WO2017215523A1 - 识别用户所在地理位置的类别的方法及装置 - Google Patents

识别用户所在地理位置的类别的方法及装置 Download PDF

Info

Publication number
WO2017215523A1
WO2017215523A1 PCT/CN2017/087721 CN2017087721W WO2017215523A1 WO 2017215523 A1 WO2017215523 A1 WO 2017215523A1 CN 2017087721 W CN2017087721 W CN 2017087721W WO 2017215523 A1 WO2017215523 A1 WO 2017215523A1
Authority
WO
WIPO (PCT)
Prior art keywords
location
geographic location
type
preset
target geographic
Prior art date
Application number
PCT/CN2017/087721
Other languages
English (en)
French (fr)
Inventor
刘志斌
段培
郑博
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to KR1020187022746A priority Critical patent/KR102121361B1/ko
Priority to JP2018542148A priority patent/JP6689515B2/ja
Priority to EP17812634.8A priority patent/EP3471374B1/en
Publication of WO2017215523A1 publication Critical patent/WO2017215523A1/zh
Priority to US15/981,978 priority patent/US11252534B2/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/52—Network services specially adapted for the location of the user terminal
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/025—Services making use of location information using location based information parameters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
    • H04W4/21—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel for social networking applications

Definitions

  • the present application relates to the field of computer technologies, and in particular, to a method and apparatus for identifying a category of a geographic location of a user.
  • GPS Global Positioning System
  • the handheld device obtains the geographical location of the user (usually the latitude and longitude information of the user's location) through the GPS equipment, and then uploads it to the server, and then the server provides corresponding push according to the geographical location of the user. service.
  • the server In order to make the pushed content more extensive, the server usually needs to classify the user's geographic location, for example, into a residence, a work place, an entertainment location, etc., and then classify the user's geographic location into the corresponding type, and then perform content according to the type. Push.
  • the present application proposes a method for identifying a category of a user's geographic location, including:
  • the location type of the target geographic location is identified according to the membership degree of the target geographic location under each preset location type.
  • Another aspect of the present application is directed to an apparatus for identifying a category of a geographic location of a user, including:
  • the memory stores an instruction module executable by the processor, the instruction module comprising:
  • a geographic location collection module configured to receive a target geographic location and a corresponding upload time when the user terminal transmits data in the instant messaging application or the social network application, and the target geographic location corresponds to at least one uploading time;
  • mapping relationship obtaining module configured to acquire a preset time-position type mapping relationship, where the time-position type mapping relationship defines a probability value corresponding to the preset time interval under each preset position type
  • a membership calculation module configured to traverse the preset location type, calculate a sum of probability values corresponding to the location time of the target geographic location, and obtain a target geographic location under each preset location type. Membership;
  • the type identification module is configured to identify the location type of the target geographic location according to the membership degree of the target geographic location under each preset location type.
  • FIG. 1 is a schematic flow chart of a method for identifying a category of a geographic location of a user in an embodiment
  • FIG. 2 is a schematic diagram showing a geographical distribution in an embodiment
  • 3 is a schematic diagram of an inappropriate time-location category mapping relationship in an embodiment
  • FIG. 4 is a schematic structural diagram of an apparatus for identifying a category of a geographical location of a user in an embodiment
  • FIG. 5 is a schematic structural diagram of a computer device for operating the foregoing method for identifying a category of a geographic location of a user in an embodiment.
  • the embodiment of the present application proposes a high-accuracy method for identifying a category of a geographical location of a user.
  • the implementation of the method may rely on a computer program running on a von Neumann system-based computer system, which may be an instant messaging application providing an LBS service, a social networking application or O2O (online to offline) , online to offline service) application server program, the computer system performing the above method may be a server device running a server program of an instant messaging application, a social network application or an O2O application.
  • a GPS device may be disposed on the user terminal, so that the geographic location where the user terminal is located may be detected in real time.
  • Clients of instant messaging applications, social networking applications, or O2O applications are also installed on the user terminals, and these applications are based on the LBS service.
  • a plurality of location types are preset on the server, such as a residence, a work point, a leisure area, etc., and a time-location type mapping relationship table is also set. For the geographic location uploaded by the user terminal, the upload time is obtained, and then the query is performed.
  • the mapping table identifies the categories of the user's geographic location.
  • the method for identifying a category of a user's geographic location includes:
  • Step S102 Receive a target geographic location and a corresponding upload time that are uploaded when the user terminal transmits data in the instant messaging application or the social network application, and one target geographic location corresponds to at least one uploading time.
  • the server collects the user's geographic location by detecting that the user terminal transmits data in an instant messaging application or a social networking application.
  • the user terminal can upload user generated content in the user (User Generate Content), upload your own geographic location. For example, when the user sends a message to another user by using the user terminal, or uploads a photo to the server, when uploading the video, the user terminal may attach the geographical location acquired by the GPS chip to the uploaded data. For another example, when the user makes a payment using the mobile terminal, the mobile terminal can upload the geographic location of the user to the server.
  • the server may receive at least one geographic location uploaded by the user terminal when transmitting data in the instant messaging application or the social network application.
  • the server may cluster the at least one geographic location to obtain a target geographic location, where the uploading time of the target geographic location is the uploading time of the at least one geographic location.
  • multiple uploaded geographic locations can be clustered. For example, as shown in FIG. 2, according to the uploaded geographic The intensity of the location is clustered, and the location area obtained by clustering is the target geographic location.
  • each uploading time of the cluster is still retained, and the uploading time of each uploaded geographic location is set as the uploading time of the target geographic location, that is, the target geographic location and the uploading time may be one-to-many relationships.
  • the physical meaning is that the user stays in a certain area for a long enough time and uploads the geographic location multiple times.
  • Step S104 Acquire a preset time-position type mapping relationship, and the time-position type mapping relationship defines a probability value under each preset position type corresponding to the preset time interval.
  • location types pre-defined on the server such as: residence, work point, leisure area;
  • the server also has a plurality of time intervals defined in advance, for example, 0 to 6 points, 6 to 9 points, and the like.
  • Each time interval is set with a probability value under each preset position type.
  • the time interval from 0 o'clock to 6 o'clock can be set to A under the position type "residence”
  • the probability value under the position type "work point” can be set to B, under the position type "leisure area”
  • the probability value can be set to C.
  • Table 1 shows a mapping table of time-location type mapping relationships in the case of a working day in one embodiment.
  • this table is only used to indicate the mapping relationship between the preset time period and each preset location type and the probability value of the mapping. In the actual product, the server does not need the same table.
  • This mapping relationship can be stored in a variety of data structures.
  • a plurality of time intervals are pre-divided, such as 0-6, 6-9, 9-12 and the like in Table 1, in each time interval.
  • Each location type corresponds to a probability value.
  • the probability of residence is 0.7
  • the probability of working point is 0.1
  • the probability of leisure area is 0.2.
  • the physical meaning is that in the time interval from 6 am to 6 am, the user has a larger The probability (70% probability) rests at the place of residence, with a lower probability of working overtime at the work point (10% probability) or playing in a recreation venue (20%).
  • the physical meaning is that at the same time, the user can only exist in one of all preset location types, that is, the user is either at home, at work, or in a leisure area, and cannot be located at two locations at the same time. May disappear out of thin air.
  • the physical meaning is that users can't be in the same place all the time, and this time-location type mapping becomes meaningless.
  • FIG. 3 shows a time-position type mapping relationship in which a design fails.
  • the so-called “residence address probability” and “work address probability” in the table are respectively equal to 1 in time.
  • the time-location type mapping relationship stored on the server may not be unique, and different time-location type mapping relationships may be pre-designed according to different users, that is, the server may acquire the instant messaging application or the social interaction on the user terminal.
  • time-location type mapping For example, users on the white shift (9 to 17 o'clock) and night shift users (22 o'clock to 6 o'clock in the morning) have different schedules, so when designing the time-location type mapping, at 0-6 time In the time-location type mapping relationship corresponding to the user of the white-shift class, the probability of the residence is large, and in the time-location type mapping relationship corresponding to the user of the night shift, the probability of the work point is large. In this way, a more realistic probability can be achieved, which makes the identification more accurate.
  • the server may also acquire a preset time period corresponding to the uploading time, and obtain a preset time-location type mapping relationship corresponding to the time period corresponding to the uploading time.
  • Table 2 shows a mapping table of time-location type mapping relationships in the case of holidays in one embodiment.
  • this table is only used to indicate the mapping relationship between the preset time period and each preset location type and the probability value of the mapping. In the actual product, the server does not need the same table.
  • This mapping relationship can be stored in a variety of data structures.
  • the server adopts different time-location type mapping relationships for different time periods (such as working days and holidays), so that the probability of the user in the location type is more consistent with the corresponding user habits in the same time interval, thereby making the recognition more accurate.
  • Step S106 traverse the preset location type, calculate the sum of the probability values corresponding to the uploading time of the target geographic location under the traversed location type, and obtain the membership degree of the target geographic location under each preset location type.
  • the degree of membership of the target geographic location L under the location type is:
  • the degree of membership of the target location L under the location type is the work point:
  • the degree of membership of the target location L under the location type is:
  • n is the total number of uploading times of the target geographic location L
  • j is the serial number of the uploading time
  • t j is the uploading time point.
  • Step S108 Identify the location type of the target geographic location according to the membership degree of the target geographic location under each preset location type.
  • the membership probability of the target geographic location under each preset location type may be obtained by a statistical method, specifically for:
  • the target probability of the target geographic location L under the location type is:
  • the probability of belonging to the target geographic location L in the location type is working underground is:
  • the probability of belonging to the target geographic location L under the location type as the leisure zone is:
  • the position type with a high probability can be selected as the position type of the target geographical position. If the probability of the three is similar, the user may be prompted to perform manual labeling.
  • the statistical method is insufficient in reliability due to the small number of samples, and thus the membership degree in each preset location type may be adopted in the target geographical location.
  • a ratio of the probability sums under the respective location types, the location type of the target geographic location is identified based on the ratio.
  • the ratio of the target geographic location L to the sum of the degree of membership under the location type being the residence and the location type being the residence is:
  • m is the number of all time intervals
  • i is the sequence number of all preset time intervals
  • t i is the time interval.
  • Table 2 it is the sum of the probability values of the column of “residence probability”.
  • the ratio of the target geographic location L to the sum of the subordinates of the location type of the work underground and the location type of the work underground is:
  • the ratio of the target geographic location L to the sum of the degree of membership under the location type as the leisure zone and the location type as the leisure zone is:
  • the position type corresponding to the largest and larger than the threshold ratio may be selected as the position type of the target geographical position. If the ratio of the three is similar, and the maximum scale value is less than the threshold, the user may be prompted to perform manual labeling.
  • the server may further detect the geographic location of the user terminal, and search for the geographic location uploaded by the user terminal.
  • the location type is selected to be pushed to the user terminal by the data content corresponding to the location type.
  • the target geographic location L is identified as the leisure zone
  • the server detects the current location of the user, it can be recognized that the user is currently in the leisure zone, and at this time, the user can be Push some shopping guides, offers or advertising information that is suitable for this place.
  • the content that the server pushes to the user can be more in line with the user's current environment, which makes the push content more accurate.
  • the server may further calculate a distribution of the geographic location under the preset location type; a user account logged in on the instant messaging application or the social network application on the user terminal; determining a credit rating of the user account according to a distribution of geographic locations under the location type.
  • the server of the credit information system can determine that the user has a commercial central area.
  • Real estate therefore, has a higher credit rating; correspondingly, if multiple target geographic locations are identified as the residence of a user, the server of the credit information system can determine that the user may have multiple properties, so it can also be given The user has a higher credit rating.
  • the server of the credit information system can determine that the user is only in the commercial central area. The employee of the job, and the housing value of the residence is low, so only the user is given a lower credit rating.
  • the above-mentioned way of setting the credit rating for the user in combination with the geographical location of the user is equivalent to the traditional technology, based on the data of the bank flow and the user's past credit history, and establishing a scoring model to assign a quantitative score to the user's "credit".
  • the user's passive behavior record and activity record are used to discriminate the actual economic strength of the user, which can prevent the user from forging data in the traditional credit information system (for example, using the short-term large amount of funds to deposit and deposit) The illusion of higher bank flow, which makes the credit rating more accurate.
  • the above method can process the continuously acquired geographical location data stream in real time, and can be run on the server side after being written into a separate application software or a dedicated module in a large software system by using a programming language such as C/C++ or Java.
  • the raw geolocation data or processed intermediate data or final result from the single or multi-user mobile client will be combined with the historical data or results on the server to calculate the updated result again, and then real-time or non- It can be output to other applications or modules in real time, or it can be written to a server-side database or file for storage.
  • the above method can also be implemented on a distributed, parallel computing platform composed of multiple servers, equipped with a customized, easy-to-interactive web interface or other various UI interfaces, formed for individuals, groups or enterprises.
  • the embodiment of the present application further provides a device for identifying a category of a geographical location of a user.
  • the device for identifying a category of a geographic location of the user includes a geographic location collection module 102 and a mapping relationship acquisition module. 104.
  • the geographic location collection module 102 is configured to receive a target geographic location and a corresponding uploading time that are uploaded when the user terminal transmits data in the instant messaging application or the social network application, and the target geographic location corresponds to the at least one uploading time;
  • the mapping relationship obtaining module 104 is configured to acquire a preset time-position type mapping relationship, where the time-position type mapping relationship defines a probability value corresponding to the preset time interval under each preset position type;
  • the membership degree calculation module 106 is configured to traverse the preset location type, calculate a sum of probability values corresponding to the location time of the target geographic location, and obtain the target geographic location under each preset location type. Membership degree;
  • the type identification module 108 is configured to identify the location type of the target geographic location according to the membership degree of the target geographic location under each preset location type.
  • the geographic location collection module 102 is further configured to receive at least one geographic location that is uploaded when the user terminal transmits data in an instant messaging application or a social network application, and collect the at least one geographic location.
  • the class obtains a target geographic location, and the uploading time of the target geographic location is a respective uploading time of the at least one geographic location.
  • the mapping relationship obtaining module 104 is further configured to acquire an account type of a user account that is logged in the instant messaging application or the social network application on the user terminal; The time-location type mapping relationship corresponding to the account type.
  • the mapping relationship obtaining module 104 is further configured to acquire a preset time period corresponding to the uploading time, and obtain a preset time corresponding to the time period corresponding to the uploading time. Location type mapping.
  • the preset time-position type mapping relationship is: a sum of probability values corresponding to each preset position type corresponding to the same time interval is 1; the same location type is at each time The sum of the probability values corresponding to the interval is not 1.
  • the type identification module 108 is further configured to: when the number of upload times corresponding to the target geographic location is greater than or equal to a threshold, calculate the target geographic location at each preset location type. Calculating the ratio of the degree of membership of the target geographic location to the sum of the membership degrees under each preset location type, and obtaining the membership probability of the target geographic location under each preset location type, Identifying a location type of the target geographic location according to a membership probability of the target geographic location under each preset location type.
  • the type identification module 108 is further configured to: when the number of upload times corresponding to the target geographic location is less than a threshold, where the target geographic location is under each preset location type.
  • the ratio of the membership degree to the sum of the probabilities under the respective location types, and the location type of the target geographic location is identified according to the ratio.
  • the foregoing apparatus further includes a content pushing module 110, configured to detect a geographic location of the user terminal, search for a location type of the geographic location uploaded by the user terminal, and select a location The data content corresponding to the location type is pushed to the user terminal.
  • a content pushing module 110 configured to detect a geographic location of the user terminal, search for a location type of the geographic location uploaded by the user terminal, and select a location The data content corresponding to the location type is pushed to the user terminal.
  • the foregoing apparatus further includes a credit evaluation module 112, configured to calculate a distribution of geographic locations under the preset location type, and obtain the user terminal a user account registered on the instant messaging application or the social network application; determining a credit rating of the user account according to a distribution of geographic locations under the location type.
  • a credit evaluation module 112 configured to calculate a distribution of geographic locations under the preset location type, and obtain the user terminal a user account registered on the instant messaging application or the social network application; determining a credit rating of the user account according to a distribution of geographic locations under the location type.
  • the probability that the user is located at a certain location category in a certain time interval also has a certain regularity. Therefore, a time-location type mapping relationship is pre-configured on the server, and a probability value under each preset position type corresponding to the preset time interval is defined in the time-location type mapping relationship.
  • the server may find the membership degree of the sum of the probability values of the target geographic location under each location type according to the uploading time of the target geographic location, so that the server may identify the geographical location of the user according to the membership degree. category.
  • the basis of adoption is the activity record passively generated by the user when using the instant messaging application or the social network application, so there is no forged component, and the recognition method is based on the objective law of the user's daily life, and therefore, the recognition accuracy is high.
  • FIG. 5 illustrates a terminal 10 of a von Neumann system-based computer system that operates the above-described method of identifying categories of geographic locations of users.
  • the computer system can be a terminal device such as a smart phone, a tablet computer, a palmtop computer, a notebook computer or a personal computer.
  • an external input interface 1001, a processor 1002, a memory 1003, and an output interface 1004 connected through a system bus may be included.
  • the external input interface 1001 can optionally include at least a network interface 10012.
  • the memory 1003 may include an external memory 10032 (eg, a hard disk, an optical disk, or a floppy disk, etc.) and an internal memory 10034.
  • the output interface 1004 can include at least a device such as a display 10042.
  • the operation of the method is based on a computer program, the program file of which is stored in the external memory 10032 of the aforementioned von Neumann system-based computer system 10, and is loaded into the internal memory 10034 at runtime, It is then compiled into a machine code and then passed to the processor 1002 for execution, so that the logical location acquisition module 102, the mapping relationship acquisition module 104, the membership calculation module 106, and the like are formed in the von Neumann system-based computer system 10.
  • Type identification module 108 is based on a computer program, the program file of which is stored in the external memory 10032 of the aforementioned von Neumann system-based computer system 10, and is loaded into the internal memory 10034 at runtime, It is then compiled into a machine code and then passed to the processor 1002 for execution, so that the logical location acquisition module 102, the mapping relationship acquisition module 104, the membership calculation module 106, and the like are formed in the von Neumann system-based computer system 10.
  • Type identification module 108 is based on a computer program, the program
  • the input parameters are all received through the external input interface 1001, and transferred to the cache in the memory 1003, and then input to the processor 1002 for processing, the processed result data or
  • the cache is cached in the memory 1003 for subsequent processing, or is passed to the output interface 1004 for output.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Operations Research (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Algebra (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Remote Sensing (AREA)
  • Computing Systems (AREA)
  • Information Transfer Between Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请实施例公开了一种识别用户所在地理位置的类别的方法及装置，其中方法包括：接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间；获取预设的时间-位置类型映射关系，时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值；遍历预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属度；根据目标地理位置在各个预设的位置类型下的隶属度识别目标地理位置的位置类型。

Description

识别用户所在地理位置的类别的方法及装置
本申请要求于2016年06月12日提交中国专利局、申请号为201610410598.0、发明名称为“识别用户所在地理位置的类别的方法和装置”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
本申请涉及计算机技术领域，尤其涉及一种识别用户所在地理位置的类别的方法及装置。
背景技术
随着互联网技术的发展，基于LBS(基于位置的服务，Location Based Service)的互联网平台以及APP(应用程序，Application)越来越多，在这些应用中，用户的手持设备上通常设置有GPS(全球定位系统，Global Positioning System)装置，手持设备通过GPS装备获取到用户所在的地理位置(通常为用户所在位置的经纬度信息)，然后上传至服务器，然后由服务器根据用户的地理位置提供相应的推送服务。为了使得推送的内容更广泛，服务器通常需要将用户的地理位置分类，例如，分为居所、工作地点、娱乐地点等类型，然后将用户的地理位置分类到相应的类型下，再根据类型进行内容推送。
发明内容
本申请一方面提出了一种识别用户所在地理位置的类别的方法，包括：
接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间；
获取预设的时间-位置类型映射关系，所述时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值；
遍历所述预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属 度；
根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型。
本申请另一方面提出了一种识别用户所在地理位置的类别的装置，包括：
处理器和存储器，所述存储器中存储有可被所述处理器执行的指令模块，所述指令模块包括：
地理位置采集模块，用于接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间；
映射关系获取模块，用于获取预设的时间-位置类型映射关系，所述时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值；
隶属度计算模块，用于遍历所述预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属度；
类型识别模块，用于根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型。
附图简要说明
为了更清楚地说明本申请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简单地介绍，下面描述中的附图仅仅是本申请的一些实施例，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。
其中：
图1为一个实施例中一种识别用户所在地理位置的类别的方法的流程示意图；
图2为一个实施例中地理位置的分布示意图；
图3为一个实施例中不恰当的时间-位置类别映射关系示意图；
图4为一个实施例中一种识别用户所在地理位置的类别的装置的结构示意图；
图5为一个实施例中运行前述识别用户所在地理位置的类别的方法的计算机设备的结构示意图。
实施本发明的方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，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，都属于本申请保护的范围。
本申请实施例提出了一种高准确度的识别用户所在地理位置的类别的方法。该方法的实现可依赖于计算机程序，该计算机程序可运行于基于冯诺依曼体系的计算机系统之上，该计算机程序可以是提供LBS服务的即时通信应用、社交网络应用或O2O(online to offline，线上到线下的服务)应用的服务器程序，执行上述方法的计算机系统可以是运行即时通信应用、社交网络应用或O2O应用的服务器程序的服务器设备。
在本方法的应用场景中，用户终端上可设置有GPS装置，从而可实时地检测到用户终端所在的地理位置。用户终端上还安装有即时通信应用、社交网络应用或O2O应用的客户端，这些应用都基于LBS服务。服务器上预先设置有多个位置类型，例如居所、工作点、休闲区域等，还设置有时间-位置类型映射关系的表，对于用户终端上传的地理位置，通过获取其上传时间，再通过查询该映射表即可对用户所在地理位置的类别进行识别。
具体的，如图1所示，该识别用户所在地理位置的类别的方法包括：
步骤S102：接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间。
服务器采集用户的地理位置是通过检测用户终端在即时通信应用或社交网络应用中传输数据来获取的。用户终端可在用户上传用户生成内容(User  Generate Content)时，上传自身的地理位置。例如，用户在使用用户终端向另一用户发送消息时，或者向服务器上传照片，上传视频时，用户终端可在上传数据中附加通过GPS芯片获取的地理位置。再例如，用户在使用移动终端进行支付时，移动终端可将用户的地理位置上传至服务器。
在本实施例中，当用户在小范围内长时间活动时，会多次上传地理位置，服务器则可接收用户终端在即时通信应用或社交网络应用中传输数据时上传的至少一个地理位置。服务器可将该至少一个地理位置聚类得到目标地理位置，目标地理位置的上传时间为所述至少一个地理位置各自的上传时间。
例如，若用户在某个公园中玩耍了一天，并拍照发布了多次内容，则用户在该公园中将上传多个地理位置到服务器，且每个地理位置对应有独立的上传时间，但对于服务器而言，往往不需要精确到一个经纬度坐标，而只需要精确到一块区域即可，因此，可对多个上传的地理位置进行聚类，例如，如图2所示，可根据上传的地理位置的密集程度进行聚类，聚类得到的位置区域即为目标地理位置。但聚类的每个上传时间仍然保留，即将对应每个上传的地理位置的上传时间均设置为该目标地理位置的上传时间，也就是说，目标地理位置与上传时间可以是一对多的关系，其物理意义即为用户在某一个区域待了足够长的时间，并且多次上传地理位置。
步骤S104：获取预设的时间-位置类型映射关系，时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值。
服务器上预先定义有多个位置类型，例如：居所、工作点、休闲区域；
服务器上还预先定义有多个时间区间，例如：0点至6点，6点至9点等。
每个时间区间在各个预设的位置类型下均设置有概率值。例如，0点至6点的时间区间在位置类型“居所”下的概率值可设置为A，在位置类型“工作点”下的概率值可设置为B，在位置类型“休闲区域”下的概率值可设置为C。
如表1所述，表1展示了一个实施例中，工作日情况下的时间-位置类型映射关系的映射表。
表1
Figure PCTCN2017087721-appb-000001
Figure PCTCN2017087721-appb-000002
需要说明的是，此表仅用于表示预设的时间段与各个预设的位置类型的映射关系及其映射的概率值，实际产品中，服务器并不需要与此完全相同的表格。该映射关系可存储于多种数据结构。
由表1可知，服务器上预存的时间-位置类型映射关系中，预先划分有多个时间区间，如表1中的0-6、6-9、9-12等时间区间，每个时间区间中，各个位置类型对应有概率值。如0-6时间区间中，居住地的概率为0.7，工作点的概率为0.1，休闲区域的概率为0.2，其物理含义为，在凌晨到早上6点这个时间区间内，用户有较大的可能性(70％的概率)在居住地休息，有较小的可能性在工作点加班(10％的概率)或在娱乐场所玩耍(20％)的概率。
需要说明的是，预设的时间-位置类型映射关系还需要满足以下条件：
1.同一时间区间t对应的用户在各个预设的位置类型下的概率值之和为1，即：
P(用户在居住地|T＝t)+P(用户在工作地|T＝t)+P(用户在休闲区域|T＝t)＝1
其物理含义就是说，同一时间，用户只能存在于所有预设的位置类型中的一个，即用户要么在居所，要么在工作地，要么在休闲区域，不可能同时位于两个地点，也不可能凭空消失。
2.同一位置类型在各个时间区间对应的概率值之和不为1，即：
Figure PCTCN2017087721-appb-000003
其物理含义就是说，用户不可能所有时间均处于同一个地点，此时这个时间-位置类型映射关系就变得没有意义。
如图3所示，图3展示的即为一种设计失败的时间-位置类型映射关系。表中所谓的“居住地址概率”和“工作地址概率”分别在时间上积分等于1。
可选的，服务器上存储的时间-位置类型映射关系可不唯一，可根据不同的用户预先设计不同的时间-位置类型映射关系，即服务器可获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号的账号类型；获取预设 的与所述账号类型对应的时间-位置类型映射关系。
例如，上白班的用户(9至17点上班)和上夜班的用户(22点至次日凌晨6点上班)的作息时间不同，因此在设计时间-位置类型映射关系时，在0-6时间段，上白班的用户对应的时间-位置类型映射关系中，居所的概率较大，而上夜班的用户对应的时间-位置类型映射关系中，工作点的概率较大。这样才能体现出较真实的概率，从而使得识别更加准确。
另外，服务器还可获取所述上传时间对应的预设的时间段，获取预设的与所述上传时间对应的时间段对应的时间-位置类型映射关系。
例如，工作日和节假日时，用户的生活习惯不同，则在同一时间区间时，居所、工作点和休闲区域的概率应该设计为不同。参考表2所示，表2展示了一个实施例中，节假日情况下的时间-位置类型映射关系的映射表。
需要说明的是，此表仅用于表示预设的时间段与各个预设的位置类型的映射关系及其映射的概率值，实际产品中，服务器并不需要与此完全相同的表格。该映射关系可存储于多种数据结构。
表2
时间区间 居住地概率 工作地概率 休闲区域概率
0-9 0.68 0.02 0.3
9-12 0.5 0.1 0.4
12-14 0.4 0.05 0.55
14-18 0.3 0.1 0.6
18-21 0.4 0.02 0.58
21-24 0.5 0.05 0.45
对比表1和表2可看出，在14-18的时间区间中，工作日用户在工作地的概率较大(70％的概率)，而在节假日，用户则在休闲区域的概率较大(60％的概率)。
服务器针对不同时间段(例如工作日和节假日)采用不同的时间-位置类型映射关系，可使得在同一时间区间时，用户在位置类型的概率更加符合相应用户习惯，从而使得识别更加准确。
步骤S106：遍历所述预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属度。
例如，在表2所示节假日的场景中，目标地理位置L在位置类型为居所下的隶属度即为：
Figure PCTCN2017087721-appb-000004
目标地理位置L在位置类型为工作点下的隶属度即为：
Figure PCTCN2017087721-appb-000005
目标地理位置L在位置类型为休闲区域下的隶属度即为：
Figure PCTCN2017087721-appb-000006
其中，n为目标地理位置L的上传时间的总次数，j为上传时间的序号，tj为上传时间点。
步骤S108：根据目标地理位置在各个预设的位置类型下的隶属度识别目标地理位置的位置类型。
在本实施例中，在样本充足的情况下，即目标地理位置对应的上传时间的数量大于或等于阈值时，可通过统计方法得到目标地理位置在各个预设的位置类型下的隶属概率，具体为：
在所述目标地理位置对应的上传时间的数量大于或等于阈值时，计算所述目标地理位置在各个预设的位置类型下的隶属度之和，计算所述目标地理位置在各个预设的位置类型下的隶属度与所述隶属度之和的比值，得到目标地理位置在各个预设的位置类型下的隶属概率，根据所述目标地理位置在各个预设的位置类型下的隶属概率识别所述目标地理位置的位置类型。
例如，目标地理位置L在位置类型为居所下的隶属概率即为：
Figure PCTCN2017087721-appb-000007
目标地理位置L在位置类型为工作地下的隶属概率即为：
Figure PCTCN2017087721-appb-000008
目标地理位置L在位置类型为休闲区域下的隶属概率即为：
Figure PCTCN2017087721-appb-000009
此时，可在P(L为居所）、P(L为工作地）和P(L为休闲区域）中，选择概率较大的位置类型作为目标地理位置的位置类型。而若三者的概率大小相近，则可提示用户进行人工标注。
而在所述目标地理位置对应的上传时间的数量小于阈值时，由于样本较少，则上述统计方法可靠性不足，因此可通过在所述目标地理位置在各个预设的位置类型下的隶属度与各自位置类型下的概率总和的比值，根据所述比值识别所述目标地理位置的位置类型。
具体的，目标地理位置L在位置类型为居所下的隶属度与位置类型为居所下的概率总和的比值为：
Figure PCTCN2017087721-appb-000010
其中，m为所有时间区间的个数，i为所有预设时间区间的序号，ti为时间区间，如表2中，即为“居住地概率”所在列的概率值的总和。
目标地理位置L在位置类型为工作地下的隶属度与位置类型为工作地下的概率总和的比值为：
Figure PCTCN2017087721-appb-000011
目标地理位置L在位置类型为休闲区域下的隶属度与位置类型为休闲区域下的概率总和的比值为：
Figure PCTCN2017087721-appb-000012
此时，可在R(L为居所）、R(L为工作地）和R(L为休闲区域）中，选择最大的且大于阈值的比例对应的位置类型作为目标地理位置的位置类型。而若三者的比例大小相近，及最大的比例值小于阈值，则可提示用户进行人工标注。
进一步的，在根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型之后，服务器还可检测用户终端的地理位置，查找所述用户终端上传的地理位置的位置类型，选择与所述位置类型对应的数据内容向所述用户终端推送。
例如，当目标地理位置L被识别为休闲区域之后，当用户位于目标地理位置L时，若服务器检测到用户当前的位置，则可识别出用户当前处于休闲区域中，此时，即可向用户推送适合此时此地的一些导购、优惠或广告信息。这样， 服务器向用户推送的内容即可更加符合用户当前身处的环境，从而使得推送内容更加准确。
进一步的，在根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型之后，服务器还可计算在所述预设的位置类型下的地理位置的分布；获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号；根据所述位置类型下的地理位置的分布确定所述用户账号的信用评级。
例如，若目标地理位置L1为商业中心区，若被识别为某用户的居所，由于通过互联网抓取的数据分析此地房价较高，则征信系统的服务器可判断出该用户在商业中心区有房产，因此具有较高的信用评级；相应的，若有多个目标地理位置均被识别为某用户的居所，则征信系统的服务器可判断出该用户可能有多处房产，因此也可赋予该用户较高的信用评级。而若目标地理位置L1被识别为该用户的工作地，而位置偏远，周边房价较低的L2被识别为该用户的居所，则征信系统的服务器可判断出该用户仅仅为在商业中心区工作的员工，且居所的住房价值较低，因此仅赋予该用户较低的信用评级。
上述结合用户所在地理位置的类别为用户设置信用评级的方式，相当于传统技术中，主要基于银行流水及用户的过往信贷记录等数据，建立一个评分模型对用户的“信用度”赋予一个量化评分的征信系统而言，采用了用户被动的行为记录和活动记录来判别用户实际的经济实力，可防止用户在传统的征信系统中伪造数据(例如利用短时间大额资金的存入存出来制造较高的银行流水的假象)，从而可使得信用评级更加准确。
需要说明的是，上述方法可以实时处理不断获取到的地理位置数据流，当用C/C++、Java等编程语言写成单独的应用软件或大型软件系统中的专用模块后，可以运行于服务器端，将接收到的来自单个或众多用户移动客户端的、原始地理位置数据或经过处理的各级中间数据或最终结果，与服务器上的历史数据或结果，再次综合计算得到更新的结果，然后实时或非实时地输出给其他应用程序或模块使用，也可以写入服务器端数据库或文件进行存储。
上述方法还可以实现在多台服务器构成的分布式、并行计算平台上，搭载定制的、易于交互的Web界面或其他各类UI界面，形成供个人、群体或企业使 用的“地理位置数据挖掘平台”。使用者可以将已有的数据包批量上传给此“地理位置数据挖掘平台”以获得类别判定结果，也可以将实时的数据流传输给此“地理位置数据挖掘平台”来实时计算和刷新类别识别结果。
本申请实施例还提出了一种高准确度的识别用户所在地理位置的类别的装置，如图4所示，上述识别用户所在地理位置的类别的装置包括地理位置采集模块102、映射关系获取模块104、隶属度计算模块106以及类型识别模块108，其中：
地理位置采集模块102，用于接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间；
映射关系获取模块104，用于获取预设的时间-位置类型映射关系，所述时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值；
隶属度计算模块106，用于遍历所述预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属度；
类型识别模块108，用于根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型。
可选的，在一个实施例中，所述地理位置采集模块102还用于接收用户终端在即时通信应用或社交网络应用中传输数据时上传的至少一个地理位置，将所述至少一个地理位置聚类得到目标地理位置，所述目标地理位置的上传时间为所述至少一个地理位置各自的上传时间。
可选的，在一个实施例中，所述映射关系获取模块104还用于获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号的账号类型；获取预设的与所述账号类型对应的时间-位置类型映射关系。
可选的，在一个实施例中，所述映射关系获取模块104还用于获取所述上传时间对应的预设的时间段，获取预设的与所述上传时间对应的时间段对应的时间-位置类型映射关系。
可选的，在一个实施例中，所述预设的时间-位置类型映射关系中：同一时间区间对应的在各个预设的位置类型下的概率值之和为1；同一位置类型在各个时间区间对应的概率值之和不为1。
可选的，在一个实施例中，所述类型识别模块108还用于在所述目标地理位置对应的上传时间的数量大于或等于阈值时，计算所述目标地理位置在各个预设的位置类型下的隶属度之和，计算所述目标地理位置在各个预设的位置类型下的隶属度与所述隶属度之和的比值，得到目标地理位置在各个预设的位置类型下的隶属概率，根据所述目标地理位置在各个预设的位置类型下的隶属概率识别所述目标地理位置的位置类型。
可选的，在一个实施例中，所述类型识别模块108还用于在所述目标地理位置对应的上传时间的数量小于阈值时，在所述目标地理位置在各个预设的位置类型下的隶属度与各自位置类型下的概率总和的比值，根据所述比值识别所述目标地理位置的位置类型。
可选的，在一个实施例中，如图4所示，上述装置还包括内容推送模块110，用于检测用户终端的地理位置，查找所述用户终端上传的地理位置的位置类型，选择与所述位置类型对应的数据内容向所述用户终端推送。
可选的，在一个实施例中，如图4所示，上述装置还包括信用评价模块112，用于计算在所述预设的位置类型下的地理位置的分布；获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号；根据所述位置类型下的地理位置的分布确定所述用户账号的信用评级。
实施本申请实施例，将具有如下有益效果：
在上述识别用户所在地理位置的类别的方法及装置中，由于用户日常活动的规律性，用户在某个时间区间位于特定位置类别的地点的概率也具有一定的规律。因此，服务器上预设有时间-位置类型映射关系，且时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值。服务器可根据目标地理位置的上传时间，在上述映射关系中查找目标地理位置在各个位置类型下的概率值之和构成的隶属度，从而使得服务器可根据该隶属度识别出用户所在的地理位置的类别。以此种方式识别用户所在地理位置的类别， 采用的依据为用户在使用即时通信应用或社交网络应用时被动产生的活动记录，因此不存在伪造的成分，且识别方式基于用户日常生活的客观规律，因此，识别的准确度较高。
在一个实施例中，如图5所示，图5展示了一种运行上述识别用户所在地理位置的类别的方法的基于冯诺依曼体系的计算机系统的终端10。该计算机系统可以是智能手机、平板电脑、掌上电脑，笔记本电脑或个人电脑等终端设备。具体的，可包括通过系统总线连接的外部输入接口1001、处理器1002、存储器1003和输出接口1004。其中，外部输入接口1001可选的可至少包括网络接口10012。存储器1003可包括外存储器10032(例如硬盘、光盘或软盘等)和内存储器10034。输出接口1004可至少包括显示屏10042等设备。
在本实施例中，本方法的运行基于计算机程序，该计算机程序的程序文件存储于前述基于冯诺依曼体系的计算机系统10的外存储器10032中，在运行时被加载到内存储器10034中，然后被编译为机器码之后传递至处理器1002中执行，从而使得基于冯诺依曼体系的计算机系统10中形成逻辑上的地理位置采集模块102、映射关系获取模块104、隶属度计算模块106以及类型识别模块108。且在上述识别用户所在地理位置的类别的方法执行过程中，输入的参数均通过外部输入接口1001接收，并传递至存储器1003中缓存，然后输入到处理器1002中进行处理，处理的结果数据或缓存于存储器1003中进行后续地处理，或被传递至输出接口1004进行输出。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (18)

  1. 一种识别用户所在地理位置的类别的方法，其特征在于，包括：
    接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间；
    获取预设的时间-位置类型映射关系，所述时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值；
    遍历所述预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属度；
    根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型。
  2. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置还包括：
    接收用户终端在即时通信应用或社交网络应用中传输数据时上传的至少一个地理位置，将所述至少一个地理位置聚类得到目标地理位置，所述目标地理位置的上传时间为所述至少一个地理位置各自的上传时间。
  3. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述获取预设的时间-位置类型映射关系还包括：
    获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号的账号类型；
    获取预设的与所述账号类型对应的时间-位置类型映射关系。
  4. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述获取预设的时间-位置类型映射关系还包括：
    获取所述上传时间对应的预设的时间段，获取预设的与所述上传时间对应的时间段对应的时间-位置类型映射关系。
  5. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述预设的时间-位置类型映射关系中：
    同一时间区间对应的在各个预设的位置类型下的概率值之和为1；
    同一位置类型在各个时间区间对应的概率值之和不为1。
  6. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型包括：
    在所述目标地理位置对应的上传时间的数量大于或等于阈值时，计算所述目标地理位置在各个预设的位置类型下的隶属度之和，计算所述目标地理位置在各个预设的位置类型下的隶属度与所述隶属度之和的比值，得到目标地理位置在各个预设的位置类型下的隶属概率，根据所述目标地理位置在各个预设的位置类型下的隶属概率识别所述目标地理位置的位置类型。
  7. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型包括：
    在所述目标地理位置对应的上传时间的数量小于阈值时，在所述目标地理位置在各个预设的位置类型下的隶属度与各自位置类型下的概率总和的比值，根据所述比值识别所述目标地理位置的位置类型。
  8. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型之后还包括：
    检测用户终端的地理位置，查找所述用户终端上传的地理位置的位置类型，选择与所述位置类型对应的数据内容向所述用户终端推送。
  9. 根据权利要求1所述的识别用户所在地理位置的类别的方法，其特征在于，所述根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型之后还包括：
    计算在所述预设的位置类型下的地理位置的分布；
    获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号；
    根据所述位置类型下的地理位置的分布确定所述用户账号的信用评级。
  10. 一种识别用户所在地理位置的类别的装置，其特征在于，包括：处理器和存储器，所述存储器中存储有可被所述处理器执行的指令模块，所述指令模块包括：
    地理位置采集模块，用于接收用户终端在即时通信应用或社交网络应用中传输数据时上传的目标地理位置以及相应的上传时间，且一个目标地理位置对应至少一个上传时间；
    映射关系获取模块，用于获取预设的时间-位置类型映射关系，所述时间-位置类型映射关系中定义了与预设的时间区间对应的在各个预设的位置类型下的概率值；
    隶属度计算模块，用于遍历所述预设的位置类型，计算目标地理位置的上传时间在遍历到的位置类型下对应的概率值之和，得到目标地理位置在各个预设的位置类型下的隶属度；
    类型识别模块，用于根据目标地理位置在各个预设的位置类型下的隶属度识别所述目标地理位置的位置类型。
  11. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述地理位置采集模块还用于接收用户终端在即时通信应用或社交网络应用中传输数据时上传的至少一个地理位置，将所述至少一个地理位置聚类得到目标地理位置，所述目标地理位置的上传时间为所述至少一个地理位置各自的上传时间。
  12. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述映射关系获取模块还用于获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号的账号类型；获取预设的与所述账号类型对应的时间-位置类型映射关系。
  13. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述映射关系获取模块还用于获取所述上传时间对应的预设的时间段，获取预设的与所述上传时间对应的时间段对应的时间-位置类型映射关系。
  14. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述预设的时间-位置类型映射关系中：
    同一时间区间对应的在各个预设的位置类型下的概率值之和为1；
    同一位置类型在各个时间区间对应的概率值之和不为1。
  15. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述类型识别模块还用于在所述目标地理位置对应的上传时间的数量大于或等于阈值时，计算所述目标地理位置在各个预设的位置类型下的隶属度之和，计算所述目标地理位置在各个预设的位置类型下的隶属度与所述隶属度之和的比值，得到目标地理位置在各个预设的位置类型下的隶属概率，根据所述目标地理位置在各个预设的位置类型下的隶属概率识别所述目标地理位置的位置类型。
  16. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述类型识别模块还用于在所述目标地理位置对应的上传时间的数量小于阈值时，在所述目标地理位置在各个预设的位置类型下的隶属度与各自位置类型下的概率总和的比值，根据所述比值识别所述目标地理位置的位置类型。
  17. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述装置还包括内容推送模块，用于检测用户终端的地理位置，查找所述用户终端上传的地理位置的位置类型，选择与所述位置类型对应的数据内容向所述用户终端推送。
  18. 根据权利要求10所述的识别用户所在地理位置的类别的装置，其特征在于，所述装置还包括信用评价模块，用于计算在所述预设的位置类型下的地理位置的分布；获取所述用户终端上在所述即时通信应用或社交网络应用上登录的用户账号；根据所述位置类型下的地理位置的分布确定所述用户账号的信用评级。
PCT/CN2017/087721 2016-06-12 2017-06-09 识别用户所在地理位置的类别的方法及装置 WO2017215523A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020187022746A KR102121361B1 (ko) 2016-06-12 2017-06-09 사용자가 위치되는 지리적 위치의 유형을 식별하기 위한 방법 및 디바이스
JP2018542148A JP6689515B2 (ja) 2016-06-12 2017-06-09 ユーザ地理的ロケーションのタイプを識別するための方法および装置
EP17812634.8A EP3471374B1 (en) 2016-06-12 2017-06-09 Method and device for identifying type of geographic location at where user is located
US15/981,978 US11252534B2 (en) 2016-06-12 2018-05-17 Method and apparatus for identifying types of user geographical locations

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610410598.0A CN106101224B (zh) 2016-06-12 2016-06-12 识别用户所在地理位置的类别的方法及装置
CN201610410598.0 2016-06-12

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/981,978 Continuation US11252534B2 (en) 2016-06-12 2018-05-17 Method and apparatus for identifying types of user geographical locations

Publications (1)

Publication Number Publication Date
WO2017215523A1 true WO2017215523A1 (zh) 2017-12-21

Family

ID=57845145

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/087721 WO2017215523A1 (zh) 2016-06-12 2017-06-09 识别用户所在地理位置的类别的方法及装置

Country Status (6)

Country Link
US (1) US11252534B2 (zh)
EP (1) EP3471374B1 (zh)
JP (1) JP6689515B2 (zh)
KR (1) KR102121361B1 (zh)
CN (1) CN106101224B (zh)
WO (1) WO2017215523A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111105261A (zh) * 2018-10-29 2020-05-05 北京奇虎科技有限公司 一种用户识别方法、装置、电子设备和存储介质
CN112883815A (zh) * 2021-01-26 2021-06-01 首都师范大学 一种农机具自动监管方法、系统及服务器

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106101224B (zh) 2016-06-12 2018-07-17 腾讯科技（深圳）有限公司 识别用户所在地理位置的类别的方法及装置
CN107103037B (zh) * 2017-03-22 2020-06-26 华为机器有限公司 一种地理区域的社会功能的识别方法与终端设备
CN108897757B (zh) * 2018-05-14 2023-08-22 平安科技（深圳）有限公司 一种照片存储方法、存储介质和服务器
CN109086323A (zh) * 2018-06-28 2018-12-25 上海中通吉网络技术有限公司 用户家庭和工作地址的确定方法和系统
CN109672715A (zh) * 2018-09-13 2019-04-23 深圳壹账通智能科技有限公司 用户常驻地判断方法、装置、设备及计算机可读存储介质
CN111126120B (zh) * 2018-11-01 2024-02-23 百度在线网络技术（北京）有限公司 城市区域分类方法、装置、设备和介质
CN111222056B (zh) * 2018-11-26 2023-07-25 中国移动通信集团重庆有限公司 相关用户的匹配方法、装置、设备和介质
CN109889370B (zh) * 2019-01-10 2021-12-21 中国移动通信集团海南有限公司 一种网络设备位置确定方法、装置及计算机可读存储介质
CN110730207B (zh) * 2019-09-06 2022-03-29 平安科技（深圳）有限公司 基于位置服务的位置识别方法、装置、设备及存储介质
CN110717006B (zh) * 2019-10-12 2022-09-20 广东小天才科技有限公司 用户学校位置的分析方法、系统、存储介质及电子设备
CN112560910B (zh) * 2020-12-02 2024-03-01 中国联合网络通信集团有限公司 用户分类方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070270160A1 (en) * 2006-05-19 2007-11-22 Karl Georg Hampel Traffic-synchronized location measurement
CN103248723A (zh) * 2013-04-10 2013-08-14 腾讯科技（深圳）有限公司 一种ip地址所在区域的确定方法及装置
CN103729387A (zh) * 2012-10-16 2014-04-16 北京糯米网科技发展有限公司 数据推送方法及装置
CN104796858A (zh) * 2015-03-23 2015-07-22 电子科技大学 一种位置服务中基于假位置和几何学的位置隐私保护方法
CN106101224A (zh) * 2016-06-12 2016-11-09 腾讯科技（深圳）有限公司 识别用户所在地理位置的类别的方法及装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9525653B2 (en) 2006-05-22 2016-12-20 Bank Of America Corporation Enhanced wireless short message service
US10163113B2 (en) * 2008-05-27 2018-12-25 Qualcomm Incorporated Methods and apparatus for generating user profile based on periodic location fixes
JP5665767B2 (ja) * 2009-12-09 2015-02-04 泰 四尾 情報配信装置、情報配信システム、情報配信方法、及びプログラム
US20110167073A1 (en) * 2010-01-04 2011-07-07 Rosenberg Erel system and method for in-depth analysis of location and time based patterns in cellular networks
JP5433472B2 (ja) * 2010-03-23 2014-03-05 日本電信電話株式会社 行動予測装置、方法及びプログラム
US8521128B1 (en) * 2011-12-09 2013-08-27 Google Inc. Method, system, and computer program product for obtaining crowd-sourced location information
CN103312755A (zh) * 2012-03-14 2013-09-18 腾讯科技（深圳）有限公司 基于地理位置的内容分享方法及装置
US20140222570A1 (en) 2012-11-17 2014-08-07 Teoco Corporation System, Method, and Computer Program Product For Probabilistically Derived Predictive Location Based Targeted Promotion
CN103905978B (zh) * 2012-12-27 2018-03-23 中国电信股份有限公司 基于位置的信息推送方法、推送装置和网络
US9094795B2 (en) * 2013-02-06 2015-07-28 Facebook, Inc. Routine estimation
CN103227821B (zh) * 2013-04-03 2015-07-01 腾讯科技（深圳）有限公司 一种目标用户位置数据的处理方法及装置
JP6175346B2 (ja) 2013-10-21 2017-08-02 株式会社Ｎｔｔドコモ 滞留目的推定装置および滞留目的推定方法
US9443326B2 (en) * 2013-12-10 2016-09-13 Microsoft Technology Licensing, Llc Semantic place labels
CN103942853B (zh) * 2014-05-04 2016-02-03 青岛中瑞汽车服务有限公司 基于lbs数据库的汽车信息采集装置和风险分析方法
EP3335209B1 (en) * 2015-08-11 2019-05-08 Telecom Italia S.p.A. Method and system for computing an o-d matrix obtained through radio mobile network data
CN105357638B (zh) * 2015-11-06 2019-10-22 百度在线网络技术（北京）有限公司 预测预定时刻的用户位置的方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070270160A1 (en) * 2006-05-19 2007-11-22 Karl Georg Hampel Traffic-synchronized location measurement
CN103729387A (zh) * 2012-10-16 2014-04-16 北京糯米网科技发展有限公司 数据推送方法及装置
CN103248723A (zh) * 2013-04-10 2013-08-14 腾讯科技（深圳）有限公司 一种ip地址所在区域的确定方法及装置
CN104796858A (zh) * 2015-03-23 2015-07-22 电子科技大学 一种位置服务中基于假位置和几何学的位置隐私保护方法
CN106101224A (zh) * 2016-06-12 2016-11-09 腾讯科技（深圳）有限公司 识别用户所在地理位置的类别的方法及装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111105261A (zh) * 2018-10-29 2020-05-05 北京奇虎科技有限公司 一种用户识别方法、装置、电子设备和存储介质
CN111105261B (zh) * 2018-10-29 2024-04-19 北京奇虎科技有限公司 一种用户识别方法、装置、电子设备和存储介质
CN112883815A (zh) * 2021-01-26 2021-06-01 首都师范大学 一种农机具自动监管方法、系统及服务器
CN112883815B (zh) * 2021-01-26 2022-11-29 首都师范大学 一种农机具自动监管方法、系统及服务器

Also Published As

Publication number Publication date
KR20180101472A (ko) 2018-09-12
EP3471374A4 (en) 2019-06-12
US20180270616A1 (en) 2018-09-20
JP6689515B2 (ja) 2020-04-28
CN106101224B (zh) 2018-07-17
CN106101224A (zh) 2016-11-09
US11252534B2 (en) 2022-02-15
KR102121361B1 (ko) 2020-06-10
EP3471374A1 (en) 2019-04-17
EP3471374B1 (en) 2020-07-22
JP2019512764A (ja) 2019-05-16

Similar Documents

Publication Publication Date Title
WO2017215523A1 (zh) 识别用户所在地理位置的类别的方法及装置
JP6784308B2 (ja) 施設特性を更新するプログラム、施設をプロファイリングするプログラム、コンピュータ・システム、及び施設特性を更新する方法
CN110956547B (zh) 一种基于搜索引擎的实时识别欺诈团伙的方法及系统
CN105677793B (zh) 地点数据库的建立和候选乘车地点的推荐方法及装置
CN109074358B (zh) 提供与用户兴趣有关的地理位置
US9450993B2 (en) Creating groups of users in a social networking system
US11122009B2 (en) Systems and methods for identifying geographic locations of social media content collected over social networks
WO2016206196A1 (zh) 用于获取用户属性信息的方法、装置及服务器
US20130304818A1 (en) Systems and methods for discovery of related terms for social media content collection over social networks
TWI703862B (zh) 內容推薦方法及裝置
US10108748B2 (en) Most relevant application recommendation based on crowd-sourced application usage data
CN112861972B (zh) 一种展业区域的选址方法、装置、计算机设备和介质
US9594810B2 (en) Methods and systems for transforming multiple data streams into social scoring and intelligence on individuals and groups
US9635507B2 (en) Mobile device analytics
CN111861296A (zh) 一种揽件任务分配方法、装置、揽件系统、设备及介质
CN111222960A (zh) 基于公共流量带的房源推荐方法及系统
CN103970891A (zh) 一种基于情境的用户兴趣信息查询方法
CN109685573A (zh) 一种商圈数据的处理方法、装置、电子设备和存储介质
WO2021114615A1 (zh) 行为风险识别的可视化方法、装置、设备及存储介质
US11061975B2 (en) Cognitive content suggestive sharing and display decay
US10157391B2 (en) Distributed telecommunication network architecture and database query for audience segmentation and analysis
US20170169454A1 (en) Identifying business online social presence with name and address using spatial filters
US20160073228A1 (en) System and method for generating expected geolocations of mobile computing devices
Gayo-Avello Political opinion
US11843669B2 (en) Posting location ordinariness/extraordinariness determination system

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 20187022746

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1020187022746

Country of ref document: KR

ENP Entry into the national phase

Ref document number: 2018542148

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 17812634

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017812634

Country of ref document: EP

Effective date: 20190114