CN107203866A - The processing method and device of order - Google Patents

Abstract

The invention discloses an order processing method and device, and relates to the technical field of big data. The method of the present invention includes: predicting the cancellation probability of the order according to the commodity attribute information of various commodities in the order; sorting each order according to the order of the cancellation probability of each order from small to large; arranging each order according to the order of each order production. The invention predicts the cancellation probability of the order based on the attributes of various commodities in the order, and arranges the production of the order according to the cancellation probability of each order. Orders with a high probability of being canceled are scheduled for post-production, which reduces the production priority of this type of order, making it likely that this type of order will not enter the production process when it is canceled, reducing the waste of human and material resources, while ensuring that the entire warehouse The continuity of the internal production process and improve production efficiency.

Description

Order processing method and device

technical field

The invention relates to the field of big data technology, in particular to an order processing method and device.

Background technique

The upsurge of the e-commerce industry has also promoted the development of logistics and warehousing industries. With the improvement of people's requirements for the efficiency of commodity delivery, warehouses are also constantly optimizing the production process, so as to complete a large number of orders in a relatively concentrated time.

Some warehouses even complete the goods out of the warehouse within an average of 10 minutes after receiving the order. Behind the high efficiency, a large number of personnel need to cooperate with each other in their respective positions to quickly complete picking, review, packaging, and out of the warehouse. The cancellation of an order will undoubtedly have a great impact on this one-way efficient process.

At present, after the order enters the production stage, it is generally impossible to determine the current stage of the order. In this case, if the order is cancelled, the order can only be cut off after the entire order production is completed.

Contents of the invention

The inventor found that the prior art solution of cutting off canceled orders wastes manpower and material resources, and if the failure to cut off the order causes the goods to go out of the warehouse, it will further cause greater losses.

A technical problem to be solved by the invention is: how to reduce the loss caused by order cancellation to the order production process.

According to an embodiment of the present invention, an order processing method is provided, including: predicting the probability of cancellation of the order according to the commodity attribute information of various commodities in the order; Orders are sorted; the production of each order is arranged according to the order of each order.

In one embodiment, predicting the cancellation probability of the order according to the commodity attribute information of various commodities in the order includes: inputting the commodity attribute information of various commodities into the classification model to obtain the cancellation probability of various commodities; The probability of being canceled for each item determines the probability of being canceled for that order.

In one embodiment, the following method is used to determine the classification model: obtain the commodity attribute information of various commodities in the historical order and the production status of the historical order as training data, and the production status includes canceled and non-cancelled; use the training data to classify the model Perform training to determine the classification model.

In one embodiment, using the training data to train the classification model includes: randomly selecting part of the commodity attribute information of various commodities with replacement according to the preset ratio range, and combining them with the corresponding production status as a decision tree Training data, train the decision tree to determine the decision tree; repeat the above process until all the decision trees in the classification model are determined.

In one embodiment, inputting commodity attribute information of various commodities into the classification model to obtain the cancellation probability of various commodities includes: selecting commodity attribute information corresponding to a decision tree in the classification model for each commodity and inputting it into the decision tree model , to obtain the classification of the product in the decision tree; determine the cancellation probability of the product according to the classification of the product in each decision tree and the total number of decision trees.

In one embodiment, the order cancellation probability is the sum of the cancellation probabilities of various commodities in the order minus the simultaneous cancellation probability of various commodities.

According to another embodiment of the present invention, an order processing device is provided, including: an order probability prediction module, used to predict the probability of cancellation of the order according to the commodity attribute information of various commodities in the order; an order sorting module, used to Orders are sorted in descending order of the probability of each order being canceled; the order production arrangement module is used to arrange the production of each order according to the order of each order.

In one embodiment, the order probability prediction module is used to input the commodity attribute information of various commodities into the classification model to obtain the cancellation probability of various commodities, and determine the order probability according to the cancellation probability of various commodities included in the order. Probability of being canceled.

In one embodiment, the processing device further includes: a classification model determination module, configured to obtain commodity attribute information of various commodities in the historical order and the production status of the historical order as training data, the production status includes canceled and not cancelled, The classification model is trained by using the training data to determine the classification model.

In one embodiment, the classification model determination module is used to randomly select some commodity attribute information of various commodities with replacement according to the preset ratio range, and combine them with the corresponding production status as the training data of a decision tree, The decision tree is trained to determine the decision tree, and the above process is repeated until all the decision trees in the classification model are determined.

In one embodiment, the order probability prediction module is used to select the commodity attribute information corresponding to the decision tree in the classification model for each commodity and input it into the decision tree model to obtain the classification of the commodity in the decision tree, and to obtain the classification of the commodity in the decision tree. The classification of the decision tree and the total number of decision trees determine the probability of the item being canceled.

In one embodiment, the order cancellation probability is the sum of the cancellation probabilities of various commodities in the order minus the simultaneous cancellation probability of various commodities.

According to yet another embodiment of the present invention, an order processing device is provided, including: a memory; and a processor coupled to the memory, the processor is configured to execute any one of the preceding instructions based on instructions stored in the memory device. The processing method of the order in the example.

According to yet another embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the order processing method in any one of the foregoing embodiments are implemented.

The invention predicts the cancellation probability of the order based on the attributes of various commodities in the order, and arranges the production of the order according to the cancellation probability of each order. Orders with a high probability of being canceled are scheduled for post-production, which reduces the production priority of such orders, making it likely that such orders will not enter the production process when they are canceled, reducing the waste of human and material resources, while ensuring that the entire warehouse The continuity of the internal production process and improve production efficiency.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 shows a schematic structural diagram of an order processing device according to an embodiment of the present invention.

Fig. 2 shows a schematic structural diagram of an order processing device according to another embodiment of the present invention.

Fig. 3 shows a schematic flowchart of an order processing method according to an embodiment of the present invention.

Fig. 4 shows a schematic flowchart of an order processing method according to another embodiment of the present invention.

Fig. 5 shows a schematic structural diagram of an order processing device according to another embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The following description of at least one exemplary embodiment is merely illustrative in nature and in no way taken as limiting the invention, its application or uses. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Aiming at the problem in the prior art that canceled orders can only be cut off after the production of the order is completed, which wastes manpower and material resources, this solution is proposed.

The order processing devices in the embodiments of the present invention can be implemented by various computing devices or computer systems, which will be described below in conjunction with FIG. 1 and FIG. 2 .

Fig. 1 is a structural diagram of an embodiment of the order processing device of the present invention. As shown in FIG. 1 , the device 10 of this embodiment includes: a memory 110 and a processor 120 coupled to the memory 110 , the processor 120 is configured to execute any one of the implementations of the present invention based on instructions stored in the memory 110 . The processing method of the order in the example.

Wherein, the memory 110 may include, for example, a system memory, a fixed non-volatile storage medium, and the like. The system memory stores, for example, an operating system, an application program, a boot loader (Boot Loader), a database, and other programs.

Fig. 2 is a structural diagram of another embodiment of the order processing device of the present invention. As shown in FIG. 2 , the device 10 of this embodiment includes: a memory 110 and a processor 120 , and may also include an input/output interface 230 , a network interface 240 , a storage interface 250 and the like. These interfaces 230 , 240 , 250 as well as the memory 110 and the processor 120 may be connected via a bus 260 , for example. Wherein, the input-output interface 230 provides a connection interface for input-output devices such as a monitor, a mouse, a keyboard, and a touch screen. The network interface 240 provides connection interfaces for various networking devices, for example, it can be connected to a database server or a cloud storage server. The storage interface 250 provides connection interfaces for external storage devices such as SD cards and U disks.

The present invention provides an order processing method, which will be described below in conjunction with FIG. 3 .

Fig. 3 is a flowchart of an embodiment of the order processing method of the present invention. As shown in Figure 3, the method of this embodiment includes:

Step S302, predicting the order cancellation probability according to the commodity attribute information of various commodities in the order.

An order contains one or more products, and each product has its corresponding product attribute information. The product attribute information includes, for example, product identification, product unit price, purchase quantity, product category, order time, order location, etc. Further product The attribute information may also include information about the corresponding purchasing user, such as user identification, user credit, and the like.

User credit can be determined according to the user's purchase records. The user credit can be determined for a certain commodity, for example, to obtain the user's historical order and the corresponding production status, the production status includes canceled and not cancelled; then extract the various commodities in the historical order and their corresponding production status, according to The ratio of the number of times the product is canceled to the total number of orders determines the user credit for the product. It is also possible to evaluate the user credit overall. For example, first obtain the user's historical orders and corresponding production status, the production status includes canceled and non-cancelled; then determine the user credit based on the ratio of the number of canceled orders in the user's history to the total number of orders of the user.

Step S304, sorting the orders according to the order of the cancellation probability of each order from small to large.

Step S306, arrange the production of each order according to the sequence of each order.

The method in the above embodiment predicts the probability of cancellation of the order based on the attributes of various commodities in the order, and arranges the production of the order according to the probability of cancellation of each order. Orders with a high probability of being canceled are scheduled for post-production, which reduces the production priority of such orders, making it likely that such orders will not enter the production process when they are canceled, reducing the waste of human and material resources, while ensuring that the entire warehouse The continuity of the internal production process and improve production efficiency.

For the problem of how to predict the probability of cancellation of the order according to the commodity attribute information of various commodities in the order in the above step S302, the present invention provides the following exemplary implementations:

Preferably, the commodity attribute information of various commodities in the order is extracted; the commodity attribute information of various commodities is respectively input into the classification model to obtain the cancellation probability of various commodities; the order is determined according to the cancellation probability of various commodities included in the order probability of being canceled.

In one embodiment, the commodity attribute information of various commodities is divided into commodity characteristic attribute information and commodity user attribute information according to characteristics; the commodity characteristic attribute information of various commodities is respectively input into the classification model to obtain the first canceled information of various commodities Probability, determine the second cancellation probability of various commodities according to the commodity user attribute information, and carry out weighted summation of the first cancellation probability and the second cancellation probability for each commodity to obtain the cancellation probability of the commodity; according to the The probability of being canceled for the various items included determines the probability of being canceled for this order. Wherein, the second probability of being canceled is, for example, the credit degree of the user for the product.

Further, the order cancellation probability is, for example, the sum of the cancellation probabilities of various commodities in the order minus the simultaneous cancellation probability of various commodities. The simultaneous cancellation probability of various commodities is, for example, the product of the cancellation probabilities of various commodities.

The classification model is, for example, a decision tree model or a naive Bayesian model, and the decision tree model is, for example, a random forest model or a gradient boosting decision tree model. The above-mentioned models are all prior art, and will not be repeated here.

Before using the classification model to obtain the cancellation probability of various commodities, the classification model can be obtained by using the historical order data to train the classification model. It will be described below in conjunction with FIG. 4 .

Fig. 4 is a flow chart of another embodiment of the order processing method of the present invention. As shown in Figure 4, before step S302 may also include:

Step S402, acquiring commodity attribute information of various commodities in the historical order and production status of the historical order as training data.

Production status includes canceled and not canceled. The production status can be binarized, for example, 0 means not cancelled, 1 means canceled.

Step S404, using the training data to train the classification model to determine the classification model.

Specifically, when the classification model is composed of multiple decision trees, randomly select part of the commodity attribute information of various commodities with replacement according to the preset ratio range, and combine them with the corresponding production status as the training data of a decision tree , train the decision tree to determine the decision tree; repeat the above process until all the decision trees in the classification model are determined.

After extracting the commodity attribute information and production status of various commodities in the historical order, it can be stored in the form of Table 1.

Table 1

Each row in Table 1 represents the commodity attribute information and the corresponding production status of a commodity. Among them, E1-Ei are independent variables, (i is a positive integer, representing the i-th commodity attribute information), and D is a dependent variable. When the classification model is composed of multiple decision trees, some data can be extracted according to Table 1 to generate multiple training subsets, and each training subset is used as the training data of a decision tree. Specifically, the column data representing the part of the product attribute information in Table 1 is extracted with replacement, and combined with the corresponding production status as a training subset. The types of product attribute information in each training subset are, for example, 10% of the total types. ~90% range. The data in each training subset is used to build a decision tree, until all the decision trees in the classification model are constructed, and then the classification model is obtained.

For example, for a decision tree, select the unit price, purchase quantity and production status of various commodities to combine to obtain the training data of the decision tree; for another decision tree, select the order time, purchase quantity and production status of various commodities. The production status is combined to obtain the training data of the decision tree.

Based on the above training process, it can be seen that each decision tree corresponds to different product attribute information. Therefore, when determining the probability of product cancellation, the following methods can be used:

For each commodity, select the commodity attribute information corresponding to the decision tree in the classification model and input it into the decision tree model to obtain the classification of the commodity in the decision tree; Cancellation probability.

After extracting the commodity attribute information and production status of various commodities in the order, they can be stored in the form of Table 2.

Table 2

For different decision trees, select the data of the column corresponding to each commodity in Table 2 and input it into the decision tree to obtain the classification of various commodities in each decision tree. The number of class cancellations divided by the total number of decision trees.

For example, if you want to get the cancellation probability of a product with a product ID of 312341, first, for the first decision tree, which is constructed based on two product attribute information, the product unit price and the purchase quantity, the product unit price of 312341 is 2.15 Input the purchase quantity 5 into the first decision tree, and get the classification of 312341 as the canceled class. Refer to the above process to obtain the classification of 312341 in each decision tree. For example, in 40 decision trees, 312341 is classified as the canceled class. In 10 trees, 312341 is divided into the non-cancelled class, then the probability of 312341 being canceled is 80%.

In the present invention, new historical order data can also be used to update the classification model at preset intervals.

The present invention also provides an order processing device, which will be described below with reference to FIG. 5 .

Fig. 5 is a structural diagram of an embodiment of the order processing device of the present invention. As shown in Figure 5, the device 50 includes:

The order probability prediction module 502 is configured to predict the probability of the order being canceled according to the commodity attribute information of various commodities in the order.

Preferably, the order probability prediction module 502 is used to input the commodity attribute information of various commodities into the classification model to obtain the cancellation probability of various commodities, and determine the cancellation of the order according to the cancellation probability of various commodities included in the order probability.

Further, the order probability prediction module 502 is used to select the commodity attribute information corresponding to the decision tree in the classification model for each commodity and input it into the decision tree model, obtain the classification of the commodity in the decision tree, and according to the classification of the commodity in each decision tree, The classification and the total number of decision trees determine the probability of an item being canceled.

Preferably, the order cancellation probability is the sum of the cancellation probabilities of various commodities in the order minus the simultaneous cancellation probability of various commodities.

The order sorting module 504 is configured to sort the orders in descending order of the probability of each order being canceled.

The order production arrangement module 506 is configured to arrange the production of each order according to the sequence of each order.

In one embodiment, the order processing device 50 may also include:

The classification model determination module 508 is used to obtain the commodity attribute information of various commodities in the historical order and the production status of the historical order as training data, the production status includes canceled and non-cancelled, and the classification model is trained using the training data to determine the classification model .

Preferably, the classification model determination module 508 is used to randomly select part of the commodity attribute information of various commodities with replacement according to the preset ratio range, and combine it with the corresponding production status as the training data of a decision tree. The decision tree is trained to determine the decision tree, and the above process is repeated until all the decision trees in the classification model are determined.

The present invention also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the order processing method in any one of the foregoing embodiments are implemented.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein .

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and a combination of processes and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection of the present invention. within range.

Claims (14)

1. a kind of processing method of order, it is characterised in that including：

Probability is cancelled according to what the information attribute value of extensive stock in order predicted the order；

Each order is ranked up according to the ascending order of probability that is cancelled of each order；

The production of each order is arranged according to the sequence of each order.

2. processing method according to claim 1, it is characterised in that

The information attribute value according to extensive stock in order predicts that the probability that is cancelled of the order includes：

The information attribute value of extensive stock is respectively inputted into disaggregated model obtain extensive stock and be cancelled probability；

According to the extensive stock included in order be cancelled the determine the probability order be cancelled probability.

3. processing method according to claim 2, it is characterised in that

Disaggregated model is determined using following methods：

Obtain History Order in extensive stock information attribute value and History Order production status as training data, The production status includes being cancelled and not cancelling；

The determination disaggregated model is trained to the disaggregated model using the training data.

4. processing method according to claim 3, it is characterised in that

It is described using the training data disaggregated model is trained including：

There is the part information attribute value for randomly selecting extensive stock put back to according to preset ratio scope, and produced with corresponding State is combined the training data as a decision tree, and the decision tree is trained and determines the decision tree；

Said process is repeated, until determining whole decision trees in the disaggregated model.

5. processing method according to claim 2, it is characterised in that

The probability that is cancelled that the information attribute value by extensive stock inputs disaggregated model acquisition extensive stock respectively includes：

Information attribute value corresponding with the decision tree in the disaggregated model, which is chosen, for every kind of commodity inputs the decision tree mould Type, obtains classification of the commodity in the decision tree；

According to the commodity probability is cancelled what the classification of each decision tree and the sum of decision tree determined the commodity.

6. processing method according to claim 2, it is characterised in that

The probability that is cancelled of order subtracts extensive stock while being cancelled general for the probability sum that is cancelled of extensive stock in order Rate.

7. a kind of processing unit of order, it is characterised in that including：

Order probabilistic forecasting module, being cancelled for the order is predicted for the information attribute value according to extensive stock in order Probability；

Order Sorting module, for being arranged according to the ascending order of probability that is cancelled of each order each order Sequence；

Order scheduling of production module, the production of each order is arranged for the sequence according to each order.

8. processing unit according to claim 7, it is characterised in that

The order probabilistic forecasting module, obtains various for the information attribute value of extensive stock to be inputted into disaggregated model respectively Commodity are cancelled probability, according to the extensive stock that is included in order be cancelled the determine the probability order be cancelled probability.

9. processing unit according to claim 8, it is characterised in that also include：

Disaggregated model determining module, information attribute value and History Order for obtaining extensive stock in History Order Production status is as training data, and the production status includes being cancelled and not cancelling, using the training data to described point Class model is trained the determination disaggregated model.

10. processing unit according to claim 9, it is characterised in that

The disaggregated model determining module, the part business for randomly selecting extensive stock put back to for having according to preset ratio scope Product attribute information, and the training data as a decision tree is combined with corresponding production status, the decision tree is carried out Training determines the decision tree, repeats said process, until determining whole decision trees in the disaggregated model.

11. processing unit according to claim 8, it is characterised in that

The order probabilistic forecasting module, for choosing business corresponding with the decision tree in the disaggregated model for every kind of commodity Product attribute information inputs the decision-tree model, obtains classification of the commodity in the decision tree, is determined according to the commodity at each What the classification of plan tree and the sum of decision tree determined the commodity is cancelled probability.

12. processing unit according to claim 8, it is characterised in that

The probability that is cancelled of order subtracts extensive stock while being cancelled general for the probability sum that is cancelled of extensive stock in order Rate.

13. a kind of processing unit of order, it is characterised in that including：

Memory；And

The processor of the memory is coupled to, the processor is configured as based on the finger being stored in the memory devices Order, performs the processing method of the order as described in claim any one of 1-6.

14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The step of any one of claim 1-6 methods described is realized during execution.