CN111144822A

CN111144822A - Warehouse-out time length determining method and device, computer equipment and storage medium

Info

Publication number: CN111144822A
Application number: CN201911389858.0A
Authority: CN
Inventors: 雷新会; 师粼波
Original assignee: Beijing Missfresh Ecommerce Co Ltd
Current assignee: Beijing Missfresh Ecommerce Co Ltd
Priority date: 2019-12-30
Filing date: 2019-12-30
Publication date: 2020-05-12

Abstract

The embodiment of the application discloses a method and a device for determining ex-warehouse time, computer equipment and a storage medium, and belongs to the technical field of internet. The method comprises the following steps: the method comprises the steps of obtaining order information of a target order, obtaining the number of staff of warehouse-out staff corresponding to warehouse identification, processing the order information and the number of staff based on a warehouse-out duration prediction model, and determining warehouse-out duration of a target article. The method can accurately determine the ex-warehouse time of the target object based on the ex-warehouse time prediction model according to the order information of the target order and the number of the personnel of the ex-warehouse personnel of the warehouse where the target object is located, and improves the accuracy of the ex-warehouse time.

Description

Warehouse-out time length determining method and device, computer equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a method and a device for determining ex-warehouse duration, computer equipment and a storage medium.

Background

With the rapid development of electronic commerce and the popularization of online shopping, more and more users buy articles on the internet, and the requirement of the users on the distribution speed of the articles is higher and higher. To meet the user's needs, the item provider needs to display the delivery time of the item for the user and deliver the item to the user before the delivery time.

The process of delivering the goods to the user by the goods provider comprises two stages of goods delivery and goods delivery, wherein the delivery time is determined by the delivery time length and the delivery time length of the goods, and the delivery time length of the goods is generally determined in the related art but cannot be determined. Therefore, how to determine the delivery time of the articles becomes an urgent problem to be solved.

Disclosure of Invention

The embodiment of the application provides a method and a device for determining the warehouse-out time, computer equipment and a storage medium, which can determine the warehouse-out time of an article. The technical scheme is as follows:

in one aspect, a method for determining a delivery duration is provided, where the method includes:

the method comprises the steps of obtaining order information of a target order, wherein the order information comprises order attribute information and order article information, the order attribute information comprises order generation time and a warehouse identifier, the order article information comprises a target article identifier, and a warehouse corresponding to the warehouse identifier is used for storing a target article corresponding to the target article identifier;

acquiring the number of personnel of the warehouse-out personnel corresponding to the warehouse identification;

and processing the order information and the personnel number based on a warehouse-out duration prediction model, and determining the warehouse-out duration of the target object.

Optionally, the obtaining the number of people who leave the warehouse corresponding to the warehouse identifier includes:

and acquiring the equipment quantity of the warehouse-out equipment corresponding to the warehouse identification, and determining the equipment quantity as the personnel quantity, wherein the warehouse-out equipment is used for recording warehouse-out articles in the warehouse.

Optionally, the obtaining of the number of devices of the warehouse-out device corresponding to the warehouse identifier includes:

acquiring an operation record of each ex-warehouse device corresponding to the warehouse identification within a preset time before the order generation time;

and acquiring the equipment number of the warehouse-out equipment in the operation records, wherein the equipment number comprises the warehouse-out records of the articles.

Optionally, the method further comprises:

acquiring the order quantity of a reference order, wherein the order attribute information of the reference order comprises the warehouse identification, and the state of the reference order is the state that the article is not taken out of the warehouse;

the step of processing the order information and the number of the personnel based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item comprises the following steps:

and processing the order information, the personnel number and the order number based on the ex-warehouse duration prediction model, and determining the ex-warehouse duration of the target object.

Optionally, the processing the order information, the number of people, and the number of orders based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item includes:

acquiring the number of delivery cycles of the target item according to the number of the personnel and the number of the orders, wherein the number of the delivery cycles is a minimum positive integer not less than the ratio of the number of the orders to the number of the personnel;

and processing the order information and the ex-warehouse cycle number based on the ex-warehouse duration prediction model, and determining the ex-warehouse duration of the target item.

Optionally, before the processing the order information and the number of people based on the ex-warehouse duration prediction model and determining the ex-warehouse duration of the target item, the method further includes:

obtaining sample order information of a sample order, wherein the sample order information comprises sample order attribute information and sample order item information, the sample order attribute information comprises sample order generation time, sample order ex-warehouse time and sample warehouse identification, the sample order item information comprises sample item identification, and a warehouse corresponding to the sample warehouse identification is used for storing sample items corresponding to the sample item identification;

acquiring the number of sample personnel of the ex-warehouse personnel corresponding to the sample warehouse identification according to the sample order generation time;

and training the ex-warehouse time length prediction model according to the sample order information and the number of the sample personnel.

Optionally, the obtaining, according to the sample order generation time, the number of sample staff of the warehouse-out staff corresponding to the sample warehouse identifier includes:

and acquiring the number of sample devices of the ex-warehouse device corresponding to the sample warehouse identification according to the sample order generation time, and determining the number of the sample devices as the number of the sample personnel.

Optionally, the obtaining, according to the sample order generation time, the number of sample devices of the ex-warehouse device corresponding to the sample warehouse identifier includes:

obtaining a sample operation record of each ex-warehouse device corresponding to the sample warehouse identification within a preset time before the sample order generation time;

and acquiring the number of sample devices of the warehouse-out equipment in the sample operation records, wherein the sample operation records comprise the item warehouse-out records.

Optionally, the method further comprises:

obtaining the sample order quantity of a sample reference order, wherein the sample order attribute information of the sample reference order comprises the sample warehouse identification, and the state of the sample reference order at the sample order generation time is the state that the article is not taken out of the warehouse;

the training of the ex-warehouse duration prediction model according to the sample order information and the number of the sample personnel comprises the following steps:

and training the ex-warehouse time length prediction model according to the sample order information, the number of the sample personnel and the number of the sample orders.

Optionally, the training the ex-warehouse duration prediction model according to the sample order information, the sample number of people, and the sample order number includes:

determining the number of sample ex-warehouse cycles of the sample article according to the number of the sample personnel and the number of the sample orders, wherein the number of the sample ex-warehouse cycles is a minimum positive integer not less than the ratio of the number of the sample orders to the number of the sample personnel;

and training the ex-warehouse duration prediction model according to the sample order information and the sample ex-warehouse cycle number.

Optionally, the order attribute information further includes a warehouse address corresponding to the warehouse identifier and a receiving address of the target item; the method further comprises the following steps of processing the order information and the number of the personnel based on a warehouse-out duration prediction model, and determining the warehouse-out duration of the target item:

processing the order information based on the distribution duration prediction model to determine the distribution duration of the target order;

and determining the processing time length of the target order according to the ex-warehouse time length and the distribution time length.

Optionally, the determining the processing duration of the target order according to the delivery duration and the delivery duration includes:

determining the sum of the ex-warehouse duration and the delivery duration as the processing duration of the target order; or,

determining the sum of the ex-warehouse time length, the delivery time length and the historical delay time length as the processing time length of the target order, wherein the historical delay time length is equal to the average value of the time differences between the actual processing time lengths and the predicted processing time lengths of the plurality of historical order forms; or,

determining the sum of the ex-warehouse time length, the distribution time length and the order distribution time length as the processing time length of the target order, wherein the order distribution time length is the time length for distributing the target order to the warehouse after the target order is generated; or,

and determining the sum of the warehouse-out time length, the distribution time length and the goods taking time length as the processing time length of the target order, wherein the goods taking time length is the time length for the distribution personnel to take goods from the warehouse.

Optionally, before determining the sum of the delivery duration, the delivery duration and the historical delay duration as the processing duration of the target order, the method further includes:

acquiring the plurality of historical orders, and determining the time difference between the actual processing time length and the predicted processing time length of each historical order;

dividing the determined multiple time differences into at least two groups, wherein the time differences in the same group belong to the same time difference range;

averaging the time difference in each group to obtain the average value of the time difference of each group;

and averaging the average value of the time difference of each group to obtain the average value of the time differences of the plurality of historical orders as the historical delay time length.

Optionally, after the processing duration of the target order is determined according to the delivery duration and the delivery duration, the method further includes:

and determining delivery time for delivering the target item to the receiving address according to the order generation time and the processing time length of the target order.

In another aspect, an ex-warehouse duration determining apparatus is provided, the apparatus including:

the order information acquisition module is used for acquiring order information of a target order, wherein the order information comprises order attribute information and order article information, the order attribute information comprises order generation time and a warehouse identifier, the order article information comprises a target article identifier, and a warehouse corresponding to the warehouse identifier is used for storing a target article corresponding to the target article identifier;

the personnel number acquisition module is used for acquiring the personnel number of the warehouse-out personnel corresponding to the warehouse identification;

and the ex-warehouse duration determining module is used for processing the order information and the personnel number based on an ex-warehouse duration prediction model and determining the ex-warehouse duration of the target object.

Optionally, the staff number obtaining module is further configured to obtain an equipment number of the warehouse exit equipment corresponding to the warehouse identifier, determine the equipment number as the staff number, and the warehouse exit equipment is configured to record the warehouse exit items in the warehouse.

Optionally, the staff number obtaining module includes:

the record acquisition unit is used for acquiring the operation record of each warehouse-out device corresponding to the warehouse identifier within the preset time before the order generation time;

and the equipment quantity obtaining unit is used for obtaining the equipment quantity of the warehouse-out equipment including the article warehouse-out record in the operation record.

Optionally, the apparatus further comprises:

the order quantity acquisition module is used for acquiring the order quantity of a reference order, the order attribute information of the reference order comprises the warehouse identification, and the state of the reference order is the state that the article is not delivered from the warehouse;

the ex-warehouse duration determining module is further configured to process the order information, the number of people, and the number of orders based on the ex-warehouse duration prediction model, and determine the ex-warehouse duration of the target item.

Optionally, the delivery duration determining module includes:

a cycle number obtaining unit, configured to obtain a number of ex-warehouse cycles of the target item according to the number of people and the number of orders, where the number of ex-warehouse cycles is a smallest positive integer not smaller than a ratio between the number of orders and the number of people;

and the ex-warehouse duration determining unit is used for processing the order information and the ex-warehouse cycle number based on the ex-warehouse duration prediction model and determining the ex-warehouse duration of the target object.

Optionally, the apparatus further comprises:

the system comprises a sample order information acquisition module, a sample order information acquisition module and a sample storage module, wherein the sample order information acquisition module is used for acquiring sample order information of a sample order, the sample order information comprises sample order attribute information and sample order article information, the sample order attribute information comprises sample order generation time, sample order warehouse-out time and sample warehouse identification, the sample order article information comprises sample article identification, and a warehouse corresponding to the sample warehouse identification is used for storing a sample article corresponding to the sample article identification;

the sample personnel number acquisition module is used for acquiring the sample personnel number of the ex-warehouse personnel corresponding to the sample warehouse identification;

and the model training module is used for training the ex-warehouse duration prediction model according to the sample order information and the number of the sample personnel.

Optionally, the sample staff number obtaining module is further configured to obtain, according to the sample order generation time, the number of sample devices of the ex-warehouse device corresponding to the sample warehouse identifier, and determine the number of sample devices as the sample staff number.

Optionally, the sample staff number obtaining module includes:

the sample record acquisition unit is used for acquiring a sample operation record of each ex-warehouse device corresponding to the sample warehouse identification within a preset time before the sample order generation time;

and the sample equipment quantity obtaining unit is used for obtaining the sample equipment quantity of the ex-warehouse equipment in the sample operation records, wherein the sample operation records comprise the article ex-warehouse records.

Optionally, the apparatus further comprises:

the sample order quantity obtaining module is used for obtaining the sample order quantity of a sample reference order, the sample order attribute information of the sample reference order comprises the sample warehouse identification, and the state of the sample reference order at the sample order generating time is the state that the article is not taken out of the warehouse;

and the model training module is also used for training the ex-warehouse duration prediction model according to the sample order information, the number of sample personnel and the number of sample orders.

Optionally, the model training module includes:

a sample cycle number obtaining unit, configured to determine, according to the number of sample persons and the number of sample orders, a number of sample ex-warehouse cycles of the sample item, where the number of sample ex-warehouse cycles is a smallest positive integer no less than a ratio of the number of sample orders to the number of sample persons;

and the model training unit is used for training the ex-warehouse duration prediction model according to the sample order information and the sample ex-warehouse periodicity.

Optionally, the order attribute information further includes a warehouse address corresponding to the warehouse identifier and a receiving address of the target item; the device further comprises:

a distribution duration determining module, configured to process the order information based on the distribution duration prediction model, and determine a distribution duration of the target order;

and the processing time length determining module is used for determining the processing time length of the target order according to the ex-warehouse time length and the distribution time length.

Optionally, the processing duration determining module includes:

the first determining unit is used for determining the sum of the ex-warehouse duration and the delivery duration as the processing duration of the target order; or,

a second determining unit, configured to determine a sum of the ex-warehouse duration, the delivery duration, and a historical delay duration as a processing duration of the target order, where the historical delay duration is equal to an average of time differences between actual processing durations and predicted processing durations of a plurality of historical orders; or,

a third determining unit, configured to determine a sum of the warehouse-out duration, the distribution duration, and an order allocation duration as a processing duration of the target order, where the order allocation duration is a duration for allocating the target order to the warehouse after the target order is generated; or,

and the fourth determining unit is used for determining the sum of the warehouse-out time length, the distribution time length and the goods taking time length as the processing time length of the target order, and the goods taking time length is the time length for the distribution personnel to take goods from the warehouse.

Optionally, the apparatus further comprises:

the time difference determining module is used for acquiring the plurality of historical orders and determining the time difference between the actual processing time length and the predicted processing time length of each historical order;

the grouping determination module is used for dividing the determined multiple time differences into at least two groups, wherein the time differences in the same group belong to the same time difference range;

the delay time length determining module is used for averaging the time difference in each group to obtain the average value of the time difference of each group;

the delay time length determining module is further configured to average the average value of the time differences of each group to obtain an average value of the time differences of the plurality of historical orders, and the average value is used as the historical delay time length.

Optionally, the apparatus further comprises:

and the delivery time determining module is used for determining the delivery time for delivering the target object to the receiving address according to the order generation time and the processing time length of the target order.

In another aspect, a computer device is provided, which includes a processor and a memory, where at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the operations as performed in the ex-warehouse duration determination method.

In another aspect, a computer-readable storage medium is provided, in which at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the operations as performed in the ex-warehouse duration determination method.

The method, the device, the computer equipment and the storage medium provided by the embodiment of the application are used for obtaining the order information of the target order, obtaining the number of the personnel of the warehouse-out personnel corresponding to the warehouse identification, processing the order information and the number of the personnel based on the warehouse-out duration prediction model, and determining the warehouse-out duration of the target object. The embodiment of the application provides a method for predicting the warehouse-out duration, which can accurately determine the warehouse-out duration of a target item based on a warehouse-out duration prediction model according to order information of the target order and the number of staff of warehouse-out staff of a warehouse where the target item is located, and improves the accuracy of the warehouse-out duration.

In addition, the method provided by the embodiment of the application obtains sample order information of the sample orders, obtains the number of the sample devices of the ex-warehouse device corresponding to the sample warehouse identification according to the sample order generation time, obtains the number of the sample orders of the sample reference orders, and trains the ex-warehouse duration prediction model according to the sample order information, the number of the sample devices and the number of the sample orders. The embodiment of the application provides a model training method, which can train a ex-warehouse time prediction model according to sample order information of a sample order and the number of sample equipment of ex-warehouse equipment of a warehouse where sample articles are located.

The method provided by the embodiment of the application comprises the steps of obtaining order information of a target order, obtaining the equipment number of warehouse-out equipment corresponding to a warehouse identifier, obtaining the order number of a reference order, processing the order information, the equipment number and the order number based on a warehouse-out time prediction model, determining warehouse-out time of the target object, processing the order information based on a distribution time prediction model, determining distribution time of the target order, determining processing time of the target order according to the warehouse-out time and the distribution time, and determining delivery time for distributing the target object to a receiving address according to order generation time and the processing time of the target order. The embodiment of the application provides a method for predicting the warehouse-out duration, which can accurately determine the warehouse-out duration of a target object based on a warehouse-out duration prediction model according to order information of the target order and the number of devices of warehouse-out equipment of a warehouse where the target object is located, and improves the accuracy of the warehouse-out duration. And the delivery time length of the target object is accurately determined based on the delivery time length prediction model, so that the delivery time of the target object can be determined, and the accuracy of the determined delivery time is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a method for determining a delivery duration according to an embodiment of the present application.

Fig. 2 is a flowchart of a ex-warehouse duration prediction model training method according to an embodiment of the present application.

Fig. 3 is a flowchart of a method for determining a delivery duration according to an embodiment of the present application.

Fig. 4 is a schematic diagram of a processing duration provided in an embodiment of the present application.

Fig. 5 is a schematic diagram of model training and use provided in an embodiment of the present application.

Fig. 6 is a schematic structural diagram of a delivery duration determining apparatus according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of a delivery duration determining apparatus according to an embodiment of the present application.

Fig. 8 is a schematic structural diagram of a terminal according to an embodiment of the present application.

Fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present application more clear, the embodiments of the present application will be further described in detail with reference to the accompanying drawings.

Fig. 1 is a flowchart of a method for determining a delivery duration according to an embodiment of the present application. Applied to a computer device, see fig. 1, the method comprises:

in step 101, order information of the target order is obtained, where the order information includes order attribute information and order item information, the order attribute information includes order generation time and a warehouse identifier, the order item information includes a target item identifier, and a warehouse corresponding to the warehouse identifier is used for storing a target item corresponding to the target item identifier.

In step 102, the number of people corresponding to the warehouse identification and the warehouse exit personnel is obtained.

In step 103, the order information and the number of the persons are processed based on the ex-warehouse duration prediction model, and the ex-warehouse duration of the target item is determined.

The method provided by the embodiment of the application obtains the order information of the target order, obtains the number of the personnel of the warehouse-out personnel corresponding to the warehouse identification, processes the order information and the number of the personnel based on the warehouse-out duration prediction model, and determines the warehouse-out duration of the target object. The embodiment of the application provides a method for predicting the warehouse-out duration, which can accurately determine the warehouse-out duration of a target item based on a warehouse-out duration prediction model according to order information of the target order and the number of staff of warehouse-out staff of a warehouse where the target item is located, and improves the accuracy of the warehouse-out duration.

In one possible implementation manner, obtaining the number of people of the warehouse exit personnel corresponding to the warehouse identifier includes:

and acquiring the equipment number of the warehouse-out equipment corresponding to the warehouse identification, determining the equipment number as the number of personnel, and recording the warehouse-out articles in the warehouse by the warehouse-out equipment.

In one possible implementation manner, obtaining the device number of the warehouse exit device corresponding to the warehouse identifier includes:

In one possible implementation, the method further comprises:

acquiring the order quantity of a reference order, wherein the order attribute information of the reference order comprises a warehouse identifier, and the state of the reference order is the state that the article is not taken out of the warehouse;

processing the order information and the personnel number based on the ex-warehouse time prediction model, and determining the ex-warehouse time of the target object, wherein the method comprises the following steps:

and processing the order information, the personnel number and the order number based on the ex-warehouse time length prediction model, and determining the ex-warehouse time length of the target object.

In one possible implementation manner, the processing the order information, the number of people, and the number of orders based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item includes:

acquiring the number of delivery cycles of the target object according to the number of personnel and the number of orders, wherein the number of delivery cycles is a minimum positive integer not less than the ratio of the number of orders to the number of personnel;

and processing the order information and the ex-warehouse cycle number based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target object.

In one possible implementation manner, before processing the order information and the number of people based on the ex-warehouse duration prediction model and determining the ex-warehouse duration of the target item, the method further includes:

obtaining sample order information of a sample order, wherein the sample order information comprises sample order attribute information and sample order article information, the sample order attribute information comprises sample order generation time, sample order warehouse-out time and sample warehouse identification, the sample order article information comprises sample article identification, and a warehouse corresponding to the sample warehouse identification is used for storing sample articles corresponding to the sample article identification;

and training a ex-warehouse time length prediction model according to the sample order information and the number of sample personnel.

In one possible implementation manner, obtaining the number of sample persons of the ex-warehouse person corresponding to the sample warehouse identifier according to the sample order generation time includes:

and acquiring the number of sample devices of the ex-warehouse device corresponding to the sample warehouse identification according to the sample order generation time, and determining the number of the sample devices as the number of sample personnel.

In one possible implementation manner, obtaining the number of sample devices of the ex-warehouse device corresponding to the sample warehouse identifier according to the sample order generation time includes:

acquiring a sample operation record of each ex-warehouse device corresponding to the sample warehouse identification within a preset time before the sample order generation time;

and acquiring the number of sample devices of the warehouse-out equipment in the sample operation records, wherein the sample operation records comprise the warehouse-out records of the articles.

In one possible implementation, the method further comprises:

acquiring the sample order quantity of a sample reference order, wherein the sample order attribute information of the sample reference order comprises a sample warehouse identifier, and the state of the sample reference order at the sample order generation time is the state that the article is not delivered out of the warehouse;

training a ex-warehouse duration prediction model according to sample order information and the number of sample personnel, comprising the following steps:

and training a ex-warehouse time length prediction model according to the sample order information, the number of sample personnel and the number of sample orders.

In one possible implementation manner, training the ex-warehouse duration prediction model according to the sample order information, the number of sample persons, and the number of sample orders includes:

determining the number of sample ex-warehouse cycles of the sample articles according to the number of sample personnel and the number of sample orders, wherein the number of the sample ex-warehouse cycles is a minimum positive integer not less than the ratio of the number of the sample orders to the number of the sample personnel;

and training a ex-warehouse duration prediction model according to the sample order information and the sample ex-warehouse cycle number.

In one possible implementation manner, the order attribute information further includes a warehouse address corresponding to the warehouse identifier and a receiving address of the target item; processing the order information and the number of the personnel based on the ex-warehouse time prediction model, and after determining the ex-warehouse time of the target object, the method further comprises the following steps:

processing the order information based on a distribution duration prediction model, and determining the distribution duration of the target order;

In one possible implementation manner, determining the processing duration of the target order according to the delivery duration and the delivery duration includes:

determining the sum of the ex-warehouse time length, the distribution time length and the historical delay time length as the processing time length of the target order, wherein the historical delay time length is equal to the average value of the time differences between the actual processing time lengths and the predicted processing time lengths of the plurality of historical order; or,

determining the sum of the warehouse-out time length, the distribution time length and the order distribution time length as the processing time length of the target order, wherein the order distribution time length is the time length for distributing the target order to a warehouse after the target order is generated; or,

In one possible implementation, before determining the sum of the delivery duration, and the historical delay duration as the processing duration of the target order, the method further includes:

acquiring a plurality of historical orders, and determining the time difference between the actual processing time length and the predicted processing time length of each historical order;

and averaging the average value of the time differences of each group to obtain the average value of the time differences of a plurality of historical orders as the historical delay time.

In one possible implementation manner, after determining the processing duration of the target order according to the delivery duration and the delivery duration, the method further includes:

and determining delivery time for delivering the target object to the receiving address according to the order generation time and the processing time length of the target order.

With the vigorous development of the electric commerce industry, a fresh electric commerce platform is emerged in the world. The fresh food e-commerce platform not only can supply full-grade fresh food such as fruits and vegetables, seafood and poultry, milk snacks and the like for users, but also can timely deliver the fresh food purchased by the users to the hands of the users.

At present, give birth to bright electricity merchant platform and adopt leading storehouse mode, leading storehouse is also called little storehouse, and after the user leaves an order, the article that the user purchased can be followed near leading storehouse delivery, and leading storehouse sets up in the place nearer apart from the user, can set up in near community or business district, can deliver and get on the home in the short time after guaranteeing the user leaves an order, guarantees product quality and delivery speed.

In the embodiment of the application, a user purchases goods on the network, when the user places an order, the computer device determines a front bin which is closest to the user according to the receiving address of the user, the front bin is used for delivering the goods placed by the user, and a delivery person takes the goods from the front bin to deliver the goods for the user. The embodiment of the application provides a method for determining the warehouse-out time length, and for any target order, the order information and the warehouse-out personnel number of the target order are processed on the basis of a warehouse-out time length prediction model, and the warehouse-out time length of the target object is determined.

Since the method for determining the ex-warehouse time length provided by the embodiment of the application is realized based on the trained ex-warehouse time length prediction model, the training process of the ex-warehouse time length prediction model is explained through the following embodiments.

Fig. 2 is a flowchart of a ex-warehouse duration prediction model training method provided in an embodiment of the present application, and is applied to a computer device, where the computer device may be a terminal or a server. Referring to fig. 2, the method includes:

201. the computer device obtains sample order information for the sample order.

In the embodiment of the application, the computer device may be a terminal or a server. The terminal can be a mobile phone, a computer, a tablet computer and the like, and the server can be a server, or a server cluster consisting of a plurality of servers, or a cloud computing service center.

In the embodiment of the application, when the computer equipment is a terminal, a user logs in the terminal based on the user identification, the terminal displays purchasable articles for the user, the user selects the articles to place an order, and when the terminal detects that the user clicks an order submitting button, an order is generated for the user and the order is displayed for the user. The terminal can send the generated order to the server, and the server performs subsequent processing on the order.

Or, when the computer device is a server, the server receives an order generation request sent by the terminal, the server generates a corresponding order according to the order generation request, the order is sent to the terminal, and the terminal displays the order to the user.

The order information of the order comprises order attribute information and order article information.

In one possible implementation, the order attribute information includes an order generation time, an order ex-warehouse time, and a warehouse identification.

Wherein the warehouse identifier is a warehouse identifier of a warehouse storing the article, and the warehouse can be a front warehouse or other types of warehouses; the order generation time refers to the time for the computer equipment to generate an order for the user after the user places the order; the order ex-warehouse time refers to the time when the warehouse corresponding to the warehouse identifier takes out the articles in the order. And the computer equipment can determine the warehouse-out time length of the order according to the order generation time and the order warehouse-out time.

Optionally, the order attribute information may further include an order identifier, which may be an order number or other identifier uniquely indicating the order.

In one possible implementation manner, the order item information includes an item identifier, and a warehouse corresponding to the warehouse identifier is used for storing an item corresponding to the item identifier. Wherein the item identifier is used for representing the item purchased by the user.

Optionally, the order item information may also include a total number of items, a number of items per category, a total number of items remaining in a warehouse storing the items, and a SKU (Stock Keeping Unit) number.

In the embodiment of the application, the computer equipment can acquire the historical order information of the stored historical orders to be used as the sample order information of the sample orders, and train the ex-warehouse time length prediction model.

In a possible implementation manner, after the computer device obtains the sample order information of the sample order, the computer device may process the sample order information, and train the ex-warehouse duration prediction model according to the processed sample order information.

In one possible implementation, the computer device may obtain sample order information for a plurality of sample orders and subsequently train according to the sample order information for the plurality of sample orders. The plurality of sample orders may be sample orders corresponding to the same warehouse or sample orders corresponding to different warehouses.

Optionally, when the computer device processes the sample order information, data filtering may be performed on the sample ex-warehouse duration, that is, the sample order corresponding to the sample ex-warehouse duration exceeding the value range in the sample ex-warehouse duration is removed. And, since the ex-warehouse duration of each warehouse may have a large difference, the data filtering may be performed on the sample ex-warehouse duration of each warehouse, respectively.

For example, for a warehouse, the average value μ and the variance δ of the ex-warehouse durations of a plurality of samples corresponding to the warehouse are obtained, the value range of the ex-warehouse duration corresponding to the warehouse is determined to be (μ -2 δ, μ +2 δ) according to the average value μ and the variance δ, the out-warehouse durations of the samples outside the range are removed, and the ex-warehouse duration prediction model is trained by using sample orders corresponding to the remaining sample out-warehouse durations.

In one possible implementation, the computer device may obtain historical orders within a preset time period as sample orders. The preset time period may be 7 days, 10 days, 30 days, or other time periods.

202. And the computer equipment acquires the number of the sample equipment of the ex-warehouse equipment corresponding to the sample warehouse identification according to the sample order generation time.

In the embodiment of the application, the computer equipment obtains the number of the personnel out of the warehouse corresponding to the warehouse identification according to the order generation time, and trains the ex-warehouse time length prediction model according to the number of the personnel. Because the personnel of leaving warehouse need operate through the equipment of leaving warehouse, go out the warehouse to article, therefore, in this application embodiment, confirm the equipment quantity of the equipment of leaving warehouse as personnel's quantity, explain for the example of the equipment quantity of leaving warehouse equipment. In another embodiment, the ex-warehouse duration prediction model can be trained according to actual application scenarios and according to the number of the staff of the access control system records, the data of the manual shift scheduling system and the like.

The warehouse-out equipment is used for recording warehouse-out articles in the warehouse corresponding to the warehouse identification. Each warehouse-out device has a unique corresponding device identifier, and because the device identifier has a mapping relationship with the warehouse identifier, the warehouse to which the warehouse-out device belongs can be determined according to the mapping relationship, and the device identifier can be a device number, a device name or other identifiers. The ex-warehouse device may be a PDA (Personal Digital Assistant) device or other devices.

The ex-warehouse equipment can generate operation records according to the executed operations, and the operation records can comprise article ex-warehouse records. The article delivery record may include information such as article identification and delivery time of the article.

For example, each article has a corresponding barcode, when the ex-warehouse device ex-warehouse the article, the ex-warehouse device scans the barcode of the article to indicate that the article has been ex-warehouse, and the ex-warehouse device correspondingly generates an article ex-warehouse record of the article that has been ex-warehouse.

In addition, the operation record may also include a log-in record and other usage records of the ex-warehouse device.

In a possible implementation manner, when the number of the sample devices is obtained, the computer device obtains a sample operation record of each ex-warehouse device corresponding to the warehouse identifier within a preset time before the sample order generation time, and obtains the number of the sample devices of the ex-warehouse device, where the sample operation record includes the article ex-warehouse record.

The preset time period may be any time period, and the preset time period may be 5 minutes, 10 minutes, 20 minutes, or other time periods.

Alternatively, if an operation record of one ex-warehouse device includes an article ex-warehouse record, the ex-warehouse device can be considered to be used, and the ex-warehouse device can be considered when acquiring the number of sample devices.

For example, if the preset time is 10 minutes, a sample operation record of the ex-warehouse equipment within 10 minutes before the sample order generation time may be obtained, and if the obtained sample operation record includes an article ex-warehouse record, the ex-warehouse equipment is considered to be in use.

In addition, the computer device may store an operation record of each ex-warehouse device, and obtain a sample operation record within a preset time period before the sample generation time from the stored operation records according to the sample order generation time, thereby obtaining the number of the sample devices.

203. The computer device obtains a sample order quantity for the sample reference order.

In the embodiment of the application, the computer device obtains the queuing position of the order, that is, obtains the order with the order state being the non-warehouse-out state of the article before the sample order generation time, and uses the order as the sample reference order. The order status may include a status of not being allocated to a warehouse, a status of not being delivered from a warehouse, a status of being delivered from a warehouse, and the like.

Alternatively, the reference order may include both immediate and reservation order types of orders.

The instant order is an order which needs to be processed immediately when the warehouse receives the order of the user after the user places the order; the reservation order refers to that the user requires the delivery time of the order when placing the order, and the warehouse does not need to immediately process the order when receiving the order of the user and only needs to deliver the order at the delivery time required by the user.

In the embodiment of the application, the number of sample orders of the sample reference orders is also considered when the ex-warehouse duration prediction model is trained, so that the predicted ex-warehouse duration is more accurate.

The sample order attribute information of the sample reference order comprises a sample warehouse identifier, and the sample warehouse identifier is used for determining that the sample reference order and the sample order are orders corresponding to the same warehouse. And the state of the sample reference order at the sample order generation time is the state that the article is not taken out of the warehouse, and the sample reference order needs to be taken out of the warehouse before the sample order is taken out of the warehouse.

Optionally, when the computer device obtains the sample order quantity of the sample reference order, only the sample instant order may be obtained, and the quantity of the sample instant order is taken as the sample order quantity; or obtaining a sample instant order and a sample reservation order, and taking the sum of the number of the sample instant orders and the number of the sample reservation orders as the number of the sample orders.

In one possible implementation, the sample order number of the sample reference orders within a preset time period is obtained, and the preset time period may be 1 hour, 30 minutes, 10 minutes, or other time period.

It should be noted that, in the embodiment of the present application, the step 202 is only executed first and then the step 203 is executed as an example for description, in another embodiment, the step 203 may be executed first and then the step 202 is executed, and the embodiment of the present application does not limit the sequence of executing the steps.

204. And training a ex-warehouse time length prediction model by the computer equipment according to the sample order information, the number of the sample equipment and the number of the sample orders.

And inputting other information except the sample ex-warehouse time and the number of the sample devices in the sample order information into the ex-warehouse time prediction model by the computer device, and training the ex-warehouse time prediction model by taking the sample ex-warehouse time as output. And training the ex-warehouse time length prediction model to learn the capacity of determining the ex-warehouse time length according to the order information, the equipment number and the order number.

In a possible implementation manner, after the sample order information is obtained, the sample order information needs to be processed to obtain a corresponding characteristic value, and a ex-warehouse duration prediction model is trained according to the characteristic value.

Optionally, the computer device may encode information, such as sample order generation time, sample order ex-warehouse time, and sample warehouse identifier, included in the sample order information to obtain a corresponding feature value, and then train an ex-warehouse duration prediction model according to the feature value. The encoding method may be one-hot encoding or other encoding methods.

In one possible implementation manner, the computer device determines the number of sample ex-warehouse cycles of the sample item according to the number of the sample devices and the number of the sample orders, and trains the ex-warehouse duration prediction model according to the sample order information and the number of the sample ex-warehouse cycles.

And the number of sample ex-warehouse cycles is not less than the minimum positive integer of the ratio of the number of sample orders to the number of sample devices.

For example, the number of sample devices is 10, the number of orders is 23, the number of sample orders is 23, each sample device can only carry out warehouse-out for one order at a time, then 10 orders of items can be carried out in one warehouse-out period, then the number of sample warehouse-out periods of the sample items can be determined to be 3, that is, the sample items can be carried out warehouse-out in the 3 rd warehouse-out period from the time when the sample orders are generated.

In one possible implementation, the ex-warehouse duration prediction model is a regression model, and the regression model may be a lifting tree model, a gradient lifting tree model, or any other regression model.

In addition, when the ex-warehouse duration prediction model is trained, the ex-warehouse duration prediction model may be trained by using an XGBoost frame (eXtreme Gradient boost frame), a LightGBM frame (Light Gradient boost Machine, distributed Gradient boost frame), or a castboost frame (sophisticated Features + Gradient boost, a deep learning frame).

In a possible implementation manner, after the computer device completes training of the ex-warehouse duration prediction model, the ex-warehouse duration prediction model may be stored, and the stored ex-warehouse duration prediction model may be subsequently obtained to determine the ex-warehouse duration of any order.

It should be noted that, in the embodiment of the present application, the description is only given by taking the number of the sample devices of the warehouse-out device obtained by the computer device as the number of the sample staff of the warehouse-out staff as an example, in another embodiment, the computer device may determine the number of the sample staff by adopting other ways without obtaining the number of the sample devices, and train the warehouse-out duration prediction model according to the sample order information, the number of the sample staff and the number of the sample orders. Or, the step 203 is not executed, and the ex-warehouse duration prediction model is trained according to the sample order information and the number of the sample personnel.

It should be noted that, in the embodiment of the present application, the number of sample orders of the sample reference orders obtained by the computer device is only used as an example for description, and in another embodiment, the computer device may not perform step 203, but only perform step 201 and step 202, and train the ex-warehouse duration prediction model according to the sample order information and the number of sample devices.

According to the method provided by the embodiment of the application, the computer equipment obtains the sample order information of the sample order, obtains the number of the sample equipment of the ex-warehouse equipment corresponding to the sample warehouse identification according to the sample order generation time, obtains the number of the sample order of the sample reference order, and trains the ex-warehouse duration prediction model according to the sample order information, the number of the sample equipment and the number of the sample order. The embodiment of the application provides a model training method, which can train a ex-warehouse time prediction model according to sample order information of a sample order and the number of sample equipment of ex-warehouse equipment of a warehouse where sample articles are located.

And moreover, the ex-warehouse time length prediction model is trained according to the number of the sample orders, and the influence of other sample reference orders on the sample ex-warehouse time length of the sample orders is considered, so that the ex-warehouse time length prediction model obtained through training is more accurate.

In addition, the ex-warehouse duration prediction model in the embodiment of the application is obtained by training according to the sample order information and the number of sample devices of a plurality of warehouses. Therefore, the ex-warehouse time length prediction model can be applied to any warehouse and has universality.

Fig. 3 is a flowchart of a method for determining a delivery duration according to an embodiment of the present application, and is applied to a computer device, where the computer device may be a terminal or a server. Referring to fig. 3, the method includes:

301. the computer device obtains order information of the target order.

The order information comprises order attribute information and order article information, the order attribute information comprises order generation time and warehouse identification, the order article information comprises target article identification, and a warehouse corresponding to the warehouse identification is used for storing the target article corresponding to the target article identification.

In this embodiment, except that the order attribute information does not include the time for taking the order out of the warehouse, the implementation manner of the computer device to obtain other order information of the target order is similar to that in step 201 in the foregoing embodiment, and is not described herein again.

302. And the computer equipment acquires the equipment number of the warehouse-out equipment corresponding to the warehouse identification.

The warehouse-out equipment is used for recording warehouse-out articles in the warehouse.

In a possible implementation manner, an operation record of each ex-warehouse device corresponding to the warehouse identifier within a preset time before the order generation time is obtained, and the obtained operation record includes the device number of the ex-warehouse device of the article ex-warehouse record.

The implementation of the computer device acquiring the number of devices in the library device is similar to that in step 202 of the above embodiment, and is not described herein again.

303. The computer device obtains an order quantity of the reference order.

The order attribute information of the reference order comprises a warehouse identifier, and the state of the reference order is the state that the article is not taken out of the warehouse.

The implementation manner of acquiring the order quantity of the reference order by the computer device is similar to the implementation manner of step 203 in the foregoing embodiment, except that the reference order acquired at the current time refers to an order whose order state is the state that the item is not taken out of the warehouse at the current time, and the sample reference order refers to an order whose order state is the state that the item is not taken out of the warehouse at the sample order generation time, which is not described in detail for step 303 in this embodiment.

304. And the computer equipment processes the order information, the equipment quantity and the order quantity based on the ex-warehouse time length prediction model, and determines the ex-warehouse time length of the target object.

In the embodiment of the application, the ex-warehouse duration prediction model is trained, and the computer equipment stores the ex-warehouse duration prediction model. When the delivery time of the target object needs to be determined, the computer device may obtain the stored delivery time prediction model. The ex-warehouse duration prediction model can be obtained through the training in the steps 201 to 204, or can be obtained through training in other manners.

In a possible implementation manner, the computer device obtains the number of ex-warehouse cycles of the target object according to the number of devices and the number of orders, processes the order information and the number of ex-warehouse cycles based on the ex-warehouse duration prediction model, and determines the ex-warehouse duration of the target object. The number of ex-warehouse cycles is not less than the minimum positive integer of the ratio of the order number to the equipment number.

It should be noted that, in this embodiment, the description is only given by taking an example that the computer device determines the device number as the number of staff, and processes the order information, the device number, and the order number based on the ex-warehouse duration prediction model, in another embodiment, the computer device may not perform step 302, obtain the number of staff by using other methods, and process the order information, the staff number, and the order number based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item. Or, step 303 is not executed, and the order information and the number of the persons are processed based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item.

It should be noted that, in the embodiment of the present application, only the computer device processes the order information, the device quantity, and the order quantity based on the ex-warehouse duration prediction model is taken as an example for description, in another embodiment, the computer device may not perform step 303, but only perform step 301 and step 302, and process the order information and the device quantity based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item.

305. And the computer equipment processes the order information based on the distribution duration prediction model and determines the distribution duration of the target order.

In the embodiment of the application, after determining the delivery Time based on the delivery Time prediction model, the computer device may also determine the delivery Time by using ETA (Estimated Time of Arrival) to determine the processing Time of the target order. Wherein the delivery duration may be determined based on a delivery duration prediction model.

The method includes the steps that computer equipment obtains a distribution duration prediction model, the distribution duration prediction model can be trained and stored by the computer equipment, the distribution duration prediction model can be obtained by adopting any training mode, and the training mode of the distribution duration prediction model is not limited in the embodiment of the application.

The order attribute information comprises a warehouse address corresponding to the warehouse identification and a receiving address of the target object. And the distribution duration prediction model determines the distribution duration of the target order according to the warehouse address and the receiving address.

In a possible implementation manner, the computer device may further process information such as order information, weather information, traffic information, and vehicle speed of a delivery person based on the delivery duration prediction model, and determine the delivery duration of the target order.

306. And the computer equipment determines the processing time length of the target order according to the ex-warehouse time length and the distribution time length.

In the embodiment of the application, after the computer device determines the ex-warehouse duration and the delivery duration, the processing duration of the target order can be determined according to the ex-warehouse duration and the delivery duration.

In one possible implementation, the computer device determines the sum of the ex-warehouse duration and the delivery duration as the processing duration of the target order.

In another possible implementation manner, considering the case of delayed delivery of the order when processing the historical order, the computer device may further obtain a historical delay time length, and determine the sum of the delivery time length, and the historical delay time length as the processing time length of the target order. Wherein the historical delay time period is equal to an average of time differences between actual processing time periods and predicted processing time periods of the plurality of historical orders.

Optionally, the computer device may obtain the historical delay duration by using bucket-based statistics, including the following steps:

1. a plurality of historical orders are obtained, and the time difference between the actual processing time length and the predicted processing time length of each historical order is determined.

2. And dividing the plurality of determined time differences into at least two groups, wherein the time differences in the same group belong to the same time difference range. Wherein each packet includes at least one time difference.

3. And averaging the time difference in each group to obtain the average value of the time difference of each group.

4. And averaging the average value of the time differences of each group to obtain the average value of the time differences of a plurality of historical orders as the historical delay time.

For example, the computer device obtains the time differences of 20 historical orders, and if the time differences of 5 orders in the 20 orders are in the range of 1-5 minutes, 7 orders are in the range of 5-10 minutes, and the time differences of 8 orders are in the range of 10-15 minutes, then according to the three ranges, the 20 time differences are divided into three groups, and the average value of the time differences in each group is obtained, and if the average value of the time differences in the group of 1-5 minutes is 2.4 minutes, the average value of the time differences in the group of 5-10 minutes is 8.1 minutes, and the average value of the time differences in the group of 10-15 minutes is 12 minutes, then the time differences in the 20 historical orders can be obtained as (2.4+8.1+12)/3, and the historical delay time length is 7.5 minutes.

Optionally, the computer device may obtain the historical delay time lengths, respectively obtain the historical orders corresponding to each warehouse in consideration of the difference of the processing time lengths of the orders by each warehouse, respectively count the historical delay time lengths of the historical orders of each warehouse, determine the processing time length of the target order, and use the sum of the historical delay time length corresponding to the warehouse, the warehouse-out time length, and the delivery time length as the processing time length according to the warehouse to which the target order belongs.

Optionally, after the first delay duration is acquired, a second delay duration is set according to a bucket allocation policy to which the first delay duration belongs, and the second delay duration is used as a historical delay duration. Wherein the second delay duration is greater than the first delay duration. The bucket allocation strategy means that each acquired first delay duration has a corresponding second delay duration.

For example, if the acquired first delay duration is 3 minutes, and the bucket allocation policy is to add the first delay duration to a second delay duration obtained after 5 minutes, the historical delay duration may be determined to be 8 minutes.

Optionally, the computer device may obtain an average value of time differences between actual delivery durations of the plurality of historical orders and the predicted delivery duration, as the historical delivery delay duration; and acquiring an average value of time differences between the actual delivery time lengths and the predicted delivery time lengths of the plurality of historical orders as the historical delivery delay time lengths. Therefore, the sum of the historical ex-warehouse delay time and the historical distribution delay time is used as the historical delay time. The historical ex-warehouse delay time and the historical delivery delay time are obtained in a similar mode to the historical delay time.

In another possible implementation, referring to fig. 4, the processing duration of the order includes an order distribution duration and a pickup duration in addition to the delivery duration and the delivery duration.

The order allocation duration refers to the time for allocating the target order to the corresponding warehouse after the target order is generated by the computer equipment; the goods taking duration refers to the goods taking duration of the target goods by the delivery personnel after the target goods are taken out of the warehouse, namely after the target goods are taken out of the warehouse by the warehouse, other goods may not be taken out of the warehouse yet, the delivery personnel can wait for the other goods to be taken out of the warehouse and deliver the target goods and the other goods together, and the waiting time of the delivery personnel is the goods taking time.

Therefore, the sum of the delivery time length, and the order allocation time length is optionally determined as the processing time length of the target order.

Optionally, the sum of the delivery time length, the delivery time length and the pickup time length is determined as the processing time length of the target order.

Optionally, the sum of the delivery time length, the order distribution time length and the goods taking time length is determined as the processing time length of the target order.

Optionally, the sum of the order allocation duration, the delivery duration, the pickup duration, the delivery duration and the historical delay duration may also be determined as the processing duration of the target order.

307. And the computer equipment determines the delivery time for delivering the target object to the receiving address according to the order generation time and the processing time length of the target order.

And the computer equipment increases the processing time length on the basis of the order generation time of the target order, and determines the obtained time as the delivery time of the target item.

In a possible implementation manner, after the user places an order for the target item on the terminal, the terminal determines the delivery time of the target item by using the method in the embodiment of the application, and displays the delivery time to the user. Or after the terminal determines the delivery time of the target object, the terminal determines a preset number of time periods after the delivery time according to the delivery time, the time intervals of the preset number of time periods are the same, the terminal displays the preset number of time periods to the user, the user can select the delivery time period, and the delivery personnel need to deliver the target object to the user within the time period selected by the user.

Or after the user places an order for the target object at the terminal, the terminal sends the order to the server, the server determines the delivery time of the target object by adopting the method in the embodiment of the application, the server sends the delivery time to the terminal, and the terminal displays the received delivery time to the user. Or after the server determines the delivery time, determining a preset number of time periods, sending the preset number of time periods to the terminal, and displaying the received preset number of time periods to the user by the terminal for the user to select.

According to the method provided by the embodiment of the application, the computer equipment obtains order information of a target order, obtains the equipment quantity of warehouse-out equipment corresponding to a warehouse identifier, obtains the order quantity of a reference order, processes the order information, the equipment quantity and the order quantity based on a warehouse-out time length prediction model, determines the warehouse-out time length of the target object, processes the order information based on a distribution time length prediction model, determines the distribution time length of the target order, determines the processing time length of the target order according to the warehouse-out time length and the distribution time length, and determines the delivery time for distributing the target object to a receiving address according to the order generation time and the processing time length of the target order. The embodiment of the application provides a method for predicting the warehouse-out duration, which can accurately determine the warehouse-out duration of a target object based on a warehouse-out duration prediction model according to order information of the target order and the number of devices of warehouse-out equipment of a warehouse where the target object is located, and improves the accuracy of the warehouse-out duration. And the delivery time length of the target object is accurately determined based on the delivery time length prediction model, so that the delivery time of the target object can be determined, and the accuracy of the determined delivery time is improved.

In addition, in the embodiment of the application, the warehouse-out time length, the distribution time length and the processing time length are determined, for an article provider, the capacity of the warehouse is estimated, the performance rate of article distribution is improved, the processing time length of the order can be reflected in order time dimension distribution, namely, the processing condition of the warehouse on the order is adjusted according to the order processing time length, and the capacity balance and warehouse allocation integration of the warehouse is promoted.

For example, a warehouse receives a plurality of orders, according to the method provided by the embodiment of the present application, processing durations of the plurality of orders are determined, and assuming that the processing durations of the plurality of orders are relatively close, the order durations of the plurality of orders may then be used as a reaction to the processing process of the warehouse on the orders, and the warehouse may adjust the number of people going out of the warehouse or the number of equipment going out of the warehouse according to the order durations, so that the plurality of orders may be delivered to the user in a relatively short time.

In addition, for the user, an accurate delivery time is determined for the user, so that the user can wait for the delivery of the article before and after the delivery time according to the delivery time without waiting for the delivery of the article all the time after ordering, and the user experience is improved.

In addition, referring to fig. 5, for the ex-warehouse duration prediction model, when the ex-warehouse duration prediction model is trained and used, the method comprises four stages of sample data preprocessing, model training, model evaluation and model use.

For the sample data preprocessing stage, the computer equipment firstly acquires sample data, wherein the sample data comprises sample order information, the number of sample equipment, the number of sample orders and other data in the embodiment; then processing the sample data, including data filtering, noise processing, data analysis, feature extraction, feature conversion, combined feature generation and the like; and adding a part of processed sample data serving as training data to a training data set, and adding the rest part of sample data serving as test data to a test data set.

And in the model training stage, training the ex-warehouse duration prediction model according to the obtained training data set.

And in the model evaluation stage, evaluating the trained ex-warehouse time length prediction model according to the obtained test data set, comparing the predicted ex-warehouse time length obtained based on the ex-warehouse time length prediction model with the actual ex-warehouse time length in the test data to obtain the difference between the predicted ex-warehouse time length and the actual ex-warehouse time length, and adjusting various parameters of the ex-warehouse time length prediction model according to the difference.

And in the model using stage, processing data such as order information, equipment quantity, order quantity and the like of the target order based on the trained ex-warehouse time duration prediction model, determining ex-warehouse time duration, determining delivery time duration according to the delivery time duration prediction model, and further determining delivery time.

Fig. 6 is a schematic structural diagram of a delivery duration determining apparatus according to an embodiment of the present application. Referring to fig. 6, the apparatus includes:

the order information acquiring module 601 is configured to acquire order information of a target order, where the order information includes order attribute information and order item information, the order attribute information includes order generation time and a warehouse identifier, the order item information includes a target item identifier, and a warehouse corresponding to the warehouse identifier is used to store a target item corresponding to the target item identifier;

a personnel number obtaining module 602, configured to obtain the quantity of personnel of the warehouse-out personnel corresponding to the warehouse identifier;

the ex-warehouse duration determining module 603 is configured to process the order information and the number of people based on the ex-warehouse duration prediction model, and determine the ex-warehouse duration of the target item.

In a possible implementation manner, the staff amount obtaining module 602 is further configured to obtain an equipment amount of the warehouse exit equipment corresponding to the warehouse identifier, determine the equipment amount as a staff amount, and record the warehouse exit equipment in the warehouse.

In one possible implementation, referring to fig. 7, the person number obtaining module 602 includes:

the record obtaining unit 6021 is configured to obtain an operation record of each warehouse-out device corresponding to the warehouse identifier within a preset time before the order generation time;

the device number acquiring unit 6022 is configured to acquire the device number of the delivery device including the item delivery record in the operation record.

In one possible implementation, referring to fig. 7, the apparatus further includes:

an order quantity obtaining module 604, configured to obtain an order quantity of a reference order, where the order attribute information of the reference order includes a warehouse identifier, and a state of the reference order is an article non-delivery state;

the delivery duration determining module 603 is further configured to process the order information, the number of people, and the number of orders based on the delivery duration prediction model, and determine a delivery duration of the target item.

In one possible implementation, referring to fig. 7, the ex-warehouse duration determining module 603 includes:

a cycle number obtaining unit 6031 configured to obtain a number of ex-warehouse cycles of the target item according to the number of persons and the number of orders, where the number of ex-warehouse cycles is a smallest positive integer not less than a ratio of the number of orders to the number of persons;

the ex-warehouse duration determining unit 6032 is configured to process the order information and the number of ex-warehouse cycles based on the ex-warehouse duration prediction model, and determine the ex-warehouse duration of the target item.

the sample order information obtaining module 605 is configured to obtain sample order information of a sample order, where the sample order information includes sample order attribute information and sample order item information, the sample order attribute information includes sample order generation time, sample order warehouse-out time, and sample warehouse identifier, the sample order item information includes sample item identifier, and a warehouse corresponding to the sample warehouse identifier is configured to store a sample item corresponding to the sample item identifier;

a sample staff number obtaining module 606, configured to obtain, according to the sample order generation time, a sample staff number of the ex-warehouse staff corresponding to the sample warehouse identifier;

and the model training module 607 is used for training the ex-warehouse time length prediction model according to the sample order information and the number of the sample personnel.

In one possible implementation manner, referring to fig. 7, the sample staff number obtaining module 606 is further configured to obtain the sample equipment number of the ex-warehouse equipment corresponding to the sample warehouse identifier according to the sample order generation time, and determine the sample equipment number as the sample staff number.

In one possible implementation, referring to fig. 7, the sample person number obtaining module 606 includes:

a sample record obtaining unit 6061, configured to obtain a sample operation record of each ex-warehouse device corresponding to the sample warehouse identifier within a preset time before the sample order generation time;

a sample device number acquiring unit 6062 configured to acquire the number of sample devices of the warehousing device including the article warehousing record in the sample operation record.

a sample order quantity obtaining module 608, configured to obtain a sample order quantity of a sample reference order, where sample order attribute information of the sample reference order includes a sample warehouse identifier, and a state of the sample reference order at a sample order generation time is an article non-warehouse-out state;

the model training module 607 is further configured to train a ex-warehouse duration prediction model according to the sample order information, the number of sample personnel, and the number of sample orders.

In one possible implementation, the model training module 607 includes:

a sample cycle number obtaining unit 6071, configured to determine a sample warehousing cycle number of the sample item according to the number of sample persons and the number of sample orders, where the sample warehousing cycle number is a smallest positive integer not smaller than a ratio of the number of sample orders to the number of sample persons;

and a model training unit 6072, configured to train a ex-warehouse duration prediction model according to the sample order information and the number of sample ex-warehouse cycles.

In one possible implementation manner, the order attribute information further includes a warehouse address corresponding to the warehouse identifier and a receiving address of the target item; referring to fig. 7, the apparatus further includes:

a delivery duration determining module 609, configured to process the order information based on the delivery duration prediction model, and determine a delivery duration of the target order;

and the processing duration determining module 610 is configured to determine the processing duration of the target order according to the ex-warehouse duration and the delivery duration.

In one possible implementation, referring to fig. 7, the processing duration determining module 610 includes:

a first determining unit 6101, configured to determine the sum of the delivery duration and the delivery duration as the processing duration of the target order; or,

a second determining unit 6102, configured to determine a sum of the ex-warehouse time length, the delivery time length, and the historical delay time length as the processing time length of the target order, where the historical delay time length is equal to an average of time differences between actual processing time lengths and predicted processing time lengths of the plurality of historical orders; or,

a third determining unit 6103, configured to determine the sum of the warehouse-out duration, the distribution duration and the order allocation duration as the processing duration of the target order, where the order allocation duration is the duration for allocating the target order to the warehouse after the target order is generated; or,

a fourth determining unit 6104, configured to determine the sum of the warehouse-out duration, the delivery duration, and the pickup duration as the processing duration of the target order, where the pickup duration is the duration of picking up the goods from the warehouse by the delivery staff.

a time difference determining module 611, configured to obtain a plurality of historical orders, and determine a time difference between an actual processing time length and a predicted processing time length of each historical order;

a grouping determination module 612, configured to divide the determined multiple time differences into at least two groups, where the time differences in the same group belong to the same time difference range;

a delay time determining module 613, configured to calculate an average value of the time differences in each group, so as to obtain an average value of the time differences in each group;

the delay time length determining module 613 is further configured to average the time difference average of each group, and obtain an average of the time differences of the plurality of historical orders as the historical delay time length.

and a delivery time determining module 614, configured to determine a delivery time for delivering the target item to the receiving address according to the order generation time and the processing duration of the target order.

The device provided by the embodiment of the application can accurately determine the warehouse-out time of the target object based on the warehouse-out time prediction model according to the order information of the target order and the number of the personnel of the warehouse-out personnel of the warehouse where the target object is located, and improves the accuracy of the warehouse-out time.

It should be noted that: the device for determining a time length of ex-warehouse provided in the above embodiment is exemplified by only the division of the above functional modules when determining the time length of out-warehouse, and in practical applications, the function distribution may be completed by different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the above described functions. In addition, the warehouse-out duration determining device and the warehouse-out duration determining method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

Fig. 8 shows a schematic structural diagram of a terminal 800 according to an exemplary embodiment of the present application.

In general, the terminal 800 includes: a processor 801 and a memory 802.

The processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 801 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 801 may also include a main processor and a coprocessor, where the main processor is a processor for processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 801 may be integrated with a GPU (Graphics Processing Unit, image Processing interactor) which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 801 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 802 is used to store at least one instruction for the processor 801 to implement the outbound time length determination method provided by the method embodiments of the present application.

In some embodiments, the terminal 800 may further include: a peripheral interface 803 and at least one peripheral. The processor 801, memory 802 and peripheral interface 803 may be connected by bus or signal lines. Various peripheral devices may be connected to peripheral interface 803 by a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 804, a touch screen display 805, a camera 806, an audio circuit 807, a positioning component 808, and a power supply 809.

The peripheral interface 803 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 801 and the memory 802. In some embodiments, the processor 801, memory 802, and peripheral interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 801, the memory 802, and the peripheral interface 803 may be implemented on separate chips or circuit boards, which are not limited by this embodiment.

The Radio Frequency circuit 804 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 804 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 804 converts an electrical signal into an electromagnetic signal to be transmitted, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 804 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 8G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 804 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 805 is used to display a UI (user interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 805 is a touch display, the display 805 also has the ability to capture touch signals on or above the surface of the display 805. The touch signal may be input to the processor 801 as a control signal for processing. At this point, the display 805 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 805 may be one, providing the front panel of the terminal 800; in other embodiments, the display 805 may be at least two, respectively disposed on different surfaces of the terminal 800 or in a folded design; in still other embodiments, the display 805 may be a flexible display disposed on a curved surface or a folded surface of the terminal 800. Even further, the display 805 may be arranged in a non-rectangular irregular pattern, i.e., a shaped screen. The Display 805 can be made of LCD (liquid crystal Display), OLED (Organic Light-Emitting Diode), and the like.

The camera assembly 806 is used to capture images or video. Optionally, camera assembly 806 includes a front camera and a rear camera. Generally, a front camera is provided at a front panel of the terminal 800, and a rear camera is provided at a rear surface of the terminal 800. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 806 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuit 807 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 801 for processing or inputting the electric signals to the radio frequency circuit 804 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 800. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 807 may also include a headphone jack.

The positioning component 808 is used to locate the current geographic position of the terminal 800 for navigation or LBS (location based Service). The positioning component 808 may be a positioning component based on the GPS (global positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.

Power supply 809 is used to provide power to various components in terminal 800. The power supply 809 can be ac, dc, disposable or rechargeable. When the power source 809 comprises a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 800 also includes one or more sensors 810. The one or more sensors 810 include, but are not limited to: acceleration sensor 811, gyro sensor 812, pressure sensor 813, fingerprint sensor 814, optical sensor 815 and proximity sensor 816.

The acceleration sensor 811 may detect the magnitude of acceleration in three coordinate axes of the coordinate system established with the terminal 800. For example, the acceleration sensor 811 may be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 801 may control the touch screen 805 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 811. The acceleration sensor 811 may also be used for acquisition of motion data of an application or a user.

The gyro sensor 812 may detect a body direction and a rotation angle of the terminal 800, and the gyro sensor 812 may cooperate with the acceleration sensor 811 to acquire a 3D motion of the user with respect to the terminal 800. From the data collected by the gyro sensor 812, the processor 801 may implement the following functions: motion sensing (such as changing the UI according to a tilt operation of the user), image stabilization at the time of photographing, application control, and inertial navigation.

Pressure sensors 813 may be disposed on the side bezel of terminal 800 and/or underneath touch display 805. When the pressure sensor 813 is disposed on the side frame of the terminal 800, the holding signal of the user to the terminal 800 can be detected, and the processor 801 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 813. When the pressure sensor 813 is disposed at a lower layer of the touch display screen 805, the processor 801 controls the operability control on the UI interface according to the pressure operation of the user on the touch display screen 805. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 814 is used for collecting a fingerprint of the user, and the processor 801 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 1414, or the fingerprint sensor 814 identifies the identity of the user according to the collected fingerprint. Upon identifying that the user's identity is a trusted identity, the user is authorized by the processor 801 to have associated sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying for and changing settings, etc. Fingerprint sensor 814 may be disposed on the front, back, or side of terminal 800. When a physical button or a vendor Logo is provided on the terminal 800, the fingerprint sensor 814 may be integrated with the physical button or the vendor Logo.

The optical sensor 815 is used to collect the ambient light intensity. In one embodiment, the processor 801 may control the display brightness of the touch screen 805 based on the ambient light intensity collected by the optical sensor 815. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 805 is increased; when the ambient light intensity is low, the display brightness of the touch display 805 is turned down. In another embodiment, the processor 801 may also dynamically adjust the shooting parameters of the camera assembly 806 based on the ambient light intensity collected by the optical sensor 815.

A proximity sensor 816, also known as a distance sensor, is typically provided on the front panel of the terminal 800. The proximity sensor 816 is used to collect the distance between the user and the front surface of the terminal 800. In one embodiment, when the proximity sensor 816 detects that the distance between the user and the front surface of the terminal 800 gradually decreases, the processor 801 controls the touch display 805 to switch from the bright screen state to the dark screen state; when the proximity sensor 816 detects that the distance between the user and the front surface of the terminal 800 becomes gradually larger, the processor 801 controls the touch display 805 to switch from the screen-on state to the screen-on state.

Those skilled in the art will appreciate that the configuration shown in fig. 8 is not intended to be limiting of terminal 800 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

Fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 900 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 901 and one or more memories 902, where the memory 902 stores at least one instruction, and the at least one instruction is loaded and executed by the processors 901 to implement the methods provided by the foregoing method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the server may also include other components for implementing the functions of the device, which are not described herein again.

The server 900 may be configured to perform the steps performed by the computer device in the outbound time length determination method described above.

The embodiment of the present application further provides a computer device for determining a time length for ex-warehouse, where the computer device includes a processor and a memory, and the memory stores at least one program code, and the at least one program code is loaded and executed by the processor, so as to implement the operations performed in the method for determining an ex-warehouse time length according to the above embodiment.

The embodiment of the present application further provides a computer-readable storage medium, where at least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by a processor, so as to implement the operations executed in the method for determining a length of time for ex-warehouse according to the foregoing embodiment.

The embodiment of the present application further provides a computer program, where at least one program code is stored in the computer program, and the at least one program code is loaded and executed by a processor, so as to implement the operations executed in the method for determining a length of time for ex-warehouse according to the above embodiment.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only an alternative embodiment of the present application and is not intended to limit the present application, and any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for determining warehouse-out time length is characterized by comprising the following steps:

2. The method of claim 1, wherein the obtaining of the number of people who are out of the warehouse and corresponding to the warehouse identifier comprises:

3. The method of claim 2, wherein the obtaining the device number of the warehouse device corresponding to the warehouse identifier comprises:

4. The method of claim 1, further comprising:

5. The method according to claim 4, wherein the processing the order information, the number of people, and the order quantity based on the ex-warehouse duration prediction model to determine the ex-warehouse duration of the target item comprises:

6. The method of claim 1, wherein the processing the order information and the quantity of people based on a warehouse-out duration prediction model further comprises, before determining the warehouse-out duration of the target item:

7. The method of claim 1, wherein the order attribute information further comprises a warehouse address corresponding to the warehouse identifier and a shipping address of the target item; the method further comprises the following steps of processing the order information and the number of the personnel based on a warehouse-out duration prediction model, and determining the warehouse-out duration of the target item:

8. An ex-warehouse duration determination apparatus, comprising:

9. A computer device, comprising a processor and a memory, wherein at least one program code is stored in the memory, and wherein the at least one program code is loaded into and executed by the processor to perform the operations of the method for determining a length of time for ex-warehouse as claimed in any of claims 1 to 7.

10. A computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded into and executed by a processor to perform the operations of the method for determining a length of time to leave a warehouse as claimed in any one of claims 1 to 7.