CN113191537A - Method, device, equipment and storage medium for predicting express package data - Google Patents
Method, device, equipment and storage medium for predicting express package data Download PDFInfo
- Publication number
- CN113191537A CN113191537A CN202110404057.8A CN202110404057A CN113191537A CN 113191537 A CN113191537 A CN 113191537A CN 202110404057 A CN202110404057 A CN 202110404057A CN 113191537 A CN113191537 A CN 113191537A
- Authority
- CN
- China
- Prior art keywords
- express
- data set
- weekly
- data
- pickup data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000003442 weekly effect Effects 0.000 claims abstract description 221
- 238000012417 linear regression Methods 0.000 claims abstract description 61
- 238000012937 correction Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000004140 cleaning Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims description 73
- 230000006870 function Effects 0.000 claims description 38
- 238000013178 mathematical model Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000000737 periodic effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 238000000611 regression analysis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
Abstract
The invention relates to the field of traffic prediction, and discloses a prediction method, a prediction device, prediction equipment and a storage medium for circumferential parcel data of express delivery, which are used for improving the accuracy of circumferential parcel data prediction in the field of express delivery logistics. The method for predicting the data of the express week package comprises the following steps: carrying out data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set with a preset period from the basic express pickup data set; preprocessing a weekly express pickup data set to obtain a to-be-processed weekly express pickup data set; carrying out logarithmic operation and differential processing on the weekly express pickup data set to be processed to obtain a weekly express pickup data set to be predicted; predicting a to-be-predicted weekly delivery pickup data set by a preset linear regression model to obtain a to-be-corrected weekly delivery pickup data set; and correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
Description
Technical Field
The invention relates to the technical field of traffic prediction, in particular to a method, a device, equipment and a storage medium for predicting express package data.
Background
Along with the continuous development in the logistics field, express delivery transportation is also improving continuously. The method is characterized in that the express receiving quantity is predicted in the logistics field, and due to the fact that express is influenced by factors such as electric business festival activity date, electric business festival activity period, legal festival date, month end time point, temporary vacation date, weather condition, economic environment and the like in the transportation process, once the express receiving quantity is predicted wrongly, waste of human resources and material resources is caused.
The conventional method for predicting the express pickup quantity is to collect a large amount of express pickup data, input the large amount of express pickup data into a preset prediction model, and predict the express pickup data of an express logistics center by using the preset prediction model.
When the prediction mode is adopted to predict express pickup data (such as weekly express pickup data), the predicted express pickup data is greatly different from the actual pickup data, so that the accuracy rate of predicting the express pickup data is low.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for predicting surrounding package data of express delivery, which are used for improving the accuracy of predicting surrounding package data in the field of express delivery logistics.
The invention provides a method for predicting express package pickup data in a first aspect, which comprises the following steps: acquiring an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set of a preset period from the basic express pickup data set; preprocessing the week express pickup data set to obtain a week express pickup data set to be processed; carrying out logarithmic operation and differential processing on the weekly express pickup data set to be processed to obtain a weekly express pickup data set to be predicted; inputting the weekly delivery pickup data set to be predicted into a preset linear regression model, and predicting the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected; and correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining an initial express pickup dataset of an express logistics center, performing data cleaning on the initial express pickup dataset to obtain a basic express pickup dataset, and selecting at least one week express pickup dataset of a preset period from the basic express pickup dataset includes: acquiring an initial express pickup data set of an express logistics center, and judging whether data in the initial express pickup data set accords with a preset data recording rule or not; if the data in the initial express pickup data set do not accord with preset data recording rules, eliminating the data which do not accord with the preset data recording rules to obtain a basic express pickup data set, and selecting at least one week express pickup data set with a preset period from the basic express pickup data set.
Optionally, in a second implementation manner of the first aspect of the present invention, the preprocessing the weekly delivery package data set to obtain a to-be-processed weekly delivery package data set includes: abnormal data are screened out from the weekly express pickup data set, and the abnormal data are used for indicating data missing in the weekly express pickup data set; determining the abnormal data type of the abnormal data, and determining the data with the data type in the week express pickup data set as the abnormal data type as alternative express pickup data; when the abnormal data type of the abnormal data is numerical data, calculating average pickup data of the alternative express pickup data, taking the average pickup data as replacement data of the abnormal data, and determining the replaced weekly express pickup data set as a to-be-processed weekly express pickup data set; and when the abnormal data type of the abnormal data is non-numerical data, taking the data with the most frequent occurrence frequency in the alternative express pickup data as the replacement data of the abnormal data, and determining the substituted express pickup data set as the to-be-processed express pickup data set.
Optionally, in a third implementation manner of the first aspect of the present invention, the performing logarithm operation and difference processing on the to-be-processed weekly delivery package data set to obtain a to-be-predicted weekly delivery package data set includes: sequentially carrying out two times of logarithmic operation on the data in the weekly delivery package data set to be processed to obtain a weekly delivery package data set after operation; and carrying out differential processing on the data in the operated weekly delivery pickup data set to obtain a weekly delivery pickup data set to be predicted.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the inputting the weekly delivery package data set to be predicted into a preset linear regression model, and predicting the weekly delivery package data set to be predicted by using the preset linear regression model to obtain the weekly delivery package data set to be corrected includes: inputting the data in the weekly delivery pickup data set to be predicted into a preset formula of a preset linear regression model, predicting the weekly delivery pickup data set to be predicted by using the preset formula to obtain the weekly delivery pickup data to be corrected, wherein the preset formula is as follows: y is w 'x + e, wherein y represents weekly express pickup data to be corrected, w' represents a model parameter, x represents weekly express pickup data to be predicted, and e represents normal distribution with an error obeying mean value of 0; and integrating the predicted weekly delivery pickup data to be corrected to obtain a weekly delivery pickup data set to be corrected.
Optionally, in a fifth implementation manner of the first aspect of the present invention, before the obtaining an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and before selecting a weekly express pickup data set of at least one preset period from the basic express pickup data set, the method for predicting express weekly pickup data further includes: the method comprises the steps of obtaining a historical express pickup data set of an express logistics center, inputting the historical express pickup data set into a preset formula of a preset linear regression model, and calculating model parameters in the preset formula.
The second aspect of the present invention provides a device for predicting express parcel pickup data, including: the data cleaning module is used for acquiring an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set of a preset period from the basic express pickup data set; the preprocessing module is used for preprocessing the week express pickup data set to obtain a week express pickup data set to be processed; the operation module is used for carrying out logarithmic operation and differential processing on the to-be-processed weekly express pickup data set to obtain a to-be-predicted weekly express pickup data set; the prediction module is used for inputting the weekly delivery pickup data set to be predicted into a preset linear regression model, predicting the weekly delivery pickup data set to be predicted through the preset linear regression model, and obtaining a weekly delivery pickup data set to be corrected; and the correction module is used for correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
Optionally, in a first implementation manner of the second aspect of the present invention, the data cleansing module is specifically configured to: acquiring an initial express pickup data set of an express logistics center, and judging whether data in the initial express pickup data set accords with a preset data recording rule or not; if the data in the initial express pickup data set do not accord with preset data recording rules, eliminating the data which do not accord with the preset data recording rules to obtain a basic express pickup data set, and selecting at least one week express pickup data set with a preset period from the basic express pickup data set.
Optionally, in a second implementation manner of the second aspect of the present invention, the preprocessing module is specifically configured to: abnormal data are screened out from the weekly express pickup data set, and the abnormal data are used for indicating data missing in the weekly express pickup data set; determining the abnormal data type of the abnormal data, and determining the data with the data type in the week express pickup data set as the abnormal data type as alternative express pickup data; when the abnormal data type of the abnormal data is numerical data, calculating average pickup data of the alternative express pickup data, taking the average pickup data as replacement data of the abnormal data, and determining the replaced weekly express pickup data set as a to-be-processed weekly express pickup data set; and when the abnormal data type of the abnormal data is non-numerical data, taking the data with the most frequent occurrence frequency in the alternative express pickup data as the replacement data of the abnormal data, and determining the substituted express pickup data set as the to-be-processed express pickup data set.
Optionally, in a third implementation manner of the second aspect of the present invention, the operation module is specifically configured to: sequentially carrying out two times of logarithmic operation on the data in the weekly delivery package data set to be processed to obtain a weekly delivery package data set after operation; and carrying out differential processing on the data in the operated weekly delivery pickup data set to obtain a weekly delivery pickup data set to be predicted.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the prediction module is specifically configured to: inputting the data in the weekly delivery pickup data set to be predicted into a preset formula of a preset linear regression model, predicting the weekly delivery pickup data set to be predicted by using the preset formula to obtain the weekly delivery pickup data to be corrected, wherein the preset formula is as follows: y is w 'x + e, wherein y represents weekly express pickup data to be corrected, w' represents a model parameter, x represents weekly express pickup data to be predicted, and e represents normal distribution with an error obeying mean value of 0; and integrating the predicted weekly delivery pickup data to be corrected to obtain a weekly delivery pickup data set to be corrected.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the device for predicting express package data further includes: the calculation module is used for acquiring a historical express picking-up data set of the express logistics center, inputting the historical express picking-up data set into a preset formula of a preset linear regression model, and calculating model parameters in the preset formula.
The third aspect of the present invention provides a device for predicting express package pickup data, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to enable the prediction device of the express weekly package data to execute the prediction method of the express weekly package data.
A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the method for predicting express package data described above.
According to the technical scheme, an initial express pickup data set of an express logistics center is obtained, data cleaning is carried out on the initial express pickup data set to obtain a basic express pickup data set, and at least one week express pickup data set of a preset period is selected from the basic express pickup data set; preprocessing the week express pickup data set to obtain a week express pickup data set to be processed; carrying out logarithmic operation and differential processing on the weekly express pickup data set to be processed to obtain a weekly express pickup data set to be predicted; inputting the weekly delivery pickup data set to be predicted into a preset linear regression model, and predicting the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected; and correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set. In the embodiment of the invention, after a week express pickup data set of at least one preset period is screened out from an initial express pickup data set of an express logistics center, logarithm operation and difference processing are carried out on the week express pickup data set to obtain a week express pickup data set to be predicted, and then a preset linear regression model and a preset error correction function are utilized to respectively predict and correct the week express pickup data set to be predicted to obtain a target week express pickup data set, so that the accuracy of predicting the week pickup data in the field of express logistics is improved.
Drawings
Fig. 1 is a schematic diagram of an embodiment of a method for predicting express parcel data in an embodiment of the invention;
fig. 2 is a schematic diagram of another embodiment of the method for predicting express parcel data in an embodiment of the invention;
fig. 3 is a schematic diagram of an embodiment of a prediction device for express parcel data in an embodiment of the invention;
fig. 4 is a schematic view of another embodiment of the prediction device for the data of the express parcel in the embodiment of the invention;
fig. 5 is a schematic diagram of an embodiment of prediction equipment for express package data in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for predicting surrounding package data of express delivery, which are used for improving the accuracy of predicting the surrounding package data in the field of express delivery logistics.
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. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, 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 convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for predicting express surrounding package data according to an embodiment of the present invention includes:
101. acquiring an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set of a preset period from the basic express pickup data set;
it is understood that the execution subject of the present invention may be a prediction device for data of express parcel pickup, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
The initial express pickup data set refers to express pickup quantity data stored in the logistics industry, and can also be express pickup quantity data in the logistics industry within a certain period of time published by a certain statistical organization. Where it is initiated. The database storing the initial express pickup data set comprises express basic information, wherein the express basic information is express basic information of express receiving and express basic information of express sending, and the express basic information specifically comprises but is not limited to: the type and storage time of the express package. It is further noted that the storage time here may be recorded by day storage, or may be recorded by the specific storage time of the recording system.
After the server acquires the initial express pickup data set, data or abnormal data which do not accord with the regulation may exist in the data in the initial express pickup data set, so that data cleaning needs to be performed on the data in the initial express pickup data set at first, a basic express pickup data set is obtained after the data cleaning is performed, at least one week express pickup data set of a preset period is selected from the basic express pickup data set, and the week express pickup data set is used as basic data of a predicted target week express pickup data set.
102. Preprocessing a weekly express pickup data set to obtain a to-be-processed weekly express pickup data set;
after the weekly delivery pickup data set is screened out from the initial delivery pickup data set, preprocessing needs to be performed on the weekly delivery pickup data set, wherein the preprocessing refers to replacing abnormal data in the weekly delivery pickup data set. The pretreatment operation is carried out on the week express pickup data set, so that the follow-up prediction on the target week express pickup data set can be more accurate.
103. Carrying out logarithmic operation and differential processing on the weekly express pickup data set to be processed to obtain a weekly express pickup data set to be predicted;
the to-be-processed week express pickup data set is subjected to logarithm operation and difference processing, so that the data difference between the to-be-processed week express pickup data set is smaller, the stability of data is improved, and the target week express pickup data set is predicted better.
104. Inputting a weekly delivery pickup data set to be predicted into a preset linear regression model, and predicting the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected;
it should be noted that the preset linear regression model is obtained by training a large number of historical express pickup data sets before predicting the target week express pickup data set, and the preset linear regression model capable of accurately predicting the week express pickup data set is obtained through training of a large number of data and correction of an error correction function. The server inputs the weekly delivery pickup data set to be predicted into a preset linear regression model, so that the weekly delivery pickup data set to be predicted can be predicted, and the weekly delivery pickup data set to be corrected is obtained.
105. And correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
In order to ensure the accuracy of the finally obtained target weekly express pickup data set, the server further needs to perform error correction on the to-be-corrected weekly express pickup data set obtained by a preset linear regression model by using a preset error correction function, and the server determines the corrected weekly express pickup data set as the target weekly express pickup data set. By the method, the target week express pickup data set is predicted, and the accuracy of predicting the week express pickup data set is improved.
In the embodiment of the invention, after a week express pickup data set of at least one preset period is screened out from an initial express pickup data set of an express logistics center, logarithm operation and difference processing are carried out on the week express pickup data set to obtain a week express pickup data set to be predicted, and then a preset linear regression model and a preset error correction function are utilized to respectively predict and correct the week express pickup data set to be predicted to obtain a target week express pickup data set, so that the accuracy of predicting the week pickup data in the field of express logistics is improved.
Referring to fig. 2, another embodiment of the method for predicting express package data according to the embodiment of the present invention includes:
201. acquiring a historical express pickup data set of an express logistics center, inputting the historical express pickup data set into a preset formula of a preset linear regression model, and calculating model parameters in the preset formula;
before the server predicts the target week express pickup data set, a linear regression model is constructed firstly, so that the week express pickup data set to be predicted is input into the linear regression model, and prediction of the week express pickup data set can be achieved. It should be noted that, the steps of constructing the linear regression model here are as follows:
(1) collecting a large number of historical express receiving data sets of an express logistics center, wherein the historical express receiving data sets comprise express receiving amount, express sending amount and express basic information;
(2) carrying out data cleaning on the historical express pickup data sets, and screening out at least one week history express pickup data set with a preset period from the historical express pickup data sets after the data cleaning;
(3) preprocessing abnormal data in the history express pickup data set to obtain a history express pickup data set to be processed;
(4) sequentially carrying out two times of logarithmic operation processing and one time of difference processing on data in the week history express pickup data set to be processed so as to reduce the difference between the data and obtain a week history express pickup data set to be predicted;
(5) inputting a weekly history express collecting data set to be predicted into a preset formula of a linear regression model, and calculating model parameters in the preset formula by using a large amount of data so that the difference between the predicted express collecting data and the actual express collecting data at each time is not large, thereby determining the actual parameters of the linear regression model and determining the preset linear regression model capable of predicting;
(6) the output data of the preset linear regression model are corrected by using different error correction functions respectively so as to reduce the difference between the predicted express item acquisition data and the real express item acquisition data.
In the step (5), the preset linear regression model has the following model parameters:
here, the data in the week history express package data set to be predicted may be divided into several groups, for example: data of each week from 1 month to 8 months in 2017 are selected and divided into eight groups of data, the eight groups of data are respectively input into the linear regression model to obtain eight groups of model parameters, and the eight groups of model parameters are respectively weighted to enable the weight sum of the model parameters to be 1. When the model parameters are weighted, the proportion of the model parameter group of the historical express package data is increased as the period is closer to the next period (9 months in 2017), and the more the weighting is added, the more the proportion is distributed. And then integrating the eight groups of model parameters with the additional weights into a group of model parameters, and further determining the model parameters in the linear regression model.
It should be further noted that, in the step (6), the error correction function may be a model error correction function, a measurement error correction function, a truncation error correction function, or a rounding error correction function, and the output data of the preset linear regression model is corrected by the above functions, so as to improve the accuracy of prediction.
202. Acquiring an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set of a preset period from the basic express pickup data set;
specifically, the server acquires an initial express pickup data set of an express logistics center and judges whether data in the initial express pickup data set meet a preset data recording rule or not; if the data in the initial express pickup data set do not accord with the preset data recording rule, the server rejects the data which do not accord with the preset data recording rule to obtain a basic express pickup data set, and at least one week express pickup data set of a preset period is selected from the basic express pickup data set.
The server is equivalent to rejecting the data which is not in accordance with the preset data recording rule in the process of carrying out data cleaning on the initial express item picking data set, and if the data in the initial express item picking data set is not in accordance with the preset data recording rule, abnormal display can occur, such as: the "#####" is displayed in the table of the initial express pickup data set, so that the server cannot know the specific numerical value of the data, and the corresponding data can only be removed. The data cleaning is equivalent to a process for reducing data errors and data inconsistency, and is mainly used for detecting and deleting irregular data, so that the accuracy of analyzing the data is further improved.
In addition, after the initial express pickup data set is cleaned, information data which are not needed in the initial express pickup data set can be removed.
Further, the server needs to screen out a weekly express pickup data set of at least one preset period from the basic express pickup data set as a prediction basis of the target weekly express pickup data set. The preset period herein refers to 7 days, and may be from monday to sunday in one week, and may also be from wednesday to tuesday in the previous week, and is not limited in this application, but once the preset period is determined, the predicted period at the time of subsequent prediction is the same as the predicted period.
203. Preprocessing a weekly express pickup data set to obtain a to-be-processed weekly express pickup data set;
specifically, the server firstly screens abnormal data in the weekly delivery package data set, wherein the abnormal data is used for indicating data missing in the weekly delivery package data set; then the server determines the abnormal data type of the abnormal data, and determines the data with the data type of the week express pickup data set as the abnormal data type as the alternative express pickup data; when the abnormal data type of the abnormal data is numerical data, the server calculates average pickup data of the alternative express pickup data, the average pickup data is used as replacement data of the abnormal data, and the replaced weekly express pickup data set is determined as a to-be-processed weekly express pickup data set; when the abnormal data type of the abnormal data is non-numerical data, the server takes the data with the most frequency in the alternative express pickup data as the replacement data of the abnormal data, and determines the replaced weekly express pickup data set as a to-be-processed weekly express pickup data set.
The server also needs to preprocess the weekly delivery package data set after obtaining the weekly delivery package data set, wherein the preprocessing refers to processing abnormal data in the weekly delivery package data set, so that the data in the weekly delivery package data set can be used as basic data for predicting a target weekly delivery package data set.
In the present application, different processing operations are performed for different types of abnormal data, which are divided into two cases:
the first condition is as follows: when the abnormal data type of the abnormal data is numerical data, the server calculates average pickup data of the alternative express pickup data, the average pickup data is used as replacement data of the abnormal data, and the replaced weekly express pickup data set is determined as a to-be-processed weekly express pickup data set.
For example: table 1, 2017, express item collecting data set display table in 1 month-2 month week
| Date | Zhou express taking data |
| First week of 2017 month 1 | 5000 |
| Second week of 1 month in 2017 | Abnormal data |
| Third week of 1 month in 2017 | 6000 |
| First week of 2017 in 2 months | 4000 |
| Second week of 2 months in 2017 | 5500 |
| Third week of 2 months in 2017 | 3500 |
The abnormal data type of the abnormal data is numerical data, and the average package data may be replaced with 4800 as replacement data of the abnormal data, that is, the abnormal data.
Case two: when the abnormal data type of the abnormal data is non-numerical data, the server takes the data with the most frequency in the alternative express pickup data as the replacement data of the abnormal data, and determines the replaced weekly express pickup data set as a to-be-processed weekly express pickup data set.
The mode principle in statistics is adopted here, the abnormal data type is replaced by non-numerical data, the missing attribute value is filled up by the value with the most dereferencing times of the attribute in all other objects (namely, the value with the highest frequency of occurrence), and the missing attribute value is supplemented by the dereferencing with the highest probability possible.
Specifically, the obtained weekly delivery package data set can be represented by the following table.
Table 2, 2017 year express item picking data set display table
| Date | Zhou express taking data |
| First week of 2017 month 1 | 5000 |
| Second week of 1 month in 2017 | 4800 |
| Third week of 1 month in 2017 | 6000 |
| First week of 2017 in 2 months | 4000 |
| Second week of 2 months in 2017 | 5500 |
| Third week of 2 months in 2017 | 3500 |
| …… | …… |
| First week of 12 months in 2017 | 9000 |
| Second week of 12 months in 2017 | 9856 |
| Third week of 12 months in 2017 | 7562 |
204. Carrying out logarithmic operation and differential processing on the weekly express pickup data set to be processed to obtain a weekly express pickup data set to be predicted;
specifically, the server sequentially performs two logarithmic operations on data in the weekly delivery package data set to be processed to obtain a calculated weekly delivery package data set; and the server performs differential processing on the data in the operated weekly delivery pickup data set to obtain a weekly delivery pickup data set to be predicted.
Because there may be a large difference in the collected data in the weekly delivery package data set, for example: the express item collecting data of 30 months and 9 months in 2017 is 3000, the express item collecting data of 1 months and 10 months in 2017 is 8000, and a large difference exists between the two data, so that in the application, the data in the express item collecting data set in the week are subjected to two times of logarithmic operation in sequence to improve the stability of the express item collecting data set. For example: the method comprises the steps of carrying out logarithm operation twice on express collecting number data 3000 of 30 months and 9 months in 2017 to obtain data of ln (ln (3000)) -2.08024, and carrying out logarithm operation twice on express collecting number data 8000 of 1 month and 10 months in 2017 to obtain data of ln (ln (8000)) -2.19580, so that the difference between the two calculated data is not large, and the accuracy of analyzing the data is further improved.
It can be understood that the data in the weekly express package data set are subjected to difference processing after being subjected to two times of processing in sequence, and the difference processing of the data is further performedThe accuracy of the analysis data is improved. It should be noted that the difference processing here can be forward difference or backward difference or center difference, for the function f (x)k) The specific difference results are as follows:
the first order forward difference is: Δ f (x)k)＝f(xk+1)-f(xk)；
The first order backward difference is: Δ f (x)k)＝f(xk)-f(xk-1)；
The first order center difference is:
in the present application, the difference mode of the difference processing is not limited, and specifically, the difference mode corresponding to the actual situation may be selected to perform the difference processing on the data in the weekly delivery package data set.
Further, after the data in the weekly delivery package data set are subjected to operation and differential processing, the difference value between the data in the weekly delivery package data set and the data is not more than 10 times of the minimum value, so that the accuracy and the stability of data analysis are greatly improved.
205. Inputting a weekly delivery pickup data set to be predicted into a preset linear regression model, and predicting the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected;
specifically, the server inputs data in the weekly delivery pickup data set to be predicted into a preset formula of a preset linear regression model, the weekly delivery pickup data set to be predicted is predicted by using the preset formula, and the weekly delivery pickup data to be corrected is obtained, wherein the preset formula is as follows: y is w 'x + e, wherein y represents weekly express pickup data to be corrected, w' represents a model parameter, x represents weekly express pickup data to be predicted, and e represents normal distribution with an error obeying mean value of 0; and integrating the predicted weekly delivery pickup data to be corrected by the server to obtain a weekly delivery pickup data set to be corrected.
The server inputs the periodic express pickup data set to be predicted into a preset formula of a preset linear regression model, and the periodic express pickup data set to be predicted is predicted through the preset formula to obtain a periodic express pickup data set to be corrected.
Linear regression is a statistical analysis method that utilizes regression analysis in mathematical statistics to determine the interdependent quantitative relationship between two or more variables, and is widely used. Specifically, the expression form of linear regression is s ═ a't + e, s denotes dependent variable data, a' denotes model parameters, t denotes independent variable data, and e denotes a normal distribution with an error obeying a mean value of 0.
The regression analysis, which includes only one independent variable and one dependent variable and the relationship between them can be approximately expressed by a straight line, is called unitary linear regression analysis. If two or more independent variables are included in the regression analysis and there is a linear relationship between the dependent variable and the independent variable, it is called a multiple linear regression analysis.
The data in the weekly delivery pickup data set to be predicted can be directly input into a preset formula in a preset linear regression model, the data in the weekly delivery pickup data set to be predicted can be predicted through the preset formula, the weekly delivery pickup data to be corrected can be obtained, the weekly delivery pickup data to be corrected can be integrated, and the periodic delivery pickup data set to be corrected can be obtained.
206. And correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
It will be appreciated that the preset error correction function herein comprises at least:
(1) model error correction function
In the process of establishing a mathematical model (preset linear regression model), complicated phenomena are required to be abstracted and summarized into the mathematical model, the influence of some secondary factors is usually ignored, and the problem is simplified. Therefore, the mathematical model and the actual problem have a certain error, which is called a model error, and the function for correcting the model error is called a model error correction function.
(2) Measuring error correction function
The data used in the process of building a mathematical model and in the process of specifying operations are often obtained by observation and measurement, and due to the limitations of precision, these data are generally approximate, that is to say the data input to the mathematical model have errors, which are referred to as measurement errors, and the function of correcting the measurement errors is referred to as a measurement error correction function.
(3) Truncation error correction function
Because finite term or finite step operation can only be completed in the actual operation process of the mathematical model, some operations which need to be calculated by the finite or infinite process need to be converted into finite operation to realize the truncation of the infinite process, the generated error becomes a truncation error, and the function for correcting the truncation error is called as a truncation error correction function.
(4) Rounding error correction function
In the process of calculating a mathematical model, due to the limitation of calculation tools, some data are often rounded, only the first few digits are kept as an approximation of the number, the error caused by rounding becomes a rounding error, and a function for correcting the rounding error is called a rounding error correction function.
Further, after the weekly delivery pickup data set to be corrected is calculated and obtained through a preset linear regression model, the error correction function is used for carrying out error correction on the weekly delivery pickup data set, and the prediction result of the target weekly delivery pickup data set is more accurate.
In the embodiment of the invention, after a week express pickup data set of at least one preset period is screened out from an initial express pickup data set of an express logistics center, logarithm operation and difference processing are carried out on the week express pickup data set to obtain a week express pickup data set to be predicted, and then a preset linear regression model and a preset error correction function are utilized to respectively predict and correct the week express pickup data set to be predicted to obtain a target week express pickup data set, so that the accuracy of predicting the week pickup data in the field of express logistics is improved.
The above description is made on the method for predicting the package pickup data in the express delivery cycle in the embodiment of the present invention, and the following description is made on the device for predicting the package pickup data in the express delivery cycle in the embodiment of the present invention, referring to fig. 3, an embodiment of the device for predicting the package pickup data in the express delivery cycle in the embodiment of the present invention includes:
the data cleaning module 301 is configured to acquire an initial express pickup data set of an express logistics center, perform data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and select at least one week express pickup data set of a preset period from the basic express pickup data set;
the preprocessing module 302 is configured to preprocess the weekly delivery pickup dataset to obtain a to-be-processed weekly delivery pickup dataset;
the operation module 303 is configured to perform logarithm operation and difference processing on the to-be-processed weekly express pickup dataset to obtain a to-be-predicted weekly express pickup dataset;
the prediction module 304 is configured to input the weekly delivery pickup data set to be predicted into a preset linear regression model, and predict the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected;
the correcting module 305 is configured to correct the weekly express pickup dataset to be corrected by using a preset error correction function, so as to obtain a target weekly express pickup dataset.
In the embodiment of the invention, after a week express pickup data set of at least one preset period is screened out from an initial express pickup data set of an express logistics center, logarithm operation and difference processing are carried out on the week express pickup data set to obtain a week express pickup data set to be predicted, and then a preset linear regression model and a preset error correction function are utilized to respectively predict and correct the week express pickup data set to be predicted to obtain a target week express pickup data set, so that the accuracy of predicting the week pickup data in the field of express logistics is improved.
Referring to fig. 4, another embodiment of the device for predicting express package data according to the embodiment of the present invention includes:
the data cleaning module 301 is configured to acquire an initial express pickup data set of an express logistics center, perform data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and select at least one week express pickup data set of a preset period from the basic express pickup data set;
the preprocessing module 302 is configured to preprocess the weekly delivery pickup dataset to obtain a to-be-processed weekly delivery pickup dataset;
the operation module 303 is configured to perform logarithm operation and difference processing on the to-be-processed weekly express pickup dataset to obtain a to-be-predicted weekly express pickup dataset;
the prediction module 304 is configured to input the weekly delivery pickup data set to be predicted into a preset linear regression model, and predict the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected;
the correcting module 305 is configured to correct the weekly express pickup dataset to be corrected by using a preset error correction function, so as to obtain a target weekly express pickup dataset.
Optionally, the data cleansing module 301 is specifically configured to:
acquiring an initial express pickup data set of an express logistics center, and judging whether data in the initial express pickup data set accords with a preset data recording rule or not;
if the data in the initial express pickup data set do not accord with preset data recording rules, eliminating the data which do not accord with the preset data recording rules to obtain a basic express pickup data set, and selecting at least one week express pickup data set with a preset period from the basic express pickup data set.
Optionally, the preprocessing module 302 is specifically configured to:
abnormal data are screened out from the weekly express pickup data set, and the abnormal data are used for indicating data missing in the weekly express pickup data set;
determining the abnormal data type of the abnormal data, and determining the data with the data type in the week express pickup data set as the abnormal data type as alternative express pickup data;
when the abnormal data type of the abnormal data is numerical data, calculating average pickup data of the alternative express pickup data, taking the average pickup data as replacement data of the abnormal data, and determining the replaced weekly express pickup data set as a to-be-processed weekly express pickup data set;
and when the abnormal data type of the abnormal data is non-numerical data, taking the data with the most frequent occurrence frequency in the alternative express pickup data as the replacement data of the abnormal data, and determining the substituted express pickup data set as the to-be-processed express pickup data set.
Optionally, the operation module 303 is specifically configured to:
sequentially carrying out two times of logarithmic operation on the data in the weekly delivery package data set to be processed to obtain a weekly delivery package data set after operation;
and carrying out differential processing on the data in the operated weekly delivery pickup data set to obtain a weekly delivery pickup data set to be predicted.
Optionally, the prediction module 304 is specifically configured to:
inputting the data in the weekly delivery pickup data set to be predicted into a preset formula of a preset linear regression model, predicting the weekly delivery pickup data set to be predicted by using the preset formula to obtain the weekly delivery pickup data to be corrected, wherein the preset formula is as follows:
y＝w′x+e，
y represents weekly express pickup data to be corrected, w' represents a model parameter, x represents weekly express pickup data to be predicted, and e represents normal distribution with the error obeying mean value of 0;
and integrating the predicted weekly delivery pickup data to be corrected to obtain a weekly delivery pickup data set to be corrected.
Optionally, the device for predicting the data of the surrounding package for express delivery further includes:
the calculation module 306 is configured to obtain a historical express package data set of the express logistics center, input the historical express package data set into a preset formula of a preset linear regression model, and calculate model parameters in the preset formula.
In the embodiment of the invention, after a week express pickup data set of at least one preset period is screened out from an initial express pickup data set of an express logistics center, logarithm operation and difference processing are carried out on the week express pickup data set to obtain a week express pickup data set to be predicted, and then a preset linear regression model and a preset error correction function are utilized to respectively predict and correct the week express pickup data set to be predicted to obtain a target week express pickup data set, so that the accuracy of predicting the week pickup data in the field of express logistics is improved.
Fig. 3 and 4 describe the prediction device of the express circumferential parcel data in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the prediction device of the express circumferential parcel data in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a device for predicting express package data according to an embodiment of the present invention, where the device 500 for predicting express package data may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing an application 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations in the prediction device 500 for the delivery of the weekly package data. Further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the prediction device 500 for express package data.
The predictive device 500 for express delivery of data from a courier package may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the configuration of the device for predicting express weekly package data shown in fig. 5 does not constitute a limitation on the device for predicting express weekly package data, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
The invention also provides a device for predicting the data of the express weekly packages, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, enable the processor to execute the steps of the method for predicting the data of the express weekly packages in the embodiments.
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 stored therein instructions, which when executed on a computer, cause the computer to perform the steps of the method for predicting express weekly package data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, 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 stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of 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 execute 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-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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 (10)
1. A prediction method for circumferential parcel pickup data of express delivery is characterized by comprising the following steps:
acquiring an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set of a preset period from the basic express pickup data set;
preprocessing the week express pickup data set to obtain a week express pickup data set to be processed;
carrying out logarithmic operation and differential processing on the weekly express pickup data set to be processed to obtain a weekly express pickup data set to be predicted;
inputting the weekly delivery pickup data set to be predicted into a preset linear regression model, and predicting the weekly delivery pickup data set to be predicted through the preset linear regression model to obtain a weekly delivery pickup data set to be corrected;
and correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
2. The method for predicting express circumference package data according to claim 1, wherein the obtaining an initial express package data set of an express logistics center, performing data cleaning on the initial express package data set to obtain a basic package data set, and selecting at least one week package data set of a preset period from the basic package data set comprises:
acquiring an initial express pickup data set of an express logistics center, and judging whether data in the initial express pickup data set accords with a preset data recording rule or not;
if the data in the initial express pickup data set do not accord with preset data recording rules, eliminating the data which do not accord with the preset data recording rules to obtain a basic express pickup data set, and selecting at least one week express pickup data set with a preset period from the basic express pickup data set.
3. The method for predicting the weekly package delivery data of claim 1, wherein the step of preprocessing the weekly package delivery data set to obtain the weekly package delivery data set to be processed comprises:
abnormal data are screened out from the weekly express pickup data set, and the abnormal data are used for indicating data missing in the weekly express pickup data set;
determining the abnormal data type of the abnormal data, and determining the data with the data type in the week express pickup data set as the abnormal data type as alternative express pickup data;
when the abnormal data type of the abnormal data is numerical data, calculating average pickup data of the alternative express pickup data, taking the average pickup data as replacement data of the abnormal data, and determining the replaced weekly express pickup data set as a to-be-processed weekly express pickup data set;
and when the abnormal data type of the abnormal data is non-numerical data, taking the data with the most frequent occurrence frequency in the alternative express pickup data as the replacement data of the abnormal data, and determining the substituted express pickup data set as the to-be-processed express pickup data set.
4. The method for predicting the weekly package pickup data for express delivery according to claim 1, wherein the step of carrying out logarithm operation and difference processing on the weekly package pickup data set to be processed to obtain the weekly package pickup data set to be predicted comprises the following steps:
sequentially carrying out two times of logarithmic operation on the data in the weekly delivery package data set to be processed to obtain a weekly delivery package data set after operation;
and carrying out differential processing on the data in the operated weekly delivery pickup data set to obtain a weekly delivery pickup data set to be predicted.
5. The method for predicting the weekly express package data according to claim 1, wherein the step of inputting the weekly express package data set to be predicted into a preset linear regression model, and predicting the weekly express package data set to be predicted through the preset linear regression model to obtain the weekly express package data set to be corrected comprises the following steps:
inputting the data in the weekly delivery pickup data set to be predicted into a preset formula of a preset linear regression model, predicting the weekly delivery pickup data set to be predicted by using the preset formula to obtain the weekly delivery pickup data to be corrected, wherein the preset formula is as follows:
y＝w′x+e，
y represents weekly express pickup data to be corrected, w' represents a model parameter, x represents weekly express pickup data to be predicted, and e represents normal distribution with the error obeying mean value of 0;
and integrating the predicted weekly delivery pickup data to be corrected to obtain a weekly delivery pickup data set to be corrected.
6. The method for predicting circumferential express package pickup data according to any one of claims 1 to 5, wherein before the initial express package pickup dataset of the express logistics center is obtained, the initial express package pickup dataset is subjected to data cleaning to obtain a basic express package pickup dataset, and at least one circumferential express package pickup dataset of a preset period is selected from the basic express package pickup dataset, the method for predicting circumferential express package pickup data further comprises:
the method comprises the steps of obtaining a historical express pickup data set of an express logistics center, inputting the historical express pickup data set into a preset formula of a preset linear regression model, and calculating model parameters in the preset formula.
7. A prediction device for circumferential parcel pickup data of express delivery is characterized by comprising:
the data cleaning module is used for acquiring an initial express pickup data set of an express logistics center, performing data cleaning on the initial express pickup data set to obtain a basic express pickup data set, and selecting at least one week express pickup data set of a preset period from the basic express pickup data set;
the preprocessing module is used for preprocessing the week express pickup data set to obtain a week express pickup data set to be processed;
the operation module is used for carrying out logarithmic operation and differential processing on the to-be-processed weekly express pickup data set to obtain a to-be-predicted weekly express pickup data set;
the prediction module is used for inputting the weekly delivery pickup data set to be predicted into a preset linear regression model, predicting the weekly delivery pickup data set to be predicted through the preset linear regression model, and obtaining a weekly delivery pickup data set to be corrected;
and the correction module is used for correcting the weekly express pickup data set to be corrected by using a preset error correction function to obtain a target weekly express pickup data set.
8. The device for predicting express parcel data according to claim 7, wherein the data cleansing module is specifically configured to:
acquiring an initial express pickup data set of an express logistics center, and judging whether data in the initial express pickup data set accords with a preset data recording rule or not;
if the data in the initial express pickup data set do not accord with preset data recording rules, eliminating the data which do not accord with the preset data recording rules to obtain a basic express pickup data set, and selecting at least one week express pickup data set with a preset period from the basic express pickup data set.
9. The device for predicting the surrounding parcel pickup data for the express delivery is characterized by comprising the following components: 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 device for predicting express weekly package data to perform the method for predicting express weekly package data according to any one of claims 1-6.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a method for predicting delivery package data according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110404057.8A CN113191537A (en) | 2021-04-15 | 2021-04-15 | Method, device, equipment and storage medium for predicting express package data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110404057.8A CN113191537A (en) | 2021-04-15 | 2021-04-15 | Method, device, equipment and storage medium for predicting express package data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113191537A true CN113191537A (en) | 2021-07-30 |
Family
ID=76974016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110404057.8A Pending CN113191537A (en) | 2021-04-15 | 2021-04-15 | Method, device, equipment and storage medium for predicting express package data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191537A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563560A (en) * | 2017-09-07 | 2018-01-09 | 顺丰速运有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN109583625A (en) * | 2018-10-19 | 2019-04-05 | 顺丰科技有限公司 | One kind pulling part amount prediction technique, system, equipment and storage medium |
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN112070284A (en) * | 2020-08-24 | 2020-12-11 | 上海东普信息科技有限公司 | Screening method, device, equipment and storage medium for component prediction |
| CN112183827A (en) * | 2020-09-15 | 2021-01-05 | 上海东普信息科技有限公司 | Method, device, equipment and storage medium for predicting express monthly pickup quantity |
-
2021
- 2021-04-15 CN CN202110404057.8A patent/CN113191537A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563560A (en) * | 2017-09-07 | 2018-01-09 | 顺丰速运有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN109583625A (en) * | 2018-10-19 | 2019-04-05 | 顺丰科技有限公司 | One kind pulling part amount prediction technique, system, equipment and storage medium |
| CN112070284A (en) * | 2020-08-24 | 2020-12-11 | 上海东普信息科技有限公司 | Screening method, device, equipment and storage medium for component prediction |
| CN112183827A (en) * | 2020-09-15 | 2021-01-05 | 上海东普信息科技有限公司 | Method, device, equipment and storage medium for predicting express monthly pickup quantity |
Non-Patent Citations (2)
| Title |
|---|
| 丁岳维编著: "《经济数学模型》", 31 January 2006, 陕西人民出版社, pages: 35 - 36 * |
| 胡佳迎: ""关于快递行业中货量预测方法的介绍"", 《电脑知识与技术》, no. 8, 15 March 2018 (2018-03-15), pages 158 - 159 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3223170A1 (en) | Data processing method and device in data modeling | |
| US8296224B2 (en) | Constrained optimized binning for scorecards | |
| CN111833594B (en) | Traffic flow prediction method, traffic flow prediction device, electronic device, and storage medium | |
| CN111402017A (en) | Credit scoring method and system based on big data | |
| EP3142050A1 (en) | Predicting attribute values for user segmentation | |
| US9417981B2 (en) | Data processing system, data processing method, and program | |
| CN112070284A (en) | Screening method, device, equipment and storage medium for component prediction | |
| CN106452934B (en) | Method and device for analyzing network performance index change trend | |
| CN112686433B (en) | Method, device, equipment and storage medium for predicting express quantity | |
| CN115756812A (en) | Resource adjusting method and device and storage medium | |
| CN113205230A (en) | Data prediction method, device and equipment based on model set and storage medium | |
| CN113191537A (en) | Method, device, equipment and storage medium for predicting express package data | |
| CN112785057A (en) | Component prediction method, device, equipment and storage medium based on exponential smoothing | |
| CN112183827A (en) | Method, device, equipment and storage medium for predicting express monthly pickup quantity | |
| US20020156603A1 (en) | Modeling tool with controlled capacity | |
| CN111737233A (en) | Data monitoring method and device | |
| CN109376929B (en) | Distribution parameter determination method, distribution parameter determination device, storage medium, and electronic apparatus | |
| CN111445969A (en) | Sales prediction method and system capable of flexibly adapting to noise | |
| US20210183528A1 (en) | Information processing apparatus, information processing method, and non-transitory computer readable medium | |
| CN114723145A (en) | Method and system for determining number of intelligent counters based on transaction amount | |
| CN111339156B (en) | Method, apparatus and computer readable storage medium for long-term determination of business data | |
| KR101340227B1 (en) | Method and computer-readable recording medium for treating helicopter flight test data | |
| CN115424826B (en) | Method, device, equipment and storage medium for determining cooling performance of converter transformer | |
| CN111984636B (en) | Data modeling method, device, equipment and storage medium | |
| JP7322918B2 (en) | Program, information processing device, and learning model generation method |
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 |