CN115759307A

CN115759307A - Order dispatching method and device, electronic equipment and storage medium

Info

Publication number: CN115759307A
Application number: CN202211464546.3A
Authority: CN
Inventors: 何东魁
Original assignee: Nanjing Leading Technology Co Ltd
Current assignee: Nanjing Leading Technology Co Ltd
Priority date: 2022-11-22
Filing date: 2022-11-22
Publication date: 2023-03-07

Abstract

The method comprises the steps of obtaining N orders to be dispatched in a designated area, wherein N is an integer larger than zero, determining N order receiving ends capable of receiving the orders based on starting points of the N orders, matching the N orders with the N order receiving ends, matching the order receiving ends according to a rule that order receiving duration is shortest if an order placing user identification of any order is located in a preset user identification set, storing order placing user identifications with higher sensitivity to order receiving duration than a set degree in the preset user identification set, and dispatching each order to the order receiving end corresponding to the order based on a matching result. Therefore, when the order is sent to the ordering user, if the sensitivity of the ordering user to the order receiving time is higher than the set degree, the order receiving time is matched with the order receiving end according to the rule that the order receiving time is the shortest, so that the order cancellation rate is reduced, and better user experience is brought.

Description

Order dispatching method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of internet technologies, and in particular, to an order dispatching method and apparatus, an electronic device, and a storage medium.

Background

With the rapid development of the internet technology, many kinds of network orders such as network appointment orders, designated driving orders and the like appear, and no matter which kind of network orders are dispatched, the order taking ends generally need to be selected reasonably, so that the order forming rate is improved.

Taking the network car booking order as an example, the network car booking platform can ensure that the maximum number of orders are matched with the cars as far as possible under the condition that some factors such as taking distance, taking time and the like are met, and then order dispatching is completed.

Therefore, the problem that the canceling rate of orders is high exists in the prior art.

Disclosure of Invention

The embodiment of the application provides an order dispatching method and device, electronic equipment and a storage medium, and aims to solve the problem that the order cancellation rate is high in the prior art.

In a first aspect, an embodiment of the present application provides an order dispatch method, including:

acquiring N orders to be dispatched in a designated area, wherein N is an integer larger than zero;

determining N order taking ends capable of taking orders based on the starting points of the N orders;

matching the N orders with the N order receiving ends, wherein if the order placing user identification of any order is located in a preset user identification set, matching the order receiving ends according to a rule that the order receiving duration is shortest, and storing the order placing user identification with the order receiving duration sensitivity higher than a set degree in the preset user identification set;

and dispatching each order to the order receiving end corresponding to the order based on the matching result.

In some embodiments, the sensitivity of each ordering user to the order-receiving duration is determined according to the following steps:

acquiring a historical order in the designated area;

dividing each historical order into a first type of historical order and a second type of historical order according to the rule that the order taking time length is smaller than the average order taking time length of each historical order and is a first type of historical order, and the order taking time length is not smaller than the average order taking time length and is a second type of historical order;

and determining the sensitivity of the ordering user to the order receiving duration based on the first type of historical orders and the second type of historical orders of the ordering user when the ordering user meets the sensitivity determination condition aiming at each ordering user.

In some embodiments, determining the sensitivity of the ordering user to the order taking duration based on the first type of historical order and the second type of historical order of the ordering user comprises:

determining a first sensitivity of the order placing user based on the established first prediction model and a first type of historical orders of the order placing user, and determining a second sensitivity of the order placing user based on the established second prediction model and a second type of historical orders of the order placing user;

and carrying out weighted summation on the first sensitivity and the second sensitivity to obtain the sensitivity of the order placing user to the order receiving time length.

In some embodiments, determining a first sensitivity of the order placing user based on the established first predictive model and the first type of historical orders of the order placing user comprises:

inputting first characteristic data of each first type historical order of the ordering user into the first prediction model to obtain the cancellation rate of the ordering user to the first type historical order;

and determining the average value of the cancellation rate of the ordering user to each first type of historical orders as the first sensitivity of the ordering user.

In some embodiments, determining a second sensitivity of the order placing user based on the established second predictive model and a second type of historical orders of the order placing user comprises:

inputting the first characteristic data of each second type historical order of the order placing user into the second prediction model to obtain the cancellation rate of the order placing user to the second type historical order;

and determining the average value of the cancellation rate of the ordering user to each second type of historical orders as a second sensitivity of the ordering user.

In some embodiments, the first predictive model and the second predictive model are trained according to the following steps:

performing model training by taking the first characteristic data of the first type of historical orders as input and taking the label value of whether the first type of historical orders are cancelled as output to obtain a first initial model, and performing model training by taking the first characteristic data of the second type of historical orders as input and taking the label value of whether the first type of historical orders are cancelled as output to obtain a second initial model;

determining a first prediction error of the second initial model for each first type of historical orders, adding the first prediction error into first feature data of the first type of historical orders, determining a second prediction error of the first initial model for each second type of historical orders, and adding the second prediction error into first feature data of the second type of historical orders;

and training the first initial model by taking the first characteristic data of the first type of historical order after adding the first prediction error as input and taking the label value of whether the first characteristic data is cancelled as output to obtain a first prediction model, and training the second initial model by taking the first characteristic data of the second type of historical order after adding the second prediction error as input and taking the label value of whether the second characteristic data is cancelled as output to obtain a second prediction model.

In some embodiments, the weights of the singleton user for the first sensitivity and the second sensitivity are determined according to the following steps:

inputting second characteristic data of each historical order of the ordering user into the established tendency analysis model to obtain tendency scores of the historical orders, wherein the order receiving duration of each historical order is greater than the average order receiving duration, and the second characteristic data comprises an indication value of whether the actual order receiving duration is less than the average order receiving duration;

carrying out weighted average on tendency scores corresponding to the historical orders of the ordering user to obtain the weight of the ordering user on the first sensitivity;

and taking the difference value between a preset value and the weight as the weight of the ordering user to the second sensitivity.

In a second aspect, an embodiment of the present application provides an order dispatch device, including:

the acquisition module is used for acquiring N orders to be dispatched in a specified area, wherein N is an integer greater than zero;

the first determining module is used for determining N order receiving ends capable of receiving orders based on the starting points of the N orders;

the matching module is used for matching the N orders with the N order receiving ends, wherein if the order placing user identification of any order is located in a preset user identification set, the order placing user identification is matched with the order receiving ends according to the rule that the order receiving time length is shortest, and the order placing user identification with the sensitivity of the order receiving time length higher than the set degree is stored in the preset user identification set;

and the dispatching module is used for dispatching each order to the order receiving end corresponding to the order based on the matching result.

In some embodiments, the system further comprises a second determining module, configured to determine the sensitivity of each order placing user to the order receiving duration according to the following steps:

acquiring historical orders in the designated area;

In some embodiments, the second determining module is specifically configured to:

inputting the first characteristic data of each first type of historical orders of the order placing user into the first prediction model to obtain the cancellation rate of the order placing user to the first type of historical orders;

inputting the first characteristic data of each second type historical order of the order placing user into the second prediction model to obtain the cancellation rate of the order placing user on the second type historical order;

and determining the average value of the cancellation rates of the ordering users to the second type of historical orders as a second sensitivity of the ordering users.

In some embodiments, further comprising a training module for training the first predictive model and the second predictive model according to the following steps:

performing model training by taking the first characteristic data of the first type of historical orders as input and the label value of whether the first type of historical orders are cancelled as output to obtain a first initial model, and performing model training by taking the first characteristic data of the second type of historical orders as input and the label value of whether the first type of historical orders are cancelled as output to obtain a second initial model;

and training the first initial model by taking the first characteristic data of the first type of historical orders after adding the first prediction error as input and the label value of whether the first characteristic data is cancelled as output to obtain a first prediction model, and training the second initial model by taking the first characteristic data of the second type of historical orders after adding the second prediction error as input and the label value of whether the first characteristic data is cancelled as output to obtain a second prediction model.

In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor, and a memory communicatively coupled to the at least one processor, wherein:

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the above-described order dispatch method.

In a fourth aspect, an embodiment of the present application provides a storage medium, where when a computer program in the storage medium is executed by a processor of an electronic device, the electronic device is capable of executing the order dispatching method.

In the embodiment of the application, N orders to be dispatched in a designated area are obtained, N is an integer larger than zero, N order taking ends capable of taking orders are determined based on starting points of the N orders, the N orders and the N order taking ends are matched, if an order placing user identification of any order is located in a preset user identification set, the order taking ends are matched according to a rule that order taking time is shortest, an order placing user identification with higher sensitivity to order taking time than a set degree is stored in the preset user identification set, and each order is dispatched to the order taking end corresponding to the order based on a matching result. Therefore, when the order is dispatched for the ordering user, if the sensitivity of the ordering user to the order receiving time is higher than the set degree, the order receiving time is shorter by matching the single end according to the rule that the order receiving time is the shortest, so that the order receiving time is shorter, the order cancellation rate is reduced, and better user experience is brought.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is an application scenario diagram of an order dispatching method according to an embodiment of the present application;

fig. 2 is a flowchart of an order dispatching method according to an embodiment of the present application;

FIG. 3 is a flowchart illustrating a method for determining sensitivity of various ordering users to order receiving duration according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of an order dispatch process according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an order dispatch device according to an embodiment of the present application;

fig. 6 is a schematic hardware structure diagram of an electronic device for implementing an order dispatching method according to an embodiment of the present application.

Detailed Description

The order cancellation method aims to solve the problem that the order cancellation rate is high in the prior art. The embodiment of the application provides an order dispatching method and device, electronic equipment and a storage medium.

The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it should be understood that the preferred embodiments described herein are merely for illustrating and explaining the present application, and are not intended to limit the present application, and that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

The order sending method provided by the embodiment of the application can be applied to various scenes such as network car booking, designated driving and the like, wherein in the scene of network car booking, the order is a network car booking order, the order placing user is a passenger end, the order receiving end is a driver end, the order starting point of the network car booking order is the getting-on position of the passenger, and it needs to be explained that the getting-on position of the passenger can be the position where the passenger end is located or other positions appointed by the passenger end; in the designated driving scene, the order is a designated driving order, the order placing user is a driving owner terminal, the order receiving terminal is a designated driving terminal, and the order starting point of the designated driving order is the position of the designated driving.

Fig. 1 is an application scenario diagram of an order dispatching method provided in an embodiment of the present application, including an order placing user, a server, and an order receiving end, where the order placing user is connected to the server through a wired network or a wireless network, and the order receiving end is also connected to the server through a wired network or a wireless network.

The order placing user sends an order placing request to the server through a mobile phone, an Ipad, a computer and the like, wherein the order placing request at least comprises a starting point of an order and user information, such as user identification, a contact way and the like.

The server can select a order receiving end based on order information in the order request after receiving the order request sent by any order placing user, and send an order receiving instruction to the selected order receiving end, wherein the order receiving instruction comprises order information such as a starting point, a terminal point, a contact way of the order placing user and the like, and the information of the order receiving end such as an order receiving end identifier, a contact way, expected order receiving duration and the like is sent to the order placing user.

And after receiving the order receiving instruction sent by the server, the order receiving end, such as a mobile phone, an Ipad, a computer and the like, executes the processes of receiving the order, sending the order and the like based on the order information in the order receiving instruction.

The server may be one server, a server cluster formed by a plurality of servers, or a cloud computing center.

After introducing the application scenario of the embodiment of the present application, the order dispatching method proposed in the present application is described below with specific embodiments.

Fig. 2 is a flowchart of an order dispatching method according to an embodiment of the present application, where the method is applied to the server in fig. 1, and the method includes the following steps.

In step 201, N orders to be dispatched in the designated area are obtained, where N is an integer greater than zero.

The obtained N orders to be dispatched in the designated area at least include information such as starting points of the N orders and order placing user identifiers of the N orders, and the designated area is, for example, a city.

In step 202, based on the starting points of the N orders, N orders available for order taking are determined.

For example, according to the starting point of any order, N order receiving ends within a preset range from the starting point of the order are determined, the N order receiving ends are used as alternative order receiving ends, and the order is dispatched by matching the endmost order receiving end from the alternative order receiving ends.

In step 203, matching the N orders with the N order taking terminals, wherein if the order placing user identifier of any order is located in the preset user identifier set, the order taking terminals are matched according to the rule that the order taking duration is the shortest, and the order placing user identifier with the sensitivity of the order taking duration higher than the set degree is stored in the preset user identifier set.

In practical application, the sensitivities of the users to the order-receiving duration in the designated area can be sorted according to the descending order, and the order-receiving user identifications arranged in the front in a preset proportion are selected to form a preset user identification set.

For example, 5 ordering users, an ordering user a, an ordering user B, an ordering user C, an ordering user D and an ordering user E are all in the designated area, the sensitivity of the order taking time of the ordering user a is 0.39, the sensitivity of the order taking time of the ordering user B is 0.8, the sensitivity of the order taking time of the ordering user C is 0.7, the sensitivity of the order taking time of the ordering user D is 0.75, and the sensitivity of the order taking time of the ordering user E is 0.6, then the ordering is performed in a numerical value descending manner to obtain a preset user identifier set of { ordering user B } and ordering user D } that is 0.8 (ordering user B) > 0.75 (ordering user D) > 0.7 (ordering user C) > 0.6 (ordering user E) > 0.39 (ordering user a), and the set selection proportion is 40%.

And the preset user identification set can be stored in the server or an offline number bin, when the preset user identification set is stored in the server, the preset user identification set is inquired locally during matching, and when the preset user identification set is stored in the offline number bin, the preset user identification set is inquired from the offline number bin during matching. In addition, the preset user identifier set may also be updated according to a preset period, such as once per month.

In specific implementation, the sensitivity of each order placing user to the order receiving duration can be determined according to the flow of fig. 3, which includes the following steps.

In step 2031, the historical orders within the designated area are obtained.

The historical orders may be all historical orders in a specified area, or historical orders in a past period, for example, historical orders in a past year, where the historical orders include characteristic data such as an order placing user identifier, an order starting point, an order ending point, an order request time, and an order receiving time.

In step 2032, each historical order is divided into a first type historical order and a second type historical order according to the rule that the order taking time is shorter than the average order taking time of each historical order, the order taking time is a first type historical order, and the order taking time is not shorter than the average order taking time is a second type historical order.

When the method is specifically implemented, firstly, the average order taking time length is determined according to the order taking time length of each order in the historical orders, then, the order taking time length of each order is compared with the average order taking time length, the order taking time length which is less than the average order taking time length is divided into a first type of historical orders, and the order taking time length which is not less than the average order taking time length is divided into a second type of historical orders.

In step 2033, for each order placing user, when the order placing user satisfies the sensitivity determination condition, the sensitivity of the order placing user to the order taking duration is determined based on the first type of history orders and the second type of history orders of the order placing user.

The method comprises the steps that the sensitivity determination condition is that the historical order quantity of an order placing user reaches a preset value, and the historical orders of the order placing user comprise a first type of historical orders and a second type of historical orders.

In some embodiments, the sensitivity of the ordering user to the order-receiving duration may be determined according to the following steps:

the method comprises the following steps of firstly, determining a first sensitivity based on the established first prediction model and a first type of historical orders of ordering users.

When the method is specifically implemented, the first characteristic data of each first-class historical order of the ordering user is input into the first prediction model, the cancellation rate of the ordering user to the first-class historical orders is obtained, and the average value of the cancellation rate of the ordering user to each first-class historical order is determined as the first sensitivity of the ordering user.

For example, 3 historical orders of the order placing user in the first category, that is, order 1, order 2, and order 3, are input into the first prediction model respectively, so as to obtain an order cancellation rate 0.2 corresponding to order 1, an order cancellation rate 0.15 corresponding to order 2, and an order cancellation rate 0.1 corresponding to order 3, and then 0.15 may be determined as the first sensitivity of the order placing user.

And secondly, determining a second sensitivity based on the established second prediction model and a second type of historical orders of the ordering users.

When the method is specifically implemented, the first characteristic data of each second type historical order of the order placing user is input into the second prediction model, the cancellation rate of the order placing user to the second type historical orders is obtained, and the average value of the cancellation rate of the order placing user to each second type historical order is determined as the second sensitivity of the order placing user.

For example, 2 orders of the second type of historical orders of the order placing user are provided, the order 4 and the order 5 are respectively input into the second prediction model, the order cancellation rate corresponding to the order 4 is obtained as 0.7, the order cancellation rate corresponding to the order 5 is obtained as 0.8, and then 0.75 can be determined as the second sensitivity of the order placing user.

The first characteristic data comprises an indicated value of whether the actual order receiving duration is smaller than the average order receiving duration, if the indicated value of the order receiving duration smaller than the average order receiving duration is 0, the indicated value of the order receiving duration not smaller than the average order receiving duration is 1.

And thirdly, carrying out weighted summation on the first sensitivity and the second sensitivity to obtain the sensitivity of the order placing user to the order receiving time.

When the method is specifically implemented, the second characteristic data of each historical order of the ordering user can be input into the established tendency analysis model, a tendency score that the order receiving duration of the historical order is not less than the average order receiving duration is obtained, the second characteristic data comprise an indicating value that whether the actual order receiving duration is less than the average order receiving duration, the second characteristic data can be the same as the first characteristic data or different from the first characteristic data, the tendency scores corresponding to the historical orders of the ordering user are weighted and averaged, the weight of the ordering user on the first sensitivity is obtained, and then the difference value of a preset value such as 1 and the weight of the first sensitivity is used as the weight of the ordering user on the second sensitivity.

Then, the sensitivity of the ordering user to the order receiving time length is determined according to the following formula:

the sensitivity of the next user to the duration of the connection order = first sensitivity + weight of first sensitivity + second sensitivity + weight of second sensitivity.

In particular, the first predictive model and the second predictive model may be trained as follows.

Step 1: and performing model training by taking the first characteristic data of the first type of historical orders as input and the label value of whether the first type of historical orders are cancelled as output to obtain a first initial model, and performing model training by taking the first characteristic data of the second type of historical orders as input and the label value of whether the first type of historical orders are cancelled as output to obtain a second initial model.

Considering that the difference between the sample size of the first type of historical order and the sample size of the second type of historical order is larger, and the sample size of the first type of historical order is possibly far larger than that of the second type of historical order, or the sample size of the second type of historical order is possibly far larger than that of the first type of historical order, therefore, the prediction accuracy of the model trained on the first type of historical order with small sample size is poorer, and the model can be updated in a sample crossing mode in order to avoid the inaccurate result of the prediction model caused by the difference of the sample sizes of the orders. The following steps are performed for this purpose.

And 2, determining a first prediction error of the second initial model for each first type of historical orders, adding the first prediction error into first characteristic data of the first type of historical orders, determining a second prediction error of the first initial model for each second type of historical orders, and adding the second prediction error into the first characteristic data of the second type of historical orders.

And step 3: and training the first initial model by taking the first characteristic data of the first type of historical order after adding the first prediction error as input and the label value of whether the first characteristic data is cancelled as output to obtain a first prediction model, and training the second initial model by taking the first characteristic data of the second type of historical order after adding the second prediction error as input and the label value of whether the first characteristic data is cancelled as output to obtain a second prediction model.

In addition, if the order placing user identifier is not located in the preset user identifier set, the order matching single end can be matched according to the comprehensive scores, for example, factors such as comprehensive evaluation order receiving duration, order placing frequency of the order placing user, service quality of the order receiving end and the like are evaluated, scores are set for each evaluation factor, and the order is sent to the order receiving end with the comprehensive scores at the preset threshold value.

In step 204, based on the matching result, each order is dispatched to the order receiving end corresponding to the order.

For example, after the order placing user a and the order placing user B place an order, since the identifier of the order placing user a is located in the preset user identifier set, the order placing end can be matched for the order of the order placing user a according to the rule that the order receiving time length is shortest.

It should be noted that, after the order receiving end is matched for each order, the server dispatches the order to the order receiving end corresponding to the order, and sends the information of the order receiving end to the order placing user corresponding to the order, including the information of the contact way of the order receiving end, the estimated order receiving time and the like.

Therefore, when the order is sent to the ordering user, if the sensitivity of the ordering user to the order receiving time is higher than the set degree, the order receiving time is matched with the order receiving end according to the rule that the order receiving time is the shortest, so that the order cancellation rate is reduced, and better user experience is brought.

The scheme provided by the embodiment of the present application is described below by taking an order as a network car booking order as an example, and fig. 4 is a schematic diagram of an order delivery process provided by the embodiment of the present application, which includes a passenger side (a car placing user), a server, a driver side (a car receiving side) and an offline car counting bin, wherein a sensitivity of a car taking duration in a network car booking scene is a sensitivity of a car taking duration, a car placing user identifier is a passenger identifier, and a user identifier set is a passenger identifier set.

Firstly, the passenger end sends an order request to the server, wherein the order request comprises: and the driver end reports the vehicle position to the server in real time.

Then, after receiving an order request of a passenger end, the server acquires an available driver end near the order starting point in real time according to the order starting point in the order, calls a passenger identification set stored in an offline bin according to an identification of the passenger end, and matches the passenger end for the order according to a rule that the length of the passenger taking time is the shortest if the passenger identification of the passenger end exists in the passenger identification set, wherein the passenger identification with the sensitivity to the taking time higher than a set degree is stored in the passenger identification set. In addition, the passenger identification set can be stored in the server and can also be stored in an offline number bin, when the passenger identification set is stored in the server, the passenger identification set is directly inquired from the local part during matching, and when the passenger identification set is stored in the offline number bin, the passenger identification set is inquired from the offline number bin during matching. In addition, the set of passenger identifications may also be updated at a preset period, such as once a month.

And then, the server is used for matching the order with the driver side, transmitting the order matching result, such as estimated pick-up time, pick-up route and other information to the passenger side, and transmitting the order matching result, such as order information, passenger contact information and other information to the driver side.

And finally, after the driver end receives the dispatching information of the server, executing the processes of taking over, delivering and the like, if the passenger end cancels the order in the taking over process, ending the service process, matching the server end for the order again, and after each order is served (including canceling the order in the taking over process), storing the data of the whole order process to an off-line counting bin by the server.

The passenger with the sensitivity to the riding time of different passengers is different, the passenger with the sensitivity to the riding time higher than the set degree is called a high-time sensitive passenger, the requirement on the riding time of the passenger is stricter, the probability of cancelling the order after receiving the estimated riding time information is higher, the passenger with the sensitivity to the riding time not higher than the set degree is called a low-time sensitive passenger, the requirement on the riding time of the passenger is looser, and the probability of cancelling the order after receiving the estimated riding time information is lower. As shown in table 1:

TABLE 1

It should be noted that the passenger sensitivity to the pickup time length is usually determined based on two types of historical orders of the passenger, the first type of historical order with the pickup time length smaller than the average pickup time length of each historical order and the second type of historical order with the pickup time length not smaller than the average pickup time length of each historical order are respectively determined, and the passenger sensitivity to the pickup time length is obtained by calculating the passenger sensitivity to the first type of historical order and the passenger sensitivity to the second type of historical order and performing weighted summation on the first sensitivity and the second sensitivity.

Wherein, the passenger sensitivity to the riding time can be obtained according to the following steps:

step 1, determining the weight of the first sensitivity of the passenger to the multiplying time and the weight of the second sensitivity of the passenger to the multiplying time.

The average pick-up time S is first calculated, for example, once a month, and may be calculated using historical orders in a specified area, such as a city, over the last year, where the characteristic data for each order includes passenger identification, pick-up time, price, weather, etc.

The calculation formula is as follows:

unit: minutes (min).

Secondly, dividing each historical order according to the size relationship between the pick-up time length of each order and the average pick-up time length S:

and finally, inputting second characteristic data of each historical order of the passenger into the established tendency analysis model to obtain tendency scores of the historical orders, wherein the tendency scores are obtained when the order taking duration of the historical orders is larger than the average order taking duration, the second characteristic data comprise an indication value of whether the actual pickup duration is smaller than the average pickup duration, weighted averaging is carried out on the tendency scores corresponding to the historical orders of the passenger to obtain the weight M of the passenger to the first sensitivity, and the difference between a preset value such as 1 and the weight M is used as the weight of the passenger to the second sensitivity.

And 2, training a first prediction model for predicting the order cancellation rate of the first type of historical orders and a second prediction model for predicting the order cancellation rate of the second type of historical orders.

Here, the historical orders in the last year in a city are used as samples, the feature data of the orders at this time includes passenger identification, order start, order end, pickup time, price, weather and feature t, each type of orders has cancelled samples in order pickup and non-cancelled samples in order pickup, the labels of the samples that are not cancelled in order pickup are assigned with 0, the labels of the samples that are cancelled in order pickup are assigned with 1, data set splitting is performed by using the feature t, then model training is performed by using the first feature data of the samples with t =0 as input and using the label value that is cancelled as output, so as to obtain mode _0 (a first initial model), model training is performed by using the first feature data of the samples with t =1 as input and the label value that is cancelled as output, so as to obtain model _1 (a second initial model), and xgboost or other supervised learning algorithms can be used here.

Considering that the difference between the sample size of t =0 and the sample size of t =1 in the historical order is relatively large, and the sample size of t =0 is possibly far larger than the sample size of t =1, and the sample size of t =1 is also possibly far larger than the sample size of t =0, therefore, the prediction accuracy of the model trained on the historical order with a small sample size is poor, and therefore, in order to avoid the inaccuracy of the prediction result of the prediction model caused by the difference of the sample sizes of the order, the model can be updated in a sample crossing manner.

In specific implementation, according to the characteristics t, H ⁰ Represents the first prediction error, H, for model _1 for each t =0 order ¹ Second prediction error, representing model _0 for each t =1 order, would be H ⁰ Adding the H into the first characteristic data of the order with t =0 ¹ To the first profile data of the t =1 order.

Then, add H in t =0 order ⁰ The subsequent first feature data is input, and the label value of whether to be cancelled is output, model _0 is trained to obtain model _0' (the first prediction model), and H is added to the order of t =1 ¹ The latter first feature data is input, and the label value of whether the label is cancelled is output, and model _1 is trained to obtain model _1' (the second prediction model).

And 3, step 3: a first sensitivity and a second sensitivity of a passenger to a length of time for a ticket is determined.

Inputting the first characteristic data of each historical order of any passenger t =0 into mode _0' to obtain the cancellation rate of the historical orders, and determining the average value of the cancellation rate of the passenger on the historical orders of t =0 as the first sensitivity tau of the passenger ₀ Inputting the first characteristic data of each historical order of the passenger t =1 into model _1' to obtain the cancellation rate of the historical orders, and determining the average value of the cancellation rate of the passenger on the historical orders of t =1 as the second sensitivity tau of the passenger ₁ 。

And 4, step 4: the sensitivity of the passenger to the length of the ride is determined.

And carrying out weighted summation on the first sensitivity and the second sensitivity to obtain the sensitivity tau of the passenger to the multiplication time, wherein the formula is as follows:

τ＝M*τ ₀ +(1-M)*τ ₁ ，

wherein M is τ ₀ 0 < M < 1.

Therefore, the sensitivity of the passengers to the riding time is reasonably quantified, and the passengers with higher sensitivity to the riding time are matched with the terminal of the driver according to the rule of the shortest riding time, so that the time requirements of different passengers are better met, the cancellation rate is favorably reduced, and the operation efficiency of the network booking platform is improved.

Based on the same technical concept, the embodiment of the present application further provides an order dispatching device, and the principle of the order dispatching device for solving the problem is similar to that of the order dispatching method, so the implementation of the order dispatching device can refer to the implementation of the order dispatching method, and repeated parts are not described again.

Fig. 5 is a schematic structural diagram of an order dispatching device according to an embodiment of the present disclosure, which includes an obtaining module 501, a first determining module 502, a matching module 503, and a dispatching module 504.

An obtaining module 501, configured to obtain N orders to be dispatched in a specified area, where N is an integer greater than zero;

a first determining module 502, configured to determine N order taking ends that can take orders based on the starting points of the N orders;

a matching module 503, configured to match the N orders with the N order taking ends, where if an order placing user identifier of any order is located in a preset user identifier set, the order taking end is matched according to a rule that an order taking duration is the shortest, and the order placing user identifier with a higher sensitivity to the order taking duration than a set degree is stored in the preset user identifier set;

and the dispatching module 504 is configured to dispatch each order to the order receiving end corresponding to the order based on the matching result.

In some embodiments, a second determining module 505 is further included for determining the sensitivity of each order placing user to the order receiving duration according to the following steps:

acquiring a historical order in the designated area;

In some embodiments, the second determining module 505 is specifically configured to:

and carrying out weighted summation on the first sensitivity and the second sensitivity to obtain the sensitivity of the ordering user to the order receiving time.

and determining the average value of the cancellation rates of the ordering users to the first type of historical orders as the first sensitivity of the ordering users.

In some embodiments, a training module 506 is further included for training the first predictive model and the second predictive model according to the following steps:

In some embodiments, the weights of the first and second sensitivities of the order user are determined according to the following steps:

The division of the modules in the embodiments of the present application is schematic, and only one logic function division is provided, and in actual implementation, there may be another division manner, and in addition, each function module in each embodiment of the present application may be integrated in one processor, may also exist alone physically, or may also be integrated in one module by two or more modules. The coupling of the various modules to each other may be through interfaces that are typically electrical communication interfaces, but mechanical or other forms of interfaces are not excluded. Accordingly, modules illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed in different locations on the same or different devices. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

Having described the order delivery method and apparatus according to the exemplary embodiment of the present application, an electronic device according to another exemplary embodiment of the present application is described next.

An electronic device 130 implemented according to this embodiment of the present application is described below with reference to fig. 6. The electronic device 130 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 6, the electronic device 130 is represented in the form of a general electronic device. The components of the electronic device 130 may include, but are not limited to: the at least one processor 131, the at least one memory 132, and a bus 133 that couples various system components including the memory 132 and the processor 131.

Bus 133 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

The memory 132 may include readable media in the form of volatile memory, such as Random Access Memory (RAM) 1321 and/or cache memory 1322, and may further include Read Only Memory (ROM) 1323.

Memory 132 may also include programs/utilities 1325 having a set (at least one) of program modules 1324, such program modules 1324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment.

The electronic device 130 may also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), with one or more devices that enable a user to interact with the electronic device 130, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 130 to communicate with one or more other electronic devices. Such communication may occur through input/output (I/O) interfaces 135. Also, the electronic device 130 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 136. As shown, the network adapter 136 communicates with other modules for the electronic device 130 over the bus 133. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, to name a few.

In an exemplary embodiment, there is also provided a storage medium in which a computer program is stored, the computer program being capable of executing the above-described order dispatch method when executed by a processor of an electronic device. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, the electronic device of the present application may include at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores a computer program executable by the at least one processor, and the computer program, when executed by the at least one processor, causes the at least one processor to perform the steps of any of the order dispatch methods provided by the embodiments of the present application.

In an exemplary embodiment, a computer program product is also provided, which, when executed by an electronic device, enables the electronic device to implement any of the exemplary methods provided herein.

Also, a computer program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable Disk, a hard Disk, a RAM, a ROM, an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a Compact Disk Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The program product for order delivery in embodiments of the present application may take the form of a CD-ROM and include program code, and may be run on a computing device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, radio Frequency (RF), etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In situations involving remote computing devices, the remote computing devices may be connected to the user computing device over any kind of Network, such as a Local Area Network (LAN) or Wide Area Network (WAN), or may be connected to external computing devices (e.g., connected over the internet using an internet service provider).

It should be noted that although in the above detailed description several units or sub-units of the apparatus are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the units described above may be embodied in one unit, according to embodiments of the application. Conversely, the features and functions of one unit described above may be further divided into embodiments by a plurality of units.

Further, while the operations of the methods of the present application are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the present application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. An order dispatch method, comprising:

acquiring N orders to be dispatched in a specified area, wherein N is an integer greater than zero;

determining N order receiving ends capable of receiving orders based on the starting points of the N orders;

matching the N orders with the N order receiving ends, wherein if the order placing user identification of any order is located in a preset user identification set, the order is matched with the order receiving ends according to the rule that the order receiving time length is shortest, and the order placing user identification with the sensitivity of the order receiving time length higher than a set degree is stored in the preset user identification set;

2. The method of claim 1, wherein the sensitivity of each ordering user to the order-receiving duration is determined according to the steps of:

acquiring a historical order in the designated area;

and aiming at each order placing user, when the order placing user meets the sensitivity determination condition, determining the sensitivity of the order placing user to the order receiving time length based on the first type of historical orders and the second type of historical orders of the order placing user.

3. The method of claim 2, wherein determining the sensitivity of the order placing user to the order taking duration based on the first type of historical order and the second type of historical order of the order placing user comprises:

4. The method of claim 3, wherein determining a first sensitivity of the order placing user based on the established first predictive model and the first type of historical orders of the order placing user comprises:

5. The method of claim 3, wherein determining a second sensitivity of the order placing user based on the established second predictive model and a second type of historical orders for the order placing user comprises:

6. The method of any of claims 3-5, wherein the first predictive model and the second predictive model are trained according to the following steps:

7. The method of claim 2, wherein the weights of the first and second sensitivities of the order user are determined according to the following steps:

and taking the difference value of the preset value and the weight as the weight of the second sensitivity of the ordering user.

8. An order dispatch device, comprising:

the acquisition module is used for acquiring N orders to be dispatched in a specified area, wherein N is an integer larger than zero;

the matching module is used for matching the N orders with the N order receiving ends, wherein if the order placing user identification of any order is located in a preset user identification set, the order placing user identification is matched with the order receiving ends according to the rule that the order receiving time length is shortest, and the order placing user identification with the sensitivity of the order receiving time length higher than a set degree is stored in the preset user identification set;

9. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein:

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A storage medium, characterized in that, when the computer program in the storage medium is executed by a processor of an electronic device, the electronic device is capable of performing the method according to any one of claims 1-7.