[go: up one dir, main page]

CN114881568A - Method, apparatus, electronic device, and medium for aligning route data and monitoring path - Google Patents

Method, apparatus, electronic device, and medium for aligning route data and monitoring path Download PDF

Info

Publication number
CN114881568A
CN114881568A CN202210557664.2A CN202210557664A CN114881568A CN 114881568 A CN114881568 A CN 114881568A CN 202210557664 A CN202210557664 A CN 202210557664A CN 114881568 A CN114881568 A CN 114881568A
Authority
CN
China
Prior art keywords
road
candidate
route information
information
road network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210557664.2A
Other languages
Chinese (zh)
Other versions
CN114881568B (en
Inventor
任朝淦
张钧波
郑宇�
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.)
Jingdong City Beijing Digital Technology Co Ltd
Original Assignee
Jingdong City Beijing Digital Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jingdong City Beijing Digital Technology Co Ltd filed Critical Jingdong City Beijing Digital Technology Co Ltd
Priority to CN202210557664.2A priority Critical patent/CN114881568B/en
Publication of CN114881568A publication Critical patent/CN114881568A/en
Application granted granted Critical
Publication of CN114881568B publication Critical patent/CN114881568B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/08Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083Shipping
    • G06Q10/0832Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9537Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047Optimisation of routes or paths, e.g. travelling salesman problem
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/08Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083Shipping
    • G06Q10/0835Relationships between shipper or supplier and carriers
    • G06Q10/08355Routing methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Software Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The present disclosure relates to a method, an apparatus, an electronic device, and a medium for aligning route data and monitoring a path, wherein the method for aligning route data includes: determining candidate road networks associated with the planned route information from a road network road library according to the planned route information of a driving object; calculating the probability of each route between adjacent road sections according to the distance between each candidate road network road of the adjacent road sections to obtain a probability matrix containing the probability of all the routes between the adjacent road sections; and performing beam search processing on the probability matrix to obtain target route information in the road network. The method can be applied to the transportation route supervision of dangerous chemical substance vehicles or the scene that artificial intelligence equipment generates the planned route of the actual road network based on voice/character input, realizes the alignment of the planned route information which possibly has errors or deviations to the road network information which actually exists, and can overcome the problem that the actual road cannot be matched due to input errors or non-specification.

Description

对齐路线数据和路径监测的方法、装置、电子设备及介质Method, apparatus, electronic device and medium for aligning route data and path monitoring

技术领域technical field

本公开涉及市域治理和车辆监管技术领域,尤其涉及一种对齐路线数据和路径监测的方法、装置、电子设备及介质。The present disclosure relates to the technical field of city management and vehicle supervision, and in particular, to a method, device, electronic device and medium for aligning route data and route monitoring.

背景技术Background technique

在市域治理过程中,需要对一些运输危化品的车辆的行驶路径进行监管。例如:在XX市危化品车辆监管的场景中,运输剧毒危化品的车辆在出发前需要运输人员或相关人员通过在监管应用输入填报或者通过手工填写请示单的方式,将计划行驶的路线信息上报给监管部门进行备案。In the process of urban governance, it is necessary to supervise the driving paths of some vehicles transporting hazardous chemicals. For example: in the scene of the supervision of hazardous chemicals vehicles in XX City, before departure, the vehicles transporting highly toxic and hazardous chemicals need transport personnel or related personnel to fill in the report in the supervision application or manually fill in the request form to transfer the planned driving The route information is reported to the regulatory authority for recordation.

然而,目前针对上报的人为输入的路线信息,如果人为输入的路线信息中存在填写错误或者是根据人为的不规范叫法进行输入时,监管应用或其后台或者人工是无法确认该车辆上报的路线信息对应于实际路网中的哪一个路网道路构成的路线,也就导致无法对上述车辆进行有效的监管。However, at present, for the reported route information entered by humans, if there is an error in the input route information or the input is based on human irregular names, the supervision application or its background or manual cannot confirm the route reported by the vehicle. The information corresponds to which road network road in the actual road network constitutes the route, which makes it impossible to effectively supervise the above-mentioned vehicles.

发明内容SUMMARY OF THE INVENTION

为了解决上述技术问题或者至少部分地解决上述技术问题,本公开的实施例提供了一种对齐路线数据和路径监测的方法、装置、电子设备及介质。In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a method, apparatus, electronic device and medium for aligning route data and path monitoring.

第一方面,本公开的实施例提供了一种对齐路线数据的方法。上述对齐路线数据的方法包括:根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路;根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵;以及对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。In a first aspect, embodiments of the present disclosure provide a method of aligning route data. The above method for aligning route data includes: according to the planned route information of the driving object, determining candidate road network roads associated with the above-mentioned planned route information from the road network road database; Calculate the probability of each route between adjacent road sections to obtain a probability matrix including the probabilities of the routes between all adjacent road sections; and perform beam search processing on the above probability matrix to obtain target route information in the road network.

根据本公开的实施例,上述根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵,包括:针对所有路段中的任意一个路段,计算当前路段的候选路网道路与下一路段的候选路网道路两两之间的距离,得到由当前路段对应的距离元素构成的距离向量;根据所有路段的距离向量,得到距离矩阵;对上述距离矩阵中每行的距离向量进行数值变换,得到变换后的目标距离向量,变换前后相应的距离元素之间的总和为一固定值;将每个目标距离向量输入至软最大化函数中进行处理,输出得到上述目标距离向量中各个距离元素对应的概率分布值,其中当前距离元素对应的概率分布值用于表征上述当前距离元素对应的路线的概率;根据所有目标距离向量对应得到的概率分布值,得到包含所有相邻路段之间路线的概率的概率矩阵。According to the embodiment of the present disclosure, the probability of each route between adjacent road segments is calculated according to the distance between each candidate road network road of the adjacent road segment, and the probability matrix including the probabilities of the route between all adjacent road segments is obtained. , including: calculating the distance between the candidate road network road of the current road segment and the candidate road network road of the next road segment for any road segment in all road segments, and obtaining the distance vector formed by the distance elements corresponding to the current road segment; The distance vectors of all road segments are obtained, and the distance matrix is obtained; the distance vector of each row in the above distance matrix is numerically transformed to obtain the transformed target distance vector, and the sum between the corresponding distance elements before and after the transformation is a fixed value; The target distance vector is input into the soft maximization function for processing, and the output obtains the probability distribution value corresponding to each distance element in the above target distance vector, wherein the probability distribution value corresponding to the current distance element is used to represent the above-mentioned current distance element The probability of the corresponding route ; According to the corresponding probability distribution values of all target distance vectors, a probability matrix containing the probabilities of routes between all adjacent road segments is obtained.

根据本公开的实施例,上述根据所有路段的距离向量,得到距离矩阵,包括:将所有路段中各个路段的距离向量作为距离矩阵的各行;将所有路段中距离向量的列数最大值作为上述距离矩阵的列规模,并在列数小于上述列规模的特定距离向量中补充默认值;其中,当对每行的距离向量进行数值变换时,上述默认值不参与计算,采用当前距离向量中的距离元素最大值与各个距离元素作差,得到变换后的距离元素;当对上述目标距离向量输入至软最大化函数中进行处理时,上述默认值对应的输出概率为预设值。According to an embodiment of the present disclosure, obtaining the distance matrix according to the distance vectors of all road segments includes: taking the distance vectors of each road segment in all road segments as each row of the distance matrix; taking the maximum number of columns of the distance vectors in all road segments as the above distance The column scale of the matrix, and the default value is added to the specific distance vector whose number of columns is smaller than the above column scale; among them, when the distance vector of each row is numerically transformed, the above default value does not participate in the calculation, and the distance in the current distance vector is used. The difference between the maximum element value and each distance element is used to obtain the transformed distance element; when the above-mentioned target distance vector is input into the soft maximization function for processing, the output probability corresponding to the above-mentioned default value is a preset value.

根据本公开的实施例,上述对上述概率矩阵进行束搜索处理,得到目标路线信息,包括:针对上述概率矩阵的首行,将当前行中每组相邻路段之间路线的概率的得分最高的前K个所对应的路线确定为候选路线,K为设定搜索束宽;针对上述概率矩阵的首行之后的后续行中的每一行,确定当前行所对应的路线分别在上一行所对应的K个候选路线的前提下的条件概率的得分,并将条件概率的得分在前K个所对应的路线确定为目标候选路线;将上述目标候选路线中得分最大的路线确定为目标路线信息。According to an embodiment of the present disclosure, performing beam search processing on the above-mentioned probability matrix to obtain target route information includes: for the first row of the above-mentioned probability matrix, selecting the route with the highest probability score between each group of adjacent road segments in the current row. The routes corresponding to the first K are determined as candidate routes, and K is the set search beam width; for each row in the subsequent rows after the first row of the above probability matrix, it is determined that the routes corresponding to the current row are respectively in the previous row. Score the conditional probability under the premise of K candidate routes, and determine the route corresponding to the first K of the conditional probability score as the target candidate route; the route with the highest score among the above target candidate routes is determined as the target route information.

根据本公开的实施例,上述规划路线信息包括:依序途经的各个路段构成的序列。其中,上述根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,包括:对上述规划路线信息中的各个路段进行文本提取,得到针对每个路段的路段关键信息;根据上述路段关键信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路。According to an embodiment of the present disclosure, the above-mentioned planned route information includes: a sequence formed by each road segment passed in sequence. Wherein, determining the candidate road network road associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object includes: performing text extraction on each road segment in the above-mentioned planned route information, and obtaining the corresponding road segment for each road segment. According to the key information of the above-mentioned road sections, screening and matching are performed in the road network road library to obtain the candidate road network roads for each road section.

根据本公开的实施例,上述根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,还包括:在不存在与特定路段的路段关键信息相匹配的候选路网道路的情况下,根据与上述特定路段相邻的相邻路段的候选路网道路,在上述路网道路库中确定与上述相邻路段的候选路网道路相交的特定路网道路作为针对上述特定路段的候选路网道路。According to an embodiment of the present disclosure, the above-mentioned determining the candidate road network road associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object further includes: when there is no road segment key information matching the specific road segment In the case of the candidate road network road of , the specific road network road that intersects the candidate road network road of the above-mentioned adjacent road segment is determined in the above-mentioned road network road library according to the candidate road network road of the adjacent road segment adjacent to the above-mentioned specific road segment As a candidate road network road for the above-mentioned specific road segment.

根据本公开的实施例,根据上述路段关键信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路,包括:According to the embodiments of the present disclosure, according to the above key information of road sections, screening and matching are performed in the road network road database to obtain candidate road network roads for each road section, including:

根据路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路;在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,视为不存在与上述特定路段的路段关键信息相匹配的候选路网道路;或者,According to the road segment keyword information, screening and matching are performed in the road network road library to obtain candidate road network roads for each road segment; There is no candidate road network road that matches the key information of the above-mentioned specific road segment; or,

根据路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路;在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,拆分上述特定路段的路段关键词信息为更细粒度化的路段关键字信息;根据上述路段关键字信息,在路网道路库中进行筛选匹配,得到针对上述特定路段的候选路网道路;在不存在与上述特定路段的路段关键字信息相匹配的候选路网道路的情况下,视为不存在与上述特定路段的路段关键信息相匹配的候选路网道路。According to the road segment keyword information, screening and matching are performed in the road network road database to obtain candidate road network roads for each road segment; The road segment keyword information of the above-mentioned specific road segment is classified into more fine-grained road segment keyword information; according to the above-mentioned road segment keyword information, screening and matching are performed in the road network road database to obtain candidate road network roads for the above-mentioned specific road segment; If there is a candidate road network road matching the link key information of the specific link, it is considered that there is no candidate road network matching the link key information of the specific link.

第二方面,本公开的实施例提供了一种路径监测的方法。上述路径监测的方法包括:采用如上所述的对齐路线数据的方法来确定行驶对象的目标路线信息;获取上述行驶对象的实际路线信息;对上述实际路线信息与上述目标路线信息进行匹配;在上述实际路线信息与上述目标路线信息不匹配的情况下,生成路线偏离的预警信息。In a second aspect, embodiments of the present disclosure provide a method for path monitoring. The above-mentioned path monitoring method includes: using the above-mentioned method for aligning route data to determine target route information of a traveling object; acquiring actual route information of the above-mentioned traveling object; matching the above-mentioned actual route information with the above-mentioned target route information; When the actual route information does not match the above-mentioned target route information, warning information of route deviation is generated.

第三方面,本公开的实施例提供了一种对齐路线数据的装置。上述对齐路线数据的装置包括:路网匹配模块、概率计算模块和处理模块。上述路网匹配模块用于根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路。上述概率计算模块用于根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵。上述处理模块用于对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。In a third aspect, embodiments of the present disclosure provide an apparatus for aligning route data. The above-mentioned apparatus for aligning route data includes: a road network matching module, a probability calculation module and a processing module. The above-mentioned road network matching module is used for determining candidate road network roads associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object. The above probability calculation module is used to calculate the probability of each route between adjacent road segments according to the distance between each candidate road network road of adjacent road segments, and obtain a probability matrix including the probabilities of routes between all adjacent road segments. The above-mentioned processing module is used to perform beam search processing on the above-mentioned probability matrix to obtain target route information in the road network.

第四方面,本公开的实施例提供了一种路径监测的装置。上述装置包括:路网匹配模块、概率计算模块、处理模块、实际路线获取模块、路线信息匹配模块和预警信息生成模块。上述路网匹配模块用于根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路。上述概率计算模块用于根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵。上述处理模块用于对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。上述实际路线获取模块用于获取上述行驶对象的实际路线信息。上述路线信息匹配模块用于对上述实际路线信息与上述目标路线信息进行匹配。上述预警信息生成模块用于在上述实际路线信息与上述目标路线信息不匹配的情况下,生成路线偏离的预警信息。In a fourth aspect, an embodiment of the present disclosure provides an apparatus for path monitoring. The above device includes: a road network matching module, a probability calculation module, a processing module, an actual route acquisition module, a route information matching module and an early warning information generation module. The above-mentioned road network matching module is used for determining candidate road network roads associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object. The above probability calculation module is used to calculate the probability of each route between adjacent road segments according to the distance between each candidate road network road of adjacent road segments, and obtain a probability matrix including the probabilities of routes between all adjacent road segments. The above-mentioned processing module is used to perform beam search processing on the above-mentioned probability matrix to obtain target route information in the road network. The above-mentioned actual route obtaining module is used to obtain the actual route information of the above-mentioned driving object. The above-mentioned route information matching module is used for matching the above-mentioned actual route information with the above-mentioned target route information. The above-mentioned early warning information generating module is configured to generate early warning information of route deviation when the above-mentioned actual route information does not match the above-mentioned target route information.

第五方面,本公开的实施例提供了一种电子设备。上述电子设备包括处理器、通信接口、存储器和通信总线,其中,处理器、通信接口和存储器通过通信总线完成相互间的通信;存储器,用于存放计算机程序;处理器,用于执行存储器上所存放的程序时,实现如上所述的对齐路线数据的方法或路径监测的方法。In a fifth aspect, embodiments of the present disclosure provide an electronic device. The above-mentioned electronic equipment includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus; the memory is used to store computer programs; In the stored program, the method of aligning route data or the method of path monitoring as described above is implemented.

第六方面,本公开的实施例提供了一种计算机可读存储介质。上述计算机可读存储介质上存储有计算机程序,上述计算机程序被处理器执行时实现如上所述的对齐路线数据的方法或路径监测的方法。In a sixth aspect, embodiments of the present disclosure provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the method for aligning route data or the method for path monitoring as described above is implemented.

本公开实施例提供的上述技术方案至少具有如下优点的部分或全部:The foregoing technical solutions provided by the embodiments of the present disclosure have at least some or all of the following advantages:

通过根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息相关联的候选路网道路;在规划路线信息存在错误或偏差的情况下,上述关联的候选路网道路能够作为一个或多个候选的关联选项,从而在后续确定目标路线信息时,进一步根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵;通过对上述概率矩阵进行束搜索处理,能够在每个路段的一个或多个候选路网道路中选择出最贴近正确状态的规划路线信息的目标路线信息,实现了将可能存在错误的规划路线信息(例如为人工语音或文本输入的信息中存在错误或偏差、电子设备下发的规划路线信息中存在错误或偏差等场景)向现实存在的路网信息的对齐,并能够一定程度上克服由于填写、输入错误或不规范导致的无法匹配实际道路的问题;在应用场景中,能够基于上述目标路线信息来对用户的实际路线进行监管和预警提示,可以应用至市域治理危化品车辆的运输路线监管的场景或者人工智能设备基于语音/文字输入生成实际路网的规划路线的场景中。The candidate road network road associated with the above-mentioned planned route information is determined from the road network road library according to the planned route information of the driving object; in the case of errors or deviations in the planned route information, the above-mentioned candidate road network road can be used as the One or more candidate association options, so that when the target route information is subsequently determined, the probability of each route between adjacent road segments is further calculated according to the distance between each candidate road network road in adjacent road segments, and all The probability matrix of the probabilities of routes between adjacent road sections; by performing beam search processing on the above probability matrix, the target route that is closest to the planned route information in the correct state can be selected from one or more candidate road network roads of each road section information, realizes the possibility of erroneous planning route information (for example, there are errors or deviations in the information entered for artificial voice or text, there are errors or deviations in the planned route information issued by electronic devices, etc.) to the actual road network. Alignment of information, and can overcome the problem of inability to match the actual road due to filling, input errors or irregularities to a certain extent; in the application scenario, the actual route of the user It can be applied to the scene of the supervision of the transportation route of the vehicle for the management of hazardous chemicals in the city or the scene of the artificial intelligence device generating the planned route of the actual road network based on the voice/text input.

附图说明Description of drawings

此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本公开的实施例,并与说明书一起用于解释本公开的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.

为了更清楚地说明本公开实施例或现有技术中的技术方案,下面将对实施例或相关技术描述中所需要使用的附图作简单地介绍,显而易见地,对于本领域普通技术人员而言,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。In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or related technologies. It is obvious to those skilled in the art that , on the premise of no creative labor, other drawings can also be obtained from these drawings.

图1示意性地示出了适用于本公开实施例的对齐路线数据的方法和路径监测的方法的系统架构;FIG. 1 schematically shows a system architecture of a method for aligning route data and a method for path monitoring applicable to an embodiment of the present disclosure;

图2示意性地示出了根据本公开实施例的对齐路线数据的方法的流程图;FIG. 2 schematically shows a flowchart of a method for aligning route data according to an embodiment of the present disclosure;

图3A示意性地示出了根据本公开一实施例的操作S201的详细实施流程图;FIG. 3A schematically shows a detailed implementation flowchart of operation S201 according to an embodiment of the present disclosure;

图3B示意性地示出了根据本公开另一实施例的操作S201的详细实施流程图;FIG. 3B schematically shows a detailed implementation flowchart of operation S201 according to another embodiment of the present disclosure;

图3C示意性地示出了根据本公开又一实施例的操作S201的详细实施流程图;FIG. 3C schematically shows a detailed implementation flowchart of operation S201 according to yet another embodiment of the present disclosure;

图3D示意性地示出了根据本公开再一实施例的操作S201的详细实施流程图;FIG. 3D schematically shows a detailed implementation flowchart of operation S201 according to still another embodiment of the present disclosure;

图4示意性地示出了根据本公开实施例的操作S202的详细实施流程图;FIG. 4 schematically shows a detailed implementation flowchart of operation S202 according to an embodiment of the present disclosure;

图5示意性地示出了根据本公开实施例的操作S203的详细实施流程图;FIG. 5 schematically shows a detailed implementation flowchart of operation S203 according to an embodiment of the present disclosure;

图6示意性地示出了根据本公开实施例的路径监测的方法的流程图;FIG. 6 schematically shows a flow chart of a method for path monitoring according to an embodiment of the present disclosure;

图7示意性地示出了根据本公开实施例的对齐路线数据的装置的结构框图;7 schematically shows a structural block diagram of an apparatus for aligning route data according to an embodiment of the present disclosure;

图8示意性地示出了根据本公开实施例的路径监测的装置的结构框图;以及FIG. 8 schematically shows a structural block diagram of an apparatus for path monitoring according to an embodiment of the present disclosure; and

图9示意性地示出了本公开实施例提供的电子设备的结构框图。FIG. 9 schematically shows a structural block diagram of an electronic device provided by an embodiment of the present disclosure.

具体实施方式Detailed ways

本公开的实施例提供了一种对齐路线数据和路径监测的方法、装置、电子设备及介质,上述对齐路线数据的方法包括:根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路;根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵;对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。Embodiments of the present disclosure provide a method, device, electronic device, and medium for aligning route data and path monitoring. The above-mentioned method for aligning route data includes: according to the planned route information of the traveling object, determining from a road network road library that is consistent with the above Plan the candidate road network roads associated with the route information; calculate the probability of each route between adjacent road segments according to the distance between each candidate road network road of adjacent road segments, and obtain the probability of the routes between all adjacent road segments. Probability matrix; perform beam search processing on the above probability matrix to obtain target route information in the road network.

上述路径监测的方法包括:采用如上所述的对齐路线数据的方法来确定行驶对象的目标路线信息;获取上述行驶对象的实际路线信息;对上述实际路线信息与上述目标路线信息进行匹配;在上述实际路线信息与上述目标路线信息不匹配的情况下,生成路线偏离的预警信息。The above-mentioned path monitoring method includes: using the above-mentioned method for aligning route data to determine target route information of a traveling object; acquiring actual route information of the above-mentioned traveling object; matching the above-mentioned actual route information with the above-mentioned target route information; When the actual route information does not match the above-mentioned target route information, warning information of route deviation is generated.

上述方法能够实现将可能存在错误的规划路线信息(例如为人工语音或文本输入的信息中存在错误或偏差、电子设备下发的规划路线信息中存在错误或偏差等场景)向现实存在的路网信息的对齐,并能够一定程度上克服由于填写、输入错误或不规范导致的无法匹配实际道路的问题;在应用场景中,能够基于上述目标路线信息来对用户的实际路线进行监管和预警提示,可以应用至市域治理危化品车辆的运输路线监管的场景。The above method can realize that there may be errors in planning route information (for example, there are errors or deviations in the information input by artificial voice or text, and there are errors or deviations in the planned route information issued by electronic devices) to the actual road network. Alignment of information, and can overcome the problem of inability to match the actual road due to filling, input errors or irregularities to a certain extent; in the application scenario, the actual route of the user It can be applied to the scene of the supervision of the transportation route of the vehicles for the management of hazardous chemicals in the city.

为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开的一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments These are some, but not all, embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

图1示意性地示出了适用于本公开实施例的对齐路线数据的方法和路径监测的方法的系统架构。FIG. 1 schematically shows a system architecture of a method for aligning route data and a method for path monitoring applicable to embodiments of the present disclosure.

参照图1所示,适用于本公开实施例的对齐路线数据的方法和路径监测的方法的系统架构100包括:终端设备101、102、103,网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型,例如有线、无线通信链路或者光纤电缆等等。Referring to FIG. 1 , a system architecture 100 suitable for a method for aligning route data and a method for path monitoring according to an embodiment of the present disclosure includes: terminal devices 101 , 102 , and 103 , a network 104 and a server 105 . The network 104 is a medium used to provide a communication link between the terminal devices 101 , 102 , 103 and the server 105 . The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

用户可以使用终端设备101、102、103通过网络104与服务器105交互,以接收或发送消息等。终端设备101、102、103上可以安装有路线监管类应用。The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like. Route supervision applications may be installed on the terminal devices 101 , 102 and 103 .

进一步的,上述终端设备101、102、103上还可以安装有其他通讯客户端应用,例如购物类应用、网页浏览器应用、搜索类应用、视频播放类应用、音乐播放类应用、即时通信工具、邮箱客户端、社交平台软件等(仅为示例)。Further, other communication client applications, such as shopping applications, web browser applications, search applications, video playback applications, music playback applications, instant messaging tools, Email clients, social platform software, etc. (examples only).

终端设备101、102、103可以是具有显示屏,支持语音或文本输入,并且具有定位功能的各种电子设备,例如电子设备包括但不限于车辆(例如为运输危化品的车辆)、智能手机、平板电脑、笔记本电脑、台式计算机、智能手表、智能手环等等。The terminal devices 101, 102, and 103 can be various electronic devices with a display screen, support voice or text input, and have a positioning function, such as electronic devices including but not limited to vehicles (such as vehicles for transporting hazardous chemicals), smart phones , tablets, laptops, desktop computers, smart watches, smart bracelets, and more.

服务器105可以是提供各种服务的服务器,例如为终端设备101、102、103上的路线监管类应用的路线上报和路线对齐功能提供服务支持的后台管理服务器(仅为示例)。后台管理服务器可以对接收到的规划路线信息等数据进行分析和处理,并将处理结果(例如路网道路中的目标路线信息)反馈给终端设备。The server 105 may be a server that provides various services, such as a background management server that provides service support for the route reporting and route alignment functions of route supervision applications on the terminal devices 101 , 102 and 103 (just an example). The background management server can analyze and process the received planned route information and other data, and feed back the processing results (for example, target route information in the road network) to the terminal device.

需要说明的是,本公开实施例所提供的对齐路线数据的方法和路径监测的方法一般可以由服务器105(可以是传统的应用服务器或者云服务器)或具有一定运算能力的终端设备101、102、103执行。It should be noted that the method for aligning route data and the method for path monitoring provided by the embodiments of the present disclosure may generally be performed by the server 105 (which may be a traditional application server or a cloud server) or terminal devices 101, 102, 103 execute.

在一示例性实施场景中,针对运输危化品的车辆上的运输人员或相关人员,需要预先通过路线监管类应用来填入(可以通过文字输入或语音输入的形式填入)规划路线信息(对应的账号权限例如为上传权限和查看自己的数据的权限)。由安装该路线监管类应用的电子设备或对应的服务器执行上述对齐路线数据的方法后,可以得到与规划路线信息对应的路网道路中的目标路线信息。In an exemplary implementation scenario, for the transport personnel or related personnel on the vehicle transporting hazardous chemicals, the planned route information (which can be filled in in the form of text input or voice input) needs to be filled in in advance through a route supervision application. The corresponding account permissions are, for example, upload permissions and permissions to view your own data). After the above-mentioned method for aligning route data is executed by the electronic device or the corresponding server on which the route supervision application is installed, the target route information in the road network road corresponding to the planned route information can be obtained.

该路线监管类应用的管理员能够登录对应的管理员账号来获取所监管区域内所有车辆的目标路线信息。The administrator of the route supervision application can log in to the corresponding administrator account to obtain the target route information of all vehicles in the supervised area.

在一实施例中,上述路线监管类应用可以安装于运输危化品的车辆上,这种情况下,路线监管类应用还可以具有实际路径监测的功能,或者对其他地图导航类应用或者路线监控类应用的数据可以进行访问,从而获取实际路线信息。由服务器或该车辆执行上述路径监测的方法,在实际路线信息与目标路线信息不匹配时,生成路线偏离的预警信息。In one embodiment, the above-mentioned route supervision application may be installed on a vehicle that transports hazardous chemicals. In this case, the route supervision application may also have the function of actual route monitoring, or monitor other map navigation applications or routes. The data of such applications can be accessed to obtain actual route information. The above-mentioned route monitoring method is executed by the server or the vehicle, and when the actual route information does not match the target route information, early warning information of route deviation is generated.

在另一实施例中,上述路线监管类应用可以安装于运输人员或相关人员携带的智能设备上,在运输时运输人员或相关人员可以通过蓝牙连接至车载导航系统,并且由该智能设备或服务器对填报的规划路线信息进行数据处理后得到的目标路线信息作为导航路线的一个选项。In another embodiment, the above-mentioned route supervision application can be installed on a smart device carried by transport personnel or related personnel. During transportation, the transport personnel or related personnel can be connected to the in-vehicle navigation system through Bluetooth, and the smart device or server can be used for transportation. The target route information obtained after data processing of the filled planned route information is used as an option of the navigation route.

尽管以危化品的路径监管作为实施场景的示例,需要说明的是,本公开实施例提供的对齐路线数据的方法不局限于路径监管领域,还可以应用至人工智能设备基于语音/文字输入生成实际路网的规划路线的场景中,或者还可以应用至电子设备下发的规划路线信息中存在错误或偏差场景下的路线对齐。Although the route supervision of hazardous chemicals is used as an example of an implementation scenario, it should be noted that the method for aligning route data provided by the embodiments of the present disclosure is not limited to the field of route supervision, and can also be applied to artificial intelligence devices based on voice/text input to generate In the scenario of the planned route of the actual road network, or it can also be applied to the route alignment in the scenario where there is an error or deviation in the planned route information issued by the electronic device.

例如在仓储物流领域,通过对智能运输机器人通过文字或语音形式输入规划路线信息,输出得到目标路线信息,该目标路线信息可以作为智能运输机器人的运输路径的一个基础,用户可以通过将上述运输路径整体作为智能运输机器人的实际运输路径,或者在上述运输路径上进行个别路段的修改,得到修改后的路径作为智能运输机器人的实际运输路径。For example, in the field of warehousing and logistics, by inputting the planned route information to the intelligent transportation robot in the form of text or voice, and outputting the target route information, the target route information can be used as a basis for the transportation route of the intelligent transportation robot. The whole is used as the actual transportation path of the intelligent transportation robot, or individual road sections are modified on the above transportation path, and the modified path is obtained as the actual transportation path of the intelligent transportation robot.

下面结合附图来对本公开的实施例进行详细介绍。The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

本公开的第一个示例性实施例提供了一种对齐路线数据的方法。The first exemplary embodiment of the present disclosure provides a method of aligning route data.

图2示意性地示出了根据本公开实施例的对齐路线数据的方法的流程图。FIG. 2 schematically shows a flowchart of a method for aligning route data according to an embodiment of the present disclosure.

参照图2所示,本公开实施例提供的对齐路线数据的方法,包括以下操作:S201、S202和S203。该操作S201~S203可由图1所示例的服务器105或终端设备101、102、103来执行。Referring to FIG. 2 , the method for aligning route data provided by an embodiment of the present disclosure includes the following operations: S201 , S202 and S203 . The operations S201 to S203 may be performed by the server 105 or the terminal devices 101 , 102 , and 103 exemplified in FIG. 1 .

在操作S201,根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路。In operation S201, according to the planned route information of the traveling object, a candidate road network road associated with the above-mentioned planned route information is determined from a road network road library.

行驶对象例如为车辆、智能运输机器人等。The traveling object is, for example, a vehicle, an intelligent transportation robot, and the like.

上述规划路线信息的获取方式包括但不限于以下场景:可以是用户通过文本或语音形式进行输入得到行驶对象的规划路线信息,或者,采用纸件填报后扫描为图片或PDF格式之后采用文本识别得到行驶对象的规划路线信息,或者由电子设备下发至行驶对象得到上述行驶对象的规划路线信息。规划路线信息可以包括多个路段,每个路段具有各自的规划道路信息,与上述规划路线信息中的每个路段中的规划道路信息相关联的候选路网道路可以有一个或多个。上述规划路线信息中可能与现实存在的路网信息之间具有偏差或者对部分路段的描述有错误。The above-mentioned ways of obtaining the planned route information include but are not limited to the following scenarios: the user can obtain the planned route information of the driving object by inputting in the form of text or voice, or, after filling out the report in paper and scanning it into a picture or PDF format, it can be obtained by text recognition. The planned route information of the traveling object, or the planned route information of the traveling object is obtained by sending the electronic device to the traveling object. The planned route information may include a plurality of road segments, each road segment has its own planned road information, and there may be one or more candidate road network roads associated with the planned road information in each road segment in the above-mentioned planned route information. The above planned route information may have a deviation from the actual road network information or the description of some road sections may be wrong.

例如,输入的规划路线信息为序列R,序列R=[r0,r1,r2,r3,…,rn-1],r0,r1,r2,r3,…,rn-1分别对应表示第1个路段的规划道路信息,第2个路段的规划道路信息,第3个路段的规划道路信息,第4个路段的规划道路信息,……,第n个路段的规划道路信息,其中n为路段总个数,n为正整数。后续为方便描述,直接将包含规划道路信息的第i(i=0,1,2,3,……,n-1)个路段直接表述为路段riFor example, the input planning route information is sequence R, sequence R=[r 0 ,r 1 ,r 2 ,r 3 ,…,rn -1 ], r 0 ,r 1 ,r 2 ,r 3 ,…,r n-1 corresponds to the planned road information of the first road segment, the planned road information of the second road segment, the planned road information of the third road segment, the planned road information of the fourth road segment, ..., the planned road information of the nth road segment Planning road information, where n is the total number of road segments, and n is a positive integer. In the following, for the convenience of description, the i-th ( i =0, 1, 2, 3, .

针对每个路段ri,i=0,1,2,3,……,n-1,与该路段的规划道路信息ri关联的候选路网道路为mi个,候选路网道路为向量形式,表示为

Figure BDA0003652866220000081
For each road segment ri , i =0,1,2,3,...,n-1, there are m i candidate road network roads associated with the planned road information ri of this road segment, and the candidate road network roads are vectors form, expressed as
Figure BDA0003652866220000081

在操作S202,根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵。In operation S202, the probability of each route between the adjacent road segments is calculated according to the distance between each candidate road network road of the adjacent road segment, and a probability matrix including the probabilities of the routes between all adjacent road segments is obtained.

根据相邻两个路段中前后两个路段的候选路网道路两两进行组合得到的距离来计算得到不同组合对应的路线的概率,从而能够生成概率矩阵。The probability of obtaining routes corresponding to different combinations is calculated according to the distances obtained by combining the candidate road network roads of the two adjacent road segments before and after, so that a probability matrix can be generated.

由于相邻的描述路段是顺序、连贯的,通过计算得到的两个相邻路段之间相距较远的候选路网道路对应的路线的概率相对较小,相距较近的候选路网道路对应的路线的概率相对较大。Since the adjacent description road segments are sequential and coherent, the probability of the route corresponding to the candidate road network road that is far apart between the two adjacent road segments obtained by calculation is relatively small, and the candidate road network road corresponding to the short distance is relatively small. The probability of the route is relatively high.

在操作S203,对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。In operation S203, beam search processing is performed on the above probability matrix to obtain target route information in the road network.

束搜索(Beam Search,也可以称为集束搜索)是一种启发式图搜索算法,通过对概率矩阵进行束搜索处理,能够采用合理的内存空间且快速地实现全局最优路线的定位,减少定位至最优路线(目标路线信息)的时间和空间成本。Beam search (also known as beam search) is a heuristic graph search algorithm. By performing beam search processing on the probability matrix, it can use a reasonable memory space and quickly realize the positioning of the global optimal route, reducing positioning. Time and space cost to the optimal route (target route information).

特殊情况下,当规划路线信息只包含一个路段时,通过根据该路段的候选路网道路与规划路线信息之间的相似度来确定目标路线信息。In a special case, when the planned route information contains only one road segment, the target route information is determined by the similarity between the candidate road network roads of the road segment and the planned route information.

基于上述操作S201~S203,通过根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息相关联的候选路网道路;在规划路线信息存在错误或偏差的情况下,上述关联的候选路网道路能够作为一个或多个候选的关联选项,从而在后续确定目标路线信息时,进一步根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵;通过对上述概率矩阵进行束搜索处理,能够在每个路段的一个或多个候选路网道路中选择出最贴近正确状态的规划路线信息的目标路线信息,实现了将可能存在错误的规划路线信息(例如为人工语音或文本输入的信息中存在错误或偏差、电子设备下发的规划路线信息中存在错误或偏差等场景)向现实存在的路网信息的对齐,并能够一定程度上克服由于填写/输入错误或不规范导致的无法匹配实际道路的问题;在应用场景中,能够基于上述目标路线信息来对用户的实际路线进行监管和预警提示,可以应用至市域治理危化品车辆的运输路线监管的场景。Based on the above operations S201 to S203, the candidate road network roads associated with the above-mentioned planned route information are determined from the road network road library according to the planned route information of the driving object; in the case of errors or deviations in the planned route information, the above-mentioned association The candidate road network road can be used as one or more candidate association options, so that when the target route information is determined subsequently, the distance between each candidate road network road in the adjacent road segment is further calculated according to the distance between the adjacent road segments. The probability of the route is obtained, and the probability matrix containing the probability of the route between all adjacent road segments is obtained; by performing beam search processing on the above probability matrix, one or more candidate road network roads of each road segment can be selected to be the closest to the correct state. The target route information of the planned route information, which realizes the possibility of erroneous planning route information (for example, there are errors or deviations in the information inputted by artificial voice or text, and there are errors or deviations in the planned route information issued by the electronic device). ) to the actual road network information, and can overcome the problem of inability to match the actual road due to filling/input errors or irregularities to a certain extent; in the application scenario, it can be based on the above target route information. Route supervision and early warning prompts can be applied to the scene of the transportation route supervision of vehicles for hazardous chemicals management in the city.

根据本公开的实施例,上述操作S201中,根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,包括:对上述规划路线信息中的各个路段进行文本提取,得到针对每个路段的路段关键信息;根据上述路段关键信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路。According to an embodiment of the present disclosure, in the above-mentioned operation S201, according to the planned route information of the traveling object, the candidate road network roads associated with the above-mentioned planned route information are determined from the road network road database, including: each road segment in the above-mentioned planned route information is determined. Perform text extraction to obtain the key information of the road section for each road section; according to the above-mentioned key information of the road section, perform screening and matching in the road network road library to obtain the candidate road network road for each road section.

在一些实施例中,上述路段关键信息包括:路段关键词信息;在另一些实施例中,上述上述路段关键信息包括:路段关键词信息和路段关键字信息。In some embodiments, the above-mentioned road section key information includes: road section keyword information; in other embodiments, the above-mentioned road section key information includes: road section keyword information and road section keyword information.

根据本公开的实施例,根据上述路段关键信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路,包括:According to the embodiments of the present disclosure, according to the above key information of road sections, screening and matching are performed in the road network road database to obtain candidate road network roads for each road section, including:

根据路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路;在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,视为不存在与上述特定路段的路段关键信息相匹配的候选路网道路;或者,According to the road segment keyword information, screening and matching are performed in the road network road library to obtain candidate road network roads for each road segment; There is no candidate road network road that matches the key information of the above-mentioned specific road segment; or,

根据路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路;在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,拆分上述特定路段的路段关键词信息为更细粒度化的路段关键字信息;根据上述路段关键字信息,在路网道路库中进行筛选匹配,得到针对上述特定路段的候选路网道路;在不存在与上述特定路段的路段关键字信息相匹配的候选路网道路的情况下,视为不存在与上述特定路段的路段关键信息相匹配的候选路网道路。According to the road segment keyword information, screening and matching are performed in the road network road database to obtain candidate road network roads for each road segment; The road segment keyword information of the above-mentioned specific road segment is classified into more fine-grained road segment keyword information; according to the above-mentioned road segment keyword information, screening and matching are performed in the road network road database to obtain candidate road network roads for the above-mentioned specific road segment; If there is a candidate road network road matching the link key information of the specific link, it is considered that there is no candidate road network matching the link key information of the specific link.

根据本公开的实施例,上述根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,还包括:在不存在与特定路段的路段关键信息相匹配的候选路网道路的情况下,根据与上述特定路段相邻的相邻路段的候选路网道路,在上述路网道路库中确定与上述相邻路段的候选路网道路相交的特定路网道路作为针对上述特定路段的候选路网道路。According to an embodiment of the present disclosure, the above-mentioned determining the candidate road network road associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object further includes: when there is no road segment key information matching the specific road segment In the case of the candidate road network road of , the specific road network road that intersects the candidate road network road of the above-mentioned adjacent road segment is determined in the above-mentioned road network road library according to the candidate road network road of the adjacent road segment adjacent to the above-mentioned specific road segment As a candidate road network road for the above-mentioned specific road segment.

下面结合图3A~图3D来对各个实施例进行详细描述。Various embodiments are described in detail below with reference to FIGS. 3A to 3D .

图3A示意性地示出了根据本公开一实施例的操作S201的详细实施流程图。FIG. 3A schematically shows a detailed implementation flowchart of operation S201 according to an embodiment of the present disclosure.

根据本公开的实施例,上述规划路线信息包括:依序途经的各个路段构成的序列。例如包括但不限于是:用户基于文本形式输入或者语音输入后转为文本形式的路段序列,或者为电子设备下发的文本形式的路段序列等。According to an embodiment of the present disclosure, the above-mentioned planned route information includes: a sequence formed by each road segment passed in sequence. For example, it includes, but is not limited to, a road segment sequence that is converted into text form after input by a user based on text or voice input, or a text form road segment sequence delivered by an electronic device, and the like.

例如,在一场景中,用户输入的行驶对象的规划路线信息为以下序列Ra:{“通盛大道”,“江山路”,“东方大道”,“通沪大道地面道路”,“沈海高速(小海出入口)”,“S15洋通高速(如东出入口)”,“掘港镇东二环路”,“苏223线19公里”,“宁海线(328国道)”}。上述括号中的内容也是用户输入的备注内容。这里对应的路段总个数n为9。For example, in a scene, the planned route information of the driving object input by the user is the following sequence Ra: {"Tongsheng Avenue", "Jiangshan Road", "Dongfang Avenue", "Tonghu Avenue Ground Road", "Shenhai Expressway" (Xiaohai Entrance and Exit)", "S15 Yangtong Expressway (Rudong Entrance and Exit)", "East 2nd Ring Road of Jiugang Town", "Su 223 Line 19 kilometers", "Ninghai Line (328 National Road)"}. The content in the above brackets is also the remark content input by the user. The total number n of the corresponding road sections here is 9.

在一实施例中,上述操作S201中,根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,包括以下操作:S311和S312。In an embodiment, in the above operation S201, according to the planned route information of the traveling object, a candidate road network road associated with the above-mentioned planned route information is determined from the road network road library, including the following operations: S311 and S312.

在操作S311,对上述规划路线信息中的各个路段进行文本提取,得到针对每个路段的路段关键词信息。In operation S311, text extraction is performed on each road segment in the above-mentioned planned route information to obtain road segment keyword information for each road segment.

首先,根据字典、正则表达式等方法去除非关键词部分。如对省市区县信息、“快速路”、“大道”、“公路”、“高速”、“街”、“段”、“路口”、“出入口”等非关键词信息进行去除。接着,对去除关键词信息之后的文本进行分词,将分词结果作为路段ri的关键词

Figure BDA0003652866220000101
ki表示路段ri的关键词总数量。First, remove non-keyword parts according to dictionaries, regular expressions, etc. For example, the non-keyword information such as the information of provinces, cities and counties, "expressways", "roads", "highways", "highways", "streets", "sections", "junctions", "entrances and exits", etc. are removed. Next, perform word segmentation on the text after removing the keyword information, and use the word segmentation result as the keyword of the road segment ri
Figure BDA0003652866220000101
k i represents the total number of keywords in road segment ri .

对上述序列Ra的各个路段进行文本提取,依次对应第1个路段、第2个路段、……第9个路段的关键词为:[{'通盛'},{'江山'},{'东方'},{'通沪','地面'},{'沈海','小海'},{'洋通','15'},{'东二环','掘港'},{'223','19'},{'328','宁海'}]。Text extraction is performed on each road section of the above sequence Ra, and the keywords corresponding to the first road section, the second road section, ... the ninth road section are: [{'Tongsheng'}, {'Jiangshan'}, {' Dongfang'}, {'Tonghu', 'Ground'}, {'Shenhai', 'Xiaohai'}, {'Yangtong', '15'}, {'East Second Ring', 'Digang'}, {'223', '19'}, {'328', 'Ninghai'}].

在操作S312,根据上述路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路。In operation S312, screening and matching are performed in the road network road library according to the above-mentioned road segment keyword information to obtain candidate road network roads for each road segment.

例如,通过在路网道路库中基于上述路段关键词信息进行筛选匹配,得到的依序对应各个路段的候选路网道路的结果为Rta:{[“通盛大道”,“通盛大道高架”,“通盛南路”],[“江山路”],[“东方路”,“东方大道高架”,“东方红大桥”,“东方大道”,“兴益村东方河路”,“东方河路”,“东方寺路”],[“通沪大道”,“通沪大道高架”,“通沪路”],[“沈海高速公路”,“小海枢纽”,“小海路”],[“洋通路”,“洋通高速公路”,“Y157”,“15组中心路”,“C215”,“Y159”,“Y152”,“C159”,“吕四港镇石堤村15组”,“Y155”,“Y615”,“15组南路”,“G15”,“S15”,“C151”,“Y315”,“X215”,“C153”,“X315”,“Y153”,“Y151”],[“东二环”],[“S223”,“S223(旧)”,“19组南庄线路”,“S19”,“Y019”,“Y194”,“Y195”],[“G328”,“G328(旧)”,“C328”,“宁海路”,“宁海东路”,“宁海南路”,“宁海西路”]};该结果中,中括号内的信息为对应于当前路段的一个或多个候选路网道路,大括号整体表示规划路线信息的所有路段的候选路网道路。For example, by performing screening and matching based on the above-mentioned road segment keyword information in the road network road database, the result of the candidate road network roads corresponding to each road segment in sequence is Rta: {["Tongsheng Avenue", "Tongsheng Avenue Elevated" , "Tongsheng South Road"], ["Jiangshan Road"], ["Dongfang Road", "Dongfang Avenue Viaduct", "Dongfanghong Bridge", "Dongfang Avenue", "Dongfang River Road in Xingyi Village", "Dongfang River Road" Road", "Dongfang Temple Road"], ["Tonghu Avenue", "Tonghu Avenue Elevated", "Tonghu Road"], ["Shenhai Expressway", "Xiaohai Hub", "Xiaohai Road"], ["Yangtong Road", "Yangtong Expressway", "Y157", "Central Road of Group 15", "C215", "Y159", "Y152", "C159", "Group 15 of Shidi Village, Lusigang Town" ","Y155","Y615","Group 15 South Road","G15","S15","C151","Y315","X215","C153","X315","Y153","Y151 "], ["East Second Ring Road"], ["S223", "S223 (Old)", "Group 19 Nanzhuang Line", "S19", "Y019", "Y194", "Y195"], ["G328 ", "G328 (Old)", "C328", "Ninghai Road", "Ninghai East Road", "Ninghai South Road", "Ninghai West Road"]}; in this result, the information in square brackets corresponds to the current One or more candidate road network roads of a road segment, the curly brackets as a whole represent candidate road network roads of all road segments of the planned route information.

大部分场景下,会存在与上述路段关键词信息匹配的候选路网道路。在个别一些场景中,会存在以下情况:在路网道路库中根据上述路段关键词信息进行筛选匹配,在某一个或某几个路段得不到匹配的候选路网道路的情况,即,不存在与特定路段的路段关键词信息相匹配的候选路网道路,那么这种情况下,可以采用图3B或图3C所示例的方案。In most scenarios, there will be candidate road network roads that match the above road segment keyword information. In some individual scenarios, there may be the following situations: in the road network road database, screening and matching is performed according to the above-mentioned road segment keyword information, but there is no matching candidate road network road in one or several road segments, that is, no There is a candidate road network road that matches the road segment keyword information of a specific road segment. In this case, the solution illustrated in FIG. 3B or FIG. 3C may be adopted.

图3B示意性地示出了根据本公开另一实施例的操作S201的详细实施流程图。FIG. 3B schematically shows a detailed implementation flowchart of operation S201 according to another embodiment of the present disclosure.

参照图3B所示,根据本公开的一种实施例,上述操作S201中,根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,包括以下操作:S321、S322和S323。Referring to FIG. 3B , according to an embodiment of the present disclosure, in the above operation S201 , according to the planned route information of the traveling object, a candidate road network road associated with the above-mentioned planned route information is determined from the road network road library, including the following operations : S321, S322 and S323.

在操作S321,对上述规划路线信息中的各个路段进行文本提取,得到针对每个路段的路段关键词信息。In operation S321, text extraction is performed on each road segment in the above-mentioned planned route information to obtain road segment keyword information for each road segment.

在操作S322,根据上述路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路。In operation S322, screening and matching are performed in the road network road database according to the above-mentioned road segment keyword information to obtain candidate road network roads for each road segment.

当存在针对每个路段的候选路网道路时,对应的情况可以参照前述结合图3A所描述的实施例所示,其中操作S321的详细描述可以参照前述实施例中关于操作S311的描述,操作S322的详细描述可以参照前述实施例中关于操作S312的描述,这里不再赘述。When there is a candidate road network road for each road segment, the corresponding situation may be shown with reference to the foregoing embodiment described in conjunction with FIG. 3A , wherein the detailed description of operation S321 may refer to the description of operation S311 in the foregoing embodiment, and operation S322 For the detailed description, reference may be made to the description about operation S312 in the foregoing embodiment, which will not be repeated here.

在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,执行操作S323。In a case where there is no candidate road network road matching the link keyword information of the specific link, operation S323 is performed.

在操作S323,根据与上述特定路段相邻的相邻路段的候选路网道路,在上述路网道路库中确定与上述相邻路段的候选路网道路相交的特定路网道路作为针对上述特定路段的候选路网道路。In operation S323, according to the candidate road network roads of adjacent road segments adjacent to the specific road segment, a specific road network road intersecting with the candidate road network roads of the adjacent road segment is determined in the road network road library as the specific road segment for the above-mentioned specific road segment candidate road network.

本实施例中,基于操作S321~S323,在通过关键词信息匹配的方式得不到某一个或多个特定路段的候选路网道路的情况下,通过采用相邻路段的候选路网道路与该特定路段之间的路线关系来确定该特定路段的候选路网道路,能够解决规划路线信息中存在错误或偏差时候选路网数据缺失导致的路径识别和对齐的问题,例如可以解决以下场景中:由于用户输入错误或者用户输入的词语不规范导致的整体路径中候选路网数据缺失的问题。In this embodiment, based on operations S321 to S323, in the case where the candidate road network road of one or more specific road segments cannot be obtained through keyword information matching, the candidate road network road of the adjacent road segment is used to match the The route relationship between a specific road segment to determine the candidate road network road for the specific road segment can solve the problem of route identification and alignment caused by the lack of road selection network data when there are errors or deviations in the planned route information. For example, it can be solved in the following scenarios: The problem of missing candidate road network data in the overall route due to user input errors or irregular words input by users.

图3C示意性地示出了根据本公开又一实施例的操作S201的详细实施流程图。FIG. 3C schematically shows a detailed implementation flowchart of operation S201 according to yet another embodiment of the present disclosure.

参照图3C所示,根据本公开的另一种实施例,上述操作S201中,根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,包括以下操作:S331、S332、S333和S334。Referring to FIG. 3C , according to another embodiment of the present disclosure, in the above operation S201 , according to the planned route information of the traveling object, the candidate road network roads associated with the above-mentioned planned route information are determined from the road network road library, including the following Operation: S331, S332, S333 and S334.

在操作S331,对上述规划路线信息中的各个路段进行文本提取,得到针对每个路段的路段关键词信息。In operation S331, text extraction is performed on each road segment in the above-mentioned planned route information to obtain road segment keyword information for each road segment.

在操作S332,根据上述路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路。In operation S332, screening and matching are performed in the road network road library according to the above-mentioned road segment keyword information to obtain candidate road network roads for each road segment.

当存在针对每个路段的候选路网道路时,对应的情况可以参照前述结合图3A所描述的实施例所示,其中操作S331的详细描述可以参照前述实施例中关于操作S311的描述,操作S332的详细描述可以参照前述实施例中关于操作S312的描述,这里不再赘述。When there is a candidate road network road for each road segment, the corresponding situation may be shown with reference to the foregoing embodiment described in conjunction with FIG. 3A , wherein the detailed description of operation S331 may refer to the description of operation S311 in the foregoing embodiment, and operation S332 For the detailed description, reference may be made to the description about operation S312 in the foregoing embodiment, which will not be repeated here.

在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,执行操作S333和S334。In the case where there is no candidate road network road matching the link keyword information of the specific link, operations S333 and S334 are performed.

在操作S333,拆分上述特定路段的路段关键词信息为更细粒度化的路段关键字信息。In operation S333, the link keyword information of the specific link is split into more fine-grained link keyword information.

例如路段关键词信息为:'东二环','掘港',拆分得到的路段关键字信息为:'东','二','环','掘','港'。For example, the keyword information of the road section is: 'East Second Ring Road', 'Digang', and the keyword information of the road section obtained by splitting is: 'East', 'Second', 'Ring', 'Dig', 'Port'.

在操作S334,根据上述路段关键字信息,在路网道路库中进行筛选匹配,得到针对上述特定路段的候选路网道路。In operation S334, screening and matching are performed in the road network road library according to the above-mentioned road segment keyword information, and a candidate road network road for the above-mentioned specific road segment is obtained.

本实施例中,基于操作S331~S334,当通过关键词信息匹配的方式得不到某一个或多个特定路段的候选路网道路时,通过基于细粒度更小的路段关键字信息来进行筛选匹配,以得到针对该特定路段的候选路网道路,能够在一定程度上解决规划路线信息中存在错误或偏差时候选路网数据缺失导致的路径识别和对齐的问题,例如可以解决以下场景中:由于用户输入错误或者用户输入的词语不规范导致的整体路径中候选路网数据缺失的问题。In this embodiment, based on operations S331 to S334, when the candidate road network road of one or more specific road sections cannot be obtained by means of keyword information matching, screening is performed based on the keyword information of road sections with smaller granularity Matching to obtain the candidate road network road for the specific road section can solve the problem of path identification and alignment caused by the lack of road selection network data when there are errors or deviations in the planned route information to a certain extent. For example, it can be solved in the following scenarios: The problem of missing candidate road network data in the overall route due to user input errors or irregular words input by users.

图3D示意性地示出了根据本公开再一实施例的操作S201的详细实施流程图。FIG. 3D schematically shows a detailed implementation flowchart of operation S201 according to still another embodiment of the present disclosure.

在上述图3C示例的实施例的基础上,本实施例对应的实施场景为:基于细粒度更小的路段关键字信息进行筛选匹配时,不存在与特定路段的路段关键字信息相匹配的候选路网道路。On the basis of the embodiment illustrated in FIG. 3C above, the corresponding implementation scenario of this embodiment is: when screening and matching is performed based on the road segment keyword information with smaller granularity, there is no candidate matching the road segment keyword information of a specific road segment. road network road.

参照图3D所示,上述操作S201中,根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路,包括以下操作:S341、S342、S343、S344和S345。Referring to FIG. 3D, in the above operation S201, according to the planned route information of the traveling object, the candidate road network roads associated with the above planned route information are determined from the road network road library, including the following operations: S341, S342, S343, S344 and S345.

在操作S341,对上述规划路线信息中的各个路段进行文本提取,得到针对每个路段的路段关键词信息。In operation S341, text extraction is performed on each road segment in the above-mentioned planned route information to obtain road segment keyword information for each road segment.

在操作S342,根据上述路段关键词信息,在路网道路库中进行筛选匹配,得到针对每个路段的候选路网道路。In operation S342, screening and matching are performed in the road network road database according to the above-mentioned road segment keyword information to obtain candidate road network roads for each road segment.

当存在针对每个路段的候选路网道路时,对应的情况可以参照前述结合图3A所描述的实施例所示,其中操作S341的详细描述可以参照前述实施例中关于操作S311的描述,操作S342的详细描述可以参照前述实施例中关于操作S312的描述,这里不再赘述。When there is a candidate road network road for each road segment, the corresponding situation may be shown with reference to the foregoing embodiment described in conjunction with FIG. 3A , wherein the detailed description of operation S341 may refer to the description of operation S311 in the foregoing embodiment, and operation S342 For the detailed description, reference may be made to the description about operation S312 in the foregoing embodiment, which will not be repeated here.

在不存在与特定路段的路段关键词信息相匹配的候选路网道路的情况下,执行操作S343和S344。In a case where there is no candidate road network road matching the link keyword information of the specific link, operations S343 and S344 are performed.

在操作S343,拆分上述特定路段的路段关键词信息为更细粒度化的路段关键字信息。In operation S343, the link keyword information of the specific link is split into more fine-grained link keyword information.

在操作S344,根据上述路段关键字信息,在路网道路库中进行筛选匹配,得到针对上述特定路段的候选路网道路。In operation S344, screening and matching are performed in the road network road database according to the above-mentioned road segment keyword information, and a candidate road network road for the above-mentioned specific road segment is obtained.

在不存在与特定路段的路段关键字信息相匹配的候选路网道路的情况下,执行操作S345。In the case where there is no candidate road network road matching the link key information of the specific link, operation S345 is performed.

在操作S345,根据与上述特定路段相邻的相邻路段的候选路网道路,在上述路网道路库中确定与上述相邻路段的候选路网道路相交的特定路网道路为针对上述特定路段的候选路网道路。In operation S345, according to the candidate road network roads of adjacent road segments adjacent to the specific road segment, the specific road network road that intersects the candidate road network roads of the adjacent road segment is determined in the road network road library as the specific road segment for the above-mentioned specific road segment candidate road network.

基于上述操作S341~S345,先基于路段关键词信息进行筛选匹配,当特定路段基于路段关键词信息得不到候选路网道路时,进一步基于细粒度更小的路段关键字信息进行筛选匹配,针对基于路段关键字信息仍旧得不到匹配的候选路网道路的特定路段,通过采用相邻路段的候选路网道路与该特定路段之间的路线关系来确定该特定路段的候选路网道路,基于逐层筛选和根据相邻路段补充数据的方式,能够解决规划路线信息中存在错误或偏差时候选路网数据缺失导致的路径识别和对齐的问题,例如可以解决以下场景中:由于用户输入错误或者用户输入的词语不规范导致的整体路径中候选路网数据缺失的问题。Based on the above operations S341 to S345, firstly, screening and matching are performed based on the road segment keyword information. When no candidate road network road is available for a specific road segment based on the road segment keyword information, the screening and matching are further performed based on the finer-grained road segment keyword information. The specific road segment of the candidate road network road that still cannot be matched based on the road segment keyword information, the candidate road network road of the specific road segment is determined by using the route relationship between the candidate road network road of the adjacent road segment and the specific road segment, based on The method of layer-by-layer screening and supplementing data according to adjacent road sections can solve the problem of route identification and alignment caused by missing route network data when there are errors or deviations in the planned route information. For example, it can solve the following scenarios: due to user input errors or The problem of missing candidate road network data in the overall route caused by the irregular words entered by the user.

图4示意性地示出了根据本公开实施例的操作S202的详细实施流程图。FIG. 4 schematically shows a detailed implementation flowchart of operation S202 according to an embodiment of the present disclosure.

根据本公开的实施例,参照图4所示,上述操作S202中,根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵,包括以下操作:S401、S402、S403、S404和S405。According to an embodiment of the present disclosure, referring to FIG. 4 , in the above operation S202 , the probability of each route between adjacent road segments is calculated according to the distance between each candidate road network road of adjacent road segments, and the probability of each route between adjacent road segments is calculated to obtain The probability matrix of the probabilities of routes between adjacent road segments, including the following operations: S401, S402, S403, S404, and S405.

在操作S401,针对所有路段中的任意一个路段,计算当前路段的候选路网道路与下一路段的候选路网道路两两之间的距离,得到由当前路段对应的距离元素构成的距离向量。In operation S401, for any one of all the road segments, the distance between the candidate road network road of the current road segment and the candidate road network road of the next road segment is calculated to obtain a distance vector composed of distance elements corresponding to the current road segment.

在一实施例中,分别将前路段候选路网道路Ci、后路段候选路网道路Ci+1按顺序两两组合,根据路网数据计算两条道路的坐标点间最短直线距离di={dis(ci,j,ci+1,j′),j=0,1,2,…,mi-1,j′=0,1,2,…,mi+1-1},dis(ci,j,ci+1,j′)表示前路段候选路网道路Ci中的第j个候选路网道路与后路段候选路网道路Ci+1的第j′个候选路网道路的坐标点之间的最短直线距离。In one embodiment, the candidate road network road C i of the front section and the candidate road network road C i+1 of the rear section are combined in pairs in sequence, and the shortest straight-line distance d i between the coordinate points of the two roads is calculated according to the road network data. ={dis(c i,j , ci+1,j′ ),j=0,1,2,…,m i -1,j′=0,1,2,…,m i+1 -1 }, dis(c i,j ,c i+1,j′ ) represents the jth candidate road network road in the candidate road network road C i of the previous link and the jth candidate road network road C i+1 of the following link segment The shortest straight-line distance between the coordinate points of each candidate road network road.

在操作S402,根据所有路段的距离向量,得到距离矩阵。In operation S402, a distance matrix is obtained according to the distance vectors of all road segments.

根据本公开的实施例,上述操作S402中,根据所有路段的距离向量,得到距离矩阵,包括以下子操作:S402a和S402b。According to an embodiment of the present disclosure, in the above operation S402, a distance matrix is obtained according to the distance vectors of all road segments, including the following sub-operations: S402a and S402b.

在子操作S402a,将所有路段中各个路段的距离向量作为距离矩阵的各行。In sub-operation S402a, the distance vector of each road segment in all road segments is taken as each row of the distance matrix.

在子操作S402b,将所有路段中距离向量的列数最大值作为上述距离矩阵的列规模,并在列数小于上述列规模的特定距离向量中补充默认值,以补齐列数。In sub-operation S402b, the maximum number of columns of distance vectors in all road segments is used as the column scale of the distance matrix, and a default value is added to a specific distance vector whose column number is smaller than the above column scale to make up the number of columns.

其中,在后续的操作S403中,当对每行的距离向量进行数值变换时,上述默认值不参与计算,采用当前距离向量中的距离元素最大值与各个距离元素作差,得到变换后的距离元素;在后续的操作S404中,当对上述目标距离向量输入至软最大化函数中进行处理时,上述默认值对应的输出概率为预设值。Wherein, in the subsequent operation S403, when performing numerical transformation on the distance vector of each row, the above-mentioned default value does not participate in the calculation, and the difference between the maximum distance element in the current distance vector and each distance element is used to obtain the transformed distance element; in the subsequent operation S404, when the above-mentioned target distance vector is input into the soft maximization function for processing, the output probability corresponding to the above-mentioned default value is a preset value.

本实施例中,记l=max({mi*mi+1,i=0,1,2,…,n-2})(其中,由于取相邻路段两两组合的路线的距离,因此此时对于距离而言,i对应的当前路段的序号最大为n-2,倒数第二个路段作为当前路段的序号最大取值),di不足l个元素时用默认值default_d补齐,将di作为距离矩阵D的第i行,则D的规模为(n-1,l),即表示距离矩阵D共有n-1行和l列,n行的序号分别为0,1,2,……n-2,l列的序号为0,1,2,……l-1。In this embodiment, denote l=max({m i *m i+1 , i=0, 1, 2, . Therefore, in terms of distance at this time, the maximum serial number of the current road segment corresponding to i is n-2, and the penultimate road segment is used as the maximum value of the serial number of the current road segment). Taking d i as the i-th row of the distance matrix D, the scale of D is (n-1,l), which means that the distance matrix D has a total of n-1 rows and l columns, and the serial numbers of the n rows are 0, 1, and 2 respectively. , ...n-2, the serial numbers of the l columns are 0, 1, 2, ...l-1.

例如,在实际操作中可以设置默认值为无限大,相应的,为方便计算直接将对应的输出概率的预设值设置为极小值1e-08。For example, in actual operation, the default value may be set to be infinite. Correspondingly, for the convenience of calculation, the default value of the corresponding output probability is directly set to a minimum value of 1e-08.

在一具体实施例中,针对上述候选路网道路的结果Rta,可以得到第0行距离向量包含的距离元素的个数为:3(“通盛大道”,“通盛大道高架”,“通盛南路”,共有3个)*1(“江山路”,共有一个)=3,类似的,得到第1行距离向量包含的距离元素的个数为:1*7=7,第2行距离向量包含的距离元素的个数为:7*3=21,第3行距离向量包含的距离元素的个数为:3*3=9,第4行距离向量包含的距离元素的个数为:3*21=63,第5行距离向量包含的距离元素的个数为:21*1=21,第6行距离向量包含的距离元素的个数为:1*7=7,第7行距离向量包含的距离元素的个数为:7*7=49。In a specific embodiment, for the result Rta of the above candidate road network road, it can be obtained that the number of distance elements included in the 0th row distance vector is: 3 ("Tongsheng Avenue", "Tongsheng Avenue Elevated", "Tongsheng Avenue Elevated", "Tongsheng Avenue Elevated", "Tongsheng Avenue Elevated Shengnan Road", a total of 3)*1("Jiangshan Road", a total of one)=3, similarly, the number of distance elements contained in the distance vector in the first row is: 1*7=7, the distance in the second row The number of distance elements contained in the vector is: 7*3=21, the number of distance elements contained in the distance vector in the third row is: 3*3=9, and the number of distance elements contained in the distance vector in the fourth row is: 3*21=63, the number of distance elements contained in the distance vector in the fifth row is: 21*1=21, and the number of distance elements contained in the distance vector in the sixth row is: 1*7=7, the distance in the seventh row The number of distance elements contained in the vector is: 7*7=49.

根据所有的距离向量可以得到候选路网道路的结果Rta对应的距离矩阵共包含8行和63列个距离元素。According to all the distance vectors, the result Rta of the candidate road network can be obtained. The distance matrix corresponding to Rta contains a total of 8 rows and 63 columns of distance elements.

在操作S403,对上述距离矩阵中每行的距离向量进行数值变换,得到变换后的目标距离向量,变换前后相应的距离元素之间的总和为一固定值。In operation S403, numerical transformation is performed on the distance vector of each row in the distance matrix to obtain a transformed target distance vector, and the sum between the corresponding distance elements before and after the transformation is a fixed value.

例如在一实施例中,针对距离矩阵D中的每行,将每行距离向量中的每个计算出来的距离元素替换为其所在行的最大距离元素值(不含默认值)减去该元素的值,得到包含变换后的目标距离向量的距离矩阵D′。在其他实施例中,也可以采用其他数值变换的方法,只要能够使得原先距离矩阵中取值较大的数值转变为取值较小的数值的变换方式均可,这样是为了确保相邻路段的候选路网道路之间的距离相对较近的对应计算得到的概率比较大。For example, in one embodiment, for each row in the distance matrix D, each calculated distance element in the distance vector of each row is replaced by the maximum distance element value (excluding the default value) of the row in which it is located minus the element The value of , obtains the distance matrix D′ containing the transformed target distance vector. In other embodiments, other numerical transformation methods may also be used, as long as the transformation methods that can transform the larger value in the original distance matrix into the smaller value are acceptable, so as to ensure the safety of adjacent road sections. The corresponding calculated probability of the relatively short distance between the candidate road network roads is relatively high.

在操作S404,将每个目标距离向量输入至软最大化函数中进行处理,输出得到上述目标距离向量中各个距离元素对应的概率分布值,其中当前距离元素对应的概率分布值用于表征上述当前距离元素对应的路线的概率。In operation S404, each target distance vector is input into the soft maximization function for processing, and the output obtains the probability distribution value corresponding to each distance element in the above target distance vector, wherein the probability distribution value corresponding to the current distance element is used to represent the above current The probability of the route corresponding to the distance element.

在操作S405,根据所有目标距离向量对应得到的概率分布值,得到包含所有相邻路段之间路线的概率的概率矩阵。In operation S405, a probability matrix including probabilities of routes between all adjacent road segments is obtained according to the corresponding probability distribution values of all target distance vectors.

针对距离矩阵D′,将该距离矩阵D′的行输入至软最大化(softmax)函数进行计算,每行的输出进行汇总,得到一概率矩阵P。即Pi,:=softmax(D′i,:),i=0,1,…,n-2;D′的一个角标“:”表示同一行中各个元素的列序号,Pi,:表示在给定描述路段i到路段i+1,二者之间的候选路网道路的排列组合的概率得分分布。概率矩阵P的规模为(n-1,l),即表示概率矩阵P共有n-1行和l列,n行的序号分别为0,1,2,……,n-2,l列的序号为0,1,2,……,l-1。For the distance matrix D', the rows of the distance matrix D' are input into a softmax function for calculation, and the outputs of each row are aggregated to obtain a probability matrix P. That is, P i,: =softmax(D' i,: ),i=0,1,...,n-2; an angle label ":" of D' indicates the column number of each element in the same row, P i,: Represents the probability score distribution of the permutations and combinations of candidate road network roads between a given description link i to link i+1. The scale of the probability matrix P is (n-1, l), which means that the probability matrix P has a total of n-1 rows and l columns, and the serial numbers of the n rows are 0, 1, 2, ..., n-2, and l columns, respectively. The serial numbers are 0, 1, 2, ..., l-1.

假设采用s表示概率矩阵中的任意一个列序号/标号,s的取值为0,1,2,……,l-1,那么Pi,s表示由候选路网道路Ci的候选道路cx到候选路网道路Ci+1的候选道路cy的得分概率;其中x=|Ci+1||s(x的值等于列序号s除以Ci+1得到商),y=s%|Ci+1|(y的值等于列序号s除以Ci+1得到余数)。Assuming that s is used to represent any column number/label in the probability matrix, and the value of s is 0, 1, 2, ..., l-1, then P i, s represents the candidate road c from the candidate road network road C i The scoring probability of the candidate road c y from x to the candidate road network road C i+1 ; where x=|C i+1 ||s (the value of x is equal to the column number s divided by C i+1 to get the quotient), y= s%|C i+1 | (the value of y is equal to the column number s divided by C i+1 to get the remainder).

例如,按照序号从0开始对路段进行编号,假设第0个路段(向量形式的候选路网道路C0)共有3(mi的一个示例)个候选路网道路,例如表示为

Figure BDA0003652866220000151
(上角标表示路段序号,下角标表示候选路网道路的序号,下面的表达形式相同),第1个路段(向量形式的候选路网道路C1)共有2(mi+1的一个示例)个候选路网道路,例如表示为
Figure BDA0003652866220000152
那么第0个路段到第1个路段对应的目标距离向量输入至softmax函数后,输出得到共6个概率分布:P0,0,P0,1,P0,2,P0,3,P0,4,P0,5。其中,|Ci+1|对应的取值为2,则在序号s=0时,x=0,y=0;在序号s=1时,x=0,y=1;在序号s=2时,x=1,y=0;在序号s=3时,x=1,y=1;在序号s=4时,x=2,y=0;在s=5时,x=2,y=1;即,P0,0,P0,1,P0,2,P0,3,P0,4,P0,5依次对应于路线
Figure BDA0003652866220000153
各自的概率,p0,0+P0,1+P0,2+P0,3+P0,4+P0,5=1。For example, the road segments are numbered from 0 according to the serial number, and it is assumed that the 0th road segment (the candidate road network road C 0 in the form of a vector) has a total of 3 (an example of m i ) candidate road network roads, for example, expressed as
Figure BDA0003652866220000151
(The upper subscript indicates the sequence number of the road segment, the lower subscript indicates the sequence number of the candidate road network road, the following expressions are the same), the first road segment (the candidate road network road C 1 in the form of a vector) has a total of 2 (m i+1 ) an example ) candidate road network roads, such as denoted as
Figure BDA0003652866220000152
Then, after the target distance vector corresponding to the 0th road segment to the 1st road segment is input into the softmax function, the output obtains a total of 6 probability distributions: P 0,0 , P 0,1 , P 0,2 , P 0,3 , P 0,4 , P 0,5 . Among them, the value corresponding to |C i+1 | is 2, then when the serial number s=0, x=0, y=0; when the serial number s=1, x=0, y=1; when the serial number s= When 2, x=1, y=0; when s=3, x=1, y=1; when s=4, x=2, y=0; when s=5, x=2 , y=1; that is, P 0,0 , P 0,1 , P 0,2 , P 0,3 , P 0,4 , P 0,5 in turn correspond to the route
Figure BDA0003652866220000153
The respective probabilities, p 0,0 +P 0,1 +P 0,2 +P 0,3 +P 0,4 +P 0,5 =1.

在其他实施例中,如果各个路段、候选路网道路不是从0开始编号,将其进行处理后得到以序号0开始的编号,概率矩阵中各列的序号和路线的对应关系可以同理求得。In other embodiments, if each road segment and candidate road network road is not numbered from 0, after processing it, the number starting from serial number 0 is obtained, and the corresponding relationship between the serial number of each column in the probability matrix and the route can be obtained in the same way. .

在一具体实施例中,针对上述示例的规划路线信息为以下序列Ra:{“通盛大道”,“江山路”,“东方大道”,“通沪大道地面道路”,“沈海高速(小海出入口)”,“S15洋通高速(如东出入口)”,“掘港镇东二环路”,“苏223线19公里”,“宁海线(328国道)”},概率矩阵中的元素P7,48为0.02329721202244289,其对应为第7行(第7个到第8个路段的路线所对应的概率,路段序号从0开始)、第48列(相邻路段中前一路段的候选路网道路的总个数与后一路段的候选路网道路的总个数的乘积最大值为63)的概率元素。In a specific embodiment, the planned route information for the above example is the following sequence Ra: {"Tongsheng Avenue", "Jiangshan Road", "Dongfang Avenue", "Tonghu Avenue Ground Road", "Shenhai Expressway (Xiaohai Road) Entrance and exit)", "S15 Yangtong Expressway (Rudong entrance and exit)", "East 2nd Ring Road of Jiugang Town", "Su 223 Line 19 kilometers", "Ninghai Line (328 National Road)"}, element P in the probability matrix 7,48 is 0.02329721202244289, which corresponds to the 7th row (the probability corresponding to the route from the 7th to the 8th road segment, the segment serial number starts from 0), the 48th column (the candidate road network of the previous road segment in the adjacent road segment) The maximum value of the product of the total number of roads and the total number of candidate road network roads in the following road segment is 63).

该概率元素P7,48表示规划路线信息中的路段“苏223线19公里”与路段“宁海线(328国道)”之间的补齐后共63个候选路网道路中的第48个候选路网道路,根据示例可知,|C8|=7,7|48=6(商为6),48%7=6(余数为6),P7,48则表示“Y195”(第7个路段中的序号为6的候选路网道路,序号从0开始)到“宁海西路”(第8个路段中的序号为6的候选路网道路,序号从0开始)这条路线的概率为0.02329721202244289。The probability element P 7 , 48 represents the 48th candidate among the 63 candidate roads in the road network after the completion between the road section "Su-223 Line 19 kilometers" and the road section "Ninghai Line (328 National Road)" in the planned route information. For roads in the road network, according to the example, |C 8 |=7, 7|48=6 (the quotient is 6), 48% 7=6 (the remainder is 6), and P 7,48 means "Y195" (the seventh The candidate road network road with the serial number 6 in the road segment, the serial number starts from 0) to "Ninghai West Road" (the candidate road network road with the serial number 6 in the 8th road segment, the serial number starts from 0) The probability of this route is 0.02329721202244289.

图5示意性地示出了根据本公开实施例的操作S203的详细实施流程图。FIG. 5 schematically shows a detailed implementation flowchart of operation S203 according to an embodiment of the present disclosure.

根据本公开的实施例,参照图5所示,上述操作S203中,对上述概率矩阵进行束搜索处理,得到目标路线信息,包括以下操作:S501、S502和S503。According to an embodiment of the present disclosure, referring to FIG. 5 , in the above operation S203 , beam search processing is performed on the above probability matrix to obtain target route information, including the following operations: S501 , S502 and S503 .

在操作S501,针对上述概率矩阵的首行,将当前行中每组相邻路段之间路线的概率的得分最高的前K个所对应的路线确定为候选路线,K为设定搜索束宽。In operation S501, for the first row of the above probability matrix, the top K routes corresponding to the highest probability scores of routes between each group of adjacent road segments in the current row are determined as candidate routes, where K is the set search beam width.

例如K=2,首行(第0行)对应的得分最高的前2个路线为第1步得到的候选路线:“通盛南路”→“江山路”;“通盛大道”→“江山路”。For example, K=2, the first 2 routes with the highest scores corresponding to the first line (the 0th line) are the candidate routes obtained in the first step: "Tongsheng South Road" → "Jiangshan Road"; "Tongsheng Avenue" → "Jiangshan Road" ".

在操作S502,针对上述概率矩阵的首行之后的后续行中的每一行,确定当前行所对应的路线分别在上一行所对应的K个候选路线的前提下的条件概率的得分,并将条件概率的得分在前K个所对应的路线确定为目标候选路线。In operation S502, for each row in the subsequent rows after the first row of the above-mentioned probability matrix, determine the score of the conditional probability of the route corresponding to the current row under the premise of the K candidate routes corresponding to the previous row, and assign the condition The routes corresponding to the first K of the probability scores are determined as target candidate routes.

针对概率矩阵的后续行,例如首行之后的第1行,通过计算当前行所在的路线在第0行所对应的2个候选路线下的条件概率的得分,确定得分最高的前2个路线为第2步得到的候选路线。例如,计算“通盛南路”→“江山路”前提下概率矩阵中第1行的各个路线对应的条件概率的得分;计算“通盛大道”→“江山路”前提下概率矩阵中第1行的各个路线对应的条件概率的得分,并将得分最高的前2个路线确定为第2步的目标候选路线,例如得到的结果为:“通盛南路”→“江山路”→“东方大道高架”,“通盛大道”→“江山路”→“东方大道”。以此类推,最终得到第8步输出的2个目标候选路线。For the subsequent rows of the probability matrix, such as the first row after the first row, by calculating the conditional probability scores of the route where the current row is located under the 2 candidate routes corresponding to the 0th row, determine the top 2 routes with the highest scores as The candidate route obtained in step 2. For example, calculate the score of the conditional probability corresponding to each route in the first row in the probability matrix under the premise of "Tongsheng South Road" → "Jiangshan Road"; calculate the first row in the probability matrix under the premise of "Tongsheng Avenue" → "Jiangshan Road" The score of the conditional probability corresponding to each route, and the top 2 routes with the highest scores are determined as the target candidate routes of the second step. ", "Tongsheng Avenue" → "Jiangshan Road" → "Dongfang Avenue". By analogy, the 2 target candidate routes output in step 8 are finally obtained.

在操作S503,将上述目标候选路线中得分最大的路线确定为目标路线信息。In operation S503, the route with the largest score among the above-mentioned target candidate routes is determined as the target route information.

例如,将第8步输出的2个目标候选路线中得分最大的路线确定为目标路线信息。For example, the route with the largest score among the two target candidate routes output in step 8 is determined as the target route information.

基于上述操作S501~S503,能够在有限的计算空间内实现高效率计算,快速定位至目标路线信息且目标路线信息大概率符合用户输入的规划路线信息。Based on the above operations S501 to S503 , efficient calculation can be achieved in a limited computing space, and target route information can be quickly located, and the target route information is likely to conform to the planned route information input by the user.

在一实施例中,基于设定搜索束宽K(例如K=2~3),对概率矩阵P逐行进行束搜索。In an embodiment, based on the set search beam width K (eg, K=2˜3), the beam search is performed row by row on the probability matrix P.

对于时间步t,计算得分

Figure BDA0003652866220000171
Figure BDA0003652866220000172
其中SC0,:=1.0。将SCt,:按从大到小排序,取前K个记录对应的得分SCt,s进入下一个时间步的计算和排序,并记录相应的序号/索引s的取值序列。For time step t, compute the score
Figure BDA0003652866220000171
Figure BDA0003652866220000172
where SC 0,: =1.0. Sort SC t,: in descending order, take the scores SC t,s corresponding to the first K records and enter the calculation and sorting of the next time step, and record the value sequence of the corresponding serial number/index s.

其中,这里的log(Pt+i-1,s)函数采用以10为底进行计算,因此通过log前的负号使得取值变为正值。Among them, the log(P t+i-1,s ) function here is calculated using the base 10, so the negative sign before the log makes the value become a positive value.

例如,在第1步(时间步t=1)的搜索中,先针对概率矩阵P中的第0行的概率向量P0,s进行搜索,计算得到得分最高的前2(K=2的示例)个路线为候选路线。For example, in the search of the first step (time step t=1), the probability vector P 0,s of the 0th row in the probability matrix P is first searched, and the top 2 (K=2 examples) with the highest scores are calculated. ) routes are candidate routes.

最终取max(sn-1,:)作为束搜索结果,根据对应的索引s的取值序列S和前路段候选路网道路Ci、后路段候选路网道路Ci+1从前往后进行解码。xi=Si-1%|Ci|,i=1,2,…,n-1,特别的x0=S0/|C1|,xi分别是最终选择的Ci候选道路索引,从而得到最终转换后的路网道路序列。Finally, max(s n-1,: ) is taken as the beam search result, according to the value sequence S of the corresponding index s, the candidate road network road C i of the front section, and the candidate road network road C i+1 of the rear section, from front to back. decoding. x i =S i-1 %|C i |, i=1,2,...,n-1, especially x 0 =S 0 /|C 1 |, x i are the final selected C i candidate road indices respectively , so as to obtain the final converted road sequence of the road network.

例如针对上述规划路线信息为序列Ra的实施例,得到的序号/索引s的取值序列S为[2,1,3,0,1,1,0,0]。For example, for the above-mentioned embodiment in which the planned route information is the sequence Ra, the obtained value sequence S of the sequence number/index s is [2, 1, 3, 0, 1, 1, 0, 0].

x0=J0/|C1|=2/1=2,x1=J0%|C1|=2%1=0,则对应选取“通盛南路”、“江山路”作为最终选择的第一、第二路段候选道路。x2=J1%|C2|=1%7=1,对应选取“东方大道高架”作为最终选择的第三路段候选道路。通过上述方式依次解码得到的最终结果为[“通盛南路”,“江山路”,“东方大道高架”,“通沪大道”,“沈海高速公路”,“洋通高速公路”,“东二环”,“S223”,“G328”]。x 0 =J 0 /|C 1 |=2/1=2, x 1 =J 0 %|C 1 |=2% 1=0, then correspondingly select "Tongsheng South Road" and "Jiangshan Road" as the final choice The candidate roads of the first and second road segments. x 2 =J 1 %|C 2 |=1% 7=1, correspondingly, “Dongfang Avenue Elevated” is selected as the finally selected candidate road for the third road segment. The final results obtained by decoding in sequence through the above methods are ["Tongsheng South Road", "Jiangshan Road", "Dongfang Avenue Elevated", "Tonghu Avenue", "Shenhai Expressway", "Yangtong Expressway", "East Second Ring", "S223", "G328"].

本公开的第二个示例性实施例提供了一种路径监测的方法。The second exemplary embodiment of the present disclosure provides a method for path monitoring.

图6示意性地示出了根据本公开实施例的路径监测的方法的流程图。FIG. 6 schematically shows a flowchart of a method for path monitoring according to an embodiment of the present disclosure.

参照图6所示,本公开实施例提供的路径监测的方法包括以下操作:S601、S602、S603和S604。该操作S601~S604可以由终端设备执行,或者也可以由服务器执行。Referring to FIG. 6 , the method for path monitoring provided by the embodiment of the present disclosure includes the following operations: S601, S602, S603, and S604. The operations S601 to S604 may be performed by a terminal device, or may also be performed by a server.

在操作S601,采用对齐路线数据的方法来确定行驶对象的目标路线信息。In operation S601, the method of aligning the route data is adopted to determine the target route information of the traveling object.

该操作S601可以采用第一个实施例描述的包含操作S201~S203的方法实现。The operation S601 may be implemented by using the method including the operations S201 to S203 described in the first embodiment.

在操作S602,获取上述行驶对象的实际路线信息。In operation S602, actual route information of the above-mentioned traveling object is acquired.

上述实际路线信息可以是由终端设备或服务器通过路径监管应用自身所具有的实际行驶路径监测的功能来获取,或者通过路径监管应用向开通数据访问权限的地图导航系统或者其他行驶路径监测系统进行获取。The above-mentioned actual route information can be obtained by the terminal device or server through the actual driving route monitoring function of the route supervision application itself, or obtained through the route supervision application from a map navigation system or other driving route monitoring system that has opened data access rights. .

在操作S603,对上述实际路线信息与上述目标路线信息进行匹配。In operation S603, the above-mentioned actual route information and the above-mentioned target route information are matched.

例如可以通过逐路段进行对比的方式来进行实际路线信息与目标路线信息的匹配。For example, the matching between the actual route information and the target route information can be performed by way of comparison by road segment.

在操作S604,在上述实际路线信息与上述目标路线信息不匹配的情况下,生成路线偏离的预警信息。In operation S604, in the case that the above-mentioned actual route information does not match the above-mentioned target route information, early warning information of route deviation is generated.

生成的预警信息可以反馈给管理员一侧,让管理员(例如路径监管部门的相关人员)决定是否采用对应的监管措施;生成的预警信息也可以反馈给使用路径监管应用的运输车辆的相关人员,使得运输车辆的相关人员根据预警信息核查自身的行驶路线是否偏离规划路线信息。The generated early warning information can be fed back to the administrator, allowing the administrator (such as the relevant personnel of the route supervision department) to decide whether to adopt the corresponding supervision measures; the generated early warning information can also be fed back to the relevant personnel of the transport vehicles using the route supervision application , so that the relevant personnel of the transport vehicle check whether their own driving route deviates from the planned route information according to the warning information.

基于上述操作S601~S604,能够实现将文字输入的规划路线信息向现实存在的路网信息的对齐,并能够一定程度上克服由于填写/输入错误或不规范导致的无法匹配实际道路的问题;另外通过对实际路线信息的获取和对实际路线信息与目标路线信息进行对比匹配,能够基于上述目标路线信息来对用户的实际路线进行监管和预警提示,可以应用至市域治理危化品车辆的运输路线监管的场景。Based on the above operations S601 to S604, it is possible to align the planned route information inputted by text to the actual road network information, and to a certain extent overcome the problem that the actual road cannot be matched due to filling/input errors or irregularities; By acquiring the actual route information and comparing and matching the actual route information with the target route information, the user's actual route can be supervised and alerted based on the above target route information, which can be applied to the transportation routes of vehicles for urban management of hazardous chemicals regulatory scenarios.

本公开的第三个示例性实施例提供了一种对齐路线数据的装置。A third exemplary embodiment of the present disclosure provides an apparatus for aligning route data.

图7示意性地示出了根据本公开实施例的对齐路线数据的装置的结构框图。FIG. 7 schematically shows a structural block diagram of an apparatus for aligning route data according to an embodiment of the present disclosure.

参照图7所示,本公开实施例提供的对齐路线数据的装置700包括:路网匹配模块701、概率计算模块702和处理模块703。Referring to FIG. 7 , an apparatus 700 for aligning route data provided by an embodiment of the present disclosure includes: a road network matching module 701 , a probability calculation module 702 and a processing module 703 .

上述路网匹配模块701用于根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路。上述路网匹配模块701包含用于实现上述操作S311~S312、S321~S323、S331~S334、S341~S345所对应的功能模块或功能子模块。The above-mentioned road network matching module 701 is configured to determine candidate road network roads associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object. The above-mentioned road network matching module 701 includes functional modules or functional sub-modules corresponding to the above-mentioned operations S311-S312, S321-S323, S331-S334, and S341-S345.

上述概率计算模块702用于根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵。上述概率计算模块702包含用于实现上述操作S401~S405所对应的功能模块或功能子模块。The above-mentioned probability calculation module 702 is configured to calculate the probability of each route between adjacent road segments according to the distance between each candidate road network road of adjacent road segments, and obtain a probability matrix including the probabilities of routes between all adjacent road segments. The above-mentioned probability calculation module 702 includes function modules or function sub-modules corresponding to the above-mentioned operations S401 to S405.

上述处理模块703用于对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。上述处理模块703包含用于实现上述操作S501~S503所对应的功能模块或功能子模块。The above-mentioned processing module 703 is configured to perform beam search processing on the above-mentioned probability matrix to obtain target route information in the road network. The above-mentioned processing module 703 includes function modules or function sub-modules corresponding to the above-mentioned operations S501 to S503.

本公开的第四个示例性实施例提供了一种路径监测的装置。A fourth exemplary embodiment of the present disclosure provides an apparatus for path monitoring.

图8示意性地示出了根据本公开实施例的路径监测的装置的结构框图。FIG. 8 schematically shows a structural block diagram of an apparatus for path monitoring according to an embodiment of the present disclosure.

参照图8所示,本公开实施例提供的路径监测的装置800包括:路网匹配模块801、概率计算模块802、处理模块803、实际路线获取模块804、路线信息匹配模块805和预警信息生成模块806。Referring to FIG. 8 , an apparatus 800 for route monitoring provided by an embodiment of the present disclosure includes: a road network matching module 801, a probability calculation module 802, a processing module 803, an actual route acquisition module 804, a route information matching module 805, and an early warning information generation module 806.

上述路网匹配模块801用于根据行驶对象的规划路线信息,从路网道路库中确定与上述规划路线信息关联的候选路网道路。The above-mentioned road network matching module 801 is configured to determine candidate road network roads associated with the above-mentioned planned route information from the road network road library according to the planned route information of the traveling object.

上述概率计算模块802用于根据相邻路段的各个候选路网道路之间的距离,计算相邻路段之间的各条路线的概率,得到包含所有相邻路段之间路线的概率的概率矩阵。The above probability calculation module 802 is configured to calculate the probability of each route between adjacent road segments according to the distance between each candidate road network road of adjacent road segments, and obtain a probability matrix including the probabilities of routes between all adjacent road segments.

上述处理模块803用于对上述概率矩阵进行束搜索处理,得到路网道路中的目标路线信息。The above-mentioned processing module 803 is configured to perform beam search processing on the above-mentioned probability matrix to obtain target route information in the road network.

上述实际路线获取模块804用于获取上述行驶对象的实际路线信息。The above-mentioned actual route obtaining module 804 is configured to obtain the actual route information of the above-mentioned traveling object.

上述路线信息匹配模块805用于对上述实际路线信息与上述目标路线信息进行匹配。The above-mentioned route information matching module 805 is configured to match the above-mentioned actual route information with the above-mentioned target route information.

上述预警信息生成模块806用于在上述实际路线信息与上述目标路线信息不匹配的情况下,生成路线偏离的预警信息。The above-mentioned early warning information generating module 806 is configured to generate early warning information of route deviation when the above-mentioned actual route information does not match the above-mentioned target route information.

上述对齐路线数据的装置700中的各个模块或者上述路径监测的装置800中的各个模块中的任意多个可以合并在一个模块中实现,或者其中的任意一个模块可以被拆分成多个模块。或者,这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合,并在一个模块中实现。对齐路线数据的装置700中的各个模块或者上述路径监测的装置800中的各个模块中的至少一个可以至少被部分地实现为硬件电路,例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC),或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现,或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者,对齐路线数据的装置700中的各个模块或者上述路径监测的装置800中的各个模块中的至少一个可以至少被部分地实现为计算机程序模块,当该计算机程序模块被运行时,可以执行相应的功能。Any of the modules in the apparatus 700 for aligning route data or the modules in the apparatus 800 for path monitoring may be combined into one module, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. At least one of the respective modules in the apparatus 700 for aligning route data or the respective modules in the above-mentioned path monitoring apparatus 800 may be implemented at least partially as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array ( PLA), system-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuits, such as hardware or firmware, or in software, hardware and any one of the three implementation manners of firmware or an appropriate combination of any of them. Alternatively, at least one of the various modules in the apparatus 700 for aligning route data or the various modules in the above-mentioned path monitoring apparatus 800 may be at least partially implemented as a computer program module, and when the computer program module is executed, it can execute the corresponding function.

本公开的第五个示例性实施例提供了一种电子设备。A fifth exemplary embodiment of the present disclosure provides an electronic device.

图9示意性示出了本公开实施例提供的电子设备的结构框图。FIG. 9 schematically shows a structural block diagram of an electronic device provided by an embodiment of the present disclosure.

参照图9所示,本公开实施例提供的电子设备900包括处理器901、通信接口902、存储器903和通信总线904,其中,处理器901、通信接口902和存储器903通过通信总线904完成相互间的通信;存储器903,用于存放计算机程序;处理器901,用于执行存储器上所存放的程序时,实现如上所述的对齐路线数据的方法或路径监测的方法。Referring to FIG. 9 , an electronic device 900 provided by an embodiment of the present disclosure includes a processor 901 , a communication interface 902 , a memory 903 , and a communication bus 904 , wherein the processor 901 , the communication interface 902 and the memory 903 communicate with each other through the communication bus 904 The memory 903 is used to store the computer program; the processor 901 is used to implement the method for aligning route data or the method for path monitoring as described above when executing the program stored in the memory.

本公开的第六个示例性实施例还提供了一种计算机可读存储介质。上述计算机可读存储介质上存储有计算机程序,上述计算机程序被处理器执行时实现如上所述的对齐路线数据的方法或路径监测的方法。The sixth exemplary embodiment of the present disclosure also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the method for aligning route data or the method for path monitoring as described above is implemented.

该计算机可读存储介质可以是上述实施例中描述的设备/装置中所包含的;也可以是单独存在,而未装配入该设备/装置中。上述计算机可读存储介质承载有一个或者多个程序,当上述一个或者多个程序被执行时,实现根据本公开实施例的方法。The computer-readable storage medium may be included in the apparatus/apparatus described in the above embodiments; or may exist alone without being assembled into the apparatus/apparatus. The above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, implement the method according to the embodiment of the present disclosure.

根据本公开的实施例,计算机可读存储介质可以是非易失性的计算机可读存储介质,例如可以包括但不限于:便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM) , erasable programmable read only memory (EPROM or flash memory), portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

需要说明的是,在本文中,诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。It should be noted that, in this document, relational terms such as "first" and "second" etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these There is no such actual relationship or sequence between entities or operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

以上所述仅是本公开的具体实施方式,使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的,本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下,在其它实施例中实现。因此,本公开将不会被限制于本文所示的这些实施例,而是要符合与本文所申请的原理和新颖特点相一致的最宽的范围。The above descriptions are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Thus, the present disclosure is not to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims (12)

1. A method of aligning route data, comprising:
determining candidate road networks associated with the planned route information from a road network road library according to the planned route information of the driving object;
calculating the probability of each route between adjacent road sections according to the distance between each candidate road network road of the adjacent road sections to obtain a probability matrix containing the probability of all the routes between the adjacent road sections;
and performing beam search processing on the probability matrix to obtain target route information in the road network.
2. The method according to claim 1, wherein calculating the probability of each route between adjacent road segments according to the distance between the candidate road networks of the adjacent road segments to obtain a probability matrix containing the probability of the route between all adjacent road segments comprises:
calculating the distance between every two candidate road networks of the current road section and the next road section aiming at any one road section in all the road sections to obtain a distance vector consisting of distance elements corresponding to the current road section;
obtaining a distance matrix according to the distance vectors of all road sections;
performing numerical transformation on the distance vector of each row in the distance matrix to obtain a transformed target distance vector, wherein the sum of corresponding distance elements before and after transformation is a fixed value;
inputting each target distance vector into a soft maximization function for processing, and outputting to obtain a probability distribution value corresponding to each distance element in the target distance vector, wherein the probability distribution value corresponding to the current distance element is used for representing the probability of a route corresponding to the current distance element;
and obtaining a probability matrix containing the probability of the routes between all adjacent road sections according to the probability distribution values correspondingly obtained by all the target distance vectors.
3. The method according to claim 2, wherein the obtaining a distance matrix according to the distance vectors of all road segments comprises:
taking the distance vector of each road section in all road sections as each row of the distance matrix;
taking the maximum value of the column number of the distance vectors in all road sections as the column scale of the distance matrix, and supplementing a default value in a specific distance vector of which the column number is smaller than the column scale;
when the distance vector of each row is subjected to numerical conversion, the default value does not participate in calculation, and the difference between the maximum value of the distance element in the current distance vector and each distance element is adopted to obtain the converted distance element; and when the target distance vector is input into a soft maximization function for processing, the output probability corresponding to the default value is a preset value.
4. The method of claim 1, wherein the performing a beam search process on the probability matrix to obtain target route information comprises:
determining the first K routes corresponding to the highest probability score of the routes between each group of adjacent road sections in the current row as candidate routes aiming at the first row of the probability matrix, wherein K is a set search beam width;
for each row in the subsequent rows after the first row of the probability matrix, determining the scores of the conditional probabilities of the routes corresponding to the current row on the premise of K candidate routes corresponding to the previous row respectively, and determining the first K corresponding routes with the highest scores of the conditional probabilities as target candidate routes;
and determining the route with the largest score in the target candidate routes as target route information.
5. The method of claim 1, wherein the planning route information comprises: a sequence formed by all road sections passing through in sequence;
the method for determining candidate road network roads associated with the planned route information from a road network road library according to the planned route information of the driving object comprises the following steps:
extracting texts of all road sections in the planned route information to obtain road section key information for each road section;
and screening and matching in a road network road library according to the key information of the road sections to obtain candidate road networks for each road section.
6. The method according to claim 5, wherein determining candidate road network roads associated with the planned route information from a road network road library based on the planned route information of the traveling object further comprises:
and in the case that no candidate road network road matched with the key information of the specific road section exists, according to the candidate road network road of the adjacent road section adjacent to the specific road section, determining the specific road network road intersected with the candidate road network road of the adjacent road section as the candidate road network road for the specific road section in the road network road library.
7. The method according to claim 5 or 6, wherein the step of performing screening matching in a road network road library according to the key information of the road segment to obtain candidate road network roads for each road segment comprises:
screening and matching are carried out in a road network road library according to the road section keyword information to obtain candidate road network roads for each road section; under the condition that no candidate road network road matched with the road section key word information of the specific road section exists, determining that no candidate road network road matched with the road section key information of the specific road section exists; or,
screening and matching are carried out in a road network road library according to the road section keyword information to obtain candidate road network roads for each road section; under the condition that no candidate road network road matched with the road section keyword information of the specific road section exists, the road section keyword information of the specific road section is split into more granular road section keyword information; screening and matching in a road network road library according to the road section keyword information to obtain candidate road network roads for the specific road section; and in the case that there is no candidate road network road matching the link key information of the specific link, determining that there is no candidate road network road matching the link key information of the specific link.
8. A method of path monitoring, comprising:
determining target route information of the driving object by adopting the method of aligning route data according to any one of claims 1 to 7;
acquiring actual route information of the driving object;
matching the actual route information with the target route information;
and generating early warning information of the deviation of the route under the condition that the actual route information is not matched with the target route information.
9. An apparatus for aligning route data, comprising:
the road network matching module is used for determining candidate road networks associated with the planned route information from a road network road library according to the planned route information of the driving object;
the probability calculation module is used for calculating the probability of each route between adjacent road sections according to the distance between each candidate road network road of the adjacent road sections to obtain a probability matrix containing the probability of all the routes between the adjacent road sections;
and the processing module is used for carrying out beam search processing on the probability matrix to obtain target route information in the road network.
10. An apparatus for path monitoring, comprising:
the road network matching module is used for determining candidate road networks associated with the planned route information from a road network road library according to the planned route information of the driving object;
the probability calculation module is used for calculating the probability of each route between adjacent road sections according to the distance between each candidate road network road of the adjacent road sections to obtain a probability matrix containing the probability of all the routes between the adjacent road sections;
the processing module is used for carrying out beam search processing on the probability matrix to obtain target route information in road networks;
the actual route acquiring module is used for acquiring actual route information of the driving object;
the route information matching module is used for matching the actual route information with the target route information;
and the early warning information generating module is used for generating early warning information of route deviation under the condition that the actual route information is not matched with the target route information.
11. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method of any one of claims 1 to 8 when executing a program stored on a memory.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1-8.
CN202210557664.2A 2022-05-19 2022-05-19 Method, device, electronic equipment and medium for aligning route data and path monitoring Active CN114881568B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210557664.2A CN114881568B (en) 2022-05-19 2022-05-19 Method, device, electronic equipment and medium for aligning route data and path monitoring

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210557664.2A CN114881568B (en) 2022-05-19 2022-05-19 Method, device, electronic equipment and medium for aligning route data and path monitoring

Publications (2)

Publication Number Publication Date
CN114881568A true CN114881568A (en) 2022-08-09
CN114881568B CN114881568B (en) 2025-05-23

Family

ID=82678348

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210557664.2A Active CN114881568B (en) 2022-05-19 2022-05-19 Method, device, electronic equipment and medium for aligning route data and path monitoring

Country Status (1)

Country Link
CN (1) CN114881568B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117708261A (en) * 2024-02-02 2024-03-15 腾讯科技(深圳)有限公司 Map data processing method, apparatus, device, storage medium, and program product

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101651788A (en) * 2008-12-26 2010-02-17 中国科学院声学研究所 Alignment system of on-line speech text and method thereof
CN109086914A (en) * 2018-07-12 2018-12-25 杭州电子科技大学 Harmful influence vehicle path planning modeling method based on dynamic domino risk
US20180374032A1 (en) * 2017-06-27 2018-12-27 Uber Technologies, Inc. Match-based route navigation system
KR101951595B1 (en) * 2018-05-18 2019-02-22 한양대학교 산학협력단 Vehicle trajectory prediction system and method based on modular recurrent neural network architecture
JP2021051711A (en) * 2019-09-20 2021-04-01 株式会社Nttドコモ Text processing apparatus, method, device, and computer-readable recording medium
CN114297338A (en) * 2021-12-02 2022-04-08 腾讯科技(深圳)有限公司 Text matching method, apparatus, storage medium and program product

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101651788A (en) * 2008-12-26 2010-02-17 中国科学院声学研究所 Alignment system of on-line speech text and method thereof
US20180374032A1 (en) * 2017-06-27 2018-12-27 Uber Technologies, Inc. Match-based route navigation system
KR101951595B1 (en) * 2018-05-18 2019-02-22 한양대학교 산학협력단 Vehicle trajectory prediction system and method based on modular recurrent neural network architecture
CN109086914A (en) * 2018-07-12 2018-12-25 杭州电子科技大学 Harmful influence vehicle path planning modeling method based on dynamic domino risk
JP2021051711A (en) * 2019-09-20 2021-04-01 株式会社Nttドコモ Text processing apparatus, method, device, and computer-readable recording medium
CN114297338A (en) * 2021-12-02 2022-04-08 腾讯科技(深圳)有限公司 Text matching method, apparatus, storage medium and program product

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117708261A (en) * 2024-02-02 2024-03-15 腾讯科技(深圳)有限公司 Map data processing method, apparatus, device, storage medium, and program product
CN117708261B (en) * 2024-02-02 2024-05-03 腾讯科技(深圳)有限公司 Map data processing method, apparatus, device, storage medium, and program product

Also Published As

Publication number Publication date
CN114881568B (en) 2025-05-23

Similar Documents

Publication Publication Date Title
US12361046B2 (en) Geo-fence based coordinate data processing method and apparatus, and computer device
US11080267B2 (en) Validating road intersections
Bilal et al. Guidelines for applied machine learning in construction industry—A case of profit margins estimation
US20190354689A1 (en) Deep neural network system for similarity-based graph representations
CN112949476B (en) Text relation detection method, device and storage medium based on graph convolution neural network
CN105531706A (en) Search Engines for Information Retrieval Systems
CN109658033B (en) Method, system, device and storage medium for calculating similarity of goods source route
CN109781132B (en) Experience route replacing method and device, electronic equipment and storage medium
CN114997263B (en) Method, device, equipment and storage medium for analyzing training rate based on machine learning
CN111930897A (en) Patent retrieval method, device, electronic equipment and computer-readable storage medium
CN114881568A (en) Method, apparatus, electronic device, and medium for aligning route data and monitoring path
US11513673B2 (en) Steering deep sequence model with prototypes
CN116304891A (en) Category prediction method and device based on multi-source data migration learning
CN115018656A (en) Risk identification method, and training method, device and equipment of risk identification model
CN114925165A (en) Consultation task decomposition method, system and platform
CN119294499A (en) Expert matching method and system based on large language model knowledge expansion and fusion
CN111797211B (en) Service information searching method, device, computer equipment and storage medium
CN116737111B (en) Safety demand analysis method based on scenerization
CN110321547B (en) A method and device for determining named entity
CN117033816A (en) Parking recommendation method and device, electronic equipment and storage medium
Zhang et al. Large language models for mobility analysis in transportation systems: A survey on forecasting tasks
Taşyürek A novel approach to improve the performance of the database storing big data with time information
CN114021751B (en) Work ticket generation method, device, computer equipment and storage medium
Tounsi et al. On coupling a content-based routing process with a multi-label residual convolutional neural network text classifier
CN120013694B (en) Tax platform cockpit data visualization method, device and storage medium

Legal Events

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