技术领域Technical field
本申请涉及地图导航技术领域，尤其涉及一种基于驾驶偏好的地图导航方法及装置。The present application relates to the field of map navigation technology, and in particular to a map navigation method and device based on driving preferences.
背景技术Background technique
目前车载地图导航系统的设计，一般以时间最短或路程最短作为规划目标生成导航方案，这类通用的导航方案虽然被广泛应用，但实际上忽略了用户的实际需求，可供用户手动设置的选项一般只有高速优先、收费成本等有限的路线推荐条件，忽略了用户更为个人化的偏好，最终输出的路径导航方案难以满足用户的个性化需求。The current design of vehicle map navigation systems generally uses the shortest time or shortest distance as the planning goal to generate navigation solutions. Although this type of general navigation solution is widely used, it actually ignores the actual needs of users and allows users to manually set options. Generally, there are only limited route recommendation conditions such as highway priority and toll cost, which ignores the user's more personal preferences, and the final output route navigation solution is difficult to meet the user's personalized needs.
因此，如何提供一种解决上述技术问题的方案是目前本领域技术人员需要解决的问题。Therefore, how to provide a solution to the above technical problems is currently a problem that those skilled in the art need to solve.
发明内容Contents of the invention
有鉴于此，本申请实施例提供了一种基于驾驶偏好的地图导航方法及装置，以解决现有技术无法满足用户的个性化需求的问题。In view of this, embodiments of the present application provide a map navigation method and device based on driving preferences to solve the problem that the existing technology cannot meet the personalized needs of users.
本申请实施例的第一方面，提供了一种基于驾驶偏好的地图导航方法，包括：The first aspect of the embodiment of the present application provides a map navigation method based on driving preferences, including:
获取当前车辆的历史数据；历史数据包括历史行驶时间与历史行驶轨迹；Obtain historical data of the current vehicle; historical data includes historical driving time and historical driving trajectory;
利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数；偏好参数用于表征当前车辆对各路线特征的偏好程度；Use machine learning algorithms to analyze historical data and determine the preference parameters of route features; the preference parameters are used to characterize the current vehicle's preference for each route feature;
接收导航指令；receive navigation instructions;
基于偏好参数，在导航地图上规划导航指令对应的导航路径，并将导航路径输出到用户终端。Based on the preference parameters, a navigation path corresponding to the navigation instruction is planned on the navigation map, and the navigation path is output to the user terminal.
本申请实施例的第二方面，提供了一种基于驾驶偏好的地图导航装置，包括：A second aspect of the embodiment of the present application provides a map navigation device based on driving preferences, including:
历史数据获取模块，用于获取当前车辆的历史数据；历史数据包括历史行驶时间与历史行驶轨迹；The historical data acquisition module is used to obtain historical data of the current vehicle; historical data includes historical driving time and historical driving trajectory;
偏好分析模块，用于利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数；偏好参数用于表征当前车辆对各路线特征的偏好程度；The preference analysis module is used to analyze historical data using machine learning algorithms to determine the preference parameters of route features; the preference parameters are used to characterize the current vehicle's preference for each route feature;
导航指令接收模块，用于接收导航指令；Navigation instruction receiving module, used to receive navigation instructions;
导航规划模块，用于基于偏好参数，在导航地图上规划导航指令对应的导航路径，并将导航路径输出到用户终端。The navigation planning module is used to plan the navigation path corresponding to the navigation instruction on the navigation map based on the preference parameters, and output the navigation path to the user terminal.
本申请实施例的第三方面，提供了一种电子设备，包括存储器、处理器以及存储在存储器中并且可在处理器上运行的计算机程序，该处理器执行计算机程序时实现上述方法的步骤。A third aspect of the embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.
本申请实施例与现有技术相比存在的有益效果至少包括：本申请实施例通过对历史数据进行分析确定各路线特征的偏好参数，然后基于偏好参数规划导航指令所对应的导航路径，由于路线特征的偏好参数基于历史数据得到，因此能够反映用户的驾驶偏好，将该偏好参数加入导航路径的规划中能够进一步提高导航路径与用户的驾驶偏好的契合度，生成的导航路径能够进一步满足用户需求，进而提升用户体验。Compared with the prior art, the beneficial effects of the embodiments of the present application include at least: the embodiments of the present application determine the preference parameters of each route feature by analyzing historical data, and then plan the navigation path corresponding to the navigation instruction based on the preference parameters. Since the route The preference parameter of the feature is obtained based on historical data, so it can reflect the user's driving preference. Adding this preference parameter to the planning of the navigation path can further improve the fit between the navigation path and the user's driving preference, and the generated navigation path can further meet the user's needs. , thereby improving user experience.
附图说明Description of drawings
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of the present application. For some embodiments, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.
图1是本申请实施例的一种应用场景的场景示意图；Figure 1 is a schematic diagram of an application scenario according to the embodiment of the present application;
图2是本申请实施例提供的一种基于驾驶偏好的地图导航方法的流程示意图；Figure 2 is a schematic flowchart of a map navigation method based on driving preferences provided by an embodiment of the present application;
图3是本申请实施例提供的一种导航地图的初始规划路径的示意图；Figure 3 is a schematic diagram of an initial planned path of a navigation map provided by an embodiment of the present application;
图4是本申请实施例提供的一种导航地图的修正后的规划路径的示意图；Figure 4 is a schematic diagram of a modified planned path of a navigation map provided by an embodiment of the present application;
图5是本申请实施例提供的一种基于驾驶偏好的地图导航装置的结构示意图；Figure 5 is a schematic structural diagram of a map navigation device based on driving preferences provided by an embodiment of the present application;
图6是本申请实施例提供的一种电子设备的结构示意图。FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
具体实施方式Detailed ways
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures and technologies are provided to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
下面将结合附图详细说明根据本申请实施例的一种基于驾驶偏好的地图导航方法及装置。A driving preference-based map navigation method and device according to embodiments of the present application will be described in detail below with reference to the accompanying drawings.
图1是本申请实施例的应用场景的场景示意图。该应用场景可以包括第一终端设备101、第二终端设备102、第三终端设备103、服务器104以及网络105。Figure 1 is a schematic diagram of an application scenario according to an embodiment of the present application. The application scenario may include the first terminal device 101, the second terminal device 102, the third terminal device 103, the server 104 and the network 105.
第一终端设备101可以是硬件，也可以是软件。当第一终端设备101为硬件时，其可以是具有显示屏且支持与服务器104通信的各种电子设备，包括但不限于车机系统、智能手机、平板电脑、膝上型便携计算机和台式计算机等；当第一终端设备101为软件时，其可以安装在如上的电子设备中。第一终端设备101可以实现为多个软件或软件模块，也可以实现为单个软件或软件模块，本申请实施例对此不作限制。进一步地，第一终端设备101上可以安装有各种应用，例如数据处理应用、即时通信工具、社交平台软件、搜索类应用、购物类应用等。The first terminal device 101 may be hardware or software. When the first terminal device 101 is hardware, it can be various electronic devices having a display screen and supporting communication with the server 104, including but not limited to car systems, smart phones, tablets, laptop computers and desktop computers. etc.; when the first terminal device 101 is software, it can be installed in the above electronic device. The first terminal device 101 may be implemented as multiple software or software modules, or may be implemented as a single software or software module, which is not limited in the embodiment of the present application. Further, various applications may be installed on the first terminal device 101, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.
第二终端设备102可以是硬件，也可以是软件。当第二终端设备102为硬件时，其可以是具有显示屏且支持与服务器104通信的各种电子设备，包括但不限于车机系统、智能手机、平板电脑、膝上型便携计算机和台式计算机等；当第二终端设备102为软件时，其可以安装在如上的电子设备中。第二终端设备102可以实现为多个软件或软件模块，也可以实现为单个软件或软件模块，本申请实施例对此不作限制。进一步地，第二终端设备102上可以安装有各种应用，例如数据处理应用、即时通信工具、社交平台软件、搜索类应用、购物类应用等。The second terminal device 102 may be hardware or software. When the second terminal device 102 is hardware, it may be various electronic devices having a display screen and supporting communication with the server 104, including but not limited to car systems, smart phones, tablets, laptop computers and desktop computers. etc.; when the second terminal device 102 is software, it can be installed in the above electronic device. The second terminal device 102 may be implemented as multiple software or software modules, or may be implemented as a single software or software module, which is not limited in the embodiment of the present application. Further, various applications may be installed on the second terminal device 102, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.
第三终端设备103可以是硬件，也可以是软件。当第三终端设备103为硬件时，其可以是具有显示屏且支持与服务器104通信的各种电子设备，包括但不限于车机系统、智能手机、平板电脑、膝上型便携计算机和台式计算机等；当第三终端设备103为软件时，其可以安装在如上的电子设备中。第三终端设备103可以实现为多个软件或软件模块，也可以实现为单个软件或软件模块，本申请实施例对此不作限制。进一步地，第三终端设备103上可以安装有各种应用，例如数据处理应用、即时通信工具、社交平台软件、搜索类应用、购物类应用等。The third terminal device 103 may be hardware or software. When the third terminal device 103 is hardware, it may be various electronic devices having a display screen and supporting communication with the server 104, including but not limited to car systems, smart phones, tablets, laptop computers and desktop computers. etc.; when the third terminal device 103 is software, it can be installed in the above electronic device. The third terminal device 103 may be implemented as multiple software or software modules, or as a single software or software module, which is not limited in the embodiment of the present application. Further, various applications may be installed on the third terminal device 103, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.
服务器104可以是提供各种服务的服务器，例如，对与其建立通信连接的终端设备发送的请求进行接收的后台服务器，该后台服务器可以对终端设备发送的请求进行接收和分析等处理，并生成处理结果。服务器104可以是一台服务器，也可以是由若干台服务器组成的服务器集群，或者还可以是一个云计算服务中心，本申请实施例对此不作限制。The server 104 may be a server that provides various services, for example, a backend server that receives requests sent by terminal devices with which a communication connection is established. The backend server may receive and analyze requests sent by the terminal devices, and generate processing. result. The server 104 may be one server, a server cluster composed of several servers, or a cloud computing service center, which is not limited in the embodiment of the present application.
需要说明的是，服务器104可以是硬件，也可以是软件。当服务器104为硬件时，其可以是为第一终端设备101、第二终端设备102和第三终端设备103提供各种服务的各种电子设备。当服务器104为软件时，其可以是为第一终端设备101、第二终端设备102和第三终端设备103提供各种服务的多个软件或软件模块，也可以是为第一终端设备101、第二终端设备102和第三终端设备103提供各种服务的单个软件或软件模块，本申请实施例对此不作限制。It should be noted that the server 104 may be hardware or software. When the server 104 is hardware, it may be various electronic devices that provide various services for the first terminal device 101, the second terminal device 102, and the third terminal device 103. When the server 104 is software, it may be multiple software or software modules that provide various services for the first terminal device 101, the second terminal device 102, and the third terminal device 103, or it may be a software module for the first terminal device 101, the second terminal device 102, and the third terminal device 103. The second terminal device 102 and the third terminal device 103 provide individual software or software modules for various services, which are not limited in this embodiment of the present application.
网络105可以是采用同轴电缆、双绞线和光纤连接的有线网络，也可以是无需布线就能实现各种通信设备互联的无线网络，例如，蓝牙(Bluetooth)、近场通信(Near FieldCommunication，NFC)、红外(Infrared)等，本申请实施例对此不作限制。The network 105 can be a wired network connected by coaxial cables, twisted pairs and optical fibers, or a wireless network that can interconnect various communication devices without wiring, such as Bluetooth, Near Field Communication, NFC), infrared (Infrared), etc., the embodiments of the present application do not limit this.
需要说明的是，第一终端设备101、第二终端设备102、第三终端设备103、服务器104以及网络105的具体类型、数量和组合可以根据应用场景的实际需求进行调整，本申请实施例对此不作限制。It should be noted that the specific types, quantities and combinations of the first terminal device 101, the second terminal device 102, the third terminal device 103, the server 104 and the network 105 can be adjusted according to the actual needs of the application scenario. The embodiments of this application are This is not a limitation.
图2是本申请实施例提供的一种基于驾驶偏好的地图导航方法的流程示意图。图2的基于驾驶偏好的地图导航方法可以由图1的第一终端设备或第二终端设备或第三终端设备或服务器执行，本实施例中的用户终端可以由图1的第一终端设备或第二终端设备或第三终端设备实现。如图2所示，该地图导航方法包括：Figure 2 is a schematic flowchart of a map navigation method based on driving preferences provided by an embodiment of the present application. The driving preference-based map navigation method in Figure 2 can be executed by the first terminal device or the second terminal device or the third terminal device or the server in Figure 1 . The user terminal in this embodiment can be executed by the first terminal device in Figure 1 or the server. The second terminal device or the third terminal device realizes. As shown in Figure 2, the map navigation method includes:
S201：获取当前车辆的历史数据；历史数据包括历史行驶时间与历史行驶轨迹；S201: Obtain historical data of the current vehicle; historical data includes historical driving time and historical driving trajectory;
S202：利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数；偏好参数用于表征当前车辆对各路线特征的偏好程度；S202: Use machine learning algorithms to analyze historical data and determine the preference parameters of route features; the preference parameters are used to characterize the current vehicle's preference for each route feature;
S203：接收导航指令；S203: Receive navigation instructions;
S204：基于偏好参数，在导航地图上规划导航指令对应的导航路径，并将导航路径输出到用户终端。S204: Based on the preference parameters, plan a navigation path corresponding to the navigation instruction on the navigation map, and output the navigation path to the user terminal.
可以理解的是，当前车辆的历史数据包括实际的历史行驶轨迹以及每次历史行驶轨迹所对应的历史行驶时间，历史数据详细地描述了每次用户的历史驾驶行为，这些历史驾驶行为能够反映出用户的驾驶偏好，即对不同的路线特征的偏好程度，以表征用户是否倾向于某些线路特征，或排斥某些线路特征等等。偏好参数可通过步骤S202利用机器学习算法对历史数据进行分析实现，针对不同的线路特征，可选用不同的机器学习算法，具体根据实际情况进行选择。It can be understood that the historical data of the current vehicle includes the actual historical driving trajectory and the historical driving time corresponding to each historical driving trajectory. The historical data describes each user's historical driving behavior in detail, and these historical driving behaviors can reflect The user's driving preference, that is, the degree of preference for different route features, indicates whether the user prefers certain route features or rejects certain route features, etc. The preference parameter can be realized by analyzing historical data using a machine learning algorithm in step S202. Different machine learning algorithms can be used for different line characteristics, and the selection is made based on the actual situation.
在步骤S201-S202确定偏好参数后，如果接收到导航指令，则基于偏好参数为导航指令规划更为符合用户的驾驶偏好的导航路径，此处导航路径区别于通用导航算法生成的常规导航路径，相对而言本实施例中的导航路径与用户的驾驶偏好更契合，用户以该导航路径行驶时适应性更好，体验更舒适。After the preference parameters are determined in steps S201-S202, if a navigation instruction is received, a navigation path that is more in line with the user's driving preference is planned for the navigation instruction based on the preference parameters, where the navigation path is different from the conventional navigation path generated by a general navigation algorithm. Relatively speaking, the navigation path in this embodiment is more consistent with the user's driving preference. The user has better adaptability and a more comfortable experience when driving on this navigation path.
可以理解的是，步骤S201在获取当前车辆的历史数据时，一般在得到用户的明确授权后进行，即本实施例方法的执行主体为用户提供明确的用户协议或隐私政策，详细解释数据手机的目的、类型以及数据将如何使用，用户需要明确同意并授权系统收集其个人数据，并通过点击对应授权意图向执行主体确认授权，之后再执行步骤S201的动作。It can be understood that when obtaining the historical data of the current vehicle in step S201, it is generally performed after obtaining explicit authorization from the user. That is, the execution subject of the method in this embodiment provides the user with a clear user agreement or privacy policy, explaining in detail the details of the data mobile phone. Regarding the purpose, type and how the data will be used, the user needs to explicitly agree and authorize the system to collect his or her personal data, and confirm the authorization with the execution subject by clicking on the corresponding authorization intention, and then perform the action of step S201.
具体的，步骤S201中收集到的历史数据包括历史行驶数据和历史行驶轨迹，还可包括用户搜索数据、收藏地点等，历史数据的数据来源包括车辆传感器、智能手机应用、车载摄像头等，其中车辆传感器包括GNSS(Global Navigation Satellite System，全球导航卫星系统)、加速度计、刹车传感器等，用于获取车辆的位置、速度、加速度和刹车等行驶数据；智能手机应用与车辆传感器类似，可以在车辆传感器数据缺失或明显有误时进行补充；车载摄像头用于获取道路情况、交通信号等行驶数据。可以理解的是根据这些原始的行驶数据还可进一步确定历史行驶时间和历史行驶轨迹，历史行驶轨迹指车辆的位置变化轨迹以及行驶车速变化情况，历史行驶时间对应位置变化轨迹，包括每次的行驶时间段、出发时刻、结束时刻、过程中停留时长等等。除此外智能手机应用和车载导航系统还可将用户输入的搜索数据、收藏地点等纳入历史数据中。Specifically, the historical data collected in step S201 includes historical driving data and historical driving trajectories, and may also include user search data, collection locations, etc. The data sources of historical data include vehicle sensors, smartphone applications, vehicle cameras, etc., among which the vehicle Sensors include GNSS (Global Navigation Satellite System), accelerometers, brake sensors, etc., which are used to obtain vehicle position, speed, acceleration, braking and other driving data; smartphone applications are similar to vehicle sensors and can be used on vehicle sensors Supplement the data when it is missing or obviously wrong; on-board cameras are used to obtain driving data such as road conditions and traffic signals. It is understandable that the historical driving time and historical driving trajectory can be further determined based on these original driving data. The historical driving trajectory refers to the position change trajectory of the vehicle and the driving speed change. The historical driving time corresponds to the position change trajectory, including each trip. Time period, starting time, ending time, length of stay during the process, etc. In addition, smartphone applications and car navigation systems can also incorporate user-entered search data, favorite locations, etc. into historical data.
在获取到历史数据后，首先进行数据预处理，数据预处理包括处理缺失值、异常值和数据标准化，以确保历史数据的一致性和可用性。数据预处理还可包括整合不同来源的数据，例如将车辆传感器的数据与智能手机应用的数据进行关联，以获取更全面的用户行为信息。After obtaining historical data, data preprocessing is first performed. Data preprocessing includes processing missing values, outliers and data standardization to ensure the consistency and availability of historical data. Data preprocessing can also include integrating data from different sources, such as correlating data from vehicle sensors with data from smartphone apps, to obtain a more comprehensive picture of user behavior.
然后执行步骤S202，利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数，可以理解的是不同的历史数据本身体现出不同的路线特征，历史数据中各路线特征的出现频次，即反映了用户的驾驶偏好。因此步骤S202利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数之前，还包括：Then step S202 is performed, using a machine learning algorithm to analyze the historical data and determine the preference parameters of the route features. It can be understood that different historical data themselves reflect different route features, and the frequency of occurrence of each route feature in the historical data reflects the user’s driving preferences. Therefore, before step S202 uses a machine learning algorithm to analyze historical data and determine the preference parameters of route characteristics, it also includes:
基于路线特征，对历史数据标记符合各路线特征的标签；Based on the route characteristics, label the historical data with labels that match the characteristics of each route;
相应的步骤S202利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：The corresponding step S202 uses a machine learning algorithm to analyze historical data and determine the preferred parameters of route characteristics, including:
利用机器学习算法对标记了标签的历史数据进行分析，确定路线特征的偏好参数。Machine learning algorithms are used to analyze tagged historical data to determine the preferred parameters of route characteristics.
具体的，路线特征包括交通流量、道路类型、道路坡度、景观类型、经停点类型中的一种或多种。其中交通流量可以是实际的交通流量数值，也可以是按照交通流量数值划分的多个等级，例如通畅、较为通畅、较为拥堵、拥堵、机器拥堵等；道路类型则包括快速道路、高速公路、一级公路、二级公路等；道路坡度用于表征道路的坡度起伏情况，例如整体平缓、盘山、存在起伏、起伏变化频次高、起伏幅度较大等；景观类型用于表征道路的景观的具体类型和风景级别，例如景观优美的道路、景观常规的道路、无景观的道路、无景观且卫生环境较差的道路等；将车辆在某一区域停留超过预设时间的停留点位置作为经停点，对应的类型也即经停点类型，包括购物区、餐厅区、公园区、工业园区、居民区等。可以理解的是，除了以上具体描述，路线特征还可根据实际需求或用户选择进行增删或修改，例如出发时间、行驶时间段、出行日期的选择等，此处不作限制。Specifically, the route characteristics include one or more of traffic flow, road type, road slope, landscape type, and stop type. The traffic flow can be the actual traffic flow value, or it can be multiple levels divided according to the traffic flow value, such as smooth, relatively smooth, relatively congested, congested, machine congestion, etc.; road types include expressways, highways, and highways. Class-grade highways, secondary highways, etc.; road slope is used to characterize the slope fluctuations of the road, such as overall gentleness, winding hills, existence of fluctuations, high frequency of fluctuations, large fluctuations, etc.; landscape type is used to characterize the specific type of landscape of the road. and scenery level, such as roads with beautiful scenery, roads with regular scenery, roads without scenery, roads without scenery and poor sanitary environment, etc.; the stopping points where vehicles stay in a certain area for more than the preset time are used as stopping points , the corresponding type is also the stopping point type, including shopping areas, restaurant areas, park areas, industrial parks, residential areas, etc. It can be understood that, in addition to the above specific description, route characteristics can also be added, deleted or modified according to actual needs or user selection, such as departure time, driving time period, travel date selection, etc., and there are no restrictions here.
进一步的对历史数据进行分析，确定路线特征的偏好参数，此处路线特征的偏好参数指的是各路线特征的偏好程度，例如历史数据中没有标记某个路线特征，或标记某个路线特征的记录较少，则可能反映出用户对该路线特征的偏好程度较低。在数学角度，偏好参数指预测出用户是否接收该路线特征的概率，基于该偏好参数，可以得到用户的具体驾驶习惯，例如是否倾向于快速道路、是否倾向于风景优美的路线、是否偏向于避免高峰交通等等。具体的偏好参数可通过具体的机器学习算法对历史数据进行分析实现，此处可选的机器学习算法包括监督学习、无监督学习、深度学习、分类算法、聚类算法或回归算法，根据不同的问题和数据类型选择合适的机器学习方法。Further analyze the historical data to determine the preference parameters of the route features. The preference parameters of the route features here refer to the preference degree of each route feature. For example, a certain route feature is not marked in the historical data, or a certain route feature is marked. Fewer records may reflect a lower user preference for this route feature. From a mathematical perspective, the preference parameter refers to the probability of predicting whether the user will accept the route features. Based on the preference parameter, the user's specific driving habits can be obtained, such as whether he prefers fast roads, whether he prefers scenic routes, and whether he prefers to avoid rush hour traffic and so on. Specific preference parameters can be realized by analyzing historical data using specific machine learning algorithms. Optional machine learning algorithms here include supervised learning, unsupervised learning, deep learning, classification algorithms, clustering algorithms or regression algorithms. Depending on the Choose an appropriate machine learning method for the problem and data type.
具体的，利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：Specifically, the process of using machine learning algorithms to analyze historical data and determine the preferred parameters of route characteristics includes:
利用决策树算法或回归分析算法对历史数据进行分析，确定路线特征为任一预设行驶场景时的偏好参数，预设行驶场景包括不同交通流量的路段、不同道路类型的路段、不同道路坡度的路段、不同景观类型的路段中的一种或多种。Use the decision tree algorithm or regression analysis algorithm to analyze historical data and determine the route characteristics as the preferred parameters for any preset driving scenario. The preset driving scenario includes sections with different traffic flows, sections with different road types, and sections with different road gradients. One or more of road segments and road segments of different landscape types.
或者，利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：Alternatively, the process of using machine learning algorithms to analyze historical data and determine the preferred parameters of route characteristics includes:
利用聚类分析算法对历史数据进行分析，确定路线特征为任一经停点类型时的偏好参数，经停点类型包括购物区、餐厅区、公园区、工业园区、居民区中的一种或多种。Use the cluster analysis algorithm to analyze historical data and determine the preferred parameters when the route characteristics are any stop type. The stop types include one or more of shopping areas, restaurant areas, parks, industrial parks, and residential areas. kind.
又或者，利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：Or, the process of using machine learning algorithms to analyze historical data and determine the preferred parameters of route characteristics includes:
利用深度学习算法对历史数据进行分析，确定多个路线特征的偏好参数，多个路线特征包括交通流量、道路类型、道路坡度、景观类型、经停点类型中的多个。Use deep learning algorithms to analyze historical data and determine the preference parameters of multiple route features, including traffic flow, road type, road slope, landscape type, and stop point type.
其中，决策树算法是一种用于分类和回归的监督学习算法，在构建一棵决策树时，决策树的节点包括各种特征，如出发时间、目的地、线路特征等，通过分析历史数据生成完整的决策树，进而预测不同导航指令下的用户路线选择，例如预测用户是否更倾向避开高峰时段的路线，或是否更倾向于快速道路等。Among them, the decision tree algorithm is a supervised learning algorithm for classification and regression. When building a decision tree, the nodes of the decision tree include various features, such as departure time, destination, route characteristics, etc., by analyzing historical data Generate a complete decision tree to predict user route choices under different navigation instructions, such as predicting whether users prefer routes that avoid peak hours or whether they prefer express roads, etc.
类似的，回归分析算法用于建立输入特征和目标变量之间的关系，以进行预测，在本实施例中回归分析算法可用于预测用户对特定路线特征的偏好程度，包括对不同交通流量、不同道路类型、不同道路类型等的偏好程度。Similarly, the regression analysis algorithm is used to establish the relationship between input features and target variables for prediction. In this embodiment, the regression analysis algorithm can be used to predict the user's preference for specific route features, including different traffic flows, different Road types, degree of preference for different road types, etc.
进一步的，聚类分析算法是一种无监督学习算法，用于将数据点分组成具有相似特征的簇。在本实施例中，聚类分析算法可以用于识别用户的兴趣点偏好，根据历史形式数据确定历史经停点，并将所有历史经停点分为不同的经停点类型，从而确定用户对各经停点类型的偏好程度。Further, the cluster analysis algorithm is an unsupervised learning algorithm used to group data points into clusters with similar characteristics. In this embodiment, the cluster analysis algorithm can be used to identify the user's preferences for points of interest, determine historical stop points based on historical form data, and classify all historical stop points into different stop point types, thereby determining the user's preference for points of interest. The degree of preference for each stop type.
进一步的，深度学习算法可以用于处理复杂的非线性关系，适用于较为复杂的用户数据分析任务，深度学习算法对应的省大学习模型可以通过多层神经网络来学习数据的高级特征，以便更好地捕捉用户的个性化偏好，在本实施例中则可用于基于历史数据确定多个线路特征的偏好参数，从而判断用户是否倾向于选择某一特定路线。Furthermore, deep learning algorithms can be used to process complex nonlinear relationships and are suitable for more complex user data analysis tasks. The large-scale learning model corresponding to the deep learning algorithm can learn advanced features of the data through multi-layer neural networks in order to more accurately analyze data. In this embodiment, it can be used to determine the preference parameters of multiple route features based on historical data to determine whether the user is inclined to choose a specific route.
可以理解的是，机器学习算法通常以数据分析模型的方式实现，该数据模型的处理阶段包括：数据准备、特征工程、模型建立、模型评估和优化、模型应用等。It can be understood that machine learning algorithms are usually implemented in the form of data analysis models. The processing stages of this data model include: data preparation, feature engineering, model establishment, model evaluation and optimization, model application, etc.
数据准备，指在构建数据分析模型之前，系统需要准备用于训练模型的数据集。这个数据集包括历史数据、历史导航记录和用户个人数据，如出发地点、目的地、导航路线、时间戳以及用户的偏好特征(例如是否避开高峰时段，是否更喜欢风景路线等)。Data preparation means that before building a data analysis model, the system needs to prepare a data set for training the model. This data set includes historical data, historical navigation records and user personal data, such as departure location, destination, navigation route, timestamp, and user preference characteristics (such as whether to avoid peak hours, whether to prefer scenic routes, etc.).
特征工程，是将原始数据转换为机器学习算法可以理解的特征的过程。在本实施例中，特征可以包括以下内容：用户的历史导航记录，包括出发地点、目的地、路线等；用户的个性化偏好，如是否避开高峰时段、是否选择风景路线。时间特征，如出行时间、星期几等；地理特征，如起点和终点的地理坐标、路段的交通流量信息等。这些特征将用于训练数据分析模型，以理解用户的导航偏好。Feature engineering is the process of converting raw data into features that can be understood by machine learning algorithms. In this embodiment, features may include the following: the user's historical navigation records, including departure location, destination, route, etc.; the user's personalized preferences, such as whether to avoid peak hours and whether to choose a scenic route. Time features, such as travel time, day of the week, etc.; geographical features, such as the geographical coordinates of the starting point and end point, traffic flow information of road sections, etc. These features will be used to train data analysis models to understand users’ navigation preferences.
模型建立，数据分析模型的构建通常依赖于机器学习算法，如决策树、随机森林、逻辑回归、神经网络等。模型的选择取决于任务和数据。在建立模型时，系统将使用历史形式数据来训练模型，以便模型能够预测用户在不同情境下的导航偏好。模型的输出将是一个或多个预测值，表示用户在特定情境下的路线选择倾向。例如，模型可以输出用户更可能选择的导航选项(如避开拥堵的路线或风景路线)的概率。Model building, the construction of data analysis models usually relies on machine learning algorithms, such as decision trees, random forests, logistic regression, neural networks, etc. The choice of model depends on the task and the data. When building a model, the system will use historical form data to train the model so that the model can predict the user's navigation preferences in different situations. The output of the model will be one or more predicted values that represent the user's route choice tendency in a specific situation. For example, the model can output the probability of a navigation option that a user is more likely to choose, such as a route that avoids congestion or a scenic route.
模型评估和优化，一旦模型建立完成，系统需要对其进行评估。这通常涉及将一部分历史数据保留为验证集，用于评估模型的性能。模型的性能评估可以使用各种指标，如准确度、召回率、F1分数等。如果模型的性能不够理想，系统可以通过改进特征工程、尝试不同的算法、增加更多的训练数据等方式来优化模型。进一步的，随着本实施例方法的应用，可持续收集用户的历史数据，历史数据与当时数据分析模型输出的偏好预测值更新至该用户的训练数据集，并再次使用训练数据集对数据分析模型进行优化。Model evaluation and optimization. Once the model is established, the system needs to evaluate it. This usually involves retaining a portion of the historical data as a validation set, which is used to evaluate the performance of the model. Model performance evaluation can use various metrics such as accuracy, recall, F1 score, etc. If the performance of the model is not satisfactory, the system can optimize the model by improving feature engineering, trying different algorithms, adding more training data, etc. Further, with the application of the method of this embodiment, the user's historical data can be continuously collected. The historical data and the preference prediction value output by the current data analysis model are updated to the user's training data set, and the training data set is used again to analyze the data. The model is optimized.
模型应用，一旦模型训练和优化完成，本实施例将把数据分析模型应用到本实施例方法中。当用户输入包括出发地点和目的地的导航指令时，步骤S204将使用数据分析模型输出的偏好参数来生成个性化的导航建议，以满足用户的导航偏好。Model application, once the model training and optimization are completed, this embodiment will apply the data analysis model to the method of this embodiment. When the user inputs a navigation instruction including a departure point and a destination, step S204 will use the preference parameters output by the data analysis model to generate personalized navigation suggestions to satisfy the user's navigation preferences.
通过这些步骤，本实施例方法可以利用机器学习算法来分析用户的个人数据，以了解其偏好和行为模式。这将为导航系统提供基础，以便根据用户的个性化需求生成定制的导航路线。算法的不断改进和优化将使系统能够更准确地理解用户的偏好，提供更好的导航建议。Through these steps, the method of this embodiment can use machine learning algorithms to analyze the user's personal data to understand their preferences and behavior patterns. This will provide the basis for the navigation system to generate customized navigation routes based on the individual needs of the user. Continuous improvement and optimization of the algorithm will enable the system to more accurately understand user preferences and provide better navigation suggestions.
进一步的，除了使用基础的历史数据进行分析得到偏好参数外，还可以直接根据用户对偏好选项的直接选择确定偏好参数，例如用户手动通过用户终端的导航界面手动输入偏好选择指令，例如最喜欢的道路类型为高速公路或风景路线，尽量避免的地区，常用目的地如家和公司等。具体的本实施例方法，还包括：接收对应路线特征的偏好选择指令，根据偏好选择指令生成确定路线特征的偏好参数。Furthermore, in addition to using basic historical data to analyze and obtain preference parameters, the preference parameters can also be determined directly based on the user's direct selection of preference options. For example, the user manually inputs preference selection instructions through the navigation interface of the user terminal, such as the favorite Road types include highways or scenic routes, areas to avoid, common destinations such as home and work, etc. The specific method of this embodiment also includes: receiving a preference selection instruction corresponding to the route characteristics, and generating preference parameters that determine the route characteristics according to the preference selection instruction.
最后，在收到导航指令时，基于偏好参数在导航地图上规划导航路径时，预处理的动作包括确定导航指令中的目的地和出发信息；对当前实时位置进行监测；获取导航地图的详细数据，包括道路状况、交通流量等等。在预处理结束后，开始规划导航路径，具体的导航路径的规划至少有两种思路，一种是对导航地图上的每条规划路径进行路径成本的修正，该修正随着偏好程度进行，然后基于修正后的路径成本进行导航路径的规划，另一种是先获取常规导航算法中的不考虑偏好参数的初步导航路径，然后判断初步导航路径是否满足偏好参数，并对初步导航路径中不满足偏好参数的部分进行路径修正，从而得到最终的导航路径。Finally, when receiving the navigation instruction and planning the navigation path on the navigation map based on the preference parameters, the preprocessing actions include determining the destination and departure information in the navigation instruction; monitoring the current real-time position; and obtaining detailed data of the navigation map. , including road conditions, traffic flow, and more. After the preprocessing is completed, the navigation path planning begins. There are at least two ideas for specific navigation path planning. One is to correct the path cost of each planned path on the navigation map. The correction is carried out according to the degree of preference, and then Navigation path planning is based on the corrected path cost. The other is to first obtain the preliminary navigation path in the conventional navigation algorithm without considering the preference parameters, and then determine whether the preliminary navigation path satisfies the preference parameters, and then determine whether the preliminary navigation path does not satisfy the preference parameters. The path correction is performed on the preference parameters to obtain the final navigation path.
具体的，基于偏好参数，在导航地图上规划导航指令对应的导航路径的过程，包括：Specifically, the process of planning the navigation path corresponding to the navigation instruction on the navigation map based on the preference parameters includes:
基于偏好参数，修正导航地图上的每条规划路径的路径成本；Based on the preference parameters, correct the path cost of each planned path on the navigation map;
基于修正后的导航地图，规划导航指令对应的导航路径。Based on the revised navigation map, the navigation path corresponding to the navigation instruction is planned.
或者，基于偏好参数，在导航地图上规划导航指令对应的导航路径的过程，包括：Or, based on preference parameters, the process of planning the navigation path corresponding to the navigation instruction on the navigation map includes:
在导航地图上规划导航指令对应的初步导航路径；Plan the preliminary navigation path corresponding to the navigation instructions on the navigation map;
分析每条初步导航路径是否满足偏好参数；Analyze whether each preliminary navigation path meets the preference parameters;
基于导航地图对不满足偏好参数的初步导航路径进行修正，以得到满足偏好参数的导航路径。The preliminary navigation path that does not satisfy the preference parameters is corrected based on the navigation map to obtain a navigation path that satisfies the preference parameters.
例如，如图3所示的导航地图上，其中S点为导航指令的起点，D点为导航指令的终点，导航地图上存在的潜在途经点包括P1、P2、P3、P4和P5，可行的规划路径分别有S-P1、S-P2、P1-P3、P2-P3、P3-P4、P3-P5、P4-D、P5-D，其中初始路径成本以行驶距离为依据，假设这几条规划路径的初始路径成本为2、3、3、3、6、4、5、6。按照第一种规划思路，基于偏好参数修正路径成本，通常偏好程度越高，偏好参数越大，修正后的路径成本越小，根据这些规划路径本身的路线特征，确定每条规划路径对应的偏好参数，并根据偏好参数修正路径成本，具体为将偏好参数的倒数与原本的初始路径成本相乘。假设修正后的路径成本依次为2、3、1.5、2、5、6、3、5，如图4所示，按照修正后的路径成本规划导航路径，规划目标为路径成本综合最小，最后得到的导航路径为S-P1-P3-P4-D。按照第二种规划思路，先按照初始路径成本综合最小为目标，获取常规的初步导航路径为S-P1-P3-P5-D，然后判断该初步导航路径是否满足偏好参数，分析每条初步导航路径是否满足偏好参数时存在一个判断基准，即偏好参数是否小于该偏好参数的预设基准数值，若是，则认为不满足偏好参数。例如对于交通流量，预设基准数值为1，交通流畅的偏好参数为1.5，交通堵塞严重的偏好参数为0.6，假设当初步导航路径中有一段规划路径P3-P5存在交通阻塞严重这一道路特征时，初步导航路径不满足偏好参数，需要进行修正，将存在交通阻塞严重这一道路特征的规划路径P3-P5替换为其他规划路径，最终得到满足偏好参数的导航路径S-P1-P3-P4-D。可以理解的是，实际的导航地图远比图3的示例复杂，具体的基于偏好参数的导航路径规划还需根据实际导航地图情况进行调整，此处不再赘述。For example, on the navigation map shown in Figure 3, point S is the starting point of the navigation instruction, and point D is the end point of the navigation instruction. The potential passing points on the navigation map include P1, P2, P3, P4 and P5. It is feasible The planned paths are S-P1, S-P2, P1-P3, P2-P3, P3-P4, P3-P5, P4-D, and P5-D. The initial path cost is based on the driving distance. Assume that these The initial path costs of the planned path are 2, 3, 3, 3, 6, 4, 5, 6. According to the first planning idea, the path cost is corrected based on the preference parameters. Usually, the higher the degree of preference, the greater the preference parameter, and the smaller the corrected path cost. Based on the route characteristics of these planned paths themselves, the preferences corresponding to each planned path are determined. parameters, and correct the path cost according to the preference parameters, specifically by multiplying the reciprocal of the preference parameters by the original initial path cost. Assume that the corrected path costs are 2, 3, 1.5, 2, 5, 6, 3, 5 in order. As shown in Figure 4, the navigation path is planned according to the corrected path cost. The planning goal is to minimize the comprehensive path cost. Finally, we get The navigation path is S-P1-P3-P4-D. According to the second planning idea, first according to the goal of minimizing the comprehensive initial path cost, the conventional preliminary navigation path is obtained as S-P1-P3-P5-D, and then it is judged whether the preliminary navigation path satisfies the preference parameters and each preliminary navigation is analyzed. There is a criterion for judging whether the path satisfies the preference parameter, that is, whether the preference parameter is smaller than the preset benchmark value of the preference parameter. If so, it is considered that the preference parameter is not satisfied. For example, for traffic flow, the preset reference value is 1, the preference parameter for smooth traffic is 1.5, and the preference parameter for severe traffic congestion is 0.6. It is assumed that when there is a section of the planned route P3-P5 in the preliminary navigation path that has the road characteristic of severe traffic congestion When , the preliminary navigation path does not meet the preference parameters and needs to be corrected. The planned paths P3-P5 with the road feature of serious traffic congestion are replaced with other planned paths, and finally the navigation path S-P1-P3-P4 that meets the preference parameters is obtained. -D. It is understandable that the actual navigation map is far more complicated than the example in Figure 3. The specific navigation path planning based on preference parameters needs to be adjusted according to the actual navigation map situation, which will not be described again here.
此处规划导航指令对应的导航路径或初步导航路径的具体路径规划算法，可以从各类路径规划算法中选择，常见的如A-star算法、dijkstra，均可应用于本实施例中，此处不作限制。The navigation path corresponding to the planned navigation instruction or the specific path planning algorithm of the preliminary navigation path can be selected from various path planning algorithms. Common ones such as A-star algorithm and dijkstra can be applied in this embodiment. Here No restrictions.
随着车辆行驶，本实施例方法的执行主体使用车辆传感器和卫星导航系统可以确定用户的位置、速度、方向等，同时还会接收实时的交通信息，包括交通流量、事故报告、施工工程等。基于这些信息，本实施例方法还可以调整导航路线，以选择最佳的道路，避免拥堵和交通延误。As the vehicle travels, the execution subject of the method in this embodiment can use vehicle sensors and satellite navigation systems to determine the user's location, speed, direction, etc., and also receive real-time traffic information, including traffic flow, accident reports, construction projects, etc. Based on this information, the method in this embodiment can also adjust the navigation route to select the best road to avoid congestion and traffic delays.
本实施例方法还允许接收用户的反馈建议、持续更新各类数据，包括历史数据、偏好参数、导航地图的地图数据等等，基于反馈建议和持续更新的各类数据对本方法中的各类算法参数进行不断的优化和改进，进一步提高对用户需求的预测准确性。The method of this embodiment also allows receiving user feedback and suggestions and continuously updating various types of data, including historical data, preference parameters, map data of navigation maps, etc. Based on the feedback suggestions and continuously updated various types of data, various algorithms in this method are Parameters are continuously optimized and improved to further improve the accuracy of predicting user needs.
本申请实施例的方法通过对历史数据进行分析确定各路线特征的偏好参数，然后基于偏好参数规划导航指令所对应的导航路径，由于路线特征的偏好参数基于历史数据得到，因此能够反映用户的驾驶偏好，将该偏好参数加入导航路径的规划中能够进一步提高导航路径与用户的驾驶偏好的契合度，生成的导航路径能够进一步满足用户需求，进而提升用户体验。The method of the embodiment of the present application determines the preference parameters of each route feature by analyzing historical data, and then plans the navigation path corresponding to the navigation instruction based on the preference parameters. Since the preference parameters of the route feature are obtained based on historical data, it can reflect the user's driving behavior. Preference, adding this preference parameter to the planning of the navigation path can further improve the fit between the navigation path and the user's driving preference, and the generated navigation path can further meet the user's needs, thereby improving the user experience.
上述所有可选技术方案，可以采用任意结合形成本申请的可选实施例，在此不再一一赘述。应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。All the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described again one by one. It should be understood that the sequence number of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.
下述为本申请装置实施例，可以用于执行本申请方法实施例。对于本申请装置实施例中未披露的细节，请参照本申请方法实施例。The following are device embodiments of the present application, which can be used to execute method embodiments of the present application. For details not disclosed in the device embodiments of this application, please refer to the method embodiments of this application.
图5是本申请实施例提供的一种基于驾驶偏好的地图导航装置的示意图。Figure 5 is a schematic diagram of a map navigation device based on driving preferences provided by an embodiment of the present application.
如图5所示，该基于驾驶偏好的地图导航装置包括：As shown in Figure 5, the driving preference-based map navigation device includes:
历史数据获取模块501，用于获取当前车辆的历史数据；历史数据包括历史行驶时间与历史行驶轨迹；The historical data acquisition module 501 is used to obtain historical data of the current vehicle; historical data includes historical driving time and historical driving trajectory;
偏好分析模块502，用于利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数；偏好参数用于表征当前车辆对各路线特征的偏好程度；The preference analysis module 502 is used to analyze historical data using machine learning algorithms to determine the preference parameters of route features; the preference parameters are used to represent the current vehicle's preference for each route feature;
导航指令接收模块503，用于接收导航指令；Navigation instruction receiving module 503, used to receive navigation instructions;
导航规划模块504，用于基于偏好参数，在导航地图上规划导航指令对应的导航路径，并将导航路径输出到用户终端。The navigation planning module 504 is used to plan a navigation path corresponding to the navigation instruction on the navigation map based on the preference parameters, and output the navigation path to the user terminal.
本申请实施例的装置通过对历史数据进行分析确定各路线特征的偏好参数，然后基于偏好参数规划导航指令所对应的导航路径，由于路线特征的偏好参数基于历史数据得到，因此能够反映用户的驾驶偏好，将该偏好参数加入导航路径的规划中能够进一步提高导航路径与用户的驾驶偏好的契合度，生成的导航路径能够进一步满足用户需求，进而提升用户体验。The device of the embodiment of the present application determines the preference parameters of each route feature by analyzing historical data, and then plans the navigation path corresponding to the navigation instruction based on the preference parameters. Since the preference parameters of the route features are obtained based on historical data, it can reflect the user's driving behavior. Preference, adding this preference parameter to the planning of the navigation path can further improve the fit between the navigation path and the user's driving preference, and the generated navigation path can further meet the user's needs, thereby improving the user experience.
在一示例性的实施例中，偏好分析模块502利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数之前，还用于：In an exemplary embodiment, the preference analysis module 502 uses a machine learning algorithm to analyze historical data, and before determining the preference parameters of the route characteristics, it is also used to:
基于路线特征，对历史数据标记符合各路线特征的标签；Based on the route characteristics, label the historical data with labels that match the characteristics of each route;
利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：The process of using machine learning algorithms to analyze historical data and determine the preferred parameters of route characteristics includes:
利用机器学习算法对标记了标签的历史数据进行分析，确定路线特征的偏好参数。Machine learning algorithms are used to analyze tagged historical data to determine the preferred parameters of route characteristics.
在一示例性的实施例中，偏好分析模块502利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：In an exemplary embodiment, the preference analysis module 502 uses a machine learning algorithm to analyze historical data and determine the preference parameters of route features, including:
利用决策树算法或回归分析算法对历史数据进行分析，确定路线特征为任一预设行驶场景时的偏好参数，预设行驶场景包括不同交通流量的路段、不同道路类型的路段、不同道路坡度的路段、不同景观类型的路段中的一种或多种。Use the decision tree algorithm or regression analysis algorithm to analyze historical data and determine the route characteristics as the preferred parameters for any preset driving scenario. The preset driving scenario includes sections with different traffic flows, sections with different road types, and sections with different road gradients. One or more of road segments and road segments of different landscape types.
在一示例性的实施例中，偏好分析模块502利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：In an exemplary embodiment, the preference analysis module 502 uses a machine learning algorithm to analyze historical data and determine the preference parameters of route features, including:
利用聚类分析算法对历史数据进行分析，确定路线特征为任一经停点类型时的偏好参数，经停点类型包括购物区、餐厅区、公园区、工业园区、居民区中的一种或多种。Use the cluster analysis algorithm to analyze historical data and determine the preferred parameters when the route characteristics are any stop type. The stop types include one or more of shopping areas, restaurant areas, parks, industrial parks, and residential areas. kind.
在一示例性的实施例中，偏好分析模块502利用机器学习算法对历史数据进行分析，确定路线特征的偏好参数的过程，包括：In an exemplary embodiment, the preference analysis module 502 uses a machine learning algorithm to analyze historical data and determine the preference parameters of route features, including:
利用深度学习算法对历史数据进行分析，确定多个路线特征的偏好参数，多个路线特征包括交通流量、道路类型、道路坡度、景观类型、经停点类型中的多个。Use deep learning algorithms to analyze historical data and determine the preference parameters of multiple route features, including traffic flow, road type, road slope, landscape type, and stop point type.
在一示例性的实施例中，偏好分析模块502还用于：In an exemplary embodiment, the preference analysis module 502 is also used to:
接收对应路线特征的偏好选择指令，根据偏好选择指令生成确定路线特征的偏好参数。Receive a preference selection instruction corresponding to the route characteristics, and generate preference parameters that determine the route characteristics according to the preference selection instruction.
在一示例性的实施例中，导航规划模块504基于偏好参数，在导航地图上规划导航指令对应的导航路径的过程，包括：In an exemplary embodiment, the navigation planning module 504 plans a navigation path corresponding to the navigation instruction on the navigation map based on the preference parameters, including:
基于偏好参数，修正导航地图上的每条规划路径的路径成本；Based on the preference parameters, correct the path cost of each planned path on the navigation map;
基于修正后的导航地图，规划导航指令对应的导航路径。Based on the revised navigation map, the navigation path corresponding to the navigation instruction is planned.
在一示例性的实施例中，导航规划模块504基于所述偏好参数，在导航地图上规划所述导航指令对应的导航路径的过程，包括：In an exemplary embodiment, the process of planning the navigation path corresponding to the navigation instruction on the navigation map by the navigation planning module 504 based on the preference parameters includes:
在导航地图上规划导航指令对应的初步导航路径；Plan the preliminary navigation path corresponding to the navigation instructions on the navigation map;
分析每条初步导航路径是否满足偏好参数；Analyze whether each preliminary navigation path meets the preference parameters;
基于导航地图对不满足偏好参数的初步导航路径进行修正，以得到满足偏好参数的导航路径。The preliminary navigation path that does not satisfy the preference parameters is corrected based on the navigation map to obtain a navigation path that satisfies the preference parameters.
图6是本申请实施例提供的电子设备6的示意图。如图6所示，该实施例的电子设备6包括：处理器601、存储器602以及存储在该存储器602中并且可在处理器601上运行的计算机程序603。处理器601执行计算机程序603时实现上述各个方法实施例中的步骤。或者，处理器601执行计算机程序603时实现上述各装置实施例中各模块/单元的功能。FIG. 6 is a schematic diagram of the electronic device 6 provided by the embodiment of the present application. As shown in FIG. 6 , the electronic device 6 of this embodiment includes: a processor 601 , a memory 602 , and a computer program 603 stored in the memory 602 and executable on the processor 601 . When the processor 601 executes the computer program 603, the steps in each of the above method embodiments are implemented. Alternatively, when the processor 601 executes the computer program 603, it implements the functions of each module/unit in each of the above device embodiments.
电子设备6可以是桌上型计算机、笔记本、掌上电脑及云端服务器等电子设备。电子设备6可以包括但不仅限于处理器601和存储器602。本领域技术人员可以理解，图6仅仅是电子设备6的示例，并不构成对电子设备6的限定，可以包括比图示更多或更少的部件，或者不同的部件。The electronic device 6 may be a desktop computer, a notebook, a handheld computer, a cloud server and other electronic devices. The electronic device 6 may include, but is not limited to, a processor 601 and a memory 602. Those skilled in the art can understand that FIG. 6 is only an example of the electronic device 6 and does not constitute a limitation on the electronic device 6. It may include more or fewer components than shown in the figure, or different components.
处理器601可以是中央处理单元(Central Processing Unit，CPU)，也可以是其它通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其它可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。The processor 601 can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or field-processable processor. Programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
存储器602可以是电子设备6的内部存储单元，例如，电子设备6的硬盘或内存。存储器602也可以是电子设备6的外部存储设备，例如，电子设备6上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。存储器602还可以既包括电子设备6的内部存储单元也包括外部存储设备。存储器602用于存储计算机程序以及电子设备所需的其它程序和数据。The memory 602 may be an internal storage unit of the electronic device 6 , for example, a hard disk or memory of the electronic device 6 . The memory 602 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SD) card, a flash memory card ( Flash Card), etc. Memory 602 may also include both internal storage units of electronic device 6 and external storage devices. Memory 602 is used to store computer programs and other programs and data required by the electronic device.
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs. Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be hardware-based. It can also be implemented in the form of software functional units.
集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个可读存储介质中，例如计算机可读存储介质。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，计算机程序可以存储在可读存储介质中，该计算机程序在被处理器执行时，可以实现上述各个方法实施例的步骤。计算机程序可以包括计算机程序代码，计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。可读存储介质可以包括：能够携带计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、电载波信号、电信信号以及软件分发介质等。Integrated modules/units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a readable storage medium, such as a computer-readable storage medium. Based on this understanding, this application can implement all or part of the processes in the methods of the above embodiments. It can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a readable storage medium. The computer program can be processed by a processor. When executed, the steps of each of the above method embodiments may be implemented. A computer program may include computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. Readable storage media may include: any entity or device that can carry computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, read-only memory (Read-Only Memory, ROM), random access Memory (Random Access Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media, etc.
以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。The above embodiments are only used to illustrate the technical solutions of the present application, but are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments. Modifications are made to the recorded technical solutions, or equivalent substitutions are made to some of the technical features; these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and shall be included in this application. within the scope of protection.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311414085.3ACN117537834A (en) | 2023-10-27 | 2023-10-27 | Map navigation method and device based on driving preference |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311414085.3ACN117537834A (en) | 2023-10-27 | 2023-10-27 | Map navigation method and device based on driving preference |
| Publication Number | Publication Date |
|---|---|
| CN117537834Atrue CN117537834A (en) | 2024-02-09 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311414085.3APendingCN117537834A (en) | 2023-10-27 | 2023-10-27 | Map navigation method and device based on driving preference |
| Country | Link |
|---|---|
| CN (1) | CN117537834A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119085685A (en)* | 2024-09-13 | 2024-12-06 | 广州小鹏自动驾驶科技有限公司 | Vehicle-side navigation path generation method, device, vehicle and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119085685A (en)* | 2024-09-13 | 2024-12-06 | 广州小鹏自动驾驶科技有限公司 | Vehicle-side navigation path generation method, device, vehicle and storage medium |
| Publication | Publication Date | Title |
|---|---|---|
| US11562300B2 (en) | System and method for optimal automated booking of on-demand transportation in multi-modal journeys | |
| US10371542B2 (en) | System and methods for performing multivariate optimizations based on location data | |
| US10809077B2 (en) | Navigating to a moving target | |
| US20180060778A1 (en) | Driver location prediction for a transportation service | |
| TW201901116A (en) | System and method for digital route planning | |
| CN115994726B (en) | Dispatch path adjustment method, dispatch path adjustment device, electronic equipment and computer readable medium | |
| WO2021052451A1 (en) | Method and system for determining estimated time of arrival | |
| CN113706857B (en) | Method, device and equipment for determining road trafficability and storage medium | |
| WO2022095813A1 (en) | Service data processing method, device, and readable storage medium | |
| WO2023045916A1 (en) | Ensuring proactive availability of vehicles for providing connected vehicle services | |
| CN110542428B (en) | Driving route quality evaluation method and device | |
| CN113177670B (en) | Data processing method, device, equipment and readable storage medium | |
| CN117612386A (en) | Highway traffic flow prediction method, device, computer equipment and storage medium | |
| CN117537834A (en) | Map navigation method and device based on driving preference | |
| Kamiński et al. | Multiagent routing simulation with partial smart vehicles penetration | |
| Gambella et al. | A city-scale IoT-enabled ridesharing platform | |
| CN114004077B (en) | Traffic simulation conversion method, device, computer equipment and storage medium | |
| CN116698075B (en) | Road network data processing method and device, electronic equipment and storage medium | |
| CN112504291A (en) | Vehicle navigation method and device | |
| Abdul Aziz et al. | Network traffic control in cyber-transportation systems accounting for user-level fairness | |
| CN114944072B (en) | Method and device for generating guidance prompt voice | |
| CN113008246A (en) | Map matching method and device | |
| US10691683B1 (en) | System and method of electronic distribution and transformation of electronic information in a centralized manner | |
| Carlos-Mancilla et al. | A Cyber-Physical System Modelling Framework for an Intelligent Urban Traffic System | |
| CN115222036A (en) | Model training method, representation information acquisition method and route planning method |
| 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 | ||
| TA01 | Transfer of patent application right | Effective date of registration:20241209 Address after:400000 No. 229, Fusheng Avenue, Jiangbei District, Chongqing Applicant after:Thalys Automobile Co.,Ltd. Country or region after:China Address before:618 Liangjiang Avenue, Longxing Town, Yubei District, Chongqing Applicant before:Chongqing Celes New Energy Automobile Design Institute Co.,Ltd. Country or region before:China | |
| TA01 | Transfer of patent application right |