CN103954277A - Method and device for detecting positions of interest points - Google Patents

Method and device for detecting positions of interest points Download PDF

Info

Publication number
CN103954277A
CN103954277A CN201410183406.8A CN201410183406A CN103954277A CN 103954277 A CN103954277 A CN 103954277A CN 201410183406 A CN201410183406 A CN 201410183406A CN 103954277 A CN103954277 A CN 103954277A
Authority
CN
China
Prior art keywords
point
interest
place
obtaining
location
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
Application number
CN201410183406.8A
Other languages
Chinese (zh)
Other versions
CN103954277B (en
Inventor
李国强
孙彬
刘燕云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201410183406.8A priority Critical patent/CN103954277B/en
Publication of CN103954277A publication Critical patent/CN103954277A/en
Application granted granted Critical
Publication of CN103954277B publication Critical patent/CN103954277B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G01C21/32—Structuring or formatting of map data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3679—Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities

Abstract

The invention provides a method and a device for detecting positions of interest points. The method comprises the following steps: obtaining a corresponding interest point of any door address in a map; detecting whether the obtained interest point is arranged in a predetermined area on one side of a road of the door address; and determining that the position of the obtained interest point is wrong data if the obtained interest point is not in the predetermined area on one side of the road of the door address. By the method and the device, interest points with wrong positions can be effectively detected.

Description

Detect method and the device of point of interest location
Technical field
The application relates to a kind of method and device that detects point of interest location, relates in particular to a kind of technology that the presumptive area of place, location road detects point of interest location of utilizing.
Background technology
Along with the develop rapidly of internet, various LBS (Location Based Service, location-based service) client application of product and electronic chart brings great convenience to daily life, and weigh these products and a locus accuracy rate that important indicator is exactly point of interest of application.
For ensureing the accuracy of point of interest location, when prior art detects interest point data on backstage, mainly solve by following two kinds of modes: one is to adopt " manually sweeping the streets " mode to revise the point of interest location in background data base, also just say, carrying GPS equipment by data acquisition personnel detects the point of interest in background data base to region to be collected image data, but, this mode need to be employed a large amount of manpowers, material resources, not only the Data Update cycle is long, and in the time that the data volume relating to is increasing, the cost of labor using also can be more and more higher, another kind is that employing figure business (having geographical manufacturer of drawing qualification) data detect the point of interest location in background data base, but, because the coverage rate of figure quotient data is limited, cannot be covered by figure quotient data so still have a large amount of points of interest.
Therefore, how effectively the position of point of interest to be detected and to become a needs problem demanding prompt solution in current back-end data testing process.
Summary of the invention
The object of the present invention is to provide a kind of method and device that detects point of interest location, to effectively detect the point of interest of positional fault.
According to an aspect of the present invention, provide a kind of method that detects point of interest location, described method comprises: the point of interest that obtains arbitrary location correspondence in map; Whether the point of interest that detection is obtained is in the presumptive area of this place, location road one side; If the point of interest obtaining not in the presumptive area of this place, location road one side, determines that the point of interest location obtaining is misdata.
Preferably, the point of interest that described detection is obtained the whether concrete steps in the presumptive area of this place, location road one side is: whether the point of interest that adopts abnormal point method of determining and calculating based on distance to detect to obtain is in the presumptive area of this place, location road one side; And/or whether the point of interest that adopts the method for cluster to detect to obtain is in the presumptive area of this place, location road one side; And/or, utilize point of interest that the correlation detection between the point of interest and this place, location road that obtain obtains whether in the presumptive area of this place, location road one side.
Preferably, the detection formula of the described abnormal point method of determining and calculating based on distance is as follows:
1 n - 1 Σ j = 1 , j ≠ i n d ij > ϵ n Σ i = 1 n ( 1 n - 1 Σ j = 1 , j ≠ i n d ij )
Wherein, n represents total number of the point of interest obtaining; ε represents the pre-determined factor of the dynamic threshold that detects abnormal point of interest; d ijrepresent the distance between i the point of interest obtaining and j the point of interest obtaining; If above-mentioned detection formula is set up, i the point of interest obtaining be not in the presumptive area of this place, location road one side.
Preferably, the method for described employing cluster detect the point of interest that obtains whether the concrete steps in the presumptive area of this place, location road one side be: the point of interest location obtaining is carried out to cluster; If the result of cluster is multiple bunches, extract at least one point of interest in any one bunch; Determine that the point of interest extracting is whether in the presumptive area of this place, location road one side; If the point of interest extracting not in the presumptive area of this place, location road one side, determines that this bunch be not in the presumptive area of this place, location road one side.
Preferably, the condition of described cluster is: the distance between any two points of interest that obtain in same bunch is less than the first preset value; And/or any one point of interest obtaining in same bunch and the distance between this bunch of central point are less than the second preset value; And/or, between any two points of interest that obtain in same bunch, do not exist across road information.
Preferably, the correlativity between the point of interest obtaining described in and this place, location road is: the vertical range between the point of interest obtaining and this place, location road; The point of interest that correlation detection between the point of interest that described utilization is obtained and this place, location road is obtained the whether concrete steps in the presumptive area of this place, location road one side is: determine whether the vertical range between point of interest and this place, location road obtaining is less than the vertical range between point of interest and other roads obtaining; If the vertical range between the point of interest obtaining and this place, location road is not less than the vertical range between point of interest and other roads obtaining, determine that the point of interest obtaining is not in the presumptive area of this place, location road one side.
Preferably, the described concrete steps of determining whether the vertical range between the point of interest and this place, location road that obtain is less than the vertical range between point of interest and other roads obtaining are: if exist another road crossing to the vertical line between this place, location road with the point of interest obtaining, the vertical range between definite point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or, if exist another road crossing to the reverse extending line of the vertical line between this place, location road with the point of interest obtaining, and the distance between crossing point and the point of interest obtaining is less than the vertical range between point of interest and this place, location road obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or the vertical range taking the point of interest that obtains between the center of circle, the point of interest obtaining and this place, location road builds a closed circle as radius; If exist another road crossing with the closed circle of structure, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
Preferably, described method also comprises: determine whether the point of interest obtaining is the point of interest of this place, location intersection in preset range; If the point of interest obtaining is the point of interest of this place, location intersection in preset range, determine that the point of interest obtaining is in the presumptive area of this place, location road one side.
Preferably, describedly determine that whether the point of interest that obtains is that the concrete steps of the point of interest of this place, location intersection in preset range are: if the vertical range between the point of interest obtaining and this place, location road and the point of interest obtaining and the difference through the vertical range between another road of this place, location intersection are less than the 3rd preset value, definite point of interest obtaining is the point of interest of this place, location intersection in preset range; And/or, if the distance between the point of interest obtaining and this place, location intersection is less than the 4th preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
According to a further aspect in the invention, provide a kind of device that detects point of interest location, described device comprises: point of interest acquiring unit, for obtaining arbitrary location at point of interest corresponding to map; Door location detecting unit, for detection of the point of interest obtaining whether in the presumptive area of this place, location road one side; Mistake screening unit, if for the point of interest that obtains not in the presumptive area of this place, location road one side, determine that the point of interest location obtaining is misdata.
Preferably, described door location detecting unit comprises: abnormality detection subelement, for the point of interest that adopts abnormal point method of determining and calculating based on distance to detect to obtain whether in the presumptive area of this place, location road one side; And/or cluster detection sub-unit, for adopting the device of cluster to determine that the point of interest that obtains is whether in the presumptive area of this place, location road one side; And/or, Road Detection subelement, whether the point of interest obtaining for the correlation detection of utilizing between point of interest and this place, location road obtaining is in the presumptive area of this place, location road one side.
Preferably, the detection formula of the described abnormal point method of determining and calculating based on distance is as follows:
1 n - 1 Σ j = 1 , j ≠ i n d ij > ϵ n Σ i = 1 n ( 1 n - 1 Σ j = 1 , j ≠ i n d ij )
Wherein, n represents total number of the point of interest obtaining; ε represents the pre-determined factor of the dynamic threshold that detects abnormal point of interest; d ijrepresent the distance between i the point of interest obtaining and j the point of interest obtaining; If above-mentioned detection formula is set up, i the point of interest obtaining be not in the presumptive area of this place, location road one side.
Preferably, described cluster detection sub-unit is carried out cluster to the point of interest location obtaining; If the result of cluster is multiple bunches, extract at least one point of interest in any one bunch; Determine that the point of interest extracting is whether in the presumptive area of this place, location road one side; If the point of interest extracting not in the presumptive area of this place, location road one side, determines that this bunch be not in the presumptive area of this place, location road one side.
Preferably, the condition of described cluster is: the distance between any two points of interest that obtain in same bunch is less than the first preset value; And/or any one point of interest obtaining in same bunch and the distance between this bunch of central point are less than the second preset value; And/or, between any two points of interest that obtain in same bunch, do not exist across road information.
Preferably, the correlativity between the point of interest obtaining described in and this place, location road is: the vertical range between the point of interest obtaining and this place, location road; Described Road Detection subelement comprises: distance is determined subelement, for determining whether the vertical range between point of interest and this place, location road obtaining is less than the vertical range between point of interest and other roads obtaining; Subelement is determined in region, if be not less than the vertical range between point of interest and other roads obtaining for the vertical range between the point of interest and this place, location road that obtain, determine that the point of interest obtaining is not in the presumptive area of this place, location road one side.
Preferably, described distance determines that subelement comprises: the first distance is determined subelement, if for existing another road crossing to the vertical line between this place, location road with the point of interest obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or, second distance is determined subelement, if for existing another road crossing to the reverse extending line of the vertical line between this place, location road with the point of interest obtaining, and the distance between crossing point and the point of interest obtaining is less than the vertical range between point of interest and this place, location road obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or the 3rd distance is determined subelement, the vertical range for the point of interest to obtain between the center of circle, the point of interest obtaining and this place, location road builds a closed circle as radius; If exist another road crossing with the closed circle of structure, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
Preferably, described device also comprises: crossing point of interest determining unit, for determining whether the point of interest obtaining is the point of interest of this place, location intersection in preset range; Mistake denoising unit, if be the point of interest of this place, location intersection in preset range for the point of interest obtaining, determines that the point of interest obtaining is in the presumptive area of this place, location road one side.
Preferably, described crossing point of interest determining unit comprises: the first crossing point of interest determining unit, if the difference for the vertical range between the vertical range between the point of interest and this place, location road that obtain and the point of interest obtaining and process another road of this place, location intersection is less than the 3rd preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range; And/or, the second crossing point of interest determining unit, if be less than the 4th preset value for the distance between the point of interest and this place, location intersection that obtain, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
Beneficial effect
Compared with prior art, the present invention not only can detect the point of interest of positional fault effectively, but also the blind spot that some are difficult for detecting detected, thus further promote the space accuracy rate of point of interest, reduce the impact that misdata is brought to user.In addition, the present invention has also effectively reduced the consumption of testing process to human and material resources.
Brief description of the drawings
By the description of carrying out below in conjunction with accompanying drawing, above and other object of the present invention and feature will become apparent, wherein:
Fig. 1 is the process flow diagram illustrating according to the method for the detection point of interest location of exemplary embodiment of the present invention;
Fig. 2 is the structured flowchart illustrating according to the device of the detection point of interest location of exemplary embodiment of the present invention;
Fig. 3 A illustrates near the distribution schematic diagram this place, location road according to the point of interest of the same door of the correspondence of exemplary embodiment of the present invention location;
Fig. 3 B illustrates near the distribution schematic diagram that converges multiple bunches according to the point of interest of the same door of the correspondence of exemplary embodiment of the present invention location this place, location road;
Fig. 4 A is the schematic diagram that passes through vertical line between point of interest and door place, location road and carry out Road Detection illustrating according to exemplary embodiment of the present invention;
Fig. 4 B illustrates the schematic diagram that carries out Road Detection according to the reverse extending line that passes through the vertical line between point of interest and door place, location road of exemplary embodiment of the present invention;
Fig. 4 C is the schematic diagram that passes through taking point of interest as the center of circle to build closed circle and carry out Road Detection illustrating according to exemplary embodiment of the present invention.
Embodiment
Below, describe with reference to the accompanying drawings embodiments of the invention in detail.
Fig. 1 shows the process flow diagram of the preferred embodiment of a kind of method that detects point of interest location of the present invention.A kind of device that detects point of interest location shown in Fig. 2 can be used for realizing the method described in Fig. 1.
With reference to Fig. 1, in 110, described device obtains the point of interest of arbitrary location correspondence in map.
Wherein, door location refers in the address information of each point of interest and comprises xx road (or street/road) xx information, in actual life same door region corresponding to location all fix, limited, and Shi Bukua road, based on such characteristic, all points of interest of corresponding same door location information all should be able to converge in the presumptive area of this place, location road one side, this presumptive area should be not only fix, limited, but also should Shi Bukua road.
When concrete enforcement, can adopt and cut word and semantic analysis technology and from back-end data, extract the door location information that each point of interest comprises, sort in the door location information to extracting, after duplicate removal, the all points of interest that therefrom obtain Ji Gaimen location, arbitrary location correspondence in map, then detect the point of interest obtaining according to the presumptive area of this place, location road one side.
In 120, described device detects the point of interest that obtains whether in the presumptive area of this place, location road one side.
Because point of interest corresponding to same door location should be to converge in the presumptive area of this place, location road one side, therefore departing from wrong point of interest that presumptive area is far away, to can be used as outlier (being abnormity point) out screened, according to an optional embodiment of the present invention, described device detect the point of interest that obtains whether the concrete steps in the presumptive area of this place, location road one side be: whether the point of interest that described device adopts the abnormal point method of determining and calculating based on distance to detect to obtain in the presumptive area of this place, location road one side.
Near the distribution schematic diagram of the point of interest that Fig. 3 A shows the same door of correspondence of the present invention location this place, location road.Point of interest x, y, z in figure, the same door location that m, n are corresponding, road A is this place, location road, as can be seen from the figure, point of interest m far can be considered abnormal point of interest because distance departs from.
Particularly, abnormality detection exemplary embodiment according to the present invention, the detection formula of the described abnormal point method of determining and calculating based on distance is as follows:
1 n - 1 Σ j = 1 , j ≠ i n d ij > ϵ n Σ i = 1 n ( 1 n - 1 Σ j = 1 , j ≠ i n d ij )
Wherein, n represents total number of the point of interest obtaining; ε represents the pre-determined factor of the dynamic threshold that detects abnormal point of interest; d ijrepresent the distance between i the point of interest obtaining and j the point of interest obtaining; If above-mentioned detection formula is set up, i the point of interest obtaining be not in the presumptive area of this place, location road one side.
Under normal circumstances, can establish ε=2, while specifically enforcement, described device also visual detection permissible accuracy carries out suitable adjustment to the size of ε.
From above-mentioned implementation process, can find out, depart from although method for detecting abnormality can filter out effectively the indivedual wrong point of interest that presumptive area is far away, but can not and effectively screen across the wrong point of interest on road the close multiple wrong point of interest of a group distance.
The point of interest that Fig. 3 B shows the same door of correspondence of the present invention location converges the distribution schematic diagram of multiple bunches near this place, location road.The same door location that point of interest x, y, z in figure, m, n, l, p are corresponding, road A is this place, location road, as can be seen from the figure, according to the distance of distance between point of interest, point of interest x, y, z can converge and be one bunch, point of interest m, n, l can converge as another bunch, point of interest p Wei Kua road point of interest.
In order to filter out the wrong point of interest of said circumstances, according to another optional embodiment of the present invention, described device detect the point of interest that obtains whether the concrete steps in the presumptive area of this place, location road one side be: whether the point of interest that described device adopts the method for cluster to detect to obtain in the presumptive area of this place, location road one side.
Particularly, the exemplary embodiment that cluster detects according to the present invention, the point of interest that described device adopts the method for cluster to detect to obtain the whether concrete steps in the presumptive area of this place, location road one side is: if the result of described device cluster is multiple bunches, extract at least one point of interest in any one bunch; Determine that the point of interest extracting is whether in the presumptive area of this place, location road one side; If the point of interest extracting not in the presumptive area of this place, location road one side, determines that this bunch be not in the presumptive area of this place, location road one side.When concrete enforcement, described device can pass through manual type modes such as (as: artificial) map comparisons and determine that the point of interest that extracts is whether in the presumptive area of this place street, location one side, also can determine that the point of interest that extracts whether in the presumptive area of this place street, location one side, is not restricted this present invention by described Approach for road detection below.
It should be noted that, because point of interest corresponding to same door location should be to converge in the presumptive area of this place, location road one side, therefore,, if the result of cluster is one bunch, described device determines that the point of interest obtaining is all in the presumptive area of this place, location road one side.
In above-mentioned cluster process, described device can filter out the wrong point of interest of different situations by changing the condition of cluster.
Particularly, change an exemplary embodiment of the condition of cluster according to the present invention, in the time that the distance between any two points of interest that obtain in same bunch is less than the first preset value, described device can be polymerized to one bunch by the close multiple wrong point of interest of those distances, if the result of cluster is multiple bunches, whether the result of determining cluster by artificial or other modes in the presumptive area of this place, location road one side, and then screens the close multiple wrong point of interest of distance in the presumptive area of this place, location road one side not.
Change another exemplary embodiment of the condition of cluster according to the present invention, in the time that the distance between any one point of interest obtaining and this bunch of central point in same bunch is less than the second preset value, described device also can screen the close multiple wrong point of interest of distance in the presumptive area of this place, location road one side not.
Change another exemplary embodiment of the condition of cluster according to the present invention, in the time not existing across road information between any two points of interest that obtain in same bunch, described device can screen those existence across the wrong point of interest of road information.When concrete enforcement, described device can determine in same cluster that whether the line between any two points of interest is crossing with this place, location road, if intersected, can determine between these two points of interest and exist across road information.
It should be noted that, described device can be implemented separately any one in above-mentioned three exemplary embodiments of condition that change clusters, also above-mentioned three exemplary embodiments that change the condition of clusters can be combined to enforcement, and this present invention is not limited.
In addition, according to another optional embodiment of the present invention, described device detect the point of interest that obtains whether the concrete steps in the presumptive area of this place, location road one side be: whether the point of interest that the correlation detection between the point of interest that described device utilization is obtained and this place, location road is obtained in the presumptive area of this place, location road one side.
In the time that the correlativity between the point of interest obtaining and this place, location road is the vertical range between point of interest and this place, location road obtaining, Road Detection exemplary embodiment according to the present invention, the point of interest that described device adopts the method for cluster to detect to obtain the whether concrete steps in the presumptive area of this place, location road one side is: whether the vertical range between definite point of interest and this place, location road obtaining of described device is less than the vertical range between point of interest and other roads obtaining; If the vertical range between the point of interest obtaining and this place, location road is not less than the vertical range between point of interest and other roads obtaining, determine that the point of interest obtaining is not in the presumptive area of this place, location road one side.
Particularly, determine an exemplary embodiment of vertical range according to the present invention, described device determines that the concrete steps whether vertical range between the point of interest and this place, location road that obtain is less than the vertical range between point of interest and other roads obtaining are: if exist another road crossing to the vertical line between this place, location road with the point of interest obtaining, the vertical range between definite point of interest and this place, location road obtaining of described device is not less than the vertical range between point of interest and other roads obtaining.
Fig. 4 A shows the present invention carries out the schematic diagram of Road Detection by the vertical line between point of interest and door place, location road.The same door location that point of interest c in figure and d are corresponding, road A is this place, location road, as can be seen from the figure, in the time that point of interest c is crossing with another road B to the vertical line between door place, location road A, vertical range between point of interest c and road A is not less than the vertical range between point of interest c and another road B, that is to say, point of interest c is not in the presumptive area of place, door location road A mono-side; In the time that point of interest d is not crossing with any road to the vertical line between door place, location road A, vertical range between point of interest d and door place, location road A is less than the vertical range between point of interest d and other roads, that is to say, point of interest d is in the presumptive area of place, door location road A mono-side.
Determine another exemplary embodiment of vertical range according to the present invention, the concrete steps whether vertical range between definite point of interest and this place, location road obtaining of described device is less than the vertical range between point of interest and other roads obtaining are: if described device exists another road crossing to the reverse extending line of the vertical line between this place, location road with the point of interest obtaining, and the distance between crossing point and the point of interest obtaining is less than the vertical range between point of interest and this place, location road obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
Fig. 4 B shows the present invention carries out the schematic diagram of Road Detection by the reverse extending line of the vertical line between point of interest and door place, location road.The same door location that point of interest c in figure and d are corresponding, road A is this place, location road, as can be seen from the figure, when point of interest c is to the reverse extending line of vertical line and the road B of point of interest opposite side between door place, location road A 2intersect, and point of interest c and road B 2between vertical range while being less than the vertical range between point of interest c and road A, vertical range between point of interest c and door place, location road A is not less than the vertical range between point of interest c and other roads, that is to say, point of interest c is not in the presumptive area of place, door location road A mono-side; When point of interest d is to the reverse extending line of vertical line and the road B of point of interest d opposite side between door place, location road A 1, B 2all intersect, and vertical range between point of interest d and road A is less than point of interest d to road B 1or road B 2between vertical range time, point of interest d and the vertical range of door between the road A of place, location are less than the vertical range between point of interest d and other roads, that is to say, point of interest d is in the presumptive area of place, door location road A mono-side.
But, between point of interest and door place, location road without other roads, and point of interest is crossed time far away to the intersection point between reverse extending line and other roads of the vertical line of door place, location road, and above-mentioned Approach for road detection cannot detect the wrong point of interest of this class distribution scenario.
For addressing the above problem, determine another exemplary embodiment of vertical range according to the present invention, described device determines that the concrete steps whether vertical range between the point of interest and this place, location road that obtain is less than the vertical range between point of interest and other roads obtaining are: taking the point of interest that obtains, the vertical range between the center of circle, the point of interest obtaining and this place, location road builds a closed circle as radius to described device; If exist another road crossing with the closed circle of structure, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.Can fully detect the blind spot that is difficult for detecting like this.
Fig. 4 C shows the present invention and carries out the schematic diagram of Road Detection by build closed circle taking point of interest as the center of circle.The same door location that point of interest x in figure and y are corresponding, road A is this place, location road, as can be seen from the figure, when taking point of interest x as the center of circle, the closed circle that builds as radius of point of interest x and the vertical range of door between the road A of place, location is when crossing with road B, vertical range between point of interest x and door place, location road A is not less than the vertical range between point of interest x and other roads, that is to say, point of interest x is not in the presumptive area of place, door location road A mono-side; When taking point of interest y as the center of circle, the closed circle that builds as radius of point of interest y and the vertical range of door between the road A of place, location is not when crossing with road B, vertical range between point of interest y and door place, location road A is less than the vertical range between point of interest y and other roads, that is to say, point of interest y is in the presumptive area of place, door location road A mono-side.
It should be noted that, described device can be implemented separately any one in the exemplary embodiment of above-mentioned three definite vertical ranges, also the exemplary embodiment of above-mentioned three definite vertical ranges can be combined to enforcement, and this present invention is not limited.
Due to according to detection method noted earlier, near the point of interest intersection of door place, location may be mistaken for the not wrong point of interest in the presumptive area of this place, location road one side, for the result of further correct detection, the point of interest of erroneous judgement is separated, according to another optional embodiment of the present invention, in the embodiment shown in fig. 1, described method also comprises: described device determines whether the point of interest obtaining is the point of interest of this place, location intersection in preset range; If the point of interest obtaining is the point of interest of this place, location intersection in preset range, determine that the point of interest obtaining is in the presumptive area of this place, location road one side, the point of interest location obtaining is correct data.
Particularly, determine an exemplary embodiment of crossing point of interest according to the present invention, described device determines that whether the point of interest that obtains is that the concrete steps of the point of interest of this place, location intersection in preset range are: if the vertical range between the point of interest that described device obtains and this place, location road and the point of interest obtaining and the difference through the vertical range between another road of this place, location intersection are less than the 3rd preset value, definite point of interest obtaining is the point of interest of this place, location intersection in preset range.
Determine another exemplary embodiment of crossing point of interest according to the present invention, described device determines that whether the point of interest that obtains is that the concrete steps of the point of interest of this place, location intersection in preset range are: if the distance between the point of interest that described device obtains and this place, location intersection is less than the 4th preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
It should be noted that, while specifically enforcement, the 3rd preset value and the 4th preset value should be as much as possible little, enough approach on geographic position with point of interest and the intersection guaranteeing to obtain.In addition, described device can be implemented separately any one in the exemplary embodiment of above-mentioned two definite crossing points of interest, also the exemplary embodiment of above-mentioned two definite crossing points of interest can be combined to enforcement, and this present invention is not limited.
In addition, also it should be noted that, above-mentioned three kinds of optional embodiments, except can implementing separately according to the method for the invention, also can be combined enforcement by above-mentioned three kinds of optional embodiments, to the wrong point of interest of various distribution scenario is fully detected.
With reference to Fig. 2, described device at least comprises point of interest acquiring unit 201, door location detecting unit 202 and wrong screening unit 203.
Wherein, point of interest acquiring unit 201, for obtaining arbitrary location at point of interest corresponding to map.
Door location detecting unit 202, for detection of the point of interest obtaining whether in the presumptive area of this place, location road one side.
Mistake screening unit 203, if for the point of interest that obtains not in the presumptive area of this place, location road one side, determine that the point of interest location obtaining is misdata.
Because point of interest corresponding to same door location should be to converge in the presumptive area of this place, location road one side, therefore departing from wrong point of interest that presumptive area is far away, to can be used as outlier (being abnormity point) out screened, according to an optional embodiment of the present invention, described door location detecting unit 202 comprises: abnormality detection subelement (not shown), for the point of interest that adopts abnormal point method of determining and calculating based on distance to detect to obtain whether in the presumptive area of this place, location road one side.
Particularly, abnormality detection exemplary embodiment according to the present invention, the detection formula of the described abnormal point method of determining and calculating based on distance is as follows:
1 n - 1 Σ j = 1 , j ≠ i n d ij > ϵ n Σ i = 1 n ( 1 n - 1 Σ j = 1 , j ≠ i n d ij )
Wherein, n represents total number of the point of interest obtaining; ε represents the pre-determined factor of the dynamic threshold that detects abnormal point of interest; d ijrepresent the distance between i the point of interest obtaining and j the point of interest obtaining; If above-mentioned detection formula is set up, i the point of interest obtaining be not in the presumptive area of this place, location road one side.
Under normal circumstances, can establish ε=2, while specifically enforcement, described device also visual detection permissible accuracy carries out suitable adjustment to the size of ε.
From above-mentioned implementation process, can find out, depart from although method for detecting abnormality can filter out effectively the indivedual wrong point of interest that presumptive area is far away, but can not and effectively screen across the wrong point of interest on road the close multiple wrong point of interest of a group distance.
In order to filter out the wrong point of interest of said circumstances, according to another optional embodiment of the present invention, described door location detecting unit 202 also comprises: cluster detection sub-unit (not shown), for the point of interest that adopts the device of cluster to determine to obtain whether in the presumptive area of this place, location road one side.
Particularly, the exemplary embodiment that cluster detects according to the present invention, described cluster detection sub-unit is carried out cluster to the point of interest location obtaining; If the result of cluster is multiple bunches, extract at least one point of interest in any one bunch; Determine that the point of interest extracting is whether in the presumptive area of this place, location road one side; If the point of interest extracting not in the presumptive area of this place, location road one side, determines that this bunch be not in the presumptive area of this place, location road one side.When concrete enforcement, described device can pass through manual type modes such as (as: artificial) map comparisons and determine that the point of interest that extracts is whether in the presumptive area of this place street, location one side, also can determine that the point of interest that extracts whether in the presumptive area of this place street, location one side, is not restricted this present invention by described Approach for road detection below.
It should be noted that, because point of interest corresponding to same door location should be to converge in the presumptive area of this place, location road one side, therefore,, if the result of cluster is one bunch, described device determines that the point of interest obtaining is all in the presumptive area of this place, location road one side.
In above-mentioned cluster process, described device can filter out the wrong point of interest of different situations by changing the condition of cluster.
Particularly, change an exemplary embodiment of the condition of cluster according to the present invention, in the time that the distance between any two points of interest that obtain in same bunch is less than the first preset value, described cluster detection sub-unit can be polymerized to one bunch by the close multiple wrong point of interest of those distances, if the result of cluster is multiple bunches, whether the result of determining cluster by artificial or other modes is in the presumptive area of this place, location road one side, and then the close multiple wrong point of interest of distance in the presumptive area of this place, location road one side is not screened.
Change another exemplary embodiment of the condition of cluster according to the present invention, in the time that the distance between any one point of interest obtaining and this bunch of central point in same bunch is less than the second preset value, described cluster detection sub-unit also can screen the close multiple wrong point of interest of distance in the presumptive area of this place, location road one side not.
Change another exemplary embodiment of the condition of cluster according to the present invention, in the time not existing across road information between any two points of interest that obtain in same bunch, described cluster detection sub-unit can screen those existence across the wrong point of interest of road information.When concrete enforcement, described cluster detection sub-unit can determine in same cluster that whether the line between any two points of interest is crossing with this place, location road, if intersected, can determine between these two points of interest and exist across road information.
It should be noted that, described device can be implemented separately any one in above-mentioned three exemplary embodiments of condition that change clusters, also above-mentioned three exemplary embodiments that change the condition of clusters can be combined to enforcement, and this present invention is not limited.
In addition, according to another optional embodiment of the present invention, described door location detecting unit 202 also comprises: Road Detection subelement (not shown), whether the point of interest obtaining for the correlation detection of utilizing between point of interest and this place, location road obtaining is in the presumptive area of this place, location road one side.
In the time that the correlativity between the point of interest obtaining and this place, location road is the vertical range between point of interest and this place, location road obtaining, Road Detection exemplary embodiment according to the present invention, described Road Detection subelement comprises: distance is determined subelement, for determining whether the vertical range between point of interest and this place, location road obtaining is less than the vertical range between point of interest and other roads obtaining; Subelement is determined in region, if be not less than the vertical range between point of interest and other roads obtaining for the vertical range between the point of interest and this place, location road that obtain, determine that the point of interest obtaining is not in the presumptive area of this place, location road one side.
Particularly, determine an exemplary embodiment of vertical range according to the present invention, described Road Detection subelement comprises: the first distance is determined subelement, if for existing another road crossing to the vertical line between this place, location road with the point of interest obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
Determine another exemplary embodiment of vertical range according to the present invention, described Road Detection subelement also comprises: second distance is determined subelement, if for existing another road crossing to the reverse extending line of the vertical line between this place, location road with the point of interest obtaining, and the distance between crossing point and the point of interest obtaining is less than the vertical range between point of interest and this place, location road obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
But, between point of interest and door place, location road without other roads, and point of interest is crossed time far away to the intersection point between reverse extending line and other roads of the vertical line of door place, location road, and above-mentioned Approach for road detection cannot detect the wrong point of interest of this class distribution scenario.
For addressing the above problem, determine another exemplary embodiment of vertical range according to the present invention, described Road Detection subelement also comprises: the 3rd distance is determined subelement, and the vertical range for the point of interest to obtain between the center of circle, the point of interest obtaining and this place, location road builds a closed circle as radius; If exist another road crossing with the closed circle of structure, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.Can fully detect the blind spot that is difficult for detecting like this.
It should be noted that, described device can be implemented separately any one in the exemplary embodiment of above-mentioned three definite vertical ranges, also the exemplary embodiment of above-mentioned three definite vertical ranges can be combined to enforcement, and this present invention is not limited.
Due to according to detection method noted earlier, near the point of interest intersection of door place, location may be mistaken for the not wrong point of interest in the presumptive area of this place, location road one side, for the result of further correct detection, the point of interest of erroneous judgement is separated, another exemplary embodiment of Road Detection according to the present invention, in the embodiment shown in Figure 2, described device also comprises: crossing point of interest determining unit (not shown), for determine the point of interest that obtains be whether this place, location intersection in preset range point of interest; Mistake denoising unit (not shown), if be the point of interest of this place, location intersection in preset range for the point of interest obtaining, determine that the point of interest obtaining is in the presumptive area of this place, location road one side, the point of interest location obtaining is correct data.
Particularly, determine an exemplary embodiment of crossing point of interest according to the present invention, described crossing point of interest determining unit comprises: the first crossing point of interest determining unit, if the difference for the vertical range between the vertical range between the point of interest and this place, location road that obtain and the point of interest obtaining and process another road of this place, location intersection is less than the 3rd preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
Determine another exemplary embodiment of crossing point of interest according to the present invention, described crossing point of interest determining unit also comprises: the second crossing point of interest determining unit, if be less than the 4th preset value for the distance between the point of interest and this place, location intersection that obtain, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
It should be noted that, while specifically enforcement, the 3rd preset value and the 4th preset value should be as much as possible little, enough approach on geographic position with point of interest and the intersection guaranteeing to obtain.In addition, described device can be implemented separately any one in the exemplary embodiment of above-mentioned two definite crossing points of interest, also the exemplary embodiment of above-mentioned two definite crossing points of interest can be combined to enforcement, and this present invention is not limited.
In addition, also it should be noted that, above-mentioned three kinds of optional embodiments, except can implementing separately according to the method for the invention, also can be combined enforcement by above-mentioned three kinds of optional embodiments, to the wrong point of interest of various distribution scenario is fully detected.
As can be seen here, the present invention not only can detect the point of interest of positional fault effectively, but also the blind spot that some are difficult for detecting detected, thereby has further promoted the space accuracy rate of point of interest, has reduced the impact that misdata is brought to user.In addition, the present invention has also effectively reduced the consumption of testing process to human and material resources.
It may be noted that according to the needs of implementing, each step of describing can be split as to more multi-step in the application, also the part operation of two or more steps or step can be combined into new step, to realize object of the present invention.
Above-mentioned the method according to this invention can be at hardware, in firmware, realize, or be implemented as and can be stored in recording medium (such as CD ROM, RAM, floppy disk, hard disk or magneto-optic disk) in software or computer code, or be implemented the original storage of downloading by network in remote logging medium or nonvolatile machine readable media and by the computer code being stored in local record medium, thereby method described here can be stored in use multi-purpose computer, such software processing on the recording medium of application specific processor or able to programme or specialized hardware (such as ASIC or FPGA).Be appreciated that, computing machine, processor, microprocessor controller or programmable hardware comprise can store or receive software or computer code memory module (for example, RAM, ROM, flash memory etc.), when described software or computer code are by computing machine, processor or hardware access and while carrying out, realize disposal route described here.In addition,, in the time that multi-purpose computer access is used for realizing the code in the processing shown in this, the execution of code is converted to multi-purpose computer for carrying out the special purpose computer in the processing shown in this.
Although be and described the present invention with reference to preferred embodiment, it should be appreciated by those skilled in the art that in the case of not departing from the spirit and scope of the present invention that are defined by the claims, can carry out various amendments and conversion to these embodiment.

Claims (18)

1. a method that detects point of interest location, is characterized in that, comprising:
Obtain the point of interest of arbitrary location correspondence in map;
Whether the point of interest that detection is obtained is in the presumptive area of this place, location road one side;
If the point of interest obtaining not in the presumptive area of this place, location road one side, determines that the point of interest location obtaining is misdata.
2. the method for claim 1, is characterized in that, whether the point of interest that described detection is obtained in the presumptive area of this place, location road one side, comprising:
Whether the point of interest that adopts abnormal point method of determining and calculating based on distance to detect to obtain is in the presumptive area of this place, location road one side; And/or,
Whether the point of interest that adopts the method for cluster to detect to obtain is in the presumptive area of this place, location road one side; And/or,
Whether the point of interest that the correlation detection between the point of interest that utilization is obtained and this place, location road is obtained is in the presumptive area of this place, location road one side.
3. method as claimed in claim 2, is characterized in that, the detection formula of the described abnormal point method of determining and calculating based on distance is as follows:
1 n - 1 Σ j = 1 , j ≠ i n d ij > ϵ n Σ i = 1 n ( 1 n - 1 Σ j = 1 , j ≠ i n d ij )
Wherein, n represents total number of the point of interest obtaining;
ε represents the pre-determined factor of the dynamic threshold that detects abnormal point of interest;
D ijrepresent the distance between i the point of interest obtaining and j the point of interest obtaining;
If above-mentioned detection formula is set up, i the point of interest obtaining be not in the presumptive area of this place, location road one side.
4. method as claimed in claim 2, is characterized in that, the method for described employing cluster detects the point of interest that obtains whether in the presumptive area of this place, location road one side, comprising:
The point of interest location obtaining is carried out to cluster;
If the result of cluster is multiple bunches, extract at least one point of interest in any one bunch;
Determine that the point of interest extracting is whether in the presumptive area of this place, location road one side;
If the point of interest extracting not in the presumptive area of this place, location road one side, determines that this bunch be not in the presumptive area of this place, location road one side.
5. method as claimed in claim 4, is characterized in that, the condition of described cluster is:
Distance between any two points of interest that obtain in same bunch is less than the first preset value; And/or,
Distance between any one point of interest obtaining and this bunch of central point in same bunch is less than the second preset value; And/or,
Between any two points of interest that obtain in same bunch, do not exist across road information.
6. method as claimed in claim 2, is characterized in that, described in correlativity between the point of interest and this place, location road that obtain be: the vertical range between the point of interest obtaining and this place, location road;
Whether the point of interest that the correlation detection between the point of interest that described utilization is obtained and this place, location road is obtained in the presumptive area of this place, location road one side, comprising:
Determine whether the vertical range between point of interest and this place, location road obtaining is less than the vertical range between point of interest and other roads obtaining;
If the vertical range between the point of interest obtaining and this place, location road is not less than the vertical range between point of interest and other roads obtaining, determine that the point of interest obtaining is not in the presumptive area of this place, location road one side.
7. method as claimed in claim 6, is characterized in that, whether the vertical range between described definite point of interest and this place, location road obtaining is less than the vertical range between point of interest and other roads obtaining, and comprising:
If exist another road crossing to the vertical line between this place, location road with the point of interest obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or,
If exist another road crossing to the reverse extending line of the vertical line between this place, location road with the point of interest obtaining, and the distance between crossing point and the point of interest obtaining is less than the vertical range between point of interest and this place, location road obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or,
Vertical range taking the point of interest that obtains between the center of circle, the point of interest obtaining and this place, location road builds a closed circle as radius; If exist another road crossing with the closed circle of structure, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
8. method as claimed in claim 2, is characterized in that, also comprises:
Determine whether the point of interest obtaining is the point of interest of this place, location intersection in preset range;
If the point of interest obtaining is the point of interest of this place, location intersection in preset range, determine that the point of interest obtaining is in the presumptive area of this place, location road one side.
9. method as claimed in claim 8, is characterized in that, whether described definite point of interest obtaining is the point of interest of this place, location intersection in preset range, comprising:
If the vertical range between the point of interest obtaining and this place, location road and the point of interest obtaining and the difference through the vertical range between another road of this place, location intersection are less than the 3rd preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range; And/or,
If the distance between the point of interest obtaining and this place, location intersection is less than the 4th preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
10. a device that detects point of interest location, is characterized in that, comprising:
Point of interest acquiring unit, for obtaining arbitrary location at point of interest corresponding to map;
Door location detecting unit, for detection of the point of interest obtaining whether in the presumptive area of this place, location road one side;
Mistake screening unit, if for the point of interest that obtains not in the presumptive area of this place, location road one side, determine that the point of interest location obtaining is misdata.
11. devices as claimed in claim 10, is characterized in that, described door location detecting unit comprises:
Abnormality detection subelement, for the point of interest that adopts abnormal point method of determining and calculating based on distance to detect to obtain whether in the presumptive area of this place, location road one side; And/or,
Cluster detection sub-unit, for adopting the device of cluster to determine that the point of interest that obtains is whether in the presumptive area of this place, location road one side; And/or,
Road Detection subelement, whether the point of interest obtaining for the correlation detection of utilizing between point of interest and this place, location road obtaining is in the presumptive area of this place, location road one side.
12. devices as claimed in claim 11, is characterized in that, the detection formula of the described abnormal point method of determining and calculating based on distance is as follows:
1 n - 1 Σ j = 1 , j ≠ i n d ij > ϵ n Σ i = 1 n ( 1 n - 1 Σ j = 1 , j ≠ i n d ij )
Wherein, n represents total number of the point of interest obtaining;
ε represents the pre-determined factor of the dynamic threshold that detects abnormal point of interest;
D ijrepresent the distance between i the point of interest obtaining and j the point of interest obtaining;
If above-mentioned detection formula is set up, i the point of interest obtaining be not in the presumptive area of this place, location road one side.
13. devices as claimed in claim 11, is characterized in that, described cluster detection sub-unit is carried out cluster to the point of interest location obtaining; If the result of cluster is multiple bunches, extract at least one point of interest in any one bunch; Determine that the point of interest extracting is whether in the presumptive area of this place, location road one side; If the point of interest extracting not in the presumptive area of this place, location road one side, determines that this bunch be not in the presumptive area of this place, location road one side.
14. devices as claimed in claim 13, is characterized in that, the condition of described cluster is:
Distance between any two points of interest that obtain in same bunch is less than the first preset value; And/or,
Distance between any one point of interest obtaining and this bunch of central point in same bunch is less than the second preset value; And/or,
Between any two points of interest that obtain in same bunch, do not exist across road information.
15. devices as claimed in claim 11, is characterized in that, described in correlativity between the point of interest and this place, location road that obtain be: the vertical range between the point of interest obtaining and this place, location road;
Described Road Detection subelement comprises:
Distance is determined subelement, for determining whether the vertical range between point of interest and this place, location road obtaining is less than the vertical range between point of interest and other roads obtaining;
Subelement is determined in region, if be not less than the vertical range between point of interest and other roads obtaining for the vertical range between the point of interest and this place, location road that obtain, determine that the point of interest obtaining is not in the presumptive area of this place, location road one side.
16. devices as claimed in claim 15, is characterized in that, described distance determines that subelement comprises:
The first distance is determined subelement, if for existing another road crossing to the vertical line between this place, location road with the point of interest obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or,
Second distance is determined subelement, if for existing another road crossing to the reverse extending line of the vertical line between this place, location road with the point of interest obtaining, and the distance between crossing point and the point of interest obtaining is less than the vertical range between point of interest and this place, location road obtaining, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining; And/or,
The 3rd distance is determined subelement, and the vertical range for the point of interest to obtain between the center of circle, the point of interest obtaining and this place, location road builds a closed circle as radius; If exist another road crossing with the closed circle of structure, determine that the vertical range between point of interest and this place, location road obtaining is not less than the vertical range between point of interest and other roads obtaining.
17. devices as claimed in claim 11, is characterized in that, also comprise:
Crossing point of interest determining unit, for determining whether the point of interest obtaining is the point of interest of this place, location intersection in preset range;
Mistake denoising unit, if be the point of interest of this place, location intersection in preset range for the point of interest obtaining, determines that the point of interest obtaining is in the presumptive area of this place, location road one side.
18. devices as claimed in claim 17, is characterized in that, described crossing point of interest determining unit comprises:
The first crossing point of interest determining unit, if the difference for the vertical range between the vertical range between the point of interest and this place, location road that obtain and the point of interest obtaining and process another road of this place, location intersection is less than the 3rd preset value, determine that the point of interest obtaining is the point of interest of this place, location intersection in preset range; And/or,
The second crossing point of interest determining unit, if be less than the 4th preset value for the distance between the point of interest and this place, location intersection that obtain, determines that the point of interest obtaining is the point of interest of this place, location intersection in preset range.
CN201410183406.8A 2014-04-30 2014-04-30 Method and device for detecting positions of interest points Active CN103954277B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410183406.8A CN103954277B (en) 2014-04-30 2014-04-30 Method and device for detecting positions of interest points

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410183406.8A CN103954277B (en) 2014-04-30 2014-04-30 Method and device for detecting positions of interest points

Publications (2)

Publication Number Publication Date
CN103954277A true CN103954277A (en) 2014-07-30
CN103954277B CN103954277B (en) 2017-05-03

Family

ID=51331587

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410183406.8A Active CN103954277B (en) 2014-04-30 2014-04-30 Method and device for detecting positions of interest points

Country Status (1)

Country Link
CN (1) CN103954277B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016086862A1 (en) * 2014-12-03 2016-06-09 高德软件有限公司 Poi data processing method and device
CN106528597A (en) * 2016-09-23 2017-03-22 百度在线网络技术（北京）有限公司 POI (Point Of Interest) labeling method and device
CN110727793A (en) * 2018-06-28 2020-01-24 百度在线网络技术（北京）有限公司 Method, device, terminal and computer readable storage medium for area identification
CN111352964A (en) * 2020-02-07 2020-06-30 北京梧桐车联科技有限责任公司 Method, device and equipment for acquiring interest point information and storage medium
CN111737382A (en) * 2020-05-15 2020-10-02 百度在线网络技术（北京）有限公司 Ranking method of geographic position points, method for training ranking model and corresponding device
CN113032514A (en) * 2021-05-28 2021-06-25 浙江口碑网络技术有限公司 Method and device for processing point of interest data
CN113297878A (en) * 2020-02-21 2021-08-24 百度在线网络技术（北京）有限公司 Road intersection identification method and device, computer equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6643629B2 (en) * 1999-11-18 2003-11-04 Lucent Technologies Inc. Method for identifying outliers in large data sets
WO2009083719A1 (en) * 2007-12-27 2009-07-09 William Browne-Swinburne Points of interest adjacent to the location of a mobile device
CN101769753A (en) * 2008-11-28 2010-07-07 张政 Method for acquiring coordinate of interest points
CN102902596A (en) * 2012-09-29 2013-01-30 北京百度网讯科技有限公司 Point of interest data verification method and point of interest data verification device
CN103037303A (en) * 2011-09-30 2013-04-10 北京千橡网景科技发展有限公司 Method and equipment used for correcting location of point of interest (POI)
CN103218406A (en) * 2013-03-21 2013-07-24 百度在线网络技术（北京）有限公司 Address information processing method and equipment for interest points

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6643629B2 (en) * 1999-11-18 2003-11-04 Lucent Technologies Inc. Method for identifying outliers in large data sets
WO2009083719A1 (en) * 2007-12-27 2009-07-09 William Browne-Swinburne Points of interest adjacent to the location of a mobile device
CN101769753A (en) * 2008-11-28 2010-07-07 张政 Method for acquiring coordinate of interest points
CN103037303A (en) * 2011-09-30 2013-04-10 北京千橡网景科技发展有限公司 Method and equipment used for correcting location of point of interest (POI)
CN102902596A (en) * 2012-09-29 2013-01-30 北京百度网讯科技有限公司 Point of interest data verification method and point of interest data verification device
CN103218406A (en) * 2013-03-21 2013-07-24 百度在线网络技术（北京）有限公司 Address information processing method and equipment for interest points

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016086862A1 (en) * 2014-12-03 2016-06-09 高德软件有限公司 Poi data processing method and device
CN106528597A (en) * 2016-09-23 2017-03-22 百度在线网络技术（北京）有限公司 POI (Point Of Interest) labeling method and device
CN106528597B (en) * 2016-09-23 2019-07-05 百度在线网络技术（北京）有限公司 The mask method and device of point of interest
CN110727793A (en) * 2018-06-28 2020-01-24 百度在线网络技术（北京）有限公司 Method, device, terminal and computer readable storage medium for area identification
CN111352964A (en) * 2020-02-07 2020-06-30 北京梧桐车联科技有限责任公司 Method, device and equipment for acquiring interest point information and storage medium
CN111352964B (en) * 2020-02-07 2023-09-12 北京梧桐车联科技有限责任公司 Method, device, equipment and storage medium for acquiring interest point information
CN113297878A (en) * 2020-02-21 2021-08-24 百度在线网络技术（北京）有限公司 Road intersection identification method and device, computer equipment and storage medium
CN113297878B (en) * 2020-02-21 2023-12-08 百度在线网络技术（北京）有限公司 Road intersection identification method, device, computer equipment and storage medium
CN111737382A (en) * 2020-05-15 2020-10-02 百度在线网络技术（北京）有限公司 Ranking method of geographic position points, method for training ranking model and corresponding device
US11556601B2 (en) 2020-05-15 2023-01-17 Baidu Online Network Technology (Beijing) Co., Ltd. Method for sorting geographic location point, method for training sorting model and corresponding apparatuses
CN113032514A (en) * 2021-05-28 2021-06-25 浙江口碑网络技术有限公司 Method and device for processing point of interest data
CN113032514B (en) * 2021-05-28 2021-09-07 浙江口碑网络技术有限公司 Method and device for processing point of interest data

Also Published As

Publication number Publication date
CN103954277B (en) 2017-05-03

Similar Documents

Publication Publication Date Title
CN103954277A (en) Method and device for detecting positions of interest points
US11636289B2 (en) Method, apparatus, and device for classifying LiDAR point cloud data, and storage medium
Islam et al. Overview for solid waste bin monitoring and collection system
WO2017129032A1 (en) Disk failure prediction method and apparatus
CN108932510A (en) A kind of rubbish detection method and device
CN105739406A (en) Water purifier, monitoring system thereof and monitoring method
CN108734306A (en) A kind of data processing method, device, road upkeep system and storage medium
CN102831541A (en) Automatic assessment method and device of house value
CN110798543B (en) IP positioning method and device, computer storage medium and computing equipment
CN109429264B (en) Data processing method, device, equipment and computer readable storage medium
CN109408383B (en) Java memory leak analysis method and device
US20150018003A1 (en) Crowdsourcing method to detect broken wifi indoor locationing model
CN108763040B (en) Data acquisition method and data acquisition device
CN106940800A (en) Measuring instrument Recognition of Reading method and device
CN103886294A (en) Method and system for recognizing number of movement times of arrester for convertor station based on images
Ali et al. Coverage and mobile sensor placement for vehicles on predetermined routes: A greedy heuristic approach
CN104298586A (en) Web system exception analytical method and device based on system log
CN111475746B (en) Point-of-interest mining method, device, computer equipment and storage medium
CN103167605B (en) A kind of WiFi outdoor positioning method that satellite auxiliary signal coverage diagram is set up/upgraded
CN107133689B (en) Position marking method
CN108629310B (en) Engineering management supervision method and device
CN105629948A (en) Test case detection method and device
CN111597417A (en) Method and device for monitoring regional water quality and electronic equipment
CN107517474B (en) Network analysis optimization method and device
CN113032514B (en) Method and device for processing point of interest data

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant