Information recommendation method, device, medium and equipment |
| WO2022105129A1 (en) * | 2020-11-17 | 2022-05-27 | 平安科技（深圳）有限公司 | Content data recommendation method and apparatus, and computer device, and storage medium |
| CN115659197A (en) * | 2022-12-28 | 2023-01-31 | 湖南财政经济学院 | Data security monitoring model training method, application method, device and storage medium |
| CN115795318A (en) * | 2022-11-17 | 2023-03-14 | 北京白龙马云行科技有限公司 | Classification method of use case object, model training method, equipment and storage medium |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309379B (en) * | 2019-05-22 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and computer readable storage medium |
| CN112348614A (en) * | 2019-11-27 | 2021-02-09 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
| CN111177534A (en) * | 2019-12-06 | 2020-05-19 | 南京欣网互联信息技术有限公司 | User behavior trajectory analysis method based on Internet big data |
| CN110941278B (en) * | 2019-12-20 | 2023-05-23 | 交控科技股份有限公司 | Dynamic safety analysis method in station |
| CN111814067B (en) * | 2020-06-30 | 2024-03-15 | 北京百度网讯科技有限公司 | Friend recommendation method, device, equipment and storage medium |
| CN111881243B (en) * | 2020-07-30 | 2024-04-02 | 河北工程大学 | Taxi track hot spot area analysis method and system |
| CN111882399A (en) * | 2020-07-31 | 2020-11-03 | 平安国际融资租赁有限公司 | Service information recommendation method, device, computer system and readable storage medium |
| CN112069913B (en) * | 2020-08-13 | 2024-04-30 | 东软集团股份有限公司 | User identification method, device, storage medium and electronic equipment |
| CN112040024B (en) * | 2020-08-28 | 2023-05-09 | 北京明略昭辉科技有限公司 | Data processing method, device, equipment and storage medium |
Citations (4)
| 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 |
| CN103116614A (en) * | 2013-01-25 | 2013-05-22 | 北京奇艺世纪科技有限公司 | Collaborative filtering recommendation method, device and system base on user track |
| CN103747523A (en) * | 2014-01-14 | 2014-04-23 | 上海河广信息科技有限公司 | User position predicating system and method based on wireless network |
| CN104765873A (en) * | 2015-04-24 | 2015-07-08 | 百度在线网络技术（北京）有限公司 | Method and device for determining similarity among users |
-
2017
- 2017-09-30 CN CN201710916517.9A patent/CN107798557B/en active Active
- 2017-10-31 WO PCT/CN2017/108738 patent/WO2019061656A1/en active Application Filing
Patent Citations (4)
| 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 |
| CN103116614A (en) * | 2013-01-25 | 2013-05-22 | 北京奇艺世纪科技有限公司 | Collaborative filtering recommendation method, device and system base on user track |
| CN103747523A (en) * | 2014-01-14 | 2014-04-23 | 上海河广信息科技有限公司 | User position predicating system and method based on wireless network |
| CN104765873A (en) * | 2015-04-24 | 2015-07-08 | 百度在线网络技术（北京）有限公司 | Method and device for determining similarity among users |
Non-Patent Citations (2)
| Title |
|---|
| ENHUI LI ETC.: "Research on LBS-based Optimizing Personal Recommendation System", 《2ND INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTER SCIENCE AND ENGINEERING (CSE 2013)》 * |
| 印桂生，程伟杰，董宇欣，董红斌，张万松: "使用轨迹指纹和地点相似性的地点推荐", 《哈尔滨工程大学学报》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985950A (en) * | 2018-07-13 | 2018-12-11 | 平安科技（深圳）有限公司 | Electronic device, user's insurance fraud method for prewarning risk and storage medium |
| CN108985950B (en) * | 2018-07-13 | 2023-04-18 | 平安科技（深圳）有限公司 | Electronic device, user fraud protection risk early warning method and storage medium |
| CN110874609B (en) * | 2018-09-04 | 2022-08-16 | 武汉斗鱼网络科技有限公司 | User clustering method, storage medium, device and system based on user behaviors |
| CN110874609A (en) * | 2018-09-04 | 2020-03-10 | 武汉斗鱼网络科技有限公司 | User clustering method, storage medium, device and system based on user behaviors |
| CN110895588B (en) * | 2018-09-13 | 2022-07-22 | 中国移动通信有限公司研究院 | Data processing method and equipment |
| CN110895588A (en) * | 2018-09-13 | 2020-03-20 | 中国移动通信有限公司研究院 | Data processing method and equipment |
| CN109614556A (en) * | 2018-10-31 | 2019-04-12 | 拉卡拉支付股份有限公司 | Access path prediction, information-pushing method and device |
| CN109829020B (en) * | 2018-12-20 | 2023-04-07 | 平安科技（深圳）有限公司 | Method and device for pushing place resource data, computer equipment and storage medium |
| CN109829020A (en) * | 2018-12-20 | 2019-05-31 | 平安科技（深圳）有限公司 | Place resource data push method, device, computer equipment and storage medium |
| CN110348990A (en) * | 2019-06-19 | 2019-10-18 | 北京淇瑀信息科技有限公司 | Line of credit method of adjustment, device and electronic equipment based on user's trip track |
| CN110750603A (en) * | 2019-09-06 | 2020-02-04 | 日立楼宇技术（广州）有限公司 | Building service prediction method, building service prediction device, building service prediction system, computer equipment and storage medium |
| CN110750603B (en) * | 2019-09-06 | 2022-08-12 | 日立楼宇技术（广州）有限公司 | Building service prediction method, building service prediction device, building service prediction system, computer equipment and storage medium |
| CN110753102A (en) * | 2019-10-15 | 2020-02-04 | 浙江口碑网络技术有限公司 | Service information pushing method and device based on geomagnetism |
| CN110753102B (en) * | 2019-10-15 | 2021-01-05 | 浙江口碑网络技术有限公司 | Service information pushing method and device based on geomagnetism |
| CN110730432B (en) * | 2019-10-21 | 2021-01-08 | 深圳市名通科技股份有限公司 | Proximity user identification method, terminal and readable storage medium |
| CN110730432A (en) * | 2019-10-21 | 2020-01-24 | 深圳市名通科技股份有限公司 | Proximity user identification method, terminal and readable storage medium |
| CN111222686A (en) * | 2019-11-21 | 2020-06-02 | 施甸县保施高速公路投资开发有限公司 | Method for optimizing state of service area of highway |
| CN111209487B (en) * | 2020-01-02 | 2020-10-27 | 平安科技（深圳）有限公司 | User data analysis method, server, and computer-readable storage medium |
| CN111209487A (en) * | 2020-01-02 | 2020-05-29 | 平安科技（深圳）有限公司 | User data analysis method, server, and computer-readable storage medium |
| CN111523058B (en) * | 2020-04-21 | 2023-11-03 | 北京嘀嘀无限科技发展有限公司 | Service area analysis processing method, device, equipment and storage medium |
| CN111523058A (en) * | 2020-04-21 | 2020-08-11 | 北京嘀嘀无限科技发展有限公司 | Service area analysis processing method, device, equipment and storage medium |
| CN112085099A (en) * | 2020-09-09 | 2020-12-15 | 西南大学 | Distributed student clustering integration method and system |
| CN112085099B (en) * | 2020-09-09 | 2022-05-17 | 西南大学 | Distributed student clustering integration method and system |
| CN111949891A (en) * | 2020-10-09 | 2020-11-17 | 广州斯沃德科技有限公司 | Personalized information recommendation method and system based on vehicle track clustering |
| CN111949891B (en) * | 2020-10-09 | 2021-06-15 | 广州斯沃德科技有限公司 | Personalized information recommendation method and system based on vehicle track clustering |
| CN112231392A (en) * | 2020-10-29 | 2021-01-15 | 广东机场白云信息科技有限公司 | Civil aviation customer source data analysis method, electronic equipment and computer readable storage medium |
| WO2022105129A1 (en) * | 2020-11-17 | 2022-05-27 | 平安科技（深圳）有限公司 | Content data recommendation method and apparatus, and computer device, and storage medium |
| CN113310495A (en) * | 2021-06-08 | 2021-08-27 | 湖南师范大学 | Indoor positioning method and system, electronic equipment and readable storage medium |
| CN113310495B (en) * | 2021-06-08 | 2022-07-12 | 湖南师范大学 | Indoor positioning method and system, electronic equipment and readable storage medium |
| CN113379454A (en) * | 2021-06-09 | 2021-09-10 | 北京房江湖科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113254570B (en) * | 2021-07-15 | 2021-10-01 | 浙江网商银行股份有限公司 | Data identification method and device |
| CN113254570A (en) * | 2021-07-15 | 2021-08-13 | 浙江网商银行股份有限公司 | Data identification method and device |
| CN114282126A (en) * | 2022-03-01 | 2022-04-05 | 阿里健康科技(中国)有限公司 | Information recommendation method, device, medium and equipment |
| CN115795318A (en) * | 2022-11-17 | 2023-03-14 | 北京白龙马云行科技有限公司 | Classification method of use case object, model training method, equipment and storage medium |
| CN115659197A (en) * | 2022-12-28 | 2023-01-31 | 湖南财政经济学院 | Data security monitoring model training method, application method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019061656A1 (en) | 2019-04-04 |
| CN107798557B (en) | 2020-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107798557A (en) | Electronic installation, the service location based on LBS data recommend method and storage medium | |
| Xiao et al. | Inferring social ties between users with human location history | |
| Takeuchi et al. | CityVoyager: An outdoor recommendation system based on user location history | |
| CN104102719B (en) | The method for pushing and device of a kind of trace information | |
| CN104081339B (en) | The data transmission by network connection is managed based on priority and data application plan | |
| CN105608179B (en) | The method and apparatus for determining the relevance of user identifier | |
| US20100153292A1 (en) | Making Friend and Location Recommendations Based on Location Similarities | |
| CN103617547B (en) | A kind of business recommended method and system | |
| CN103905471B (en) | Information-pushing method, server and the social networks of social networks | |
| CN113412608B (en) | Content pushing method and device, server and storage medium | |
| CN109084795B (en) | Method and device for searching service facilities based on map service | |
| CN106416313A (en) | Identifying an entity associated with wireless network access point | |
| CN108536694A (en) | Estimation method, device and the terminal device of user preference | |
| CN104408043A (en) | Information processing method and server | |
| CN110298687B (en) | Regional attraction assessment method and device | |
| US20150248436A1 (en) | Methods, Circuits, Devices, Systems and Associated Computer Executable Code for Assessing a Presence Likelihood of a Subject at One or More Venues | |
| CN105721629A (en) | User identifier matching method and device | |
| CN109460520A (en) | Point of interest recommended method based on geography-social relationships and deep implicit interest digging | |
| CN112214677B (en) | Point of interest recommendation method and device, electronic equipment and storage medium | |
| CN104239453A (en) | Data processing method and device | |
| CN110874437A (en) | Personalized interest point recommendation method based on multiple interest point pair sorting | |
| CN107315833A (en) | Method and apparatus of the retrieval with downloading based on application program | |
| CN107133689B (en) | Position marking method | |
| CN109446415A (en) | A kind of application recommendation, acquisition methods and equipment | |
| CN109409959A (en) | A kind of user information analysis method, device, equipment and medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |