CN112149855A - Order allocation method and device - Google Patents
Order allocation method and device Download PDFInfo
- Publication number
- CN112149855A CN112149855A CN202011120410.1A CN202011120410A CN112149855A CN 112149855 A CN112149855 A CN 112149855A CN 202011120410 A CN202011120410 A CN 202011120410A CN 112149855 A CN112149855 A CN 112149855A
- Authority
- CN
- China
- Prior art keywords
- order
- terminal
- matching
- grabbing probability
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for order allocation, which comprise the following steps: performing condition matching on the current order according to the order matching condition corresponding to the terminal, and screening out the order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform; aiming at each screened order, determining the forward grade of the order corresponding to the terminal according to a preset strategy; predicting the order grabbing probability of the terminal according to the forward road grade of the order by adopting a pre-established order grabbing probability prediction model; and determining whether the screened order is distributed to the terminal or not according to the order grabbing probability of the order. The invention also provides an order distribution device which comprises an order screening unit, a forward road grade determining unit, an order grabbing probability predicting unit and an order distribution unit. By utilizing the order distribution method and the order distribution equipment, the idle driving range of a driver and the waiting time of passengers can be effectively reduced, so that the user experience is improved.
Description
Technical Field
The invention relates to the technical field of computer processing, in particular to a method and a device for order allocation.
Background
With the increasing number of drivers and passengers using taxi taking software, the drivers cannot guarantee all-day online order taking, and the drivers can only give up the order taking due to temporary accidents, so that the drivers can drive to take care of their own things.
Through investigation of the driver, it is known that the driver still has a strong desire to take the order in response to the above situation. Although the existing order taking mode gives the driver a wide choice, when the above conditions occur, the driver still has difficulty in meeting the proper order, and particularly when the order taking mode is changed into the assignment mode, the order listening density is reduced, and the driver has more difficulty in meeting the order required by the driver.
How to realize the optimal order matching between the driver and the passenger according to the order-taking willingness of the driver is an urgent problem to be solved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides the order distribution method and the order distribution device, which can ensure the accuracy of order distribution and effectively reduce the idle driving mileage of a driver by screening orders according to the order taking willingness of the driver in the order distribution stage.
According to an aspect of the present invention, there is provided a method of order allocation, the method comprising:
performing condition matching on the current order according to the order matching condition corresponding to the terminal, and screening out the order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform;
aiming at each screened order, determining the forward grade of the order corresponding to the terminal according to a preset strategy; and
predicting the order grabbing probability of the terminal according to the forward grade of the order by adopting a pre-established order grabbing probability prediction model;
and determining whether the screened order is distributed to the terminal or not according to the order grabbing probability of the order.
Optionally, the method further includes:
acquiring order matching conditions corresponding to the terminal;
the acquisition mode of the order matching condition comprises the following steps:
receiving order matching conditions uploaded by the terminal, or
And determining an order matching condition corresponding to the terminal according to a preset rule based on the current motion state information of the terminal.
Optionally, the determining, according to a preset policy, a road grade of the order corresponding to the terminal includes:
acquiring the starting place and the destination of the screened order;
acquiring a current destination of a user to which the terminal belongs;
determining the forward-route grade of the starting place and the destination of the order corresponding to the current destination of the user to which the terminal belongs according to a preset strategy;
wherein the on-road grade comprises a direct arrival and an indirect arrival.
Optionally, the method further includes:
acquiring historical order data of a terminal in a preset time period;
taking the historical order data as training data, and training the training data by adopting a linear regression model to obtain the order grabbing probability pre-estimation model;
and the historical order data comprises the forward grade characteristics of each historical order corresponding to the terminal.
Optionally, the linear regression model is a logistic regression model or a support vector machine model.
Optionally, the method further includes:
optimizing the order grabbing probability estimation model by adopting a machine learning algorithm according to order data acquired on line in real time;
and the order data acquired in real time comprises the road grade characteristics of the terminal corresponding to the order.
Optionally, determining whether to allocate the screened order to the terminal according to the order grabbing probability includes:
judging whether the order grabbing probability is greater than a preset threshold value or not;
and if the order grabbing probability of the order is larger than a preset threshold value, determining that the order meets order distribution conditions, and distributing the screened order to the terminal.
Optionally, when there are a plurality of orders meeting the order distribution condition in the screened orders, the method further includes:
and according to the sequence of the order grabbing probability from large to small, allocating orders meeting order allocation conditions to the terminal.
According to another aspect of the present invention, there is provided an order distribution apparatus, comprising:
the order screening unit is used for carrying out condition matching on the current order according to the order matching condition corresponding to the terminal and screening out the order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform;
the forward level determining unit is used for determining the forward level of each order screened by the order screening unit, which corresponds to the terminal, according to a preset strategy;
the order-grabbing probability prediction unit is used for predicting the order-grabbing probability of the terminal according to the forward grade of the order by adopting a pre-established order-grabbing probability prediction model;
and the order distribution unit is used for determining whether to distribute the screened order to the terminal according to the order grabbing probability predicted by the order grabbing probability prediction unit.
Optionally, the apparatus further comprises:
the matching condition acquisition unit is used for acquiring the order matching conditions corresponding to the terminal;
the matching condition acquisition unit includes: a receiving module or a judging module;
the receiving module is used for receiving the order matching conditions uploaded by the terminal;
and the judging module is used for determining the order matching conditions corresponding to the terminal according to a preset rule based on the current motion state information of the terminal.
Optionally, the forward road grade determining unit includes:
the order address acquisition module is used for acquiring the starting place and the destination of the screened order;
the terminal address acquisition module is used for acquiring the current destination of the user to which the terminal belongs;
the forward level judging module is used for determining the forward level of the starting place and the destination of the order corresponding to the current destination of the user to which the terminal belongs according to a preset strategy;
wherein the on-road grade comprises a direct arrival and an indirect arrival.
Optionally, the apparatus further comprises:
the historical data acquisition unit is used for acquiring historical order data of the terminal in a preset time period;
the prediction model establishing unit is used for taking the historical order data as training data and training the training data by adopting a linear regression model to obtain the order grabbing probability prediction model;
and the historical order data comprises the forward grade characteristics of each historical order corresponding to the terminal.
Optionally, the linear regression model is a logistic regression model or a support vector machine model.
Optionally, the prediction model establishing unit is further configured to optimize the order grabbing probability prediction model by using a machine learning algorithm according to order data obtained on line in real time;
and the order data acquired in real time comprises the road grade characteristics of the terminal corresponding to the order.
Optionally, the order allocation unit includes:
the judging module is used for judging whether the order grabbing probability is greater than a preset threshold value or not;
and the distribution module is used for determining that the order meets the order distribution condition and distributing the screened order to the terminal when the judgment result of the judgment module is that the order grabbing probability of the order is greater than a preset threshold value.
Optionally, the allocating module is further configured to, when there are a plurality of screened orders meeting the order allocation condition in the orders, allocate the orders meeting the order allocation condition to the terminal according to a descending order of the order grabbing probability.
According to the technical scheme, the order allocation method and device provided by the invention have the advantages that the matching conditions of the order are limited by the driver, the preliminary screening is carried out at the initial stage of the order allocation according to the order receiving willingness of the driver, the order grabbing probability prediction is carried out according to the preliminary screening result, the order is allocated based on the order grabbing probability, the accurate pushing of the order is realized, the idle driving mileage of the driver and the waiting time of passengers are effectively reduced, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart illustrating a method for order allocation according to an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating a method for order allocation according to another embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of an order allocating apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an order distribution apparatus according to another embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As shown in fig. 1, a flow chart of a method for order allocation according to an embodiment of the present disclosure is shown, where the method includes the following steps:
s11, performing condition matching on the current order according to the order matching condition corresponding to the terminal, and screening out the order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform;
in practical application, after receiving a taxi taking request sent by User Equipment (User Equipment, abbreviated as UE), the taxi taking platform generates a corresponding order according to the taxi taking request. Wherein, the taxi taking request sent by the UE further comprises: one or more of information such as a departure place, a destination, and a user identification of the UE. The user identifier of the UE includes one or more of a mobile phone number, an Identity identifier (id), a hardware address (MAC), and other information. The taxi taking platform automatically pushes a terminal of a taxi driver within a preset range within a certain time length according to departure place information included in the taxi taking request, and the driver can take a one-key response through the terminal and keep contact with passengers.
In this embodiment, after the taxi-taking platform generates the corresponding order according to the taxi-taking request, the taxi-taking platform performs condition matching on the current order according to the order matching condition corresponding to the terminal, and screens out the order to be allocated in the taxi-taking platform meeting the order matching condition to allocate the order to the terminal. The matching conditions of the orders are limited by the driver, preliminary screening is carried out from the initial stage of order distribution according to the order receiving willingness of the driver, accurate order pushing is achieved, the idle driving mileage of the driver and the waiting time of passengers are effectively reduced, and therefore the user experience is improved.
The order matching conditions comprise conditions such as the matching range and the matching time of the order. Specifically, the matching range of the order can be determined according to the city and the urban area where the terminal belongs, the current geographic position of the terminal, the current motion state and the current destination of the driver user to which the terminal belongs; the matching time can be determined according to the current time schedule of the driver user belonging to the terminal.
S12, aiming at each screened order, determining the forward grade of the order corresponding to the terminal according to a preset strategy;
specifically, the determining, according to a preset policy, the forward road grade of the order corresponding to the terminal further includes the following steps not shown in the figure:
s121, acquiring the starting place and the destination of the screened order;
s122, acquiring the current destination of the user to which the terminal belongs;
s123, determining the forward road grade of the starting place and the destination of the order corresponding to the current destination of the user to which the terminal belongs according to a preset strategy;
in this embodiment, the forward grades include direct and indirect grades. In practical applications, the concrete setting of the on-road grade can be set and divided more accurately according to user requirements, for example, it can be seen that the on-road grade is divided into A, B, C, D, E grades according to the road distance actually required to be traveled by the driver user, and/or the time actually required for traveling, and the like, wherein the road distance actually required to be traveled by the driver user, and/or the time actually required for traveling is a preset strategy for determining the on-road grade of the order corresponding to the terminal.
The information about the order includes, but is not limited to, the following: the origin of the order, the destination of the order, additional fees the passenger is willing to pay, the time the passenger is willing to wait, whether the passenger carries a large piece of luggage, etc. Where the place of origin of the order may be entered or spoken by the passenger using his user device to initiate the taxi-taking software passenger terminal, may be determined via location information obtained from a location system in the passenger's user device, such as a global positioning system, a base station location system, etc., or may be determined via other information where appropriate, where such other information may include, but is not limited to, bus stops, subway stations, specific intersections, and specific buildings, as well as two-dimensional code information posted at such locations, etc.
In this embodiment, the starting place and the destination of each selected order meeting the order matching condition corresponding to the terminal are obtained from the information of each order, the destination of the user to which the terminal belongs is obtained according to the current travel of the user to which the terminal belongs uploaded by the terminal, and then the forward grade of the starting place and the destination of each order corresponding to the current destination of the user to which the terminal belongs is determined according to a preset strategy.
S13, predicting the order grabbing probability of the terminal according to the forward road grade of the order by adopting a pre-established order grabbing probability prediction model;
in this step, the order grabbing probability of the terminal relative to the order is predicted according to the forward road grade of the current terminal corresponding to each order determined in step S12 and according to the forward road grade characteristics of the order.
And S14, determining whether the screened order is distributed to the terminal according to the order grabbing probability.
According to the order distribution method provided by the embodiment of the invention, the matching conditions of the order are limited by the driver, preliminary screening is carried out at the initial stage of order distribution according to the order receiving willingness of the driver, the order grabbing probability prediction is carried out according to the preliminary screening result, and the order is distributed based on the order grabbing probability, so that the accurate pushing of the order is realized, the idle driving mileage of the driver and the waiting time of passengers are effectively reduced, and the user experience is improved.
It should be understood by those skilled in the art that the User Equipment (UE) mentioned in the embodiments of the present invention refers to a calling service party, such as a passenger in a vehicle calling service, a mobile terminal or a Personal Computer (PC) used in the calling service party. Such as a smart phone, a Personal Digital Assistant (PDA), a tablet computer, a laptop computer, a car computer (carputer), a handheld game console, smart glasses, a smart watch, a wearable device, a virtual display device or a display enhancement device (e.g., Google Glass, Oculus Rift, Hololens, Gear VR), etc.
It should be understood by those skilled in the art that the terminal mentioned in the embodiments of the present invention is a device used by a service provider, such as a driver in a car calling service of a vehicle, a mobile terminal or a Personal Computer (PC) for receiving an order. Such as a smart phone, a Personal Digital Assistant (PDA), a tablet computer, a laptop computer, a car computer (carputer), a handheld game console, smart glasses, a smart watch, a wearable device, a virtual display device or a display enhancement device (e.g., Google Glass, Oculus Rift, Hololens, Gear VR), etc.
In this embodiment, in order to distinguish between a passenger and a driver, the user equipment UE and the terminal are respectively used to represent devices such as mobile terminals held by the passenger and the driver.
Further, as shown in fig. 2, before the step S11, the method for allocating an order provided in another embodiment of the present disclosure further includes a step S10:
s10, obtaining order matching conditions corresponding to the terminal;
specifically, the obtaining manner of the order matching condition in step S10 further includes:
receiving order matching conditions uploaded by the terminal, or
And determining an order matching condition corresponding to the terminal according to a preset rule based on the current motion state information of the terminal.
In the embodiment, two acquisition modes of order matching conditions are provided, (1) the order matching conditions uploaded by a driver directly through a terminal are received; (2) monitoring the current motion state information of the terminal, such as the running speed, the running direction and the like, and determining the order matching conditions corresponding to the terminal according to preset rules based on the current motion state information of the terminal.
The preset rule in the second acquisition mode of the order matching condition can be set according to the distance difference and the time difference acceptable by the driver.
Further, the order distribution method provided by the present embodiment further includes the following steps not shown in the figure:
a01, acquiring historical order data of the terminal in a preset time period;
a02, taking the historical order data as training data, and training the training data by adopting a linear regression model to obtain the order grabbing probability pre-estimation model;
and the historical order data comprises the forward grade characteristics of each historical order corresponding to the terminal.
In this embodiment, the linear regression model may be one of the following: logistic regression model, support vector machine model.
The following describes the technical solution of the present invention with a logistic stewart regression model as a linear regression training model as a specific embodiment.
The Logistic Regression (Logistic Regression) model is widely applied to the binary problem, and when the predicted variable X is equal to X, the probability that the target variable Y is equal to 1 is expressed by the following formula:
P(Y＝1|X＝x)＝1/(1+exp(-w*x)
when the predicted variable X is X, the probability that the target variable Y is 0 is expressed by the following equation:
P(Y＝0|X＝x)＝1-1/(1+exp(-w*x)
wherein x represents a predicted variable, y represents a target variable, y ═ 1 represents that the order is predicted to be preempted, y ═ 0 represents that the order is predicted to be not preempted, and w represents a model parameter.
Specifically, historical order data (e.g., one or more of order-related characteristics at the time of placing an order, driver-related characteristics, order and driver-related characteristics, etc.) may be extracted as a predictive variable X, with the probability of competition for newly initiating an order being a target variable Y. By carrying out logistic regression model training on the deal information of the historical orders, the competition probability of the current order to be distributed can be predicted. In the practical process, the accuracy of the logistic stewart regression model can be continuously improved by continuously adding the characteristics related to whether the newly-initiated order is preempted or not.
The order distribution method provided by this embodiment, after step a02, further includes the following steps not shown in the figure:
a03, optimizing the order grabbing probability pre-estimation model by adopting a machine learning algorithm according to order data acquired on line in real time;
and the order data acquired in real time comprises the road grade characteristics of the terminal corresponding to the order.
In this embodiment, the estimation of the order grabbing probability is divided into two stages, namely, offline training and online real-time calculation. An off-line training stage: various characteristics such as order related characteristics, driver related characteristics, order and driver related characteristics and the like during order broadcasting are extracted into prediction variables, whether the driver robs the order is taken as a target variable, and model training is carried out by using historical data of the order broadcasting and the order grabbing to obtain an order grabbing probability prediction model. An on-line real-time calculation stage: and applying the model to the on-line, calculating the forward grade of the order extracted in real time corresponding to the terminal, and optimizing the pre-established prediction model by adopting a machine learning algorithm.
The order distribution method provided by the embodiment realizes self-learning after collecting data on line by using a machine learning algorithm and accurately estimates the order receiving probability of a driver.
In this embodiment, step S14 specifically includes the following steps not shown in the figure:
s141, judging whether the order grabbing probability is greater than a preset threshold value;
and S141, when the order grabbing probability of the order is greater than a preset threshold value, determining that the order meets order distribution conditions, and distributing the screened order to the terminal.
Further, when there are a plurality of orders meeting the order distribution condition in the screened orders, the order distribution method provided in this embodiment further includes:
and according to the sequence of the order grabbing probability from large to small, allocating orders meeting order allocation conditions to the terminal.
In practical application, passengers send orders according to travel demands of the passengers, drivers select the orders according to passenger carrying demands of the drivers, and the drivers usually set destinations the drivers want to go to. Therefore, according to the order distribution method of the embodiment, the matching conditions of the order are limited by the driver, preliminary screening is performed at the initial stage of order distribution according to the order-taking willingness of the driver, the order-grabbing probability prediction is performed according to the preliminary screening result, the order is distributed based on the order-grabbing probability, the accurate pushing of the order is realized, the idle driving mileage of the driver and the waiting time of passengers are effectively reduced, and therefore the user experience is improved.
As shown in fig. 3, a schematic structural diagram of an order distribution apparatus is provided for another embodiment of the present disclosure, and the apparatus includes: an order screening unit 201, a forward road grade determining unit 202, an order grabbing probability predicting unit 203 and an order distributing unit 204, wherein:
the order screening unit 201 is configured to perform condition matching on a current order according to an order matching condition corresponding to a terminal, and screen out an order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform;
the forward level determining unit 202 is configured to determine, according to a preset policy, a forward level of each order screened by the order screening unit, where the order corresponds to the terminal;
the order grabbing probability prediction unit 203 is used for predicting the order grabbing probability of the terminal according to the forward road grade of the order by adopting a pre-established order grabbing probability prediction model;
the order allocation unit 204 is configured to determine whether to allocate the screened order to the terminal according to the order grabbing probability predicted by the order grabbing probability prediction unit.
According to the order distribution device provided by the embodiment of the invention, the matching conditions of the order are limited by the driver, preliminary screening is carried out at the initial stage of order distribution according to the order receiving willingness of the driver, the order grabbing probability prediction is carried out according to the preliminary screening result, the order is distributed based on the order grabbing probability, the accurate pushing of the order is realized, the idle driving mileage of the driver and the waiting time of passengers are effectively reduced, and the user experience is improved.
Further, the order distribution apparatus provided in another embodiment of the present disclosure, as shown in fig. 4, further includes a matching condition obtaining unit 200;
specifically, the matching condition obtaining unit 200 is configured to obtain an order matching condition corresponding to the terminal;
wherein the matching condition obtaining unit 200 further includes: a receiving module or a judging module;
the receiving module is used for receiving the order matching conditions uploaded by the terminal;
and the judging module is used for determining the order matching conditions corresponding to the terminal according to a preset rule based on the current motion state information of the terminal.
Specifically, the forward road grade determining unit 202 further includes an order address obtaining module, a terminal address obtaining module, and a forward road grade determining module, where:
the order address acquisition module is used for acquiring the starting place and the destination of the screened order;
the terminal address acquisition module is used for acquiring the current destination of the user to which the terminal belongs;
the forward level judging module is used for determining the forward level of the starting place and the destination of the order corresponding to the current destination of the user to which the terminal belongs according to a preset strategy;
wherein the on-road grade comprises a direct arrival and an indirect arrival.
In this embodiment, the above order allocation apparatus further includes a historical data obtaining unit and a prediction model establishing unit, which are not shown in fig. 3, wherein;
the historical data acquisition unit is used for acquiring historical order data of the terminal in a preset time period;
the prediction model establishing unit is used for taking the historical order data as training data and training the training data by adopting a linear regression model to obtain the order grabbing probability prediction model;
and the historical order data comprises the forward grade characteristics of each historical order corresponding to the terminal.
Wherein the linear regression model may be one of: logistic regression model, support vector machine model.
The following describes the technical solution of the present invention with a logistic stewart regression model as a linear regression training model as a specific embodiment.
The Logistic Regression (Logistic Regression) model is widely applied to the binary problem, and when the predicted variable X is equal to X, the probability that the target variable Y is equal to 1 is expressed by the following formula:
P(Y＝1|X＝x)＝1/(1+exp(-w*x)
when the predicted variable X is X, the probability that the target variable Y is 0 is expressed by the following equation:
P(Y＝0|X＝x)＝1-1/(1+exp(-w*x)
wherein x represents a predicted variable, y represents a target variable, y ═ 1 represents that the order is predicted to be preempted, y ═ 0 represents that the order is predicted to be not preempted, and w represents a model parameter.
Specifically, historical order data (e.g., one or more of order-related characteristics at the time of placing an order, driver-related characteristics, order and driver-related characteristics, etc.) may be extracted as a predictive variable X, with the probability of competition for newly initiating an order being a target variable Y. By carrying out logistic regression model training on the deal information of the historical orders, the competition probability of the current order to be distributed can be predicted. In the practical process, the accuracy of the logistic stewart regression model can be continuously improved by continuously adding the characteristics related to whether the newly-initiated order is preempted or not.
Further, the prediction model establishing unit is further configured to optimize the order grabbing probability prediction model by using a machine learning algorithm according to order data acquired online in real time;
and the order data acquired in real time comprises the road grade characteristics of the terminal corresponding to the order.
Further, the order distribution unit 204 specifically includes a determining module and a distribution module, where:
the judging module is used for judging whether the order grabbing probability is greater than a preset threshold value;
and the distribution module is used for determining that the order meets the order distribution condition and distributing the screened order to the terminal when the judgment result of the judgment module is that the order grabbing probability of the order is greater than a preset threshold value.
The distribution module is further configured to distribute the orders meeting the order distribution condition to the terminal according to the order grabbing probability in a descending order when a plurality of orders meeting the order distribution condition exist in the screened orders.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
In summary, according to the method and device for order allocation provided by the embodiments of the present disclosure, a driver limits matching conditions of orders, performs preliminary screening at an initial stage of order allocation according to an order-receiving willingness of the driver, and performs order-grabbing probability prediction for a preliminary screening result, so as to perform order allocation based on the order-grabbing probability, thereby implementing accurate order push, effectively reducing a driver's air-driving distance and passenger waiting time, and thus improving user experience.
It should be noted that, in the respective components of the system of the present disclosure, the components therein are logically divided according to the functions to be implemented, but the present disclosure is not limited thereto, and the respective components may be re-divided or combined as needed, for example, some components may be combined into a single component, or some components may be further decomposed into more sub-components.
Various component embodiments of the disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in a system according to embodiments of the present disclosure. The present disclosure may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present disclosure may be stored on a computer-readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above embodiments are only suitable for illustrating the present disclosure, and not limiting the present disclosure, and those skilled in the relevant art can make various changes and modifications without departing from the spirit and scope of the present disclosure, so that all equivalent technical solutions also belong to the scope of the present disclosure, and the scope of the present disclosure should be defined by the claims.
Claims (22)
1. A method of order distribution, the method comprising:
performing condition matching on the current order according to the order matching condition corresponding to the terminal, and screening out the order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform;
aiming at each screened order, determining the forward grade of the order corresponding to the terminal according to a preset strategy;
predicting the order grabbing probability of the terminal according to the forward grade of the order by adopting a pre-established order grabbing probability prediction model;
and determining whether the screened order is distributed to the terminal or not according to the order grabbing probability of the order.
2. The method of claim 1, wherein the order matching conditions include a matching range and a matching time of the order; the matching range is determined according to the city and the urban area of the terminal, the current geographic position of the terminal, the current motion state and the current destination of the user of the terminal; the matching time is determined according to the current time schedule of the user to which the terminal belongs.
3. The method as claimed in claim 1, wherein the grade of the road is divided according to the road distance actually required to be traveled by the user to which the terminal belongs and/or the time actually required to be traveled by the user to which the terminal belongs.
4. The method of claim 1, wherein the determining the forward grade of the order corresponding to the terminal according to a preset policy comprises:
acquiring the starting place and the destination of the screened order;
acquiring a current destination of a user to which the terminal belongs;
determining the forward-route grade of the starting place and the destination of the order corresponding to the current destination of the user to which the terminal belongs according to the preset strategy;
wherein the on-road grade comprises a direct arrival and an indirect arrival.
5. The method of claim 1, wherein the method further comprises:
acquiring order matching conditions corresponding to the terminal;
the acquisition mode of the order matching condition comprises the following steps:
receiving the order matching conditions uploaded by the terminal, or
And determining the order matching condition corresponding to the terminal according to a preset rule based on the current motion state information of the terminal.
6. The method according to claim 5, wherein the predetermined rule comprises setting an acceptable distance gap and/or time gap for the user to which the terminal belongs.
7. The method of claim 1, wherein the method further comprises:
acquiring historical order data of the terminal in a preset time period;
taking the historical order data as training data, and training the training data by adopting a linear regression model to obtain the order grabbing probability pre-estimation model;
and the historical order data comprises the forward grade characteristics of each historical order corresponding to the terminal.
8. The method of claim 7, wherein the linear regression model is a logistic regression model or a support vector machine model.
9. The method of claim 7, wherein the method further comprises:
optimizing the order grabbing probability estimation model by adopting a machine learning algorithm according to order data acquired on line in real time;
and the order data acquired in real time comprises the road grade characteristics of the terminal corresponding to the order.
10. The method according to claim 1, wherein determining whether to allocate the screened order to the terminal according to the order grabbing probability specifically comprises:
judging whether the order grabbing probability is greater than a preset threshold value or not;
and if the order grabbing probability is larger than the preset threshold value, determining that the order meets the order distribution condition, and distributing the screened order to the terminal.
11. The method of claim 10, wherein when there are a plurality of orders matching the order distribution condition among the screened orders, the method further comprises:
and according to the sequence of the order grabbing probability from large to small, allocating orders meeting the order allocation conditions to the terminal.
12. An apparatus for order distribution, the apparatus comprising:
the order screening unit is used for carrying out condition matching on the current order according to the order matching condition corresponding to the terminal and screening out the order meeting the order matching condition; the current order is an order to be distributed in the taxi taking platform;
the forward level determining unit is used for determining the forward level of each order screened by the order screening unit, which corresponds to the terminal, according to a preset strategy;
the order-grabbing probability prediction unit is used for predicting the order-grabbing probability of the terminal according to the forward grade of the order by adopting a pre-established order-grabbing probability prediction model;
and the order distribution unit is used for determining whether to distribute the screened order to the terminal according to the order grabbing probability predicted by the order grabbing probability prediction unit.
13. The apparatus of claim 12, wherein the order matching conditions include a matching range and a matching time of the order; the matching range is determined according to the city and the urban area of the terminal, the current geographic position of the terminal, the current motion state and the current destination of the user of the terminal; the matching time is determined according to the current time schedule of the user to which the terminal belongs.
14. The apparatus as claimed in claim 12, wherein the grade of the road is divided according to a road distance actually required to be traveled by the user to which the terminal belongs and/or a time actually required to be traveled by the user to which the terminal belongs.
15. The apparatus of claim 12, wherein the apparatus further comprises:
the matching condition acquisition unit is used for acquiring the order matching conditions corresponding to the terminal;
the matching condition acquisition unit includes: a receiving module or a judging module;
the receiving module is used for receiving the order matching conditions uploaded by the terminal;
the judging module is used for determining the order matching conditions corresponding to the terminal according to a preset rule based on the current motion state information of the terminal.
16. The apparatus of claim 15, wherein the predetermined rule comprises a distance gap and/or a time gap that is acceptable for a user to whom the terminal belongs.
17. The apparatus as claimed in claim 12, wherein said forward rank determining unit comprises:
the order address acquisition module is used for acquiring the starting place and the destination of the screened order;
the terminal address acquisition module is used for acquiring the current destination of the user to which the terminal belongs;
the forward level judging module is used for determining the forward level of the starting place and the destination of the order corresponding to the current destination of the user to which the terminal belongs according to the preset strategy;
wherein the on-road grade comprises a direct arrival and an indirect arrival.
18. The apparatus of claim 12, wherein the apparatus further comprises:
the historical data acquisition unit is used for acquiring historical order data of the terminal in a preset time period;
the prediction model establishing unit is used for taking the historical order data as training data and training the training data by adopting a linear regression model to obtain the order grabbing probability prediction model;
and the historical order data comprises the forward grade characteristics of each historical order corresponding to the terminal.
19. The apparatus of claim 18, wherein the linear regression model is a logistic regression model or a support vector machine model.
20. The apparatus of claim 18, wherein the prediction model building unit is further configured to optimize the pre-estimation model of the order grabbing probability by using a machine learning algorithm according to order data obtained on line in real time;
and the order data acquired in real time comprises the road grade characteristics of the terminal corresponding to the order.
21. The apparatus of claim 12, wherein the order allocation unit comprises:
the judging module is used for judging whether the order grabbing probability is greater than a preset threshold value or not;
and the distribution module is used for determining that the order meets the order distribution condition and distributing the screened order to the terminal when the judgment result of the judgment module is that the order grabbing probability of the order is greater than the preset threshold value.
22. The apparatus of claim 21, wherein the allocating module is further configured to, when there are a plurality of screened orders meeting the order allocation condition, allocate orders meeting the order allocation condition to the terminal in an order from a greater order grabbing probability to a smaller order grabbing probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011120410.1A CN112149855A (en) | 2015-07-28 | 2015-07-28 | Order allocation method and device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011120410.1A CN112149855A (en) | 2015-07-28 | 2015-07-28 | Order allocation method and device |
| CN201510451956.8A CN105117777A (en) | 2015-07-28 | 2015-07-28 | Order distributing method and apparatus |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510451956.8A Division CN105117777A (en) | 2015-01-29 | 2015-07-28 | Order distributing method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149855A true CN112149855A (en) | 2020-12-29 |
Family
ID=54665759
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510451956.8A Pending CN105117777A (en) | 2015-01-29 | 2015-07-28 | Order distributing method and apparatus |
| CN202011120410.1A Pending CN112149855A (en) | 2015-07-28 | 2015-07-28 | Order allocation method and device |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510451956.8A Pending CN105117777A (en) | 2015-01-29 | 2015-07-28 | Order distributing method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN105117777A (en) |
Families Citing this family (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SG11201706188YA (en) | 2015-01-29 | 2017-08-30 | Beijing Didi Infinity Tech And Dev Co Ltd | Order allocation system and method |
| CN107424022B (en) * | 2016-05-23 | 2022-02-11 | 北京嘀嘀无限科技发展有限公司 | Order pushing method and system |
| CN105847299A (en) * | 2016-05-25 | 2016-08-10 | 广西白海豚网络技术有限公司 | Application and self-recommendation network system of driver |
| CN106530188B (en) * | 2016-09-30 | 2021-06-11 | 百度在线网络技术（北京）有限公司 | Driver order-receiving probability evaluation method and device in online taxi calling service platform |
| US10355788B2 (en) * | 2017-01-06 | 2019-07-16 | Uber Technologies, Inc. | Method and system for ultrasonic proximity service |
| CN108734950B (en) * | 2017-04-18 | 2021-03-16 | 北京嘀嘀无限科技发展有限公司 | Car pooling method and device and network car booking method and device |
| CN107025490A (en) * | 2017-04-13 | 2017-08-08 | 成都悠途信息技术有限公司 | A kind of user precisely matches order generating system and method by bus with driver terminal |
| CN109118334B (en) * | 2017-06-01 | 2022-04-01 | 北京星选科技有限公司 | Order processing method and device |
| CN109146211A (en) * | 2017-06-16 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | The distribution of order, the training method of model and device |
| CN109146109B (en) * | 2017-06-16 | 2021-07-27 | 北京嘀嘀无限科技发展有限公司 | Order distribution and model training method and device |
| CA3028215C (en) * | 2017-06-16 | 2021-10-26 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for allocating service requests |
| CN107844930B (en) * | 2017-06-26 | 2020-09-18 | 北京星选科技有限公司 | Order allocation method and device |
| CN109598566B (en) * | 2017-09-30 | 2021-07-09 | 北京嘀嘀无限科技发展有限公司 | Ordering prediction method, ordering prediction device, computer equipment and computer readable storage medium |
| CN109647719B (en) * | 2017-10-11 | 2020-07-31 | 北京京东振世信息技术有限公司 | Method and device for sorting goods |
| CN109902847B (en) * | 2017-12-11 | 2022-04-12 | 北京京东尚科信息技术有限公司 | Method and device for predicting amount of orders in branch warehouse |
| CN110110871B (en) * | 2018-02-01 | 2022-08-19 | 北京嘀嘀无限科技发展有限公司 | Order allocation method and system |
| CN108921637A (en) * | 2018-05-15 | 2018-11-30 | 中国联合网络通信集团有限公司 | A kind of order allocation method, platform and system |
| CN110570263B (en) * | 2018-06-06 | 2021-10-15 | 北京嘀嘀无限科技发展有限公司 | Order distribution method, distribution system, computer device and readable storage medium |
| CN109214551B (en) * | 2018-08-08 | 2022-08-26 | 北京三快在线科技有限公司 | Distribution scheduling method and device |
| SG11201811698UA (en) * | 2018-08-09 | 2020-03-30 | Beijing Didi Infinity Technology & Development Co Ltd | Systems and methods for allocating orders |
| CN110874777A (en) * | 2018-08-30 | 2020-03-10 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device |
| CN110956524A (en) * | 2018-09-27 | 2020-04-03 | 北京嘀嘀无限科技发展有限公司 | Service information pushing method and device, electronic equipment and computer storage medium |
| CN109508862A (en) * | 2018-10-10 | 2019-03-22 | 达疆网络科技(上海)有限公司 | A kind of allocator and device |
| CN111222729B (en) * | 2018-11-23 | 2022-07-05 | 北京嘀嘀无限科技发展有限公司 | Service type determination method and device, electronic equipment and storage medium |
| CN111325594A (en) * | 2018-12-17 | 2020-06-23 | 北京三快在线科技有限公司 | Potential tail bill judging and scheduling method and device |
| CN109886603B (en) * | 2019-03-12 | 2020-11-06 | 北京同城必应科技有限公司 | Order pushing method, device, equipment and storage medium |
| CN111027710A (en) * | 2019-12-06 | 2020-04-17 | 浙江大搜车软件技术有限公司 | Resource clue allocation method, device, computer equipment and storage medium |
| CN111597260B (en) * | 2020-05-12 | 2021-11-02 | 乐清市凡山电器有限公司 | Logistics order management system and method based on block chain |
| WO2021226925A1 (en) * | 2020-05-14 | 2021-11-18 | Beijing Didi Infinity Technology And Development Co., Ltd. | Method and system for constructing virtual environment for ride-hailing platforms |
| CN111553645B (en) * | 2020-06-08 | 2024-02-02 | 北京顺达同行科技有限公司 | Order allocation method, order allocation device, computer equipment and storage medium |
| CN111967720B (en) * | 2020-07-22 | 2024-03-08 | 汉海信息技术(上海)有限公司 | Scheduling method and system for network taxi taking |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514738B (en) * | 2013-09-18 | 2015-09-02 | 福建工程学院 | A kind of taxi taking share-car matching process and system thereof by the way |
| CA2932828C (en) * | 2013-12-11 | 2023-12-05 | Uber Technologies, Inc. | Optimizing selection of drivers for transport requests |
| CN104574947A (en) * | 2014-11-27 | 2015-04-29 | 北京嘀嘀无限科技发展有限公司 | Order handling method and equipment |
| CN104715426B (en) * | 2015-04-08 | 2018-08-03 | 北京嘀嘀无限科技发展有限公司 | Method and apparatus for order-processing |
-
2015
- 2015-07-28 CN CN201510451956.8A patent/CN105117777A/en active Pending
- 2015-07-28 CN CN202011120410.1A patent/CN112149855A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN105117777A (en) | 2015-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112149855A (en) | Order allocation method and device | |
| US11416795B2 (en) | Systems and methods for vehicle resource management | |
| US9805431B2 (en) | Systems and methods for allocating networked vehicle resources in priority environments | |
| US11386359B2 (en) | Systems and methods for managing a vehicle sharing facility | |
| US20170169366A1 (en) | Systems and Methods for Adjusting Ride-Sharing Schedules and Routes | |
| CN107491825B (en) | Taxi booking processing method and system | |
| CN107203824B (en) | Car pooling order distribution method and device | |
| EP3262831B1 (en) | Telephone call placement | |
| WO2016135649A1 (en) | Systems and methods for managing a vehicle sharing facility | |
| US20200210905A1 (en) | Systems and Methods for Managing Networked Vehicle Resources | |
| CN111080048A (en) | Order dispatching method and device for reserving order of taxi taking, electronic equipment and storage medium | |
| CN102592470B (en) | Traffic information publishing method, device and system | |
| EP3262601A1 (en) | A system and method of calculating a price for a vehicle journey | |
| CN113888857A (en) | Public transportation management system, device and method based on Internet of vehicles | |
| EP3945477A1 (en) | Systems and methods for ridesharing with connected and unconnected passengers | |
| CN114862491A (en) | Vehicle position determining method, order dispatching method, device, server and storage medium | |
| CN113052397B (en) | Method and device for determining boarding information, electronic equipment and storage medium | |
| CN107121145A (en) | A kind of information processing method and device | |
| CN109345436B (en) | Riding condition monitoring method, management and control platform, storage medium and system | |
| CN117874372B (en) | Public transport voice broadcasting method, device, equipment and medium | |
| CN110926490A (en) | Method and device for selecting driving route, computer readable medium and electronic equipment | |
| CN112561164A (en) | Car pooling service providing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |