CN115545307A

CN115545307A - Goods allocation method, device, equipment and storage medium

Info

Publication number: CN115545307A
Application number: CN202211229558.8A
Authority: CN
Inventors: 王震东; 杨周龙; 孙佳斌
Original assignee: Dongpu Software Co Ltd
Current assignee: Dongpu Software Co Ltd
Priority date: 2022-10-08
Filing date: 2022-10-08
Publication date: 2022-12-30

Abstract

The invention relates to the technical field of logistics, in particular to a goods allocation method, a goods allocation device, goods allocation equipment and a storage medium. The method comprises the steps of obtaining state information corresponding to target goods in a target warehouse; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptance according to the logistics evaluation information, and determining the ideal inventory of the target goods in the target warehouse; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

Description

Goods allocation method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of logistics, in particular to a goods allocation method, a goods allocation device, goods allocation equipment and a storage medium.

Background

Currently, warehouses may be used to supply target goods to docked sellers, who are the subject of selling the target goods. The allocation of goods in a warehouse depends mainly on the daily delivery of goods from the warehouse, i.e. the daily amount of goods transported out of the warehouse.

In the prior art, for the allocation of goods, logistics management personnel generally allocate and transport a corresponding number of goods from other warehouses or distribution centers according to own experience, and for the demand of future goods, the demand is generally predicted manually according to experience. For the goods allocation scheme which adopts the machine learning model for prediction, the considered parameters are mainly the delivery volume, and the market sale condition of sellers in warehouse docking is not considered.

In summary, the prior art has a problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods.

Disclosure of Invention

The present application mainly aims to provide a method, an apparatus, a device and a storage medium for allocating goods, so as to solve the problem that goods cannot be allocated effectively based on predicted demand corresponding to the goods in the prior art.

The first aspect of the present invention provides a cargo deployment method, including: acquiring state information corresponding to target goods in a target warehouse, wherein the state information comprises goods types, inventory quantities, delivery quantities and butt-joint seller identifications; sending a data sharing request to a preset seller information platform according to the butted seller identifier, and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing based on the data sharing request through an editing interface preset in the seller information platform; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand amount corresponding to the target good based on the type of the good, the delivery amount, the sales amount and the market acceptance; determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand; and determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signal.

Optionally, in a first implementation manner of the first aspect of the present invention, the determining a predicted demand amount corresponding to the target good based on the type of the good, the shipment amount, the sales amount, and the market acceptance includes: extracting an delivery quantity change characteristic from daily delivery quantity in the preset time period, and inquiring a reference delivery quantity data record in a pre-obtained reference delivery quantity data set according to the delivery quantity change characteristic; generating an shipment volume reference curve based on the reference shipment volume data record and determining a predicted shipment volume based on the shipment volume reference curve; generating a market reference coefficient based on the cargo type, the sales volume, and the market acceptance, and determining a forecasted demand volume according to the forecasted delivery volume and the market reference coefficient.

Optionally, in a second implementation manner of the first aspect of the present invention, before querying a reference shipment volume data record in a pre-obtained shipment volume data set according to the shipment volume change characteristic, the method further includes: extracting all delivery volume data records from a preset historical delivery volume data set; analyzing the delivery volume data records, and determining the historical delivery volume corresponding to each delivery volume data record; according to the historical shipment volume corresponding to each shipment volume data record, determining the shipment volume interval corresponding to each shipment volume data record in a preset shipment volume interval table; generating an shipment volume data set corresponding to each shipment volume interval based on the shipment volume data record corresponding to each shipment volume interval; calculating the average delivery volume according to the daily delivery volume in the preset time period; determining a corresponding reference delivery volume interval according to the average delivery volume, wherein the reference delivery volume interval is a delivery volume interval in which the average delivery volume falls; and determining the reference delivery volume data set from the delivery volume data sets corresponding to the delivery volume intervals according to the reference delivery volume intervals, wherein the reference delivery volume data set is the delivery volume data set corresponding to the reference delivery volume intervals.

Optionally, in a third implementation manner of the first aspect of the present invention, the method for extracting an shipment volume change feature from daily shipment volumes in the preset time period and querying a reference shipment volume data record in a pre-obtained reference shipment volume data set according to the shipment volume change feature includes: calculating daily variation of the shipment in the time period based on the daily shipment in the preset time period; generating a variation vector based on the daily variation of the shipment quantity, and generating a shipment quantity variation matrix based on the variation vector; calculating a reference daily variation of the shipment corresponding to each shipment data record in the reference shipment data set, wherein the reference daily variation of the shipment is the daily variation of the shipment corresponding to each shipment data record in the reference shipment data set; generating a reference change vector based on the reference daily change amount of the shipment amount, and generating a shipment amount reference change matrix based on the reference change vector; and inquiring a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change matrix, wherein the reference delivery volume data record is a corresponding delivery volume data record when the similarity between the delivery volume reference change matrix and the delivery volume change matrix reaches a preset threshold value.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the generating an shipment volume reference curve based on the reference shipment volume data record includes: extracting reference time and reference shipment quantity corresponding to the reference time from the reference shipment quantity data record; determining a prediction time span according to the time period, and selecting prediction time from the reference time based on the prediction time span; and generating an shipment quantity reference curve based on the predicted time and the reference shipment quantity corresponding to the predicted time.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the generating a market reference coefficient based on the type of goods, the sales amount, and the market acceptance, where the sales amount is a daily sales amount in a preset time period, includes: extracting reference sales data from a preset historical sales data set according to the goods type, and generating a reference sales data set based on the reference sales data; extracting sales volume change characteristics from daily sales volume in the preset time period, and inquiring reference sales volume data records in the reference sales data set according to the sales volume change characteristics; generating a sales reference curve based on the reference sales data record and determining a predicted sales based on the sales reference curve; calculating the average sales volume in the time period according to the daily sales volume in the preset time period, and calculating the proportion between the predicted sales volume and the average sales volume; and generating a sales prediction coefficient according to the proportion, and adjusting the sales prediction coefficient according to the market acceptance to obtain a market reference coefficient.

Optionally, in a sixth implementation manner of the first aspect of the present invention, the state information further includes a warehouse identifier, and the determining the goods allocation information based on the inventory amount and the ideal inventory amount includes: inquiring an associated warehouse identifier from a preset warehouse information table according to the warehouse identifier, and acquiring an associated inventory amount corresponding to the associated warehouse according to the associated warehouse identifier, wherein the associated warehouse identifier is a warehouse identifier corresponding to the associated warehouse having a goods transportation traffic relation with the target warehouse, and the associated warehouse is a warehouse having a goods transportation traffic relation with the target warehouse; determining a goods allocation quantity according to the stock quantity and the ideal stock quantity, and determining goods transportation quantity corresponding to each associated warehouse according to the associated stock quantity and the goods allocation quantity; and generating goods allocation information based on the associated warehouse identifications corresponding to the associated warehouses and the goods transportation volumes corresponding to the associated warehouses.

A second aspect of the present invention provides a cargo deployment apparatus, comprising: the system comprises an acquisition module, a storage module and a delivery module, wherein the acquisition module is used for acquiring state information corresponding to target goods in a target warehouse, and the state information comprises goods types, stock quantity, delivery quantity and butt-joint seller identifiers; the receiving module is used for sending a data sharing request to a preset seller information platform according to the butted seller identifier and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing through an editing interface preset in the seller information platform based on the data sharing request; the first determining module is used for extracting sales volume, sales evaluation information and logistics evaluation information from the shared data and determining market acceptance corresponding to the target goods based on the sales evaluation information; a second determining module, configured to determine a predicted demand amount corresponding to the target good based on the type of the good, the shipment amount, the sales amount, and the market acceptance; a third determining module, configured to determine, according to the logistics evaluation information, a logistics acceptance degree corresponding to the target goods, and determine, based on the logistics acceptance degree and the predicted demand amount, an ideal inventory amount of the target goods in the target warehouse; and the allocation module is used for determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signal.

Optionally, in a first implementation manner of the second aspect of the present invention, the second determining module includes: the query unit is used for extracting the delivery volume change characteristics from the daily delivery volume in the preset time period and querying a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change characteristics; a first determination unit for generating an shipment reference curve based on a reference shipment data record and determining a predicted shipment based on the shipment reference curve; and the second determining unit is used for generating a market reference coefficient based on the goods type, the sales volume and the market acceptance, and determining the predicted demand volume according to the predicted delivery volume and the market reference coefficient.

Optionally, in a second implementation manner of the second aspect of the present invention, the second determining module further includes a third determining unit, configured to extract all shipment data records from a preset historical shipment data set; analyzing the delivery volume data records, and determining the historical delivery volume corresponding to each delivery volume data record; according to the historical shipment volume corresponding to each shipment volume data record, determining the shipment volume interval corresponding to each shipment volume data record in a preset shipment volume interval table; generating an shipment volume data set corresponding to each shipment volume interval based on the shipment volume data records corresponding to each shipment volume interval; calculating the average delivery volume according to the daily delivery volume in the preset time period; determining a corresponding reference shipment volume interval according to the average shipment volume, wherein the reference shipment volume interval is the shipment volume interval in which the average shipment volume falls; and determining the reference delivery volume data set from the delivery volume data sets corresponding to the delivery volume intervals according to the reference delivery volume intervals, wherein the reference delivery volume data set is the delivery volume data set corresponding to the reference delivery volume intervals.

Optionally, in a third implementation manner of the second aspect of the present invention, the query unit is further configured to calculate a daily variation of the shipment volume in the time period based on the daily shipment volume in the preset time period; generating a variation vector based on the daily variation of the delivery amount, and generating a delivery amount variation matrix based on the variation vector; calculating a reference daily variation of the shipment corresponding to each shipment data record in the reference shipment data set, wherein the reference daily variation of the shipment is the daily variation of the shipment corresponding to each shipment data record in the reference shipment data set; generating a reference change vector based on the reference daily change amount of the shipment amount, and generating a shipment amount reference change matrix based on the reference change vector; and inquiring a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change matrix, wherein the reference delivery volume data record is a corresponding delivery volume data record when the similarity between the delivery volume reference change matrix and the delivery volume change matrix reaches a preset threshold value.

Optionally, in a fourth implementation manner of the second aspect of the present invention, the first determining unit is further configured to extract a reference time and a reference shipment amount corresponding to the reference time from the reference shipment amount data record; determining a prediction time span according to the time period, and selecting prediction time from the reference time based on the prediction time span; and generating an shipment quantity reference curve based on the predicted time and the reference shipment quantity corresponding to the predicted time.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the second determining unit is further configured to extract reference sales data from a preset historical sales data set according to the type of the goods, and generate a reference sales data set based on the reference sales data; extracting sales volume change characteristics from daily sales volume in the preset time period, and inquiring a reference sales volume data record in the reference sales data set according to the sales volume change characteristics; generating a sales reference curve based on the reference sales data record, and determining a predicted sales based on the sales reference curve; calculating the average sales volume in the time period according to the daily sales volume in the preset time period, and calculating the proportion between the predicted sales volume and the average sales volume; and generating a sales prediction coefficient according to the proportion, and adjusting the sales prediction coefficient according to the market acceptance to obtain a market reference coefficient.

Optionally, in a sixth implementation manner of the second aspect of the present invention, the blending module includes: an obtaining unit, configured to query an associated warehouse identifier from a preset warehouse information table according to the warehouse identifier, and obtain an associated inventory amount corresponding to an associated warehouse according to the associated warehouse identifier, where the associated warehouse identifier is a warehouse identifier corresponding to an associated warehouse having a freight traffic relationship with the target warehouse, and the associated warehouse is a warehouse having a freight traffic relationship with the target warehouse; a fourth determining unit, configured to determine a cargo allocation amount according to the inventory amount and the ideal inventory amount, and determine a cargo transportation amount corresponding to each associated warehouse according to the associated inventory amount and the cargo allocation amount; and the generation unit is used for generating the goods allocation information based on the associated warehouse identification corresponding to each associated warehouse and the goods transportation amount corresponding to each associated warehouse.

A third aspect of the present invention provides a computer apparatus comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the computer device to perform the steps of the cargo deployment method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the above-mentioned goods allocation method.

According to the technical scheme, the method specifically comprises the steps of obtaining state information corresponding to target goods in a target warehouse; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; in the above, the shipment volume change feature is extracted from the daily shipment volume in the preset time period, and the corresponding data record is extracted from the historical data based on the shipment volume change feature; generating an shipment reference curve based on the data record, and predicting the shipment based on the shipment reference curve; generating a market reference coefficient based on the goods type, the sales volume and the market acceptance, and adjusting the predicted delivery volume to obtain a predicted demand volume, so that the accuracy of prediction is improved; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

Drawings

FIG. 1 is a schematic diagram of a cargo deployment method according to a first embodiment of the present invention;

FIG. 2 is a schematic diagram of a cargo allocation method according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a third embodiment of a cargo allocation method according to an embodiment of the invention;

FIG. 4 is a schematic diagram of an embodiment of a cargo deployment apparatus according to the present invention;

FIG. 5 is a schematic view of another embodiment of a cargo deployment apparatus according to the present invention;

fig. 6 is a schematic diagram of an embodiment of a computer device in the embodiment of the present invention.

Detailed Description

In order to solve the problem that goods cannot be effectively deployed based on predicted demand corresponding to the goods in the prior art, the application provides a goods deployment method, a goods deployment device, goods deployment equipment and a storage medium. The method comprises the steps of obtaining state information corresponding to target goods in a target warehouse; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; in the above, the shipment volume change feature is extracted from the daily shipment volume in the preset time period, and the corresponding data record is extracted from the historical data based on the shipment volume change feature; generating an shipment reference curve based on the data record, and predicting the shipment based on the shipment reference curve; generating a market reference coefficient based on the cargo type, the sales volume and the market acceptance, and adjusting the predicted delivery volume to obtain the predicted demand volume, so that the accuracy of prediction is improved; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Moreover, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For understanding, the following describes a specific process of an embodiment of the present invention, and referring to fig. 1, a first embodiment of a cargo deployment method according to an embodiment of the present invention includes the following steps:

101. acquiring state information corresponding to target goods in a target warehouse, wherein the state information comprises goods types, inventory quantities, delivery quantities and butt-joint seller identifications;

in this step, the status information further includes a warehouse identifier;

in this step, the delivery amount includes a daily delivery amount within a preset time period, for example, when the time period is set to 30 natural days, the delivery amount is a target quantity of goods transported from the target warehouse every day in 30 natural days.

In practical application, the identification of the butt seller is an identification corresponding to a seller having a relationship of goods transportation with the target warehouse, and the seller is a main body selling the target goods.

For this step, it can be specifically realized by the following means:

and reading state information corresponding to the target goods in the target warehouse from a preset warehouse information table, wherein the state information at least comprises goods types, inventory quantity, delivery quantity, butt seller identification and logistics evaluation information.

In practical applications, the warehouse information table further includes the following fields:

daily trend plot, left ordinate: ticket amount, unit: w; right ordinate: weight, unit: t; b. and (4) optional: total (default), ticket amount, weight. (1) When all the choices are selected, showing the 7 day ticket amount (actual value + predicted value) + the weight (actual value + predicted value); (2) when the ticket amount is selected, only 7-day ticket amounts (actual value + predicted value) are displayed; (3) when weight is selected, only 7 day weight (actual value + predicted value) is shown; c. the weight (actual value + predicted value) or the ticket amount (actual value + predicted value) of a certain day or all the weights and the ticket amount are displayed in a clicking mode; 2) List: a. no nationwide (total) and large-area totals; b. defaulting the current sites (allocated) to be sequenced according to the sequence under the standard large area, and under the condition that the current sites are the same, saying the subordinate sites to be sequenced according to the sequence under the standard large area; c. and (6) predicting.

Ticket amount (W): prediction A shows the predicted ticket quantity in the query time range, unit: w, rounding and rounding; and the actual B displays the actual ticket quantity in the query time range, unit: w, rounding and rounding; if the query time range is the query operation current day, the actual ticket quantity has no value, and the "-" is displayed, and the deviation C = (A-B)/B is displayed in the same way; the deviation C = (A-B)/B shows the deviation of ticket quantity in the query time range; calculating the formula: c = (a-B)/B = (a-B)/100%, rounding, and the numerical value is positive number or 0, then "+" is displayed before the numerical value and the font color is green, otherwise "-" is displayed before the numerical value.

Order weight (t): and D, displaying the predicted ticket weight in the query time range in unit: t, rounding off and rounding; and the actual E displays the actual ticket weight in the query time range, unit: t, rounding off and rounding; if the query time range is the query operation current day, the actual ticket weight has no value, and the "-" is displayed, and the deviation F = (D-E)/E is displayed in the same way as "-"; the deviation F = (D-E)/E shows the weight deviation of the ticket within the query time range; calculating the formula: f = (D-E)/E100%, rounding, and a numeric value is positive or 0, then "+" is displayed before the numeric value and the font color is green, otherwise "-" is displayed before the numeric value.

102. Sending a data sharing request to a preset seller information platform according to the identification of the butted seller, and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing a preset editing interface in the seller information platform based on the data sharing request;

in this step, the shared data includes at least one of sales volume, sales evaluation information, and logistics evaluation information.

In practical application, the logistics evaluation information can be edited by the seller through an editing interface preset in the seller information platform based on the condition that the target goods are transported through the target warehouse.

103. Extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information;

in this step, the determining the market acceptance corresponding to the target good based on the sales evaluation information includes:

extracting the scores of all the buyers for the target goods from the sales evaluation information;

and calculating the average value of the scores to obtain the market acceptance corresponding to the target goods.

104. Determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance;

for this step, it can be specifically realized by the following means:

extracting the shipment volume change characteristics from the daily shipment volume in the preset time period;

inquiring a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change characteristics, wherein the reference delivery volume data set can be extracted from a preset historical data set based on the cargo type;

generating an shipment volume reference curve based on the reference shipment volume data record and determining a predicted shipment volume based on the shipment volume reference curve;

a market reference coefficient is generated based on the cargo type, the sales volume, and the market acceptance, and a forecasted demand is determined from the forecasted shipment and the market reference coefficient, e.g., the forecasted shipment is multiplied by the market reference coefficient to obtain a forecasted demand.

In practical application, this step can be realized by the following steps:

and predicting the goods quantity based on the goods type, the shipment quantity, the sales quantity and the market acceptance according to a goods quantity prediction model obtained by pre-training to obtain the predicted demand quantity.

Specifically, the cargo quantity prediction model may be trained by:

s1, acquiring characteristic data X and actual cargo quantity data Y of all flow directions of historical N days from a database;

s2, preprocessing the data obtained in the S1 to obtain ideal characteristic data X 'and cargo quantity data Y', dividing training sets Xtrain and Ytrain, and verifying sets Xvalid and Yvalid;

s3, constructing a routing mapping matrix A;

s4, selecting a machine learning model, and customizing a loss function of the machine learning model into a loss function of the integrated line segment error;

s5, training the neural network model by using the training sets Xtrain and Ytrain to obtain a model f;

s6, inputting the Xvalid into the model f, and outputting and calculating a flow direction error and a line segment error;

and S7, selecting different machine learning models to train in the S4-S6, and selecting the model with the minimum segment error to obtain a cargo quantity prediction model.

105. Determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand;

in this step, the determining the market acceptance corresponding to the target good according to the logistics evaluation information includes:

extracting the scores of all buyers for the target goods from the logistics evaluation information;

106. And determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at the preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate the goods through the allocation control signal.

In the step, the distribution equipment comprises at least one of a goods conveyor belt, a goods conveying pipe, a goods conveying vehicle, an automatic driving transport vehicle and a transport robot;

for this step, it can be specifically realized by the following means:

inquiring an associated warehouse identifier from a preset warehouse information table according to the warehouse identifier, and acquiring an associated inventory amount corresponding to the associated warehouse according to the associated warehouse identifier, wherein the associated warehouse identifier is a warehouse identifier corresponding to the associated warehouse having a goods transportation traffic relation with the target warehouse, and the associated warehouse is a warehouse having a goods transportation traffic relation with the target warehouse;

determining a goods allocation quantity according to the stock quantity and the ideal stock quantity, and determining goods transportation quantity corresponding to each associated warehouse according to the associated stock quantity and the goods allocation quantity;

generating goods allocation information based on the associated warehouse identification corresponding to each associated warehouse and the goods transportation amount corresponding to each associated warehouse;

inquiring a target position corresponding to the target warehouse from the warehouse information table according to the warehouse identification;

inquiring an associated position and an equipment identifier corresponding to each associated warehouse from the warehouse information table according to the associated warehouse identifier corresponding to each associated warehouse, wherein the associated position is a position for carrying out goods transportation in the associated warehouse;

generating a control instruction set corresponding to the allocating device according to the associated position, the target position and the device identifier, and generating an allocating control signal based on the control instruction set;

the allocation control signal is sent to the corresponding allocating equipment, and the corresponding allocating equipment is controlled to transport goods through the allocation control signal so as to realize goods allocation;

specifically, the generating a control instruction set corresponding to the allocating device according to the associated position, the target position, the freight transportation amount, and the device identifier includes:

inquiring corresponding single transportation amount in a preset equipment information table according to the equipment identifier, and determining the transportation times according to the single transportation amount and the goods transportation amount;

generating a transportation path according to the associated position, the target position and the transportation times;

inquiring a corresponding instruction coding mode in a preset instruction coding table by taking the equipment identifier as an index;

and coding the transportation path into a corresponding instruction according to the instruction coding mode, and generating a control instruction set based on the instruction.

By implementing the method, state information corresponding to the target goods in the target warehouse is obtained; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; in the above, the shipment volume change feature is extracted from the daily shipment volume in the preset time period, and the corresponding data record is extracted from the historical data based on the shipment volume change feature; generating an shipment reference curve based on the data record, and predicting the shipment based on the shipment reference curve; generating a market reference coefficient based on the cargo type, the sales volume and the market acceptance, and adjusting the predicted delivery volume to obtain the predicted demand volume, so that the accuracy of prediction is improved; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

Referring to fig. 2, a second embodiment of the cargo allocation method according to the embodiment of the present invention includes the following steps:

201. acquiring state information corresponding to target goods in a target warehouse, wherein the state information comprises goods types, inventory quantities, delivery quantities and butt-joint seller identifications;

in this step, the status information further includes a warehouse identifier;

in this step, the delivery amount includes a daily delivery amount in a preset time period, for example, when the time period is set to 7 natural days, the delivery amount is a daily delivery amount corresponding to each day of the 7 natural days.

In practical application, the identification of the butt-joint seller is an identification corresponding to a seller who has a goods transportation transaction relation with the target warehouse, and the seller is a main body selling the target goods;

for this step, it can be specifically realized by the following means:

202. Sending a data sharing request to a preset seller information platform according to the identification of the butted seller, and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing a preset editing interface in the seller information platform based on the data sharing request;

203. extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information;

in practical application, the sales evaluation information can be edited based on the actual situation of the target goods through an editing interface preset in the seller information platform.

204. Determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance;

for this step, it can be specifically realized by the following manner:

extracting an shipment quantity change characteristic from daily shipment quantities within the preset time period, and inquiring a reference shipment quantity data record in a pre-obtained reference shipment quantity data set according to the shipment quantity change characteristic;

generating a market reference coefficient based on the cargo type, the sales volume, and the market acceptance, and determining a forecasted demand volume according to the forecasted delivery volume and the market reference coefficient.

Further, the shipment volume data set may be obtained by:

extracting all shipment data records from a preset historical shipment data set; analyzing the delivery volume data records, and determining the historical delivery volume corresponding to each delivery volume data record; according to the historical shipment volume corresponding to each shipment volume data record, determining the shipment volume interval corresponding to each shipment volume data record in a preset shipment volume interval table; generating an shipment volume data set corresponding to each shipment volume interval based on the shipment volume data records corresponding to each shipment volume interval; calculating the average delivery volume according to the daily delivery volume in the preset time period; determining a corresponding reference shipment volume interval according to the average shipment volume, wherein the reference shipment volume interval is the shipment volume interval in which the average shipment volume falls; and determining the reference delivery volume data set from the delivery volume data sets corresponding to the delivery volume intervals according to the reference delivery volume intervals, wherein the reference delivery volume data set is the delivery volume data set corresponding to the reference delivery volume intervals.

Further, the process of extracting the shipment volume change feature from the daily shipment volume in the preset time period and querying a reference shipment volume data record in a pre-obtained reference shipment volume data set according to the shipment volume change feature includes:

calculating a daily variation of the shipment amount in the time period based on the daily shipment amount in the preset time period, for example, the daily variation may be obtained by subtracting the daily shipment amount of the previous day from the daily shipment amount of each day in the time period, and for the first day in the time period, the corresponding daily variation may be set to 0;

generating a variation vector based on the daily variation of the shipment and generating a shipment variation matrix based on the variation vector, for example, taking an absolute value of a value obtained by subtracting the daily shipment on the previous day from the daily shipment on each day in the time period as a modulus of the variation vector, and taking a sign of a value obtained by subtracting the daily shipment on the previous day from the daily shipment on each day in the time period as a direction of the variation vector;

calculating a reference daily variation of the shipment corresponding to each shipment data record in the reference shipment data set, wherein the reference daily variation of the shipment is the daily variation of the shipment corresponding to each shipment data record in the reference shipment data set;

generating a reference change vector based on the reference daily change amount of the shipment amount, and generating a shipment amount reference change matrix based on the reference change vector;

inquiring a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change matrix, wherein the reference delivery volume data record is a corresponding delivery volume data record when the similarity between the delivery volume reference change matrix and the delivery volume change matrix reaches a preset threshold value;

specifically, the querying a reference shipment volume data record in a pre-obtained reference shipment volume data set according to the shipment volume change matrix includes:

comparing each delivery quantity reference change matrix with the delivery quantity change matrix to obtain corresponding similarity;

and querying a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the similarity, wherein the reference delivery volume data record is a delivery volume data record corresponding to the similarity reaching a preset threshold, for example, the preset threshold may be set to 0.9.

Further, the process of generating an shipment reference curve based on the reference shipment data record and determining a predicted shipment based on the shipment reference curve includes:

extracting a reference shipment amount corresponding to a reference time and the reference time from the reference shipment amount data record, for example, extracting a shipment amount corresponding to a history date from the reference shipment amount data record, determining a reference time based on the history date, and determining a reference shipment amount based on the shipment amount corresponding to the history date;

determining a predicted time span according to the time period, for example, if the time period is preset 7 natural days, the predicted time span may be set to 8 days;

selecting a prediction time from the reference times based on the prediction time span, for example, if the prediction time span is 8 days, the prediction time is the last 8 days of all the reference times;

generating an shipment amount reference curve based on the predicted time and a reference shipment amount corresponding to the predicted time, for example, taking the predicted time as a value of an abscissa, taking the reference shipment amount corresponding to the predicted time as a value of an ordinate, and generating the shipment amount reference curve in a preset planar rectangular coordinate system based on the value of the abscissa and the value of the ordinate;

determining a predicted time point in a preset time correspondence table according to the last time point in the time period, and determining a reference shipment volume in the shipment volume reference curve based on the predicted time point;

further, the time correspondence table may be obtained by:

extracting a corresponding reference time period from the reference delivery data record according to the delivery reference change matrix;

adjusting the reference time period according to the time span, for example, if the time span is 8 days and the reference time period is 20/8/2022/8/30/2022/8/2022, adjusting the reference time period to 27/8/20/2022/8/2022;

and determining a correspondence relationship between the time points from the time period and the reference time period, and generating the time correspondence table based on the correspondence relationship between the time points, for example, if the time period is from 20 days at 9 months in 2022 years to 27 days at 9 months in 2022 years, and the reference time period is from 20 days at 8 months in 2022 years to 27 days at 8 months in 2022 years, each of 20 days at 8 months in 2022 years to 27 days at 8 months in 2022 years in the reference time is sequentially made to correspond to each of 20 days at 9 months in 2022 years to 27 days at 9 months in 2022 years in the time period.

Further, the sales volume is daily sales volume within a preset time period, and the generating a market reference coefficient based on the type of goods, the sales volume and the market acceptance comprises:

extracting reference sales data from a preset historical sales data set according to the goods type, and generating a reference sales data set based on the reference sales data; extracting sales volume change characteristics from daily sales volume in the preset time period, and inquiring reference sales volume data records in the reference sales data set according to the sales volume change characteristics; generating a sales reference curve based on the reference sales data record, and determining a predicted sales based on the sales reference curve; calculating the average sales volume in the time period according to the daily sales volume in the preset time period, and calculating the proportion between the predicted sales volume and the average sales volume; and generating a sales prediction coefficient according to the proportion, and adjusting the sales prediction coefficient according to the market acceptance to obtain a market reference coefficient.

205. Determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand;

in this step, the process of determining the ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the forecast demand includes:

determining a corresponding logistics acceptance threshold value according to the cargo type;

judging whether the logistics acceptance is greater than a corresponding logistics acceptance threshold value;

if yes, determining the ideal stock quantity of the target goods in the target warehouse according to the predicted demand quantity;

and if the actual inventory quantity of the target goods in the target warehouse is not larger than the target inventory quantity, calculating the proportion of the logistics acceptance degree relative to the logistics acceptance degree threshold value, and multiplying the predicted demand quantity by the proportion to obtain the ideal inventory quantity of the target goods in the target warehouse.

206. And determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at the preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate the goods through the allocation control signal.

For this step, it can be specifically realized by the following manner:

inquiring an associated warehouse identifier from a preset warehouse information table according to the warehouse identifier, and acquiring an associated inventory amount corresponding to the associated warehouse according to the associated warehouse identifier, wherein the associated warehouse identifier is a warehouse identifier corresponding to the associated warehouse having a goods transportation traffic relation with the target warehouse, and the associated warehouse is a warehouse having a goods transportation traffic relation with the target warehouse; determining a goods allocation quantity according to the stock quantity and the ideal stock quantity, and determining goods transportation quantity corresponding to each associated warehouse according to the associated stock quantity and the goods allocation quantity; and generating goods allocation information based on the associated warehouse identifications corresponding to the associated warehouses and the goods transportation volumes corresponding to the associated warehouses.

By implementing the method, state information corresponding to the target goods in the target warehouse is obtained; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; in the above, the shipment volume change feature is extracted from the daily shipment volume in the preset time period, and the corresponding data record is extracted from the historical data based on the shipment volume change feature; generating an shipment reference curve based on the data record, and predicting the shipment based on the shipment reference curve; in the prediction process, determining a prediction time span according to the time period, selecting prediction time from the reference time based on the prediction time span, improving the prediction accuracy, generating a market reference coefficient based on the goods type, the sales volume and the market acceptance, adjusting the predicted delivery volume to obtain the predicted demand volume, and further improving the prediction accuracy; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

Referring to fig. 3, a third embodiment of the cargo allocation method according to the embodiment of the present invention includes the following steps:

301. acquiring state information corresponding to target goods in a target warehouse, wherein the state information comprises goods types, stock quantity, delivery quantity and butt-joint seller identifiers;

in this step, the status information further includes a warehouse identifier;

in this step, the shipment volume is a daily shipment volume within a preset time period.

302. Sending a data sharing request to a preset seller information platform according to the identification of the butted seller, and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing a preset editing interface in the seller information platform based on the data sharing request;

303. extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information;

in this step, the sales volume is a daily sales volume within a preset time period.

304. Determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance;

for this step, it can be specifically realized by the following means:

extracting an shipment quantity change characteristic from daily shipment quantities within the preset time period, and inquiring a reference shipment quantity data record in a pre-obtained reference shipment quantity data set according to the shipment quantity change characteristic; generating an shipment volume reference curve based on the reference shipment volume data record and determining a predicted shipment volume based on the shipment volume reference curve; generating a market reference coefficient based on the cargo type, the sales volume, and the market acceptance, and determining a forecasted demand volume according to the forecasted delivery volume and the market reference coefficient.

In practical application, this step can be realized by the following steps:

extracting sales volume change characteristics from daily sales volume in the preset time period, and inquiring reference sales volume data records in a pre-obtained reference sales volume data set according to the sales volume change characteristics;

generating a sales reference curve based on the reference sales data record and determining a predicted sales based on the sales reference curve;

and determining the predicted demand according to the predicted sales volume and the market acceptance.

Further, the reference sales data set may be obtained by:

extracting all sales volume data records from a preset historical sales volume data set;

analyzing the sales volume data records, and determining historical sales volumes corresponding to the sales volume data records;

according to the historical sales volume corresponding to each sales volume data record, determining the sales volume interval corresponding to each sales volume data record in a preset sales volume interval table;

generating a sales volume data set corresponding to each sales volume interval based on the sales volume data records corresponding to each sales volume interval;

calculating average sales volume according to daily sales volume in the preset time period;

determining a corresponding reference sales volume interval according to the average sales volume, wherein the reference sales volume interval is a sales volume interval in which the average sales volume falls;

and determining the reference sales volume data set from the sales volume data sets corresponding to the sales volume intervals according to the reference sales volume intervals, wherein the reference sales volume data set is the sales volume data set corresponding to the reference sales volume interval.

Further, the method for extracting the sales variation feature from the daily sales in the preset time period and querying the reference sales data record in the pre-obtained reference sales data set according to the sales variation feature includes:

calculating the daily variation of the sales in the time period based on the daily sales in the preset time period;

generating a variation vector based on the daily variation of the sales volume, and generating a sales volume variation matrix based on the variation vector;

calculating a reference daily variation of the sales volume corresponding to each sales volume data record in the reference sales volume data set, wherein the reference daily variation of the sales volume is the daily variation of the sales volume corresponding to each sales volume data record in the reference sales volume data set;

generating a reference change vector based on the reference daily change amount of the sales volume, and generating a sales volume reference change matrix based on the reference change vector;

and inquiring a reference sales data record in a reference sales data set obtained in advance according to the sales variation matrix, wherein the reference sales data record is a corresponding sales data record when the similarity between the sales reference variation matrix and the sales variation matrix reaches a preset threshold value.

Further, the generating a sales reference curve based on the reference sales data record includes:

extracting reference sales corresponding to reference time and reference time from the reference sales data record;

determining a prediction time span according to the time period, and selecting prediction time from the reference time based on the prediction time span;

and generating a sales reference curve based on the predicted time and the reference sales corresponding to the predicted time.

Further, said determining a forecasted demand based on said forecasted sales and said market acceptance comprises:

determining a corresponding market acceptance threshold value according to the cargo type;

judging whether the market acceptance is greater than a corresponding market acceptance threshold value;

if so, determining the predicted demand of the target goods in the target warehouse according to the predicted sales volume;

if the market acceptance degree is not larger than the threshold value, calculating the proportion of the market acceptance degree relative to the threshold value of the market acceptance degree, and multiplying the predicted sales volume by the proportion to obtain the predicted demand volume of the target goods in the target-oriented warehouse.

305. Determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand;

for this step, it can be specifically realized by the following manner:

determining a corresponding current logistics information table according to the cargo type;

determining a corresponding seasonal influence factor in a corresponding seasonal logistics information table according to the time period;

multiplying the current impact factor and the logistics acceptance to obtain an adjustment parameter;

the predicted demand amount is adjusted based on the adjustment parameter to obtain an ideal inventory amount of the target goods in the target warehouse, for example, the adjustment parameter and the predicted demand amount are added to obtain the ideal inventory amount, and the adjustment parameter and the predicted demand amount may be multiplied to obtain the ideal inventory amount.

306. And determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at the preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate the goods through the allocation control signal.

For this step, it can be specifically realized by the following manner:

subtracting the stock quantity from the ideal stock quantity to obtain a blending quantity;

inquiring a deployment position corresponding to the target goods and a target position corresponding to the target warehouse according to the warehouse information table;

generating a deployment path based on the deployment position and the target position, wherein the deployment path is a path in which the deployment position points to the target position;

generating a control instruction set corresponding to the allocating equipment based on the allocating path, and generating allocating control signals based on the control instruction set;

and sending the allocation control signal to corresponding allocation equipment, and controlling the corresponding allocation equipment to transport goods through the allocation control signal so as to realize goods allocation.

By implementing the method, state information corresponding to the target goods in the target warehouse is obtained; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; in the above, the shipment volume change feature is extracted from the daily shipment volume in the preset time period, and the corresponding data record is extracted from the historical data based on the shipment volume change feature; generating an shipment reference curve based on the data record, and predicting the shipment based on the shipment reference curve; in practical application, the sales volume change characteristics can be extracted from the daily sales volume in the preset time period, and corresponding data records can be extracted from historical data based on the sales volume change characteristics; a sales volume reference curve is generated based on the data record, the sales volume is predicted based on the sales volume reference curve, and the predicted demand is determined according to the predicted sales volume and the market acceptance, so that the prediction accuracy is improved; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

With reference to fig. 4, the cargo deployment method in the embodiment of the present invention is described above, and a cargo deployment device in the embodiment of the present invention is described below, where the cargo deployment device in the embodiment of the present invention includes:

an obtaining module 401, configured to obtain status information corresponding to a target item in a target warehouse, where the status information includes an item type, a stock quantity, a delivery quantity, and a docking seller identifier;

a receiving module 402, configured to send a data sharing request to a preset seller information platform according to the identifier of the butted seller, and receive shared data sent by the seller information platform, where the shared data is obtained by editing based on the data sharing request through an editing interface preset in the seller information platform;

a first determining module 403, configured to extract sales volume, sales evaluation information, and logistics evaluation information from the shared data, and determine market acceptance corresponding to the target good based on the sales evaluation information;

a second determining module 404, configured to determine a predicted demand amount corresponding to the target cargo based on the cargo type, the shipment amount, the sales amount, and the market acceptance;

a third determining module 405, configured to determine a logistics acceptance degree corresponding to the target goods according to the logistics evaluation information, and determine an ideal inventory amount of the target goods in the target warehouse based on the logistics acceptance degree and the predicted demand amount;

and the allocating module 406 is configured to determine cargo allocating information based on the inventory amount and the ideal inventory amount, generate an allocating control signal for a preset allocating device based on the cargo allocating information, and control the corresponding allocating device to allocate the cargo through the allocating control signal.

By implementing the device, state information corresponding to the target goods in the target warehouse is acquired; extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information; determining a predicted demand corresponding to the target goods based on the goods type, the shipment quantity, the sales quantity and the market acceptance; determining logistics acceptability corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptability and the predicted demand; determining goods allocation information based on the inventory amount and the ideal inventory amount, generating allocation control signals aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signals; in the above, the shipment volume change feature is extracted from the daily shipment volume in the preset time period, and the corresponding data record is extracted from the historical data based on the shipment volume change feature; generating an shipment reference curve based on the data record, and predicting the shipment based on the shipment reference curve; generating a market reference coefficient based on the cargo type, the sales volume and the market acceptance, and adjusting the predicted delivery volume to obtain the predicted demand volume, so that the accuracy of prediction is improved; therefore, the problem that goods cannot be effectively allocated based on the predicted demand corresponding to the goods in the prior art is solved.

Referring to fig. 5, another embodiment of the cargo deployment device according to the embodiment of the present invention includes:

In this embodiment, the second determining module 404 includes:

a third determining unit 4041, configured to extract all delivery volume data records from a preset historical delivery volume data set; analyzing the delivery volume data records, and determining the historical delivery volume corresponding to each delivery volume data record; according to the historical shipment volume corresponding to each shipment volume data record, determining the shipment volume interval corresponding to each shipment volume data record in a preset shipment volume interval table; generating an shipment volume data set corresponding to each shipment volume interval based on the shipment volume data records corresponding to each shipment volume interval; calculating the average delivery volume according to the daily delivery volume in the preset time period; determining a corresponding reference delivery volume interval according to the average delivery volume, wherein the reference delivery volume interval is a delivery volume interval in which the average delivery volume falls; determining a reference shipment volume data set from the shipment volume data sets corresponding to the shipment volume intervals according to the reference shipment volume intervals, wherein the reference shipment volume data set is the shipment volume data set corresponding to the reference shipment volume intervals;

the query unit 4042 is configured to extract an shipment volume change feature from the daily shipment volume within the preset time period, and query a reference shipment volume data record in a pre-obtained reference shipment volume data set according to the shipment volume change feature;

the query unit 4042 is further configured to calculate a daily variation of the shipment volume in the time period based on the daily shipment volume in the preset time period; generating a variation vector based on the daily variation of the delivery amount, and generating a delivery amount variation matrix based on the variation vector; calculating a reference daily variation of the shipment corresponding to each shipment data record in the reference shipment data set, wherein the reference daily variation of the shipment is the daily variation of the shipment corresponding to each shipment data record in the reference shipment data set; generating a reference change vector based on the reference daily change quantity of the delivery quantity, and generating a delivery quantity reference change matrix based on the reference change vector; inquiring a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change matrix, wherein the reference delivery volume data record is a corresponding delivery volume data record when the similarity between the delivery volume reference change matrix and the delivery volume change matrix reaches a preset threshold value;

a first determination unit 4043 configured to generate an shipment volume reference curve based on a reference shipment volume data record, and determine a predicted shipment volume based on the shipment volume reference curve;

the first determining unit 4043 is further configured to extract a reference shipment volume corresponding to a reference time and the reference time from the reference shipment volume data record; determining a prediction time span according to the time period, and selecting prediction time from the reference time based on the prediction time span; generating an shipment volume reference curve based on the predicted time and a reference shipment volume corresponding to the predicted time;

a second determining unit 4044, configured to generate a market reference coefficient based on the type of the good, the sales amount, and the market acceptance, and determine the predicted demand amount according to the predicted delivery amount and the market reference coefficient.

The second determining unit 4044 is further configured to extract reference sales data from a preset historical sales data set according to the cargo type, and generate a reference sales data set based on the reference sales data; extracting sales volume change characteristics from daily sales volume in the preset time period, and inquiring reference sales volume data records in the reference sales data set according to the sales volume change characteristics; generating a sales reference curve based on the reference sales data record, and determining a predicted sales based on the sales reference curve; calculating the average sales volume in the time period according to the daily sales volume in the preset time period, and calculating the proportion between the predicted sales volume and the average sales volume; generating a sales prediction coefficient according to the proportion, and adjusting the sales prediction coefficient according to the market acceptance to obtain a market reference coefficient;

in this embodiment, the allocating module 406 includes:

an obtaining unit 4061, configured to query an associated warehouse identifier from a preset warehouse information table according to the warehouse identifier, and obtain an associated inventory amount corresponding to an associated warehouse according to the associated warehouse identifier, where the associated warehouse identifier is a warehouse identifier corresponding to an associated warehouse having a freight traffic relationship with the target warehouse, and the associated warehouse is a warehouse having a freight traffic relationship with the target warehouse;

a fourth determining unit 4062, configured to determine a cargo allocation amount according to the inventory amount and the ideal inventory amount, and determine a cargo transportation amount corresponding to each associated warehouse according to the associated inventory amount and the cargo allocation amount;

the generating unit 4063 is configured to generate the cargo allocation information based on the associated warehouse identifier corresponding to each associated warehouse and the cargo transportation amount corresponding to each associated warehouse.

Referring to fig. 6, an embodiment of a computer device according to an embodiment of the present invention will be described in detail from the perspective of hardware processing.

Fig. 6 is a schematic structural diagram of a computer device 600 according to an embodiment of the present invention, which may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) for storing applications 633 or data 632. Memory 620 and storage medium 630 may be, among other things, transient or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a sequence of instructions for operating on the computer device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the computer device 600.

The computer device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input-output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and so forth. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 6 is not intended to be limiting of the computer devices provided herein and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, having instructions stored thereon, which, when executed on a computer, cause the computer to perform the steps of the cargo allocation method.

In practical applications, the above-provided method can be implemented based on Artificial Intelligence (AI) which is a theory, method, technique and application system that simulates, extends and expands human Intelligence, senses environment, acquires knowledge and uses knowledge to obtain the best result by using a digital computer or a machine controlled by a digital computer. The cloud server may be implemented based on a server, and the server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a web service, cloud communication, middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method for deploying goods, the method comprising:

acquiring state information corresponding to target goods in a target warehouse, wherein the state information comprises goods types, inventory quantities, delivery quantities and butt-joint seller identifications;

sending a data sharing request to a preset seller information platform according to the butted seller identifier, and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing based on the data sharing request through an editing interface preset in the seller information platform;

extracting sales volume, sales evaluation information and logistics evaluation information from the shared data, and determining market acceptance corresponding to the target goods based on the sales evaluation information;

determining a predicted demand amount corresponding to the target good based on the type of the good, the delivery amount, the sales amount and the market acceptance;

determining logistics acceptance corresponding to the target goods according to the logistics evaluation information, and determining ideal inventory of the target goods in the target warehouse based on the logistics acceptance and the predicted demand;

and determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signal.

2. The method for deploying goods according to claim 1, wherein the shipment is a daily shipment within a preset time period, and the determining the predicted demand corresponding to the target goods based on the type of goods, the shipment, the sales, and the market acceptance comprises:

3. The method of deploying cargo as defined in claim 2, wherein before querying a reference delivery volume data record in a pre-obtained delivery volume data set according to the delivery volume variation characteristic, the method further comprises:

extracting all shipment data records from a preset historical shipment data set;

analyzing the delivery volume data records, and determining the historical delivery volume corresponding to each delivery volume data record;

according to the historical shipment volume corresponding to each shipment volume data record, determining the shipment volume interval corresponding to each shipment volume data record in a preset shipment volume interval table;

generating an shipment volume data set corresponding to each shipment volume interval based on the shipment volume data records corresponding to each shipment volume interval;

calculating the average delivery volume according to the daily delivery volume in the preset time period;

determining a corresponding reference shipment volume interval according to the average shipment volume, wherein the reference shipment volume interval is the shipment volume interval in which the average shipment volume falls;

and determining the reference delivery volume data set from the delivery volume data sets corresponding to the delivery volume intervals according to the reference delivery volume intervals, wherein the reference delivery volume data set is the delivery volume data set corresponding to the reference delivery volume intervals.

4. The cargo allocation method according to claim 2, wherein the delivery volume change feature is a delivery volume change matrix, and the extracting the delivery volume change feature from the daily delivery volume within the preset time period and querying a reference delivery volume data record from a pre-obtained reference delivery volume data set according to the delivery volume change feature comprises:

calculating daily variation of the shipment in the time period based on the daily shipment in the preset time period;

generating a variation vector based on the daily variation of the delivery amount, and generating a delivery amount variation matrix based on the variation vector;

and inquiring a reference delivery volume data record in a pre-obtained reference delivery volume data set according to the delivery volume change matrix, wherein the reference delivery volume data record is a corresponding delivery volume data record when the similarity between the delivery volume reference change matrix and the delivery volume change matrix reaches a preset threshold value.

5. The method of deploying cargo of claim 2, wherein generating an shipment volume reference curve based on the reference shipment volume data record comprises:

extracting reference time and reference shipment quantity corresponding to the reference time from the reference shipment quantity data record;

and generating an shipment quantity reference curve based on the predicted time and a reference shipment quantity corresponding to the predicted time.

6. The method for allocating goods according to claim 2, wherein the sales volume is a daily sales volume within a preset time period, and the generating a market reference coefficient based on the goods type, the sales volume and the market acceptance comprises:

extracting reference sales data from a preset historical sales data set according to the goods types, and generating a reference sales data set based on the reference sales data;

extracting sales volume change characteristics from daily sales volume in the preset time period, and inquiring reference sales volume data records in the reference sales data set according to the sales volume change characteristics;

calculating the average sales volume in the time period according to the daily sales volume in the preset time period, and calculating the proportion between the predicted sales volume and the average sales volume;

and generating a sales prediction coefficient according to the proportion, and adjusting the sales prediction coefficient according to the market acceptance to obtain a market reference coefficient.

7. The method of any of claims 1-6, wherein the status information further comprises a warehouse identifier, and wherein determining the cargo allocation information based on the inventory amount and the ideal inventory amount comprises:

and generating goods allocation information based on the associated warehouse identifications corresponding to the associated warehouses and the goods transportation volumes corresponding to the associated warehouses.

8. A cargo deployment device, comprising:

the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring state information corresponding to target goods in a target warehouse, and the state information comprises goods types, inventory quantity, delivery quantity and a butt-joint seller identifier;

the receiving module is used for sending a data sharing request to a preset seller information platform according to the butted seller identifier and receiving shared data sent by the seller information platform, wherein the shared data is obtained by editing through an editing interface preset in the seller information platform based on the data sharing request;

the first determining module is used for extracting sales volume, sales evaluation information and logistics evaluation information from the shared data and determining market acceptance corresponding to the target goods based on the sales evaluation information;

a second determining module, configured to determine a predicted demand amount corresponding to the target good based on the type of the good, the shipment amount, the sales amount, and the market acceptance;

a third determining module, configured to determine a logistics acceptance degree corresponding to the target cargo according to the logistics evaluation information, and determine an ideal inventory amount of the target cargo in the target warehouse based on the logistics acceptance degree and the predicted demand amount;

and the allocation module is used for determining goods allocation information based on the inventory amount and the ideal inventory amount, generating an allocation control signal aiming at preset allocation equipment based on the goods allocation information, and controlling the corresponding allocation equipment to allocate goods through the allocation control signal.

9. A computer device, comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invoking the instructions in the memory to cause the computer device to perform the steps of the cargo deployment method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for deploying goods according to any of claims 1 to 7.