CN109068272A - Similar users recognition methods, device, equipment and readable storage medium storing program for executing - Google Patents
Similar users recognition methods, device, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109068272A CN109068272A CN201811005730.5A CN201811005730A CN109068272A CN 109068272 A CN109068272 A CN 109068272A CN 201811005730 A CN201811005730 A CN 201811005730A CN 109068272 A CN109068272 A CN 109068272A
- Authority
- CN
- China
- Prior art keywords
- access point
- wireless access
- fingerprint
- print data
- cluster
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention provides a kind of similar users recognition methods, device, equipment and readable storage medium storing program for executing, and each wireless access point finger print data in default wireless access point fingerprint database is clustered into multiple wireless access point fingerprint clusters;According to the number of the wireless access point finger print data in each wireless access point fingerprint cluster, the fingerprint cluster is ranked up;Default number of clusters before being extracted in ranking results, and the number of wireless access point finger print data described in the fingerprint cluster is greater than the wireless access point fingerprint cluster of the first preset number, the wireless access point fingerprint characteristic vector as user;Calculate the similarity between the wireless access point fingerprint characteristic vector;The similarity between corresponding user is determined according to the similarity between the wireless access point fingerprint characteristic vector.Solves the problems, such as to can not achieve more accurately similar users identification due to generating same position under different consumption scenes because of user in the prior art.
Description
Technical field
The present embodiments relate to electronic technology field more particularly to a kind of similar users recognition methods, device, equipment and
Readable storage medium storing program for executing.
Background technique
While social application and shopping application are universal, generate a large amount of user data, wherein according to user data into
Row user's similarity analysis is the important one aspect of user behavior analysis.
In the prior art, main to extract the position and time that user's communication behavior occurs by obtaining, it is opposite to calculate user
Common index in base station, and the feature vector that user often uses base station is extracted according to this, and then calculate the phase between different user
Like degree index.
Although, since base station range is wider, base station is special however, the above method has the generality of application
Vector is levied for the characterization of user behavior and inaccurate, different consumption scenes under same market is will cause and generates asking for same position
Topic.
Summary of the invention
The present invention provides a kind of similar users recognition methods, to solve in first technology because user is under different consumption scenes
It leads to the problem of same position and can not achieve more accurately similar users identification.
According to the first aspect of the invention, a kind of similar users recognition methods is provided, which comprises
Each wireless access point finger print data in default wireless access point fingerprint database is clustered into multiple wireless
Access point fingerprint cluster;
According to the number of the wireless access point finger print data in each wireless access point fingerprint cluster, by the fingerprint cluster into
Row sequence;
Default number of clusters before being extracted in ranking results, and the number of wireless access point finger print data described in the fingerprint cluster
Wireless access point fingerprint characteristic vector greater than the wireless access point fingerprint cluster of the first preset number, as user;
Calculate the similarity between the wireless access point fingerprint characteristic vector;
The similarity between corresponding user is determined according to the similarity between the wireless access point fingerprint characteristic vector.
According to the second aspect of the invention, a kind of similar users identification device is provided, described device includes:
Cluster module, for gathering each wireless access point finger print data in default wireless access point fingerprint database
Class is at multiple wireless access point fingerprint clusters;
Sorting module, for the number according to the wireless access point finger print data in each wireless access point fingerprint cluster,
The fingerprint cluster is ranked up;
Feature vector determining module, for presetting number of clusters, and nothing described in the fingerprint cluster before extracting in ranking results
The number of line access point finger print data is greater than the wireless access point fingerprint cluster of the first preset number, the wireless access point as user
Fingerprint characteristic vector;
Similarity calculation module, for calculating the similarity between the wireless access point fingerprint characteristic vector;
Similar users determining module, for according to determining pair of the similarity between the wireless access point fingerprint characteristic vector
Using the similarity between family.
According to the third aspect of the invention we, a kind of equipment is provided, comprising:
Processor, memory and it is stored in the computer journey that can be run on the memory and on the processor
Sequence, which is characterized in that the processor realizes similar users recognition methods as the aforementioned when executing described program.
According to the fourth aspect of the invention, provide a kind of readable storage medium storing program for executing, when the instruction in the storage medium by
When the processor of electronic equipment executes, so that electronic equipment is able to carry out similar users recognition methods above-mentioned.
A kind of similar users recognition methods, device, equipment and readable storage medium storing program for executing provided in an embodiment of the present invention, will preset
Each wireless access point finger print data in wireless access point fingerprint database is clustered into multiple wireless access point fingerprint clusters;Root
According to the number of the wireless access point finger print data in each wireless access point fingerprint cluster, the fingerprint cluster is ranked up;?
Default number of clusters before being extracted in ranking results, and the number of wireless access point finger print data described in the fingerprint cluster is greater than first in advance
Wireless access point fingerprint characteristic vector if the wireless access point fingerprint cluster of number, as user;Calculate the wireless access point
Similarity between fingerprint characteristic vector;It determines according to the similarity between the wireless access point fingerprint characteristic vector to application
Similarity between family.Solve in the prior art to user behavior characterize it is inaccurate, cause user in different consumption scenes
It is lower to lead to the problem of same position.Have and be more suitable for indoor scene, and more segmented user's scene, improves user's similarity and determine
The beneficial effect of precision.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of step flow chart of similar users recognition methods provided in an embodiment of the present invention;
Fig. 2 is a kind of step flow chart of similar users recognition methods provided in an embodiment of the present invention;
Fig. 3 is a kind of structure chart of similar users identification device provided in an embodiment of the present invention;
Fig. 4 is a kind of structure chart of similar users identification device provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
The term being related in the embodiment of the present invention is introduced first below:
Wi-Fi fingerprint: GPS is difficult to solve some orientation problems under indoor environment, all exists under most of indoor environment
WiFi, therefore positioning is carried out without additional deployment hardware device using WiFi, it is the method for saving very much cost.Due to letter
Number deep fades and multipath effect, general outdoor positioning facility (such as GPS) can not effectively work in building.
Positioning accuracy is also a problem, which building is GPS perhaps may indicate that mobile device at, but under indoor scene,
It is desirable to obtain more accurate indoor location, this needs more accurate cartographic information and higher positioning accuracy.Based on wireless
What the localization method of signal considered first is to use WiFi (WLAN based on IEEE802.11 standard) as basic location facilities.
But WiFi signal is not to design for positioning, usually single antenna, bandwidth are small, and indoor complicated signal passes
Broadcasting environment is difficult to realize traditional distance measuring method based on arrival time/reaching time-difference (TOA/TDOA), based on arrival
The method of signal angle is similarly difficult to realize, if installing the antenna that can be oriented in WiFi network needs additional flower again
Take.Therefore, the mainly location fingerprint method that everybody studies in detail in recent years.
WiFi is widely used in all kinds of large-scale or aediculas such as family, hotel, coffee-house, airport, market, in this way
So that WiFi becomes a most noticeable wireless technology in positioning field.In general, a WiFi system is by some fixations
Access point (AP) composition, they are deployed in the position being easily installed more indoors, system or network administrator it is generally known this
The position of a little AP.Can connect the mobile device (such as laptop, mobile phone) of WiFi between each other can directly or
It is grounded (passing through AP) communication, it can be considered to realize positioning function simultaneously outside communication function.
Wherein, " location fingerprint " connects the position in actual environment with certain " fingerprint ", a position corresponding one
A unique fingerprint.It can be the corresponding unique fingerprint of a Wi-Fi Hotspot herein, and map a specific position
It sets, this fingerprint can be one-dimensional or multidimensional, for example equipment to be positioned is receiving or sending information, then fingerprint can be
One feature or multiple features (most commonly signal strength) of this information or signal.If equipment to be positioned is to send
Signal perceives the signal of equipment to be positioned by the receiving device of some fixations or then information is positioned to it, and this mode is usually
It is called long range positioning or network positions.The signal or information of the sending device of some fixations are received if it is equipment to be positioned,
Then the position of itself is estimated according to the feature that these are detected, this mode can be described as self poisoning.Movement to be positioned is set
It is standby perhaps can it detects that feature be communicated to the server node in network, server, which can use it, can be obtained institute
There is information to estimate the position of mobile device, this mode can be described as mixed positioning.In all these modes, handle is required
The signal characteristic perceived is taken away the signal characteristic in one database of matching, this process is considered as a pattern-recognition
Problem.
Location fingerprint can be a plurality of types of, and (helpful to the demarcation of location) feature of any " position unique " can
It is used as a location fingerprint.For example the multidiameter configuration of signal of communication on some position, whether can detect on some position
The RSS (received signal strength) from base station signal that is detected on to access point or base station, some position, lead on some position
The two-way time of signal or delay when letter, these can act as a location fingerprint, or can also be combined as
Location fingerprint.We introduce two kinds of most common signal characteristics: multidiameter configuration, RSS below.
Embodiment one
Referring to Fig.1, it illustrates a kind of step flow charts of similar users recognition methods, the specific steps of which are as follows:
Step 101, each wireless access point finger print data in default wireless access point fingerprint database is clustered into
Multiple wireless access point fingerprint clusters.
In the embodiment of the present invention, when user's carrying mobile terminal carries out commercial activity in an application scenarios, due to moving
Dynamic terminal can regularly obtain the location data of user, wherein GPS solution and its longitude and latitude label generated are mesh
The recognised standard of preceding geographic position data, and most of smart phone obtain the basic mode in user geographical location.As long as with
GPS positioning function is opened at family, and mobile phone can be obtained related data, when the GPS chip of mobile device cannot receive GPS signal
When, mobile device just needs the cell tower being connect with it to communicate and estimate the distance between it and signal tower constantly to report
The geographic position data accusing its geographical location, however obtaining by this method is accurate not as good as pure GPS data.The application
In middle embodiment by taking Wi-Fi connection as an example, the method that the Wi-Fi connection utilized obtains user's location data is that one kind being capable of essence
The method for really obtaining geographic position data, but need to use effective Wi-Fi Hotspot, the address of Wi-Fi and GPS coordinate are one
One is corresponding, it can accurately indicate the location of user, and in many customer consumption places, many retailers are mentioned
For free Wi-Fi Hotspot, by extracting the Wi-Fi finger print data in each Wi-Fi Hotspot for user current location at random,
And clustered, generate each Wi-Fi fingerprint classification.
Wherein, it is clustered in this application using the cosine similarity between each Wi-Fi finger print data, however in reality
In, clustering method is unlimited, and the embodiments of the present invention are not limited thereto.
It step 102, will be described according to the number of the wireless access point finger print data in each wireless access point fingerprint cluster
Fingerprint cluster is ranked up.
In the embodiment of the present invention, after the cluster result for obtaining Wi-Fi finger print data, according to the Wi-Fi in each classification
The number of finger print data carries out sequence from high to low.
Step 103, default number of clusters before being extracted in ranking results, and wireless access point fingerprint number described in the fingerprint cluster
According to number be greater than the wireless access point fingerprint cluster of the first preset number, wireless access point fingerprint characteristic vector as user.
In the embodiment of the present invention, in the ranking results that step 102 obtains, M classification before screening wherein, and each class
Wi-Fi finger print data in not is more than the classification of the first preset data PrintVal, the Wi-Fi fingerprint category feature as user.
Step 104, the similarity between the wireless access point fingerprint characteristic vector is calculated.
In the embodiment of the present invention, the similarity between any two fingerprint category feature is calculated according to the following formula:
Wherein, S is the similarity between the Wi-Fi fingerprint characteristic of user a and b, WaWith WbWi-Fi for user a and b refers to
Line class, Wa·WbFor the cosine similarity of fingerprint, xaWith ybRespectively fingerprint Wa, WbFingerprint quantity.
Step 105, it is determined between corresponding user according to the similarity between the wireless access point fingerprint characteristic vector
Similarity.
In the embodiment of the present invention, the similarity between two fingerprint category features is calculated according to above-mentioned steps, can be learnt pair
Using the similarity between family, if similarity S is greater than preset value, it is judged that two users have similar behavior spy
Sign.
It is to be appreciated that wireless access point in the embodiment of the present invention is illustrated by taking WiFi as an example, in reality
In, it is also possible to carry out wireless access by modes such as bluetooth, mobile phone hot spots, the comparison embodiment of the present invention is not limited
System.
In conclusion a kind of similar users recognition methods provided in an embodiment of the present invention, by default wireless access point fingerprint
Each wireless access point finger print data in database is clustered into multiple wireless access point fingerprint clusters;It described is wirelessly connect according to each
The fingerprint cluster is ranked up by the number of the wireless access point finger print data in access point fingerprint cluster;It is extracted in ranking results
Preceding default number of clusters, and the number of wireless access point finger print data described in the fingerprint cluster is greater than wirelessly connecing for the first preset number
Access point fingerprint cluster, the wireless access point fingerprint characteristic vector as user;Calculate the wireless access point fingerprint characteristic vector it
Between similarity;It is determined according to the similarity between the wireless access point fingerprint characteristic vector similar between corresponding user
Degree.Solve in the prior art to user behavior characterize it is inaccurate, cause user to generate identical bits under different consumption scenes
The problem of setting.Have and be more suitable for indoor scene, and more segmented user's scene, improves the beneficial effect of user's similarity judgement precision
Fruit.
Embodiment two
Referring to Fig. 2, it illustrates a kind of step flow charts of similar users recognition methods, the specific steps of which are as follows:
Step 201, the network positions data of user are obtained.
In the embodiment of the present invention, when carry out activity in user indoors scene, the net of user is obtained by Wi-Fi Hotspot
Network location data, and Wi-Fi finger print data therein is extracted, and remove invalid Wi-Fi, such as move Wi-Fi, it is large-scale
Wi-Fi, the weak Wi-Fi etc. of signal strength.
Step 202, from extracted in the network positions data corresponding wireless access point finger print data and on call time.
In the embodiment of the present invention, when extracting corresponding Wi-Fi finger print data in network positions data, while the net is extracted
It calls time in network location data.
Specifically, each wireless aps (router) has a globally unique MAC Address, and in general wireless
AP will not be moved whithin a period of time, when equipment is in the case where opening Wi-Fi, can scan and collect the AP signal of surrounding,
Regardless of whether encryption, or whether have connected or even signal strength is not enough to be shown in wireless signal list, it can obtain
These data that can indicate AP are sent location server by the MAC Address broadcast out to AP, equipment, and server retrieves
The geographical location of each AP, and combine the degree of strength of each signal, calculate the geographical location of equipment and return to user
Equipment, location-based service quotient will constantly update, supplement the database of oneself, to guarantee the accuracy of data, as extraction active user
When the position data of equipment, while obtaining current network time.
Step 203, the time interval of each wireless access point finger print data is calculated according to calling time on described.
In the embodiment of the present invention, by each Wi-Fi finger print data of extraction and it is corresponding on call time, calculate wherein
Time interval just do not retain, if time interval is less than prefixed time interval for example, two positioning intervals are less than
One second, then the location data that the latter obtains is without retaining, because in practical applications, one second time was not enough to user
Location data largely changed.
Certainly, in practical applications, preset time is set according to actual needs by related technical personnel, and the present invention is real
It is without restriction to this to apply example.
Step 204, the time interval is extracted greater than prefixed time interval and signal strength is greater than the wireless of preset strength
Access point finger print data generates default wireless access point fingerprint database.
In the embodiment of the present invention, for the Wi-Fi fingerprint number of multiple and different Wi-Fi Hotspots of the position acquisition of active user
According to wherein time interval being greater than prefixed time interval, and signal strength enough Wi-Fi finger print datas storage, and generate one
A default Wi-Fi fingerprint database.
Step 205, the second preset number is randomly selected in the default wireless access point fingerprint database wirelessly to connect
Access point finger print data.
Step 206, according to the first cosine similarity between the second preset number wireless access point finger print data
With the relationship of preset threshold, initial wireless access point fingerprint cluster is generated.
In the embodiment of the present invention, N number of finger print data is randomly selected as N in the Wi-Fi preset fingerprint database of generation
A fingerprint cluster, the fingerprint number that each class includes are 1, calculate separately the similarity between N number of fingerprint class, if the similarity is super
Cross preset threshold, then it is similar between two classes of confirmation, they are merged into a class, has all been compared until between all N number of classes
Finish, finally obtains Nf initial fingerprint cluster, due to the merging of classification, Nf is less than or equal to N.
Preferably, step 206, it specifically includes: sub-step A1-A4;
Sub-step A1, at the beginning of setting the second preset number for the second preset number wireless access point finger print data
Beginning wireless access point fingerprint cluster, each initial wireless access point fingerprint cluster include a wireless access point finger print data;
Sub-step A2 calculates the first cosine similarity between the initial wireless access point fingerprint cluster;
The initial wireless access point fingerprint cluster that cosine similarity is greater than preset threshold is merged into one by sub-step A3
Initial wireless access point fingerprint cluster;
Sub-step A4 keeps the initial wireless access point fingerprint cluster that cosine similarity is less than the preset threshold not
Become.
Specifically, it is poly- as N number of fingerprint to randomly select N number of Wi-Fi finger print data in Wi-Fi preset fingerprint database
Class, i.e., the Wi-Fi fingerprint number that each class includes are 1, then calculate separately the cosine similarity between this N number of fingerprint class, example
Such as, if the cosine similarity SKnn of the fingerprint of fingerprint cluster cluster clusterA and fingerprint cluster cluster clusterB is more than preset threshold
Fingerprint cluster cluster clusterA and fingerprint cluster cluster clusterB are then merged into a fingerprint cluster, and choose and refer to by VWeight
Feature of the Wi-Fi finger print data as fingerprint class in line clustering cluster clusterA, and the fingerprint number of clusterA is increased
1, by fingerprint cluster cluster clusterC with merge after fingerprint cluster cluster clusterA calculate cosine similarity, if if fingerprint cluster
The cosine similarity SKnn of the fingerprint of cluster clusterA and fingerprint cluster cluster clusterC is more than preset threshold VWeight, then will
Fingerprint cluster cluster clusterC merges with fingerprint cluster cluster clusterA, still by the Wi-Fi in fingerprint cluster cluster clusterA
Feature of the finger print data as fingerprint class keeps two fingerprint clusters constant, calculates cosine similarity with other fingerprint clusters
Afterwards, and the fingerprint number of clusterA increase by 1, at this point, the fingerprint number of clusterA is 3, if fingerprint cluster cluster
The cosine similarity SKnn of the fingerprint of clusterA and fingerprint cluster cluster clusterB is less than preset threshold VWeight, then protects
It is constant to hold two clusters, is then compared again with preset threshold VWeight with other again, and repeat the conjunction of foregoing description
And step.
And so on, N number of fingerprint cluster cluster is calculated into cosine similarity from each other, is more than default threshold by cosine similarity
The cluster of value merges, and is less than remaining unchanged for preset threshold, finally obtains Nf initial fingerprint cluster, wherein Nf is less than
Or it is equal to N.
Step 207, the remaining wireless access point in the default wireless access point fingerprint database is calculated separately to refer to
The second cosine between line data and original wireless access point finger print data in each initial wireless access point fingerprint cluster is similar
Degree.
Step 208, according to the relationship of second cosine similarity and the preset threshold, the wireless access point is referred to
Line data clusters are at multiple wireless access point fingerprint clusters.
It, will be in default Wi-Fi fingerprint database after obtaining Nf initial Wi-Fi fingerprint clusters in the embodiment of the present invention
In other remaining Wi-Fi finger print datas, one by one with Nf initial fingerprint cluster calculation cosine similarity, i.e. the second cosine is similar
Degree, is then compared with preset threshold, is clustered each Wi-Fi finger print data according to comparison result, until all Wi-Fi
Finger print data all clusters completion.
Preferably, step 208, it specifically includes: sub-step B1-B2;
Sub-step B1, if second cosine similarity is greater than the preset threshold, by the wireless access point fingerprint
Data are added in the corresponding initial wireless access point fingerprint cluster, generate a wireless access point fingerprint cluster;
The wireless access point finger print data is arranged if the cosine similarity is less than preset threshold by sub-step B2
For new wireless access point fingerprint cluster.
Specifically, for example, to calculate other Wi-Fi fingerprints printA similar to the cosine of this Nf Wi-Fi fingerprint class respectively
SKnn is spent, the maximum Wi-Fi fingerprint class ClusterA of similarity is chosen.If the cosine similarity of two Wi-Fi fingerprints is more than threshold values
VWeight, the then fingerprint number that ClusterA includes increase by 1;If being less than threshold values VWeight, newly-increased one is with printA
The fingerprint number that fingerprint the class ClusterB, ClusterB of fingerprint characteristic include is 1.Above-mentioned sorting procedure is repeated, until all
Wi-Fi finger print data in default Wi-Fi fingerprint database is all assigned to respectively affiliated fingerprint class.
It step 209, will be described according to the number of the wireless access point finger print data in each wireless access point fingerprint cluster
Fingerprint cluster is ranked up.
This step is identical as step 102, and this will not be detailed here.
Step 210, default number of clusters before being extracted in ranking results, and wireless access point fingerprint number described in the fingerprint cluster
According to number be greater than the wireless access point fingerprint cluster of the first preset number, wireless access point fingerprint characteristic vector as user.
In the embodiment of the present invention, after all Wi-Fi fingerprints all cluster completion, according to each Wi-Fi fingerprint classification
In include fingerprint number, sort from high to low, MCluster before extracting, and number N Print is more than the class of PrintVal
Wi-FiCluster, the Wi-Fi fingerprint category feature as user.
Step 211, the similarity between the wireless access point fingerprint characteristic vector is calculated.
This step is identical as step 104, and this will not be detailed here.
Step 212, it is determined between corresponding user according to the similarity between the wireless access point fingerprint characteristic vector
Similarity.
This step is identical as step 105, and this will not be detailed here.
In conclusion a kind of similar users recognition methods provided in an embodiment of the present invention, obtains the network positions number of user
According to;From extracted in the network positions data corresponding wireless access point finger print data and on call time;It is reported according to described
Time calculates the time interval of each wireless access point finger print data;The time interval is extracted greater than prefixed time interval and
Signal strength is greater than the wireless access point finger print data of preset strength, generates default wireless access point fingerprint database.It will preset
Each wireless access point finger print data in wireless access point fingerprint database is clustered into multiple wireless access point fingerprint clusters;Root
According to the number of the wireless access point finger print data in each wireless access point fingerprint cluster, the fingerprint cluster is ranked up;?
Default number of clusters before being extracted in ranking results, and the number of wireless access point finger print data described in the fingerprint cluster is greater than first in advance
Wireless access point fingerprint characteristic vector if the wireless access point fingerprint cluster of number, as user;Calculate the wireless access point
Similarity between fingerprint characteristic vector;It determines according to the similarity between the wireless access point fingerprint characteristic vector to application
Similarity between family.Solve in the prior art to user behavior characterize it is inaccurate, cause user in different consumption scenes
It is lower to lead to the problem of same position.Have and be more suitable for indoor scene, and more segmented user's scene, improves user's similarity and determine
The beneficial effect of precision.
Embodiment three
It is specific as follows it illustrates a kind of structural block diagram of similar users identification device referring to Fig. 3:
Cluster module 301, for by each wireless access point fingerprint number in default wireless access point fingerprint database
According to being clustered into multiple wireless access point fingerprint clusters;
Sorting module 302, for the number according to the wireless access point finger print data in each wireless access point fingerprint cluster
The fingerprint cluster is ranked up by mesh;
Feature vector determining module 303, for number of clusters default before being extracted in ranking results, and described in the fingerprint cluster
The number of wireless access point finger print data is greater than the wireless access point fingerprint cluster of the first preset number, the wireless access as user
Point fingerprint characteristic vector;
Similarity calculation module 304, for calculating the similarity between the wireless access point fingerprint characteristic vector;
Similar users determining module 305, for true according to the similarity between the wireless access point fingerprint characteristic vector
Surely the similarity between user is corresponded to.
Referring to Fig. 4, it illustrates the structural block diagram of another similar users identification device based on Fig. 3 embodiment, tools
Body is as follows:
Location data obtains module 306, for obtaining the network positions data of user;
Wireless access point finger print data and the extraction module 307 that above calls time, for being extracted from the network positions data
Corresponding wireless access point finger print data and on call time;
Time interval computing module 308, for calculating each wireless access point finger print data according to calling time on described
Time interval;
Default wireless access point fingerprint database generation module 309, for extracting the time interval greater than preset time
Interval and signal strength are greater than the wireless access point finger print data of preset strength, generate default wireless access point fingerprint database.
Cluster module 301, for by each wireless access point fingerprint number in default wireless access point fingerprint database
According to being clustered into multiple wireless access point fingerprint clusters;
Preferably, the cluster module 301, comprising:
Wireless access point finger print data chooses submodule 3011, in the default wireless access point fingerprint database
Randomly select the second preset number wireless access point finger print data;
Initial wireless access point fingerprint fasciation is at submodule 3012, for according to the second preset number wireless access
The relationship of the first cosine similarity and preset threshold between point finger print data, generates initial wireless access point fingerprint cluster;
Preferably, the initial wireless access point fingerprint fasciation is at submodule 3012, comprising:
Initial wireless access point fingerprint cluster setting unit is used for the second preset number wireless access point fingerprint number
According to the second preset number initial wireless access point fingerprint cluster is set as, each initial wireless access point fingerprint cluster includes an institute
State wireless access point finger print data;
First cosine similarity computing unit, for calculating the first cosine between the initial wireless access point fingerprint cluster
Similarity;
Combining unit, the initial wireless access point fingerprint cluster for cosine similarity to be greater than preset threshold are merged into
One initial wireless access point fingerprint cluster;
Initial wireless access point fingerprint cluster stick unit, for cosine similarity to be less than the described first of the preset threshold
Beginning wireless access point fingerprint cluster remains unchanged.
Second cosine similarity computational submodule 3013, for calculating separately the default wireless access point fingerprint database
In the remaining wireless access point finger print data refer to original wireless access point in each initial wireless access point fingerprint cluster
The second cosine similarity between line data;
Submodule 3014 is clustered, it, will be described for the relationship according to second cosine similarity and the preset threshold
Wireless access point finger print data is clustered into multiple wireless access point fingerprint clusters.
Preferably, the cluster submodule 3014, comprising:
Wireless access point fingerprint classification generation unit, if being greater than the preset threshold for second cosine similarity,
Then the wireless access point finger print data is added in the corresponding initial wireless access point fingerprint cluster, generates one wirelessly
Access point fingerprint cluster;
Wireless access point fingerprint classification setting unit will be described if being less than preset threshold for the cosine similarity
Wireless access point finger print data is set as new wireless access point fingerprint cluster.
Sorting module 302, for the number according to the wireless access point finger print data in each wireless access point fingerprint cluster
The fingerprint cluster is ranked up by mesh;
Feature vector determining module 303, for number of clusters default before being extracted in ranking results, and described in the fingerprint cluster
The number of wireless access point finger print data is greater than the wireless access point fingerprint cluster of the first preset number, the wireless access as user
Point fingerprint characteristic vector;
Similarity calculation module 304, for calculating the similarity between the wireless access point fingerprint characteristic vector;
Similar users determining module 305, for true according to the similarity between the wireless access point fingerprint characteristic vector
Surely the similarity between user is corresponded to.
The embodiment of the present invention also provides a kind of equipment, comprising: processor, memory and is stored on the memory simultaneously
The computer program that can be run on the processor, which is characterized in that the processor is realized as above when executing described program
Similar users recognition methods described in the one or more stated.
The embodiment of the present invention also provides a kind of readable storage medium storing program for executing, when the instruction in the storage medium is by electronic equipment
When processor executes, so that electronic equipment is able to carry out similar users recognition methods as mentioned.
In conclusion a kind of similar users identification device provided in an embodiment of the present invention, obtains module by location data,
For obtaining the network positions data of user;Later, call time extraction module by wireless access point finger print data and above, is used for
From extracted in the network positions data corresponding wireless access point finger print data and on call time;Recycle time interval meter
Module is calculated, for calculating the time interval of each wireless access point finger print data according to calling time on described;Later using pre-
If wireless access point fingerprint database generation module, for extracting the time interval greater than prefixed time interval and signal strength
Greater than the wireless access point finger print data of preset strength, default wireless access point fingerprint database is generated.Cluster module, being used for will
Each wireless access point finger print data in default wireless access point fingerprint database is clustered into multiple wireless access point fingerprints
Cluster;It will for the number according to the wireless access point finger print data in each wireless access point fingerprint cluster by sorting module
The fingerprint cluster is ranked up;And by feature vector determining module, for number of clusters default before being extracted in ranking results, and
The number of wireless access point finger print data described in the fingerprint cluster is greater than the wireless access point fingerprint cluster of the first preset number, makees
For the wireless access point fingerprint characteristic vector of user;Also by similarity calculation module, for calculating the wireless access point
Similarity between fingerprint characteristic vector;Finally by similar users determining module, for according to the wireless access point fingerprint
Similarity between feature vector determines the similarity between corresponding user.It solves and user behavior is characterized not in the prior art
It is enough accurate, cause user to lead to the problem of same position under different consumption scenes.Have and be more suitable for indoor scene, and more segments
User's scene improves the beneficial effect of user's similarity judgement precision.
It has the advantages that
First, not using user location, and clustered using Wi-Fi fingerprint, as user characteristics point, is more suitable for interior
Scene.
Second, more having segmented user according to similarity calculation user's similarity of different user Wi-Fi fingerprint characteristic vector
Scene, user's judgement precision are higher.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize one in payment information processing equipment according to an embodiment of the present invention
The some or all functions of a little or whole components.The present invention is also implemented as executing method as described herein
Some or all device or device programs (for example, computer program and computer program commodity data).It is such
It realizes that program of the invention can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or with any other shape
Formula provides.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
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, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (12)
1. a kind of similar users recognition methods, which is characterized in that the described method includes:
Each wireless access point finger print data in default wireless access point fingerprint database is clustered into multiple wireless access
Point fingerprint cluster;
According to the number of the wireless access point finger print data in each wireless access point fingerprint cluster, the fingerprint cluster is arranged
Sequence;
Default number of clusters before being extracted in ranking results, and the number of wireless access point finger print data described in the fingerprint cluster is greater than
The wireless access point fingerprint cluster of first preset number, the wireless access point fingerprint characteristic vector as user;
Calculate the similarity between the wireless access point fingerprint characteristic vector;
The similarity between corresponding user is determined according to the similarity between the wireless access point fingerprint characteristic vector.
2. the method according to claim 1, wherein it is described will be in default wireless access point fingerprint database
Before the step of each wireless access point finger print data is clustered into multiple wireless access point fingerprint clusters, further includes:
Obtain the network positions data of user;
From extracted in the network positions data corresponding wireless access point finger print data and on call time;
The time interval of each wireless access point finger print data is calculated according to calling time on described;
Extract the wireless access point fingerprint number that the time interval is greater than preset strength greater than prefixed time interval and signal strength
According to the default wireless access point fingerprint database of generation.
3. the method according to claim 1, wherein described will be each in default wireless access point fingerprint database
The step of wireless access point finger print data is clustered into multiple wireless access point fingerprint clusters, comprising:
The second preset number wireless access point finger print data is randomly selected in the default wireless access point fingerprint database;
According to the first cosine similarity and preset threshold between the second preset number wireless access point finger print data
Relationship generates initial wireless access point fingerprint cluster;
Calculate separately in the default wireless access point fingerprint database the remaining wireless access point finger print data with it is described
The second cosine similarity in each initial wireless access point fingerprint cluster between original wireless access point finger print data;
According to the relationship of second cosine similarity and the preset threshold, the wireless access point finger print data is clustered into
Multiple wireless access point fingerprint clusters.
4. according to the method described in claim 3, it is characterized in that, described according to the second preset number wireless access point
The step of relationship of the first cosine similarity between finger print data and preset threshold, generation initial wireless access point fingerprint cluster,
Include:
The second preset number initial wireless access point is set by the second preset number wireless access point finger print data
Fingerprint cluster, each initial wireless access point fingerprint cluster include a wireless access point finger print data;
Calculate the first cosine similarity between the initial wireless access point fingerprint cluster;
The initial wireless access point fingerprint cluster that cosine similarity is greater than preset threshold is merged into an initial wireless access
Point fingerprint cluster;
The initial wireless access point fingerprint cluster that cosine similarity is less than the preset threshold is remained unchanged.
5. according to the method described in claim 3, it is characterized in that, described according to second cosine similarity and described default
The relationship of threshold value, the step of wireless access point finger print data is clustered into multiple wireless access point fingerprint clusters, comprising:
If second cosine similarity is greater than the preset threshold, the wireless access point finger print data is added to correspondence
The initial wireless access point fingerprint cluster in, generate a wireless access point fingerprint cluster;
If the cosine similarity is less than preset threshold, new wireless access is set by the wireless access point finger print data
Point fingerprint cluster.
6. a kind of similar users identification device, which is characterized in that described device includes:
Cluster module, for each wireless access point finger print data in default wireless access point fingerprint database to be clustered into
Multiple wireless access point fingerprint clusters;
Sorting module, for the number according to the wireless access point finger print data in each wireless access point fingerprint cluster, by institute
Fingerprint cluster is stated to be ranked up;
Feature vector determining module for number of clusters default before extracting in ranking results, and wirelessly connects described in the fingerprint cluster
The number of access point finger print data is greater than the wireless access point fingerprint cluster of the first preset number, the wireless access point fingerprint as user
Feature vector;
Similarity calculation module, for calculating the similarity between the wireless access point fingerprint characteristic vector;
Similar users determining module, for determining according to the similarity between the wireless access point fingerprint characteristic vector to application
Similarity between family.
7. device according to claim 6, which is characterized in that further include:
Location data obtains module, for obtaining the network positions data of user;
Wireless access point finger print data and the extraction module that above calls time, for extracting corresponding nothing from the network positions data
Line access point finger print data and on call time;
Time interval computing module, for according between the time for calculating each wireless access point finger print data of calling time on described
Every;
Default wireless access point fingerprint database generation module, for extracting the time interval greater than prefixed time interval and letter
Number intensity is greater than the wireless access point finger print data of preset strength, generates default wireless access point fingerprint database.
8. device according to claim 6, which is characterized in that the cluster module, comprising:
Wireless access point finger print data chooses submodule, for randomly selecting in the default wireless access point fingerprint database
Second preset number wireless access point finger print data;
Initial wireless access point fingerprint fasciation is at submodule, for according to the second preset number wireless access point fingerprint number
The relationship of the first cosine similarity between and preset threshold generates initial wireless access point fingerprint cluster;
Second cosine similarity computational submodule, it is remaining in the default wireless access point fingerprint database for calculating separately
In the wireless access point finger print data and each initial wireless access point fingerprint cluster original wireless access point finger print data it
Between the second cosine similarity;
Submodule is clustered, for the relationship according to second cosine similarity and the preset threshold, by the wireless access
Point finger print data is clustered into multiple wireless access point fingerprint clusters.
9. device according to claim 8, which is characterized in that the initial wireless access point fingerprint classification generates submodule
Block, comprising:
Initial wireless access point fingerprint cluster setting unit, for setting the second preset number wireless access point finger print data
It is set to the second preset number initial wireless access point fingerprint cluster, each initial wireless access point fingerprint cluster includes a nothing
Line access point finger print data;
First cosine similarity computing unit, it is similar for calculating the first cosine between the initial wireless access point fingerprint cluster
Degree;
Combining unit, the initial wireless access point fingerprint cluster for cosine similarity to be greater than preset threshold merge into one
Initial wireless access point fingerprint cluster;
Initial wireless access point fingerprint cluster stick unit, for cosine similarity to be less than to the initial nothing of the preset threshold
Line access point fingerprint cluster remains unchanged.
10. device according to claim 8, the cluster submodule, comprising:
Wireless access point fingerprint classification generation unit will if being greater than the preset threshold for second cosine similarity
The wireless access point finger print data is added in the corresponding initial wireless access point fingerprint cluster, generates a wireless access
Point fingerprint cluster;
Wireless access point fingerprint classification setting unit will be described wireless if being less than preset threshold for the cosine similarity
Access point finger print data is set as new wireless access point fingerprint cluster.
11. a kind of equipment characterized by comprising
Processor, memory and it is stored in the computer program that can be run on the memory and on the processor,
It is characterized in that, the processor realizes the similar users as described in one or more in claim 1-5 when executing described program
Recognition methods.
12. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment
When row, so that electronic equipment is able to carry out the similar users recognition methods as described in one or more in claim to a method 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811005730.5A CN109068272B (en) | 2018-08-30 | 2018-08-30 | Similar user identification method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811005730.5A CN109068272B (en) | 2018-08-30 | 2018-08-30 | Similar user identification method, device, equipment and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109068272A true CN109068272A (en) | 2018-12-21 |
CN109068272B CN109068272B (en) | 2021-01-08 |
Family
ID=64758782
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811005730.5A Active CN109068272B (en) | 2018-08-30 | 2018-08-30 | Similar user identification method, device, equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109068272B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110245132A (en) * | 2019-06-12 | 2019-09-17 | 腾讯科技(深圳)有限公司 | Data exception detection method, device, computer readable storage medium and computer equipment |
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 |
CN112738724A (en) * | 2020-12-17 | 2021-04-30 | 福建新大陆软件工程有限公司 | Method, device, equipment and medium for accurately identifying regional target crowd |
CN113840392A (en) * | 2021-09-17 | 2021-12-24 | 杭州云深科技有限公司 | Method and device for determining user intimacy, computer equipment and storage medium |
CN115766204A (en) * | 2022-11-14 | 2023-03-07 | 电子科技大学 | Dynamic IP equipment identification system and method for encrypted flow |
CN117237804A (en) * | 2023-09-15 | 2023-12-15 | 江苏三棱智慧物联发展股份有限公司 | Pyrotechnical recognition system and method based on federal learning |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102638888A (en) * | 2012-03-19 | 2012-08-15 | 华中科技大学 | Indoor positioning fingerprint grouping method based on signal statistics |
CN103476115A (en) * | 2013-09-22 | 2013-12-25 | 中国地质大学(武汉) | Method for WiFi fingerprint positioning based on AP set similarity |
CN104684083A (en) * | 2015-03-26 | 2015-06-03 | 哈尔滨工业大学 | AP (access point) selecting method based on clustering idea |
CN106060779A (en) * | 2016-07-18 | 2016-10-26 | 北京方位捷讯科技有限公司 | Fingerprint feature matching method and device |
US20170140193A1 (en) * | 2015-11-16 | 2017-05-18 | MorphoTrak, LLC | Minutiae Grouping for Distorted Fingerprint Matching |
CN206272854U (en) * | 2016-11-14 | 2017-06-20 | 成都信息工程大学 | A kind of social networks construction device based on WiFi network linkage record |
CN107835498A (en) * | 2017-10-18 | 2018-03-23 | 上海掌门科技有限公司 | A kind of method and apparatus for being used to manage user |
CN108234686A (en) * | 2017-12-20 | 2018-06-29 | 中国联合网络通信集团有限公司 | A kind of method and apparatus of indoor and outdoor judgement |
-
2018
- 2018-08-30 CN CN201811005730.5A patent/CN109068272B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102638888A (en) * | 2012-03-19 | 2012-08-15 | 华中科技大学 | Indoor positioning fingerprint grouping method based on signal statistics |
CN103476115A (en) * | 2013-09-22 | 2013-12-25 | 中国地质大学(武汉) | Method for WiFi fingerprint positioning based on AP set similarity |
CN104684083A (en) * | 2015-03-26 | 2015-06-03 | 哈尔滨工业大学 | AP (access point) selecting method based on clustering idea |
US20170140193A1 (en) * | 2015-11-16 | 2017-05-18 | MorphoTrak, LLC | Minutiae Grouping for Distorted Fingerprint Matching |
CN106060779A (en) * | 2016-07-18 | 2016-10-26 | 北京方位捷讯科技有限公司 | Fingerprint feature matching method and device |
CN206272854U (en) * | 2016-11-14 | 2017-06-20 | 成都信息工程大学 | A kind of social networks construction device based on WiFi network linkage record |
CN107835498A (en) * | 2017-10-18 | 2018-03-23 | 上海掌门科技有限公司 | A kind of method and apparatus for being used to manage user |
CN108234686A (en) * | 2017-12-20 | 2018-06-29 | 中国联合网络通信集团有限公司 | A kind of method and apparatus of indoor and outdoor judgement |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110245132A (en) * | 2019-06-12 | 2019-09-17 | 腾讯科技(深圳)有限公司 | Data exception detection method, device, computer readable storage medium and computer equipment |
CN110245132B (en) * | 2019-06-12 | 2023-10-31 | 腾讯科技(深圳)有限公司 | Data anomaly detection method, device, computer readable storage medium and computer equipment |
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 |
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 |
CN112738724A (en) * | 2020-12-17 | 2021-04-30 | 福建新大陆软件工程有限公司 | Method, device, equipment and medium for accurately identifying regional target crowd |
CN112738724B (en) * | 2020-12-17 | 2022-09-23 | 福建新大陆软件工程有限公司 | Method, device, equipment and medium for accurately identifying regional target crowd |
CN113840392A (en) * | 2021-09-17 | 2021-12-24 | 杭州云深科技有限公司 | Method and device for determining user intimacy, computer equipment and storage medium |
CN113840392B (en) * | 2021-09-17 | 2023-09-22 | 杭州云深科技有限公司 | User intimacy determination method, device, computer equipment and storage medium |
CN115766204A (en) * | 2022-11-14 | 2023-03-07 | 电子科技大学 | Dynamic IP equipment identification system and method for encrypted flow |
CN115766204B (en) * | 2022-11-14 | 2024-04-26 | 电子科技大学 | Dynamic IP equipment identification system and method for encrypted traffic |
CN117237804A (en) * | 2023-09-15 | 2023-12-15 | 江苏三棱智慧物联发展股份有限公司 | Pyrotechnical recognition system and method based on federal learning |
CN117237804B (en) * | 2023-09-15 | 2024-02-13 | 江苏三棱智慧物联发展股份有限公司 | Pyrotechnical recognition system and method based on federal learning |
Also Published As
Publication number | Publication date |
---|---|
CN109068272B (en) | 2021-01-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109068272A (en) | Similar users recognition methods, device, equipment and readable storage medium storing program for executing | |
CN102932911B (en) | Positioning method and positioning system of location fingerprints | |
US9313617B2 (en) | Identification of points of interest and positioning based on points of interest | |
US9277362B2 (en) | Method and apparatus for generating and using location information | |
US20130205196A1 (en) | Location-based mobile application marketplace system | |
US8830909B1 (en) | Methods and systems to determine user relationships, events and spaces using wireless fingerprints | |
CN106658704A (en) | Positioning method and system of starting point of indoor positioning | |
CN107302793B (en) | Positioning method, server, terminal and system based on wireless signals | |
CN109275090B (en) | Information processing method, device, terminal and storage medium | |
CN105338619A (en) | Positioning method and positioning device | |
CN108450060B (en) | Positioning method and device based on WI-FI access point | |
CN103747519A (en) | Method and system for dynamically establishing indoor positioning fingerprint database | |
CA2751729C (en) | Method and apparatus for generating and using location information | |
CN102480784A (en) | Method and system for evaluating fingerprint positioning error | |
CN105592420A (en) | Method and device for generating environment feature library and indoor positioning method and device based on environment feature library | |
Wang et al. | Adaptive rfid positioning system using signal level matrix | |
CN107071708B (en) | Passive wireless signal acquisition and positioning method for intelligent mobile terminal | |
CN112526572A (en) | Network switching method and positioning system for indoor and outdoor seamless navigation | |
CN109325177A (en) | Information-pushing method, system, readable storage medium storing program for executing and computer equipment | |
CN105072169A (en) | Intelligent information display system of culture exhibition hall | |
CN107277776A (en) | A kind of location fingerprint alignment system and method | |
CN111757284B (en) | Indoor entrance positioning method and electronic equipment | |
CN108519579A (en) | The WiFi fingerprint location technologies of preferred AP are analyzed based on interval overlap degree | |
CN108668218A (en) | A kind of method of locating terminal and device | |
Elbakly et al. | A calibration-free RF localization system |
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 |