WO2020052312A1 - 一种定位方法、装置、电子设备及可读存储介质 - Google Patents

一种定位方法、装置、电子设备及可读存储介质 Download PDF

Info

Publication number
WO2020052312A1
WO2020052312A1 PCT/CN2019/092354 CN2019092354W WO2020052312A1 WO 2020052312 A1 WO2020052312 A1 WO 2020052312A1 CN 2019092354 W CN2019092354 W CN 2019092354W WO 2020052312 A1 WO2020052312 A1 WO 2020052312A1
Authority
WO
WIPO (PCT)
Prior art keywords
cluster
positioning
clustering
optimal
points
Prior art date
Application number
PCT/CN2019/092354
Other languages
English (en)
French (fr)
Inventor
朱静雅
朱青祥
Original Assignee
北京三快在线科技有限公司
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 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Publication of WO2020052312A1 publication Critical patent/WO2020052312A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • G06F18/232Non-hierarchical techniques
    • G06F18/2321Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions

Definitions

  • Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a positioning method and device.
  • POI Point of Interest
  • O2O and map applications POI (Point of Interest) data of tens of millions or even hundreds of millions of levels are collected online.
  • the positioning accuracy of these POI data is particularly important, and it has a great impact on the user experience.
  • solutions for calibrating POI coordinates mainly include the following three types: inverse calculation through addresses, or through field collection, and multi-source fusion algorithms.
  • inverse address calculation means that the longitude and latitude coordinates of the POI address can be used to calculate the longitude and latitude coordinates.
  • Actual mining refers to arranging a manual team to sweep the street and collect POI addresses and latitude and longitude coordinates offline. Due to errors caused by manual negligence and high labor costs, it is often impossible to ensure timeliness.
  • the latitude and longitude multi-source calibration algorithm is a sorting algorithm based on spatial density. It needs to rely on too many data sources, requires more coverage of merchants, and does not use the positioning information contained in the picture. The embodiments of the present disclosure can obtain anchor points efficiently and simply.
  • an embodiment of the present disclosure provides a positioning method, including:
  • a central anchor point in the optimal clustering cluster is determined as a standard anchor point of the business object.
  • an embodiment of the present disclosure provides a positioning device, including:
  • a multimedia data acquisition module configured to acquire multimedia data in a user's behavior data for a business object
  • a data information acquisition module configured to extract a generation time and an anchor point of the multimedia data
  • a clustering module configured to cluster the anchor points to obtain one or more clusters
  • An optimal cluster cluster determining module configured to determine an optimal cluster cluster according to the generation time and the number of positioning points in each of the cluster clusters
  • the standard positioning point determination module is configured to determine a central positioning point in the optimal clustering cluster as a standard positioning point of the business object.
  • an electronic device including:
  • an embodiment of the present disclosure provides a readable storage medium, and when an instruction in the storage medium is executed by a processor of an electronic device, the electronic device is capable of performing the positioning method of the embodiment of the present disclosure.
  • An embodiment of the present disclosure provides a positioning method, by acquiring multimedia data in a user's behavior data for a business object; extracting the generation time and positioning points of the multimedia data; and clustering the positioning points to obtain one or more Cluster clusters; determining an optimal cluster cluster according to the generation time and the number of positioning points in each of the cluster clusters; and determining the business object according to a central positioning point in the optimal cluster cluster Standard anchor points.
  • the positioning method provided in the embodiment of the present disclosure can determine a standard positioning point through positioning points of multimedia data in user behavior data, thereby obtaining positioning points efficiently and simply.
  • FIG. 1 is a flowchart of specific steps of a positioning method provided by Embodiment 1 of the present disclosure
  • Embodiment 2 is a flowchart of specific steps of a positioning method provided by Embodiment 2 of the present disclosure
  • FIG. 2A is a flowchart of an example of data processing provided in Embodiment 2 of the present disclosure
  • FIG. 3 is a structural diagram of a positioning device according to a third embodiment of the present disclosure.
  • FIG. 4 is a structural diagram of a positioning device according to a fourth embodiment of the present disclosure.
  • FIG. 5 schematically illustrates a block diagram of an electronic device for performing a method according to the present disclosure.
  • FIG. 6 schematically illustrates a storage unit for holding or carrying program code implementing a method according to the present disclosure.
  • FIG. 1 a flowchart of specific steps of a positioning method according to the first embodiment of the present disclosure is shown.
  • Step 101 Obtain multimedia data from user behavior data for a business object.
  • the data that the user performs various operations on a business object is behavior data, which includes user comment data, scene description diagrams uploaded by the merchant, error information added by the user, crowdsourcing tasks, user notes, and so on.
  • multimedia data that is, image or video data
  • multimedia data is obtained from a large number of user behavior data.
  • the merchant is also one of the users using the application platform.
  • the above multimedia data may also include other multimedia data that can provide user positioning information, such as audio and text, which is not limited in the embodiments of the present disclosure.
  • Step 102 extract a generation time and an anchor point of the multimedia data
  • the positioning information can be extracted from the multimedia data.
  • the user uploads the multimedia data with a timestamp, so the timestamp of the multimedia data can be extracted to obtain the specific time when the user took the multimedia data.
  • the shooting time is the time for marking in the mobile terminal when the user is shooting multimedia data.
  • Step 103 Cluster the positioning points to obtain one or more clusters.
  • clustering is performed on anchor points that belong to the same POI, where POI is an abbreviation of "Point of Interest", and Chinese can be translated as "point of interest".
  • a POI can be a house, a shop, a post box, a bus station, and so on.
  • the anchor points under one POI are aggregated into different clusters.
  • Step 104 Determine an optimal clustering cluster according to the generation time and the number of positioning points in each of the clustering clusters.
  • the point with the latest shooting time in the cluster cluster or the point with the largest number of positioning points in the cluster cluster is determined as the optimal cluster cluster.
  • the number of positioning points provided can obtain more accurate positioning information.
  • Step 105 Determine the central positioning point in the optimal clustering cluster as the standard positioning point of the business object.
  • the longitude and latitude values of each anchor point in the optimal clustering cluster are averaged, and the central anchor point corresponding to the final average obtained is the standard anchor point of the merchant.
  • the above-mentioned standard positioning points are obtained by performing the center point calculation by the optimal clustering method.
  • the density clustering method is used in the embodiments of the present disclosure.
  • the clustering method is not limited to density clustering.
  • the final standard positioning point is not necessarily the central positioning point calculated by the average value, for example, the weight of each point is calculated by the weight of each latitude and longitude, and the positioning point with the highest score is selected as the central positioning point and determined as the standard.
  • the obtained central positioning point since the weight value is set by a related technical person, the obtained central positioning point may not be the central positioning point obtained by the average value of the points. Therefore, the concept of the central positioning point is not limited in the embodiments of the present disclosure.
  • the average value described above corresponds to the center anchor point.
  • an embodiment of the present disclosure provides a positioning method.
  • the method includes: acquiring multimedia data in a user's behavior data for a business object; extracting a generation time and a positioning point of the multimedia data; Points are clustered to obtain one or more cluster clusters; an optimal cluster cluster is determined according to the generation time and the number of positioning points in each of the cluster clusters; The central anchor point is determined as a standard anchor point of the business object.
  • the existing positioning technology solves the problems of high error, poor timeliness, and difficult implementation.
  • the standard positioning point can be determined by the positioning point of the multimedia data in the user behavior data.
  • FIG. 2 a flowchart of specific steps of a positioning method provided in Embodiment 2 of the present disclosure is shown.
  • Step 201 Obtain multimedia data from user behavior data for a business object.
  • This step is the same as step 101 and will not be described in detail here.
  • Step 202 extracting a generation time and an anchor point of the multimedia data
  • step 102 This step is the same as step 102 and will not be described in detail here.
  • Step 203 Cluster the anchor points by using a density-based clustering algorithm with noise to obtain one or more clusters.
  • the DBSCAN clustering is used for the latitude and longitude points belonging to the same POI, where POI is an abbreviation of "Point of Interest", and Chinese can be translated as "interest point”.
  • a POI can be a house, a shop, a post box, a bus station, and so on.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • the preset cluster contains at least 3 points, and the distance between the points is set to 20m.
  • Step 204 Determine the cluster cluster whose latest shooting time is the first cluster cluster.
  • the average number of days since the shooting date is calculated, and the cluster cluster closest to the current time is selected and labeled as the first cluster. cluster.
  • Step 205 Determine the cluster cluster with the highest number of positioning points in the cluster cluster as the second cluster cluster.
  • a cluster with the largest number of positioning points is selected from the clusters of the clusters, and the cluster is marked as a second cluster.
  • Step 206 if the first cluster cluster and the second cluster cluster are the same, determine the cluster cluster as an optimal cluster cluster;
  • this cluster is selected as the final cluster, that is, the optimal cluster cluster.
  • Step 207 if the first cluster cluster is different from the second cluster cluster, obtain a first number of positioning points in the first cluster cluster;
  • Step 208 if the number of the first positioning points exceeds a second preset threshold, determine the first cluster cluster as an optimal cluster cluster;
  • Step 209 If the number of the first positioning points does not exceed a second preset threshold, determine the second cluster cluster as an optimal cluster cluster.
  • the number of positioning points of the cluster with the closest time is acquired. If the number of positioning points accounts for more than 1/3 of the total number (second preset threshold), Then the cluster with the latest time is selected, that is, the first cluster cluster, otherwise the cluster with the largest number, that is, the second cluster cluster, is selected as the optimal cluster cluster.
  • the above method is used to deal with the relocation of merchants in actual applications. It can be combined with a better trade-off of time and quantity, which can both sense changes and ensure a certain degree of confidence.
  • Step 210 Discretize the number of positioning points in the optimal clustering cluster according to the golden section method to obtain discrete positioning points.
  • the number of positioning points in the optimal clustering cluster is combined with the Fibonacci sequence (golden section method) to discretize, the Fibonacci sequence is: 1 1 2 3 5 8 21 21 34 55 55 89 ... .... Since each cluster has a minimum of 3 points, the corresponding scoring strategy based on the number of discrete positioning points is described below.
  • Step 211 Scoring the discrete positioning points by using a preset scoring strategy to obtain positioning scores of the discrete positioning points;
  • the preset scoring strategy is that the number of discrete points is 10 points for 3-5, 20 points for 5-8, 30 points for 8-13, 40 points for 13-21, and so on, 89 -144 is 90 points ...
  • This method can be understood as a discretization method.
  • the continuous data is discretized using the golden section method. Compared with equal division, it has low frequency sensitivity and is more in line with current application scenarios.
  • Step 212 If the positioning score is lower than a first preset threshold, send a prompt message to the user.
  • the score curve composed of the scores of discrete scoring in the optimal clustering cluster is too low and lower than the first preset threshold set by the relevant technical personnel, it indicates that the positioning points in the optimal clustering cluster If it is not accurate enough, a prompt message is sent to the user stating that the anchor point may not be accurate enough.
  • the background technician obtains the prompt, he will take corresponding measures to optimize the score, for example, push the corresponding address information in the cluster to the merchant to modify, perform manual review, or push the user to modify. .
  • Step 213 Obtain the latitude and longitude values of each anchor point in the optimal clustering cluster.
  • each positioning point in the determined optimal clustering cluster has a latitude and longitude value, and the latitude and longitude value of each point is extracted for operation.
  • Step 214 Calculate an average latitude and longitude value of the latitude and longitude value.
  • a value obtained by adding the longitude value of each anchor point to the number of anchor points is an average value of longitude, and similarly, an average latitude is calculated.
  • Step 215 Obtain a central anchor point in the optimal clustering cluster according to the average latitude and longitude value
  • an anchor point is determined according to the longitude average value and the dimensional mean value, that is, the central anchor point in the optimal clustering cluster.
  • Step 216 Determine the central anchor point as a standard anchor point of the business object.
  • the central anchor point is determined as a standard anchor point of the business object, that is, the merchant.
  • the standard anchor point obtained by combining clustering and time does not depend on the description of the address.
  • the latest latitude and longitude of the anchor point can be obtained at any time, and the standard anchor point obtained through the average calculation method has a high accuracy rate, is simple to implement, and does not rely on manual intervention.
  • an embodiment of the present disclosure provides a positioning method.
  • the method includes: acquiring multimedia data in a user's behavior data for a business object; extracting a generation time and a positioning point of the multimedia data; Points are clustered to obtain one or more cluster clusters; an optimal cluster cluster is determined according to the generation time and the number of positioning points in each of the cluster clusters; The number of positioning points is discretized according to the golden section method to obtain discrete positioning points. The discrete positioning points are scored by using a preset scoring strategy to obtain the positioning points of the discrete positioning points. A preset threshold is used to send prompt information to the user.
  • a central anchor point in the optimal clustering cluster is determined as a standard anchor point of the business object.
  • the existing positioning technology solves the problems of high error, poor timeliness, and difficult implementation.
  • the standard positioning point can be determined by the positioning point of the multimedia data in the user behavior data.
  • the positioning points are discretized and scored by the golden section method, and the accuracy of the positioning points can be determined by the points for reference.
  • FIG. 3 a structural diagram of a positioning device according to a third embodiment of the present disclosure is shown, as follows.
  • a multimedia data acquisition module 301 configured to acquire multimedia data in a user's behavior data for a business object
  • a data information acquisition module 302 configured to extract a generation time and an anchor point of the multimedia data
  • a clustering module 303 configured to cluster the anchor points to obtain one or more clusters
  • An optimal clustering cluster determining module 304 configured to determine an optimal clustering cluster according to the generation time and the number of positioning points in each of the clustering clusters;
  • the standard positioning point determining module 305 is configured to determine a central positioning point in the optimal clustering cluster as a standard positioning point of the business object.
  • an embodiment of the present disclosure provides a positioning device.
  • the device includes: a multimedia data acquisition module for acquiring multimedia data in a user's behavior data for a business object; a data information acquisition module for extracting all data The generation time and positioning points of the multimedia data are described; a clustering module is configured to cluster the positioning points to obtain one or more clustering clusters; an optimal clustering cluster determining module is configured to, according to the generation time, And the number of positioning points in each of the clustering clusters to determine an optimal clustering cluster; a standard positioning point determining module for determining a central positioning point in the optimal clustering cluster as a standard positioning of the business object point.
  • the existing positioning technology solves the problems of high error, poor timeliness, and difficult implementation.
  • the standard positioning point can be determined by the positioning point of the multimedia data in the user behavior data.
  • the third embodiment is a device embodiment corresponding to the first embodiment of the method.
  • the third embodiment is a device embodiment corresponding to the first embodiment of the method.
  • FIG. 4 a structural diagram of a positioning device according to a fourth embodiment of the present disclosure is shown, as follows.
  • a multimedia data acquisition module 401 configured to acquire multimedia data in a user's behavior data for a business object
  • a data information acquisition module 402 configured to extract a generation time and an anchor point of the multimedia data
  • a clustering module 403, configured to cluster the anchor points to obtain one or more clusters
  • the clustering module 403 includes:
  • a clustering sub-module is configured to cluster the anchor points by using a noise-based density-based clustering algorithm to obtain one or more clusters.
  • An optimal cluster cluster determining module 404 configured to determine an optimal cluster cluster according to the generation time and the number of positioning points in each of the cluster clusters;
  • the optimal cluster cluster determining module 404 includes:
  • a first clustering cluster submodule configured to determine the clustering cluster whose latest shooting time is the first clustering cluster
  • a second clustering cluster submodule configured to determine the clustering cluster with the highest number of localization points in the clustering cluster as a second clustering cluster
  • An optimal clustering cluster determining submodule configured to determine the clustering cluster as an optimal clustering cluster if the first clustering cluster and the second clustering cluster are the same;
  • a first positioning point number obtaining sub-module configured to obtain a first positioning point number in the first clustering cluster if the first clustering cluster is different from the second clustering cluster;
  • a first optimal clustering cluster determining submodule configured to determine the first clustering cluster as the optimal clustering cluster if the number of the first positioning points exceeds a second preset threshold
  • a second optimal cluster cluster determination sub-module is configured to determine the second cluster cluster as an optimal cluster cluster if the number of the first positioning points does not exceed a second preset threshold.
  • a discretization module 405, configured to discretize the number of positioning points in the optimal clustering cluster according to the golden section method to obtain discrete positioning points;
  • a positioning score obtaining module 406 configured to score the discrete positioning points by using a preset scoring strategy to obtain positioning scores of the discrete positioning points;
  • the prompting module 407 is configured to send prompting information to the user if the positioning score is lower than a first preset threshold.
  • the standard positioning point determination module 407 is configured to determine a central positioning point in the optimal clustering cluster as a standard positioning point of the business object.
  • the standard positioning point determination module 407 includes:
  • a latitude and longitude value acquisition submodule configured to obtain the latitude and longitude values of each anchor point in the optimal clustering cluster
  • An average latitude and longitude value calculation submodule configured to calculate an average longitude and latitude value of the latitude and longitude value
  • a central positioning point acquisition submodule configured to acquire a central positioning point in the optimal clustering cluster according to the average latitude and longitude value
  • the standard positioning point determination submodule is configured to determine the central positioning point as a standard positioning point of the business object.
  • an embodiment of the present disclosure provides a positioning device.
  • the device includes a multimedia data acquisition module for acquiring multimedia data in a user's behavior data for a business object; a data information acquisition module for extracting the Generation time and anchor point of multimedia data; a clustering module for clustering the anchor points to obtain one or more cluster clusters; an optimal cluster cluster determining module for generating the cluster according to the generation time, and The number of positioning points in each of the clustering clusters determines an optimal clustering cluster; a discretization module is configured to discretize the number of positioning points in the optimal clustering clusters according to the golden section method to obtain discrete positioning points; A positioning score acquisition module is configured to score the discrete positioning points by using a preset scoring strategy to obtain positioning scores of the discrete positioning points; a prompting module is configured to, if the positioning score is lower than a first preset A threshold, sending prompt information to the user.
  • the standard positioning point determination module is configured to determine a central positioning point in the optimal clustering cluster as a standard positioning point of the business object.
  • a central anchor point in the optimal clustering cluster is determined as a standard anchor point of the business object.
  • the existing positioning technology solves the problems of high error, poor timeliness, and difficult implementation.
  • the standard positioning point can be determined by the positioning point of the multimedia data in the user behavior data.
  • the positioning points are discretized and scored by the golden section method, and the accuracy of the positioning points can be determined by the scores for users' reference.
  • the fourth embodiment is a device embodiment corresponding to the second embodiment of the method.
  • the fourth embodiment is a device embodiment corresponding to the second embodiment of the method.
  • An embodiment of the present disclosure further provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor. The positioning method of the embodiment is disclosed.
  • An embodiment of the present disclosure further provides a computer-readable storage medium, and when an instruction in the storage medium is executed by a processor of an electronic device, the electronic device is capable of performing the positioning method in the embodiment of the present disclosure.
  • the description is relatively simple.
  • the related parts refer to the description of the method embodiment.
  • the device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, may be located One place, or it can be distributed across multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the objective of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative labor.
  • the various component embodiments of the present disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components in a computing processing device according to an embodiment of the present disclosure.
  • the present disclosure may also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing part or all of the methods described herein.
  • Such a program that implements the present disclosure may be stored on a computer-readable storage medium or may have the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
  • FIG. 5 illustrates a computing processing device that can implement a method according to the present disclosure.
  • the computing processing device traditionally includes a processor 1010 and a computer program product or computer-readable storage medium in the form of a memory 1020.
  • the memory 1020 may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), an EPROM, a hard disk, or a ROM.
  • the memory 1020 has a storage space 1030 of program code 1031 for performing any of the method steps in the above method.
  • the storage space 1030 for program code may include respective program codes 1031 respectively for implementing various steps in the above method. These program codes can be read from or written into one or more computer program products.
  • Such computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks.
  • Such a computer program product is typically a portable or fixed storage unit as described with reference to FIG. 7.
  • the storage unit may have a storage segment, a storage space, and the like arranged similarly to the memory 1020 in the computing processing device of FIG. 6.
  • the program code may be compressed, for example, in a suitable form.
  • the storage unit includes computer-readable code 1031 ', that is, code that can be read by, for example, a processor such as 1010. These codes, when run by a computing processing device, cause the computing processing device to execute the method described above. Steps.
  • one embodiment means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Also, please note that the word examples "in one embodiment” herein do not necessarily refer to the same embodiment.
  • any reference signs placed between parentheses shall not be construed as limiting the claim.
  • the word “comprising” does not exclude the presence of elements or steps not listed in a claim.
  • the word “a” or “an” preceding an element does not exclude the presence of a plurality of such elements.
  • the disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claim listing several devices, several of these devices may be embodied by the same hardware item.
  • the use of the words first, second, and third does not imply any order. These words can be interpreted as names.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开实施例提供了一种定位方法,涉及计算机技术领域,有助于高效、简单的获取定位点。本公开实施例提供的定位方法,包括:获取用户针对业务对象的行为数据中的多媒体数据;提取所述多媒体数据的生成时间和定位点;对所述定位点进行聚类,得到一个或多个聚类簇;根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。

Description

一种定位方法、装置、电子设备及可读存储介质
本申请要求在2018年9月14日提交中国专利局、申请号为201811075583.9、发明名称为“一种定位方法、装置、电子设备及可读存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本公开实施例涉及计算机技术领域,尤其涉及一种定位方法及装置。
背景技术
在定位技术领域,如在O2O、地图类应用中,在线上收录千万甚至上亿级别的POI(Point of Interest,兴趣点)数据,即在地理信息系统中,一个POI可以是一栋房子、一个商铺、一个邮筒、一个公交站等,这些POI数据的定位准确性尤为重要,对用户体验影响非常大。
现有技术中,对POI坐标进行校准的方案,主要包括以下三种:通过地址反算,或者通过实地采集,多源融合算法。
然而,地址反算是指,通过POI的地址,推算得出其经纬度坐标,会存在较大的误差。实采是指,安排人工团队进行扫街,对线下的POI地址和经纬度坐标进行实地采集,由于人工疏忽带来的错误,以及人力成本非常高,往往无法确保时效性。经纬度多源校准算法是一种基于空间密度的排序算法,需要依赖太多数据源,要求覆盖商户较多,且没有使用图片中包含的定位信息。本公开实施例可以高效、简单的获取定位点。
发明内容
第一方面,本公开实施例提供了一种定位方法,包括:
获取用户针对业务对象的行为数据中的多媒体数据;
提取所述多媒体数据的生成时间和定位点;
对所述定位点进行聚类,得到一个或多个聚类簇;
根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类 簇;
根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。
第二方面,本公开实施例提供了一种定位装置,包括:
多媒体数据获取模块,用于获取用户针对业务对象的行为数据中的多媒体数据;
数据信息获取模块,用于提取所述多媒体数据的生成时间和定位点;
聚类模块,用于对所述定位点进行聚类,得到一个或多个聚类簇;
最优聚类簇确定模块,用于根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;
标准定位点确定模块,用于根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。
第三方面,本公开实施例提供了一种电子设备,包括:
处理器、存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现本公开实施例的所述定位方法。
第四方面,本公开实施例提供了一种可读存储介质,当所述存储介质中的指令由电子设备的处理器执行时,使得电子设备能够执行本公开实施例的所述定位方法。
本公开实施例提供了一种定位方法,通过获取用户针对业务对象的行为数据中的多媒体数据;提取所述多媒体数据的生成时间和定位点;对所述定位点进行聚类,得到一个或多个聚类簇;根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。本公开实施例提供的定位方法,可以通过用户行为数据中的多媒体数据的定位点确定出标准定位点,从而高效、简单的获取定位点。
上述说明仅是本公开技术方案的概述,为了能够更清楚了解本公开的技术手段,而可依照说明书的内容予以实施,并且为了让本公开的上述和其它目的、特征和优点能够更明显易懂,以下特举本公开的具体实施方式。
附图说明
为了更清楚地说明本公开实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本公开实施例一提供的一种定位方法的具体步骤流程图;
图2是本公开实施例二提供的一种定位方法的具体步骤流程图;
图2A是本公开实施例二提供的数据处理示例流程图;
图3是本公开实施例三提供的一种定位装置的结构图;
图4是本公开实施例四提供的一种定位装置的结构图;
图5示意性地示出了用于执行根据本公开的方法的电子设备的框图;以及
图6示意性地示出了用于保持或者携带实现根据本公开的方法的程序代码的存储单元。
具体实施例
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。
实施例一
参照图1,其示出了本公开实施例一提供的一种定位方法的具体步骤流程图。
步骤101,获取用户针对业务对象的行为数据中的多媒体数据;
本公开实施例中,用户在针对一业务对象进行各种操作的数据为行为数据,其中包括用户评论数据,商户上传的场景描述图,用户添加的报错信息, 众包任务,用户笔记等。
具体地,在众多用户行为数据中获取其中的多媒体数据,即图像或者视频数据。
可以理解地,商户也是使用应用平台的用户之一。
可以理解地,上述多媒体数据除了包括图像或视频数据意外,还可以包括其他可以提供用户定位信息的多媒体数据,例如音频、文字等,本公开实施例对此不加以限制。
步骤102,提取所述多媒体数据的生成时间和定位点;
具体地,在用户上传多媒体数据时,由于移动终端会实时获取用户的定位信息,并标记在上述多媒体数据中,所以可以在多媒体数据中提取该定位信息。
同样地,用户上传多媒体数据中同样带有时间戳,所以可以提取多媒体数据的时间戳,以获得用户拍摄多媒体数据的具体时间。
可以理解地,拍摄时间是以用户拍摄多媒体数据时,移动终端中进行标记的时间。
步骤103,对所述定位点进行聚类,得到一个或多个聚类簇。
本公开实施例中,对属于同一个POI下的定位点进行聚类,其中,POI是“Point of Interest”的缩写,中文可以翻译为“兴趣点”。在地理信息系统中,一个POI可以是一栋房子、一个商铺、一个邮筒、一个公交站等。
所以,聚类后将一个POI下的定位点聚合成为不同的聚类簇。
步骤104,根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;
具体地,将聚类簇中拍摄时间最新的点或者聚类簇中的定位点数最多的点,确定为最优聚类簇。
可以理解地,时间较新的聚类簇或者定位点数较多的聚类簇,提供的定位点数可以得到较为准确的定位信息。
步骤105,根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。
具体地,将最优聚类簇中的每一个定位点的经纬度值做平均值计算,得 到的最终平均值对应的中心定位点,即为该商户的标准定位点。
可以理解地,上述标准定位点是通过最优聚类法进行中心点计算得到的,本公开实施例中用到的是密度聚类法,而在实际应用中,聚类方法不限于密度聚类法,所以最终的标准定位点也不一定是通过平均值计算的中心定位点,例如通过每个经纬度的权重计算每个点的分数,选分数最高的定位点为中心定位点,并确定为标准定位点,由于权重值由相关技术人员设定,所得到的中心定位点不一定会是各点的平均值所得到的中心定位点,因此,本公开实施例对中心定位点的概念不限制在上述描述的平均值对应的中心定位点内。
综上所述,本公开实施例提供了一种定位方法,所述方法包括:获取用户针对业务对象的行为数据中的多媒体数据;提取所述多媒体数据的生成时间和定位点;对所述定位点进行聚类,得到一个或多个聚类簇;根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。解决了现有定位技术中存在的误差高、时效差且不易执行的问题,可以通过用户行为数据中的多媒体数据的定位点确定出标准定位点。
实施例二
参照图2,其示出了本公开实施例二提供的一种定位方法的具体步骤流程图。
步骤201,获取用户针对业务对象的行为数据中的多媒体数据;
此步骤与步骤101相同,在此不再详述。
步骤202,提取所述多媒体数据的生成时间和定位点;
此步骤与步骤102相同,在此不再详述。
步骤203,通过具有噪声的基于密度的聚类算法对所述定位点进行聚类,得到一个或多个聚类簇。
本公开实施例中,如图2A所示的多媒体数据处理流程图,对属于同一个POI下的经纬度点采用DBSCAN聚类,其中,POI是“Point of Interest”的缩写,中文可以翻译为“兴趣点”。在地理信息系统中,一个POI可以是一栋房子、一个商铺、一个邮筒、一个公交站等。
具体地,基于密度的聚类DBSCAN(Density-Based Spatial Clustering of Applications with Noise)是一个比较有代表性的基于密度的聚类算法。与划分和层次聚类方法不同,它将簇定义为密度相连的点的最大集合,能够把具有足够高密度的区域划分为簇,并可在噪声的空间数据库中发现任意形状的聚类。
其中,预设簇中最少包含3个点,点与点之间的距离设置为20m。
步骤204,将所述拍摄时间为最新的所述聚类簇确定为第一聚类簇;
具体地,在得到的所有聚类中,结合每个簇的中的定位点的拍摄时间,计算平均拍摄日期距今的天数,选出距今时间最近的聚类簇,标记为第一聚类簇。
步骤205,将所述聚类簇中定位点数最多的所述聚类簇确定为第二聚类簇;
具体地,从聚类的簇中选出定位点数最多的簇,标记为第二聚类簇。
步骤206,若所述第一聚类簇和所述第二聚类簇相同,则将所述聚类簇确定为最优聚类簇;
具体地,如果第一聚类簇和第二聚类簇为同一个,则选取此簇为最终簇,即最优聚类簇。
步骤207,若所述第一聚类簇和所述第二聚类簇不同,则获取所述第一聚类簇中的第一定位点数;
步骤208,若所述第一定位点数超过第二预设阈值,则将所述第一聚类簇确定为最优聚类簇;
步骤209,若所述第一定位点数未超过第二预设阈值,则将所述第二聚类簇确定为最优聚类簇。
具体地,如果第一聚类簇和第二聚类簇不是同一个,则获取时间最近的簇的定位点数,若其中定位点数量占总数量的1/3(第二预设阈值)以上,则选取时间最新的簇,即第一聚类簇,否则选取数量最大的簇,即第二聚类簇,为最优聚类簇。
可以理解地,上述方法在实际应用中是为了应对商户搬迁等行为,可结合时间和数量更好的权衡,既能感知变化又能保证一定的置信度。
步骤210,将所述最优聚类簇中的定位点数按照黄金分割法进行离散化,得到离散定位点;
具体地,对最优聚类簇中的定位点数结合斐波那契序列(黄金分割法)进行离散化,斐波那契序列为:1 1 2 3 5 8 13 21 34 55 89 144.......由于限定了每个簇最少3个点,所以根据离散定位点数制定出的对应的打分策略,描述如下。
步骤211,利用预设打分策略对所述离散定位点进行打分,得到所述离散定位点的定位分值;
具体地,预设打分策略为,离散点数目在3-5个为10分,5-8个为20分,8-13个为30分,13-21个为40分,以此类推,89-144为90分.......此方法可以理解为一种离散化方法。
可以理解地,将连续数据采用黄金分割的方式进行离散化,相较于等比划分,具备低频敏感,更符合当前应用场景。
步骤212,若所述定位分值低于第一预设阈值,则发送提示信息至所述用户。
具体地,如果在最优聚类簇中进行离散化打分的分值组成的分值曲线过低,低于相关技术人员设置的第一预设阈值,则表明最优聚类簇中的定位点不够准确,则向用户发送提示信息,说明该定位点也许不够准确。
可以理解地,当后台技术人员获取到该提示后,会采取相应措施对该分值进行优化,例如,将该聚类簇中对应的地址信息推送商户修改,进行人工审核,或者推送用户修改等。
步骤213,获取所述最优聚类簇中的各定位点的经纬度值;
本公开实施例中,在确定的最优聚类簇中的每个定位点都具有经纬度值,提取每个点的经纬度值,以备运算。
步骤214,计算所述经纬度值的平均经纬度值;
具体地,将各定位点的经度值相加所得值,与定位点数的比值,为经度平均值,同样地,计算出纬度平均值。
步骤215,根据所述平均经纬度值,获取所述最优聚类簇中的中心定位点;
具体地,根据经度平均值和维度平均值确定一个定位点,即为该最优聚类簇中的中心定位点。
步骤216,将所述中心定位点确定为所述业务对象的标准定位点。
具体地,将该中心定位点确定为该业务对象,即商户,的标准定位点。
可以理解地,结合聚类和时间得到的标准定位点,不依赖与地址的描述。
其中,随时可以获得最新的定位点经纬度,再通过平均值计算方式,得到的标准定位点准确率较高,执行简单,不依赖与人工介入。
综上所述,本公开实施例提供了一种定位方法,所述方法包括:获取用户针对业务对象的行为数据中的多媒体数据;提取所述多媒体数据的生成时间和定位点;对所述定位点进行聚类,得到一个或多个聚类簇;根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;将所述最优聚类簇中的定位点数按照黄金分割法进行离散化,得到离散定位点;利用预设打分策略对所述离散定位点进行打分,得到所述离散定位点的定位分值;若所述定位分值低于第一预设阈值,则发送提示信息至所述用户。根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。解决了现有定位技术中存在的误差高、时效差且不易执行的问题,可以通过用户行为数据中的多媒体数据的定位点确定出标准定位点。除此之外,通过黄金分割法进行定位点离散化和打分,可以通过分值确定定位点的准确度,给用户以参考。
实施例三
参照图3,其示出了本公开实施例三提供的一种定位装置的结构图,具体如下。
多媒体数据获取模块301,用于获取用户针对业务对象的行为数据中的多媒体数据;
数据信息获取模块302,用于提取所述多媒体数据的生成时间和定位点;
聚类模块303,用于对所述定位点进行聚类,得到一个或多个聚类簇;
最优聚类簇确定模块304,用于根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;
标准定位点确定模块305,用于根据所述最优聚类簇中的中心定位点确 定为所述业务对象的标准定位点。
综上所述,本公开实施例提供了一种定位装置,所述装置包括:多媒体数据获取模块,用于获取用户针对业务对象的行为数据中的多媒体数据;数据信息获取模块,用于提取所述多媒体数据的生成时间和定位点;聚类模块,用于对所述定位点进行聚类,得到一个或多个聚类簇;最优聚类簇确定模块,用于根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;标准定位点确定模块,用于根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。解决了现有定位技术中存在的误差高、时效差且不易执行的问题,可以通过用户行为数据中的多媒体数据的定位点确定出标准定位点。
实施例三为方法实施例一对应的装置实施例,详细信息可以参照实施例一的详细说明,在此不再赘述。
实施例四
参照图4,其示出了本公开实施例四提供的一种定位装置的结构图,具体如下。
多媒体数据获取模块401,用于获取用户针对业务对象的行为数据中的多媒体数据;
数据信息获取模块402,用于提取所述多媒体数据的生成时间和定位点;
聚类模块403,用于对所述定位点进行聚类,得到一个或多个聚类簇;
优选地,所述聚类模块403,包括:
聚类子模块,用于通过具有噪声的基于密度的聚类算法对所述定位点进行聚类,得到一个或多个聚类簇。
最优聚类簇确定模块404,用于根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;
优选地,所述最优聚类簇确定模块404,包括:
第一聚类簇子模块,用于将所述拍摄时间为最新的所述聚类簇确定为第一聚类簇;
第二聚类簇子模块,用于将所述聚类簇中定位点数最多的所述聚类簇确定为第二聚类簇;
最优聚类簇确定子模块,用于若所述第一聚类簇和所述第二聚类簇相同,则将所述聚类簇确定为最优聚类簇;
第一定位点数获取子模块,用于若所述第一聚类簇和所述第二聚类簇不同,则获取所述第一聚类簇中的第一定位点数;
第一最优聚类簇确定子模块,用于若所述第一定位点数超过第二预设阈值,则将所述第一聚类簇确定为最优聚类簇;
第二最优聚类簇确定子模块,用于若所述第一定位点数未超过第二预设阈值,则将所述第二聚类簇确定为最优聚类簇。
离散化模块405,用于将所述最优聚类簇中的定位点数按照黄金分割法进行离散化,得到离散定位点;
定位分值获取模块406,用于利用预设打分策略对所述离散定位点进行打分,得到所述离散定位点的定位分值;
提示模块407,用于若所述定位分值低于第一预设阈值,则发送提示信息至所述用户。
标准定位点确定模块407,用于根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。
优选地,所述标准定位点确定模块407,包括:
经纬度值获取子模块,用于获取所述最优聚类簇中的各定位点的经纬度值;
平均经纬度值计算子模块,用于计算所述经纬度值的平均经纬度值;
中心定位点获取子模块,用于根据所述平均经纬度值,获取所述最优聚类簇中的中心定位点;
标准定位点确定子模块,用于将所述中心定位点确定为所述业务对象的标准定位点。
综上所述,本公开实施例提供了一种定位装置,所述装置包括多媒体数据获取模块,用于获取用户针对业务对象的行为数据中的多媒体数据;数据信息获取模块,用于提取所述多媒体数据的生成时间和定位点;聚类模块,用于对所述定位点进行聚类,得到一个或多个聚类簇;最优聚类簇确定模块,用于根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类 簇;离散化模块,用于将所述最优聚类簇中的定位点数按照黄金分割法进行离散化,得到离散定位点;定位分值获取模块,用于利用预设打分策略对所述离散定位点进行打分,得到所述离散定位点的定位分值;提示模块,用于若所述定位分值低于第一预设阈值,则发送提示信息至所述用户。标准定位点确定模块,用于根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。解决了现有定位技术中存在的误差高、时效差且不易执行的问题,可以通过用户行为数据中的多媒体数据的定位点确定出标准定位点。除此之外,通过黄金分割法进行定位点离散化和打分,可以通过分值确定定位点的准确度,给用户以参考
实施例四为方法实施例二对应的装置实施例,详细信息可以参照实施例二的详细说明,在此不再赘述。
本公开实施例还提供了一种电子设备,包括:处理器、存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现本公开实施例的所述定位方法。
本公开实施例还提供了一种计算机可读存储介质,当所述存储介质中的指令由电子设备的处理器执行时,使得电子设备能够执行本公开实施例的所述定位方法。
对于装置实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
以上所描述的装置实施例仅仅是示意性的,其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下,即可以理解并实施。
本公开的各个部件实施例可以以硬件实现,或者以在一个或者多个处理器上运行的软件模块实现,或者以它们的组合实现。本领域的技术人员应当 理解,可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本公开实施例的计算处理设备中的一些或者全部部件的一些或者全部功能。本公开还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如,计算机程序和计算机程序产品)。这样的实现本公开的程序可以存储在计算机可读存储介质上,或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到,或者在载体信号上提供,或者以任何其他形式提供。
例如,图5示出了可以实现根据本公开的方法的计算处理设备。该计算处理设备传统上包括处理器1010和以存储器1020形式的计算机程序产品或者计算机可读存储介质。存储器1020可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器1020具有用于执行上述方法中的任何方法步骤的程序代码1031的存储空间1030。例如,用于程序代码的存储空间1030可以包括分别用于实现上面的方法中的各种步骤的各个程序代码1031。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘,紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如参考图7所述的便携式或者固定存储单元。该存储单元可以具有与图6的计算处理设备中的存储器1020类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常,存储单元包括计算机可读代码1031’,即可以由例如诸如1010之类的处理器读取的代码,这些代码当由计算处理设备运行时,导致该计算处理设备执行上面所描述的方法中的各个步骤。
本文中所称的“一个实施例”、“实施例”或者“一个或者多个实施例”意味着,结合实施例描述的特定特征、结构或者特性包括在本公开的至少一个实施例中。此外,请注意,这里“在一个实施例中”的词语例子不一定全指同一个实施例。
在此处所提供的说明书中,说明了大量具体细节。然而,能够理解,本公开的实施例可以在没有这些具体细节的情况下被实践。在一些实例中,并未详细示出公知的方法、结构和技术,以便不模糊对本说明书的理解。
在权利要求中,不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本公开可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中,这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
最后应说明的是:以上实施例仅用以说明本公开的技术方案,而非对其限制;尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本公开各实施例技术方案的精神和范围。

Claims (13)

  1. 一种定位方法,所述方法包括:
    获取用户针对业务对象的行为数据中的多媒体数据;
    提取所述多媒体数据的生成时间和定位点;
    对所述定位点进行聚类,得到一个或多个聚类簇;
    根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;
    根据所述最优聚类簇中的中心确定所述业务对象的标准定位点。
  2. 根据权利要求1所述的方法,在所述根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇的步骤之后,还包括:
    将所述最优聚类簇中的定位点数按照黄金分割法进行离散化,得到离散定位点;
    利用预设打分策略对所述离散定位点进行打分,得到所述离散定位点的定位分值;
    若所述定位分值低于第一预设阈值,则发送提示信息至所述用户。
  3. 根据权利要求1所述的方法,所述对所述定位点进行聚类,得到一个或多个聚类簇的步骤,包括:
    通过具有噪声的基于密度的聚类算法对所述定位点进行聚类,得到一个或多个聚类簇。
  4. 根据权利要求1所述的方法,所述根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇的步骤,包括:
    将所述拍摄时间为最新的所述聚类簇确定为第一聚类簇;
    将所述聚类簇中定位点数最多的所述聚类簇确定为第二聚类簇;
    若所述第一聚类簇和所述第二聚类簇相同,则将所述聚类簇确定为最优聚类簇;
    若所述第一聚类簇和所述第二聚类簇不同,则获取所述第一聚类簇中的第一定位点数;
    若所述第一定位点数超过第二预设阈值,则将所述第一聚类簇确定为最优聚类簇;
    若所述第一定位点数未超过第二预设阈值,则将所述第二聚类簇确定为最优聚类簇。
  5. 根据权利要求4所述的方法,所述根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点的步骤,包括:
    获取所述最优聚类簇中的各定位点的经纬度值;
    计算所述经纬度值的平均经纬度值;
    根据所述平均经纬度值,获取所述最优聚类簇中的中心定位点;
    将所述中心定位点确定为所述业务对象的标准定位点。
  6. 一种定位装置,所述装置包括:
    多媒体数据获取模块,用于获取用户针对业务对象的行为数据中的多媒体数据;
    数据信息获取模块,用于提取所述多媒体数据的生成时间和定位点;
    聚类模块,用于对所述定位点进行聚类,得到一个或多个聚类簇;
    最优聚类簇确定模块,用于根据所述生成时间,以及各所述聚类簇中的定位点数,确定出最优聚类簇;
    标准定位点确定模块,用于根据所述最优聚类簇中的中心定位点确定为所述业务对象的标准定位点。
  7. 根据权利要求6所述的装置,还包括:
    离散化模块,用于将所述最优聚类簇中的定位点数按照黄金分割法进行离散化,得到离散定位点;
    定位分值获取模块,用于利用预设打分策略对所述离散定位点进行打分,得到所述离散定位点的定位分值;
    提示模块,用于若所述定位分值低于第一预设阈值,则发送提示信息至所述用户。
  8. 根据权利要求6所述的装置,所述聚类模块,包括:
    聚类子模块,用于通过具有噪声的基于密度的聚类算法对所述定位点进行聚类,得到一个或多个聚类簇。
  9. 根据权利要求6所述的装置,所述最优聚类簇确定模块,包括:
    第一聚类簇子模块,用于将所述拍摄时间为最新的所述聚类簇确定为第 一聚类簇;
    第二聚类簇子模块,用于将所述聚类簇中定位点数最多的所述聚类簇确定为第二聚类簇;
    最优聚类簇确定子模块,用于若所述第一聚类簇和所述第二聚类簇相同,则将所述聚类簇确定为最优聚类簇;
    第一定位点数获取子模块,用于若所述第一聚类簇和所述第二聚类簇不同,则获取所述第一聚类簇中的第一定位点数;
    第一最优聚类簇确定子模块,用于若所述第一定位点数超过第二预设阈值,则将所述第一聚类簇确定为最优聚类簇;
    第二最优聚类簇确定子模块,用于若所述第一定位点数未超过第二预设阈值,则将所述第二聚类簇确定为最优聚类簇。
  10. 根据权利要求9所述的装置,所述标准定位点确定模块,包括:
    经纬度值获取子模块,用于获取所述最优聚类簇中的各定位点的经纬度值;
    平均经纬度值计算子模块,用于计算所述经纬度值的平均经纬度值;
    中心定位点获取子模块,用于根据所述平均经纬度值,获取所述最优聚类簇中的中心定位点;
    标准定位点确定子模块,用于将所述中心定位点确定为所述业务对象的标准定位点。
  11. 一种计算机程序,包括计算机可读代码,当所述计算机可读代码在计算处理设备上运行时,导致所述计算处理设备执行根据权利要求1-5中的任一个所述的定位方法。
  12. 一种计算机可读存储介质,其中存储了如权利要求11所述的计算机程序。
  13. 一种电子设备,包括:处理器、存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现如权利要求1-5中一个或多个所述的定位方法。
PCT/CN2019/092354 2018-09-14 2019-06-21 一种定位方法、装置、电子设备及可读存储介质 WO2020052312A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811075583.9A CN109522374B (zh) 2018-09-14 2018-09-14 一种定位方法、装置、电子设备及可读存储介质
CN201811075583.9 2018-09-14

Publications (1)

Publication Number Publication Date
WO2020052312A1 true WO2020052312A1 (zh) 2020-03-19

Family

ID=65770987

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/092354 WO2020052312A1 (zh) 2018-09-14 2019-06-21 一种定位方法、装置、电子设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN109522374B (zh)
WO (1) WO2020052312A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113342915A (zh) * 2021-06-22 2021-09-03 深圳壹账通智能科技有限公司 地址脱敏方法、装置、电子设备及存储介质
CN117457114A (zh) * 2023-12-25 2024-01-26 大连锦辉盛世科技有限公司 一种西药药学成分数据智能存储管理方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109522374B (zh) * 2018-09-14 2020-04-17 北京三快在线科技有限公司 一种定位方法、装置、电子设备及可读存储介质
CN111737374B (zh) * 2019-06-21 2023-05-09 腾讯科技(深圳)有限公司 位置坐标确定方法、装置、电子设备及存储介质
CN110888866B (zh) * 2019-12-05 2023-01-17 秒针信息技术有限公司 数据扩充方法、装置、数据处理设备及存储介质
CN111079859B (zh) * 2019-12-31 2020-12-04 哈尔滨工程大学 一种无源多站多目标测向交叉定位与虚假点去除方法
CN111898624B (zh) * 2020-01-21 2024-04-02 北京畅行信息技术有限公司 定位信息的处理方法、装置、设备及存储介质
CN111667026B (zh) * 2020-06-30 2022-11-25 成都新潮传媒集团有限公司 一种多媒体设备地理位置的排错方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104133845A (zh) * 2014-06-30 2014-11-05 百度在线网络技术(北京)有限公司 一种多媒体信息展示的方法与设备
US20160316323A1 (en) * 2014-04-22 2016-10-27 Tencent Technology (Shenzhen) Company Limited Group Positioning Method and System
CN106102164A (zh) * 2016-06-12 2016-11-09 北京三快在线科技有限公司 一种确定接入点位置的方法与装置
CN107908636A (zh) * 2017-09-26 2018-04-13 武汉大学 一种利用社交媒体挖掘人类活动时空模式的方法
CN107908655A (zh) * 2017-10-12 2018-04-13 北京三快在线科技有限公司 一种定位的方法和装置
CN109522374A (zh) * 2018-09-14 2019-03-26 北京三快在线科技有限公司 一种定位方法、装置、电子设备及可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8184913B2 (en) * 2009-04-01 2012-05-22 Microsoft Corporation Clustering videos by location
GB201211626D0 (en) * 2012-06-29 2012-08-15 Tomtom Dev Germany Gmbh Location estimation method and system
US20140129334A1 (en) * 2012-11-02 2014-05-08 Pitney Bowes Inc. Method and system for modeling consumer activity areas based on social media and mobile data
CN106358154A (zh) * 2016-09-07 2017-01-25 中国人民解放军国防科学技术大学 一种模块化的可扩展室内外无缝定位方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160316323A1 (en) * 2014-04-22 2016-10-27 Tencent Technology (Shenzhen) Company Limited Group Positioning Method and System
CN104133845A (zh) * 2014-06-30 2014-11-05 百度在线网络技术(北京)有限公司 一种多媒体信息展示的方法与设备
CN106102164A (zh) * 2016-06-12 2016-11-09 北京三快在线科技有限公司 一种确定接入点位置的方法与装置
CN107908636A (zh) * 2017-09-26 2018-04-13 武汉大学 一种利用社交媒体挖掘人类活动时空模式的方法
CN107908655A (zh) * 2017-10-12 2018-04-13 北京三快在线科技有限公司 一种定位的方法和装置
CN109522374A (zh) * 2018-09-14 2019-03-26 北京三快在线科技有限公司 一种定位方法、装置、电子设备及可读存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113342915A (zh) * 2021-06-22 2021-09-03 深圳壹账通智能科技有限公司 地址脱敏方法、装置、电子设备及存储介质
CN117457114A (zh) * 2023-12-25 2024-01-26 大连锦辉盛世科技有限公司 一种西药药学成分数据智能存储管理方法
CN117457114B (zh) * 2023-12-25 2024-03-12 大连锦辉盛世科技有限公司 一种西药药学成分数据智能存储管理方法

Also Published As

Publication number Publication date
CN109522374B (zh) 2020-04-17
CN109522374A (zh) 2019-03-26

Similar Documents

Publication Publication Date Title
WO2020052312A1 (zh) 一种定位方法、装置、电子设备及可读存储介质
US9824156B1 (en) Targeting of digital content to geographic regions
US9495596B2 (en) Systems and method for identifying locations of infrastructure assets using aerial imagery
US20200081932A1 (en) System and Method for Large Scale Crowdsourcing of Map Data Cleanup and Correction
CN111212383B (zh) 区域常住人口数量的确定方法、装置、服务器和介质
WO2016155386A1 (zh) 用于确定网页页面中包括兴趣点poi数据的方法及装置
CN107168991B (zh) 一种搜索结果展示方法和装置
JP7081884B2 (ja) 音声指紋の照合のための装置及びコンピュータ可読記憶媒体
CN104090970A (zh) 兴趣点的展现方法及装置
CN111427983B (zh) 基于地理信息检索的服务方法、系统、设备及存储介质
CN109947881B (zh) 一种poi判重方法、装置、移动终端及计算机可读存储介质
CN110674349B (zh) 视频poi识别方法、装置及电子设备
US9787557B2 (en) Determining semantic place names from location reports
CN110633381A (zh) 一种识别虚假房源的方法、装置、存储介质及电子设备
CN110211121B (zh) 用于推送模型的方法和装置
CN110659433B (zh) Poi价值评估的方法、装置、设备和计算机存储介质
CN111866727A (zh) 司机聚集点的展示方法、装置、电子设备、存储介质
US20180066946A1 (en) Method and System for Improving Spatial Accuracy of Map Data
Shah et al. Geocoding for public health research: Empirical comparison of two geocoding services applied to Canadian cities
CN110889029B (zh) 城市目标推荐方法和装置
JPWO2018105122A1 (ja) 教師データ候補抽出プログラム、教師データ候補抽出装置、及び教師データ候補抽出方法
JP5637073B2 (ja) 情報処理装置、情報処理方法、及びプログラム
CN113758492A (zh) 地图检测方法和装置
US20180267992A1 (en) Information processing system, information processing method, and non-transitory computer-readable recording medium
CN111639173B (zh) 疫情数据处理方法、装置、设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19859643

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19859643

Country of ref document: EP

Kind code of ref document: A1