CN107169012A - POI recommends method, device, equipment and computer-readable recording medium - Google Patents
POI recommends method, device, equipment and computer-readable recording medium Download PDFInfo
- Publication number
- CN107169012A CN107169012A CN201710209459.6A CN201710209459A CN107169012A CN 107169012 A CN107169012 A CN 107169012A CN 201710209459 A CN201710209459 A CN 201710209459A CN 107169012 A CN107169012 A CN 107169012A
- Authority
- CN
- China
- Prior art keywords
- poi
- clusters
- target
- homogeneity
- user
- 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
Abstract
The present invention provides a kind of POI and recommends method, device, equipment and computer-readable recording medium.The embodiment of the present invention passes through according to acquired user target POI interested, obtain the target POI clusters belonging to the target POI, and then according to the target POI clusters, obtain the homogeneity POI clusters between the target POI clusters with homogeneity incidence relation, make it possible to according to the structure distance between the homogeneity POI clusters and the target POI, the homogeneity POI clusters for selecting structure closest, recommend the user, due to the excavation using homogeneity incidence relation, so that each POI clusters divided disclosure satisfy that the particular demands of user, therefore, it is suitable as the based process unit recommended, accurately to user recommend the user may POI interested or it should be understood that POI, so as to improve the success rate of POI recommendations.
Description
【Technical field】
Recommend method, device, equipment and computer-readable storage the present invention relates to recommended technology, more particularly to a kind of POI
Medium.
【Background technology】
With the development of the communication technology, terminal is integrated with increasing function, so that the systemic-function row of terminal
More and more corresponding applications (Application, APP) are contained in table.It can be related to some points of interest in some applications
(Point of Interest, POI) recommendation service, POI is an information word in geography information, is based on geographical letter
Retail shop, public service website and bus station of breath etc. build or can provided the information of the services sites of service.
How accurately to user recommend the user may POI interested or it should be understood that POI, to improve POI
The success rate of recommendation, is the technical problem of a urgent need to resolve.
【The content of the invention】
The many aspects of the present invention provide a kind of POI and recommend method, device, equipment and computer-readable recording medium, use
To improve the success rate of POI recommendations.
An aspect of of the present present invention recommends method there is provided a kind of POI, including：
Obtain user target POI interested；
According to the target POI, the target POI clusters belonging to the target POI are obtained；
According to the target POI clusters, the homogeneity between the target POI clusters with homogeneity incidence relation is obtained
POI clusters；
According to the structure distance between the homogeneity POI clusters and the target POI, the closest homogeneity of selection structure
POI clusters, recommend the user.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the acquisition are used
Family target POI interested, including：
According to the attribute data of the user, the target POI is obtained；Or
According to the nearest inquiry operation of the user, the target POI is obtained；Or
According to the current inquiry operation of the user, the target POI is obtained；Or
The position being currently located according to the user, obtains the target POI.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
State target POI, before obtaining the target POI clusters belonging to the target POI, in addition to：
Obtain the user behavior data of the whole network user；
According to the user behavior data, the incidence relation between POI two-by-two is obtained；
According to the relevant parameter of the incidence relation between the incidence relation between the POI two-by-two and the POI two-by-two, adopt
Community discovery algorithm is used, POI clustering processings are carried out, to obtain at least one POI cluster with tree structure relation, for root
According to the target POI, obtain the target POI clusters belonging to the target POI, and according to the target POI clusters, obtain with
There is the homogeneity POI clusters of homogeneity incidence relation between the target POI clusters.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the POI two-by-two
Between incidence relation relevant parameter, including：
The support of incidence relation between the POI two-by-two；Or
The cosine phase of incidence relation between the support of incidence relation between the POI two-by-two and the POI two-by-two
Like degree.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
The relevant parameter of the incidence relation between the incidence relation between POI two-by-two and the POI two-by-two is stated, is calculated using community discovery
Method, carries out POI clustering processings, to obtain at least one POI cluster with tree structure relation, including：
According to the relevant parameter of the incidence relation between the POI two-by-two, the incidence relation between the POI two-by-two is entered
Row filtration treatment；
According to the incidence relation between the POI two-by-two after the filtration treatment, using community discovery algorithm, POI is carried out
Clustering processing, to obtain at least one POI cluster with tree structure relation.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
The structure distance between homogeneity POI clusters and the target POI is stated, the closest homogeneity POI clusters of selection structure are recommended
The user, including：
According to the structure distance between the homogeneity POI clusters and the target POI, prioritizing selection and the target POI
The homogeneity POI clusters of the identical leaf node of cluster, recommend the user；
If selected homogeneity POI clusters are unsatisfactory for that POI quantity can be recommended, father identical with the target POI clusters is selected
The homogeneity POI clusters of the brotgher of node of close node, recommend the user, by that analogy, until selected homogeneity POI clusters
Untill satisfaction can recommend POI quantity.
Another aspect of the present invention there is provided a kind of POI recommendation apparatus, including：
Acquiring unit, the target POI interested for obtaining user；
Associative cell, for according to the target POI, obtaining the target POI clusters belonging to the target POI；
The associative cell, is additionally operable to according to the target POI clusters, obtain has between the target POI clusters
The homogeneity POI clusters of homogeneity incidence relation；
Recommendation unit, for according to the structure distance between the homogeneity POI clusters and the target POI, selecting structure
Closest homogeneity POI clusters, recommend the user.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the acquisition list
Member, specifically for
According to the attribute data of the user, the target POI is obtained；Or
According to the nearest inquiry operation of the user, the target POI is obtained；Or
According to the current inquiry operation of the user, the target POI is obtained；Or
The position being currently located according to the user, obtains the target POI.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the association table
Member, is additionally operable to
Obtain the user behavior data of the whole network user；
According to the user behavior data, the incidence relation between POI two-by-two is obtained；And
According to the relevant parameter of the incidence relation between the incidence relation between the POI two-by-two and the POI two-by-two, adopt
Community discovery algorithm is used, POI clustering processings are carried out, to obtain at least one POI cluster with tree structure relation, for root
According to the target POI, obtain the target POI clusters belonging to the target POI, and according to the target POI clusters, obtain with
There is the homogeneity POI clusters of homogeneity incidence relation between the target POI clusters.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the POI two-by-two
Between incidence relation relevant parameter, including：
The support of incidence relation between the POI two-by-two；Or
The cosine phase of incidence relation between the support of incidence relation between the POI two-by-two and the POI two-by-two
Like degree.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the association table
Member, specifically for
According to the relevant parameter of the incidence relation between the POI two-by-two, the incidence relation between the POI two-by-two is entered
Row filtration treatment；
According to the incidence relation between the POI two-by-two after the filtration treatment, using community discovery algorithm, POI is carried out
Clustering processing, to obtain at least one POI cluster with tree structure relation.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, recommendation unit, tool
Body is used for
According to the structure distance between the homogeneity POI clusters and the target POI, prioritizing selection and the target POI
The homogeneity POI clusters of the identical leaf node of cluster, recommend the user；
If selected homogeneity POI clusters are unsatisfactory for that POI quantity can be recommended, father identical with the target POI clusters is selected
The homogeneity POI clusters of the brotgher of node of close node, recommend the user, by that analogy, until selected homogeneity POI clusters
Untill satisfaction can recommend POI quantity.
Another aspect of the present invention includes there is provided a kind of equipment, the equipment：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes that the POI on the one hand provided as described above recommends method.
Another aspect of the present invention is stored thereon with computer program there is provided a kind of computer-readable recording medium, the journey
Realize that the POI on the one hand provided as described above recommends method when sequence is executed by processor.
As shown from the above technical solution, the embodiment of the present invention is by according to acquired user target POI interested, obtaining
The target POI clusters belonging to the target POI are obtained, and then according to the target POI clusters, are obtained and the target POI clusters
Between there is the homogeneity POI clusters of homogeneity incidence relation, enabling according to the homogeneity POI clusters and the target POI it
Between structure distance, the closest homogeneity POI clusters of selection structure are recommended the user, are closed due to being associated using homogeneity
The excavation of system so that each POI clusters divided disclosure satisfy that the particular demands of user, therefore, is suitable as the base recommended
Plinth processing unit, accurately to user recommend the user may POI interested or it should be understood that POI, so as to improve
The success rate that POI recommends.
In addition, using technical scheme provided by the present invention, by replacing single POI with cluster, realizing and utilizing cluster
Global Information describes POI individual information, so as to enrich single POI information, can effectively improve the reliable of POI recommendations
Property.
In addition, using technical scheme provided by the present invention, POI division is more accurate, will not be because of the passes of POI in itself
Keyword, or loss of learning cause to divide indefinite or even mistake.
In addition, using technical scheme provided by the present invention, can be needed to select different levels according to different scenes, it is different
The POI of semantic granularity.
In addition, using technical scheme provided by the present invention, being capable of significant increase Consumer's Experience.
【Brief description of the drawings】
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In required for the accompanying drawing that uses be briefly described, it should be apparent that, drawings in the following description are some realities of the present invention
Example is applied, for those of ordinary skill in the art, without having to pay creative labor, can also be attached according to these
Figure obtains other accompanying drawings.
Fig. 1 recommends the schematic flow sheet of method for the POI that one embodiment of the invention is provided；
The structural representation for the POI recommendation apparatus that Fig. 2 provides for another embodiment of the present invention；
Fig. 3 is suitable for for the block diagram for the exemplary computer system/server 12 for realizing embodiment of the present invention.
【Embodiment】
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The whole other embodiments obtained under the premise of creative work is not made, belong to the scope of protection of the invention.
It should be noted that terminal involved in the embodiment of the present invention can include but is not limited to mobile phone, individual digital
Assistant (Personal Digital Assistant, PDA), radio hand-held equipment, tablet personal computer (Tablet Computer),
PC (Personal Computer, PC), MP3 player, MP4 players, wearable device (for example, intelligent glasses,
Intelligent watch, Intelligent bracelet etc.) etc..
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, represents there may be
Three kinds of relations, for example, A and/or B, can be represented：Individualism A, while there is A and B, these three situations of individualism B.Separately
Outside, character "/" herein, it is a kind of relation of "or" to typically represent forward-backward correlation object.
Fig. 1 recommends the schematic flow sheet of method for the POI that one embodiment of the invention is provided, as shown in Figure 1.
101st, user target POI interested is obtained.
102nd, according to the target POI, the target POI clusters belonging to the target POI are obtained.
103rd, according to the target POI clusters, obtain has the same of homogeneity incidence relation between the target POI clusters
Matter POI clusters.
104th, according to the structure distance between the homogeneity POI clusters and the target POI, selection structure is closest
Homogeneity POI clusters, recommend the user.
It should be noted that 101~104 executive agent can be partly or entirely the application for being located locally terminal,
Or can also be the plug-in unit being arranged in the application of local terminal or SDK (Software
Development Kit, SDK) etc. functional unit, either can also in network side server processing engine or
Can also be the distributed system positioned at network side, the present embodiment is to this without being particularly limited to.
It is understood that the application can be mounted in the local program (nativeApp) in terminal, or may be used also
To be a web page program (webApp) of browser in terminal, the present embodiment is to this without being particularly limited to.
So, by according to acquired user target POI interested, obtaining the target POI belonging to the target POI
Cluster, and then according to the target POI clusters, obtain the homogeneity between the target POI clusters with homogeneity incidence relation
POI clusters, enabling according to the structure distance between the homogeneity POI clusters and the target POI, selection structure distance is most
Near homogeneity POI clusters, recommend the user, due to the excavation using homogeneity incidence relation so that each POI divided
Cluster disclosure satisfy that the particular demands of user, therefore, be suitable as the based process unit recommended, and accurately recommending to user should
User may POI interested or it should be understood that POI, so as to improve the success rate of POI recommendations.
Alternatively, in a possible implementation of the present embodiment, in 101, a variety of methods can be specifically used,
Obtain user target POI interested.
During a concrete implementation, specifically the target can be obtained according to the attribute data of the user
POI.For example, the attribute data of user is is 20 years old at the age, sex be female, resident address be Shangdi and hobby to stroll in the park,
So, then the target POI can be obtained for Yuanmingyuan Park.
During another concrete implementation, specifically it can obtain described according to the nearest inquiry operation of the user
Target POI.For example, user inquired about Yuanmingyuan Park within three days, then, then the target POI can be obtained for Yuanmingyuan Park.
During another concrete implementation, specifically it can obtain described according to the current inquiry operation of the user
Target POI.For example, user currently inquires about Yuanmingyuan Park, then, then the target POI can be obtained for Yuanmingyuan Park.
During another concrete implementation, the position that can be specifically currently located according to the user obtains described
Target POI.For example, the position that user is currently located is in Yuanmingyuan Park, then, then the target POI can be obtained for Yuanmingyuan Park.
Alternatively, in a possible implementation of the present embodiment, before 102, it can further include structure
Build the POI cluster set with tree structure.
During a concrete implementation, the user behavior data of the whole network user can be specifically obtained, and then, then can be with
According to the user behavior data, the incidence relation between POI two-by-two is obtained.It is then possible to according between the POI two-by-two
The relevant parameter of incidence relation between incidence relation and the POI two-by-two, using community discovery algorithm, is carried out at POI clusters
Reason, to obtain at least one POI cluster with tree structure relation, for according to the target POI, obtaining the target
Target POI clusters belonging to POI, and according to the target POI clusters, obtain having together between the target POI clusters
The homogeneity POI clusters of matter incidence relation.Wherein, at least one can be included at least one described POI cluster in each POI clusters
Individual POI.
So, by the prolonged behavior of a large number of users, the incidence relation between POI and POI is excavated, is closed by this
Connection relation, the POI of all full doses is linked together to form POI network.Then, by using community discovery algorithm,
Go to find the POI i.e. POI clusters of the good cluster cluster of cohesion in this network of throwing the net, POI clusters, which have, here disclosure satisfy that largely
The feature of particular demands of the user under similar scene.This scheme is a kind of division of stratification, uses identical method pair
Sorted POI, is divided again for the first time, it becomes possible to obtain the POI classification of bigger granularity.
In the implementation process, the relevant parameter of the incidence relation between the POI two-by-two used can be described two
The support of incidence relation between two POI, or can also be the support of the incidence relation between the POI two-by-two and institute
The cosine similarity of the incidence relation between POI two-by-two is stated, the present embodiment is to this without being particularly limited to.
Specifically, it is possible, firstly, to gather user behavior number of each user in the range of certain time in the whole network user
According to for example, click behavioral data, retrieval behavioral data or positioning track data etc., obtain the incidence relation between POI two-by-two, together
When, can also be further according to the user behavior data gathered, the association for obtaining the incidence relation between the POI two-by-two is joined
Number is for example, the cosine of the incidence relation between the support and the POI two-by-two of incidence relation between the POI two-by-two is similar
Degree.
The support of incidence relation between POI two-by-two, depending on user in the range of certain time consecutively or simultaneously, point
Hit, retrieve or positioned the two POI number of times.
For example, a user in the range of certain time consecutively or simultaneously, click on, retrieve or positioned the two POI, that
, the support of incidence relation can then increase by 1 between the two POI.
The cosine similarity of incidence relation between POI two-by-two, depending on the support of the incidence relation between POI two-by-two
With the temperature of each POI in POI two-by-two.
For example, the cosine similarity of the incidence relation between POI can be two-by-two
One user clicks on, retrieves or positioned this POI in the range of certain time, then, this POI temperature can then increase
Plus 1.
The relevant parameter of incidence relation between incidence relation between POI two-by-two is obtained, and the POI two-by-two
Afterwards, then the association between the POI two-by-two can be closed according to the relevant parameter of the incidence relation between the POI two-by-two
It is to delete the incidence relation between the weaker POI two-by-two of incidence relation that system, which carries out filtration treatment,.
The incidence relation between the POI two-by-two will be used as using the support of the incidence relation between POI two-by-two below
Exemplified by relevant parameter, how filtration treatment is carried out to the incidence relation between the POI two-by-two under explanation.
The support for the incidence relation that can be given between POI two-by-two, pre-sets two threshold values S1 and S2, and S2 is more than
S1.Support is less than to the incidence relation between S1 POI two-by-two, directly deleted；Support is more than or equal to S2 two-by-two
Incidence relation between POI, directly retains；It is more than or equal to S1 and the association being less than between S2 POI two-by-two for support
Relation, then need further to be judged, to determine which can retain, and which needs to delete.For example, setting a threshold value again
L, is more than or equal to S1 and the incidence relation being less than between S2 POI two-by-two for support, if the two POI and other POI
Between incidence relation support be less than L, then the incidence relation between the two POI need retain；If the two POI and its
The support of incidence relation between his POI is more than or equal to L, then the incidence relation between the two POI needs to delete.
In the incidence relation between filtering out POI two-by-two after weaker incidence relation, obtain a POI and POI and lead to
Cross association relational organization into one using POI as node, incidence relation be side network.It is then possible to be calculated using community discovery
Method, in the network obtained, finds the POI i.e. POI clusters of the more close cluster cluster of incidence relation.Calculated in community discovery
In method, the every cluster POI data volume upper limit can be set for example, 25 etc..The result that first time is divided is as handling next time
Base unit be to regard a new POI as, repeat aforesaid operations, it is possible to obtain the thicker POI division results of granularity.Until hair
Now there is effective incidence relation between no any two POI clusters and terminate division.
So, the POI cluster set with tree structure is just constructed, the POI clusters in the POI cluster set are all tools
There are the homogeneity POI clusters of homogeneity incidence relation.
Alternatively, in 104, specifically can be according to the homogeneity in a possible implementation of the present embodiment
Structure distance between POI clusters and the target POI, prioritizing selection leaf node identical with the target POI clusters it is same
Matter POI clusters, recommend the user.If selected homogeneity POI clusters are unsatisfactory for recommending POI quantity, selection with it is described
The homogeneity POI clusters of the brotgher of node of the identical father's node of target POI clusters, recommend the user, by that analogy, Zhi Daosuo
The homogeneity POI clusters of selection are met untill can recommending POI quantity.
In the implementation, target POI can be obtained according to the constructed POI cluster set with tree structure
Cluster and should with the structure in POI cluster set of tree structure in other POI clusters between each homogeneity POI clusters away from
From.Structure between target POI clusters and some homogeneity POI clusters illustrates target POI clusters and some homogeneity apart from smaller
Similarity between POI clusters is higher, more should preferential recommendation to user.
Specifically, specifically can be according to the homogeneity POI groups when recommending selected homogeneity POI clusters to user
Each POI temperature in cluster, according to order from big to small, the POI in selected homogeneity POI clusters is recommended to user.
In the present embodiment, by according to acquired user target POI interested, obtaining belonging to the target POI
Target POI clusters, and then according to the target POI clusters, obtain has homogeneity incidence relation between the target POI clusters
Homogeneity POI clusters, enabling according to the structure distance between the homogeneity POI clusters and the target POI, select structure
Closest homogeneity POI clusters, recommend the user, due to the excavation using homogeneity incidence relation so that divided
Each POI clusters disclosure satisfy that the particular demands of user, therefore, be suitable as the based process unit recommended, accurately to
Family recommend the user may POI interested or it should be understood that POI, so as to improve the success rate of POI recommendations.
In addition, using technical scheme provided by the present invention, POI division is more accurate, will not be because of the passes of POI in itself
Keyword, or loss of learning cause to divide indefinite or even mistake.
In addition, using technical scheme provided by the present invention, can be needed to select different levels according to different scenes, it is different
The POI of semantic granularity.
In addition, using technical scheme provided by the present invention, being capable of significant increase Consumer's Experience.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some steps can be carried out sequentially or simultaneously using other.Secondly, those skilled in the art should also know
Know, embodiment described in this description belongs to preferred embodiment, involved action and module is not necessarily of the invention
It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
The structural representation for the POI recommendation apparatus that Fig. 2 provides for another embodiment of the present invention, as shown in Figure 2.The present embodiment
POI recommendation apparatus can include acquiring unit 21, associative cell 22 and recommendation unit 23.Wherein, acquiring unit 21, for obtaining
Take family target POI interested；Associative cell 22, for according to the target POI, obtaining the mesh belonging to the target POI
Mark POI clusters；The associative cell 22, is additionally operable to, according to the target POI clusters, obtain between the target POI clusters
Homogeneity POI clusters with homogeneity incidence relation；Recommendation unit 23, for according to the homogeneity POI clusters and the target POI
Between structure distance, the closest homogeneity POI clusters of selection structure recommend the user.
It should be noted that the POI recommendation apparatus that the present embodiment is provided can be partly or entirely to be located locally end
The application of the terminal device on the vehicles is specified at end, or can also be to be arranged in inserting in the application of local terminal
The functional unit such as part or SDK (Software Development Kit, SDK), or can also be positioned at net
Processing engine in the server of network side, or can also be positioned at network side distributed system, the present embodiment to this without
It is particularly limited to.
It is understood that the application can be mounted in the local program (nativeApp) in terminal, or may be used also
To be a web page program (webApp) of browser in terminal, the present embodiment is to this without being particularly limited to.
Alternatively, in a possible implementation of the present embodiment, the acquiring unit 21 specifically can be used for root
According to the attribute data of the user, the target POI is obtained；Or according to the nearest inquiry operation of the user, obtain described
Target POI；Or according to the current inquiry operation of the user, obtain the target POI；Or according to the current institute of the user
Position, obtain the target POI.
Alternatively, in a possible implementation of the present embodiment, the associative cell 22 can also be used further
In the user behavior data for obtaining the whole network user；According to the user behavior data, the incidence relation between POI two-by-two is obtained；
And according to the relevant parameter of the incidence relation between the incidence relation between the POI two-by-two and the POI two-by-two, using society
Area finds algorithm, carries out POI clustering processings, to obtain at least one POI cluster with tree structure relation, for according to institute
State target POI, obtain the target POI clusters belonging to the target POI, and according to the target POI clusters, obtain with it is described
There is the homogeneity POI clusters of homogeneity incidence relation between target POI clusters.
In the implementation process, the relevant parameter of the incidence relation between the POI two-by-two used can be described two
The support of incidence relation between two POI, or can also be the support of the incidence relation between the POI two-by-two and institute
The cosine similarity of the incidence relation between POI two-by-two is stated, the present embodiment is to this without being particularly limited to.
Alternatively, in a possible implementation of the present embodiment, the associative cell 22 specifically can be used for root
According to the relevant parameter of the incidence relation between the POI two-by-two, the incidence relation between the POI two-by-two is carried out at filtering
Reason；And according to the incidence relation between the POI two-by-two after the filtration treatment, using community discovery algorithm, carry out POI and gather
Class processing, to obtain at least one POI cluster with tree structure relation.
Alternatively, in a possible implementation of the present embodiment, the recommendation unit 23 specifically can be according to institute
State the structure distance between homogeneity POI clusters and the target POI, prioritizing selection leaf section identical with the target POI clusters
The homogeneity POI clusters of point, recommend the user.If selected homogeneity POI clusters are unsatisfactory for that POI quantity can be recommended, selection
The homogeneity POI clusters of the brotgher of node of father's node identical with the target POI clusters, recommend the user, by that analogy,
Untill selected homogeneity POI clusters satisfaction can recommend POI quantity.
In the implementation, target POI can be obtained according to the constructed POI cluster set with tree structure
Cluster and should with the structure in POI cluster set of tree structure in other POI clusters between each homogeneity POI clusters away from
From.Structure between target POI clusters and some homogeneity POI clusters illustrates target POI clusters and some homogeneity apart from smaller
Similarity between POI clusters is higher, more should preferential recommendation to user.
Specifically, specifically can root when the recommendation unit 23 is to user's recommendation selected homogeneity POI clusters
According to the temperature of each POI in homogeneity POI clusters, according to order from big to small, selected homogeneity POI groups are recommended to user
POI in cluster.
So, to recommend the homogeneity with user's target POI homogeneities interested to user by using POI semantic structures
POI clusters, the structure can preferably catch the inner link between POI, so also can preferably find interested with user
POI homogeneities POI.
It should be noted that method in the corresponding embodiments of Fig. 1, the POI recommendation apparatus that can be provided by the present embodiment is real
It is existing.The related content that may refer in the corresponding embodiments of Fig. 1 is described in detail, here is omitted.
In the present embodiment, by user of the associative cell according to acquired in acquiring unit target POI interested, institute is obtained
The target POI clusters belonging to target POI are stated, and then according to the target POI clusters, are obtained between the target POI clusters
Homogeneity POI clusters with homogeneity incidence relation so that recommendation unit can be according to the homogeneity POI clusters and the target
Structure distance between POI, the closest homogeneity POI clusters of selection structure, recommends the user, due to being closed using homogeneity
The excavation of connection relation so that each POI clusters divided disclosure satisfy that the particular demands of user, therefore, is suitable as recommending
Based process unit, accurately to user recommend the user may POI interested or it should be understood that POI, so as to carry
The success rate that high POI recommends.
In addition, using technical scheme provided by the present invention, POI division is more accurate, will not be because of the passes of POI in itself
Keyword, or loss of learning cause to divide indefinite or even mistake.
In addition, using technical scheme provided by the present invention, can be needed to select different levels according to different scenes, it is different
The POI of semantic granularity.
In addition, using technical scheme provided by the present invention, being capable of significant increase Consumer's Experience.
Fig. 3 shows the block diagram suitable for being used for the exemplary computer system/server 12 for realizing embodiment of the present invention.
The computer system/server 12 that Fig. 3 is shown is only an example, to the function of the embodiment of the present invention and should not use scope
Bring any limitation.
As shown in figure 3, computer system/server 12 is showed in the form of universal computing device.Computer system/service
The component of device 12 can include but is not limited to：One or more processor or processing unit 16, storage device or system
Memory 28, the bus 18 of connection different system component (including system storage 28 and processing unit 16).
Bus 18 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.Lift
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA (MAC)
Bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Computer system/server 12 typically comprises various computing systems computer-readable recording medium.These media can be appointed
What usable medium that can be accessed by computer system/server 12, including volatibility and non-volatile media, it is moveable and
Immovable medium.
System storage 28 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Computer system/server 12 may further include other removable
Dynamic/immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for
Read and write immovable, non-volatile magnetic media (Fig. 3 is not shown, is commonly referred to as " hard disk drive ").Although not showing in Fig. 3
Going out, can providing for the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable
The CD drive of anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases,
Each driver can be connected by one or more data media interfaces with bus 18.System storage 28 can be included extremely
A few program product, the program product has one group of (for example, at least one) program module, and these program modules are configured to
Perform the function of various embodiments of the present invention.
Program/utility 40 with one group of (at least one) program module 42, can be stored in such as system storage
In device 28, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other
The realization of network environment is potentially included in each or certain combination in program module and routine data, these examples.Journey
Sequence module 42 generally performs function and/or method in embodiment described in the invention.
Computer system/server 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, aobvious
Show device 24 etc.) communicate, the equipment that can also enable a user to interact with the computer system/server 12 with one or more is led to
Letter, and/or any set with make it that the computer system/server 12 communicated with one or more of the other computing device
Standby (such as network interface card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 44.And
And, computer system/server 12 can also pass through network adapter 20 and one or more network (such as LAN
(LAN), wide area network (WAN) and/or public network, such as internet) communication.As illustrated, network adapter 20 passes through bus
18 communicate with other modules of computer system/server 12.It should be understood that although not shown in the drawings, computer can be combined
Systems/servers 12 use other hardware and/or software module, include but is not limited to：Microcode, device driver, at redundancy
Manage unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 is stored in program in system storage 28 by operation, thus perform various function application and
Data processing, for example, realize that the POI that the embodiment corresponding to Fig. 1 is provided recommends method.
Another embodiment of the present invention additionally provides a kind of computer-readable recording medium, is stored thereon with computer program,
The program realizes that the POI that the embodiment corresponding to Fig. 1 is provided recommends method when being executed by processor.
Specifically, any combination of one or more computer-readable media can be used.Computer-readable medium
Can be computer-readable signal media or computer-readable recording medium.Computer-readable recording medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specifically example (non exhaustive list) of computer-readable recording medium includes：With one or more wires
Electrical connection, portable computer diskette, hard disk, random access memory (RAM), read-only storage (ROM), erasable type can compile
Journey read-only storage (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic
Memory device or above-mentioned any appropriate combination.In this document, computer-readable recording medium can be any includes
Or the tangible medium of storage program, the program can be commanded execution system, device or device using or in connection make
With.
Computer-readable signal media can be included in a base band or as the data-signal of carrier wave part propagation,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium beyond computer-readable recording medium, the computer-readable medium can send, propagate or
Transmit for being used or program in connection by instruction execution system, device or device.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but do not limit
In --- wireless, electric wire, optical cable, RF etc., or above-mentioned any appropriate combination.
It can be write with one or more programming languages or its combination for performing the computer that the present invention is operated
Program code, described program design language includes object oriented program language-such as Java, Smalltalk, C++,
Also include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
Fully perform, partly perform on the user computer on the user computer, as independent software kit execution, a portion
Divide part execution or the execution completely on remote computer or server on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can be by the network of any kind --- including LAN (LAN) or
Wide area network (WAN) --- subscriber computer is connected to, or, it may be connected to outer computer (for example utilizes Internet service
Provider comes by Internet connection).
It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, for example, multiple units or group
Part can combine or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown
Or the coupling each other discussed or direct-coupling or communication connection can be by some interfaces, device or unit it is indirect
Coupling is communicated to connect, and can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit to realize.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (14)
1. a kind of POI recommends method, it is characterised in that including：
Obtain user target POI interested；
According to the target POI, the target POI clusters belonging to the target POI are obtained；
According to the target POI clusters, the homogeneity POI groups between the target POI clusters with homogeneity incidence relation are obtained
Cluster；
According to the structure distance between the homogeneity POI clusters and the target POI, the closest homogeneity POI of selection structure
Cluster, recommends the user.
2. according to the method described in claim 1, it is characterised in that described to obtain user target POI interested, including：
According to the attribute data of the user, the target POI is obtained；Or
According to the nearest inquiry operation of the user, the target POI is obtained；Or
According to the current inquiry operation of the user, the target POI is obtained；Or
The position being currently located according to the user, obtains the target POI.
3. method according to claim 1 or 2, it is characterised in that described according to the target POI, obtains the target
Before target POI clusters belonging to POI, in addition to：
Obtain the user behavior data of the whole network user；
According to the user behavior data, the incidence relation between POI two-by-two is obtained；
According to the relevant parameter of the incidence relation between the incidence relation between the POI two-by-two and the POI two-by-two, using society
Area finds algorithm, carries out POI clustering processings, to obtain at least one POI cluster with tree structure relation, for according to institute
State target POI, obtain the target POI clusters belonging to the target POI, and according to the target POI clusters, obtain with it is described
There is the homogeneity POI clusters of homogeneity incidence relation between target POI clusters.
4. method according to claim 3, it is characterised in that the relevant parameter of the incidence relation between the POI two-by-two,
Including：
The support of incidence relation between the POI two-by-two；Or
The cosine similarity of incidence relation between the support of incidence relation between the POI two-by-two and the POI two-by-two.
5. method according to claim 3, it is characterised in that incidence relation described in the basis two-by-two between POI and
The relevant parameter of incidence relation between the POI two-by-two, using community discovery algorithm, carries out POI clustering processings, to be had
There is at least one POI cluster of tree structure relation, including：
According to the relevant parameter of the incidence relation between the POI two-by-two, the incidence relation between the POI two-by-two was carried out
Filter is handled；
According to the incidence relation between the POI two-by-two after the filtration treatment, using community discovery algorithm, POI clusters are carried out
Processing, to obtain at least one POI cluster with tree structure relation.
6. the method according to Claims 1 to 5 any claim, it is characterised in that described according to the homogeneity POI groups
Structure distance between cluster and the target POI, the closest homogeneity POI clusters of selection structure, recommends the user, wraps
Include：
According to the structure distance between the homogeneity POI clusters and the target POI, prioritizing selection and the target POI clusters
The homogeneity POI clusters of identical leaf node, recommend the user；
If selected homogeneity POI clusters are unsatisfactory for that POI quantity can be recommended, Father's Day identical with the target POI clusters is selected
The homogeneity POI clusters of the brotgher of node of point, recommend the user, by that analogy, until selected homogeneity POI clusters are met
Untill POI quantity can be recommended.
7. a kind of POI recommendation apparatus, it is characterised in that including：
Acquiring unit, the target POI interested for obtaining user；
Associative cell, for according to the target POI, obtaining the target POI clusters belonging to the target POI；
The associative cell, is additionally operable to according to the target POI clusters, obtain has homogeneity between the target POI clusters
The homogeneity POI clusters of incidence relation；
Recommendation unit, for according to the structure distance between the homogeneity POI clusters and the target POI, selecting structure distance
Nearest homogeneity POI clusters, recommend the user.
8. device according to claim 7, it is characterised in that the acquiring unit, specifically for
According to the attribute data of the user, the target POI is obtained；Or
According to the nearest inquiry operation of the user, the target POI is obtained；Or
According to the current inquiry operation of the user, the target POI is obtained；Or
The position being currently located according to the user, obtains the target POI.
9. the device according to claim 7 or 8, it is characterised in that the associative cell, is additionally operable to
Obtain the user behavior data of the whole network user；
According to the user behavior data, the incidence relation between POI two-by-two is obtained；And
According to the relevant parameter of the incidence relation between the incidence relation between the POI two-by-two and the POI two-by-two, using society
Area finds algorithm, carries out POI clustering processings, to obtain at least one POI cluster with tree structure relation, for according to institute
State target POI, obtain the target POI clusters belonging to the target POI, and according to the target POI clusters, obtain with it is described
There is the homogeneity POI clusters of homogeneity incidence relation between target POI clusters.
10. device according to claim 9, it is characterised in that the association ginseng of the incidence relation between the POI two-by-two
Number, including：
The support of incidence relation between the POI two-by-two；Or
The cosine similarity of incidence relation between the support of incidence relation between the POI two-by-two and the POI two-by-two.
11. device according to claim 9, it is characterised in that the associative cell, specifically for
According to the relevant parameter of the incidence relation between the POI two-by-two, the incidence relation between the POI two-by-two was carried out
Filter is handled；
According to the incidence relation between the POI two-by-two after the filtration treatment, using community discovery algorithm, POI clusters are carried out
Processing, to obtain at least one POI cluster with tree structure relation.
12. the device according to claim 7~11 any claim, it is characterised in that recommendation unit, specifically for
According to the structure distance between the homogeneity POI clusters and the target POI, prioritizing selection and the target POI clusters
The homogeneity POI clusters of identical leaf node, recommend the user；
If selected homogeneity POI clusters are unsatisfactory for that POI quantity can be recommended, Father's Day identical with the target POI clusters is selected
The homogeneity POI clusters of the brotgher of node of point, recommend the user, by that analogy, until selected homogeneity POI clusters are met
Untill POI quantity can be recommended.
13. a kind of equipment, it is characterised in that the equipment includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors are real
The existing method as described in any in claim 1~6.
14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The method as described in any in claim 1~6 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710209459.6A CN107169012B (en) | 2017-03-31 | 2017-03-31 | POI recommendation method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710209459.6A CN107169012B (en) | 2017-03-31 | 2017-03-31 | POI recommendation method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107169012A true CN107169012A (en) | 2017-09-15 |
| CN107169012B CN107169012B (en) | 2021-03-19 |
Family
ID=59849056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710209459.6A Active CN107169012B (en) | 2017-03-31 | 2017-03-31 | POI recommendation method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169012B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127284A (en) * | 2019-11-11 | 2020-05-08 | 阿里巴巴集团控股有限公司 | Site selection method, recommendation method, equipment and storage medium for traffic stop station |
| CN111382138A (en) * | 2018-12-27 | 2020-07-07 | 中国移动通信集团辽宁有限公司 | POI data processing method, device, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488789A (en) * | 2013-10-08 | 2014-01-01 | 百度在线网络技术（北京）有限公司 | Recommendation method, recommendation device and search engine |
| CN104123398A (en) * | 2014-08-15 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN104391853A (en) * | 2014-09-25 | 2015-03-04 | 深圳大学 | POI (point of interest) recommending method, POI information processing method and server |
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| US9129227B1 (en) * | 2012-12-31 | 2015-09-08 | Google Inc. | Methods, systems, and media for recommending content items based on topics |
| CN105808698A (en) * | 2016-03-03 | 2016-07-27 | 江苏大学 | Internet-of-things user query request-oriented TOP-k position point-of-interest recommendation method |
-
2017
- 2017-03-31 CN CN201710209459.6A patent/CN107169012B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9129227B1 (en) * | 2012-12-31 | 2015-09-08 | Google Inc. | Methods, systems, and media for recommending content items based on topics |
| CN103488789A (en) * | 2013-10-08 | 2014-01-01 | 百度在线网络技术（北京）有限公司 | Recommendation method, recommendation device and search engine |
| CN104123398A (en) * | 2014-08-15 | 2014-10-29 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN104391853A (en) * | 2014-09-25 | 2015-03-04 | 深圳大学 | POI (point of interest) recommending method, POI information processing method and server |
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN105808698A (en) * | 2016-03-03 | 2016-07-27 | 江苏大学 | Internet-of-things user query request-oriented TOP-k position point-of-interest recommendation method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382138A (en) * | 2018-12-27 | 2020-07-07 | 中国移动通信集团辽宁有限公司 | POI data processing method, device, equipment and medium |
| CN111382138B (en) * | 2018-12-27 | 2023-04-07 | 中国移动通信集团辽宁有限公司 | POI data processing method, device, equipment and medium |
| CN111127284A (en) * | 2019-11-11 | 2020-05-08 | 阿里巴巴集团控股有限公司 | Site selection method, recommendation method, equipment and storage medium for traffic stop station |
| CN111127284B (en) * | 2019-11-11 | 2023-06-20 | 阿里巴巴集团控股有限公司 | Address selection method, recommendation method, device and storage medium for traffic stop sites |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107169012B (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133263A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN107085600A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| US20190354555A1 (en) | Dynamic faceting for personalized search and discovery | |
| CN107391592A (en) | Processing method, device, equipment and the computer-readable recording medium of geography fence | |
| CN102135983A (en) | Group dividing method and device based on network user behavior | |
| CN108133357A (en) | A kind of talent recommendation method and computing device | |
| CN111314063A (en) | Big data information management method, system and device based on Internet of things | |
| CN107169005A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN107085599A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN110674397B (en) | Method, device, equipment and readable medium for training age point prediction model | |
| CN111126422B (en) | Method, device, equipment and medium for establishing industry model and determining industry | |
| CN107169012A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN107478243A (en) | Air navigation aid, device, equipment and computer-readable recording medium | |
| CN107729944B (en) | Identification method and device of popular pictures, server and storage medium | |
| CN107169014B (en) | POI recommendation method, device, equipment and computer readable storage medium | |
| CN107169015A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN107193861A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN107180073A (en) | POI recommends method, device, equipment and computer-readable recording medium | |
| CN109345175A (en) | Source of goods method for pushing, system, equipment and storage medium based on driver's matching degree | |
| CN111353864B (en) | Product recommendation method and device, server and storage medium | |
| CN109542986B (en) | Element normalization method, device, equipment and storage medium of network data | |
| CN114265981A (en) | Recommendation word determining method, device, equipment and storage medium | |
| CN107421536A (en) | Panorama gathers localization method, device, equipment and the computer-readable recording medium of picture point | |
| CN110516860A (en) | Processing method, equipment and the computer readable storage medium of weather forecasting data | |
| CN108280139A (en) | Processing method, device, equipment and the computer readable storage medium of POI data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |