WO2015062409A1 - 移动用户位置预测方法及设备 - Google Patents

移动用户位置预测方法及设备 Download PDF

Info

Publication number
WO2015062409A1
WO2015062409A1 PCT/CN2014/088464 CN2014088464W WO2015062409A1 WO 2015062409 A1 WO2015062409 A1 WO 2015062409A1 CN 2014088464 W CN2014088464 W CN 2014088464W WO 2015062409 A1 WO2015062409 A1 WO 2015062409A1
Authority
WO
WIPO (PCT)
Prior art keywords
activity
mobile user
probability
behavior
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2014/088464
Other languages
English (en)
French (fr)
Inventor
丁强
余辰
李莉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to EP14856995.7A priority Critical patent/EP3048820B1/en
Priority to KR1020167012508A priority patent/KR101787929B1/ko
Priority to JP2016526824A priority patent/JP6277569B2/ja
Publication of WO2015062409A1 publication Critical patent/WO2015062409A1/zh
Priority to US15/139,556 priority patent/US9906913B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/029Location-based management or tracking services
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00Computing arrangements based on specific mathematical models
    • G06N7/01Probabilistic graphical models, e.g. probabilistic networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/52Network services specially adapted for the location of the user terminal
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/535Tracking the activity of the user
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W64/00Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • the embodiments of the present invention relate to communication technologies, and in particular, to a mobile user location prediction method and device.
  • contextual intelligence applications With the rapid development of geographic information systems, mobile positioning technologies, wireless communication networks, intelligent terminal technologies, and sensor technologies, contextual intelligence applications are also rapidly developing. In scenario intelligence applications, how to predict the geographic location of mobile users is important for the opening of contextual intelligence applications.
  • Embodiments of the present invention provide a mobile user location prediction method and device to improve the accuracy of a target geographic location of a mobile user.
  • the present invention provides a mobile user location prediction method, including:
  • the historical activity migration rule includes: the mobile user determined by the historical behavior activity of the mobile user is converted from the current behavior activity to the The probability of occurrence of the target behavioral activity and the weighting factor of the historical behavioral activity;
  • the public activity migration rule includes a probability that the mobile user is converted from a current behavioral activity to the target behavioral activity and a weighting factor of the public behavioral activity determined by historical behavioral activities of other mobile users.
  • the probability of occurrence of the current behavior of the mobile user, the historical activity migration of the mobile user Regularity and the law of public activity migration determining the probability of occurrence of the target behavior of the mobile user, including:
  • Determining an occurrence probability of the target user's target behavior activity according to an occurrence probability of the target behavior activity corresponding to the historical behavior activity and an occurrence probability of the target behavior activity corresponding to the public behavior activity.
  • the predicting the target geographic location of the mobile user according to the determined target behavior activity of the mobile user includes:
  • the target behavior activity of the mobile user exists in a historical behavior activity record of the mobile user, the historical behavior activity record including a historical geographic location corresponding to the target behavior activity;
  • the geographic location predicts the target geographic location of the mobile user.
  • the determining a probability of occurrence of a current behavior of a mobile user includes:
  • sensing data corresponding to the mobile user determining a motion state of the mobile user according to the sensing data, and determining an occurrence probability of the current behavior of the mobile user according to the motion state of the mobile user;
  • the current time, each of the interest points, and a probability of occurrence of a current behavior activity have a corresponding relationship
  • Determining, according to the current time and the distribution of the interest points, the probability of occurrence of the current behavior of the mobile user including:
  • the present invention provides a user equipment, including:
  • a first probability determining module configured to determine a probability of occurrence of a current behavior of the mobile user
  • a second probability determining module configured to determine an occurrence probability of the target user behavior of the mobile user according to an occurrence probability of the current behavior of the mobile user, a historical activity migration rule of the mobile user, and a public activity migration rule;
  • a behavior activity determining module configured to determine a target behavior activity of the mobile user according to an occurrence probability of the target behavior activity of the mobile user
  • a prediction module configured to perform according to the determined target behavior of the mobile user The target geographic location of the mobile user is measured.
  • the historical activity migration rule includes: the mobile user determined by the historical behavior activity of the mobile user is converted from the current behavior activity to the The probability of occurrence of the target behavioral activity and the weighting factor of the historical behavioral activity;
  • the public activity migration rule includes a probability that the mobile user is converted from a current behavioral activity to the target behavioral activity and a weighting factor of the public behavioral activity determined by historical behavioral activities of other mobile users.
  • the second probability determining module is specifically configured to:
  • Determining an occurrence probability of the target user's target behavior activity according to an occurrence probability of the target behavior activity corresponding to the historical behavior activity and an occurrence probability of the target behavior activity corresponding to the public behavior activity.
  • the predicting module is specifically configured to:
  • the target behavior activity of the mobile user exists in a historical behavior activity record of the mobile user, the historical behavior activity record including a historical geographic location corresponding to the target behavior activity;
  • the first probability determining module is specifically configured to:
  • sensing data corresponding to the mobile user determining a motion state of the mobile user according to the sensing data, and determining an occurrence probability of the current behavior of the mobile user according to the motion state of the mobile user;
  • the current time, each of the interest points, and a probability of occurrence of the current behavior activity have a corresponding relationship
  • the first probability determining module is further specifically configured to:
  • the mobile user location prediction method and device determine the occurrence probability of the current behavior of the mobile user by using the user equipment; the probability of occurrence of the current behavior of the mobile user, and the historical activity migration rule of the mobile user And determining a probability of occurrence of the target behavior of the mobile user; determining a target behavior of the mobile user according to an occurrence probability of the target behavior of the mobile user; determining the mobile user according to the determined
  • the target behavior activity predicts a target geographic location of the mobile user.
  • the invention determines the target geographical location of the mobile user through the public activity migration law without the mobile user's large historical activity migration law, and improves the accuracy of the target geographical location.
  • this embodiment can also predict the geographic location that does not appear in the historical migration rule of the mobile user, obtain the target geographic location, and improve the universal applicability of the mobile user location prediction method.
  • FIG. 1 is a schematic flowchart diagram of Embodiment 1 of a mobile user location prediction method according to the present invention
  • Embodiment 1 of a user equipment according to the present invention is a schematic structural diagram of Embodiment 1 of a user equipment according to the present invention.
  • FIG. 3 is a schematic structural diagram of Embodiment 2 of a user equipment according to the present invention.
  • FIG. 1 is a schematic flowchart diagram of Embodiment 1 of a method for predicting a location of a mobile user according to the present invention.
  • the mobile user location prediction method provided by this embodiment may be implemented by a user equipment, and the user equipment may be implemented by software and/or hardware. As shown in FIG. 1, the mobile user location prediction method provided by this embodiment includes:
  • Step 101 Determine an occurrence probability of a current behavior of the mobile user.
  • Step 102 Determine an occurrence probability of the target behavior of the mobile user according to an occurrence probability of the current behavior of the mobile user, a historical activity migration rule of the mobile user, and a public activity migration rule.
  • Step 103 Determine, according to an occurrence probability of the target behavior activity of the mobile user, a target behavior activity of the mobile user.
  • Step 104 Predict the target geographic location of the mobile user according to the determined target behavior activity of the mobile user.
  • the user equipment determines a target geographic location of the mobile user, where the target geographic location refers to a destination that may be needed in the next step when the mobile user is located in the current geographic location. ground. For example, if it is determined that the target geographic location of the mobile user is a frequent shopping mall, the merchant discount and promotion information can be pushed to the mobile user in advance, which not only saves the user's time but also improves the user experience. Alternatively, it is known that the target geographical location of the mobile user is home, and the mobile user is reminded to purchase the flour on the way home from work, and the remote control turns on the air conditioner at home, and simultaneously transmits the traffic congestion status of each road section to the user equipment.
  • the embodiment details how to determine the target geographic location of the mobile user.
  • the user equipment first determines the probability of occurrence of the current behavioral activity of the mobile user. Specifically, it can be implemented by the following possible implementation manners.
  • obtaining a current geographic location and a current time of the mobile user and determining, according to the current geographic location, a distribution of interest points of the mobile user in the second preset geographic location range, according to the current time And the distribution of interest points, determining a probability of occurrence of the current behavioral activity of the mobile user.
  • the behavioral activities of the mobile user in daily life include eating, working, shopping, etc., assuming that there are M kinds, M is a natural number, and each behavior activity corresponds to a point of interest (POI), and the interest point may be specifically For restaurants, shopping malls, office buildings, etc., assume that there are N kinds, N is a natural number.
  • POI point of interest
  • the current time, each point of interest, and the occurrence probability of the current behavioral activity have a corresponding relationship.
  • the correspondence relationship may be represented by a condition occurrence probability p(Act i
  • the occurrence probability of the current behavior of the mobile user may be an experience value given by the expert, or may be statistically obtained according to the collected historical activity records of the plurality of mobile users.
  • the mobile user's current behavioral activity is the probability of occurrence of eating, the probability of occurrence is 0.9, and the probability of occurrence of the work is 0.9.
  • the probability of occurrence is 0.05.
  • the ratio of the points of interest is determined according to the distribution of the points of interest; according to the ratio of the points of interest, and to each Determining a probability of occurrence of the current behavior activity corresponding to the point of interest, and determining an occurrence probability of the current behavior of the mobile user at the current time.
  • all the points of interest in the second preset geographic location range are obtained according to the coordinate search of the current geographic location of the mobile user, and the probability of occurrence of the same current behavioral activity is summed with respect to all the points of interest, and the current geographic location is obtained.
  • the probability of occurrence of behavioral activities That is, the formula one is shown.
  • Acti represents the probability of occurrence of the current behavior of the mobile user
  • POIk represents the point of interest
  • T represents the current time
  • Loc represents the current geographic location
  • N is the number of points of interest.
  • Another possible implementation manner acquiring sensing data corresponding to the mobile user, determining a motion state of the mobile user according to the sensing data, and determining, according to the motion state of the mobile user, the mobile user The probability of occurrence of current behavioral activities.
  • a motion sensor such as an acceleration sensor or a gyroscope
  • a light sensor such as an acceleration sensor or a gyroscope
  • a global positioning system Global Position System, Referred to as GPS
  • the motion state of the mobile user is determined by means of probability inference, rule inference, etc., and the probability of occurrence of the current behavior of the mobile user is determined according to the motion state of the mobile user.
  • the motion state has a corresponding relationship with the occurrence probability of the current behavior of the mobile user, and the probability of occurrence of the current behavior activity can be determined according to the correspondence relationship.
  • Yet another possible implementation manner is to obtain a background sound of the current geographic location of the mobile user, and determine, according to the background sound, an occurrence probability of the current behavior of the mobile user.
  • the background sound of the mobile user is collected by using the microphone of the mobile device, and the background sound data is preprocessed and the characteristics of Mel Frequency Cepstrum Coefficient (MFCC), zero-crossing rate, short-time energy, etc. are extracted. Identifying special sounds or performing scene analysis, so the mobile user's activity can be estimated according to the background sound. If there is a tableware impact sound in the background sound, the current behavior of the mobile user is judged as eating, and if there are many people discussing the sound at the same time, the movement is judged. The user's current behavior is a meeting.
  • the background sound has a corresponding relationship with the occurrence probability of the current behavior of the mobile user, and the occurrence probability of the current behavior activity can be determined according to the correspondence relationship.
  • an occurrence probability of the target behavior activity of the mobile user is determined according to an occurrence probability of the current behavior of the mobile user, a historical activity migration rule of the mobile user, and a public activity migration rule.
  • the historical activity migration rule includes: a probability that the mobile user is converted from the current behavior activity to the target behavior activity and a weight factor of the historical behavior activity determined by the historical behavior activity of the mobile user;
  • the public activity migration rule includes a probability that the mobile user is converted from a current behavioral activity to the target behavioral activity and a weighting factor of the public behavioral activity determined by historical behavioral activities of other mobile users.
  • the probability of occurrence of the transition of the mobile user from the current behavior activity to the target behavior activity p common (Act i
  • the law of public activity migration can be the experience value given by the expert, or it can be statistically obtained based on the historical activity records of multiple mobile users collected.
  • the historical activity migration law can be obtained from a variety of ways, such as the development of a software that allows mobile users to actively cooperate with the labeling of current behavioral activities to collect data, or through third-party location-based services that mobile users have used (Location Based Service). , referred to as LBS), the sign-in service is obtained, or is extracted from the electronic diary recorded by the mobile user and the schedule in the calendar.
  • LBS Location Based Service
  • the probability of occurrence of the target behavioral activity corresponding to the historical behavioral activity can be realized by the following formula:
  • ⁇ (t) represents the weighting factor of the historical behavioral activity
  • p personal (Act next act
  • M representing the behavioral activity Number
  • M is a natural number.
  • step 101 when the current behavioral activity is determined to be eating, the probability of occurrence is 0.305, when the current behavioral activity is working, the probability of occurrence is 0.5, and the current behavioral activity is shopping, and the probability of occurrence is 0.195.
  • the migration behavior of historical behavioral activities is also shown in Table 2.
  • the occurrence probability of the target behavior activity corresponding to the public behavior activity can be specifically realized by the following formula:
  • (1- ⁇ (t)) represents the weighting factor of the public behavioral activity
  • p common (Act next act
  • M representing the number of behavioral activities, and M being a natural number.
  • the implementation manner of determining the probability of occurrence of the target behavior activity corresponding to the public behavior activity may participate in determining the probability of occurrence of the target behavior activity corresponding to the historical behavior activity, and details are not described herein again.
  • ⁇ (t) is a weighting factor
  • ⁇ (t) is increasing with time, because the collected user activity law information is increasing with time, and the individual activity law Will gradually dominate the forecast.
  • the probability of occurrence of the target behavior activity of the mobile user is determined according to an occurrence probability of the target behavior activity corresponding to the historical behavior activity and an occurrence probability of the target behavior activity corresponding to the public behavior activity.
  • the probability of occurrence of the target behavior activity corresponding to the historical behavior activity and the probability of occurrence of the target behavior activity corresponding to the public behavior activity are summed for the conversion from the same current behavior activity to the same target behavior activity, and the movement is obtained.
  • the probability of occurrence of the user's target behavioral activity P (Act next act).
  • step 103 the target behavior activity of the mobile user is determined according to the probability of occurrence of the target behavior of the mobile user.
  • the target behavioral activity with the highest probability of occurrence of the target behavioral activity is selected.
  • Step 104 Predict a target geographic location of the mobile user according to the target behavior activity of the mobile user.
  • determining whether the target behavior activity of the mobile user exists in a historical behavior activity record with the mobile user where the historical behavior activity record includes a historical geographic location corresponding to the target behavior activity;
  • the historical behavior activity record includes historical geographic locations that the mobile user has previously visited.
  • the target behavior activity exists in the historical behavior activity record, the target user's target geographic location is predicted according to the historical geographic location that the mobile user has previously visited.
  • Num personal (Act next , loc i ) represents the number of times the activity Act next occurred at the location loc i in the historical behavior activity record.
  • the representative selects the loci that takes Num personal (Act next , loc i ) to the maximum value.
  • the target geographic location may be the geographical location corresponding to the target behavior activity within the first preset geographic location, and the target geographic location is the probability and target of the locx The distance dist(.) between the geographic location locx and the current geographic location, and the number of times other mobile users are engaged in the target behavioral activity Act next at the target geographic location locx.
  • ⁇ (.) decreases as dist(Loc next ,loc x ) increases, and increases with Num common (Act next ,loc x ), dist(Loc next ,loc x ) denotes locx and current position
  • the distance between Num common (Act next , loc x ) indicates the number of times other mobile users are engaged in the target behavior activity Act next at locx. Representative selected so that ⁇ (dist (Loc next, loc x), Num common (Act next, loc x) locx takes the maximum value.
  • ⁇ (.) is not limited and can be
  • Rank near (.) indicates the ranking of the distance between locx and the current position from low to high
  • Rank freq indicates the ranking of the number of times other mobile users engage in the target behavior Activity Act next in locx
  • ⁇ ⁇ (0,1) is a weighting factor
  • the target geographic location with the highest probability is selected as the target geographic location of the mobile user.
  • the present invention determines the occurrence probability of the current behavior of the mobile user by using the user equipment; determining the mobile user according to the probability of occurrence of the current behavior of the mobile user, the historical activity migration rule of the mobile user, and the migration rule of the public activity. a probability of occurrence of the target behavioral activity; determining a target behavioral activity of the mobile user according to the probability of occurrence of the target behavioral activity of the mobile user; predicting the mobile subscriber's based on the determined target behavioral activity of the mobile subscriber Target location.
  • the invention determines the target geographical location of the mobile user through the public activity migration law without the mobile user's large historical activity migration law, and improves the accuracy of the target geographical location. At the same time, through the law of public activity migration, this embodiment can also predict the geographic location that does not appear in the historical migration rule of the mobile user, obtain the target geographic location, and improve the universal applicability of the mobile user location prediction method.
  • FIG. 2 is a schematic structural diagram of Embodiment 1 of a user equipment according to the present invention.
  • the user equipment 20 provided by the embodiment of the present invention includes: a first probability determining module 201, a second probability determining module 202, a behavior activity determining module 203, and a predicting module 204.
  • the first probability determining module 201 is configured to determine an occurrence probability of a current behavior of the mobile user.
  • the second probability determining module 202 is configured to determine an occurrence probability of the target user behavior of the mobile user according to an occurrence probability of the current behavior of the mobile user, a historical activity migration rule of the mobile user, and a public activity migration rule.
  • the behavior activity determining module 203 is configured to determine a target behavior activity of the mobile user according to an occurrence probability of the target behavior activity of the mobile user;
  • the prediction module 204 is configured to predict a target geographic location of the mobile user according to the determined target behavior activity of the mobile user.
  • the user equipment provided in this embodiment may be used to implement the technical solution of the mobile user location prediction method provided by any embodiment of the present invention.
  • the implementation principle and technical effects are similar, and details are not described herein again.
  • the historical activity migration rule includes: a probability that the mobile user is converted from the current behavior activity to the target behavior activity and a weighting factor of the historical behavior activity determined by the historical behavior activity of the mobile user ;
  • the public activity migration rule includes a probability that the mobile user is converted from a current behavioral activity to the target behavioral activity and a weighting factor of the public behavioral activity determined by historical behavioral activities of other mobile users.
  • the second probability determining module 202 is specifically configured to:
  • the probability of occurrence of the target behavioral activity corresponding to the historical behavioral activity and the public determines the probability of occurrence of the target behavior activity of the mobile user.
  • the prediction module 204 is specifically configured to:
  • the target behavior activity of the mobile user exists in a historical behavior activity record of the mobile user, the historical behavior activity record including a historical geographic location corresponding to the target behavior activity;
  • the first probability determining module 201 is specifically configured to:
  • sensing data corresponding to the mobile user determining a motion state of the mobile user according to the sensing data, and determining an occurrence probability of the current behavior of the mobile user according to the motion state of the mobile user;
  • the current time, each of the points of interest, and the occurrence probability of the current behavioral activity have a corresponding relationship
  • the first probability determining module 201 is further specifically configured to:
  • the user equipment provided in this embodiment may be used to implement the technical solution of the mobile user location prediction method provided by any embodiment of the present invention.
  • the implementation principle and technical effects are similar, and details are not described herein again.
  • FIG. 3 is a schematic structural diagram of Embodiment 2 of a user equipment according to the present invention.
  • the user equipment 30 provided by the example includes a processor 301 and a memory 302.
  • the user equipment 30 may further include a transmitter and a receiver.
  • the transmitter and receiver can be coupled to the processor 301.
  • the transmitter is for transmitting data or information
  • the receiver is for receiving data or information
  • the memory 302 stores execution instructions, when the user device 30 is running
  • the processor 301 is in communication with the memory 302, and the processor 301 calls execution in the memory 302. Instruction to do the following:
  • the user equipment provided in this embodiment may be used to implement the technical solution of the mobile user location prediction method provided by any embodiment of the present invention.
  • the implementation principle and technical effects are similar, and details are not described herein again.
  • the historical activity migration rule includes: a probability that the mobile user is converted from the current behavior activity to the target behavior activity and a weighting factor of the historical behavior activity determined by the historical behavior activity of the mobile user ;
  • the public activity migration rule includes a probability that the mobile user is converted from a current behavioral activity to the target behavioral activity and a weighting factor of the public behavioral activity determined by historical behavioral activities of other mobile users.
  • determining the probability of occurrence of the target behavior of the mobile user according to the probability of occurrence of the current behavior of the mobile user, the historical activity migration rule of the mobile user, and the public activity migration rule including:
  • the probability of occurrence of the mobile user being converted from the current behavioral activity to the target behavioral activity determined by the probability of occurrence of the current behavioral activity, the historical behavioral activity of other mobile users And a weighting factor of the public behavior activity, determining an occurrence probability of the target behavior activity corresponding to the public behavior activity;
  • Determining an occurrence probability of the target user's target behavior activity according to an occurrence probability of the target behavior activity corresponding to the historical behavior activity and an occurrence probability of the target behavior activity corresponding to the public behavior activity.
  • the predicting the target geographic location of the mobile user according to the determined target behavior activity of the mobile user including:
  • the target behavior activity of the mobile user exists in a historical behavior activity record of the mobile user, the historical behavior activity record including a historical geographic location corresponding to the target behavior activity;
  • the determining the probability of occurrence of the current behavior of the mobile user includes:
  • sensing data corresponding to the mobile user determining a motion state of the mobile user according to the sensing data, and determining an occurrence probability of the current behavior of the mobile user according to the motion state of the mobile user;
  • the current time, each of the points of interest, and the occurrence probability of the current behavior activity have a corresponding relationship
  • Determining, according to the current time and the distribution of the interest points, the probability of occurrence of the current behavior of the mobile user including:
  • the user equipment provided in this embodiment may be used to implement the technical solution of the mobile user location prediction method provided by any embodiment of the present invention.
  • the implementation principle and technical effects are similar, and details are not described herein again.
  • the aforementioned program can be stored in a computer readable storage medium.
  • the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Hardware Design (AREA)
  • Telephonic Communication Services (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Telephone Function (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明实施例提供一种移动用户位置预测方法及设备,该方法包括:确定移动用户的当前行为活动的发生概率;根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。本实施例可以提高移动用户的目标地理位置的可用性。

Description

移动用户位置预测方法及设备 技术领域
本发明实施例涉及通信技术,尤其涉及一种移动用户位置预测方法及设备。
背景技术
随着地理信息系统、移动定位技术、无线通讯网络、智能终端技术、传感器技术的飞速发展,情境智能应用也飞速发展。在情景智能应用中,如何预测移动用户的目标地理位置,对情景智能应用的开放十分重要。
现有技术中,通过记录移动用户曾经频繁到访的多个历史地理位置,在预测移动用户的目标地理位置时,根据预设的预测模型,从多个历史地理位置中选取移动用户的目标地理位置。
然而,在预测初期阶段,由于缺少足够的历史地理位置信息,移动用户的目标地理位置的选取就会受到很大的限制,导致移动用户的目标地理位置的准确性较低。
发明内容
本发明实施例提供一种移动用户位置预测方法及设备,以提高移动用户的目标地理位置的准确性。
第一方面,本发明提供一种移动用户位置预测方法,包括:
确定移动用户的当前行为活动的发生概率;
根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。
结合第一方面,在第一方面的第一种可能的实现方式中,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
结合第一方面的第一种可能的实现方式,在第一方面的第二种可能的实现方式中,所述根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率,包括:
根据所述当前行为活动的发生概率、由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率;
根据所述当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率;
根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公共行为活动对应的目标行为活动的发生概率,确定所述移动用户的目标行为活动的发生概率。
结合第一方面,在第一方面的第三种可能的实现方式中,所述根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置,包括:
确定所述移动用户的所述目标行为活动是否存在于所述移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活动对应的历史地理位置;
若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
若否,根据第一预设地理位置范围内、与所述目标行为活动对应的 地理位置,预测所述移动用户的目标地理位置。
结合第一方面、第一方面的第一种至第三种任一种可能的实现方式,在第一方面的第四种可能的实现方式中,所述确定移动用户的当前行为活动的发生概率,包括:
获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,或者
获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率;或者
获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
结合第一方面的第四种可能的实现方式,在第一方面的第五种可能的实现方式中,所述当前时间、各所述兴趣点、当前行为活动的发生子概率具有对应关系;
所述根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,包括:
根据所述兴趣点分布,确定各所述兴趣点的比率;
根据各所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的发生概率。
第二方面,本发明提供一种用户设备,包括:
第一概率确定模块,用于确定移动用户的当前行为活动的发生概率;
第二概率确定模块,用于根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
行为活动确定模块,用于根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
预测模块,用于根据确定的所述移动用户的所述目标行为活动,预 测所述移动用户的目标地理位置。
结合第二方面,在第二方面的第一种可能的实现方式中,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
结合第二方面的第一种可能的实现方式,在第二方面的第二种可能的实现方式中,所述第二概率确定模块具体用于:
根据所述当前行为活动的发生概率、由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率;
根据所述当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率;
根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公共行为活动对应的目标行为活动的发生概率,确定所述移动用户的目标行为活动的发生概率。
结合第二方面,在第二方面的第三种可能的实现方式中,所述预测模块具体用于:
确定所述移动用户的所述目标行为活动是否存在于所述移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活动对应的历史地理位置;
若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
若否,根据第一预设地理位置范围内、与所述目标行为活动对应的地理位置,预测所述移动用户的目标地理位置。
结合第二方面、第二方面的第一种至第三种任一种可能的实现方式, 在第二方面的第四种可能的实现方式中,所述第一概率确定模块具体用于:
获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,或者
获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率;或者
获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
结合第二方面的第四种可能的实现方式,在第二方面的第五种可能的实现方式中,所述当前时间、各所述兴趣点、当前行为活动的发生子概率具有对应关系;
所述第一概率确定模块还具体用于:
根据所述兴趣点分布,确定各所述兴趣点的比率;
根据各所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的发生概率。
本发明实施例提供的移动用户位置预测方法及设备,通过用户设备确定移动用户的当前行为活动的发生概率;根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。本发明在没有移动用户大量的历史活动迁移规律的情况下,通过公共活动迁移规律确定移动用户的目标地理位置,提高了目标地理位置的准确性。同时,通过公共活动迁移规律,本实施例还可以对没有出现在移动用户历史迁移规律中的地理位置进行预测,得到目标地理位置,提高移动用户位置预测方法的普遍适用性。
附图说明
为了更清楚地说明本发明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发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本发明移动用户位置预测方法实施例一的流程示意图
图2为本发明用户设备实施例一的结构示意图;
图3为本发明用户设备实施例二的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明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发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,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,都属于本发明保护的范围。
图1为本发明移动用户位置预测方法实施例一的流程示意图。本实施例提供的移动用户位置预测方法可以由用户设备实现,该用户设备可以通过软件和/或硬件实现。如图1所示,本实施例提供的移动用户位置预测方法包括:
步骤101、确定移动用户的当前行为活动的发生概率;
步骤102、根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
步骤103、根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
步骤104、根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。
在具体实现过程中,用户设备确定移动用户的目标地理位置,其中,目标地理位置是指移动用户位于当前地理位置时,可能下一步需要去的目 的地。例如,判断移动用户的目标地理位置是经常光顾的购物中心,那么可以提前把商家打折和促销活动信息推送给移动用户,既节省了用户的时间,也提高了用户体验。或者,已知移动用户的目标地理位置是家,则提醒移动用户下班回家途中购买面粉,远程控制把家里的空调打开,同时把各路段交通拥堵状况发送到用户设备上。
本领域技术人员可以理解,上述实施例仅是对移动用户的目标地理位置的部分应用过程,不是全部应用过程,对于移动用户的目标地理位置的其它应用过程,本实施例此处不再赘述。
下面,本实施例对如何确定移动用户的目标地理位置,进行详细说明。
在步骤101中,用户设备先确定移动用户的当前行为活动的发生概率。具体地,可通过以下可能的实现方式实现。
一种可能的实现方式,获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率。
具体地,移动用户日常生活中的行为活动有吃饭、工作、购物等,假设有M种,M为自然数,每一种行为活动对应一个兴趣点(Point of Interest,简称POI),兴趣点具体可以为餐厅、商场、写字楼等,假设有N种,N为自然数。
特别地,当前时间、各兴趣点、当前行为活动的发生子概率具有对应关系。具体地,可通过条件发生概率p(Acti|POIk,T)表示对应关系,其中,Acti代表移动用户的当前行为活动的发生子概率,POIk代表兴趣点,T代表当前时间,具体可如表一所示。其中,该移动用户的当前行为活动的发生子概率可以是专家给出的经验值,也可以根据收集到的多个移动用户的历史活动记录来统计获取。
表一
Figure PCTCN2014088464-appb-000001
Figure PCTCN2014088464-appb-000002
在当前时间处于8:00-11:30时间段时,如表一可知,当兴趣点为写字楼时,移动用户当前行为活动为吃饭的发生子概率为0.05,工作的发生子概率为0.9,购物的发生子概率为0.05。
由于相对于移动用户当前地理位置的第二预设地理位置范围内有很多兴趣点,因此根据所述兴趣点分布,确定所述兴趣点的比率;根据所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的发生概率。
具体地,根据移动用户当前地理位置的坐标搜索得到第二预设地理位置范围内所有兴趣点,相对于所有的兴趣点,对同一当前行为活动的发生子概率求和,得到在当前地理位置当前行为活动的发生概率。即公式一所示。
Figure PCTCN2014088464-appb-000003
  (公式一)
其中,Acti代表移动用户的当前行为活动的发生子概率,POIk代表兴趣点,T代表当前时间,Loc代表当前地理位置,N为兴趣点的个数。Pk为同一类型的兴趣点的数量占所有兴趣点的比率,pk(0≤pk≤1)。例如,兴趣点为餐厅时,Pk=0.4,兴趣点为商场时,Pk=0.3,兴趣点为写字楼时,Pk=0.3。
当前时间处于8:00-11:30时间段内,当前行为活动为吃饭,则当前行为活动的发生概率为P=0.4×0.5+0.3×0.3+0.3×0.05=0.305;当前行为活动为工作,则当前行为活动的发生概率为P=0.4×0.5+0.3×0.1+0.3×0.9=0.5;当前行为活动为购物,则当前行为活动的发生概率为P=0.4×0+0.3×0.6+0.3×0.05=0.195。
另一种可能的实现方式,获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率。
具体地,利用用户设备上的运动传感器(如加速度传感器、陀螺仪)对移动用户运动状态(静止、步行、乘车)进行判别,或者利用光线传感器、气压计、全球定位系统(Global Position System,简称GPS)来判断移动用户当前地理位置是室内/室外。通过将上述多种传感数据综合应用,通过发生概率推理、规则推理等方式确定移动用户的运动状态,根据移动用户的运动状态,确定移动用户的当前行为活动的发生概率。本领域技术人员可以理解,运动状态与移动用户的当前行为活动的发生概率具有对应关系,可根据对应关系,确定当前行为活动的发生概率。
又一种可能的实现方式,获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
具体地,利用移动设备的麦克风采集移动用户的背景音,通过对背景音数据进行预处理并抽取Mel频率倒谱系数(Mel Frequency Cepstrum Coefficient,简称MFCC)、过零率、短时能量等特征来识别特殊声音或进行场景分析,因此可根据背景音推测移动用户的活动,如果背景音中有餐具撞击声音则判断移动用户当前的行为活动为吃饭,如果有多人同时讨论的声音,则判断移动用户的当前行为活动为开会。本领域技术人员可以理解,背景音与移动用户的当前行为活动的发生概率具有对应关系,可根据对应关系,确定当前行为活动的发生概率。
在步骤102中,根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率。
其中,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
下面采用具体实施例,进行详细说明。
首先,根据移动用户普遍的公共活动迁移规律,得到移动用户由当前行为活动转换到目标行为活动的发生概率pcommon(Acti|Acti-1),如表二所示。公共活动迁移规律可以是专家给出的经验值,也可以根据收集到的多个移 动用户的历史活动记录来统计获取。
表二
Figure PCTCN2014088464-appb-000004
同时,若已知历史活动迁移规律,也可得到移动用户由当前行为活动转换到所述目标行为活动的发生概率,ppersonal(Acti|Acti-1)。其中,历史活动迁移规律可以从多种途径获得,例如专门开发一个让移动用户主动配合标注当前行为活动的软件来收集数据,也可以通过移动用户曾经使用的第三方基于位置的服务(Location Based Service,简称LBS),签到服务获得,或者从移动用户记录的电子日记、日历中的行程安排中提取。本领域技术人员可以理解,历史行为活动的迁移规律也可如表二所示,本实施例此处不再赘述。
然后,根据当前行为活动的发生概率、由移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率,具体可通过如下公式实现:
Figure PCTCN2014088464-appb-000005
  (公式二)
其中,pl(Actnext=act)代表与历史行为活动对应的目标行为活动的发生概率,α(t)代表历史行为活动的权重因子,ppersonal(Actnext=act|Actcurrent=bi)代表由移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率,p(Actcurrent=bi)代表当前行为活动的发生概率,M代表行为活动的个数,M为自然数。
例如,在步骤101的一种可能的实现方式中,确定当前行为活动为吃饭时,发生概率为0.305,当前行为活动为工作时,发生概率为0.5,当前行为活动为购物,发生概率为0.195。
若α(t)=0.6,历史行为活动的迁移规律也如表二所示,则与历史行为活动对应的目标行为活动为购物时,发生概率pl(Actnext=act)=0.6×(0.305×0.4+0.5×0.2+0.195×0=0.1332;与历史行为活动对应的目标行为活动为吃饭时,发生概率为pl(Actnext=act)=0.6×(0.305×0+0.5×0.8+0.195×0.9)=0.3453;与历史行为活动对应的目标行为活动为工作时,发生概率为pl(Actnext=act)=0.6×(0.305×0.6+0.5×0+0.195×0.1)=0.2025。
同时,根据当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率,具体可通过如下公式实现:
Figure PCTCN2014088464-appb-000006
  (公式三)
其中,pg(Actnext=act)代表与公共行为活动对应的目标行为活动的发生概率,(1-α(t))代表公共行为活动的权重因子,pcommon(Actnext=act|Actcurrent=bi)代表由其他移动用户的历史行为活动确定的移动用户由当前行为活动转换到所述目标行为活动的发生概率,M代表行为活动的个数,M为自然数。
在具体实现过程中,确定与所述公共行为活动对应的目标行为活动的发生概率的实现方式,可参加确定与历史行为活动对应的目标行为活动的发生概率,此处不再赘述。
本领域技术人员可以理解,α(t)为权重因子,且α(t)是随着时间递增的,这是因为随着时间的增长,收集到的用户活动规律信息不断增加,个人的活动规律将在预测中逐渐占据主导地位。
最终,根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公共行为活动对应的目标行为活动的发生概率,确定所述移动用户的目标行为活动的发生概率。
在具体实现过程中,将历史行为活动对应的目标行为活动的发生概率以及与所述公共行为活动对应的目标行为活动的发生概率针对从同一当前 行为活动转换到同一目标行为活动求和,得到移动用户的目标行为活动的发生概率P(Actnext=act)。
即p(Actnext=act)=Pl(Actnext=act)+Pg(Actnext=act)  (公式四)
在步骤103中,根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动。
具体地,选取目标行为活动的发生概率最大的做为目标行为活动。
步骤104、根据所述移动用户的目标行为活动,预测所述移动用户的目标地理位置。
具体地,确定移动用户的目标行为活动是否存在与移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活动对应的历史地理位置;
若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
若否,根据第一预设地理位置范围内、与所述目标行为活动对应的地理位置,预测所述移动用户的目标地理位置。
在具体实现过程中,历史行为活动记录包括移动用户以前访问过的历史地理位置。当目标行为活动存在于历史行为活动记录中时,根据移动用户以前访问过的历史地理位置,预测移动用户的目标地理位置。
Figure PCTCN2014088464-appb-000007
  (公式五)
其中,Numpersonal(Actnext,loci)表示在历史行为活动记录中,活动Actnext在地点loci发生的次数,
Figure PCTCN2014088464-appb-000008
代表选取使Numpersonal(Actnext,loci)取最大值的loci。
当目标行为活动不存在于历史行为活动记录中时,则目标地理位置可能是第一预设地理位置范围内、与所述目标行为活动对应的地理位置,且目标地理位置是locx的概率与目标地理位置locx和当前地理位置之间的距离dist(.),以及其他移动用户在目标地理位置locx从事目标行为活动Actnext的次数有关。
Figure PCTCN2014088464-appb-000009
  (公式六)
其中,Ψ(.)随着dist(Locnext,locx)的增加而减少,随着Numcommon(Actnext,locx)的增加而增加,dist(Locnext,locx)表示locx和当前位置之间的距离,Numcommon(Actnext,locx)表示其他移动用户在locx从事目标行为活动Actnext的次数,
Figure PCTCN2014088464-appb-000010
代表选取使Ψ(dist(Locnext,locx),Numcommon(Actnext,locx)取最大值的locx。
特别地,Ψ(.)具体的形式不限,可以是
Figure PCTCN2014088464-appb-000011
  (公式七)
也可以是
Figure PCTCN2014088464-appb-000012
  (公式八)
其中,Ranknear(.)表示对locx和当前位置之间的距离从低到高排序的名次,Rankfreq表示其他移动用户在locx从事目标行为活动Actnext的次数从多到少排序的名次,β∈(0,1)是权重因子。
最终,选取概率最大的目标地理位置作为所述移动用户的目标地理位置。
本发明通过用户设备确定移动用户的当前行为活动的发生概率;根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。本发明在没有移动用户大量的历史活动迁移规律的情况下,通过公共活动迁移规律确定移动用户的目标地理位置,提高了目标地理位置的准确性。同时,通过公共活动迁移规律,本实施例还可以对没有出现在移动用户历史迁移规律中的地理位置进行预测,得到目标地理位置,提高移动用户位置预测方法的普遍适用性。
图2为本发明用户设备实施例一的结构示意图。如图2所示,本发明实施例提供的用户设备20包括:第一概率确定模块201、第二概率确定模块202、行为活动确定模块203和预测模块204。
其中,第一概率确定模块201,用于确定移动用户的当前行为活动的发生概率;
第二概率确定模块202,用于根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
行为活动确定模块203,用于根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
预测模块204,用于根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。
本实施例提供的用户设备,可以用于执行本发明任意实施例所提供的移动用户位置预测方法的技术方案,其实现原理和技术效果类似,此处不再赘述。
可选地,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
可选地,所述第二概率确定模块202具体用于:
根据所述当前行为活动的发生概率、由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率;
根据所述当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率;
根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公 共行为活动对应的目标行为活动的发生概率,确定所述移动用户的目标行为活动的发生概率。
可选地,所述预测模块204具体用于:
确定所述移动用户的所述目标行为活动是否存在于所述移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活动对应的历史地理位置;
若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
若否,根据第一预设地理位置范围内、与所述目标行为活动对应的地理位置,预测所述移动用户的目标地理位置。
可选地,所述第一概率确定模块201具体用于:
获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,或者
获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率;或者
获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
可选地,当前时间、各所述兴趣点、当前行为活动的发生子概率具有对应关系;
所述第一概率确定模块201还具体用于:
根据所述兴趣点分布,确定各所述兴趣点的比率;
根据各所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的发生概率。
本实施例提供的用户设备,可以用于执行本发明任意实施例所提供的移动用户位置预测方法的技术方案,其实现原理和技术效果类似,此处不再赘述。
图3为本发明用户设备实施例二的结构示意图。如图3所示,本实施 例提供的用户设备30包括处理器301和存储器302。可选地,用户设备30还可以包括发射器、接收器。发射器和接收器可以和处理器301相连。其中,发射器用于发送数据或信息,接收器用于接收数据或信息,存储器302存储执行指令,当用户设备30运行时,处理器301与存储器302之间通信,处理器301调用存储器302中的执行指令,用于执行以下操作:
确定移动用户的当前行为活动的发生概率;
根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。
本实施例提供的用户设备,可以用于执行本发明任意实施例所提供的移动用户位置预测方法的技术方案,其实现原理和技术效果类似,此处不再赘述。
可选地,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
可选地,所述根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率,包括:
根据所述当前行为活动的发生概率、由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率;
根据所述当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率 和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率;
根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公共行为活动对应的目标行为活动的发生概率,确定所述移动用户的目标行为活动的发生概率。
可选地,所述根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置,包括:
确定所述移动用户的所述目标行为活动是否存在于所述移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活动对应的历史地理位置;
若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
若否,根据第一预设地理位置范围内、与所述目标行为活动对应的地理位置,预测所述移动用户的目标地理位置。
可选地,所述确定移动用户的当前行为活动的发生概率,包括:
获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,或者
获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率;或者
获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
可选地,所述当前时间、各所述兴趣点、当前行为活动的发生子概率具有对应关系;
所述根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,包括:
根据所述兴趣点分布,确定各所述兴趣点的比率;
根据各所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的 发生概率。
本实施例提供的用户设备,可以用于执行本发明任意实施例所提供的移动用户位置预测方法的技术方案,其实现原理和技术效果类似,此处不再赘述。
本领域普通技术人员可以理解:实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,执行包括上述各方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上各实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述各实施例对本发明进行了详细的说明,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,或者对其中部分或者全部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发明各实施例技术方案的范围。

Claims (12)

  1. 一种移动用户位置预测方法,其特征在于,包括:
    确定移动用户的当前行为活动的发生概率;
    根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
    根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
    根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。
  2. 根据权利要求1所述的方法,其特征在于,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
    所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率,包括:
    根据所述当前行为活动的发生概率、由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率;
    根据所述当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率;
    根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公共行为活动对应的目标行为活动的发生概率,确定所述移动用户的 目标行为活动的发生概率。
  4. 根据权利要求1所述的方法,其特征在于,所述根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置,包括:
    确定所述移动用户的所述目标行为活动是否存在于所述移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活动对应的历史地理位置;
    若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
    若否,根据第一预设地理位置范围内、与所述目标行为活动对应的地理位置,预测所述移动用户的目标地理位置。
  5. 根据权利要求1至4任一项所述的方法,其特征在于,所述确定移动用户的当前行为活动的发生概率,包括:
    获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,或者
    获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率;或者
    获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
  6. 根据权利要求5所述的方法,其特征在于,所述当前时间、各所述兴趣点、当前行为活动的发生子概率具有对应关系;
    所述根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,包括:
    根据所述兴趣点分布,确定各所述兴趣点的比率;
    根据各所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的发生概率。
  7. 一种用户设备,其特征在于,包括:
    第一概率确定模块,用于确定移动用户的当前行为活动的发生概 率;
    第二概率确定模块,用于根据所述移动用户的当前行为活动的发生概率、所述移动用户的历史活动迁移规律以及公共活动迁移规律,确定所述移动用户的目标行为活动的发生概率;
    行为活动确定模块,用于根据所述移动用户的目标行为活动的发生概率,确定所述移动用户的目标行为活动;
    预测模块,用于根据确定的所述移动用户的所述目标行为活动,预测所述移动用户的目标地理位置。
  8. 根据权利要求7所述的设备,其特征在于,所述历史活动迁移规律包括:由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子;
    所述公共活动迁移规律包括由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子。
  9. 根据权利要求8所述的设备,其特征在于,所述第二概率确定模块具体用于:
    根据所述当前行为活动的发生概率、由所述移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述历史行为活动的权重因子,确定与所述历史行为活动对应的目标行为活动的发生概率;
    根据所述当前行为活动的发生概率、由其他移动用户的历史行为活动确定的所述移动用户由当前行为活动转换到所述目标行为活动的发生概率和所述公共行为活动的权重因子,确定与所述公共行为活动对应的目标行为活动的发生概率;
    根据与所述历史行为活动对应的目标行为活动的发生概率和与所述公共行为活动对应的目标行为活动的发生概率,确定所述移动用户的目标行为活动的发生概率。
  10. 根据权利要求7所述的设备,其特征在于,所述预测模块具体用于:
    确定所述移动用户的所述目标行为活动是否存在于所述移动用户的历史行为活动记录中,所述历史行为活动记录包括与所述目标行为活 动对应的历史地理位置;
    若是,根据所述历史行为活动记录,预测所述移动用户的目标地理位置;
    若否,根据第一预设地理位置范围内、与所述目标行为活动对应的地理位置,预测所述移动用户的目标地理位置。
  11. 根据权利要求7至10任一项所述的设备,其特征在于,所述第一概率确定模块具体用于:
    获取所述移动用户的当前地理位置和当前时间,根据所述当前地理位置,确定第二预设地理位置范围内所述移动用户的兴趣点分布,根据所述当前时间和所述兴趣点分布,确定所述移动用户的当前行为活动的发生概率,或者
    获取与所述移动用户对应的传感数据,根据所述传感数据确定所述移动用户的运动状态,根据所述移动用户的运动状态,确定所述移动用户的当前行为活动的发生概率;或者
    获取所述移动用户的当前地理位置的背景音,根据所述背景音,确定所述移动用户的当前行为活动的发生概率。
  12. 根据权利要求11所述的设备,其特征在于,当前时间、各所述兴趣点、当前行为活动的发生子概率具有对应关系;
    所述第一概率确定模块还具体用于:
    根据所述兴趣点分布,确定各所述兴趣点的比率;
    根据各所述兴趣点的比率,以及与各所述兴趣点对应的所述当前行为活动的发生子概率,确定在所述当前时间所述移动用户的当前行为活动的发生概率。
PCT/CN2014/088464 2013-10-28 2014-10-13 移动用户位置预测方法及设备 Ceased WO2015062409A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
EP14856995.7A EP3048820B1 (en) 2013-10-28 2014-10-13 Method and device for predicting position of mobile user
KR1020167012508A KR101787929B1 (ko) 2013-10-28 2014-10-13 모바일 사용자의 위치를 예측하는 방법 및 디바이스
JP2016526824A JP6277569B2 (ja) 2013-10-28 2014-10-13 モバイルユーザの位置を予測するための方法、および機器
US15/139,556 US9906913B2 (en) 2013-10-28 2016-04-27 Method for predicting position of mobile user, and equipment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310518476.X 2013-10-28
CN201310518476.XA CN104581622B (zh) 2013-10-28 2013-10-28 移动用户位置预测方法及设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/139,556 Continuation US9906913B2 (en) 2013-10-28 2016-04-27 Method for predicting position of mobile user, and equipment

Publications (1)

Publication Number Publication Date
WO2015062409A1 true WO2015062409A1 (zh) 2015-05-07

Family

ID=53003313

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/088464 Ceased WO2015062409A1 (zh) 2013-10-28 2014-10-13 移动用户位置预测方法及设备

Country Status (6)

Country Link
US (1) US9906913B2 (zh)
EP (1) EP3048820B1 (zh)
JP (1) JP6277569B2 (zh)
KR (1) KR101787929B1 (zh)
CN (1) CN104581622B (zh)
WO (1) WO2015062409A1 (zh)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10135831B2 (en) 2011-01-28 2018-11-20 F5 Networks, Inc. System and method for combining an access control system with a traffic management system
US10015143B1 (en) 2014-06-05 2018-07-03 F5 Networks, Inc. Methods for securing one or more license entitlement grants and devices thereof
US10505818B1 (en) 2015-05-05 2019-12-10 F5 Networks. Inc. Methods for analyzing and load balancing based on server health and devices thereof
CN105183800A (zh) * 2015-08-25 2015-12-23 百度在线网络技术(北京)有限公司 信息预测的方法和装置
CN105357637B (zh) * 2015-10-28 2019-06-11 同济大学 一种位置和行为信息预测系统及方法
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
CN105933857B (zh) * 2015-11-25 2019-05-14 中国银联股份有限公司 一种移动终端位置预测方法及装置
CN105608153A (zh) * 2015-12-18 2016-05-25 晶赞广告(上海)有限公司 一种通用的poi信息关联方法
CN105426553B (zh) * 2016-01-15 2018-09-11 四川农业大学 一种基于智能设备的目标实时跟踪预警方法以及系统
CN105974360A (zh) * 2016-04-27 2016-09-28 沈阳云飞科技有限公司 一种基于adl的监测分析方法、装置
CN107436894A (zh) * 2016-05-26 2017-12-05 冯小平 一种数据推送方法及装置
CN107436897A (zh) * 2016-05-26 2017-12-05 冯小平 一种用户当前行为的确定方法及装置
CN106528614B (zh) * 2016-09-29 2019-03-08 南京邮电大学 一种移动社交网络中用户的地理位置预测方法
CN106453050B (zh) * 2016-10-10 2019-11-22 腾讯科技(深圳)有限公司 基于社交应用的信息处理方法、系统以及相关设备
US10972453B1 (en) 2017-05-03 2021-04-06 F5 Networks, Inc. Methods for token refreshment based on single sign-on (SSO) for federated identity environments and devices thereof
CN108012237B (zh) * 2017-12-13 2020-02-14 Oppo广东移动通信有限公司 定位控制方法、装置、存储介质及终端设备
US10176379B1 (en) * 2018-06-01 2019-01-08 Cisco Technology, Inc. Integrating computer vision and wireless data to provide identification
CN111797301A (zh) * 2019-04-09 2020-10-20 Oppo广东移动通信有限公司 活动预测方法、装置、存储介质及电子设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101989127A (zh) * 2009-08-03 2011-03-23 索尼公司 数据处理装置、数据处理方法以及程序
CN102984799A (zh) * 2012-11-27 2013-03-20 中国人民解放军信息工程大学 一种用户位置判定方法及系统
EP2642431A1 (en) * 2010-11-18 2013-09-25 Sony Corporation Data processing device, data processing method, and program

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030022656A1 (en) 2001-06-08 2003-01-30 Hinnant Harris O. Position prediction for authentication of a mobile transmitter
JP2004333136A (ja) * 2003-04-30 2004-11-25 Sony Corp ナビゲーション装置
JP4388114B2 (ja) * 2004-07-13 2009-12-24 パナソニック株式会社 移動先表示装置および移動先表示方法
JP4402099B2 (ja) * 2005-12-05 2010-01-20 パナソニック株式会社 地点情報検索装置、地点情報検索方法、及びプログラム
US7848880B2 (en) * 2007-02-28 2010-12-07 Microsoft Corporation Traffic information adaptive to a user's travel
JP5016968B2 (ja) * 2007-04-24 2012-09-05 トヨタホーム株式会社 機器制御システム
US8031595B2 (en) * 2007-08-21 2011-10-04 International Business Machines Corporation Future location determination using social networks
JP2012008771A (ja) * 2010-06-24 2012-01-12 Sony Corp 情報処理装置、情報処理システム、情報処理方法およびプログラム
JP5365653B2 (ja) * 2011-03-01 2013-12-11 日本電気株式会社 消費電力削減装置、システム方法及びプログラム
US20120226554A1 (en) * 2011-03-01 2012-09-06 Jeffrey C Schmidt System and method for providing data to a portable communications device based on real-time subscriber behavior
CN102682041B (zh) 2011-03-18 2014-06-04 日电(中国)有限公司 用户行为识别设备及方法
JP2012256239A (ja) * 2011-06-09 2012-12-27 Toyota Central R&D Labs Inc 目的地予測装置及びプログラム
CN102509170A (zh) 2011-10-10 2012-06-20 浙江鸿程计算机系统有限公司 一种基于历史轨迹数据挖掘的位置预测系统及方法
CN103052022B (zh) * 2011-10-17 2015-08-19 中国移动通信集团公司 基于移动行为的用户稳定点发现方法和系统
WO2014074513A1 (en) * 2012-11-06 2014-05-15 Intertrust Technologies Corporation Activity recognition systems and methods

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101989127A (zh) * 2009-08-03 2011-03-23 索尼公司 数据处理装置、数据处理方法以及程序
EP2642431A1 (en) * 2010-11-18 2013-09-25 Sony Corporation Data processing device, data processing method, and program
CN102984799A (zh) * 2012-11-27 2013-03-20 中国人民解放军信息工程大学 一种用户位置判定方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3048820A4 *

Also Published As

Publication number Publication date
CN104581622A (zh) 2015-04-29
EP3048820A4 (en) 2016-10-19
KR101787929B1 (ko) 2017-10-18
US20160242009A1 (en) 2016-08-18
JP6277569B2 (ja) 2018-02-14
EP3048820A1 (en) 2016-07-27
EP3048820B1 (en) 2020-08-19
JP2017501609A (ja) 2017-01-12
KR20160070817A (ko) 2016-06-20
CN104581622B (zh) 2018-09-07
US9906913B2 (en) 2018-02-27

Similar Documents

Publication Publication Date Title
WO2015062409A1 (zh) 移动用户位置预测方法及设备
US12302190B2 (en) Determining a significant user location for providing location-based services
US11553302B2 (en) Labeling a significant location based on contextual data
JP6284538B2 (ja) データクラスタのためのコンテキストラベル
US10070261B2 (en) Harvesting labels for significant locations and updating a location fingerprint database using harvested labels
CN108875007B (zh) 兴趣点的确定方法和装置、存储介质、电子装置
EP3342192B1 (en) Method and arrangement for locating a mobile device
US8718672B2 (en) Identifying status based on heterogeneous sensors
US11761785B2 (en) Labeling a significant location based on contextual data
US8676668B2 (en) Method for the determination of a time, location, and quantity of goods to be made available based on mapped population activity
CN106461786B (zh) 室内全球定位系统
KR20110028216A (ko) 위치 인식을 통한 동적 이벤트 계획
RU2680093C2 (ru) Определение радиуса погрешности местоположения
CN104186016A (zh) 定位移动设备
JP6358247B2 (ja) 情報処理装置、情報処理方法およびプログラム
US20200092019A1 (en) Method and system for determining signal strength for a mobile device
US9602589B1 (en) Systems and methods for determining room types for regions of a map
JP6223302B2 (ja) 携帯端末を所持したユーザの滞在判定が可能な装置、プログラム及び方法
CN115326071A (zh) 一种自适应融合的室内定位方法、计算机设备和可读存储介质
RU2574602C2 (ru) Гибридное геопозиционирование мобильного телефона

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: 14856995

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2014856995

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2014856995

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2016526824

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20167012508

Country of ref document: KR

Kind code of ref document: A