【技术领域】【Technical field】
本发明涉及交通技术，尤其涉及一种服务订单的处理方法及装置。The invention relates to traffic technology, in particular to a method and device for processing service orders.
【背景技术】【Background technique】
目前，为了增加城市公共交通的营运能力与营运效率，出现了在线叫车服务例如，出租车、快车、顺风车等，用户可以便捷地通过所使用的终端上的叫车应用(Application，APP)，发布服务订单，由叫车软件所对应的处理引擎对服务订单进行分配处理。现有的订单分配过程中，可以根据订单数据和营运车辆的营运数据即行驶数据，对待分配订单进行分配处理。通常来说，每个营运车辆执行一个服务订单即接受一个服务订单或拒绝一个服务订单，是受服务订单的预估订单价格、服务订单的起始点位置、服务订单的终止点位置等订单数据，以及营运车辆的行驶速度、营运车辆距离起始点位置的距离、营运车辆的历史数据等营运车辆的营运数据等多个因素影响的。At present, in order to increase the operating capacity and efficiency of urban public transportation, online car-hailing services such as taxis, express trains, and ride-hailing services have emerged. Users can conveniently use the car-calling application (Application, APP) , release the service order, and the processing engine corresponding to the car-hailing software will distribute and process the service order. In the existing order allocation process, the order to be allocated can be allocated and processed according to the order data and the operating data of the operating vehicle, that is, the driving data. Generally speaking, each operating vehicle executes a service order, that is, accepts a service order or rejects a service order, which is the estimated order price of the service order, the starting point location of the service order, the ending point location of the service order and other order data, And the speed of the operating vehicle, the distance between the operating vehicle and the starting point, the historical data of the operating vehicle and other factors such as the operating data of the operating vehicle.
然而，由于影响营运车辆执行服务订单的各种因素的度量方式存在较大差异，并且难以统一进行量化，亟需提供一种量化影响营运车辆执行服务订单的因素的方法。However, due to the large differences in the measurement methods of various factors that affect the execution of service orders by operating vehicles, and it is difficult to quantify them uniformly, it is urgent to provide a method for quantifying the factors that affect the execution of service orders by operating vehicles.
【发明内容】【Content of invention】
本发明的多个方面提供一种服务订单的处理方法及装置，用以量化影响营运车辆执行服务订单的因素。Aspects of the present invention provide a method and device for processing service orders, which are used to quantify the factors affecting the execution of service orders by operating vehicles.
本发明的一方面，提供一种服务订单的处理方法，包括：In one aspect of the present invention, a method for processing a service order is provided, including:
获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据；Obtaining the operation data of the designated operating vehicle and the order data of each of the at least one service order of the designated operating vehicle;
根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量；According to the operating data and the order data of each service order, using the pre-created decision tree and the attribute list of the decision tree, obtain the attribute revenue vector of the designated operating vehicle executing each service order;
根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量。According to the attribute revenue vector of each service order executed by the designated commercial vehicle, the influencing factor vector of the designated commercial vehicle is obtained.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量之前，还包括：According to the above-mentioned aspect and any possible implementation manner, an implementation manner is further provided, according to the operation data and the order data of each service order, using the pre-created decision tree and the decision tree The attribute list, before obtaining the attribute income vector of each service order executed by the specified operating vehicle, further includes:
获取指定时间范围所产生的至少一个服务订单中每个服务订单的订单数据；Obtain order data for each service order in at least one service order generated in a specified time range;
获取所述每个服务订单所相关的营运车辆的营运数据；Obtain the operating data of the operating vehicles associated with each of the service orders;
将所述每个服务订单的订单数据和所述每个服务订单所相关的营运车辆的营运数据，作为训练数据；Using the order data of each service order and the operating data of the operating vehicles associated with each service order as training data;
利用所述训练数据，创建所述决策树。Using the training data, the decision tree is created.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量，包括：According to the above-mentioned aspect and any possible implementation manner, an implementation manner is further provided, according to the operation data and the order data of each service order, using the pre-created decision tree and the decision tree An attribute list to obtain the attribute income vector of each service order executed by the designated operating vehicle, including:
根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获取所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量；According to the operation data and the order data of each service order, using the pre-created decision tree and the attribute list of the decision tree, obtain the specified operation vehicle to execute the each service order on the decision tree path, and the income vector of each non-leaf node in all non-leaf nodes on the path;
根据所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量，获得所述指定营运车辆执行所述每个服务订单的属性收益向量。According to the path of each service order executed by the designated commercial vehicle on the decision tree, and the revenue vector of each non-leaf node in all non-leaf nodes on the path, the specified commercial vehicle executes the A vector of attribute returns for each service order.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量，包括：According to the above-mentioned aspect and any possible implementation manner, an implementation manner is further provided, according to the attribute revenue vector of each service order executed by the designated commercial vehicle, the influencing factor vector of the designated commercial vehicle is obtained ,include:
根据所述指定营运车辆接受服务订单的属性收益向量和所述指定营运车辆接受服务订单的数量，获得所述指定营运车辆的接受因素向量；Obtaining the acceptance factor vector of the designated operating vehicle according to the attribute revenue vector of the designated operating vehicle accepting service orders and the quantity of service orders accepted by the designated operating vehicle;
根据所述指定营运车辆拒绝服务订单的属性收益向量和所述指定营运车辆拒绝服务订单的数量，获得所述指定营运车辆的拒绝因素向量；Obtaining the rejection factor vector of the designated commercial vehicle according to the attribute revenue vector of the designated commercial vehicle's service rejection order and the quantity of the designated commercial vehicle's service rejection order;
根据所述指定营运车辆的接受因素向量和所述指定营运车辆的拒绝因素向量，获得所述指定营运车辆的影响因素向量。According to the acceptance factor vector of the designated commercial vehicle and the rejection factor vector of the designated commercial vehicle, the influence factor vector of the designated commercial vehicle is obtained.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述决策树的数量为N，N为大于或等于1的整数。According to the foregoing aspect and any possible implementation manner, an implementation manner is further provided, the number of the decision trees is N, and N is an integer greater than or equal to 1.
本发明的另一方面，提供一种服务订单的处理装置，包括：Another aspect of the present invention provides a service order processing device, including:
获取单元，用于获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据；An acquisition unit, configured to acquire the operating data of the designated operating vehicle and the order data of each service order in at least one service order of the designated operating vehicle;
收益单元，用于根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量；A revenue unit, configured to obtain the cost of executing each service order by the specified operating vehicle by using the pre-created decision tree and the attribute list of the decision tree according to the operation data and the order data of each service order. attribute return vector;
影响单元，用于根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量。The influencing unit is configured to obtain an influencing factor vector of the designated commercial vehicle according to the attribute income vector of each service order executed by the designated commercial vehicle.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述收益单元，还用于According to the above aspect and any possible implementation manner, an implementation manner is further provided, the revenue unit is also used to
获取指定时间范围所产生的至少一个服务订单中每个服务订单的订单数据；Obtain order data for each service order in at least one service order generated in a specified time range;
获取所述每个服务订单所相关的营运车辆的营运数据；Obtain the operating data of the operating vehicles associated with each of the service orders;
将所述每个服务订单的订单数据和所述每个服务订单所相关的营运车辆的营运数据，作为训练数据；以及using the order data of each service order and the operating data of the operating vehicle associated with each service order as training data; and
利用所述训练数据，创建所述决策树。Using the training data, the decision tree is created.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述收益单元，具体用于According to the above aspect and any possible implementation manner, an implementation manner is further provided, the revenue unit is specifically used for
根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获取所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量；以及According to the operation data and the order data of each service order, using the pre-created decision tree and the attribute list of the decision tree, obtain the specified operation vehicle to execute the each service order on the decision tree path, and the payoff vector of each non-leaf node among all non-leaf nodes on the path; and
根据所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量，获得所述指定营运车辆执行所述每个服务订单的属性收益向量。According to the path of each service order executed by the designated commercial vehicle on the decision tree, and the revenue vector of each non-leaf node in all non-leaf nodes on the path, the specified commercial vehicle executes the A vector of attribute returns for each service order.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述影响单元，具体用于According to the above aspect and any possible implementation manner, an implementation manner is further provided, the influencing unit is specifically used for
根据所述指定营运车辆接受服务订单的属性收益向量和所述指定营运车辆接受服务订单的数量，获得所述指定营运车辆的接受因素向量；Obtaining the acceptance factor vector of the designated operating vehicle according to the attribute revenue vector of the designated operating vehicle accepting service orders and the quantity of service orders accepted by the designated operating vehicle;
根据所述指定营运车辆拒绝服务订单的属性收益向量和所述指定营运车辆拒绝服务订单的数量，获得所述指定营运车辆的拒绝因素向量；以及Obtaining a rejection factor vector of the designated commercial vehicle according to the attribute revenue vector of the designated commercial vehicle's service rejection order and the quantity of the designated commercial vehicle's service rejection order; and
根据所述指定营运车辆的接受因素向量和所述指定营运车辆的拒绝因素向量，获得所述指定营运车辆的影响因素向量。According to the acceptance factor vector of the designated commercial vehicle and the rejection factor vector of the designated commercial vehicle, the influence factor vector of the designated commercial vehicle is obtained.
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述决策树的数量为N，N为大于或等于1的整数。According to the foregoing aspect and any possible implementation manner, an implementation manner is further provided, the number of the decision trees is N, and N is an integer greater than or equal to 1.
由上述技术方案可知，本发明实施例通过获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据，进而根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量，使得能够根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量，从而实现了量化影响营运车辆执行服务订单的因素的目的。It can be seen from the above technical solution that the embodiment of the present invention obtains the operation data of the designated operating vehicle and the order data of each service order in at least one service order of the designated operating vehicle, and then according to the operating data and each service order The order data of the order, using the pre-created decision tree and the attribute list of the decision tree, obtains the attribute revenue vector of the specified business vehicle executing the service order, so that the specified business vehicle can execute the each service order The property revenue vector of a service order is obtained to obtain the influencing factor vector of the specified operating vehicle, thereby realizing the purpose of quantifying the factors affecting the execution of the service order by the operating vehicle.
另外，采用本发明所提供的技术方案，能够将量化结果用于营运车辆的营运行为分析，优化在线叫车服务的订单分配，能够有效地提升用户的体验。In addition, by adopting the technical solution provided by the present invention, the quantitative results can be used to analyze the operating behavior of operating vehicles, optimize the order distribution of online car-calling services, and effectively improve user experience.
【附图说明】【Description of drawings】
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings that need to be used in the embodiments or the description of the prior art. Obviously, the drawings in the following descriptions are of the present invention For some embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without paying creative efforts.
图1为本发明一实施例提供的服务订单的处理方法的流程示意图；FIG. 1 is a schematic flowchart of a method for processing a service order provided by an embodiment of the present invention;
图2为本发明另一实施例提供的服务订单的处理装置的结构示意图。Fig. 2 is a schematic structural diagram of a service order processing device provided by another embodiment of the present invention.
【具体实施方式】【detailed description】
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的全部其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
需要说明的是，本发明实施例中所涉及的终端可以包括但不限于手机、个人数字助理(Personal Digital Assistant，PDA)、无线手持设备、平板电脑(Tablet Computer)、个人电脑(Personal Computer，PC)、MP3播放器、MP4播放器、可穿戴设备(例如，智能眼镜、智能手表、智能手环等)等。It should be noted that the terminals involved in the embodiments of the present invention may include, but are not limited to, mobile phones, personal digital assistants (Personal Digital Assistant, PDA), wireless handheld devices, tablet computers (Tablet Computer), personal computers (Personal Computer, PC ), MP3 players, MP4 players, wearable devices (eg, smart glasses, smart watches, smart bracelets, etc.), etc.
另外，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。In addition, the term "and/or" in this article is only an association relationship describing associated objects, which means that there may be three relationships, for example, A and/or B, which may mean: A exists alone, A and B exist at the same time, There are three cases of B alone. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.
图1为本发明一实施例提供的服务订单的处理方法的流程示意图，如图1所示。FIG. 1 is a schematic flowchart of a method for processing a service order provided by an embodiment of the present invention, as shown in FIG. 1 .
101、获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据。101. Obtain operating data of a designated operating vehicle and order data of each service order in at least one service order of the designated operating vehicle.
本发明中，所涉及的指定营运车辆中“指定”二字，并没有特殊含义，就是为了指定当前的操作对象而已，因此，指定营运车辆就是普通的营运车辆，例如，出租车、快车、顺风车等。In the present invention, the word "specify" in the designated operating vehicle involved has no special meaning, it is just to designate the current operation object. Therefore, the designated operating vehicle is an ordinary operating vehicle, such as taxi, express, Shunfeng car etc.
102、根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量。102. According to the operation data and the order data of each service order, use the pre-created decision tree and the attribute list of the decision tree to obtain the attribute revenue vector of each service order executed by the designated operating vehicle .
103、根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量。103. Obtain an influencing factor vector of the designated commercial vehicle according to the attribute revenue vector of each service order executed by the designated commercial vehicle.
需要说明的是，101～103的执行主体的部分或全部可以为位于本地终端的应用，或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(SoftwareDevelopment Kit，SDK)等功能单元，或者还可以为位于网络侧服务器中的处理引擎，或者还可以为位于网络侧的分布式系统，本实施例对此不进行特别限定。It should be noted that part or all of the execution subjects of 101-103 may be applications located on the local terminal, or may also be functions such as plug-ins or software development kits (Software Development Kit, SDK) set in the applications located on the local terminal. The unit may also be a processing engine located in a server on the network side, or may also be a distributed system located on the network side, which is not particularly limited in this embodiment.
可以理解的是，所述应用可以是安装在终端上的本地程序(nativeApp)，或者还可以是终端上的浏览器的一个网页程序(webApp)，本实施例对此不进行限定。It can be understood that the application may be a local program (nativeApp) installed on the terminal, or may also be a webpage program (webApp) of a browser on the terminal, which is not limited in this embodiment.
这样，利用基于决策树的分类算法对营运车辆的营运行为进行建模，来创建决策树，利用影响营运车辆执行服务订单的各种因素在决策树的创建过程中的纯净度收益，来量化各种因素，从而实现了量化影响营运车辆执行服务订单的因素的目的。In this way, the operating behavior of operating vehicles is modeled using a decision tree-based classification algorithm to create a decision tree, and the purity gains of various factors that affect operating vehicles to execute service orders in the process of creating a decision tree are used to quantify each The purpose of quantifying the factors that affect the execution of service orders by operating vehicles is achieved.
在用户使用叫车应用的过程中，所产生的服务订单，其相关的订单数据可以包括但不限于下列数据中的至少一项：During the process of using the ride-hailing application by the user, the service order generated, and its related order data may include but not limited to at least one of the following data:
服务订单的起始点位置、服务订单的终止点位置、服务订单的起始点位置和服务订单的终止点位置是否为用户的家或者工作单位、服务订单的起始点位置和服务订单的终止点位置是否为商圈、服务订单的起始点位置和服务订单的终止点位置是否为交通枢纽、服务订单所在城市、服务订单的开始时间、服务订单的车辆类型、服务订单的起始点位置与服务订单的终止点位置之间的行驶距离、服务订单的预估订单价格、服务订单的预估订单价格与所有服务订单的平均订单价格的比值、服务订单的预估行驶时间、服务订单的预估行驶速度与所有服务订单的平均行驶速度的比值、服务订单是否穿越拥堵区域以及用户性别。The location of the starting point of the service order, the location of the ending point of the service order, whether the location of the starting point of the service order and the location of the ending point of the service order are the user's home or work unit, whether the location of the starting point of the service order and the location of the ending point of the service order Is the business district, the location of the starting point of the service order and the location of the ending point of the service order are transportation hubs, the city where the service order is located, the start time of the service order, the type of vehicle of the service order, the location of the starting point of the service order and the termination of the service order distance traveled between point locations, estimated order price for service orders, ratio of estimated order price for service orders to average order price for all service orders, estimated travel time for service orders, estimated travel speed for service orders vs. The ratio of the average travel speed of all service orders, whether the service order traverses a congested area, and the gender of the user.
其中，服务订单的起始点位置和服务订单的终止点位置的记录方式，可以采用多种方式，本实施例对此不进行特别限定。Wherein, the recording manner of the starting point location of the service order and the ending point location of the service order may be recorded in various ways, which are not particularly limited in this embodiment.
例如，可以将服务订单的起始点位置和服务订单的终止点位置，转化为区域编码如，采用空间索引编码(GeoHash)方法等。For example, the location of the start point of the service order and the location of the end point of the service order can be converted into an area code, for example, by using a spatial index code (GeoHash) method and the like.
或者，再例如，可以将服务订单的起始点位置和服务订单的终止点位置，按照经纬度进行划分，分成指定形状的区块如矩形或六边形等形状，然后，分别对这些区块进行标识，来给每个区块分配唯一的标识。Or, for another example, the location of the starting point of the service order and the location of the ending point of the service order can be divided according to latitude and longitude, and divided into blocks of specified shapes such as rectangles or hexagons, and then these blocks are identified separately , to assign a unique identifier to each block.
其中，服务订单的开始时间可以包括但不限于以下维度数据：Among them, the start time of the service order may include but not limited to the following dimension data:
是否上午、是否下午、是否晚上、是否后半夜、星期、小时、是否周末、以及是否为上下班高峰时间段。Whether it is morning, whether it is afternoon, whether it is evening, whether it is late night, whether it is a week, hour, whether it is a weekend, and whether it is a rush hour for commuting.
根据所产生的服务订单，还可以进一步搜索服务订单的起始点位置附近的营运车辆，其相关的营运数据可以包括但不限于营运车辆位置信息和营运车辆历史信息中的至少一项，本实施例对此不进行特别限定。According to the generated service order, it is also possible to further search for operating vehicles near the starting point of the service order, and its related operating data may include but not limited to at least one of operating vehicle location information and operating vehicle history information. In this embodiment This is not particularly limited.
营运车辆位置信息，可以包括但不限于下列信息中的至少一项：The location information of commercial vehicles may include but not limited to at least one of the following information:
营运车辆当前的行驶速度、营运车辆当前移动状态的持续时间、营运车辆当前的所在位置、营运车辆当前的所在位置与服务订单的起始点位置之间的行驶距离、营运车辆接到用户的预估行驶时间、以及营运车辆接到用户的预估行驶速度。The current driving speed of the commercial vehicle, the duration of the current moving state of the commercial vehicle, the current location of the commercial vehicle, the driving distance between the current location of the commercial vehicle and the starting point of the service order, the estimate of the commercial vehicle receiving the user Travel time, and the estimated travel speed of the commercial vehicle receiving the user.
其中，营运车辆当前的所在位置的记录方式，与服务订单的起始点位置和服务订单的终止点位置的记录方式类似，可以采用多种方式，本实施例对此不进行特别限定。详细描述可以参见服务订单的起始点位置和服务订单的终止点位置的相关内容，此处不再赘述。Wherein, the recording method of the current location of the operating vehicle is similar to the recording method of the starting point location and the ending point location of the service order, and various methods can be used, which are not particularly limited in this embodiment. For a detailed description, please refer to the relevant content of the starting point location of the service order and the ending point location of the service order, and will not be repeated here.
营运车辆历史信息，营运车辆当前的所在位置与服务订单的起始点位置之间的行驶距离(即接人行驶距离)，与营运车辆历史的平均接人行驶距离的比值、服务订单的预估接人行驶时间与营运车辆历史的平均接人行驶时间的比值、过去M天拒绝服务订单的数量与接受服务订单的数量的比值、营运车辆过去M天平均在线时长与指定区域内(如营运车辆的注册地址所在区域等)所有营运车辆过去M天平均在线时长的比值、营运车辆过去M天平均在线时长的4分位数与指定区域内(如营运车辆的注册地址所在区域等)所有营运车辆过去M天平均在线时长的4分位数的比值、营运车辆过去M天平均拒绝服务订单的数量与指定区域内(如营运车辆的注册地址所在区域等)所有营运车辆过去M天平均拒绝服务订单的数量的比值、营运车辆过去M天平均接受服务订单的数量与指定区域内(如营运车辆的注册地址所在区域等)所有营运车辆过去M天平均接受服务订单的数量的比值、营运车辆过去M天行驶轨迹中移动状态的持续时间与营运车辆过去M天行驶轨迹的持续时间的比值(即营运车辆过去M天行驶轨迹中的移动状态时间占比)、以及营运车辆过去M天行驶轨迹中的移动状态时间占比与指定区域内(如营运车辆的注册地址所在区域等)所有营运车辆过去M天行驶轨迹中的移动状态时间占比的比值。Historical information of operating vehicles, the travel distance between the current location of the operating vehicle and the starting point of the service order (i.e., the distance traveled by pick-up), the ratio of the average pick-up distance to the history of the operating vehicle, and the estimated pick-up distance of the service order. The ratio of passenger travel time to the average receiving travel time of operating vehicles, the ratio of the number of rejected service orders to the number of accepted service orders in the past M days, the average online time of operating vehicles in the past M days and the specified area (such as the number of operating vehicles) The area where the registered address is located, etc.) The ratio of the average online time of all operating vehicles in the past M days, the quartile of the average online time of operating vehicles in the past M days, and the past The ratio of the quartiles of the average online time of M days, the average number of rejected service orders of operating vehicles in the past M days, and the average number of rejected service orders of all operating vehicles in the past M days in the designated area (such as the area where the registered address of the operating vehicles is located, etc.) The ratio of the quantity, the ratio of the average number of service orders received by operating vehicles in the past M days to the average number of service orders received by all operating vehicles in the past M days in the specified area (such as the area where the registered address of the operating vehicles is located, etc.), the ratio of the average number of service orders received by operating vehicles in the past M days The ratio of the duration of the moving state in the driving trajectory to the duration of the driving trajectory of the commercial vehicle in the past M days (that is, the time ratio of the moving state in the driving trajectory of the commercial vehicle in the past M days), and the moving state of the driving trajectory of the commercial vehicle in the past M days The ratio of the time proportion to the time proportion of the moving state of all commercial vehicles in the past M days of driving trajectories in the specified area (such as the area where the registered address of the commercial vehicle is located, etc.).
可选地，在本实施例的一个可能的实现方式中，在101中，具体可以从指定时间范围所产生的服务订单中每个服务订单的订单数据，以及每个服务订单所相关的营运车辆的营运数据中，可以获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据。Optionally, in a possible implementation of this embodiment, in 101, specifically, the order data of each service order in the service orders generated within a specified time range, and the operating vehicle associated with each service order In the operating data of the specified operating vehicle, the operating data of the specified operating vehicle and the order data of each service order in at least one service order of the specified operating vehicle can be obtained.
可选地，在本实施例的一个可能的实现方式中，在102之前，还可以进一步获取指定时间范围所产生的至少一个服务订单中每个服务订单的订单数据，以及获取所述每个服务订单所相关的营运车辆的营运数据。进而，则可以将所述每个服务订单的订单数据和所述每个服务订单所相关的营运车辆的营运数据，作为训练数据，利用所述训练数据，创建所述决策树。Optionally, in a possible implementation of this embodiment, before step 102, the order data of each service order in at least one service order generated within a specified time range may be further acquired, and each service order may be acquired The operating data of the operating vehicle related to the order. Furthermore, the order data of each service order and the operating data of the operating vehicles related to each service order may be used as training data, and the decision tree may be created using the training data.
具体来说，在创建决策树的过程中，可以将指定一段时间之内的服务订单的分配数据作为一条训练数据，每条训练数据可以由服务订单的订单数据和该服务订单相关营运车辆的营运数据组成，训练数据中的每项内容就是一项属性。进一步地，还可以根据这些运车辆是否接受该服务订单，给每个营运车辆打上标记，例如，接受标记为1，拒绝标记为0。Specifically, in the process of creating a decision tree, the distribution data of service orders within a specified period of time can be used as a piece of training data. Data composition, each item in the training data is an attribute. Further, it is also possible to mark each operating vehicle according to whether these transporting vehicles accept the service order, for example, 1 is marked for acceptance, and 0 is marked for rejection.
在所组成的训练数据的基础之上，可以构建N个决策树。其中，所构建的所述决策树的数量N，可以为大于或等于1的整数。On the basis of the composed training data, N decision trees can be constructed. Wherein, the number N of the decision trees to be constructed may be an integer greater than or equal to 1.
具体来说，如果N为1，那么，可以采用C4.5算法、ID3算法等常用决策树构建方法，构建一个决策树。Specifically, if N is 1, then a decision tree can be constructed using common decision tree construction methods such as C4.5 algorithm and ID3 algorithm.
具体来说，如果N为大于或等于2的整数，那么，可以采用随机森林(randomforest)和梯度提升树(Gradient Boosting Decision Tree，GBDT)的方法，构建多个决策树。Specifically, if N is an integer greater than or equal to 2, multiple decision trees can be constructed by using random forest (random forest) and gradient boosting tree (Gradient Boosting Decision Tree, GBDT) methods.
可选地，在本实施例的一个可能的实现方式中，在102中，具体可以根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获取所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量，进而，则可以根据所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量，获得所述指定营运车辆执行所述每个服务订单的属性收益向量，例如，将路径上全部非叶子节点中每个非叶子节点的收益向量的平均值，作为所述指定营运车辆执行所述每个服务订单的属性收益向量。Optionally, in a possible implementation of this embodiment, in 102, specifically, according to the operation data and the order data of each service order, the pre-created decision tree and the attribute list, to obtain the path of the specified business vehicle to execute each service order on the decision tree, and the revenue vector of each non-leaf node in all non-leaf nodes on the path, and then, according to the The specified operating vehicle executes the path of each service order on the decision tree, and the revenue vector of each non-leaf node in all non-leaf nodes on the path, and obtains the specified operating vehicle executing each The attribute revenue vector of the service order, for example, the average value of the revenue vectors of each non-leaf node in all non-leaf nodes on the path is used as the attribute revenue vector of each service order executed by the designated commercial vehicle.
在决策树的创建过程中，需要基于每一项属性进行分裂，来获得非叶子节点，每个非叶子节点可以对应分裂所经过的所有属性。每个非叶子节点所对应的所有属性的纯净度收益，可以采用现有的决策树模型中常用的标准，例如，基尼(GINI)系数增益、信息增益和信息增益比等。具体地，具体可以记录决策树创建过程中，所获得的每个非叶子节点所对应的所有属性的纯净度收益Gain(i,t)。其中，i表示训练数据中的第i个属性，t为决策树中对应的非叶子节点。因此，每个非叶子节点t都会有一个长度为训练数据的属性个数的属性收益向量vec(t)＝(Gain(1,t),Gain(2,t),……Gain(S,t))，其中，S为属性个数。In the process of creating a decision tree, it is necessary to split based on each attribute to obtain non-leaf nodes, and each non-leaf node can correspond to all attributes passed through the split. The purity gains of all attributes corresponding to each non-leaf node can adopt the commonly used standards in existing decision tree models, for example, Gini (GINI) coefficient gain, information gain, and information gain ratio. Specifically, the purity gains Gain(i,t) of all attributes corresponding to each non-leaf node obtained during the decision tree creation process may be recorded. Among them, i represents the i-th attribute in the training data, and t is the corresponding non-leaf node in the decision tree. Therefore, each non-leaf node t will have an attribute gain vector vec(t)=(Gain(1,t),Gain(2,t),...Gain(S,t) whose length is the number of attributes of the training data )), where S is the number of attributes.
在利用决策树进行判别时，主要取决于在决策树上走过的路径P即从决策树的根节点，经过非叶子节点，到达给出类别结果的叶子节点的路径。本发明中，可以采用路径P上全部非叶子节点中每个非叶子节点的收益向量，来反映营运车辆如何执行服务订单所考虑的因素，记为因素向量e(o,p)。因此，因素向量e(o,p)即所述指定营运车辆执行服务订单o的属性收益向量，可以表示为路径P上全部非叶子节点中每个非叶子节点的收益向量的平均值，即e(o,p)＝∑t∈pvec(t)/Length(p)，其中，Length(p)表示路径P上非叶子节点的数量。When using a decision tree for discrimination, it mainly depends on the path P traveled on the decision tree, that is, the path from the root node of the decision tree, through non-leaf nodes, to the leaf node that gives the category result. In the present invention, the income vector of each non-leaf node in all non-leaf nodes on the path P can be used to reflect the factors considered in how the operating vehicle executes the service order, which is recorded as the factor vector e(o,p). Therefore, the factor vector e(o,p) is the attribute income vector of the specified operating vehicle executing the service order o, which can be expressed as the average value of the income vector of each non-leaf node in all non-leaf nodes on the path P, that is, e (o,p)=∑t∈p vec(t)/Length(p), where Length(p) represents the number of non-leaf nodes on the path P.
可选地，在本实施例的一个可能的实现方式中，在103中，具体可以根据所述指定营运车辆接受服务订单的属性收益向量和所述指定营运车辆接受服务订单的数量，获得所述指定营运车辆的接受因素向量，以及根据所述指定营运车辆拒绝服务订单的属性收益向量和所述指定营运车辆拒绝服务订单的数量，获得所述指定营运车辆的拒绝因素向量。然后，则可以根据所述指定营运车辆的接受因素向量和所述指定营运车辆的拒绝因素向量，获得所述指定营运车辆的影响因素向量。Optionally, in a possible implementation of this embodiment, in step 103, specifically, according to the attribute revenue vector of the service order accepted by the designated commercial vehicle and the quantity of service orders accepted by the designated commercial vehicle, the The acceptance factor vector of the specified commercial vehicle, and the rejection factor vector of the specified commercial vehicle is obtained according to the attribute revenue vector of the specified commercial vehicle's service rejection order and the quantity of the specified commercial vehicle's service rejection order. Then, the influence factor vector of the designated commercial vehicle can be obtained according to the acceptance factor vector of the designated commercial vehicle and the rejection factor vector of the designated commercial vehicle.
通常，由于营运车辆执行一个服务订单包括接受服务订单和拒绝服务订单两种执行行为，因此，指定营运车辆执行所述每个服务订单的属性收益向量，可以为指定营运车辆接受服务订单的属性收益向量，或者还可以为指定营运车辆拒绝服务订单的属性收益向量，本实施例对此不进行特别限定。那么，某个指定营运车辆的影响因素向量Decision_vec，则可以由指定营运车辆的接受因素向量acceptvec和指定营运车辆的拒绝因素向量rejectvec组成，记为Decision_vec＝(acceptvec,rejectvec)。Usually, since the execution of a service order by an operating vehicle includes two execution behaviors of accepting the service order and rejecting the service order, the attribute income vector of the specified operating vehicle executing each service order can be the attribute income of the specified operating vehicle accepting the service order vector, or may also be an attribute revenue vector of a service rejection order of a designated operating vehicle, which is not particularly limited in this embodiment. Then, the influencing factor vector Decision_vec of a designated operating vehicle can be composed of the accepting factor vector acceptvec of the designated operating vehicle and the rejecting factor vector rejectvec of the designated operating vehicle, recorded as Decision_vec=(acceptvec , rejectvec ).
这是所采用的决策树的数量为1时，指定营运车辆的影响因素向量Decision_vec的组成。This is the composition of the influencing factor vector Decision_vec of the specified operating vehicle when the number of decision trees adopted is 1.
那么，若所采用的决策树的数量大于1时，可以分别针对每颗决策树，计算一个Decision_vec，然后，则可以对所获得的多个Decision_vec进行求和处理和归一化处理，将其结果作为指定营运车辆的影响因素向量。Then, if the number of decision trees used is greater than 1, one Decision_vec can be calculated for each decision tree, and then the obtained multiple Decision_vec can be summed and normalized, and the result As a vector of influencing factors for a designated commercial vehicle.
其中，可以将指定营运车辆接受服务订单的属性收益向量e(o,p)的加权值与指定营运车辆接受服务订单的数量number_of_accept_order的比值，作为指定营运车辆的接受因素向量acceptvec，即acceptvec＝∑o∈acceptorderwoe(o,p)/number_of_accept_order。指定营运车辆的接受因素向量acceptvec中的元素与训练时决策树中的属性对应，元素的取值越大，表示该属性对指定营运车辆接受服务订单的影响作用越大。这里，元素又可以称之为影响营运车辆执行服务订单的因素。Among them, the ratio of the weighted value of the attribute revenue vector e(o,p) of the designated operating vehicle accepting service orders to the number_of_accept_order of the designated operating vehicle’s acceptance of service orders can be used as the acceptance factor vector acceptvec of the designated operating vehicle, that is, acceptvec =∑o∈acceptorder wo e(o,p)/number_of_accept_order. The elements in the acceptance factor vector acceptvec of the designated operating vehicle correspond to the attributes in the decision tree during training, and the larger the value of the element, the greater the impact of the attribute on the acceptance of service orders by the designated operating vehicle. Here, elements can also be referred to as factors that affect the execution of service orders by operating vehicles.
类似地，可以将指定营运车辆拒绝服务订单的属性收益向量e(o,p)的加权值与指定营运车辆拒绝服务订单的数量number_of_reject_order的比值，作为指定营运车辆的拒绝因素向量rejectvec，即rejectvec＝∑o∈rejectorderwoe(o,p)/number_of_reject_order。指定营运车辆的拒绝因素向量rejectvec中的元素与训练时决策树中的属性对应，元素的取值越大，表示该属性对指定营运车辆拒绝服务订单的影响作用越大。这里，元素又可以称之为影响营运车辆执行服务订单的因素。Similarly, the ratio of the weighted value of the attribute revenue vector e(o,p) of the specified business vehicle’s rejection order to the number_of_reject_order of the specified business vehicle’s rejection order can be used as the rejection factor vector rejectvec of the specified business vehicle, that is, rejectvec =∑o∈rejectorder wo e(o,p)/number_of_reject_order. The elements in the rejection factor vector rejectvec of the specified operating vehicle correspond to the attributes in the decision tree during training. The larger the value of the element, the greater the impact of the attribute on the rejection of the service order of the specified operating vehicle. Here, elements can also be referred to as factors that affect the execution of service orders by operating vehicles.
本实施例中，通过获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据，进而根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量，使得能够根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量，从而实现了量化影响营运车辆执行服务订单的因素的目的。In this embodiment, by obtaining the operation data of the designated operating vehicle and the order data of each service order in at least one service order of the designated operating vehicle, and then according to the operating data and the order data of each service order, Using the pre-created decision tree and the attribute list of the decision tree to obtain the attribute revenue vector of the specified business vehicle executing the each service order, so that the specified business vehicle can execute the attributes of each service order The revenue vector is used to obtain the vector of influencing factors of the specified operating vehicle, so as to achieve the purpose of quantifying the factors affecting the execution of the service order by the operating vehicle.
另外，采用本发明所提供的技术方案，能够将量化结果用于营运车辆的营运行为分析，优化在线叫车服务的订单分配，能够有效地提升用户的体验。In addition, by adopting the technical solution provided by the present invention, the quantitative results can be used to analyze the operating behavior of operating vehicles, optimize the order distribution of online car-calling services, and effectively improve user experience.
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本发明所必须的。It should be noted that for the foregoing method embodiments, for the sake of simple description, they are expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence. Because of the present invention, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.
图2为本发明另一实施例提供的服务订单的处理装置的结构示意图，如图2所示。本实施例的服务订单的处理装置可以包括获取单元21、收益单元22和影响单元23。其中，获取单元21，用于获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据；收益单元22，用于根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量；影响单元23，用于根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量。FIG. 2 is a schematic structural diagram of a service order processing device provided by another embodiment of the present invention, as shown in FIG. 2 . The apparatus for processing a service order in this embodiment may include an acquisition unit 21 , a revenue unit 22 and an influence unit 23 . Wherein, the obtaining unit 21 is used to obtain the operation data of the specified operation vehicle and the order data of each service order in at least one service order of the specified operation vehicle; the revenue unit 22 is used to obtain the operation data according to the operation data and the The order data of each service order, using the pre-created decision tree and the attribute list of the decision tree, to obtain the attribute revenue vector of each service order executed by the designated commercial vehicle; the influencing unit 23 is configured to according to the specified The operating vehicle executes the attribute revenue vector of each service order to obtain the influencing factor vector of the designated operating vehicle.
其中，所述决策树的数量可以为N，N为大于或等于1的整数。Wherein, the number of the decision trees may be N, and N is an integer greater than or equal to 1.
需要说明的是，本实施例所提供的服务订单的处理装置可以为位于本地终端的应用，或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(SoftwareDevelopment Kit，SDK)等功能单元，或者还可以为位于网络侧服务器中的处理引擎，或者还可以为位于网络侧的分布式系统，本实施例对此不进行特别限定。It should be noted that the service order processing device provided in this embodiment may be an application located on a local terminal, or may also be a plug-in or a software development kit (Software Development Kit, SDK) set in an application located on a local terminal. The functional unit may also be a processing engine located in a server on the network side, or may also be a distributed system located on the network side, which is not particularly limited in this embodiment.
可以理解的是，所述应用可以是安装在终端上的本地程序(nativeApp)，或者还可以是终端上的浏览器的一个网页程序(webApp)，本实施例对此不进行限定。It can be understood that the application may be a local program (nativeApp) installed on the terminal, or may also be a webpage program (webApp) of a browser on the terminal, which is not limited in this embodiment.
可选地，在本实施例的一个可能的实现方式中，所述收益单元22，还可以进一步用于获取指定时间范围所产生的至少一个服务订单中每个服务订单的订单数据；获取所述每个服务订单所相关的营运车辆的营运数据；将所述每个服务订单的订单数据和所述每个服务订单所相关的营运车辆的营运数据，作为训练数据；以及利用所述训练数据，创建所述决策树。Optionally, in a possible implementation of this embodiment, the revenue unit 22 may be further configured to obtain order data of each service order in at least one service order generated within a specified time range; obtain the The operating data of the operating vehicles associated with each service order; using the order data of each service order and the operating data of the operating vehicles associated with each service order as training data; and using the training data, Create the decision tree.
可选地，在本实施例的一个可能的实现方式中，所述收益单元22，具体可以用于根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获取所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量；以及根据所述指定营运车辆执行所述每个服务订单在所述决策树上的路径，以及所述路径上全部非叶子节点中每个非叶子节点的收益向量，获得所述指定营运车辆执行所述每个服务订单的属性收益向量。Optionally, in a possible implementation of this embodiment, the revenue unit 22 may specifically be configured to use a pre-created decision tree and the The attribute list of the decision tree, obtaining the path on the decision tree for the specified business vehicle to execute each service order, and the revenue vector of each non-leaf node in all non-leaf nodes on the path; and according to The specified operating vehicle executes the path of each service order on the decision tree, and the revenue vector of each non-leaf node in all non-leaf nodes on the path, and obtains the specified operating vehicle executing the path of each service order. The attribute return vector of a service order.
可选地，在本实施例的一个可能的实现方式中，所述影响单元23，具体可以用于根据所述指定营运车辆接受服务订单的属性收益向量和所述指定营运车辆接受服务订单的数量，获得所述指定营运车辆的接受因素向量；根据所述指定营运车辆拒绝服务订单的属性收益向量和所述指定营运车辆拒绝服务订单的数量，获得所述指定营运车辆的拒绝因素向量；以及根据所述指定营运车辆的接受因素向量和所述指定营运车辆的拒绝因素向量，获得所述指定营运车辆的影响因素向量。Optionally, in a possible implementation of this embodiment, the influencing unit 23 may specifically be configured to: according to the attribute revenue vector of the designated commercial vehicle accepting service orders and the quantity of service orders accepted by the designated commercial vehicle , obtain the acceptance factor vector of the designated commercial vehicle; obtain the rejection factor vector of the designated commercial vehicle according to the attribute revenue vector of the designated commercial vehicle’s refusal service order and the quantity of the designated commercial vehicle’s refusal of service order; and The acceptance factor vector of the specified commercial vehicle and the rejection factor vector of the specified commercial vehicle are used to obtain the influencing factor vector of the specified commercial vehicle.
需要说明的是，图1对应的实施例中方法，可以由本实施例提供的服务订单的处理装置实现。详细描述可以参见图1对应的实施例中的相关内容，此处不再赘述。It should be noted that the method in the embodiment corresponding to FIG. 1 can be implemented by the service order processing device provided in this embodiment. For detailed description, reference may be made to relevant content in the embodiment corresponding to FIG. 1 , and details are not repeated here.
本实施例中，通过获取单元获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据，进而由收益单元根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量，使得影响单元能够根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量，从而实现了量化影响营运车辆执行服务订单的因素的目的。In this embodiment, the acquisition unit obtains the operation data of the designated operating vehicle and the order data of each service order in at least one service order of the designated operating vehicle, and then the revenue unit uses the operating data and the order data of each service order The order data of the order, using the pre-created decision tree and the attribute list of the decision tree, obtains the attribute revenue vector of each service order executed by the designated commercial vehicle, so that the influencing unit can execute the specified commercial vehicle according to the The attribute income vector of each service order is obtained to obtain the influencing factor vector of the specified operating vehicle, thereby achieving the purpose of quantifying the factors that affect the operating vehicle's execution of the service order.
另外，采用本发明所提供的技术方案，能够将量化结果用于营运车辆的营运行为分析，优化在线叫车服务的订单分配，能够有效地提升用户的体验。In addition, by adopting the technical solution provided by the present invention, the quantitative results can be used to analyze the operating behavior of operating vehicles, optimize the order distribution of online car-calling services, and effectively improve user experience.
本发明实施例提供的上述方法和装置可以以设置并运行于设备中的计算机程序体现。该设备可以包括一个或多个处理器，还包括存储器和一个或多个程序。其中该一个或多个程序存储于存储器中，被上述一个或多个处理器执行以实现本发明上述实施例中所示的方法流程和/或装置操作。例如，被上述一个或多个处理器执行的方法流程，可以包括：The foregoing methods and devices provided in the embodiments of the present invention may be embodied in computer programs that are configured and run in devices. The device may include one or more processors and also include memory and one or more programs. The one or more programs are stored in the memory and executed by the one or more processors to implement the method flow and/or device operations shown in the above embodiments of the present invention. For example, the method flow executed by the above-mentioned one or more processors may include:
获取指定营运车辆的营运数据和所述指定营运车辆的至少一个服务订单中每个服务订单的订单数据；Obtaining the operation data of the designated operating vehicle and the order data of each of the at least one service order of the designated operating vehicle;
根据所述营运数据和所述每个服务订单的订单数据，利用预先创建的决策树和所述决策树的属性列表，获得所述指定营运车辆执行所述每个服务订单的属性收益向量；According to the operating data and the order data of each service order, using the pre-created decision tree and the attribute list of the decision tree, obtain the attribute revenue vector of the designated operating vehicle executing each service order;
根据所述指定营运车辆执行所述每个服务订单的属性收益向量，获得所述指定营运车辆的影响因素向量。According to the attribute revenue vector of each service order executed by the designated commercial vehicle, the influencing factor vector of the designated commercial vehicle is obtained.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.
在本发明所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或页面组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or page components can be combined Or it can be integrated into another system, or some features can be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一个计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。The above-mentioned integrated units implemented in the form of software functional units may be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, and includes several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) or a processor (processor) execute part of the method described in each embodiment of the present invention step. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other various media that can store program codes. .
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710000762.5ACN106651213B (en) | 2017-01-03 | 2017-01-03 | Service order processing method and device |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710000762.5ACN106651213B (en) | 2017-01-03 | 2017-01-03 | Service order processing method and device |
| Publication Number | Publication Date |
|---|---|
| CN106651213Atrue CN106651213A (en) | 2017-05-10 |
| CN106651213B CN106651213B (en) | 2020-11-20 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710000762.5AActiveCN106651213B (en) | 2017-01-03 | 2017-01-03 | Service order processing method and device |
| Country | Link |
|---|---|
| CN (1) | CN106651213B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182524A (en)* | 2017-12-26 | 2018-06-19 | 北京三快在线科技有限公司 | A kind of order allocation method and device, electronic equipment |
| CN110209922A (en)* | 2018-06-12 | 2019-09-06 | 中国科学院自动化研究所 | Object recommendation method, apparatus, storage medium and computer equipment |
| CN110363571A (en)* | 2019-06-24 | 2019-10-22 | 阿里巴巴集团控股有限公司 | The sensed in advance method and apparatus of trade user |
| CN111066048A (en)* | 2017-09-08 | 2020-04-24 | 滴滴研究院美国公司 | System and method for ride order dispatch |
| CN111133484A (en)* | 2017-09-28 | 2020-05-08 | 北京嘀嘀无限科技发展有限公司 | System and method for evaluating a dispatch strategy associated with a specified driving service |
| CN111292106A (en)* | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining business demand influence factors |
| CN111695695A (en)* | 2020-06-09 | 2020-09-22 | 北京百度网讯科技有限公司 | Quantitative analysis method and device for user decision behaviors |
| CN111861086A (en)* | 2020-02-14 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Resource allocation method and system |
| US11216832B2 (en) | 2019-06-24 | 2022-01-04 | Advanced New Technologies Co., Ltd. | Predicting future user transactions |
| CN117575300A (en)* | 2024-01-19 | 2024-02-20 | 德阳凯达门业有限公司 | Task allocation method and device for workshops |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7715961B1 (en)* | 2004-04-28 | 2010-05-11 | Agnik, Llc | Onboard driver, vehicle and fleet data mining |
| CN102509449A (en)* | 2011-10-24 | 2012-06-20 | 北京东方车云信息技术有限公司 | Vehicle scheduling method based on fuzzy decision |
| CN104504460A (en)* | 2014-12-09 | 2015-04-08 | 北京嘀嘀无限科技发展有限公司 | Method and device for predicting user loss of car-hailing platform |
| CN104573873A (en)* | 2015-01-23 | 2015-04-29 | 哈尔滨工业大学 | Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree |
| CN106096748A (en)* | 2016-04-28 | 2016-11-09 | 武汉宝钢华中贸易有限公司 | Entrucking forecast model in man-hour based on cluster analysis and decision Tree algorithms |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7715961B1 (en)* | 2004-04-28 | 2010-05-11 | Agnik, Llc | Onboard driver, vehicle and fleet data mining |
| CN102509449A (en)* | 2011-10-24 | 2012-06-20 | 北京东方车云信息技术有限公司 | Vehicle scheduling method based on fuzzy decision |
| CN104504460A (en)* | 2014-12-09 | 2015-04-08 | 北京嘀嘀无限科技发展有限公司 | Method and device for predicting user loss of car-hailing platform |
| CN104573873A (en)* | 2015-01-23 | 2015-04-29 | 哈尔滨工业大学 | Airport terminal departure passenger traffic volume prediction method based on fuzzy decision-making tree |
| CN106096748A (en)* | 2016-04-28 | 2016-11-09 | 武汉宝钢华中贸易有限公司 | Entrucking forecast model in man-hour based on cluster analysis and decision Tree algorithms |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111066048A (en)* | 2017-09-08 | 2020-04-24 | 滴滴研究院美国公司 | System and method for ride order dispatch |
| CN111066048B (en)* | 2017-09-08 | 2024-04-26 | 北京嘀嘀无限科技发展有限公司 | System and method for ride order dispatch |
| CN111133484A (en)* | 2017-09-28 | 2020-05-08 | 北京嘀嘀无限科技发展有限公司 | System and method for evaluating a dispatch strategy associated with a specified driving service |
| CN108182524B (en)* | 2017-12-26 | 2021-07-06 | 北京三快在线科技有限公司 | Order allocation method and device and electronic equipment |
| CN108182524A (en)* | 2017-12-26 | 2018-06-19 | 北京三快在线科技有限公司 | A kind of order allocation method and device, electronic equipment |
| CN110209922B (en)* | 2018-06-12 | 2023-11-10 | 中国科学院自动化研究所 | Object recommendation method, device, storage medium and computer equipment |
| CN110209922A (en)* | 2018-06-12 | 2019-09-06 | 中国科学院自动化研究所 | Object recommendation method, apparatus, storage medium and computer equipment |
| CN111292106A (en)* | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining business demand influence factors |
| CN110363571A (en)* | 2019-06-24 | 2019-10-22 | 阿里巴巴集团控股有限公司 | The sensed in advance method and apparatus of trade user |
| US11216832B2 (en) | 2019-06-24 | 2022-01-04 | Advanced New Technologies Co., Ltd. | Predicting future user transactions |
| CN111861086A (en)* | 2020-02-14 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Resource allocation method and system |
| CN111861086B (en)* | 2020-02-14 | 2024-05-28 | 北京嘀嘀无限科技发展有限公司 | Resource allocation method and system |
| CN111695695A (en)* | 2020-06-09 | 2020-09-22 | 北京百度网讯科技有限公司 | Quantitative analysis method and device for user decision behaviors |
| CN111695695B (en)* | 2020-06-09 | 2023-08-08 | 北京百度网讯科技有限公司 | User decision-making behavior quantitative analysis method and device |
| CN117575300A (en)* | 2024-01-19 | 2024-02-20 | 德阳凯达门业有限公司 | Task allocation method and device for workshops |
| CN117575300B (en)* | 2024-01-19 | 2024-05-14 | 德阳凯达门业有限公司 | Task allocation method and device for workshops |
| Publication number | Publication date |
|---|---|
| CN106651213B (en) | 2020-11-20 |
| Publication | Publication Date | Title |
|---|---|---|
| CN106651213A (en) | Processing method and device for service orders | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN110472154B (en) | Resource pushing method and device, electronic equipment and readable storage medium | |
| CN104731917B (en) | A kind of recommendation method and device | |
| CN107122369B (en) | Service data processing method, device and system | |
| CN113383362B (en) | User identification method and related product | |
| CN106372674B (en) | Driver classification method and device in online taxi service platform | |
| CN107944593A (en) | A kind of resource allocation methods and device, electronic equipment | |
| WO2019061990A1 (en) | User intention prediction method, electronic device, and computer readable storage medium | |
| CN110909540A (en) | Method and device for identifying new words of short message spam and electronic equipment | |
| CN103618668A (en) | Method and device for pushing and receiving microblogs | |
| CN110392155B (en) | Notification message display and processing method, device and equipment | |
| CN111681049B (en) | User behavior processing method, storage medium and related equipment | |
| CN115907056A (en) | Prediction model training method, information prediction method and corresponding devices | |
| CN114117221A (en) | Information recommendation method, device, and computer-readable storage medium | |
| CN106446149A (en) | Filtering method and device for notification message | |
| CN107729944B (en) | Identification method and device of popular pictures, server and storage medium | |
| CN113821703B (en) | Internet of vehicles user portrait generation method and system thereof | |
| CN111695922A (en) | Potential user determination method and device, storage medium and electronic equipment | |
| CN113032674A (en) | Project publishing method, device, equipment and medium | |
| CN111160987A (en) | Information display method, device and system | |
| CN113744066B (en) | Information pushing method and device | |
| CN113326888B (en) | Labeling capability information determination method, related devices and computer program products | |
| CN116166879A (en) | Sharing service processing method, device, computer equipment and storage medium | |
| CN113297436B (en) | User policy distribution method and device based on relational graph network and electronic equipment |
| 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 |