CN113762844A

CN113762844A - Method and device for determining shelf loading time of articles

Info

Publication number: CN113762844A
Application number: CN202011118154.2A
Authority: CN
Inventors: 陆继任; 祝捷; 蒋宁宁; 康宁轩
Original assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2020-10-19
Filing date: 2020-10-19
Publication date: 2021-12-07

Abstract

The invention discloses a method and a device for determining the shelf loading time of an article, and relates to the technical field of computers. One embodiment of the method comprises: acquiring related information of an article to be placed on a shelf and a target performance rate condition, wherein the related information comprises information of a target transfer route; obtaining a first time length according to the relevant information and a preset time length generator; determining target offset duration according to the information of the target transfer route and the target performance rate condition; taking the sum of the first time length and the target offset time length as the transfer time length of the articles to be placed on the shelf; and calculating the shelving time of the articles to be shelved according to the dialing duration, and outputting the shelving time so as to show the shelving time to the user. The method and the device can improve the accuracy of the time for putting articles on shelves and improve the user experience; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of days for turnover of inventory of articles is reduced, the utilization rate of storehouses and the turnover rate of inventory are improved, and the cost is reduced.

Description

Method and device for determining shelf loading time of articles

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a shelf loading time of an article, an electronic device, and a computer-readable medium.

Background

Inventory transfers refer to the process of transferring an item from one warehouse to another. For an enterprise with multiple warehouses or branch organizations, it is a common business to allocate articles among different warehouses.

For example, the e-commerce platform calls items out of a certain warehouse from other warehouses, sells the items to the customer through pre-sale, and meanwhile, commits to the customer for a transport time called to the warehouse and a combined time distributed to the customer after the warehouse arrives, calculates the shelf time according to the combined time, and displays the shelf time as a commitment to the user.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:

the combination time is generally set manually according to experience, and if the combination time is set to be short, and the articles cannot arrive at the warehouse on time within the combination time and cannot be put on shelf on time, customer complaints may be caused. In order to reduce the complaints of customers caused by inaccurate promised time, the combination time of the goods is usually set to be long so as to ensure high performance. However, this increases the number of days to turnover the stock, and the stock utilization is low. How to provide a proper combination duration and a proper shelf-loading time can meet a certain performance rate and shorten unnecessary inventory turnover as much as possible, which is a technical problem to be solved urgently.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method, an apparatus, an electronic device, and a computer-readable medium for determining an article shelf time, which can improve the accuracy of the article shelf time and improve user experience; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of turnover days of the inventory of the articles is reduced, the problems caused by too short or too long time of manual configuration are reduced, the utilization rate of the storeroom and the turnover rate of the inventory are improved, and the cost is reduced.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method of determining an item listing time, including:

acquiring related information of an article to be shelved and a target performance rate condition corresponding to the article to be shelved, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target transfer route;

obtaining a first time length according to the related information and a preset time length generator;

determining target offset duration according to the information of the target transfer route and the target performance rate condition;

taking the sum of the first time length and the target offset time length as a transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse;

and calculating the shelving time of the articles to be shelved according to the transfer duration, and outputting the shelving time so as to show the shelving time to a user.

Optionally, before determining the target offset duration, the method further comprises:

determining historical allocation routes, and acquiring a test data set corresponding to each historical allocation route, wherein the test data set comprises relevant information of a plurality of test samples and actual allocation duration of the plurality of test samples;

obtaining a plurality of second time lengths according to the relevant information of the plurality of test samples and the preset time length generator;

determining a plurality of performance rate conditions;

determining an offset time length corresponding to each performance rate condition according to the actual transfer time lengths of the plurality of test samples and the plurality of second time lengths;

generating an offset duration list corresponding to the historical allocation route according to the offset duration corresponding to each performance rate condition;

determining a target offset duration according to the information of the target allocation route and the target performance rate condition comprises: and selecting a target offset time length from an offset time length list corresponding to the target transfer route according to the information of the target transfer route and the target performance rate condition.

Optionally, determining, according to the actual transfer durations of the plurality of test samples and the second duration, an offset duration corresponding to each performance rate condition includes:

determining a candidate duration set, wherein the candidate duration set comprises a plurality of candidate durations;

for each performance rate condition, traversing candidate durations in the candidate duration set, determining a target candidate duration which enables a test performance rate to meet the performance rate condition and has a minimum average error, and taking the target candidate duration as an offset duration corresponding to the performance rate condition, wherein the test performance rate and the average error are determined according to a third duration and an actual transfer duration of the test sample, and the third duration is the sum of the second duration and the candidate duration.

Optionally, after determining the related information of the article to be shelved, the method further comprises: performing feature processing on the related information to obtain feature data;

according to the related information and a preset time generator, obtaining a first time comprises: and obtaining a first time length according to the characteristic data and a preset time length generator.

Optionally, the performing feature processing on the related information includes: processing the related information into a plurality of characteristic fields, and determining the data type of each characteristic field, wherein the data type comprises a character type; the characteristic field of which the data type is character type is subjected to one-hot coding.

Optionally, the method further comprises obtaining the preset duration generator according to the following process: acquiring a training data set, wherein the training data set comprises relevant information of a plurality of training samples and actual call duration of the plurality of training samples; carrying out feature processing on the relevant information of the training sample to obtain historical feature data; constructing a prediction model and a loss function; and training the prediction model according to the historical characteristic data, the actual call duration of the training samples and the loss function to obtain the preset duration generator.

Optionally, the prediction model is a gradient boosting decision tree model;

the meaning of the loss function is: if the difference between the output of the gradient lifting decision tree model and the actual transfer duration of the training sample is within a preset interval, taking the difference as a loss; and if the difference between the output of the gradient lifting decision tree model and the actual dialing duration of the training artifact is not within a preset interval, taking K times of the difference as loss, wherein K is a real number greater than 1.

Optionally, the related information further comprises one or more of: the method comprises the following steps of issuing time, the number of the articles to be shelved, the type information of the articles to be shelved, the information of an originating distribution center corresponding to an originating warehouse and the information of a target distribution center corresponding to a target warehouse, wherein the issuing time is determined according to the time for sending a task for allocating the articles to be shelved to the originating warehouse.

To achieve the above object, according to another aspect of embodiments of the present invention, there is provided an apparatus for determining an item shelving time, including:

the information determining module is used for acquiring related information of the articles to be shelved and target performance rate conditions corresponding to the articles to be shelved, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target transfer route;

the first time length determining module is used for obtaining a first time length according to the relevant information and a preset time length generator;

the offset duration determining module is used for determining target offset duration according to the information of the target transfer route and the target performance rate condition;

a transfer duration determining module, configured to use a sum of the first duration and the target offset duration as a transfer duration for transferring the to-be-shelved item from the originating warehouse to the destination warehouse;

and the shelving time determining module is used for calculating the shelving time of the articles to be shelved according to the transfer duration and outputting the shelving time so as to show the shelving time to a user.

Optionally, the apparatus further comprises an offset determination module configured to: determining historical allocation routes, and acquiring a test data set corresponding to each historical allocation route, wherein the test data set comprises relevant information of a plurality of test samples and actual allocation duration of the plurality of test samples; obtaining a plurality of second time lengths according to the relevant information of the plurality of test samples and the preset time length generator; determining a plurality of performance rate conditions; determining an offset time length corresponding to each performance rate condition according to the actual transfer time lengths of the plurality of test samples and the second time length; generating an offset duration list corresponding to the historical allocation route according to the offset duration corresponding to each performance rate condition;

the duration determination module is further configured to: and selecting a target offset time length from an offset time length list corresponding to the target transfer route according to the information of the target transfer route and the target performance rate condition.

Optionally, the bias determination module is further configured to: determining a candidate duration set, wherein the candidate duration set comprises a plurality of candidate durations; for each performance rate condition, traversing candidate durations in the candidate duration set, determining a target candidate duration which enables a test performance rate to meet the performance rate condition and has a minimum average error, and taking the target candidate duration as an offset duration corresponding to the performance rate condition, wherein the test performance rate and the average error are determined according to a third duration and an actual transfer duration of the test sample, and the third duration is the sum of the second duration and the candidate duration.

Optionally, the information determining module is further configured to: performing feature processing on the related information to obtain feature data;

the duration determination module is further configured to: and obtaining a first time length according to the characteristic data and a preset time length generator.

Optionally, the information determining module is further configured to: processing the related information into a plurality of characteristic fields, and determining the data type of each characteristic field, wherein the data type comprises a character type; the characteristic field of which the data type is character type is subjected to one-hot coding.

Optionally, the apparatus further comprises a training module for: acquiring a training data set, wherein the training data set comprises relevant information of a plurality of training samples and actual call duration of the plurality of training samples; carrying out feature processing on the relevant information of the training sample to obtain historical feature data; constructing a prediction model and a loss function; and training the prediction model according to the historical characteristic data, the actual call duration of the training samples and the loss function to obtain the preset duration generator.

Optionally, the prediction model is a gradient boosting decision tree model;

To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus including: one or more processors; a storage device for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement a method of determining an item on-shelf time of an embodiment of the present invention.

To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided a computer-readable medium having stored thereon a computer program, which when executed by a processor, implements a method of determining an item shelf time according to an embodiment of the present invention.

One embodiment of the above invention has the following advantages or benefits: the method comprises the steps that related information of an object to be shelved and a target performance rate condition corresponding to the object to be shelved are obtained, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target transfer route; obtaining a first time length according to the related information and a preset time length generator; determining target offset duration according to the information of the target transfer route and the target performance rate condition; taking the sum of the first time length and the target offset time length as a transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse; according to the transfer duration, the shelving time of the articles to be shelved is calculated, and the shelving time is output to show the technical means of the shelving time to a user, so that the accuracy of the shelving time of the articles can be improved, and the user experience is improved; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of turnover days of the inventory of the articles is reduced, the problems caused by too short or too long time of manual configuration are reduced, the utilization rate of the storeroom and the turnover rate of the inventory are improved, and the cost is reduced.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

FIG. 1 is a schematic diagram of the main flow of a method of determining an item listing time according to an embodiment of the present invention;

FIG. 2 is a schematic illustration of a sub-flow of a method of determining an item listing time according to an embodiment of the present invention;

FIG. 3 is a schematic illustration of a sub-flow of a method of determining an item listing time according to another embodiment of the present invention;

FIG. 4 is a schematic diagram of the main modules of an apparatus for determining the time to put an item on shelf according to an embodiment of the present invention;

FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic diagram of a main flow of a method for determining an item shelf loading time according to an embodiment of the present invention, as shown in fig. 1, the method includes:

step S101: acquiring related information of an article to be shelved and a target performance rate condition corresponding to the article to be shelved, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target transfer route;

step S102: obtaining a first time length according to the related information and a preset time length generator;

step S103: determining target offset duration according to the information of the target transfer route and the target performance rate condition;

step S104: taking the sum of the first time length and the target offset time length as a transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse;

step S105: and calculating the shelving time of the articles to be shelved according to the transfer duration, and outputting the shelving time so as to show the shelving time to a user.

For step S101, the originating warehouse refers to the warehouse from which the item to be shelved is issued, and the destination warehouse refers to the warehouse from which replenishment is required to be allocated from another place. The originating repository information may include an address and identification (e.g., a number) of the originating repository. The destination repository information may include an address and an identification (e.g., a number) of the destination repository. The information for the target dispatch route includes a navigation distance from the originating warehouse to the destination warehouse.

In alternative embodiments, the related information may further include one or more of the following: issuing time, the number of the articles to be shelved, the type information of the articles to be shelved, the information of an originating distribution center corresponding to the originating warehouse and the information of a destination distribution center corresponding to the destination warehouse. The delivery time is determined according to the time for sending the task of allocating the articles to be shelved to the starting warehouse, for example, the number of hours for sending the task of allocating the articles to be shelved to the starting warehouse is used as the delivery time. For example, if the time for transferring the task of the article to be shelved to the originating warehouse is 12:30:00, the time for sending is 12. After the task of transferring the articles to be placed on shelves is issued to the originating warehouse, the originating warehouse needs time for production, the articles are sent from the originating warehouse to the destination warehouse after production, and different issuing time affects production time of the originating warehouse and further affects transferring time of transferring the articles to be placed on shelves from the originating warehouse to the destination warehouse. Therefore, in the embodiment of the present invention, the issue time is used as one of the factors for determining the dialing duration. The category refers to the category of the article. In an alternative embodiment, the class refers to an identification of a primary class. The information for the distribution center to which the originating warehouse corresponds includes the address and identification (e.g., number) of the distribution center to which the originating warehouse corresponds. The information of the distribution center corresponding to the destination warehouse includes an address and an identification (e.g., a number) of the distribution center corresponding to the destination warehouse. The information of the target-dispatched route may include a start point (i.e., a location of the originating warehouse), a must-pass point (a location of the originating distribution center and a location of the destination distribution center), an end point (a location of the destination warehouse), and a navigation distance of the target-dispatched route. The navigation distance may be obtained by inputting the start point, must-pass point, and end point into a navigation application.

In an alternative embodiment, the information about the articles to be shelved may be obtained according to the following process:

receiving basic information of an article to be shelved, wherein the basic information comprises: information of an originating warehouse, information of a target warehouse, issuing time and the number of the articles to be shelved;

matching corresponding extended information from a preset database according to the basic information of the articles to be shelved, wherein the extended information comprises the type information of the articles to be shelved, the information of an originating distribution center corresponding to the originating warehouse, the information of a target distribution center corresponding to the target warehouse and the information of a target transfer route;

and taking the basic information and the extended information as the related information of the articles to be shelved.

In an optional embodiment, after determining the information about the article to be shelved, the method further comprises: and performing characteristic processing on the related information to obtain characteristic data.

Specifically, the performing the feature processing on the related information includes: processing the related information into a plurality of characteristic fields, and determining the data type of each characteristic field, wherein the data type comprises a character type; the characteristic field of which the data type is character type is subjected to one-hot coding.

As an example, the related information is processed into a plurality of characteristic fields according to table 1 below.

Table 1:

in table 1 above, there is a characteristic field in which the data type is a character type. In order to enable the recognition by the preset time length generator, the character-type characteristic field needs to be subjected to characteristic processing. Specifically, the characteristic processing of the character-type characteristic field is to perform one-hot encoding of the character-type characteristic field. One-Hot Encoding (One-Hot Encoding) is to represent some parameters with 0 and 1, using an N-bit status register to encode N states. For example, the originating warehouse has a number of 616, which is [0, 1, 0, 1, … … 0, 0] after unique hot encoding. No processing is required for the numeric type of the feature field. The characteristic data comprises a numerical characteristic field and coded data, and the coded data refers to data obtained by carrying out one-hot coding on the character type characteristic field.

For step S102, in an alternative embodiment, as shown in fig. 2, the duration generator may be trained according to the following process:

step S201: acquiring a training data set, wherein the training data set comprises relevant information of a plurality of training samples and actual call duration of the plurality of training samples;

step S202: carrying out feature processing on the relevant information of the training sample to obtain historical feature data;

step S203: constructing a prediction model and a loss function;

step S204: and training the prediction model according to the historical characteristic data, the actual call duration of the training samples and the loss function to obtain the preset duration generator.

For step S201, the information related to the training sample includes the number of the historical dispatched articles, the delivery time, the information of the originating warehouse, the information of the destination warehouse, the information of the article type, the information of the distribution center corresponding to the originating warehouse, the information of the distribution center corresponding to the destination warehouse, and the information of the historical dispatched route. The issuing time is determined according to the time for sending the task of transferring the training sample to the starting warehouse, for example, the hour value of the time for sending the task of transferring the training sample to the starting warehouse is used as the issuing time. For example, if the time for the task of transferring the training sample to the originating warehouse is 12:15:00, the issuing time is 12. As an example, the information related to the training samples may be processed into the feature field according to table 2 below.

Table 2:

for step S202, in table 2 above, there is data whose data type is a character type. In order to enable the model to be recognized, it is necessary to perform feature processing on the character-type data. Specifically, the characteristic processing of the character-type data is that the character-type data is subjected to one-hot encoding. One-Hot Encoding (One-Hot Encoding) is to represent some parameters with 0 and 1, using an N-bit status register to encode N states. For example, the originating warehouse has a number of 616, which is [0, 1, 0, 1, … … 0, 0] after unique hot encoding.

For step S203, a gradient boosting decision tree model is constructed, and the expression thereof is shown as formula (1):

wherein, f (b + w)₁x₁+w₂x₂+…+w₈x₈) An algorithmic function representing a gradient boosting decision tree model, b represents a bias term, w₁～w₈Is x₁～x₈Weight of (1), x₁～x₈In order to characterize the features in table 1 above,

and (4) representing the output of the gradient boost decision tree model, namely the predicted time length of the gradient boost decision tree model. A Gradient Boosting Decision Tree (GBDT) model is a model that classifies or regresses data by using an additive model (i.e., a linear combination of basis functions) and continuously reducing residual errors generated in a training process.

Then, a loss function is constructed, the meaning of the loss function being: if the difference between the output of the gradient lifting decision tree model and the actual transfer duration of the training sample is within a preset interval, taking the difference as a loss; and if the difference between the output of the gradient lifting decision tree model and the actual dialing duration of the training artifact is not within a preset interval, taking K times of the difference as loss, wherein K is a real number greater than 1.

As an example, the preset interval may be [0, 24], K being 20. The expression of the loss function is shown in the following equation (2):

wherein loss represents loss, and y is the label in table 1 above, i.e. the actual call duration of the training sample.

The loss function represents: if the difference between the predicted time length of the gradient lifting decision tree model and the actual transfer time length is within 0-24 hours, the loss is the difference between the predicted time length and the actual transfer time length; if the difference between the predicted duration and the actual dialing duration is less than 0 or greater than 24, the loss is 20 times the difference between the predicted duration and the actual dialing duration. This is because the error is within 0-24 hours, the predicted result has been achieved, and the error is within 0-24 hours. In this embodiment, fulfillment is defined as a predicted duration being greater than or equal to an actual call duration. If the error is greater than 24 hours or no performance is achieved (namely the predicted time length is smaller than the actual transfer time length), the difference between the predicted time length and the actual transfer time length is enlarged, namely the proportion of the error is increased, so that the gradient lifting decision tree model focuses on learning samples with difference greater than 24 hours or no performance, and the predicted time length is biased to be within 0-24 hours of the actual transfer time length.

In practical application, a lightGBM algorithm package can be used to construct and train a gradient boosting decision tree model, and the training process is roughly as follows:

(1)

the algorithm is initialized and the algorithm is started,

a predicted dial-in duration representing the nth number;

(2)

training the first tree f₁(x) (ii) a Wherein the content of the first and second substances,

f(x)＝f(b+w₁x₁+w₂x₂+…+w₈x₈)；

(3)

training a second tree f₂(x) The first tree is no longer adjusted;

(4)

training the t tree, wherein the t-1 tree is not adjusted;

(5) assuming that the t-th tree is trained at this time, the objective function is shown as the following formula (3):

wherein the content of the first and second substances,

as a loss function of the above, y_iIndicating the true dialing duration for the ith sample,

indicating the predicted commit time of the ith sample on the t-th tree.

And the initialization values of the weight w and the bias b are 0, and the weight w and the bias b are updated by using a gradient descent strategy in the training process of the gradient lifting decision tree model. And then continuously circulating the operation to find out a group of most appropriate parameters b and w (namely finding out a group of appropriate trees), so that the difference between the dial time output by the model and the actual dial time is biased to be within 0-24 hours, and the preset time generator is obtained. Gradient Descent algorithm (Gradient decision Optimization) is the most commonly used Optimization algorithm for neural network model training. For the deep learning model, the optimization training is basically carried out by adopting a gradient descent algorithm. The gradient descent strategy refers to each iteration of the gradient lifting decision tree model

Wherein a ═ f (b + w)₁x₁+w₂x₂+…+w₈x₈). According to the derivative chain rule, obtain

Wherein z is b + w₁x₁+w₂x₂+…+w₈x₈To thereby obtain

Finally pass through w_j：＝w_j-ηdw_j. Where j is 1, 2, … 8, and η is a learning rate and is generally set to 0.01 to 0.5. In the present embodiment, η is 0.1.

After obtaining the preset duration generator, the feature data of the article to be shelved may be input into the preset duration generator, so as to obtain the first duration predicted by the preset duration generator.

For step S103, a target offset duration may be selected from the list of offset durations corresponding to the target allocation route according to the target allocation route and the target performance rate condition. Wherein the list of offset durations may be obtained according to the following procedure:

step 1: determining historical allocation routes, and acquiring a test data set corresponding to each historical allocation route, wherein the test data set comprises relevant information of a plurality of test samples and actual allocation duration of the plurality of test samples;

step 2: obtaining a plurality of second time lengths according to the relevant information of the plurality of test samples and the preset time length generator;

and step 3: determining a plurality of performance rate conditions;

and 4, step 4: determining an offset time length corresponding to each performance rate condition according to the actual transfer time lengths of the plurality of test samples and the second time length;

and 5: and generating an offset duration list corresponding to the historical allocation route according to the offset duration corresponding to each performance rate condition.

For steps 1 and 2, the test samples in the test data set are different samples than the training samples in the training data set above. In an alternative embodiment, the historical dialing data may be obtained, and the historical dialing data is divided into training data and test data according to a preset proportion, for example, 70% of the historical dialing data is used as the training data, and the remaining 30% of the historical dialing data is used as the test data. After the test data are obtained, the test data are divided according to the historical allocation routes, and test data sets corresponding to the historical allocation routes are obtained, namely the allocation routes of the test samples in the test data sets are the same. Then, a plurality of second time lengths are obtained according to the relevant information of the test samples in the test data set and a preset time length generator.

For step 3, the fulfillment rate condition can be flexibly preset according to the application requirement. For example, the performance rate condition may be: k is more than or equal to 10 percent and less than or equal to 20 percent, and k represents the achievement rate. The number of performance rate conditions and performance rate conditions may be flexibly set according to application requirements, and the invention is not limited herein.

For step 4, the offset duration corresponding to each historical dial route may be determined according to the following process:

a candidate duration set is determined, the candidate duration set comprising a plurality of candidate durations. As an example, the set of candidate durations includes integers between 0 and 23.

And selecting one candidate duration from the candidate duration set, calculating the sum of the second duration and the selected candidate duration, and taking the sum as a third duration. Determining the number of the test samples in the test data set, wherein the third time length is greater than or equal to the actual transfer time length, taking the ratio of the number to the number of all the test samples in the test data set as the test achievement rate, calculating the difference between the third time lengths of all the test samples and the actual transfer time length, and calculating the average of all the differences, wherein the average is the average error. And traversing the candidate duration in the candidate duration set in sequence according to the process, determining the target candidate duration which enables the test performance rate to meet the performance rate condition and has the minimum average error, and taking the target candidate duration as the bias duration corresponding to the performance rate condition.

For example, it is assumed that the test data set S corresponding to the historical allocation route a includes 100 test samples, the actual allocation time of the 100 test samples is 12 hours, the candidate duration set Q is [0, 1, 2, 3 … 23], and the fulfillment rate condition is that k is greater than or equal to 30% and less than or equal to 40%. Through steps 1 and 2, the second time duration of 80 of the 100 test samples is 10 hours, and the second time duration of 20 test samples is 13 hours. And selecting 1 from the candidate time length set, wherein the third time length of 80 test samples is 11, the third time length of 20 test samples is 14, and the calculated test performance rate is that k is 20/100 is 20%, and the performance rate condition is not met. And sequentially calculating the candidate duration in the candidate duration set Q according to the process, wherein the target candidate duration which enables the test performance rate to meet the performance rate condition and has the minimum average error is used as the bias duration corresponding to the performance rate condition.

After determining the offset duration corresponding to each performance rate condition, generating an offset duration list corresponding to the historical allocation route based on the offset duration corresponding to each performance rate condition. Further, a target offset duration may be selected from the list of offset durations corresponding to the target allocation route according to the target allocation route and the target performance rate condition.

For step S104, the sum of the first duration and the target offset duration is used as a transfer duration for transferring the item to be shelved from the originating warehouse to the destination warehouse. Because the first time length predicted by the time length generator has a certain error, the first time length is corrected through the target offset time length corresponding to the target transfer route, so that the transfer time length required by transferring the goods to be placed on the shelf from the starting warehouse to the target warehouse is more accurate, and the placing time obtained according to the transfer time is more accurate.

For step S105, after determining the allocation duration of the to-be-shelved item from the originating warehouse to the destination warehouse, according to the allocation duration and the delivery time, determining the shelving time of the item, and displaying the shelving time to the customer. Namely, the transfer duration is added on the basis of the sending time, and the obtained time is the time for putting on shelf.

According to the method for determining the shelving time of the article, the related information of the article to be shelved and the target performance rate condition corresponding to the article to be shelved are obtained, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target allocation route; obtaining a first time length according to the related information and a preset time length generator; determining target offset duration according to the information of the target transfer route and the target performance rate condition; taking the sum of the first time length and the target offset time length as a transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse; according to the transfer duration, the shelving time of the articles to be shelved is calculated, and the shelving time is output to show the technical means of the shelving time to a user, so that the accuracy of the shelving time of the articles can be improved, and the user experience is improved; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of turnover days of the inventory of the articles is reduced, the problems caused by too short or too long time of manual configuration are reduced, the utilization rate of the storeroom and the turnover rate of the inventory are improved, and the cost is reduced.

In order to make the method for determining the shelf life of the article more clear in the embodiment of the present invention, the following embodiment is described as an example.

(1) Determining related information of the articles to be placed on the shelves:

it is determined that warehouse # 3 under the distribution center (614) in city D lacks 100M items and needs to be allocated from warehouse # 1 under the distribution center (6) in city E. The time for the allocating task of the M article to be issued to a warehouse No. 3 under a distribution center (614) of a city D is 2020-07-0115: 00:00, and the issuing time is determined to be 15 hours; the first class of M articles is food and beverage, and the ID is 1320; the navigation distance from warehouse # 1 under the distribution center (6) in city E to warehouse # 3 under the distribution center (614) in city D is 300 km.

(2) And performing characteristic processing on the related information to obtain characteristic data.

(3) And inputting the characteristic data into a preset time length generator to obtain a first time length corresponding to the article to be shelved of 70 hours.

(4) The target offset time corresponding to the target route (from warehouse # 1 under distribution center (6) in city E to warehouse # 3 under distribution center (614) in city D) is 2 hours.

(5) The transfer time of the goods to be placed on the shelves from the warehouse No. 1 under the distribution center (6) in the city E to the warehouse No. 3 under the distribution center (614) in the city D is 72 hours (namely 70 hours +2 hours).

(6) The time that the allocating task of the M article is issued to a warehouse No. 3 under a distribution center (614) of a city D is 2020-07-0115: 00:00, the allocating time is 72 hours, the estimated shelving time of the article is calculated to be 2020-07-0415: 00:00, and the shelving time is used as commitment time to be displayed to a customer.

Fig. 3 is a flow chart illustrating the main steps of a method for determining the shelf loading time of an article according to another embodiment of the present invention, as shown in fig. 3, the method includes:

step S301: determining related information of an article to be placed on a shelf, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target transfer route;

step S302: performing feature processing on the related information to obtain feature data;

step S303: determining a target performance rate condition corresponding to the article to be shelved;

step S304: inputting the characteristic data into the preset duration generator to obtain a first duration;

step S305: determining a target offset duration according to the target transfer route and the target performance rate condition;

step S306: and taking the sum of the first time length and the offset time length as the transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse.

Step S307: and calculating the shelving time of the articles to be shelved according to the transfer duration, and outputting the shelving time so as to show the shelving time to a user.

The steps S301 to S302 may refer to the embodiment shown in fig. 1, and the present invention is not described herein again. With respect to step S303, in the present embodiment, the target performance rate condition may be selected from a plurality of performance rate conditions when determining the offset duration list. For step S304, the preset duration generator may refer to the preset duration generator in fig. 1.

For step S305, a target offset duration may be selected from the list of offset durations corresponding to the target allocation route according to the target allocation route and the target performance rate condition. Wherein the list of offset durations may be obtained according to the following procedure:

and step 3: determining a plurality of performance rate conditions;

After determining the offset duration corresponding to each performance rate condition, generating an offset duration list corresponding to the historical allocation route based on the offset duration corresponding to each performance rate condition. Further, a target offset duration may be selected from the list of offset durations corresponding to the target allocation route according to the target allocation route and the target performance rate condition. Furthermore, the sum of the first time length and the target offset time length is used as the transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the destination warehouse.

For step S307, after determining the allocation duration for allocating the article to be shelved from the originating warehouse to the destination warehouse, determining the shelving time of the article according to the allocation duration and the delivery time, and displaying the shelving time to the customer. Namely, the transfer duration is added on the basis of the sending time, and the obtained time is the time for putting on shelf.

According to the method for determining the shelving time of the article, provided by the embodiment of the invention, the related information of the article to be shelved and the target performance rate condition corresponding to the article to be shelved are obtained, wherein the related information comprises the information of an originating warehouse, the information of a target warehouse and the information of a target allocation route; obtaining a first time length according to the related information and a preset time length generator; determining target offset duration according to the information of the target transfer route and the target performance rate condition; taking the sum of the first time length and the target offset time length as a transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse; according to the transfer duration, the shelving time of the articles to be shelved is calculated, and the shelving time is output to show the technical means of the shelving time to a user, so that the accuracy of the shelving time of the articles can be improved, and the user experience is improved; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of turnover days of the inventory of the articles is reduced, the problems caused by too short or too long time of manual configuration are reduced, the utilization rate of the storeroom and the turnover rate of the inventory are improved, and the cost is reduced.

Fig. 4 is a schematic diagram of main blocks of an apparatus 400 for determining an article listing time according to an embodiment of the present invention, as shown in fig. 4, the apparatus 400 for determining an article listing time includes:

the information determining module 401 is configured to obtain related information of an article to be shelved and a target performance rate condition corresponding to the article to be shelved, where the related information includes information of an originating warehouse, information of a destination warehouse, and information of a target allocation route;

a first duration determining module 402, configured to obtain a first duration according to the relevant information and a preset duration generator;

a bias duration determining module 403, configured to determine a target bias duration according to the information of the target allocation route and the target performance rate condition;

a transfer duration determining module 404, configured to use a sum of the first duration and the target offset duration as a transfer duration for transferring the to-be-shelved item from the originating warehouse to the destination warehouse;

and the shelving time determining module 405 is configured to calculate the shelving time of the to-be-shelved item according to the allocation duration, and output the shelving time so as to show the shelving time to a user.

the offset duration determination module 403 is further configured to: and selecting a target offset time length from an offset time length list corresponding to the target transfer route according to the information of the target transfer route and the target performance rate condition.

Optionally, the offset duration determining module 403 is further configured to: determining a candidate duration set, wherein the candidate duration set comprises a plurality of candidate durations; for each performance rate condition, traversing candidate durations in the candidate duration set, determining a target candidate duration which enables a test performance rate to meet the performance rate condition and has a minimum average error, and taking the target candidate duration as an offset duration corresponding to the performance rate condition, wherein the test performance rate and the average error are determined according to a third duration and an actual transfer duration of the test sample, and the third duration is the sum of the second duration and the candidate duration.

Optionally, the information determining module 401 is further configured to: performing feature processing on the related information to obtain feature data;

the first duration determining module 402 is further configured to: and obtaining a first time length according to the characteristic data and a preset time length generator.

Optionally, the information determining module 401 is further configured to: processing the related information into a plurality of characteristic fields, and determining the data type of each characteristic field, wherein the data type comprises a character type; the characteristic field of which the data type is character type is subjected to one-hot coding.

The device for determining the shelf loading time of the articles can improve the accuracy of the shelf loading time of the articles and improve the user experience; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of turnover days of the inventory of the articles is reduced, the problems caused by too short or too long time of manual configuration are reduced, the utilization rate of the storeroom and the turnover rate of the inventory are improved, and the cost is reduced.

The device can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.

Fig. 5 illustrates an exemplary system architecture 500 to which the method of determining an item listing time or the apparatus for determining an item listing time of embodiments of the present invention may be applied.

As shown in fig. 5, the system architecture 500 may include

terminal devices

501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the

terminal devices

501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. Various communication client applications may be installed on the

terminal devices

501, 502, 503.

The

terminal devices

501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 505 may be a server providing various services, such as a background management server providing support for item allocation tasks initiated by users using the

terminal devices

501, 502, 503. The background management server can analyze and process the received object allocation task, and feed back a processing result (shelf loading time) to the terminal equipment.

It should be noted that the method for determining the shelf life of the item provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the apparatus for determining the shelf life of the item is generally disposed in the server 505.

It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use in implementing a terminal server device of an embodiment of the present invention is shown. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

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

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a sending module, an obtaining module, a determining module, and a first processing module. The names of these modules do not in some cases constitute a limitation on the unit itself, and for example, the sending module may also be described as a "module that sends a picture acquisition request to a connected server".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise:

According to the technical scheme of the embodiment of the invention, the related information of the to-be-shelved goods and the target performance rate condition corresponding to the to-be-shelved goods are obtained, wherein the related information comprises information of an originating warehouse, information of a target warehouse and information of a target transfer route; obtaining a first time length according to the related information and a preset time length generator; determining target offset duration according to the information of the target transfer route and the target performance rate condition; taking the sum of the first time length and the target offset time length as a transfer time length for transferring the articles to be placed on the shelves from the originating warehouse to the target warehouse; according to the transfer duration, the shelving time of the articles to be shelved is calculated, and the shelving time is output to show the technical means of the shelving time to a user, so that the accuracy of the shelving time of the articles can be improved, and the user experience is improved; under the condition of ensuring a certain performance rate, the error between the calculated shelf-loading time and the actual shelf-loading time is reduced, the number of turnover days of the inventory of the articles is reduced, the problems caused by too short or too long time of manual configuration are reduced, the utilization rate of the storeroom and the turnover rate of the inventory are improved, and the cost is reduced.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method of determining an item listing time, comprising:

2. The method of claim 1, wherein prior to determining the target bias duration, the method further comprises:

determining a plurality of performance rate conditions;

3. The method of claim 2, wherein determining an offset duration corresponding to each performance rate condition based on the actual call durations for the plurality of test samples and the second duration comprises:

4. The method of any of claims 1-3, wherein after determining information about the item to be shelved, the method further comprises: performing feature processing on the related information to obtain feature data;

5. The method of claim 4, wherein performing feature processing on the related information comprises:

processing the related information into a plurality of characteristic fields, and determining the data type of each characteristic field, wherein the data type comprises a character type;

the characteristic field of which the data type is character type is subjected to one-hot coding.

6. The method of claim 4, further comprising obtaining the preset duration generator according to the following procedure:

acquiring a training data set, wherein the training data set comprises relevant information of a plurality of training samples and actual call duration of the plurality of training samples;

carrying out feature processing on the relevant information of the training sample to obtain historical feature data;

constructing a prediction model and a loss function;

and training the prediction model according to the historical characteristic data, the actual call duration of the training samples and the loss function to obtain the preset duration generator.

7. The method of claim 6, wherein the predictive model is a gradient boosting decision tree model;

8. The method according to any of claims 1-3, wherein the related information further comprises one or more of: the method comprises the following steps of issuing time, the number of the articles to be shelved, the type information of the articles to be shelved, the information of an originating distribution center corresponding to an originating warehouse and the information of a target distribution center corresponding to a target warehouse, wherein the issuing time is determined according to the time for sending a task for allocating the articles to be shelved to the originating warehouse.

9. An apparatus for determining a time to put an item on shelf, comprising:

10. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

11. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-8.