WO2017054332A1 - 路径查询方法、装置、设备及非易失性计算机存储介质 - Google Patents

路径查询方法、装置、设备及非易失性计算机存储介质 Download PDF

Info

Publication number
WO2017054332A1
WO2017054332A1 PCT/CN2015/098278 CN2015098278W WO2017054332A1 WO 2017054332 A1 WO2017054332 A1 WO 2017054332A1 CN 2015098278 W CN2015098278 W CN 2015098278W WO 2017054332 A1 WO2017054332 A1 WO 2017054332A1
Authority
WO
WIPO (PCT)
Prior art keywords
road segment
road
destination point
obtaining
sequence
Prior art date
Application number
PCT/CN2015/098278
Other languages
English (en)
French (fr)
Inventor
刘峰
Original Assignee
百度在线网络技术(北京)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 百度在线网络技术(北京)有限公司 filed Critical 百度在线网络技术(北京)有限公司
Priority to US15/765,204 priority Critical patent/US20190056235A1/en
Priority to KR1020187009021A priority patent/KR102015235B1/ko
Priority to EP15905242.2A priority patent/EP3358474B1/en
Priority to JP2018516192A priority patent/JP6613475B2/ja
Publication of WO2017054332A1 publication Critical patent/WO2017054332A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3453Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3484Personalized, e.g. from learned user behaviour or user-defined profiles
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3453Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3492Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20Instruments for performing navigational calculations
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/36Input/output arrangements for on-board computers
    • G01C21/3605Destination input or retrieval
    • G01C21/3617Destination input or retrieval using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/36Input/output arrangements for on-board computers
    • G01C21/3667Display of a road map
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases

Definitions

  • the present invention relates to query technology, and in particular, to a path query method, apparatus, device, and non-volatile computer storage medium.
  • the terminal integrates more and more functions, so that the system function list of the terminal contains more and more corresponding applications (Application, APP).
  • Some applications involve some path query services, such as Baidu maps. These applications first display the path query query interface to the user for input, and then, according to the information input by the user, set the information of the endpoints such as the departure point and the destination point, and then request the query engine to provide the path data.
  • the query engine may perform a path query operation based on the urban road network and the road weights of the roads in the urban road network.
  • certain factors affecting the change of road weight may change at any time, such as road width, road quality, etc., and the road weight of some roads may not be updated in time, so that the path query operation is performed depending on the road weight.
  • the obtained query result may be unreasonable.
  • the query result is not the optimal query result, and may even be a poor query result, which leads to a decrease in the reliability of the path query operation.
  • aspects of the present invention provide a path query method, apparatus, device, and non-volatile computer storage medium for improving the reliability of a path query operation.
  • An aspect of the present invention provides a path query method, including:
  • Obtaining query data the query data including a departure point and a destination point;
  • each of the M road segment sequences includes at least one road segment;
  • M is an integer greater than or equal to 2;
  • N is an integer greater than or equal to 1 and less than or equal to M;
  • the path query result is output.
  • each of the at least one road segment included in each of the road segment sequences is reachable to an adjacent road segment of the road segment.
  • the transition probability of the destination point, before selecting a sequence of N segments from the M segment sequence, as a result of the path query further includes:
  • the obtaining, according to the destination point, the at least one user history trajectory that reaches the destination point includes:
  • the method further includes:
  • the urban road network is divided by a specified separation distance to generate a plurality of urban road network areas in the urban road network.
  • each of the at least one road segment included in the sequence of each road segment is turned
  • the adjacent road segment of the road segment can reach the transition probability of the destination point, and select N road segment sequences from the M road segment sequences as the path query result, including:
  • N road segment sequences are selected from the M road segment sequences as a path query result.
  • N route sequence is selected from the M link sequence according to the joint probability of each link sequence, as a path query result.
  • a link sequence having a joint probability greater than or equal to a preset probability threshold is used as a sequence of one of the N road segments.
  • Another aspect of the present invention provides a path query device, including:
  • An obtaining unit configured to obtain query data, where the query data includes a departure location and a destination point;
  • a matching unit configured to obtain, according to the query data, a sequence of M segments, where each segment sequence of the M segments includes at least one segment; M is an integer greater than or equal to 2;
  • a selecting unit configured to: according to the transition probability that each of the at least one road segment included in each of the road segment sequences is turned to the adjacent road segment of the road segment, the transition probability of the destination point is reachable from the M N segments are selected in the sequence of segments as a path query result; N is an integer greater than or equal to 1 and less than or equal to M;
  • An output unit configured to output the path query result.
  • the device further comprising a processing unit
  • the apparatus further comprising a dividing unit, configured to
  • the urban road network is divided by a specified separation distance to generate a plurality of urban road network areas in the urban road network.
  • N road segment sequences are selected from the M road segment sequences as a path query result.
  • a link sequence having a joint probability greater than or equal to a preset probability threshold is used as a sequence of one of the N road segments.
  • an apparatus comprising:
  • One or more processors are One or more processors;
  • One or more programs the one or more programs being stored in the memory, when executed by the one or more processors:
  • Obtaining query data the query data including a departure point and a destination point;
  • each of the M road segment sequences includes at least one road segment;
  • M is an integer greater than or equal to 2;
  • N is an integer greater than or equal to 1 and less than or equal to M;
  • the path query result is output.
  • a nonvolatile computer storage medium storing one or more programs when the one or more programs are executed by a device causes The device:
  • Obtaining query data the query data including a departure point and a destination point;
  • each of the M road segment sequences includes at least one road segment;
  • M is an integer greater than or equal to 2;
  • N is an integer greater than or equal to 1 and less than or equal to M;
  • the path query result is output.
  • the embodiment of the present invention obtains query data, where the query data includes a departure point and a destination point, and further obtains M road segment sequences according to the query data, so that at least according to each road segment sequence Each road segment in a road segment turns to the adjacent road segment of the road segment to reach the transition probability of the destination point, and selects N road segment sequences from the M road segment sequences as the path query result, since the path query is no longer dependent on the road weight Therefore, the problem that the query result is unreasonable due to the inability of the road weight of some roads to be updated in time can be avoided in the prior art, thereby improving the reliability of the path query operation.
  • the trajectory big data execution path query operation of the user history trajectory is adopted, the user's experience route can be found, and a more reasonable query result can be provided, for example, discovering a new road and avoiding Congested roads, etc., can greatly enhance the user experience.
  • FIG. 1 is a schematic flowchart of a path query method according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a path query apparatus according to another embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a path query apparatus according to another embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of a path query apparatus according to another embodiment of the present invention.
  • the terminals involved in the embodiments of the present invention may include, but are not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and a personal computer (Personal Computer, PC). ), MP3 player, MP4 player, wearable device (for example, smart glasses, smart watches, smart bracelets, etc.).
  • PDA personal digital assistant
  • PC Personal Computer
  • FIG. 1 is a schematic flowchart of a path query method according to an embodiment of the present invention, as shown in FIG. 1 .
  • the so-called road segment in the traffic field, refers to the relationship between two adjacent nodes on the urban road network.
  • Traffic The so-called urban road network refers to a network structure consisting of different functions, grades, and location roads in a city with a certain density and appropriate form.
  • road segment sequence refers to a sequence of road segments formed by an orderly arrangement of a series of connected road segments, which may also be called a path.
  • N is an integer greater than or equal to 1 and less than or equal to M.
  • the so-called “reachable destination point” may mean passing or passing the destination point and continuing to move to other places, or may also stop moving to other places with the destination point as the end point, this embodiment is This is not particularly limited.
  • execution entities of 101 to 103 may be applications located in the local terminal, or may be plug-ins or software development kits (SDKs) installed in applications located in the local terminal.
  • the functional unit may also be a query engine located in the network side server, or may be a distributed system located on the network side, which is not specifically limited in this embodiment.
  • the application may be a local application (nativeApp) installed on the terminal, or may be a web application (webApp) of the browser on the terminal, which is not limited in this embodiment.
  • the query data includes a departure point and a destination point, and further, according to the query data, obtaining M road segment sequences, so that each road segment sequence can be obtained.
  • Each of the at least one road segment included in the column turns to the transition probability of the adjacent segment of the road segment to reach the destination point, and selects N road segment sequences from the M road segment sequences as a path query result, since no longer depends
  • the road weight performs the path query operation. Therefore, the problem that the query result is unreasonable due to the inability of the road weight of some roads to be updated in time can be avoided in the prior art, thereby improving the reliability of the path query operation.
  • Some applications involve some path query services, such as Baidu maps. These applications first display the path query query interface to the user for input, and then, according to the information input by the user, set the information of the endpoints such as the departure point and the destination point, and then request the query engine to provide the path data. .
  • the query keyword provided by the user may also be collected, which may also be referred to as query data.
  • the query command can be triggered in the following two ways:
  • the query keyword input or selected by the user on the page presented by the current application may include a departure location and a destination point. Then, by clicking the query button on the page, a query command is triggered, and the query keyword includes the query keyword. In this way, after receiving the query command, the query keywords included therein can be parsed.
  • asynchronous loading technology for example, Ajax asynchronous loading or Jsonp asynchronous loading, etc.
  • real-time acquisition of the input content input by the user on the page displayed by the current application in order to distinguish from the query keyword, the input content at this time may be referred to as input. Key words.
  • An input character to trigger a query command the query command including the query keyword.
  • the query keywords included therein can be parsed.
  • an interface such as an Ajax interface or a Jsonp interface may be provided.
  • the interfaces may be written in a language such as Java or a Hypertext Preprocessor (PHP) language, and the specific call may be in a language such as Jquery or native JavaScript. Write it.
  • PGP Hypertext Preprocessor
  • the purpose of the user query may be arbitrarily or non-specific, which may cause the departure and destination points included in the query data provided by the user to have certain uncertainties.
  • Appropriate expansion processing is included for the departure and destination points included in the query data, and the query starting point and the query end point of the query are expanded to make the query starting point no longer limited to the starting point, and the query end point is no longer limited to the purpose. location. In this way, the query results can be made more in line with the user's true travel intention.
  • the departure point can be extended by using the urban road network area to which the departure point is included in the query data
  • the destination point is extended by using the urban road network area to which the destination point included in the query data belongs, and execution is performed. Path query operation.
  • the so-called urban road network refers to a network structure consisting of different functions, grades, and location roads in a city with a certain density and appropriate form.
  • the so-called urban road network area refers to a designated area in the urban road network.
  • the designated areas may be a plurality of areas in the urban road network randomly divided based on the urban road network, or may be divided into urban road networks by a specified separation distance, and the generated urban road network is A plurality of urban road network areas are not particularly limited in this embodiment.
  • the urban road network area to which the departure location belongs may be obtained according to the departure location included in the query data, and according to the query.
  • the destination point included in the data obtains the urban road network area to which the destination point belongs.
  • a link matching process is performed in the urban road network to obtain a matched M road segment sequence.
  • the road segments included in each of the road segment sequences are the first connected road segments from the urban road network region to which the departure point belongs to the urban road network region to which the destination point belongs.
  • the starting point of the query and the query end point of the query are expanded, the starting point of the query is no longer limited to the starting point included in the query data, and the query end point is no longer limited to the purpose of the query data.
  • the location therefore, can obtain more matching segments of the road segment, thus enriching the data processing source on which the path query operation is based.
  • At least one user history track that reaches the destination point may be obtained according to the destination point, and the at least one may be obtained.
  • the number of first tracks of each road segment included in the sequence of the historical road segments is obtained, and each phase of the road segment is passed through the road segment.
  • a transition probability that each of the road segments included in the historical road segment sequence can be transferred to the destination point for each adjacent road segment of the road segment can be obtained.
  • the ratio of the number of second paths to the number of first paths is The second path number/first path number, as each of the road segments included in the historical road segment sequence turns to each of the adjacent road segments of the road segment to reach the transition probability of the destination point.
  • the transition probability of each road segment corresponding to the user history track in the urban road network to the destination point of each adjacent road segment of the road segment can be obtained, and each of the other road segments in the urban road network is directed to the road segment.
  • the transition probability that an adjacent road segment can reach the destination point can be recorded as 0.
  • the so-called user history track is a collection of several track points of the user.
  • the user history trajectory can be matched to the road segment in the urban road network, and the subsequent path query operation can be performed.
  • a matching algorithm in the prior art for example, a hidden Markov model, etc., may be used.
  • details refer to related content in the prior art, and details are not described herein again.
  • the location expansion method described above may also be used to extend the destination point.
  • the urban road network area to which the destination point belongs may be obtained according to the destination point, and further, the urban road network to which the destination point belongs may be obtained according to the urban road network area to which the destination point belongs.
  • At least one user history trajectory of the region as at least one user history trajectory to the destination point.
  • the so-called "at least one user history track reaching the urban road network area to which the destination point belongs” may refer to a user history track that passes through or passes through the urban road network area to which the destination point belongs, and continues to move to other places. Or may be a user history track that does not continue to move to other locations with the urban road network area to which the destination point belongs as the end point.
  • This embodiment is not particularly limited in this embodiment.
  • the road segments corresponding to the historical tracks of the users reaching each urban road network area may be formed into a single independent road network, and each user history track can reach the independent road network.
  • Urban road network area If the user history track passes through or passes through a certain urban road network area and continues to move to other urban road network areas, then in the independent road network, part of the path after the certain urban road network area may be deleted, The end point of each user history track in the independent road network is made to be the certain city road network area.
  • the independent road network may be used to index the road segments corresponding to the historical tracks of the users. In this way, when querying at least one user history track of the urban road network area according to a certain urban road network area, the query can be directly performed according to the index, which can effectively improve the efficiency of the path query operation.
  • each of the at least one road segment included in each of the road segment sequences may be redirected to an adjacent road segment of the road segment.
  • the transition probability of the destination point obtains a joint probability of the sequence of each road segment.
  • N route segments are selected from the M link sequence as a path query result.
  • a road segment sequence includes n road segments, that is, from the departure point (ie, the urban road network area to which the departure point belongs) to the destination point (ie, the urban road network area to which the destination point belongs), which are link1, link2, ...
  • Linkn-1, linkn, n is an integer greater than or equal to 2.
  • the transition probability of linkn-1 to linkn is denoted as P linkn
  • the N road segments with the largest joint probability can be specified. Column as the result of the path query. For example, the sequence of all the road segments may be sorted according to the order of joint probability, and the sequence of N road segments arranged in front is selected as the query result of the path query operation.
  • a link sequence whose joint probability is greater than or equal to a preset probability threshold may be specifically used as a sequence of one of the N road segments.
  • the query data includes a departure point and a destination point, and further, according to the query data, obtaining M road segment sequences, so that each of the at least one road segment included in each road segment sequence can be obtained.
  • the road segment turns to the adjacent road segment of the road segment to reach the transition probability of the destination point, and selects N road segment sequences from the M road segment sequences as the path query result, since the path query operation is no longer relied on the road weight, The problem that the query result is unreasonable due to the inability of the road weight of some roads to be updated in time is avoided in the prior art, thereby improving the reliability of the path query operation.
  • the trajectory big data execution path query operation of the user history trajectory is adopted, the user's experience route can be found, and a more reasonable query result can be provided, for example, discovering a new road and avoiding Congested roads, etc., can greatly enhance the user experience.
  • FIG. 2 is a schematic structural diagram of a path query apparatus according to another embodiment of the present invention, as shown in FIG. 2 .
  • the path querying apparatus of this embodiment may include an obtaining unit 21, a matching unit 22, a selecting unit 23, and an output unit 24.
  • the obtaining unit 21 is configured to acquire query data, where the query data includes a departure point and a destination point
  • the matching unit 22 is configured to obtain M road segment sequences according to the query data, and each of the M road segment sequences
  • the sequence of the road segment includes at least one road segment; M is an integer greater than or equal to 2;
  • the selecting unit 23 is configured to reach, according to each of the at least one road segment included in the sequence of each road segment, the adjacent road segment of the road segment a transition probability of the destination point, selecting N route segments from the M road segment sequences as a path query result; N being an integer greater than or equal to 1 and less than or equal to M; and an output unit 24 for outputting the path search result.
  • part or all of the path query device provided in this embodiment may be an application located in a local terminal, or may be a plug-in or a software development kit (Software Development Kit) installed in an application located in the local terminal.
  • the functional unit, such as the SDK may also be a query engine located in the network side server, or may be a distributed system located on the network side, which is not specifically limited in this embodiment.
  • the application may be a local application (nativeApp) installed on the terminal, or may be a web application (webApp) of the browser on the terminal, which is not limited in this embodiment.
  • the path querying apparatus may further include a processing unit 31, configured to obtain a destination according to the destination point. Determining at least one user history track of the destination point; obtaining a historical link sequence corresponding to each user history track in the at least one user history track; Obtaining, according to the historical link sequence corresponding to each user history track, the number of first tracks of each road segment included by the historical road segment sequence, and passing each adjacent road segment of the road segment after passing the road segment a second number of paths; and obtaining, according to the number of the first trajectories and the number of the second trajectories, each of the road segments included in the sequence of historical road segments to each adjacent road segment of the road segment to reach the destination point Probability.
  • the processing unit 31 may obtain, according to the destination point, a city road network area to which the destination point belongs, and obtain a city to which the destination point belongs according to the urban road network area to which the destination point belongs. At least one user history track of the road network area as the at least one user history track reaching the destination point.
  • the path querying apparatus provided in this embodiment may further include a dividing unit 41, configured to use the specified separation distance to the urban road network. Dividing is performed to generate a plurality of urban road network regions in the urban road network.
  • the selecting unit 23 may be specifically configured to: according to each of the at least one road segment included in each sequence of segments, turn to a phase of the road segment The neighboring segment can reach the transition probability of the destination point, obtain the joint probability of each of the link segments, and select N segments from the M segment sequence according to the joint probability of each segment sequence as the path search result.
  • the selecting unit 23 may be specifically configured to use the N route sequence with the largest joint probability as the path query result.
  • the selecting unit 23 may be specifically configured to use a link sequence with a joint probability greater than or equal to a preset probability threshold as one of the N link sequences.
  • the query data is obtained by the obtaining unit, where the query data includes a departure point and a destination point, and then the matching unit obtains M road segment sequences according to the query data, so that the selection unit can be included according to each road segment sequence.
  • Each of the at least one road segment turns to an adjacent road segment of the road segment to reach a transition probability of the destination point, and selects N road segment sequences from the M road segment sequences as a path query result, since the road weight is no longer relied on
  • the path query operation can avoid the problem that the query result is unreasonable due to the inability of the road weight of some roads to be updated in time in the prior art, thereby improving the reliability of the path query operation.
  • the trajectory big data execution path query operation of the user history trajectory is adopted, the user's experience route can be found, and a more reasonable query result can be provided, for example, discovering a new road and avoiding Congested roads, etc., can greatly enhance the user experience.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical, mechanical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • General Health & Medical Sciences (AREA)
  • Navigation (AREA)

Abstract

一种路径查询方法、装置、设备及非易失性计算机存储介质。通过获取查询数据,所述查询数据包括出发地点和目的地点(101),进而根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段(102),使得能够根据每个路段序列所包括的至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果(103),输出所述路径查询结果(104)。由于不再依赖道路权重执行路径查询操作,因此,能够避免现有技术中由于某些道路的道路权重无法及时更新而导致的查询结果不合理的问题,从而提高了路径查询操作的可靠性。

Description

路径查询方法、装置、设备及非易失性计算机存储介质
本申请要求了申请日为2015年09月30日,申请号为201510639503.8发明名称为“路径查询方法及装置”的中国专利申请的优先权。
技术领域
本发明涉及查询技术,特别涉及一种路径查询方法、装置、设备及非易失性计算机存储介质。
背景技术
随着通信技术的发展,终端集成了越来越多的功能,从而使得终端的系统功能列表中包含了越来越多相应的应用(Application,APP)。有些应用中会涉及一些路径查询服务,例如,百度地图等。这些应用首先向用户展示路径查询查询界面,以供用户进行输入,然后,则可以根据用户输入的信息,设置查询端点信息例如,出发地点和目的地点等端点的信息,进而请求查询引擎提供路径数据。查询引擎可以基于城市道路网以及该城市道路网中的道路的道路权重,执行路径查询操作。
然而,在一些情况下例如,影响道路权重变化的某些因素可能会随时发生变化如,道路宽度、路面质量等,某些道路的道路权重可能无法及时更新,使得依赖道路权重执行路径查询操作,所获得的查询结果可能不合理,例如,查询结果不是最优查询结果,甚至还可能会是较差的查询结果,从而导致了路径查询操作的可靠性的降低。
发明内容
本发明的多个方面提供一种路径查询方法、装置、设备及非易失性计算机存储介质,用以提高路径查询操作的可靠性。
本发明的一方面,提供一种路径查询方法,包括:
获取查询数据,所述查询数据包括出发地点和目的地点;
根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
输出所述路径查询结果。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果之前,还包括:
根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹;
获得所述至少一个用户历史轨迹中每个用户历史轨迹所对应的历史路段序列;
根据所述每个用户历史轨迹所对应的历史路段序列,获得通过所述历史路段序列所包括的每个路段的第一轨迹数量,以及通过该路段之后再通过该路段的每个相邻路段的第二路径数量;
根据所述第一轨迹数量和所述第二轨迹数量,获得所述历史路段序列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转移概率。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹,包括:
根据所述目的地点,获得所述目的地点所属的城市道路网区域;
根据所述目的地点所属的城市道路网区域,获得到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹,以作为所述到达所述目的地点的至少一个用户历史轨迹。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述目的地点,获得所述目的地点所属的城市道路网区域之前,还包括:
以指定间隔距离,对城市道路网进行划分,生成所述城市道路网中的若干个城市道路网区域。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述每个路段序列所包括的所述至少一个路段中每个路段转向 该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,包括:
根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,获得所述每个路段序列的联合概率;
根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,包括:
将联合概率最大的N个路段序列,作为所述路径查询结果;或者
将联合概率大于或等于预先设置的概率阈值的路段序列,作为所述N个路段序列中的一个路段序列。
本发明的另一方面,提供一种路径查询装置,包括:
获取单元,用于获取查询数据,所述查询数据包括出发地点和目的地点;
匹配单元,用于根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
选择单元,用于根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M 个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
输出单元,用于输出所述路径查询结果。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述装置还包括处理单元,用于
根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹;
获得所述至少一个用户历史轨迹中每个用户历史轨迹所对应的历史路段序列;
根据所述每个用户历史轨迹所对应的历史路段序列,获得通过所述历史路段序列所包括的每个路段的第一轨迹数量,以及通过该路段之后再通过该路段的每个相邻路段的第二路径数量;以及
根据所述第一轨迹数量和所述第二轨迹数量,获得所述历史路段序列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转移概率。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述处理单元,具体用于
根据所述目的地点,获得所述目的地点所属的城市道路网区域;以及
根据所述目的地点所属的城市道路网区域,获得到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹,以作为所述到达所述 目的地点的至少一个用户历史轨迹。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述装置还包括划分单元,用于
以指定间隔距离,对城市道路网进行划分,生成所述城市道路网中的若干个城市道路网区域。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述选择单元,具体用于
根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,获得所述每个路段序列的联合概率;以及
根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述选择单元,具体用于
将联合概率最大的N个路段序列,作为所述路径查询结果;或者
将联合概率大于或等于预先设置的概率阈值的路段序列,作为所述N个路段序列中的一个路段序列。
本发明的另一方面,提供一种设备,包括:
一个或者多个处理器;
存储器;
一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时:
获取查询数据,所述查询数据包括出发地点和目的地点;
根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
输出所述路径查询结果。
本发明的另一方面,提供一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
获取查询数据,所述查询数据包括出发地点和目的地点;
根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
输出所述路径查询结果。
由上述技术方案可知,本发明实施例通过获取查询数据,所述查询数据包括出发地点和目的地点,进而根据所述查询数据,获得M个路段序列,使得能够根据每个路段序列所包括的至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,由于不再依赖道路权重执行路径查询操作,因此,能够避免现有技术中由于某些道路的道路权重无法及时更新而导致的查询结果不合理的问题,从而提高了路径查询操作的可靠性。
另外,采用本发明所提供的技术方案,由于采用了用户历史轨迹这一轨迹大数据执行路径查询操作,使得能够发现用户的经验路线,可以提供更加合理的查询结果,例如,发现新道路、躲避拥堵道路等,能够极大提升用户体验。
附图说明
为了更清楚地说明本发明实施例中的技术方案,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为本发明一实施例提供的路径查询方法的流程示意图;
图2为本发明另一实施例提供的路径查询装置的结构示意图;
图3为本发明另一实施例提供的路径查询装置的结构示意图;
图4为本发明另一实施例提供的路径查询装置的结构示意图。
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全部其他实施例,都属于本发明保护的范围。
需要说明的是,本发明实施例中所涉及的终端可以包括但不限于手机、个人数字助理(Personal Digital Assistant,PDA)、无线手持设备、平板电脑(Tablet Computer)、个人电脑(Personal Computer,PC)、MP3播放器、MP4播放器、可穿戴设备(例如,智能眼镜、智能手表、智能手环等)等。
另外,本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
图1为本发明一实施例提供的路径查询方法的流程示意图,如图1所示。
101、获取查询数据,所述查询数据包括出发地点和目的地点。
102、根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数。
所谓的路段,在交通领域,是指城市道路网上相邻两个节点之间的 交通线路。所谓的城市道路网(urban road network),是指城市范围内由不同功能、等级、区位的道路,以一定的密度和适当的形式组成的网络结构。
所谓的路段序列,是指一串连通的路段有序排列所形成的路段序列,又可以叫做路径。
103、根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数。
所谓的“可达目的地点”,可以是指经过或通过所述目的地点,并且继续向其他地点移动,或者还可以是以所述目的地点为终点不再继续向其他地点移动,本实施例对此不进行特别限定。
104、输出所述路径查询结果。
需要说明的是,101~103的执行主体的部分或全部可以为位于本地终端的应用,或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(Software Development Kit,SDK)等功能单元,或者还可以为位于网络侧服务器中的查询引擎,或者还可以为位于网络侧的分布式系统,本实施例对此不进行特别限定。
可以理解的是,所述应用可以是安装在终端上的本地程序(nativeApp),或者还可以是终端上的浏览器的一个网页程序(webApp),本实施例对此不进行限定。
这样,通过获取查询数据,所述查询数据包括出发地点和目的地点,进而根据所述查询数据,获得M个路段序列,使得能够根据每个路段序 列所包括的至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,由于不再依赖道路权重执行路径查询操作,因此,能够避免现有技术中由于某些道路的道路权重无法及时更新而导致的查询结果不合理的问题,从而提高了路径查询操作的可靠性。
通常,一些应用中会涉及一些路径查询服务,例如,百度地图等。这些应用首先向用户展示路径查询查询界面,以供用户进行输入,然后,则可以根据用户输入的信息,设置查询端点信息例如,出发地点和目的地点等端点的信息,进而请求查询引擎提供路径数据。
可选地,在本实施例的一个可能的实现方式中,在101中,具体可以采集用户所提供的查询关键词,也可以称为查询数据。
具体地,可以通过用户所触发的查询命令实现。具体可以采用下述两种方式触发查询命令:
方式一:
用户可以在当前应用所展现的页面上所输入或选择的查询关键词,该查询关键词可以包括出发地点和目的地点。然后,通过点击该页面上的查询按钮,以触发查询命令,该查询命令中包含所述查询关键词。这样,在接收到该查询命令之后,则可以解析出其中所包含的所述查询关键词。
方式二:
采用异步加载技术例如,Ajax异步加载或Jsonp异步加载等,实时获取用户在当前应用所展现的页面上所输入的输入内容,为了与查询关键词进行区分,此时的输入内容可以称为是输入关键词。然后,获取完 一个输入字符,以触发查询命令,该查询命令中包含所述查询关键词。这样,在接收到该查询命令之后,则可以解析出其中所包含的所述查询关键词。具体地,具体可以提供Ajax接口或Jsonp接口等接口,这些接口可以使用Java、超级文本预处理(Hypertext Preprocessor,PHP)语言等语言进行编写,其具体的调用可以使用Jquery,或者原生的JavaScript等语言进行编写。
在大部分情况下,用户查询的目的可能会具有随意性或非特定性,这就会使得用户所提供的查询数据中所包括的出发地点和目的地点可能具有一定的不确定性,因此,可以对查询数据中所包括出发地点和目的地点进行适当的扩展处理,将本次查询的查询起点和查询终点的范围扩大,以使得查询起点不再局限于出发地点,查询终点也不再局限于目的地点。这样,就能够使得查询结果更加符合用户真正的出行意图。
本发明中,可以利用查询数据中所包括的出发地点所属的城市道路网区域,来扩展该出发地点,利用查询数据中所包括的目的地点所属的城市道路网区域,来扩展该目的地点,执行路径查询操作。
所谓的城市道路网(urban road network),是指城市范围内由不同功能、等级、区位的道路,以一定的密度和适当的形式组成的网络结构。
该实现方式中,所谓的城市道路网区域,是指城市道路网中的指定区域。这些指定区域,可以为基于城市道路网,随机划分的所述城市道路网中的若干区域,或者还可以为以指定间隔距离,对城市道路网进行划分,所生成的所述城市道路网中的若干个城市道路网区域,本实施例对此不进行特别限定。
可选地,在本实施例的一个可能的实现方式中,在102中,具体可以根据所述查询数据所包括的出发地点,获得所述出发地点所属的城市道路网区域,以及根据所述查询数据所包括的目的地点,获得所述目的地点所属的城市道路网区域。然后,根据所述出发地点所属的城市道路网区域和所述目的地点所属的城市道路网区域,在城市道路网中进行路段匹配处理,以获得匹配的M个路段序列。这些路段序列中每个路段序列中所包括的路段,都是从所述出发地点所属的城市道路网区域到所述目的地点所属的城市道路网区域依次联通的路段即首位相连的路段。这样,由于将本次查询的查询起点和本次查询的查询终点的范围扩大了,使得查询起点不再局限于查询数据所包括的出发地点,查询终点也不再局限于查询数据所包括的目的地点,因此,能够获得更多匹配的路段序列,从而更加丰富了路径查询操作依据的数据处理来源。
其中,所采用的路段匹配处理的具体方法,可以采用现有技术中的各种方法,详细描述可以参见现有技术中的相关内容,此处不再赘述。
可选地,在本实施例的一个可能的实现方式中,在103中,具体可以根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹,进而,则可以获得所述至少一个用户历史轨迹中每个用户历史轨迹所对应的历史路段序列。接着,可以根据所述每个用户历史轨迹所对应的历史路段序列,获得通过所述历史路段序列所包括的每个路段的第一轨迹数量,以及通过该路段之后再通过该路段的每个相邻路段的第二路径数量。然后,则可以根据所述第一轨迹数量和所述第二轨迹数量,获得所述历史路段序列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转移概率。例如,将第二路径数量与第一路径数量的比值即 第二路径数量/第一路径数量,作为所述历史路段序列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转移概率。
这样,则可以获得城市道路网中用户历史轨迹所对应的每个路段向该路段的每个相邻路段可达所述目的地点的转移概率,而城市道路网络中的其他路段向该路段的每个相邻路段可达所述目的地点的转移概率则可以记为0。
所谓的用户历史轨迹,是由用户的若干个轨迹点组成的集合。在本发明中,可以将用户历史轨迹匹配到城市道路网中的路段,执行后续的路径查询操作。具体的匹配方法,可以采用现有技术中的匹配算法,例如,隐马尔科夫模型等,详细描述可以参见现有技术中的相关内容,此处不再赘述。
类似地,在该实现方式中,也可以采用上述的地点扩展方法,对目的地点进行扩展。具体地,具体可以根据所述目的地点,获得所述目的地点所属的城市道路网区域,进而,则可以根据所述目的地点所属的城市道路网区域,获得到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹,以作为所述到达所述目的地点的至少一个用户历史轨迹。这样,由于将本次查询的查询终点的范围扩大了,使得查询终点不再局限于目的地点,因此,能够获得更多的用户历史轨迹,作为路径查询操作依据,从而更加丰富了路径查询操作依据的数据来源。
所谓的“到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹”,可以是指经过或通过所述目的地点所属的城市道路网区域,并且继续向其他地点移动的用户历史轨迹,或者还可以是以所述目的地点所属的城市道路网区域为终点不再继续向其他地点移动的用户历史轨 迹,本实施例对此不进行特别限定。
在一个具体的实现过程中,可以将到达每个城市道路网区域的这些用户历史轨迹所对应的路段,组成一个单独的独立道路网络,该独立道路网络中,每条用户历史轨迹都能够到达该城市道路网区域。若是经过或通过某个城市道路网区域,并且继续向其他城市道路网区域移动的用户历史轨迹,那么,在独立道路网络中,可以将所述某个城市道路网区域之后的部分路径删除,以使得该独立道路网络中的每条用户历史轨迹的终点都为所述某个城市道路网区域。
为了提高路径查询操作的效率,可以利用该独立道路网络对这些用户历史轨迹所对应的路段进行索引。这样,在根据某个城市道路网区域,查询到达该城市道路网区域的至少一个用户历史轨迹的时候,直接根据索引进行查询即可,能够有效提高路径查询操作的效率。
可选地,在本实施例的一个可能的实现方式中,在103中,具体可以根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,获得所述每个路段序列的联合概率。然后,则可以根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果。
该实现方式中,假设一个路段序列包括n个路段即从出发地点(即出发地点所属的城市道路网区域)到目的地点(即目的地点所属的城市道路网区域)依次为link1、link2、……linkn-1、linkn,n为大于或等于2的整数。将linkn-1到linkn的转移概率,记为Plinkn,该路段序列的联合概率可以为所有转移概率的乘积,可以记为∏n i=2Plinkn
在一个具体的实现过程中,具体可以将联合概率最大的N个路段序 列,作为所述路径查询结果。例如,具体可以按照联合概率从大到小的顺序,对全部的路段序列进行排序,选择排在前面的N个路段序列,作为所述路径查询操作的查询结果
在另一个具体的实现过程中,具体可以将联合概率大于或等于预先设置的概率阈值的路段序列,作为所述N个路段序列中的一个路段序列。
本实施例中,通过获取查询数据,所述查询数据包括出发地点和目的地点,进而根据所述查询数据,获得M个路段序列,使得能够根据每个路段序列所包括的至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,由于不再依赖道路权重执行路径查询操作,因此,能够避免现有技术中由于某些道路的道路权重无法及时更新而导致的查询结果不合理的问题,从而提高了路径查询操作的可靠性。
另外,采用本发明所提供的技术方案,由于采用了用户历史轨迹这一轨迹大数据执行路径查询操作,使得能够发现用户的经验路线,可以提供更加合理的查询结果,例如,发现新道路、躲避拥堵道路等,能够极大提升用户体验。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明并不受所描述的动作顺序的限制,因为依据本发明,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本发明所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中 没有详述的部分,可以参见其他实施例的相关描述。
图2为本发明另一实施例提供的路径查询装置的结构示意图,如图2所示。本实施例的路径查询装置可以包括获取单元21、匹配单元22、选择单元23和输出单元24。其中,获取单元21,用于获取查询数据,所述查询数据包括出发地点和目的地点;匹配单元22,用于根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;选择单元23,用于根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;输出单元24,用于输出所述路径查询结果。
需要说明的是,本实施例所提供的路径查询装置的部分或全部可以为位于本地终端的应用,或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(Software Development Kit,SDK)等功能单元,或者还可以为位于网络侧服务器中的查询引擎,或者还可以为位于网络侧的分布式系统,本实施例对此不进行特别限定。
可以理解的是,所述应用可以是安装在终端上的本地程序(nativeApp),或者还可以是终端上的浏览器的一个网页程序(webApp),本实施例对此不进行限定。
可选地,在本实施例的一个可能的实现方式中,如图3所示,本实施例所提供的路径查询装置还可以进一步包括处理单元31,用于根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹;获得所述至少一个用户历史轨迹中每个用户历史轨迹所对应的历史路段序列; 根据所述每个用户历史轨迹所对应的历史路段序列,获得通过所述历史路段序列所包括的每个路段的第一轨迹数量,以及通过该路段之后再通过该路段的每个相邻路段的第二路径数量;以及根据所述第一轨迹数量和所述第二轨迹数量,获得所述历史路段序列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转移概率。
具体地,所述处理单元31具体可以根据所述目的地点,获得所述目的地点所属的城市道路网区域;以及根据所述目的地点所属的城市道路网区域,获得到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹,以作为所述到达所述目的地点的至少一个用户历史轨迹。
可选地,在本实施例的一个可能的实现方式中,如图4所示,本实施例所提供的路径查询装置还可以进一步包括划分单元41,用于以指定间隔距离,对城市道路网进行划分,生成所述城市道路网中的若干个城市道路网区域。
可选地,在本实施例的一个可能的实现方式中,所述选择单元23,具体可以用于根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,获得所述每个路段序列的联合概率;以及根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果。
在一个具体的实现过程中,所述选择单元23,具体可以用于将联合概率最大的N个路段序列,作为所述路径查询结果。
在另一个具体的实现过程中,所述选择单元23,具体可以用于将联合概率大于或等于预先设置的概率阈值的路段序列,作为所述N个路段序列中的一个路段序列。
需要说明的是,图1对应的实施例中方法,可以由本实施例提供的路径查询装置实现。详细描述可以参见图1对应的实施例中的相关内容,此处不再赘述。
本实施例中,通过获取单元获取查询数据,所述查询数据包括出发地点和目的地点,进而由匹配单元根据所述查询数据,获得M个路段序列,使得选择单元能够根据每个路段序列所包括的至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,由于不再依赖道路权重执行路径查询操作,因此,能够避免现有技术中由于某些道路的道路权重无法及时更新而导致的查询结果不合理的问题,从而提高了路径查询操作的可靠性。
另外,采用本发明所提供的技术方案,由于采用了用户历史轨迹这一轨迹大数据执行路径查询操作,使得能够发现用户的经验路线,可以提供更加合理的查询结果,例如,发现新道路、躲避拥堵道路等,能够极大提升用户体验。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本发明所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所 显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用以使得一台计算机装置(可以是个人计算机,服务器,或者网络装置等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,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精神和 范围。

Claims (14)

  1. 一种路径查询方法,其特征在于,包括:
    获取查询数据,所述查询数据包括出发地点和目的地点;
    根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
    根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
    输出所述路径查询结果。
  2. 根据权利要求1所述的方法,其特征在于,所述根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果之前,还包括:
    根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹;
    获得所述至少一个用户历史轨迹中每个用户历史轨迹所对应的历史路段序列;
    根据所述每个用户历史轨迹所对应的历史路段序列,获得通过所述历史路段序列所包括的每个路段的第一轨迹数量,以及通过该路段之后再通过该路段的每个相邻路段的第二路径数量;
    根据所述第一轨迹数量和所述第二轨迹数量,获得所述历史路段序列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转 移概率。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹,包括:
    根据所述目的地点,获得所述目的地点所属的城市道路网区域;
    根据所述目的地点所属的城市道路网区域,获得到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹,以作为所述到达所述目的地点的至少一个用户历史轨迹。
  4. 根据权利要求3所述的方法,其特征在于,所述根据所述目的地点,获得所述目的地点所属的城市道路网区域之前,还包括:
    以指定间隔距离,对城市道路网进行划分,生成所述城市道路网中的若干个城市道路网区域。
  5. 根据权利要求1~4任一权利要求所述的方法,其特征在于,所述根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,包括:
    根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,获得所述每个路段序列的联合概率;
    根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果。
  6. 根据权利要求5所述的方法,其特征在于,所述根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果,包括:
    将联合概率最大的N个路段序列,作为所述路径查询结果;或者
    将联合概率大于或等于预先设置的概率阈值的路段序列,作为所述N个路段序列中的一个路段序列。
  7. 一种路径查询装置,其特征在于,包括:
    获取单元,用于获取查询数据,所述查询数据包括出发地点和目的地点;
    匹配单元,用于根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
    选择单元,用于根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
    输出单元,用于输出所述路径查询结果。
  8. 根据权利要求7所述的装置,其特征在于,所述装置还包括处理单元,用于
    根据所述目的地点,获得到达所述目的地点的至少一个用户历史轨迹;
    获得所述至少一个用户历史轨迹中每个用户历史轨迹所对应的历史路段序列;
    根据所述每个用户历史轨迹所对应的历史路段序列,获得通过所述历史路段序列所包括的每个路段的第一轨迹数量,以及通过该路段之后再通过该路段的每个相邻路段的第二路径数量;以及
    根据所述第一轨迹数量和所述第二轨迹数量,获得所述历史路段序 列所包括的每个路段转向该路段的每个相邻路段可达所述目的地点的转移概率。
  9. 根据权利要求8所述的装置,其特征在于,所述处理单元,具体用于
    根据所述目的地点,获得所述目的地点所属的城市道路网区域;以及
    根据所述目的地点所属的城市道路网区域,获得到达所述目的地点所属的城市道路网区域的至少一个用户历史轨迹,以作为所述到达所述目的地点的至少一个用户历史轨迹。
  10. 根据权利要求9所述的装置,其特征在于,所述装置还包括划分单元,用于
    以指定间隔距离,对城市道路网进行划分,生成所述城市道路网中的若干个城市道路网区域。
  11. 根据权利要求7~10任一权利要求所述的装置,其特征在于,所述选择单元,具体用于
    根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,获得所述每个路段序列的联合概率;以及
    根据所述每个路段序列的联合概率,从M个路段序列中选择N个路段序列,以作为路径查询结果。
  12. 根据权利要求11所述的装置,其特征在于,所述选择单元,具体用于
    将联合概率最大的N个路段序列,作为所述路径查询结果;或者
    将联合概率大于或等于预先设置的概率阈值的路段序列,作为所述N个路段序列中的一个路段序列。
  13. 一种设备,包括:
    一个或者多个处理器;
    存储器;
    一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时:
    获取查询数据,所述查询数据包括出发地点和目的地点;
    根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
    根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
    输出所述路径查询结果。
  14. 一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
    获取查询数据,所述查询数据包括出发地点和目的地点;
    根据所述查询数据,获得M个路段序列,所述M个路段序列中每个路段序列包括至少一个路段;M为大于或等于2的整数;
    根据所述每个路段序列所包括的所述至少一个路段中每个路段转向该路段的相邻路段可达所述目的地点的转移概率,从M个路段序列中选 择N个路段序列,以作为路径查询结果;N为大于或等于1且小于或等于M的整数;
    输出所述路径查询结果。
PCT/CN2015/098278 2015-09-30 2015-12-22 路径查询方法、装置、设备及非易失性计算机存储介质 WO2017054332A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
US15/765,204 US20190056235A1 (en) 2015-09-30 2015-12-22 Path querying method and device, an apparatus and non-volatile computer storage medium
KR1020187009021A KR102015235B1 (ko) 2015-09-30 2015-12-22 경로조회 방법, 장치, 디바이스 및 비휘발성 컴퓨터 기억 매체
EP15905242.2A EP3358474B1 (en) 2015-09-30 2015-12-22 Route search method, device and apparatus, and non-volatile computer storage medium
JP2018516192A JP6613475B2 (ja) 2015-09-30 2015-12-22 経路照会方法、装置、デバイス及び不揮発性コンピューター記憶媒体

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510639503.8 2015-09-30
CN201510639503.8A CN105354221A (zh) 2015-09-30 2015-09-30 路径查询方法及装置

Publications (1)

Publication Number Publication Date
WO2017054332A1 true WO2017054332A1 (zh) 2017-04-06

Family

ID=55330194

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/098278 WO2017054332A1 (zh) 2015-09-30 2015-12-22 路径查询方法、装置、设备及非易失性计算机存储介质

Country Status (6)

Country Link
US (1) US20190056235A1 (zh)
EP (1) EP3358474B1 (zh)
JP (1) JP6613475B2 (zh)
KR (1) KR102015235B1 (zh)
CN (1) CN105354221A (zh)
WO (1) WO2017054332A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111078810A (zh) * 2019-11-29 2020-04-28 北京三快在线科技有限公司 经验路线生成方法和装置、存储介质和电子设备
CN111222059A (zh) * 2020-01-17 2020-06-02 西安交通大学 一种城市可达区域搜索系统及方法

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108304235B (zh) * 2017-02-20 2020-09-29 腾讯科技(深圳)有限公司 页面显示方法和装置
CN109493592B (zh) * 2017-09-11 2021-03-26 腾讯科技(深圳)有限公司 路径推荐方法及装置
CN107643085B (zh) * 2017-09-18 2021-02-12 苏州大学 一种路径推荐方法与装置
CN112394380B (zh) * 2019-08-16 2024-04-02 阿里巴巴集团控股有限公司 一种数据处理方法、装置及系统
CN110542428B (zh) * 2019-08-27 2021-06-15 腾讯科技(深圳)有限公司 驾驶路线质量评估方法及装置
CN114065992A (zh) * 2020-08-05 2022-02-18 北京三快在线科技有限公司 路线规划和订单推荐的方法、装置、电子设备及存储介质
CN114419357B (zh) * 2022-03-10 2022-06-21 腾讯科技(深圳)有限公司 数据处理方法、装置、计算机及可读存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103512581A (zh) * 2012-06-28 2014-01-15 北京搜狗科技发展有限公司 一种路径规划方法和装置
CN104165625A (zh) * 2013-05-17 2014-11-26 北京百度网讯科技有限公司 路径规划方法和设备
CN104536986A (zh) * 2014-12-08 2015-04-22 安一恒通(北京)科技有限公司 路径查询方法及装置

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1330937C (zh) * 2001-08-06 2007-08-08 松下电器产业株式会社 信息提供方法
JP3882554B2 (ja) * 2001-09-17 2007-02-21 日産自動車株式会社 ナビゲーション装置
GB0518617D0 (en) * 2005-09-13 2005-10-19 Hopkins Mark Network message and alert selection apparatus and method
US7893849B2 (en) * 2005-10-20 2011-02-22 Poltorak Alexander I Apparatus and method for providing travel information
US7610151B2 (en) * 2006-06-27 2009-10-27 Microsoft Corporation Collaborative route planning for generating personalized and context-sensitive routing recommendations
US7783417B2 (en) * 2007-03-09 2010-08-24 Mitac International Corporation Methods and apparatus for determining a route having an estimated minimum fuel usage for a vehicle
CN101349566A (zh) * 2007-07-19 2009-01-21 康佳集团股份有限公司 一种车辆实时导航方法及系统
CN101493329B (zh) * 2008-01-23 2011-04-27 华东师范大学 一种多目标点路径规划方法和装置
US8478642B2 (en) * 2008-10-20 2013-07-02 Carnegie Mellon University System, method and device for predicting navigational decision-making behavior
EP2443418B1 (en) * 2009-06-16 2018-12-05 TomTom North America Inc. Methods and systems for creating digital street network database
JP5495014B2 (ja) * 2009-09-09 2014-05-21 ソニー株式会社 データ処理装置、データ処理方法、およびプログラム
JP2011252844A (ja) * 2010-06-03 2011-12-15 Sony Corp データ処理装置、データ処理方法、およびプログラム
US8645061B2 (en) * 2010-06-16 2014-02-04 Microsoft Corporation Probabilistic map matching from a plurality of observational and contextual factors
JP5182336B2 (ja) * 2010-08-02 2013-04-17 株式会社デンソー 運転特性特定装置および経路探索装置
CN103443584A (zh) * 2011-03-25 2013-12-11 索尼公司 信息处理设备、信息处理方法和程序
CN102288193B (zh) * 2011-07-06 2013-06-26 东南大学 一种基于历史数据的机动车出行路径的确定方法
US20130054050A1 (en) * 2011-08-24 2013-02-28 Dimitar Petrov Filev Methods and apparatus for a vehicle to cloud to vehicle control system
DE102011083375A1 (de) * 2011-09-26 2013-03-28 Robert Bosch Gmbh Verfahren zur Übermittlung von Routendaten für die Verkehrstelematik
CN103487057B (zh) * 2013-10-08 2016-10-12 百度在线网络技术(北京)有限公司 基于端点扩展的路径规划方法及装置
US9091561B1 (en) * 2013-10-28 2015-07-28 Toyota Jidosha Kabushiki Kaisha Navigation system for estimating routes for users
CN104537836B (zh) * 2014-12-30 2016-11-30 北京通博科技有限公司 路段行驶时间分布预测方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103512581A (zh) * 2012-06-28 2014-01-15 北京搜狗科技发展有限公司 一种路径规划方法和装置
CN104165625A (zh) * 2013-05-17 2014-11-26 北京百度网讯科技有限公司 路径规划方法和设备
CN104536986A (zh) * 2014-12-08 2015-04-22 安一恒通(北京)科技有限公司 路径查询方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3358474A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111078810A (zh) * 2019-11-29 2020-04-28 北京三快在线科技有限公司 经验路线生成方法和装置、存储介质和电子设备
CN111222059A (zh) * 2020-01-17 2020-06-02 西安交通大学 一种城市可达区域搜索系统及方法
CN111222059B (zh) * 2020-01-17 2023-03-28 西安交通大学 一种城市可达区域搜索系统及方法

Also Published As

Publication number Publication date
US20190056235A1 (en) 2019-02-21
EP3358474A1 (en) 2018-08-08
EP3358474A4 (en) 2018-12-05
CN105354221A (zh) 2016-02-24
KR102015235B1 (ko) 2019-10-21
KR20180048893A (ko) 2018-05-10
EP3358474B1 (en) 2021-09-08
JP6613475B2 (ja) 2019-12-04
JP2018531379A (ja) 2018-10-25

Similar Documents

Publication Publication Date Title
WO2017054332A1 (zh) 路径查询方法、装置、设备及非易失性计算机存储介质
CN108038183B (zh) 结构化实体收录方法、装置、服务器和存储介质
US20200349175A1 (en) Address Search Method and Device
CN107609101B (zh) 智能交互方法、设备及存储介质
CN107797984B (zh) 智能交互方法、设备及存储介质
US9690806B2 (en) Method and apparatus of recommending candidate terms based on geographical location
US8965974B2 (en) Systems and methods for determining user attribute values by mining user network data and information
JP2018531379A6 (ja) 経路照会方法、装置、デバイス及び不揮発性コンピューター記憶媒体
US10783885B2 (en) Image display device, method for driving the same, and computer readable recording medium
TW201604698A (zh) 一種軌跡資訊的推送方法及裝置
CN109416695A (zh) 在自动聊天中提供本地服务信息
WO2012001096A2 (en) Method and system for using an information system
WO2016045567A1 (zh) 网页数据分析方法及装置
CN102955821A (zh) 一种对查询序列进行扩展处理的方法与设备
KR102601545B1 (ko) 지리 위치점 정렬 방법, 정렬 모델 트레이닝 방법 및 대응하는 장치
JP6728178B2 (ja) 検索データを処理するための方法及び装置
US11893073B2 (en) Method and apparatus for displaying map points of interest, and electronic device
WO2017028395A1 (zh) 一种提供搜索结果的方法与装置
CN106919703A (zh) 电影信息搜索方法及装置
CN103955480A (zh) 一种用于确定用户所对应的目标对象信息的方法与设备
CN108319628A (zh) 一种用户兴趣确定方法及装置
CN105243131B (zh) 路径查询方法及装置
CN115062150B (zh) 一种文本分类方法、装置、电子设备及存储介质
US10511556B2 (en) Bursty detection for message streams
CN113094604B (zh) 搜索结果排序方法、搜索方法及装置

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: 15905242

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2018516192

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 20187009021

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2015905242

Country of ref document: EP