CN110619400A

CN110619400A - Method and device for generating order information

Info

Publication number: CN110619400A
Application number: CN201810628111.5A
Authority: CN
Inventors: 孙泽; 刘仁敏; 刘旭; 程瑞华
Original assignee: Beijing Jingdong Zhenshi Information Technology Co Ltd
Current assignee: Beijing Jingdong Zhenshi Information Technology Co Ltd
Priority date: 2018-06-19
Filing date: 2018-06-19
Publication date: 2019-12-27

Abstract

The embodiment of the application discloses a method and a device for generating order information. One embodiment of the method comprises: acquiring an unprocessed order set of a target warehouse in a target time period; generating average first target attribute information of the unprocessed order set based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set; and inputting the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute to obtain the predicted processing quantity of the unprocessed orders in the target time period by the target warehouse, wherein the processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed orders. This embodiment enables prediction of the number of orders that the target warehouse may handle during the target time period.

Description

Method and device for generating order information

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a method and a device for generating order information.

Background

For an offline warehouse of an e-commerce enterprise and an express enterprise, the order number, the number of workers and the like of the warehouse are reasonably configured by a warehouse manager or a technician according to historical experience. Since the task amount of the warehouse is variable in the actual production process, the allocation of resources and manpower for the warehouse is always a direction for continuous optimization and improvement of e-commerce and express enterprises.

Disclosure of Invention

The embodiment of the application provides a method and a device for generating order information.

In a first aspect, an embodiment of the present application provides a method for generating order information, where the method includes: acquiring an unprocessed order set of a target warehouse in a target time period; generating average first target attribute information of the unprocessed order set based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set; and inputting the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute to obtain the predicted processing quantity of the unprocessed orders in the target time period by the target warehouse, wherein the processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed orders.

In some embodiments, the process quantity prediction model is trained by: obtaining a plurality of training samples, wherein the training samples comprise average first target attribute information of unprocessed order sets of a target warehouse in a target history time period and the number of unprocessed orders processed by the target warehouse in the target history time period; and training to obtain a processing quantity prediction model by using a machine learning method and taking the average first target attribute information of the unprocessed order set of the target warehouse in each training sample in the target history time period as input and the quantity of the unprocessed orders processed by the target warehouse in the target history time period as output.

In some embodiments, the first target attribute of the unprocessed order comprises at least one of: the average number of included items, the average number of included item types, the average number of parcels, the average weight, the average volume, the number of official employees of the target warehouse within the target time period, the number of temporary employees of the target warehouse within the target time period, the total working time of the official employees, and the total working time of the temporary employees.

In some embodiments, the method further comprises: selecting a prediction processing quantity of unprocessed orders from the unprocessed order set to generate a to-be-processed order set; for each order to be processed in the order set to be processed, inputting attribute information of a second target attribute of the order to be processed into a pre-trained processing time prediction model corresponding to the second target attribute to obtain the predicted processing time of the order to be processed by the target warehouse, wherein the processing time prediction model is used for representing the corresponding relation between the attribute information of the second target attribute of the order to be processed and the predicted processing time of the order to be processed; the total predicted processing time for the set of orders to be processed is determined based on the predicted processing time for each order to be processed in the set of orders to be processed.

In some embodiments, the process time prediction model is trained by: acquiring a plurality of training samples, wherein the training samples comprise attribute information of a second target attribute of the order processed by the target warehouse and processing time of the processed order by the target warehouse; and by utilizing a machine learning method, taking the attribute information of the second target attribute of the order processed by the target warehouse in each training sample as input, taking the processing time of the processed order by the target warehouse as output, and training to obtain a processing time prediction model.

In some embodiments, the second target attribute of the pending order comprises at least one of: temporary employee tags containing item number, containing item type number, parcel number, weight, volume, and target warehouse.

In a second aspect, an embodiment of the present application provides an apparatus for generating order information, where the apparatus includes: an acquisition unit configured to acquire a set of unprocessed orders of a target warehouse within a target time period; an average first target attribute information generating unit configured to generate average first target attribute information of the unprocessed order set based on attribute information of a first target attribute of each unprocessed order in the unprocessed order set; and the predicted processing quantity generation unit is configured to input the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute to obtain a predicted processing quantity of the unprocessed orders in the target time period by the target warehouse, wherein the processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed orders.

In some embodiments, the apparatus further comprises: the to-be-processed order set generating unit is configured to select a prediction processing quantity of unprocessed orders from the unprocessed order set and generate a to-be-processed order set; the prediction processing time generation unit is configured to input attribute information of a second target attribute of each to-be-processed order in the to-be-processed order set to a pre-trained processing time prediction model corresponding to the second target attribute to obtain the prediction processing time of the to-be-processed order by the target warehouse, wherein the processing time prediction model is used for representing the corresponding relation between the attribute information of the second target attribute of the to-be-processed order and the prediction processing time of the to-be-processed order; and the predicted total processing time generation unit is configured to determine the predicted total processing time of the set of the orders to be processed based on the predicted processing time of each order to be processed in the set of the orders to be processed.

In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.

In a fourth aspect, the present application provides a computer-readable medium, on which a computer program is stored, which, when executed by a processor, implements the method as described in any implementation manner of the first aspect.

According to the method and the device for generating order information, provided by the embodiment of the application, the average first target attribute information of the unprocessed order set is generated based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set of the target warehouse in the target time period. Then, the average first target attribute information is input into a pre-trained processing quantity prediction model corresponding to the first target attribute, so that the predicted processing quantity of the target warehouse for unprocessed orders in the target time period is obtained, and the prediction of the quantity of the orders which can be processed by the target warehouse in the target time period is realized.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for generating order information of the present application;

FIG. 3 is a schematic diagram of an application scenario of a method for generating order information according to the present application;

FIG. 4 is a flow diagram of yet another embodiment of a method for generating order information according to the present application;

FIG. 5 is a schematic illustration of yet another application scenario of a method for generating order information according to the present application;

FIG. 6 is a block diagram illustrating one embodiment of an apparatus for generating order information according to the present application;

fig. 7 is a schematic structural diagram of a computer system suitable for implementing the terminal device or the server according to the embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Fig. 1 shows an exemplary architecture 100 to which the method for generating order information or the apparatus for generating order information of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The terminal devices 101, 102, 103 interact with a server 105 via a network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various client applications installed thereon, such as a web browser application, a shopping-like application, a search-like application, an instant messaging tool, a mailbox client, social platform software, a text editing-like application, a browser-like application, and the like.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting data processing, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server that provides various services, such as an order processing server that processes information of orders on the terminal apparatuses 101, 102, 103. The order processing server may perform processing such as analysis on the acquired information of the order (for example, attribute information of the target attribute of the unprocessed order) to obtain a processing result (for example, a predicted processing amount of the unprocessed order).

Note that, the order information may be directly stored locally in the server 105, and the server 105 may directly extract and process the order information stored locally, and in this case, the terminal apparatuses 101, 102, and 103 and the network 104 may not be present).

It should be noted that the method for generating order information provided in the embodiment of the present application is generally performed by the server 105, and accordingly, the apparatus for generating order information is generally disposed in the server 105. At this time, the terminal apparatuses 101, 102, 103 and the network 104 may not exist. In addition, the method for generating order information provided by the embodiment of the present application may also be executed by the terminal devices 101, 102, and 103, and accordingly, the apparatus for generating order information is disposed in the terminal devices 101, 102, and 103. At this point, the exemplary system architecture 100 may not have the network 104 and the server 105.

It should be noted that the server 105 may be a single server, or may be composed of a plurality of servers or a plurality of server clusters.

The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating order information according to the present application is shown. The method for generating order information includes the steps of:

step 201, obtaining an unprocessed order set of a target warehouse within a target time period.

In this embodiment, an executing entity (such as the server 105 shown in fig. 1) of the method for generating order information may obtain an unprocessed order set of the target warehouse in the target time period from the terminal device or another server storing order data of the target warehouse through a wired connection or a wireless connection. In addition, the order data of the target warehouse may also be stored locally in the execution main body, and in this case, the execution main body may directly obtain an unprocessed order set of the target warehouse within the target time period from the local.

A warehouse may refer to a storage facility for providing storage services, and may generally include a warehouse for storing goods, a transportation and transfer facility (such as a crane, an elevator, a slide, etc.), a transportation pipeline and equipment for entering and exiting the warehouse, a fire-fighting facility, a management room, etc. The warehouse may store any items involved in various industries. For example, general goods, electronic equipment, food, rubber products, medicines, medical instruments, chemicals, cultural goods, instruments and meters, etc. can be stored, metal materials, building materials, ores, mechanical products, vehicles, oils, chemical raw materials, wood and products thereof, etc. can be stored, and gas such as cement, dry slag, fly ash, bulk grain, petroleum, gas, etc. can be stored. The target warehouse may be a warehouse designated in advance by an actual manager or a technician, or a warehouse screened out according to a certain preset rule according to a specific application requirement.

The target time period may be a time period specified in advance by an actual manager or a technician, or may be a time period satisfying an actual application requirement. For example, the target time period may be the current day, within 24 hours (e.g., nine am to nine the next day), within 48 hours, a month, or a quarter, etc.

The order may refer to the order form issued by the purchasing department or user of the enterprise, school or government to the supplier. For example, the order may be an electronic order of a product or service purchased by the user on an e-commerce website, a ticket order for purchase, a paper order provided by a purchaser or a supplier, or the like. The processing of the order by the warehouse may include making a pick order according to the contents of the order, picking by staff, assembling, packaging, shipping, etc.

It should be understood that the processing of the order is related to the specific content of the order, and the processing flow of the order can be determined according to the actual content of the order. For example, for a returned order, the corresponding process flow may include receiving returned items, reviewing warranty cards, inspecting returned items, returning items for repair, recycling or storage, etc. For the service type, such as the order of the home services, the corresponding processing flow includes picking the service personnel, registering the serial number of the service personnel, picking the tools or objects required by the service, reviewing the information of the service order (such as the service address, the service duration, the special requirement, etc.), and the like. An unprocessed order may refer to an order that the supplier or service provider received the order and has not yet performed any processing or operations. An unprocessed order for a warehouse may refer to an order assigned to the warehouse by a supplier or service provider that has not yet been processed or operated.

Step 202, generating average first target attribute information of the unprocessed order set based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set.

In this embodiment, the executing agent may first obtain attribute information of the first target attribute of each unprocessed order in the unprocessed order set. Then, based on the attribute information of the first target attribute of each unprocessed order, average first target attribute information of the unprocessed order set is obtained. Wherein the first target attribute of an unprocessed order may refer to any information directly or indirectly related to the unprocessed order. For example, the first target attribute of the unprocessed order may include attributes directly related to the unprocessed order, such as order number, order time, name of the item contained by the order, number of items contained by the order (which may indicate the number of items involved in the order), number of types of items contained by the order (which may indicate the number of types of items involved in the order), number of packages in the order (which may indicate the number of packages into which the items involved in the order need to be packaged), weight and volume of the order (which may indicate the total weight and volume of the items involved in the order), and total amount of the order. The first target attributes of the unprocessed order may also include, for example, a warehouse name and number assigned to the order, a size of the warehouse, a number and total working time of official employees of the warehouse, a number and total working time of temporary employees of the warehouse, a supplier of the order, a representative code number of the order, etc., indirectly related to the unprocessed order, or may be any combination of the above first target attributes.

Correspondingly, the set of unprocessed orders has an average first target attribute corresponding to the unprocessed orders therein. For example, average number of items, average number of types of items, average number of parcels, average weight, average volume, and the like. It should be understood that the attributes of the order are related to the specific content to which the order relates. For example, for an order related to electronic information (e.g., a user purchases a member of a website), the corresponding attributes of the order may not include the quantity of the type of the item, the number of packages to be packaged in the order, the weight and volume of the corresponding packages, and other attributes. The attribute information of the first target attribute of the unprocessed order may refer to a quantized specific numerical value of the attribute of the order, or may refer to a specific identifier or number corresponding to the first target attribute of the unprocessed order. For example, for the attribute of the number of items included in the unprocessed order, the attribute value may be a specific numerical value for indicating the number of items involved or included in the unprocessed order. For the attribute of the name of the item to which the unprocessed order relates, the attribute value may be a number of the item by the supplier. The first target attribute may be some attribute of the unprocessed order that is pre-specified by the actual operator or technician based on historical experience, or some attribute of the unprocessed order that is determined according to the specific application requirements.

It should be noted that the above-mentioned first target attribute is only named for convenience of description, and those skilled in the art should understand that the first one does not constitute a specific limitation on the target attribute.

In practice, after obtaining the attribute information of the first target attribute of each unprocessed order in the unprocessed order set, the sum of the attribute information of the first target attribute of each unprocessed order in the unprocessed order set may be determined first, and then divided by the number of unprocessed orders in the unprocessed order set, and the obtained result may be used as the average first target attribute information of the unprocessed order set.

It should be noted that, if there are a plurality of first target attribute information, the sum of the attribute information of each target attribute of each unprocessed order is determined, and then the sum is divided by the number of unprocessed orders, so as to obtain the flat first target attribute information of the unprocessed order set. For example, for an unprocessed order set C containing two unprocessed orders a and B, where the first target attribute of unprocessed order a includes the number of items contained in order a and the number of categories of items contained in order a, the corresponding attribute information is 10 and 6, respectively, that is, unprocessed order a contains 10 items, which relates to 6 items. The first target attribute of unprocessed order B includes the number of items included in order B and the number of categories of items included in order B, and the corresponding attribute information is 8 and 7, respectively, that is, unprocessed order B includes 8 items, which relates to 7 types of items. Then, with respect to the attribute of the number of contained items, the average number of contained items of the unprocessed order a and the unprocessed order B may be 9((10+8)/2 ═ 9). With regard to the attribute of the number of types of contained items, the average number of types of contained items of the unprocessed order a and the unprocessed order B may be 6.5((6+7)/2 ═ 6.5). Thus, the first target attribute information for the corresponding unprocessed order set C may be (9, 6.5). Note that, if the unprocessed order does not have the first target attribute, or if the attribute information of the first target attribute of the unprocessed order is lost, the attribute information of the first target attribute may be processed as 0.

Step 203, inputting the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute, so as to obtain the predicted processing quantity of the target warehouse for unprocessed orders in the target time period.

In this embodiment, the executing entity may first obtain a pre-trained processing quantity prediction model corresponding to the first target attribute of each unprocessed order in the unprocessed order set of the target warehouse obtained in step 202 in the target time period. Then, the average first target attribute information obtained in step 202 is input to a pre-trained processing quantity prediction model corresponding to the first target attribute, so as to obtain a predicted processing quantity of the target warehouse for unprocessed orders in the target time period. The processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed order.

In practice, the execution body may store therein a plurality of pre-trained process quantity prediction models. Wherein each processed quantity prediction model corresponds to a first target attribute of each unprocessed order in the set of unprocessed orders for the target warehouse over the target time period. For example, a plurality of process quantity prediction models corresponding to different applications may be trained in advance according to different application requirements. For example, if it is desired to know the relationship between the number of items contained in each daily order of a warehouse and the number of types of items contained in each daily order of the warehouse and the number of orders that can be processed in each day of the warehouse, a processing quantity prediction model representing the correspondence between the average number of items contained in the set of unprocessed orders of each day of the warehouse and the average number of types of items contained in the set of unprocessed orders of each day of the warehouse and the predicted processing quantity of unprocessed orders of each day of the warehouse may be trained. For example, to learn the relationship between the number of items, the weight of the items, the official employee number and the total working time of a warehouse per month and the number of orders that the warehouse can handle per month, a processing quantity prediction model representing the correspondence between the average number of items, the average weight, the official employee number and the total working time of the set of unprocessed orders of the warehouse per month and the predicted processing quantity of unprocessed orders of the warehouse per month can be trained.

As an example, the processed quantity prediction model may be a correspondence table in which the average first target attribute information of the unprocessed order sets of the target warehouse within the target history time period and the quantity of the unprocessed orders processed by the target warehouse within the target history time period are stored, which is generated by a technician based on statistics of the average first target attribute of a large number of unprocessed order sets of the target warehouse within the target history time period and the quantity of the unprocessed orders processed by the target warehouse within the target history time period. Then, the executing entity may first determine average first target attribute information of the unprocessed order sets based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order sets of the target warehouse within the target time period, and find the number of processed unprocessed orders corresponding to the average first target attribute information from the correspondence table. The processing quantity prediction model may also be a calculation formula for characterizing average first target attribute information of the unprocessed order sets of the target warehouse in the target history time period and the unprocessed orders processed by the target warehouse in the target history time period, which is obtained by a technician based on statistics of related data of orders of a large number of target warehouses in the target history time period, so that the execution body may determine the predicted processing quantity of the unprocessed orders of the target warehouse in the target time period based on the calculation formula.

As an example, the process quantity prediction model may be obtained by training: first, attribute information of a first target attribute of each unprocessed order in the set of unprocessed orders by the target warehouse during a target history time period (e.g., during each month of the first three years of the current date) and a quantity of unprocessed orders processed by the target warehouse during the target history time period are obtained.

Then, data filtering may be performed on the obtained attribute information of the first target attribute of each unprocessed order, for example, some abnormal values existing therein, such as null data or data logically having an error (for example, the number of categories of an item related to a certain order is too large, etc.) may be deleted, and then, based on the attribute information of the first target attribute of each unprocessed order in the filtered unprocessed order set, an average first target attribute information of the unprocessed order set is determined, and the average first target attribute information and the number of processed unprocessed orders corresponding to each unprocessed order in the unprocessed order set together constitute a training sample.

The training samples may then be divided into a training set, a test set, and a validation set. The division ratio of the training set, the test set and the verification set can be 6:2:2, and the specific division ratio can also be determined by a technician. Then, some existing regression models (such as a progressive gradient regression tree) or a combination of existing multiple regression models can be selected as the initialization processing quantity prediction model. The average first target attribute of the set of unprocessed orders in the training set is then used as an input to train a number of initial process quantity prediction models based on the output of the models and a preset penalty function. When the value of the loss function is smaller than a certain threshold value, the training can be stopped, a plurality of processed quantity prediction models trained by the training set are obtained, then the average first target attribute of an unprocessed order set in a verification set is respectively used as the input of the plurality of processed quantity prediction models trained by the training set, the difference between the output of the models and the quantity of the corresponding processed unprocessed orders in the verification set is counted, then the accuracy of the plurality of processed quantity prediction models trained by the training set is determined based on the difference, and one processed quantity prediction model with the highest accuracy can be selected as the trained processed quantity prediction model. Then, the trained processing quantity prediction model can be tested by using the test set, and the performance of the trained processing quantity prediction model is measured according to the test result.

In practice, based on the obtained predicted processing quantity, the quantity of orders that can be processed by the target warehouse in the target time period can be predicted. Then, the resources (such as the number of employees, etc.) of the target warehouse in the target time period can be configured in advance according to the obtained predicted number and in combination with the actual demand.

In some optional implementations of this embodiment, the process quantity prediction model may be obtained by training: first, a plurality of training samples may be obtained, each training sample including average first target attribute information for a set of unprocessed orders for a target warehouse over a target history period (e.g., within a day prior to 30 days of a current date), and a number of unprocessed orders processed within the target history period.

Then, an initialized processing quantity prediction model is obtained, the average first target attribute information of the unprocessed order set in the obtained training sample is used as input, and the initialized processing quantity prediction model is trained based on the output of the model and a preset loss function, so that the processing quantity prediction model is obtained. The initialized process quantity prediction model may be an untrained Deep learning model (DNN) or an untrained Deep learning model. Each layer of the initial process quantity prediction model may be provided with initial parameters that may be continually adjusted during the training process. The initialization processing quantity prediction model may be various types of untrained or untrained artificial neural networks or a model obtained by combining various types of untrained or untrained artificial neural networks, for example, the initialization processing quantity prediction model may be an untrained convolutional neural network, an untrained cyclic neural network, or a model obtained by combining an untrained convolutional neural network, an untrained cyclic neural network, and an untrained fully-connected layer.

The value of the loss function may be used to represent a difference between the predicted processed quantity output by the model and the quantity of the processed unprocessed orders corresponding to the average first target attribute information of the input unprocessed order set. The smaller the loss function, the smaller the difference. In the training process, an absolute value of a difference between the predicted processed number output by the model and the number of processed unprocessed orders corresponding to the average first target attribute information of the input set of unprocessed orders may be used as a loss function. Then, when it is determined that the values of the loss function of two or more times before and after the determination are both smaller than a certain threshold, the training is completed. And taking the initialized processing quantity prediction model after training as a processing quantity prediction model.

With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method for generating order information according to the present embodiment. In the application scenario of fig. 3, a set of unprocessed orders 301 for a target warehouse over a target time period (e.g., the current day) may be obtained, including unprocessed orders A, B and C. Attribute information 302 for the first target attribute of unprocessed order A includes M1 and N1, attribute information 302 for the first target attribute of unprocessed order B includes M2 and N2, and attribute information 302 for the first target attribute of unprocessed order C includes M3 and N3. Where M and N are first target attributes of the unprocessed order, such as may be the unprocessed order containing the number of items and the number of official employees of the target warehouse during the current day, respectively.

The sum of M1, M2, and M3 was then divided by 3 to give M4, and the sum of N1, N2, and N3 was divided by 3 to give N4. M4 and N4 are the average first target attribute information for the set of unprocessed orders 301. A pre-trained process quantity prediction model 304 corresponding to the first target attributes M and N of the unprocessed order is then obtained. Then, the average first target attribute information M4 and N4 of the unprocessed order set 301 are input (may be in the form of a vector { M4N4 }) to the process quantity prediction model 304, so as to obtain the predicted process quantity of the unprocessed order by the target warehouse in the current day.

The method provided by the above embodiment of the present application generates average first target attribute information of the unprocessed order set based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set of the target warehouse within the target time period. Then, the average first target attribute information is input into a pre-trained processing quantity prediction model corresponding to the first target attribute, so that the predicted processing quantity of the target warehouse for unprocessed orders in the target time period is obtained, and the prediction of the quantity of the orders which can be processed by the target warehouse in the target time period is realized.

With further reference to fig. 4, a flow 400 of yet another embodiment of a method for generating order information is illustrated. The process 400 for generating order information includes the following steps:

step 401, an unprocessed order set of a target warehouse within a target time period is obtained.

Step 402, generating average first target attribute information for the set of unprocessed orders based on the attribute information for the first target attribute for each unprocessed order in the set of unprocessed orders.

Step 403, inputting the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute, so as to obtain a predicted processing quantity of the target warehouse for unprocessed orders in the target time period.

The specific implementation process of steps 401, 402, and 403 may refer to the related descriptions of steps 201, 202, and 203 in the corresponding embodiment of fig. 2, and will not be described herein again.

Step 404, selecting a predicted number of unprocessed orders from the unprocessed order set, and generating a set of pending orders.

In this embodiment, the executing agent may randomly select the unprocessed orders with the predicted processing quantity obtained in step 403 from the unprocessed order set as the to-be-processed orders, so as to obtain the to-be-processed order set, or may designate and select the unprocessed orders with the predicted processing quantity as the to-be-processed orders by a technician or a manager, so as to generate the to-be-processed order set.

Step 405, for each to-be-processed order in the to-be-processed order set, inputting the attribute information of the second target attribute of the to-be-processed order to a pre-trained processing time prediction model corresponding to the second target attribute, so as to obtain the predicted processing time of the target warehouse for the to-be-processed order.

In this embodiment, for each to-be-processed order in the to-be-processed order set obtained in step 404, the executing entity may input attribute information of a second target attribute of the to-be-processed order to a pre-trained processing time prediction model corresponding to the second target attribute, so as to obtain the predicted time of the target warehouse for the to-be-processed order. The processing time prediction model is used for representing the corresponding relation between the attribute information of the second target attribute of the order to be processed and the predicted processing time of the order to be processed.

The second target attribute may be any information directly or indirectly related to the pending order. For example, the second target attributes of the pending order may include attributes directly related to the pending order such as order number, order time, name of the item contained in the order, number of items contained in the order, number of types of items contained in the order, number of packages in the order, weight and volume of the order, total amount of the order, and the like. The second target attributes of the order to be processed may also include, for example, a name and a number of a warehouse assigned to the order, a size of the warehouse, a temporary employee identifier of the warehouse (which may identify whether the warehouse has a temporary employee, for example, a value of 1 indicates that the warehouse has a temporary employee, and a value of 0 indicates that the warehouse does not have a temporary employee), a supplier of the order, a representative code number of the order processing staff, and the like, which are indirectly related to the order, and may also be any combination of the above second target attributes. The attribute information of the second target attribute of the to-be-processed order may refer to a quantized specific numerical value of the second target attribute of the to-be-processed order, or may refer to a specific identifier or number corresponding to the second target attribute of the to-be-processed order. The second target attribute may be some attributes of the to-be-processed order pre-specified by the actual operator or technician according to historical experience, or some attributes of the to-be-processed order determined according to specific application requirements.

It should be noted that the second target attribute is only named for convenience of description, and those skilled in the art should understand that the second attribute does not constitute a specific limitation to the target attribute. The second target attribute may be the same as or different from the first target attribute in step 202.

In practice, the execution body may store therein a plurality of pre-trained processing time prediction models. Wherein each processing time prediction model corresponds to a second target attribute of the pending orders for the target warehouse. For example, multiple processing time prediction models corresponding to different applications may be trained in advance according to different application requirements. For example, if it is desired to know the relationship between the number of items and the type of items included in the order in a warehouse and the time for the warehouse to process the pending order, a processing time prediction model representing the correspondence between the number of items and the type of items included in the pending order in the target warehouse and the time for the target warehouse to process the pending order may be trained. For example, if it is desired to know the relationship between the number of items included in the pending order of a warehouse and whether the warehouse is processed by temporary staff, and the time of the pending order processing by the warehouse, a processing time prediction model representing the relationship between the number of items included in the pending order of the warehouse and the time of the pending order processing by the warehouse may be trained.

As an example, the processing time prediction model may be a correspondence table in which attribute information of the second target attribute of the to-be-processed order of the target warehouse and the time at which the target warehouse processes the to-be-processed order are stored, which is generated by a technician based on statistics of attribute information of the second target attribute of a large number of to-be-processed orders of the target warehouse and the time at which the target warehouse processes each of the to-be-processed orders. Then, the executing agent may first find, based on the attribute information of the second target attribute of the to-be-processed order in the target warehouse, a time for processing the to-be-processed order corresponding to the attribute information of the second target attribute information from the correspondence table. The processing time prediction model may also be a calculation formula of attribute information for characterizing a second object attribute of the to-be-processed order of the target warehouse and the time for the target warehouse to process the to-be-processed order, which is obtained by a technician based on statistics of data related to the to-be-processed orders of a large number of target warehouses, so that the execution main body may determine the time for the target warehouse to process the to-be-processed order based on the calculation formula.

As an example, the processing time prediction model may be obtained by training: first, attribute information of a second object attribute of a large number of orders processed by the object warehouse is acquired, and a time at which the object warehouse processes each order. Then, data filtering may be performed on the obtained attribute information of the second target attribute of the processed order, for example, some abnormal values existing therein, such as null data or data logically having an error (for example, the number of the types of the items related to a certain order is too large, etc.), and then a training sample may be composed based on the attribute information of the second target attribute of the filtered processed order and the time of processing the order corresponding thereto, respectively.

The training samples may then be divided into a training set, a test set, and a validation set. The division ratio of the training set, the test set and the verification set can be 6:2:2, and the specific division ratio can also be determined by a technician. Then, some existing regression models (progressive gradient decision trees) or a combination of existing multiple regression models can be selected as the initialization processing time prediction model. Then, attribute information of a second target attribute of the processed orders in the training set is used as input, and a plurality of initialization processing time prediction models are trained on the basis of the output of the models and a preset loss function. When the value of the loss function is smaller than a certain threshold value, the training can be stopped, a plurality of processing time prediction models trained by the training set are obtained, then attribute information of second target attributes of processed orders in the verification set is respectively used as input of the plurality of processing time prediction models trained by the training set, the difference between the output of the models and the time of corresponding processed orders in the verification set is counted, then the accuracy of the plurality of processing time prediction models trained by the training set is determined based on the difference, and one processing time prediction model with the highest accuracy can be selected as the trained processing time prediction model. Then, the trained processing time prediction model can be tested by using the test set, and the performance of the trained processing time prediction model is measured according to the test result.

In some optional implementations of the present embodiment, the processing time prediction model may be obtained by training: first, a plurality of training samples may be obtained, each training sample including attribute information of a second object attribute of an order processed by the object warehouse and a time at which the order was processed by the object warehouse. Then, an initialized processing time prediction model is acquired, and the initialized processing time prediction model is trained based on the output of the model and a preset loss function with the attribute information of the second target attribute of the processed order in the acquired training sample as input, thereby obtaining the processing time prediction model.

The initialization processing time prediction model may be an untrained Deep learning model (DNN) or an untrained Deep learning model. Each layer of the initialized processing time prediction model can be provided with initial parameters, and the parameters can be continuously adjusted in the training process. The initialization time prediction model may be various types of untrained or untrained artificial neural networks or a model obtained by combining various types of untrained or untrained artificial neural networks, for example, the initialization time prediction model may be an untrained convolutional neural network, an untrained cyclic neural network, or a model obtained by combining an untrained convolutional neural network, an untrained cyclic neural network, and an untrained fully-connected layer.

The value of the loss function may be used to represent a difference between the predicted processing time output by the model and the time for processing the order corresponding to the input attribute information of the second target attribute of the processed order. The smaller the loss function, the smaller the difference. In the training process, an absolute value of a difference between the predicted processing time output by the model and the time of processing the order corresponding to the attribute information of the second target attribute of the input processed order may be used as the loss function. Then, when it is determined that the values of the loss function of two or more times before and after the determination are both smaller than a certain threshold, the training is completed. And taking the initialized processing time prediction model after the training as a processing time prediction model.

Step 406, determining a total predicted processing time for the set of orders to be processed based on the predicted processing time for each order to be processed in the set of orders to be processed.

In this embodiment, the executing agent may use the sum of the predicted processing time of each order as the predicted total processing time of the set of orders to be processed based on the predicted processing time of each order in the set of orders to be processed obtained in step 405. In practice, the resources of the target warehouse (e.g., the number of employees, the working time of the employees, whether the warehouse receives new orders again, etc.) may be configured in advance based on the obtained predicted total processing time and in combination with the actual demand.

With continued reference to fig. 5, fig. 5 is a schematic diagram of an application scenario of the method for generating order information according to the present embodiment. In the application scenario of fig. 5, in conjunction with application scenario 3 described above, it is assumed that the predicted process number output by process number prediction model 304 is 2. Then, first, 2 unprocessed orders a and B may be randomly selected from the unprocessed order set 301 to generate a pending order set 501. Here, it is assumed that the second target attributes of the to-be-processed orders a and B are respectively the same as the first target attributes thereof. A pre-trained processing time prediction model 503 corresponding to the second target attribute of the order to be processed is then obtained. Then, the attribute information 502 of the second target attribute of the to-be-processed order a is input into the processing time prediction model 503, so as to obtain the predicted processing time T1 of the target warehouse for the to-be-processed order a. Similarly, the attribute information 502 of the second target attribute of the to-be-processed order B is input to the processing time prediction model 503, so as to obtain the predicted processing time T2 of the target warehouse for the to-be-processed order B. Then, the sum of the two prediction processing times T1 and T2 obtained above may be taken as the prediction processing total time T3.

As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, after the prediction of the number of the orders that can be processed by the target warehouse within the target time period is realized, the flow of the information pushing method in this embodiment may further select two unprocessed orders for prediction processing to generate a to-be-processed order set, and then input the attribute information of the second target attribute of each to-be-processed order into the pre-trained processing time prediction model corresponding to the second target attribute information, so as to obtain the predicted processing time of the target warehouse for each to-be-processed order set, and further obtain the predicted processing total time of the target warehouse for the to-be-processed order set.

With further reference to fig. 6, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for generating order information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 6, the apparatus 600 for generating order information of the present embodiment includes an acquisition unit 601, an average first target attribute information generation unit 602, and a prediction process amount generation unit 603. Wherein the obtaining unit 601 is configured to obtain a set of unprocessed orders of the target warehouse within the target time period; the average first target attribute information generating unit 602 is configured to generate average first target attribute information of the unprocessed order set based on attribute information of the first target attribute of each unprocessed order in the unprocessed order set; the predicted processing quantity generation unit 603 is configured to input the average first target attribute information to a pre-trained processing quantity prediction model corresponding to the first target attribute, to obtain a predicted processing quantity of the unprocessed order in the target time period by the target warehouse, where the processing quantity prediction model is used to represent a corresponding relationship between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed order.

In this embodiment, specific processes of the obtaining unit 601, the average first target attribute information generating unit 602, and the predicted process quantity generating unit 603 in the apparatus 600 for generating order information and technical effects brought by the specific processes may respectively refer to the related descriptions of step 201, step 202, and step 203 in the corresponding embodiment of fig. 2, and are not repeated herein.

In some optional implementations of this embodiment, the process quantity prediction model is obtained by training through the following steps: obtaining a plurality of training samples, wherein the training samples comprise average first target attribute information of unprocessed order sets of a target warehouse in a target history time period and the number of unprocessed orders processed by the target warehouse in the target history time period; and training to obtain a processing quantity prediction model by using a machine learning method and taking the average first target attribute information of the unprocessed order set of the target warehouse in each training sample in the target history time period as input and the quantity of the unprocessed orders processed by the target warehouse in the target history time period as output.

In some optional implementations of this embodiment, the first target attribute of the unprocessed order includes at least one of: the average number of included items, the average number of included item types, the average number of parcels, the average weight, the average volume, the number of official employees of the target warehouse within the target time period, the number of temporary employees of the target warehouse within the target time period, the total working time of the official employees, and the total working time of the temporary employees.

In some optional implementations of this embodiment, the apparatus further includes: a to-be-processed order set generating unit (not shown in the figure) configured to select a predicted number of unprocessed orders from the unprocessed order set, and generate a to-be-processed order set; a predicted processing time generating unit (not shown in the figure) configured to, for each to-be-processed order in the to-be-processed order set, input attribute information of a second target attribute of the to-be-processed order into a pre-trained processing time prediction model corresponding to the second target attribute, so as to obtain a predicted processing time of the to-be-processed order by the target warehouse, where the processing time prediction model is used to represent a corresponding relationship between the attribute information of the second target attribute of the to-be-processed order and the predicted processing time of the to-be-processed order; a predicted total processing time generation unit (not shown in the figure) configured to determine a predicted total processing time for the set of orders to be processed based on the predicted processing time for each order to be processed in the set of orders to be processed.

In some optional implementations of this embodiment, the processing time prediction model is trained by: acquiring a plurality of training samples, wherein the training samples comprise attribute information of a second target attribute of the order processed by the target warehouse and processing time of the processed order by the target warehouse; and by utilizing a machine learning method, taking the attribute information of the second target attribute of the order processed by the target warehouse in each training sample as input, taking the processing time of the processed order by the target warehouse as output, and training to obtain a processing time prediction model.

In some optional implementations of the embodiment, the second target attribute of the pending order includes at least one of: temporary employee tags containing item number, containing item type number, parcel number, weight, volume, and target warehouse.

The apparatus provided in the foregoing embodiment of the present application, first obtains, by the obtaining unit 601, an unprocessed order set of the target warehouse in the target time period. Then, the average first target attribute information of the unprocessed order set is generated by the average first target attribute information generating unit 602 based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set of the target warehouse within the target time period. Then, the predicted processing quantity generation unit 603 inputs the average first target attribute information to the pre-trained processing quantity prediction model corresponding to the first target attribute, so as to obtain the predicted processing quantity of the target warehouse for unprocessed orders in the target time period, thereby realizing the prediction of the quantity of orders that can be processed by the target warehouse in the target time period.

Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use in implementing a terminal device or server of an embodiment of the present application. The terminal device or the server shown in fig. 7 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. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program, when executed by a Central Processing Unit (CPU)701, performs the above-described functions defined in the method of the present application.

It should be noted that the computer readable medium of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer 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 of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer 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. In this application, however, a computer readable signal medium may include a propagated data signal with computer 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 computer readable signal medium may also be any computer readable medium that is not a computer 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 computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, an average first target attribute information generation unit, and a prediction processing amount generation unit. Where the names of these units do not in some cases constitute a limitation on the units themselves, for example, an acquisition unit may also be described as a "unit that acquires a set of unprocessed orders for a target warehouse over a target time period".

As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: acquiring an unprocessed order set of a target warehouse in a target time period; generating average first target attribute information of the unprocessed order set based on the attribute information of the first target attribute of each unprocessed order in the unprocessed order set; and inputting the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute to obtain the predicted processing quantity of the unprocessed orders in the target time period by the target warehouse, wherein the processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed orders.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims

1. A method for generating order information, comprising:

acquiring an unprocessed order set of a target warehouse in a target time period;

generating average first target attribute information for the set of unprocessed orders based on attribute information for the first target attribute for each unprocessed order in the set of unprocessed orders;

and inputting the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute to obtain the predicted processing quantity of the target warehouse for unprocessed orders in the target time period, wherein the processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity for the unprocessed orders.

2. The method of claim 1, wherein the process quantity prediction model is trained by:

obtaining a plurality of training samples, a training sample comprising average first target attribute information for a set of unprocessed orders by the target warehouse over a target history time period, and a number of unprocessed orders processed by the target warehouse over the target history time period;

and training to obtain the processed quantity prediction model by using a machine learning method and taking average first target attribute information of the unprocessed order sets of the target warehouse in each training sample in a target history time period as input, and taking the quantity of unprocessed orders processed by the target warehouse in the target history time period as output.

3. The method of claim 1, wherein the first target attribute of the unprocessed order comprises at least one of:

an average included item number, an average included item type number, an average parcel number, an average weight, an average volume, a number of official employees of the target warehouse within the target time period, a number of temporary employees of the target warehouse within the target time period, a total working time of the official employees, and a total working time of the temporary employees.

4. The method according to one of claims 1-3, wherein the method further comprises:

selecting a prediction processing quantity of unprocessed orders from the unprocessed order set to generate a to-be-processed order set;

for each to-be-processed order in the to-be-processed order set, inputting attribute information of a second target attribute of the to-be-processed order into a pre-trained processing time prediction model corresponding to the second target attribute to obtain predicted processing time of the to-be-processed order by the target warehouse, wherein the processing time prediction model is used for representing a corresponding relation between the attribute information of the second target attribute of the to-be-processed order and the predicted processing time of the to-be-processed order;

determining a predicted total processing time for the set of orders to be processed based on the predicted processing time for each order to be processed in the set of orders to be processed.

5. The method of claim 4, wherein the process time prediction model is trained by:

obtaining a plurality of training samples, wherein the training samples comprise attribute information of the second target attribute of the order processed by the target warehouse and processing time of the processed order by the target warehouse;

and training to obtain the processing time prediction model by using a machine learning method and taking the attribute information of the second target attribute of the order processed by the target warehouse in each training sample as input and the processing time of the processed order by the target warehouse as output.

6. The method of claim 4, wherein the second target attribute of the pending order comprises at least one of:

including the number of items, including the number of item types, the number of packages, the weight, the volume, and the temporary employee badge for the target warehouse.

7. An apparatus for generating order information, comprising:

an acquisition unit configured to acquire a set of unprocessed orders of a target warehouse within a target time period;

an average first target attribute information generating unit configured to generate average first target attribute information of the unprocessed order set based on attribute information of a first target attribute of each unprocessed order in the unprocessed order set;

and the predicted processing quantity generation unit is configured to input the average first target attribute information into a pre-trained processing quantity prediction model corresponding to the first target attribute to obtain a predicted processing quantity of the unprocessed orders in the target time period by the target warehouse, wherein the processing quantity prediction model is used for representing the corresponding relation between the average first target attribute information of the unprocessed order set and the predicted processing quantity of the unprocessed orders.

8. The apparatus of claim 7, wherein the process quantity prediction model is trained by:

9. The apparatus of claim 7, wherein the first target attribute of the unprocessed order comprises at least one of:

10. The apparatus according to one of claims 7-9, wherein the apparatus further comprises:

the to-be-processed order set generating unit is configured to select unprocessed orders with predicted processing quantity from the unprocessed order set and generate a to-be-processed order set;

the predicted processing time generation unit is configured to, for each to-be-processed order in the to-be-processed order set, input attribute information of a second target attribute of the to-be-processed order into a pre-trained processing time prediction model corresponding to the second target attribute, so as to obtain predicted processing time of the to-be-processed order by the target warehouse, wherein the processing time prediction model is used for representing a corresponding relation between the attribute information of the second target attribute of the to-be-processed order and the predicted processing time of the to-be-processed order;

a predicted total processing time generation unit configured to determine a predicted total processing time for the set of orders to be processed based on a predicted processing time for each order to be processed in the set of orders to be processed.

11. The apparatus of claim 10, wherein the process time prediction model is trained by:

12. The apparatus of claim 10, wherein the second target attribute of the pending order comprises at least one of:

13. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.

14. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-6.