CN114077915A - Logistics distribution method and device for predicting shift, and computer equipment - Google Patents

Logistics distribution method and device for predicting shift, and computer equipment Download PDF

Info

Publication number
CN114077915A
CN114077915A CN202010824896.0A CN202010824896A CN114077915A CN 114077915 A CN114077915 A CN 114077915A CN 202010824896 A CN202010824896 A CN 202010824896A CN 114077915 A CN114077915 A CN 114077915A
Authority
CN
China
Prior art keywords
sequence data
unit sequence
shift
data set
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010824896.0A
Other languages
Chinese (zh)
Inventor
王弋宁
冯钰�
刘子恒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SF Technology Co Ltd
Original Assignee
SF Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by SF Technology Co Ltd filed Critical SF Technology Co Ltd
Priority to CN202010824896.0A priority Critical patent/CN114077915A/en
Publication of CN114077915A publication Critical patent/CN114077915A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to a logistics dispatching method and device for predicting shift, computer equipment and storage media. The method comprises the following steps: obtaining historical logistics sending quantity of a target shift within a specified time before a prediction time point, and determining logistics sending cumulant corresponding to each preset slicing time of the target shift within each specified time according to preset slicing time and each historical logistics sending quantity to obtain a unit sequence group; establishing a shift sequence data set of the target shift according to the obtained unit sequence number sets; obtaining a target unit sequence data set required by predicting a target shift at a prediction time point from the shift sequence data set through similarity calculation; and predicting the logistics distribution amount of the target shift at the prediction time point according to the fitting result by fitting the target unit sequence data set. By adopting the method, the timeliness of the logistics shift delivery amount can be predicted.

Description

Logistics distribution method and device for predicting shift, and computer equipment
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for predicting a shift in logistics distribution, a computer device, and a storage medium.
Background
With the development of electronic commerce, the logistics industry plays an important role in economic development. The logistics related information prediction and marketization rule exploration play an important role in improving logistics efficiency and resource allocation.
At present, the route information is mainly predicted manually according to the regional market state and fluctuation; or history-based information prediction is performed according to long-term static time sequence information, for example, static component quantity prediction, which is more focused on stable periodic information prediction, however, short-term routing information change is supported by insufficient real-time information for fluctuation peaks and exogenous events (for example, production is slowed down due to public epidemic situations) and logistics peaks (for example, the situation that purchase capacity of big shopping nodes such as twenty-one cannot be supplied in time) and resources cannot be adjusted and applied in time under the current special situation, so that the timeliness of predicting the distribution quantity of logistics shifts is low.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device, and a storage medium for predicting a logistics shift distribution amount, which can improve timeliness of distribution amount prediction of a logistics shift.
A method of logistics distribution for predicting a shift, the method comprising:
determining a predicted time point of the logistics dispatching amount of the target shift;
acquiring historical logistics dispatching quantity of a target shift within a specified time before a predicted time point;
determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of a target shift according to the preset slicing time length and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time;
establishing a shift sequence data set of the target shift according to each unit sequence number set;
calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group;
and (4) by fitting the target unit sequence data set, predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result.
In one embodiment, acquiring historical logistics distribution volume of a target shift within a specified time length before a predicted time point comprises:
acquiring the original logistics sending quantity of each logistics routing node in a specified time before a predicted time point of a target shift;
and cleaning each original logistics distribution quantity according to a data cleaning rule accumulated in the forward direction of time to obtain historical logistics distribution quantity.
In one embodiment, determining, according to preset slicing durations and historical logistics issuing quantities, logistics issuing cumulant corresponding to each preset slicing duration in each specified duration of a target shift to obtain a unit sequence group, including:
and time slicing is carried out on each appointed time length by taking the preset slicing time length as time granularity based on the historical logistics sending quantity of each routing node, and the logistics sending cumulant corresponding to each preset slicing time length is determined to obtain the unit sequence group corresponding to each appointed time length.
In one embodiment, calculating the similarity between each unit sequence number group in the shift sequence data group, and obtaining the target unit sequence data group according to the similarity between each unit sequence number group comprises:
missing value supplement is carried out on each unit sequence data group in the shift sequence data group to obtain a complete shift sequence data group;
and determining the similarity between each unit sequence data group in the complete shift sequence data group according to the difference matrix, and obtaining the target unit sequence data group according to the similarity.
In one embodiment, the preprocessing each unit sequence data set in the shift sequence data set to obtain a complete shift sequence data set includes:
acquiring the length of each unit sequence data group in the shift sequence data group;
determining a missing unit sequence data set and a complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data group is a first length; the length of the complete unit sequence data set is a second length;
and constructing a grid matrix according to the first length and the second length, and supplementing missing points for each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set.
In one embodiment, constructing a grid matrix according to the first length and the second length, and performing missing value supplementation on each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set, includes:
determining complete unit sequence data groups with the highest similarity to the missing unit sequence data groups from the complete unit sequence data groups;
constructing a grid matrix according to the first length and the second length, and mapping the corresponding logistics issuing cumulant in the complete unit sequence data group and the missing unit sequence data group with the highest similarity to the grid matrix in sequence;
and (4) performing missing point supplement on each missing unit sequence data set in the grid matrix according to the specified search direction to obtain a complete shift sequence data set.
In one embodiment, determining the similarity between the unit sequence data sets in the complete shift sequence data set according to the difference matrix, and obtaining the target unit sequence data set according to the similarity includes:
determining the similarity between each unit sequence data group in the complete shift sequence data group according to the difference matrix to obtain N target unit sequence data groups;
determining variance values and mean value dispersion of the N target unit sequence data groups;
the target unit sequence data group with the maximum variance value and the maximum mean value dispersion is removed from the N target unit sequence data groups;
through fitting the target unit sequence data set, the logistics dispatching amount of the target shift at the prediction time point is predicted according to the fitting result, and the method comprises the following steps:
performing linear fitting on the target unit sequence data group with the maximum elimination variance value and the maximum mean value dispersion, and determining a linear fitting function;
and determining the logistics dispatching amount of the target shift at the predicted time point according to the linear fitting function.
A logistics distribution amount device for predicting a shift, comprising:
the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining the predicted time point of the logistics distribution amount of a target shift;
the acquisition module is used for acquiring historical logistics dispatching quantity of the target shift within a specified time before the predicted time point;
the second determining module is used for determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of the target shift according to the preset slicing time length and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time;
the construction module is used for constructing a shift sequence data set of the target shift according to each unit sequence number set;
the calculation module is used for calculating the similarity between each unit sequence array in the shift sequence data set and obtaining a target unit sequence data set according to the similarity between each unit sequence array;
and the prediction module is used for predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result by fitting the target unit sequence data set.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
determining a predicted time point of the logistics dispatching amount of the target shift;
acquiring historical logistics dispatching quantity of a target shift within a specified time before a predicted time point;
determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of a target shift according to the preset slicing time length and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time;
establishing a shift sequence data set of the target shift according to each unit sequence number set;
calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group;
and (4) by fitting the target unit sequence data set, predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
determining a predicted time point of the logistics dispatching amount of the target shift;
acquiring historical logistics distribution quantity of a target shift within a specified time before a predicted time point;
determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of a target shift according to the preset slicing time length and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time;
establishing a shift sequence data set of the target shift according to each unit sequence number set;
calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group;
and (4) by fitting the target unit sequence data set, predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result.
The logistics shipment method, the device, the computer equipment and the storage medium for predicting the shift are characterized in that the logistics shipment cumulant corresponding to each preset slicing time length of the target shift in each specified time length is determined according to the preset slicing time length and each historical logistics shipment quantity by obtaining the historical logistics shipment quantity of the target shift in the specified time length before the predicted time point, and a unit sequence group is obtained; establishing a shift sequence data set of the target shift according to the obtained unit sequence number sets; obtaining a target unit sequence data set required by predicting a target shift at a prediction time point from the shift sequence data set through similarity calculation; predicting the logistics dispatching amount of the target shift at the prediction time point according to the fitting result through fitting of the target unit sequence data set; time slicing is carried out on historical logistics sending quantity to obtain a logistics sending cumulative quantity set with each preset slicing time length, and a unit sequence data set is obtained; the logistics dispatching amount at the forecasting time point is forecasted by constructing a shift sequence data set of the logistics dispatching amount and calculating the similarity of sequence data of the unit sequence data in the shift sequence data set, and the forecasting timeliness of the logistics shift dispatching amount is improved.
Drawings
FIG. 1 is a diagram of an embodiment of an environment in which the method for logistics distribution for class prediction is implemented;
FIG. 2 is a schematic flow diagram illustrating a method for logistics distribution to predict shift in one embodiment;
FIG. 3 is a graph illustrating cumulative amounts of material flow distribution in one embodiment;
FIG. 4 is a schematic flowchart of a method for supplementing missing values of unit sequence data according to an embodiment;
FIG. 5 is a schematic flow chart of a logistic dispatch method to predict shift in another embodiment;
FIG. 6 is a block diagram of an embodiment of a logistics distribution device for predicting a shift;
FIG. 7 is a block diagram of an embodiment of a logistics distribution device for predicting a shift;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The logistics dispatching method for predicting shifts can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 determines a prediction time point of the logistics sending quantity of the target shift, and obtains historical logistics sending quantity of the target shift within a specified time before the prediction time point from the server 104; determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of a target shift according to the preset slicing time length and each historical logistics distribution quantity to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time; establishing a shift sequence data set of the target shift according to each unit sequence number set; calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group; and (4) by fitting the target unit sequence data set, predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for logistics dispatching for predicting shift is provided, which is illustrated by taking the method as an example for the terminal in fig. 1, and includes the following steps:
step 202, determining a predicted time point of the logistics distribution amount of the target shift.
The target shift refers to an departure shift of a logistics vehicle carrying logistics express, and each target shift has a designated logistics route. The logistics route includes a departure place and a destination, for example, the logistics route of the target shift a is from the departure place a1 to the destination b 1; the logistics route for target shift B is from origin a2 to destination B2. Before the express delivery of the delivery logistics, the target class needs to go through the processes of warehousing, sorting, vehicle preparation, loading, departure and the like, wherein each process corresponds to one routing node, namely warehousing, sorting, vehicle preparation, loading and departure correspond to a warehousing node, a sorting node, a vehicle preparation node, a loading node and a departure node respectively; the corresponding logistics sending volume can be obtained on each routing node, and the logistics sending volume history logistics sending volume corresponding to each logistics routing node can be the same or different. In addition, an incidence relation exists between the target shift and the waybill express information of the logistics express, and the waybill express information of each logistics express comprises information such as the weight, the delivery city, the receiving city and the express attribute of the logistics express.
And step 204, acquiring historical logistics dispatching quantity of the target shift within a specified time before the predicted time point. The specified duration is obtained by analyzing historical logistics dispatching quantity data of the precipitated target shift; the specified duration may be, but is not limited to, 72 hours prior to the predicted time point. For example, the forecast time point is 10 months, 10 days, 9 hours, and 30 minutes, and the historical distribution volume within 72 hours before the forecast time point needs to be acquired.
Specifically, by determining a predicted time point of the logistics distribution amount of the target shift, the historical logistics distribution amount within a specified time length before the predicted time point is obtained from the server according to the predicted time point and the target shift.
And step 206, determining the logistics distribution cumulant corresponding to each preset slicing time length of the target shift in each specified time length according to the preset slicing time length and each historical logistics distribution cumulant, and obtaining a unit sequence group.
The unit sequence group is a logistics issuing accumulated quantity set of the target shift in each preset slicing time length. The preset slicing time period may be, but is not limited to, a time period of 1 hour. The logistics distribution accumulation amount corresponding to each preset slicing time length is accumulated once every hour from the beginning of the history forward-pushing of the predicted time point to the specified time length interval (the first 72 hours in the embodiment), from 72 hours to the back, and from 72 hours to 71 hours, from 71 hours to 70 hours, until the logistics distribution accumulation amount reaches-1.
Based on historical sending item flow in a specified time, time length slicing is carried out on the specified time length according to the pre-slicing time length, the logistics sending item cumulant of the preset slicing time length, namely the total route cumulant, can be obtained, and a unit sequence data set is obtained, wherein the unit sequence data set comprises the logistics sending item cumulant of each preset slicing time length. For example, as shown in table 1, the predicted target shift is 020W0700, and the target shift end time is 09 hours and 30 minutes; the prediction time point is 10 months, 10 days, 09 hours and 30 minutes; obtaining the historical logistics distribution quantity of a target shift in a specified time before a prediction time point, wherein the historical logistics distribution quantity is 280, and the time period corresponding to the specified time is 10 months, 7 days, 10 hours, 30 minutes to 10 months, 10 days, 9 days, 30 minutes; the preset slicing time is 1 hour long, the target shift ending time is 09 hours, 30 minutes is used as the number of hours for positive and negative division, the logistics distribution cumulant of each preset slicing time is obtained, and the obtained logistics distribution cumulant of each preset slicing time is used as a group of unit sequence groups.
Table 1:
Figure BDA0002635784620000071
Figure BDA0002635784620000081
according to the logic of generating the unit sequence data, acquiring the historical data of the target shift from the server to obtain the unit sequence data group of each day of the target shift, and as shown in table 2, predicting that the target shift is 020W0700, the end time of the target shift is 09 minutes and 30 minutes, the starting date of the historical logistics distribution amount of the sediment is 3 months and 3 days, and the end date of the historical data: 10 months and 10 days; the unit sequence data set corresponding to each day in the time period from 3 months to 10 months and 10 days is obtained, the data in the unit sequence data set is displayed in a curve form, the variation trend of the logistics distribution accumulation amount can be obtained, and as shown in fig. 3, a chart area is displayed in a logistics distribution accumulation amount curve graph corresponding to each day from 7 months 16 to 7 months 22.
Table 2:
Figure BDA0002635784620000082
Figure BDA0002635784620000091
specifically, based on each historical logistics sending amount, time slicing is performed on each specified time length by taking the preset slicing time length as time granularity, and the logistics sending cumulant corresponding to each preset slicing time length is determined to obtain the unit sequence group corresponding to each specified time length.
In step 208, a shift sequence data set of the target shift is constructed based on the unit sequence numbers.
Specifically, the starting date and the ending date of the historical logistics dispatching amount of the target shift are determined, the historical logistics dispatching amount of the target shift in the interval from the starting date to the ending date is obtained from the server, the unit sequence data set of the target shift every day in the time period from the starting date to the ending date is obtained according to the logic generated by the unit sequence data, and the shift sequence data set of the target shift is obtained. As shown in table 2, a shift sequence data set of the target shift was obtained from the unit sequence data sets for each day in the period from 3 months 3 to 10 months 10 days.
And step 210, calculating the similarity between each unit sequence number group in the shift sequence data group, and obtaining the target unit sequence data group according to the similarity between each unit sequence number group.
Specifically, missing value supplement is carried out on each unit sequence data set in the shift sequence data set by constructing a grid matrix and a difference matrix, so that a complete shift sequence data set is obtained; and determining the similarity among the unit sequence data groups in the complete shift sequence data group, and obtaining N target unit sequence data groups according to the similarity. For example, the constructed target shift sequence data set includes two unit sequence data sets A, B, which are respectively expressed as:
A＝q0，q1，q2，...，qm
B＝k0，k1，k2，...，km
wherein q ismRepresents the cumulative amount of material flow distribution per hour, k, in sequence AnRepresents the cumulative amount of material flow sent per hour in sequence B; the specified time is 72 hours;represents the length of the unit sequence data set A, and n represents the length of the unit sequence data set B; the length of the unit sequence data group represents the number of the logistics distribution accumulation obtained by time slicing the specified time length. In the normal case, m ≠ n ═ 72 time intervals are complete unit sequence data combinations, and in practice m ≠ n, or m ≦ 72, or n ≦ 72 may occur. By constructing an M x n grid matrix M, qiAnd kjRespectively carrying out the logistics issuance cumulant of the ith preset slicing time length of the sequence A and the logistics issuance cumulant of the jth preset slicing time length of the sequence B, wherein the horizontal axis of the matrix is I, the vertical axis is J, and q isiAnd kjMapping the point in the matrix to (i, j); searching according to the specified search directions (i +1, j), (i, j +1), (i +1, j +1) by the difference matrix MgAnd supplementing missing values in the unit sequence data set to obtain a complete shift sequence data set.
Wherein the difference matrix can represent MgComprises the following steps:
Mg＝Min(Mg(i-1，j-1),Mg(i-1，j),Mg(i，j-1))+M(i，j)
and 212, fitting the target unit sequence data set, and predicting the logistics distribution amount of the target shift at the prediction time point according to the obtained fitting result.
Specifically, variance values and mean value dispersion of N target unit sequence data sets are determined; the target unit sequence data group with the maximum variance value and the maximum mean value dispersion is removed from the N target unit sequence data groups; performing linear fitting on the target unit sequence data group with the maximum elimination variance value and the maximum mean value dispersion, determining a linear fitting function, and determining the logistics dispatching amount of the target shift at the prediction time point according to the linear fitting function; wherein N is a positive integer.
In the logistics distribution method for predicting the shift, historical logistics distribution quantity of the target shift in a specified time before a prediction time point is obtained, and logistics distribution cumulant corresponding to each preset slicing time of the target shift in each specified time is determined according to the preset slicing time and each historical logistics distribution quantity, so that a unit sequence group is obtained; establishing a shift sequence data set of the target shift according to the obtained unit sequence number sets; obtaining a target unit sequence data set required by predicting a target shift at a prediction time point from the shift sequence data set through similarity calculation; predicting the logistics dispatching amount of the target shift at the prediction time point according to the fitting result through fitting of the target unit sequence data set; time slicing is carried out on historical logistics sending quantity to obtain a logistics sending cumulative quantity set with each preset slicing time length, and a unit sequence data set is obtained; the logistics dispatching amount at the forecasting time point is forecasted by constructing a shift sequence data set of the logistics dispatching amount and calculating the similarity of sequence data of the unit sequence data in the shift sequence data set, and the forecasting timeliness of the logistics shift dispatching amount is improved.
In one embodiment, as shown in fig. 4, a missing value supplementing method for a unit sequence data set is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
in step 402, the length of each unit sequence data set in the shift sequence data set is obtained.
The data of the unit sequence data group refers to the logistics distribution cumulant corresponding to each preset slicing time length, and the length of the unit sequence data group represents the number of the logistics distribution cumulant obtained by time slicing on the specified time length.
Step 404, determining missing unit sequence data set and complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data set is a first length, and the length of the complete unit sequence data set is a second length.
Specifically, according to the comparison of the length of each unit sequence data set with the length threshold value, when the length is not equal to the length threshold value, the corresponding unit sequence data set is a missing unit sequence data set, and when the length is equal to the length threshold value, the corresponding unit sequence data set is a complete unit sequence data set. The length threshold is determined according to the specified duration and the preset slicing duration, for example, the specified duration is 72 hours, the preset slicing duration is 1 hour, and the determined length threshold is 72.
And 406, constructing a grid matrix according to the first length and the second length, and supplementing missing points to each missing unit sequence data group based on the grid matrix and each complete unit sequence data group to obtain a complete shift sequence data group.
Specifically, the similarity between each missing unit sequence data group and each complete unit sequence data group is sequentially calculated, and the complete unit sequence data group with the highest similarity to each missing unit sequence data group is determined from each complete unit sequence data group according to the calculated similarity; constructing a grid matrix according to the first length of the missing unit sequence data group and the second length of the complete unit sequence data group, and mapping the corresponding logistics sending cumulant in the complete unit sequence data group with the highest similarity and the missing unit sequence data group to the grid matrix in sequence; and (4) performing missing point supplement on each missing unit sequence data set in the grid matrix according to the specified search direction to obtain a complete shift sequence data set.
In the missing value supplementing method for the unit sequence data set, the missing unit sequence data set and the complete unit sequence data set in the shift sequence data set are determined according to the length of each unit sequence data set in the shift sequence data set; the length of the missing unit sequence data group is a first length, and the length of the complete unit sequence data group is a second length; and constructing a grid matrix according to the first length and the second length, and supplementing missing points for each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set, so that inaccurate logistics dispatching quantity prediction caused by data loss is avoided.
In one embodiment, as shown in fig. 5, a method for logistics dispatching for predicting shift is provided, which is described by taking the method as an example for the terminal in fig. 1, and includes the following steps:
step 502, determining a predicted time point of the logistics distribution amount of the target shift.
And step 504, acquiring historical logistics dispatching quantity of the target shift within a specified time before the predicted time point.
Specifically, the original logistics dispatching amount of a target shift in a specified time before a predicted time point is obtained; and cleaning each original logistics distribution quantity according to a data cleaning rule accumulated in the forward direction of time to obtain historical logistics distribution quantity. The forward accumulated data cleaning rule refers to that the logistics distribution quantity is cleaned every preset time interval from the fact that the history of the predicted time point is pushed forward to a specified time interval, and the logistics distribution quantity is accumulated.
And step 506, time slicing is carried out on each appointed time length by taking the preset slicing time length as time granularity based on each historical logistics sending quantity, the logistics sending cumulant corresponding to each preset slicing time length is determined, and the unit sequence group corresponding to each appointed time length is obtained.
And step 508, performing missing value supplement on each unit sequence data group in the shift sequence data group to obtain a complete shift sequence data group.
Specifically, the length of each unit sequence data group in the shift sequence data group is acquired; determining a missing unit sequence data set and a complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data group is a first length; the length of the complete unit sequence data set is a second length; determining complete unit sequence data groups with the highest similarity to the missing unit sequence data groups from the complete unit sequence data groups; constructing a grid matrix according to the first length and the second length, and mapping the corresponding logistics issuing cumulant in the complete unit sequence data group and the missing unit sequence data group with the highest similarity to the grid matrix in sequence; and (4) performing missing point supplement on each missing unit sequence data set in the grid matrix according to the specified search direction to obtain a complete shift sequence data set.
And step 510, determining the similarity between each unit sequence data group in the complete shift sequence data group to obtain N target unit sequence data groups.
In step 512, variance values and mean value dispersion of the N target unit sequence data sets are determined.
And 514, removing the target unit sequence data group with the maximum variance value and the maximum mean value dispersion from the N target unit sequence data groups.
And 516, performing linear fitting on the target unit sequence data group with the maximum elimination variance value and the maximum mean value dispersion, and determining a linear fitting function.
And step 518, determining the logistics dispatching amount of the target shift at the predicted time point according to the linear fitting function.
In the embodiment, historical logistics sending amount of a target shift in a specified time before a prediction time point is obtained, time slicing is performed on each specified time by taking a preset slicing time as time granularity on the basis of each historical logistics sending amount, logistics sending cumulant corresponding to each preset slicing time is determined, a unit sequence group corresponding to each specified time is obtained, missing value supplement is performed on the unit sequence group, and a complete shift sequence data group is obtained; determining N target unit sequence data sets by calculating each unit sequence data set in the shift sequence data sets, removing the target unit sequence data sets with the maximum variance value and the maximum mean value dispersion from the N target unit sequence data sets, and fitting the remaining target unit sequence data sets to obtain the logistics distribution quantity of the target shift at the prediction time point; by carrying out time slicing on a large amount of historical logistics distribution quantity data and predicting the logistics distribution quantity of the predicted point of the target shift according to the sliced data, the timeliness and the accuracy of prediction are improved.
It should be understood that although the various steps of fig. 2, 4 and 5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 4 and 5 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 6, there is provided a logistics distribution amount device for predicting a shift, comprising: a first determination module 602, an acquisition module 604, a second determination module 606, a construction module 608, a calculation module 610, and a prediction module 612, wherein:
the first determining module 602 is configured to determine a predicted time point of the logistics distribution amount of the target shift.
The obtaining module 604 is configured to obtain historical logistics dispatch volume of the target shift within a specified time before the predicted time point.
A second determining module 606, configured to determine, according to the preset slicing time and each historical logistics issuing quantity, a logistics issuing cumulant corresponding to each preset slicing time in each specified time for the target shift, so as to obtain a unit sequence group; the unit sequence group is a logistics distribution accumulated quantity set of the target shift in each preset slicing time length.
The building module 608 is configured to build a shift sequence data set of the target shift according to each unit sequence number set.
The calculating module 610 is configured to calculate a similarity between each unit sequence number group in the shift sequence data group, and obtain the target unit sequence data group according to the similarity between each unit sequence number group.
And the predicting module 612 is configured to predict the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result by fitting the target unit sequence data set.
In the logistics distribution quantity device for predicting the shift, the logistics distribution cumulative quantity corresponding to each preset slicing time length of the target shift in each specified time length is determined according to the preset slicing time length and each historical logistics distribution quantity by obtaining the historical logistics distribution quantity of the target shift in the specified time length before the prediction time point, and a unit sequence group is obtained; establishing a shift sequence data set of the target shift according to the obtained unit sequence number sets; obtaining a target unit sequence data set required by predicting a target shift at a prediction time point from the shift sequence data set through similarity calculation; predicting the logistics dispatching amount of the target shift at the prediction time point according to the fitting result through fitting of the target unit sequence data set; time slicing is carried out on historical logistics sending quantity to obtain a logistics sending cumulative quantity set with each preset slicing time length, and a unit sequence data set is obtained; and after a shift sequence data set of the logistics sending quantity is constructed, the logistics sending quantity at the prediction time point is predicted according to the similarity of the sequence data of the unit sequence data in the shift sequence data set, and the timeliness of the logistics shift sending quantity prediction is improved.
In another embodiment, as shown in fig. 7, a logistics dispatching device for predicting a shift is provided, which comprises, in addition to a first determining module 602, an obtaining module 604, a second determining module 606, a constructing module 608, a calculating module 610 and a predicting module 612: a data washing module 614, a data processing module 616, a mapping module 618, and a fitting module 620, wherein:
the data cleaning module 614 is used for acquiring the original logistics dispatching amount of the target shift within a specified time before the predicted time point; and cleaning each original logistics distribution quantity according to a data cleaning rule accumulated in the forward direction of time to obtain historical logistics distribution quantity.
In an embodiment, the second determining module 606 is further configured to perform time slicing on each specified duration by using a preset slicing duration as a time granularity based on each historical logistics distribution quantity, and determine a logistics distribution cumulative quantity corresponding to each preset slicing duration to obtain a unit sequence group corresponding to each specified duration.
And the data processing module 616 is configured to perform missing value supplementation on each unit sequence data set in the shift sequence data set to obtain a complete shift sequence data set.
In one embodiment, the data processing module 616 includes an acquisition sub-module and a construction sub-module, wherein:
the acquisition submodule is used for acquiring the length of each unit sequence data set in the shift sequence data set; determining a missing unit sequence data set and a complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data group is a first length; the length of the complete unit sequence data set is a second length.
And constructing a submodule for constructing the grid matrix according to the first length and the second length.
The data processing module 616 is further configured to perform missing point supplementation on each missing unit sequence data set based on the grid matrix and each complete unit sequence data set, so as to obtain a complete shift sequence data set.
The data processing module 616 is further configured to perform missing point supplementation on each missing unit sequence data set in the grid matrix according to the specified search direction, so as to obtain a complete shift sequence data set.
In one embodiment, the calculating module 610 is further configured to determine a similarity between unit sequence data sets in the complete shift sequence data set according to the difference matrix, and obtain the target unit sequence data set according to the similarity.
And the mapping module 618 is configured to construct a grid matrix according to the first length and the second length, and sequentially map the corresponding logistics sending cumulant in the complete unit sequence data set and the missing unit sequence data set with the highest similarity to the grid matrix.
In one embodiment, the calculating module 610 is further configured to determine a similarity between each unit sequence data set in the complete shift sequence data set according to the difference matrix, so as to obtain N target unit sequence data sets; determining variance values and mean value dispersion of the N target unit sequence data groups; and (4) eliminating the target unit sequence data group with the maximum variance value and the maximum mean value dispersion from the N target unit sequence data groups.
And the fitting module 620 is configured to perform linear fitting on the target unit sequence data group with the largest elimination variance value and the largest mean dispersion, and determine a linear fitting function.
The prediction module 612 is further configured to determine the logistics dispatching amount of the target shift at the predicted time point according to a linear fitting function.
In one embodiment, historical logistics sending amount of a target shift in a specified time before a prediction time point is obtained, time slicing is carried out on each specified time by taking a preset slicing time as time granularity on the basis of each historical logistics sending amount, logistics sending cumulant corresponding to each preset slicing time is determined, a unit sequence group corresponding to each specified time is obtained, missing value supplement is carried out on the unit sequence group, and a complete shift sequence data group is obtained; determining N target unit sequence data sets by calculating each unit sequence data set in the shift sequence data sets, removing the target unit sequence data sets with the maximum variance value and the maximum mean value dispersion from the N target unit sequence data sets, and fitting the remaining target unit sequence data sets to obtain the logistics distribution quantity of the target shift at the prediction time point; by carrying out time slicing on a large amount of historical logistics distribution quantity data and predicting the logistics distribution quantity of the predicted point of the target shift according to the sliced data, the timeliness and the accuracy of prediction are improved.
For the specific definition of the device for dispatching logistics for predicting shift, refer to the above definition of the method for dispatching logistics for predicting shift, which is not repeated herein. The modules in the logistics dispatching device for predicting the shift can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of logistics distribution for predicting a shift. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
determining a predicted time point of the logistics dispatching amount of the target shift;
acquiring historical logistics dispatching quantity of a target shift within a specified time before a predicted time point;
determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of a target shift according to the preset slicing time length and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time;
establishing a shift sequence data set of the target shift according to each unit sequence number set;
calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group;
and (4) by fitting the target unit sequence data set, predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring the original logistics dispatching amount of a target shift within a specified time before a predicted time point;
and cleaning each original logistics distribution quantity according to a data cleaning rule accumulated in the forward direction of time to obtain historical logistics distribution quantity.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and time slicing is carried out on each appointed time length by taking the preset slicing time length as time granularity on the basis of each historical logistics distribution quantity, and the logistics distribution cumulant corresponding to each preset slicing time length is determined to obtain the unit sequence group corresponding to each appointed time length.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
missing value supplement is carried out on each unit sequence data group in the shift sequence data group to obtain a complete shift sequence data group;
and determining the similarity between the unit sequence data groups in the complete shift sequence data group, and obtaining the target unit sequence data group according to the similarity.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring the length of each unit sequence data group in the shift sequence data group;
determining a missing unit sequence data set and a complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data group is a first length; the length of the complete unit sequence data set is a second length;
and constructing a grid matrix according to the first length and the second length, and supplementing missing points for each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining complete unit sequence data groups with the highest similarity to the missing unit sequence data groups from the complete unit sequence data groups;
constructing a grid matrix according to the first length and the second length, and mapping the corresponding logistics issuing cumulant in the complete unit sequence data group and the missing unit sequence data group with the highest similarity to the grid matrix in sequence;
and (4) performing missing point supplement on each missing unit sequence data set in the grid matrix according to the specified search direction to obtain a complete shift sequence data set.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining the similarity between each unit sequence data group in the complete shift sequence data group according to the difference matrix to obtain N target unit sequence data groups;
determining variance values and mean value dispersion of the N target unit sequence data groups;
the target unit sequence data group with the maximum variance value and the maximum mean value dispersion is removed from the N target unit sequence data groups;
through fitting the target unit sequence data set, the logistics dispatching amount of the target shift at the prediction time point is predicted according to the fitting result, and the method comprises the following steps:
performing linear fitting on the target unit sequence data group with the maximum elimination variance value and the maximum mean value dispersion, and determining a linear fitting function;
and determining the logistics dispatching amount of the target shift at the predicted time point according to the linear fitting function.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
determining a predicted time point of the logistics dispatching amount of the target shift;
acquiring historical logistics dispatching quantity of a target shift within a specified time before a predicted time point;
determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of a target shift according to the preset slicing time length and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of a target shift in each preset slicing time;
establishing a shift sequence data set of the target shift according to each unit sequence number set;
calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group;
and (4) by fitting the target unit sequence data set, predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the original logistics dispatching amount of a target shift within a specified time before a predicted time point;
and cleaning each original logistics distribution quantity according to a data cleaning rule accumulated in the forward direction of time to obtain historical logistics distribution quantity.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and time slicing is carried out on each appointed time length by taking the preset slicing time length as time granularity on the basis of each historical logistics distribution quantity, and the logistics distribution cumulant corresponding to each preset slicing time length is determined to obtain the unit sequence group corresponding to each appointed time length.
In one embodiment, the computer program when executed by the processor further performs the steps of:
missing value supplement is carried out on each unit sequence data group in the shift sequence data group to obtain a complete shift sequence data group;
and determining the similarity between the unit sequence data groups in the complete shift sequence data group, and obtaining the target unit sequence data group according to the similarity.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the length of each unit sequence data group in the shift sequence data group;
determining a missing unit sequence data set and a complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data group is a first length; the length of the complete unit sequence data set is a second length;
and constructing a grid matrix according to the first length and the second length, and supplementing missing points for each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining complete unit sequence data groups with the highest similarity to the missing unit sequence data groups from the complete unit sequence data groups;
constructing a grid matrix according to the first length and the second length, and mapping the corresponding logistics issuing cumulant in the complete unit sequence data group and the missing unit sequence data group with the highest similarity to the grid matrix in sequence;
and (4) performing missing point supplement on each missing unit sequence data set in the grid matrix according to the specified search direction to obtain a complete shift sequence data set.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the similarity between each unit sequence data group in the complete shift sequence data group according to the difference matrix to obtain N target unit sequence data groups;
determining variance values and mean value dispersion of the N target unit sequence data groups;
the target unit sequence data group with the maximum variance value and the maximum mean value dispersion is removed from the N target unit sequence data groups;
through fitting the target unit sequence data set, the logistics dispatching amount of the target shift at the prediction time point is predicted according to the fitting result, and the method comprises the following steps:
performing linear fitting on the target unit sequence data group with the maximum elimination variance value and the maximum mean value dispersion, and determining a linear fitting function;
and determining the logistics dispatching amount of the target shift at the predicted time point according to the linear fitting function.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that a person skilled in the art could make a number of variations and modifications without departing from the concept of the present application, and such variations and modifications are within the scope of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method of logistics dispatching for predicting a shift, the method comprising:
determining a predicted time point of the logistics dispatching amount of the target shift;
acquiring historical logistics distribution quantity of the target shift in a specified time before the predicted time point;
determining logistics distribution cumulant corresponding to each preset slicing time length of the target shift in each specified time length according to preset slicing time lengths and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of the target shift in each preset slicing time;
constructing a shift sequence data set of the target shift according to each unit sequence set;
calculating the similarity between each unit sequence data group in the shift sequence data group, and obtaining a target unit sequence data group according to the similarity between each unit sequence data group;
and predicting the logistics distribution amount of the target shift at the prediction time point according to the obtained fitting result by fitting the target unit sequence data set.
2. The method of claim 1, wherein said obtaining historical logistics dispatch volume for a specified duration of said target shift prior to said predicted time point comprises:
acquiring the original logistics dispatching amount of the target shift within a specified time before the predicted time point;
and cleaning each original logistics distribution quantity according to a data cleaning rule accumulated in the forward direction of time to obtain historical logistics distribution quantity.
3. The method according to claim 1, wherein the step of determining the cumulative logistics distribution amount corresponding to each preset slicing time duration in each specified time duration of the target shift according to a preset slicing time duration and each historical logistics distribution amount to obtain a unit sequence group comprises:
and time slicing is carried out on each appointed time length by taking preset slicing time length as time granularity on the basis of each historical logistics distribution sending quantity, and logistics sending cumulant corresponding to each preset slicing time length is determined to obtain a unit sequence array corresponding to each appointed time length.
4. The method according to claim 1, wherein the calculating the similarity between each unit sequence number group in the shift sequence data group and obtaining the target unit sequence data group according to the similarity between each unit sequence number group comprises:
missing value supplement is carried out on each unit sequence data group in the shift sequence data group to obtain a complete shift sequence data group;
and determining the similarity between the unit sequence data groups in the complete shift sequence data group, and obtaining a target unit sequence data group according to the similarity.
5. The method of claim 4, wherein the missing value processing of each unit sequence data set in the shift sequence data set to obtain a complete shift sequence data set comprises:
acquiring the length of each unit sequence data group in the shift sequence data group;
determining a missing unit sequence data set and a complete unit sequence data set in the shift sequence data set according to the length; the length of the missing unit sequence data group is a first length; the length of the complete unit sequence data set is a second length;
and constructing a grid matrix according to the first length and the second length, and supplementing missing points for each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set.
6. The method of claim 5, wherein constructing a grid matrix according to the first length and the second length, and performing missing value supplementation on each missing unit sequence data set based on the grid matrix and each complete unit sequence data set to obtain a complete shift sequence data set comprises:
determining a complete unit sequence data set having the highest similarity to each missing unit sequence data set from each complete unit sequence data set;
constructing a grid matrix according to the first length and the second length, and mapping the complete unit sequence data group with the highest similarity and the corresponding logistics issuance cumulant in the missing unit sequence data group to the grid matrix in sequence;
and supplementing missing points to each missing unit sequence data set in the grid matrix according to the specified search direction to obtain a complete shift sequence data set.
7. The method of claim 4, wherein the determining a similarity between the unit sequence data sets in the complete shift sequence data set and obtaining a target unit sequence data set according to the similarity comprises:
determining the similarity between each unit sequence data group in the complete shift sequence data group according to the difference matrix to obtain N target unit sequence data groups;
determining variance values and mean dispersion of the N target unit sequence data sets;
the target unit sequence data group with the maximum variance value and the maximum mean value dispersion is removed from the N target unit sequence data groups;
the predicting the logistics dispatching amount of the target shift at the prediction time point according to the fitting result by fitting the target unit sequence data set comprises the following steps:
performing linear fitting on the target unit sequence data group with the maximum elimination variance value and the maximum mean value dispersion, and determining a linear fitting function;
and determining the logistics dispatching amount of the target shift at the predicted time point according to a linear fitting function.
8. A logistics dispatching device for predicting a shift, the device comprising:
the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining the predicted time point of the logistics distribution amount of a target shift;
the acquisition module is used for acquiring the historical logistics dispatching amount of the target shift in a specified time before the prediction time point;
the second determining module is used for determining logistics distribution cumulant corresponding to each preset slicing time length in each specified time length of the target shift according to preset slicing time lengths and each historical logistics distribution cumulant to obtain a unit sequence group; the unit sequence group is a logistics issuing accumulated quantity set of the target shift in each preset slicing time;
the construction module is used for constructing a shift sequence data set of the target shift according to each unit sequence set;
the calculation module is used for calculating the similarity between each unit sequence array in the shift sequence data set and obtaining a target unit sequence data set according to the similarity between each unit sequence array;
and the prediction module is used for predicting the logistics dispatching amount of the target shift at the prediction time point according to the obtained fitting result by fitting the target unit sequence data set.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 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 of any one of claims 1 to 7.
CN202010824896.0A 2020-08-17 2020-08-17 Logistics distribution method and device for predicting shift, and computer equipment Pending CN114077915A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010824896.0A CN114077915A (en) 2020-08-17 2020-08-17 Logistics distribution method and device for predicting shift, and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010824896.0A CN114077915A (en) 2020-08-17 2020-08-17 Logistics distribution method and device for predicting shift, and computer equipment

Publications (1)

Publication Number Publication Date
CN114077915A true CN114077915A (en) 2022-02-22

Family

ID=80281055

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010824896.0A Pending CN114077915A (en) 2020-08-17 2020-08-17 Logistics distribution method and device for predicting shift, and computer equipment

Country Status (1)

Country Link
CN (1) CN114077915A (en)

Similar Documents

Publication Publication Date Title
US7987106B1 (en) System and methods for forecasting time series with multiple seasonal patterns
CN102521056B (en) Task allocation device and task allocation method
US20150227964A1 (en) Revenue Estimation through Ensemble Modeling
CN108182633B (en) Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium
CN103685347A (en) Method and device for allocating network resources
JP6536028B2 (en) Order plan determination device, order plan determination method and order plan determination program
CN113537850A (en) Storage optimization method and device, computer equipment and storage medium
CN111612560A (en) Promotion object recommendation method and system, storage medium and electronic device
CN108874520A (en) Calculation method and device
CN112100177A (en) Data storage method and device, computer equipment and storage medium
CN114077915A (en) Logistics distribution method and device for predicting shift, and computer equipment
CN114791915B (en) Data aggregation method and device, computer equipment and storage medium
CN111091138A (en) Irradiation forecast processing method and stacked generalization model training method and device
CN115759742A (en) Enterprise risk assessment method and device, computer equipment and storage medium
US20230053859A1 (en) Method and apparatus for outputting information
CN113760550A (en) Resource allocation method and resource allocation device
CN113837782A (en) Method and device for optimizing periodic item parameters of time series model and computer equipment
CN116127342B (en) Information clustering processing method, system and platform based on hotel
CN112380419B (en) Bidding data query method, system and electronic equipment
CN113627662B (en) Inventory data prediction method, apparatus, device and storage medium
CN110457122B (en) Task processing method, task processing device and computer system
CN117495131A (en) Power consumption data prediction method, device, computer equipment and storage medium
CN117874548A (en) Processing method, device and computer equipment for time sequence data of charging and replacing station
CN114066491A (en) Method and device for determining goods replenishment strategy based on multi-cycle total sales forecast
CN118036913A (en) Task allocation method, device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination