CN116167692A - Automatic optimization method and system combining manifest information - Google Patents

Automatic optimization method and system combining manifest information Download PDF

Info

Publication number
CN116167692A
CN116167692A CN202310151139.5A CN202310151139A CN116167692A CN 116167692 A CN116167692 A CN 116167692A CN 202310151139 A CN202310151139 A CN 202310151139A CN 116167692 A CN116167692 A CN 116167692A
Authority
CN
China
Prior art keywords
cargo
cluster
goods
destination
time sequence
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.)
Granted
Application number
CN202310151139.5A
Other languages
Chinese (zh)
Other versions
CN116167692B (en
Inventor
李强
王宏
杨靖
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.)
Shanghai Langhui Huike Technology Co ltd
Original Assignee
Shanghai Langhui Huike 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 Shanghai Langhui Huike Technology Co ltd filed Critical Shanghai Langhui Huike Technology Co ltd
Priority to CN202310151139.5A priority Critical patent/CN116167692B/en
Publication of CN116167692A publication Critical patent/CN116167692A/en
Application granted granted Critical
Publication of CN116167692B publication Critical patent/CN116167692B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

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

Abstract

The invention relates to the technical field of goods storage, and discloses an automatic optimizing method and system combined with manifest information, wherein the method comprises the following steps: constructing a cargo demand quantity time sequence of each cargo destination coordinate corresponding to each type of cargo; performing cluster analysis on the cargo demand quantity time sequence of each type of cargo to form a plurality of clusters of each type of cargo; carrying out probability distribution statistics on the cargo demand quantity in different clusters to serve as a time sequence demand characteristic; and selecting a cluster with the most obvious current time sequence demand characteristics, and distributing cargoes to a shipment warehouse corresponding to a cargo destination in the cluster in advance. According to the invention, different cargo destinations are clustered by combining historical manifest information, and the cargo destinations contained in each cluster after clustering have similar time sequence demand characteristics for the same cargo, so that the cluster with the most obvious current time sequence demand characteristics is selected, and the cargo is distributed to the cargo warehouse corresponding to the cargo destination in the cluster in advance, thereby improving the subsequent cargo delivery speed.

Description

Automatic optimization method and system combining manifest information
Technical Field
The invention relates to the technical field of cargo storage optimization, in particular to an automatic optimization method and system combined with manifest information.
Background
With the rapid development of electronic commerce, warehouse logistics is increasingly important. The invention provides an automatic optimizing method and system combining manifest information, aiming at the problem that the existing warehousing mode is difficult to optimize warehousing layout and causes larger logistics expense due to larger difference of the demand degrees of different areas on commodities.
Disclosure of Invention
In view of the above, the present invention provides an automatic optimization method for combining manifest information, which aims at: 1) Acquiring cargo demand quantity time sequence of different cargo destination coordinates by combining historical manifest information, performing cluster analysis on the cargo demand quantity time sequence of each type of cargo to form a plurality of clusters of each type of cargo, wherein each cluster comprises a plurality of cargo destinations, clustering is performed by using a time sequence mean value only relative to a traditional clustering algorithm, the distance influencing factors of the destination coordinates are added on the basis of the time sequence, the cargo destination coordinates in each cluster are close as much as possible on the basis of ensuring that the cargo destinations contained in each cluster have similar time sequence demand characteristics, further, the cluster with the most obvious current time sequence demand characteristics is selected, and the cargo is pre-distributed to a cargo warehouse corresponding to the cargo destination in the cluster, wherein the more obvious the current time sequence demand characteristics are, the larger the demand of the cargo destination in the cluster on the cargo is indicated, so that the nearby cargo warehouse has enough cargo storage capacity before submitting the manifest request, and the cargo request speed is improved; 2) The method comprises the steps of performing pre-clustering treatment before cluster analysis, selecting the cluster number with larger similarity among clusters and larger dispersion among clusters as the optimal cluster number by analyzing the similarity among clusters and the outer dispersion among clusters under different cluster numbers, improving the clustering effect, sequentially adopting two clustering modes, firstly adopting a Kmeans algorithm to divide and obtain the clustering result of the maximum cluster number, diffusing the dimensionality of the clustering result, avoiding sinking into a local optimal solution, and combining the clustering clusters aiming at the clustering result to form a final clustering result conforming to the optimal clustering number.
In order to achieve the above object, the present invention provides an automatic optimizing method for combining manifest information, comprising the steps of:
s1: collecting a historical manifest form and preprocessing to obtain preprocessed historical manifest information, wherein the manifest information comprises manifest generation time, cargo destination coordinates, shipping warehouse coordinates, cargo names and cargo demand quantity;
s2: constructing a cargo demand quantity time sequence of each cargo destination coordinate corresponding to each type of cargo;
s3: performing cluster analysis on the cargo demand quantity time sequence of each type of cargo to form a plurality of clusters of each type of cargo,
wherein each cluster comprises a plurality of cargo destinations;
s4: carrying out probability distribution statistics on the required quantity of the goods in different clusters to obtain time sequence required characteristics of the goods in different clusters;
s5: selecting a cluster with the most obvious current time sequence demand characteristic, and distributing cargoes to a shipment warehouse corresponding to a cargo destination in the cluster in advance, wherein the more obvious the current time sequence demand characteristic is, the larger the demand of the cargo destination in the cluster for the cargoes is.
As a further improvement of the present invention:
optionally, in the step S1, a history manifest form is collected and preprocessed to obtain preprocessed history manifest information, which includes:
Collecting historical manifest forms, wherein the historical manifest forms represent and record the cargo transportation histories of different cargoes sent to different destinations, and the historical manifest forms comprise manifest generation time, cargo names, cargo demand quantity, cargo warehouse coordinates and corresponding cargo destination coordinates, and each manifest form records the cargo category required by the same cargo destination coordinate at the manifest generation time and the corresponding cargo demand quantity;
preprocessing the collected historical manifest form to obtain preprocessed historical manifest information, wherein the preprocessing flow of the historical manifest form is as follows:
s11: traversing goods s n Where n.epsilon.1, N]N corresponds to the total number of names of the goods, and the goods with different names belong to different categories;
s12: for goods s in time sequence order n History manifest table of (c)The grids are ordered, goods destination coordinates, goods demand and goods warehouse coordinates are extracted from the historical manifest form, and the extracted information is used as goods demand information;
s13: aligning the cargo demand information of the same cargo destination under different time sequence information according to the cargo destination coordinates to obtain the preprocessed cargo s n Wherein the column information of the history manifest information corresponds to manifest generation time, and each column information represents the cargo demand information of the same cargo destination for the same cargo at different manifest generation times.
In the embodiment of the invention, the manifest generation time is the time of applying for the cargoes by the cargo destination, when the cargo destination sends out a request for applying for the cargoes and fills in the required cargo category and the corresponding cargo required quantity, the cargo transportation system receives the application of the cargo destination and selects a warehouse closest to the cargo destination and with the storage cargo quantity meeting the cargo destination requirement as a shipping warehouse, and a corresponding manifest form is generated based on the coordinates of the shipping warehouse.
Optionally, the step S2 constructs a cargo demand number timing sequence of the cargo destination coordinates corresponding to each type of cargo, including:
construction of each class of goods s n Corresponding cargo destination coordinate s n (h) Is a time sequence of the number of cargo demands, wherein s n (h) Representing goods s in historical manifest information n Is the h cargo destination coordinate, h E [1, n ] h ]，n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates, the constructed cargo destination coordinates s n (h) The cargo demand quantity time sequence is as follows:
X n,h ＝(x n,h (t 1 ),x n,h (t 2 ),...,x n,h (t i ),...,x n,h (t L ))
wherein:
X n,h representing cargo destination coordinates s n (h) Is a time sequence of the cargo demand quantity;
{t i |i∈[1,L]preset is indicated by }Dividing L time periods first, t i Representing the ith time period divided, in one embodiment of the present invention, each time period is 1 month in length;
x n,h (t i ) Indicated in time period t i In, cargo destination coordinates s n (h) For goods s n Is the total required quantity of goods;
goods s n Corresponding to any two different cargo destination coordinates s n (h a ),s n (h b ) The time sequence of the cargo demand quantity is respectively as follows
Figure BDA0004090872730000023
Wherein h is a ,h b ∈[1,n h ]，s n (h a )≠s n (h b )。
Optionally, in the step S3, a time sequence of the cargo demand number of each type of cargo is subjected to cluster analysis to form a plurality of clusters of each type of cargo, including:
for each type of goods s n N corresponding to h Clustering analysis is carried out on the time sequence of the quantity of the individual goods required to form goods s n Each cluster comprises a plurality of groups of cargo demand quantity time sequence corresponding to a plurality of cargo destinations, wherein the cluster analysis flow is as follows:
s31: determining the goods s n The corresponding maximum cluster number is k max Optimum cluster number k * Wherein
Figure BDA0004090872730000021
n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates;
s32: determining k max The method comprises the steps of establishing a corresponding cluster by using centers in initial clusters, and determining the current iteration number g of the centers in the clusters, wherein each initial cluster center is a cargo s n The corresponding cargo destination coordinate, the determined k initial intra-cluster center is z n,k (0)，k∈[1,k max ]Then the result obtained by the center in the kth initial cluster at the z-th iteration is z n,k (g) The initial value of g is 1;
S33: calculating the similarity of the goods destination coordinates of the non-cluster center and the cluster center, wherein the goods destination coordinates s of the non-cluster center n (h ′ ) From the intra-cluster center z n,k (g) The similarity calculation formula of (2) is：
Figure BDA0004090872730000022
Wherein:
alpha represents a distance coefficient, which is set to 0.01;
distance(s n (h ′ ),z n,k (g) Representing cargo destination coordinates s n (h ′ ) From the intra-cluster center z n,k (g) Is a distance of (2);
x n，h′ (t i ) Indicated in time period t i In, cargo destination coordinates s n (h') for goods s n Is the total required quantity of goods; x's' n，k (t i ) Indicated in time period t i In, cargo destination coordinate z n，k (g) For goods s n Is the total required quantity of goods;
sim(s n (h′)，z n，k (g) Destination coordinates s of goods representing centers in non-clusters n (h') and the intra-cluster center z n，k (g) Similarity of (2);
destination coordinates s of goods to be not center in cluster n (h') distributing the cluster to the cluster corresponding to the center in the cluster with the highest similarity;
s34: updating the center in each cluster, wherein the updating principle of the center in each cluster is as follows: calculating the sequence average value of the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster, calculating the Euclidean distance between the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster and the sequence average value, and selecting the cargo destination coordinate corresponding to the cargo demand quantity time sequence with the smallest Euclidean distance as the updated center in the cluster;
If k max No occurrence of center in each clusterIf the change occurs, the clustering is terminated to obtain k max Cluster, otherwise let g=g+1, return to step S33;
s35: calculating the intra-cluster center similarity of any two clusters, wherein the calculation formula of the similarity is the formula in the step S33;
s36: combining the two clusters with the highest similarity, returning to the step S35 until the current cluster number reaches the optimal cluster number k * 。
Optionally, in the step S4, performing probability distribution statistics on the required quantity of goods in different clusters includes:
for goods s in different clusters n Carrying out probability distribution statistics on the required quantity of the goods, and taking the probability distribution statistics result as goods s n The time sequence demand characteristics in different clusters, wherein the probability distribution statistical formula of the cargo demand quantity in the kth cluster is as follows:
Figure BDA0004090872730000031
wherein:
P n，k (t i ) Indicated in time period t i In, probability distribution of cargo demand quantity in kth cluster;
sum(k，s n ，t i ) Indicated in time period t i Within, all cargo destinations within the kth cluster are for cargo s n Is not required.
Optionally, the step S5 selects a cluster with the most obvious current time sequence demand feature, and distributes the goods to a shipping warehouse corresponding to a goods destination in the cluster in advance, including:
setting a historical time period with highest similarity with the current time period, wherein the historical time period with highest similarity with the current time period is a last year contemporaneous time period and a last month time period in sequence;
Traversing goods s n K in the history period * The probability distribution of each cluster is that the cluster with the largest probability distribution is selected as the cluster with the most obvious current time sequence demand characteristics;
and distributing the cargoes to a shipping warehouse nearest to the destination of the cargoes in the cluster in advance according to the selected cluster.
Alternatively, the step S31 determines the optimal cluster number k using the following steps * ：
S311: setting the cluster numbers to be 1 and k respectively max 1 and k are obtained according to steps S32 to S34, respectively max A cluster;
s312: respectively calculating 1 cluster and k max Sum of squares of similarity of clusters, sum of squares of similarity of 1 cluster being sse 1 ，k max The sum of the squares of the similarity of the clusters is
Figure BDA0004090872730000033
Wherein the sum of squares of the similarity of k clusters calculates the formula sse k The method comprises the following steps:
Figure BDA0004090872730000032
wherein:
p represents the cargo destination coordinates of the non-intra-cluster center in the j-th cluster, C j A cargo destination coordinate set representing a non-intra-cluster center in a j-th cluster, z j Representing the intra-cluster center of the jth cluster;
s313: setting an optimal cluster number k * An initial value of 2 and a maximum value of k max Setting the number of clusters in steps S32 to S34 to k * Calculating to obtain k * Similarity threshold ratio for individual clusters:
Figure BDA0004090872730000034
s314: calculation based on the number of clusters k * Discrete threshold of classification results of (a):
Figure BDA0004090872730000041
wherein:
Figure BDA0004090872730000042
represents k * Maximum similarity between the intra-cluster node of the kth cluster in the clusters and the intra-cluster nodes of other different clusters, wherein the intra-cluster node comprises cargo destination coordinates of non-intra-cluster centers and intra-cluster centers, and a similarity calculation formula is the formula in the step S33;
S315: constructing a clustering evaluation index:
Figure BDA0004090872730000043
wherein:
k * ∈[2，k max ]is selected such that D (k * ) Up to a maximum k * As the final optimal cluster number k * 。
Alternatively, the step S32 employs the following steps to determine k max Center within each initial cluster:
s321: calculating to obtain goods s n Arbitrary two different cargo destination coordinates s n (h a )，s n (h b ) Corresponding time sequence of cargo demand quantity
Figure BDA00040908727300000412
Distance d (h) a ，h b ) And (3) forming a distance matrix: />
Figure BDA0004090872730000044
Wherein:
d(n h 1) represents cargo destination coordinates s n (n h ) Coordinates s with destination of goods n (1) Corresponding time sequence of cargo demand quantity
Figure BDA00040908727300000413
X n，1 A distance therebetween;
s322: combining two different cargo destination coordinates with a distance less than a preset threshold value in a distance matrix intoA class of goods destination coordinates, if the class number after combination is smaller than k max Then the preset value threshold is increased until the class number after combination is equal to or greater than k max ；
S323: selecting a cargo destination coordinate from the destination coordinates of each type of cargo as a candidate coordinate, so that a candidate evaluation function value reaches the minimum, wherein the candidate evaluation function is as follows:
Figure BDA0004090872730000045
wherein:
v represents the destination coordinates s of the goods in the destination coordinates of the m-th class of goods n (v)，Ω m Represents the cargo destination coordinate set, mu, in the m-th cargo destination coordinates m The distance average value of the cargo demand quantity time sequence corresponding to any two cargo destination coordinates in the mth cargo destination coordinates is represented;
S324: comparing candidate evaluation function values of candidate coordinates in destination coordinates of each type of goods, and selecting k with the minimum candidate evaluation function value max The candidate coordinates are taken as the initial intra-cluster centers.
Optionally, the distance calculation in step S321 includes:
for goods s n Arbitrary two different cargo destination coordinates s n (h a )，s n (h b ) Corresponding time sequence of cargo demand quantity
Figure BDA0004090872730000046
Wherein:
Figure BDA0004090872730000047
Figure BDA0004090872730000048
initialization of
Figure BDA0004090872730000049
The distance of (2) is:
dis(t 1 ，t 1 )＝0
for a pair of
Figure BDA00040908727300000410
Wherein the iteration formula is:
Figure BDA00040908727300000411
Figure BDA0004090872730000051
wherein:
t r ∈[t 1 ，t L ]；
i represents a penalty matrix if
Figure BDA0004090872730000052
Less than the preset distance threshold, then I (t r ，t r-1 ) Is 1, otherwise I (t r ，t r-1 ) Is 0;
repeating the iteration until dis (t L ，t L ) And dis (t) L ，t L ) As a time series sequence of the number of goods required
Figure BDA0004090872730000053
Distance d (h a ，h b )。
In order to solve the above problems, the present invention provides an automatic optimizing system in combination with manifest information, the system comprising:
the history manifest processing device is used for collecting a history manifest form and preprocessing the history manifest form to obtain preprocessed history manifest information;
the time sequence demand analysis device is used for constructing a cargo demand quantity time sequence of each cargo destination coordinate corresponding to each cargo, carrying out cluster analysis on the cargo demand quantity time sequence of each cargo to form a plurality of clusters of each cargo, and carrying out probability distribution statistics on cargo demand quantity in different clusters to obtain time sequence demand characteristics of the cargoes in different clusters;
And the goods storage amount optimizing module of the goods delivery warehouse is used for selecting the cluster with the most obvious current time sequence demand characteristic and distributing the goods to the goods delivery warehouse corresponding to the goods destination in the cluster in advance.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
a memory storing at least one instruction;
the communication interface is used for realizing the communication of the electronic equipment; and
And the processor executes the instructions stored in the memory to realize the automatic optimization method for combining the manifest information.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one instruction that is executed by a processor in an electronic device to implement the above-mentioned automatic optimization method in combination with manifest information.
Compared with the prior art, the invention provides an automatic optimizing method combined with manifest information, and the technology has the following advantages:
firstly, the scheme provides a warehouse optimization method combining manifest information, a historical manifest form is collected, wherein the historical manifest form represents and records the cargo transportation history conditions of different cargoes sent to different destinations, the cargo transportation history conditions comprise manifest generation time, cargo names, cargo demand numbers, cargo warehouse coordinates and corresponding cargo destination coordinates, each manifest form records cargo types required by the same cargo destination coordinates at the manifest generation time and corresponding cargo demand numbers, further, the historical manifest information is combined to obtain cargo demand number time sequence sequences of the different cargo destination coordinates, clustering analysis is carried out on the cargo demand number time sequence sequences of each type of cargoes to form a plurality of clusters of each type of cargoes, wherein each cluster comprises a plurality of cargo destinations, compared with a traditional clustering algorithm, only a time sequence average value is used for clustering, distance influence factors of the destination coordinates are added on the basis of the time sequence sequences, the condition that the cargo destinations contained in each cluster have similar time sequence demand characteristics is guaranteed, the cargo coordinates in each cluster are selected as far as possible, further, the current demand characteristics are most distributed to the cargo in the clusters in advance, the current cluster has obvious time sequence demand characteristics, and the current demand is required by the cargo warehouse has high enough speed before the cargo is requested to be delivered to the cargo in the cargo warehouse.
Meanwhile, the scheme provides a cargo destination clustering method for each type of cargo s n N corresponding to h Clustering analysis is carried out on the time sequence of the quantity of the individual goods required to form goods s n Each cluster comprises a plurality of groups of cargo demand quantity time sequence corresponding to a plurality of cargo destinations, wherein the cluster analysis flow is as follows: determining the goods s n The corresponding maximum cluster number is k max Optimum cluster number k * Wherein
Figure BDA0004090872730000054
n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates; determining k max The method comprises the steps of establishing a corresponding cluster by using centers in initial clusters, and determining the current iteration number g of the centers in the clusters, wherein each initial cluster center is a cargo s n The corresponding cargo destination coordinate, the determined k initial intra-cluster center is z n，k (0)，k∈[1，k max ]Then the result obtained by the center in the kth initial cluster at the z-th iteration is z n，k (g) The initial value of g is 1; calculating the similarity of the goods destination coordinates of the non-cluster center and the cluster center, wherein the goods destination coordinates s of the non-cluster center n (h') and the intra-cluster center z n，k (g) The similarity calculation formula of (2) is: />
Figure BDA0004090872730000061
Wherein: alpha represents a distance coefficient, which is set to 0.01; distance(s) n (h′)，z n，k (g) Representing cargo destination coordinates s n (h') and the intra-cluster center z n，k (g) Is a distance of (2); x is x n，h′ (t i ) Indicated in time period t i In, cargo destination coordinates s n (h') for goods s n Is the total required quantity of goods; x's' n，k (t i ) Indicated in time period t i In, cargo destination coordinate z n，k (g) For goods s n Is the total required quantity of goods; sim(s) n (h′)，z n，k (g) Destination coordinates s of goods representing centers in non-clusters n (h') and the intra-cluster center z n，k (g) Similarity of (2); destination coordinates s of goods to be not center in cluster n (h') distributing the cluster to the cluster corresponding to the center in the cluster with the highest similarity; updating the center in each cluster, wherein the updating principle of the center in each cluster is as follows: calculating the sequence average value of the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster, calculating the Euclidean distance between the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster and the sequence average value, and selecting the cargo destination coordinate corresponding to the cargo demand quantity time sequence with the smallest Euclidean distance as the updated center in the cluster; if k max If the center in each cluster does not change, the clustering is terminated to obtain k max A cluster; calculating the intra-cluster center similarity of any two clusters; iteratively combining the two clusters with the highest similarity until the current cluster number reaches the optimal cluster number k * . The method comprises the steps of pre-clustering before cluster analysis, selecting the cluster number with larger similarity and outer dispersion as the optimal cluster number by analyzing the similarity and outer dispersion between clusters under different cluster numbers, improving the clustering effect, adopting two clustering modes sequentially, firstly adopting Kmeans algorithm to divide and obtain the clustering result of the maximum cluster number, diffusing the dimension of the clustering result, avoiding sinking into local optimal solution, and aiming at clusteringAnd carrying out cluster merging treatment on the class results to form a final cluster result conforming to the optimal cluster number.
Drawings
FIG. 1 is a flow chart of an automatic optimizing method for combining manifest information according to an embodiment of the present invention;
FIG. 2 is a functional block diagram of an automatic optimizing system combined with manifest information according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for implementing an automatic optimization method combined with manifest information according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an automatic optimization method combined with manifest information. The execution subject of the automatic optimizing method combined with manifest information includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the automatic optimization method for combining manifest information may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
s1: and acquiring and preprocessing a historical manifest form to obtain preprocessed historical manifest information, wherein the manifest information comprises manifest generation time, cargo destination coordinates, shipping warehouse coordinates, cargo names and cargo demand quantity.
The step S1 is to collect and preprocess a history manifest form to obtain preprocessed history manifest information, and comprises the following steps:
collecting historical manifest forms, wherein the historical manifest forms represent and record the cargo transportation histories of different cargoes sent to different destinations, and the historical manifest forms comprise manifest generation time, cargo names, cargo demand quantity, cargo warehouse coordinates and corresponding cargo destination coordinates, and each manifest form records the cargo category required by the same cargo destination coordinate at the manifest generation time and the corresponding cargo demand quantity;
Preprocessing the collected historical manifest form to obtain preprocessed historical manifest information, wherein the preprocessing flow of the historical manifest form is as follows:
s11: traversing goods s n Where n.epsilon.1, N]N corresponds to the total number of names of the goods, and the goods with different names belong to different categories;
s12: for goods s in time sequence order n Ordering the historical manifest forms of the goods, extracting the destination coordinates, the demand of the goods and the warehouse coordinates of the goods from the historical manifest forms, and taking the extracted information as the demand information of the goods;
s13: aligning the cargo demand information of the same cargo destination under different time sequence information according to the cargo destination coordinates to obtain the preprocessed cargo s n Wherein the column information of the history manifest information corresponds to manifest generation time, and each column information represents the cargo demand information of the same cargo destination for the same cargo at different manifest generation times.
S2: and constructing a cargo demand quantity time sequence corresponding to each cargo destination coordinate of each type of cargo.
And step S2, constructing a cargo demand quantity time sequence of cargo destination coordinates corresponding to each type of cargo, comprising the following steps:
Construction of each class of goods s n Corresponding cargo destination coordinate s n (h) Is a time sequence of the number of cargo demands, wherein s n (h) Representing goods s in historical manifest information n Is the h cargo destination coordinate, h E [1, n ] h ]，n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates, the constructed cargo destination coordinates s n (h) The cargo demand quantity time sequence is as follows:
X n，h ＝(x n，h (t 1 )，x n，h (t 2 )，...，x n，h (t i )，...，x n，h (t L ))
wherein:
X n，h representing cargo destination coordinates s n (h) Is a time sequence of the cargo demand quantity;
{t i |i∈[1，L]the pre-divided L time periods, t i Representing the ith time period divided, in one embodiment of the present invention, each time period is 1 month in length;
x n，h (t i ) Indicated in time period t i In, cargo destination coordinates s n (h) For goods s n Is the total required quantity of goods;
goods s n Corresponding to any two different cargo destination coordinates s n (h a )，s n (h b ) The time sequence of the cargo demand quantity is respectively as follows
Figure BDA0004090872730000073
Wherein h is a ，h b ∈[1，n h ]，s n (h a )≠s n (h b )。
S3: and carrying out cluster analysis on the cargo demand quantity time sequence of each type of cargo to form a plurality of clusters of each type of cargo, wherein each cluster comprises a plurality of cargo destinations.
In the step S3, cluster analysis is performed on the time sequence of the cargo demand quantity of each type of cargo to form a plurality of clusters of each type of cargo, including:
For each type of goods s n N corresponding to h Clustering analysis is carried out on the time sequence of the quantity of the individual goods required to form goods s n Each cluster comprises a plurality of groups of cargo demand quantity time sequence corresponding to a plurality of cargo destinations, wherein the cluster analysis flow is as follows:
s31: determining the goods s n The corresponding maximum cluster number is k max Optimum cluster numberk * Wherein
Figure BDA0004090872730000071
n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates;
s32: determining k max The method comprises the steps of establishing a corresponding cluster by using centers in initial clusters, and determining the current iteration number g of the centers in the clusters, wherein each initial cluster center is a cargo s n The corresponding cargo destination coordinate, the determined k initial intra-cluster center is z n，k (0)，k∈[1，k max ]Then the result obtained by the center in the kth initial cluster at the z-th iteration is z n，k (g) The initial value of g is 1;
s33: calculating the similarity of the goods destination coordinates of the non-cluster center and the cluster center, wherein the goods destination coordinates s of the non-cluster center n (h') and the intra-cluster center z n，k (g) The similarity calculation formula of (2) is:
Figure BDA0004090872730000072
wherein:
alpha represents a distance coefficient, which is set to 0.01;
distance(s n (h′)，z n，k (g) Representing cargo destination coordinates s n (h') and the intra-cluster center z n，k (g) Is a distance of (2);
x n，h′ (t i ) Indicated in time period t i In, cargo destination coordinates s n (h') for goods s n Is the total required quantity of goods;
x′ n，k (t i ) Indicated in time period t i In, cargo destination coordinate z n，k (g) For goods s n Is the total required quantity of goods;
sim(s n (h′)，z n，k (g) Destination coordinates s of goods representing centers in non-clusters n (h') and the intra-cluster center z n，k (g) Similarity of (2);
destination coordinates s of goods to be not center in cluster n (h') distributing the cluster to the cluster corresponding to the center in the cluster with the highest similarity;
s34: updating the center in each cluster, wherein the updating principle of the center in each cluster is as follows: calculating the sequence average value of the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster, calculating the Euclidean distance between the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster and the sequence average value, and selecting the cargo destination coordinate corresponding to the cargo demand quantity time sequence with the smallest Euclidean distance as the updated center in the cluster;
if k max If the center in each cluster does not change, the clustering is terminated to obtain k max Cluster, otherwise let g=g+1, return to step S33;
s35: calculating the intra-cluster center similarity of any two clusters, wherein the calculation formula of the similarity is the formula in the step S33;
s36: combining the two clusters with the highest similarity, returning to the step S35 until the current cluster number reaches the optimal cluster number k * 。
S4: and carrying out probability distribution statistics on the required quantity of the goods in different clusters to obtain time sequence demand characteristics of the goods in different clusters.
And in the step S4, carrying out probability distribution statistics on the cargo demand quantity in different clusters, wherein the method comprises the following steps:
for goods s in different clusters n Carrying out probability distribution statistics on the required quantity of the goods, and taking the probability distribution statistics result as goods s n The time sequence demand characteristics in different clusters, wherein the probability distribution statistical formula of the cargo demand quantity in the kth cluster is as follows:
Figure BDA0004090872730000081
wherein:
P n，k (t i ) Indicated in time period t i In, probability distribution of cargo demand quantity in kth cluster;
sum(k，s n ，t i ) Indicated in time period t i Within, all cargo destinations within the kth cluster are for cargo s n Is not required.
S5: selecting a cluster with the most obvious current time sequence demand characteristic, and distributing cargoes to a shipment warehouse corresponding to a cargo destination in the cluster in advance, wherein the more obvious the current time sequence demand characteristic is, the larger the demand of the cargo destination in the cluster for the cargoes is.
And S5, selecting the cluster with the most obvious current time sequence demand characteristic, and distributing the goods to a delivery warehouse corresponding to the goods destination in the cluster in advance, wherein the method comprises the following steps:
setting a historical time period with highest similarity with the current time period, wherein the historical time period with highest similarity with the current time period is a last year contemporaneous time period and a last month time period in sequence;
Traversing goods s n K in the history period * The probability distribution of each cluster is that the cluster with the largest probability distribution is selected as the cluster with the most obvious current time sequence demand characteristics;
and distributing the cargoes to a shipping warehouse nearest to the destination of the cargoes in the cluster in advance according to the selected cluster.
As another preferred embodiment of the present invention, the step S31 determines the optimal cluster number k by using the following steps * ：
S311: setting the cluster numbers to be 1 and k respectively max 1 and k are obtained according to steps S32 to S34, respectively max A cluster;
s312: respectively calculating 1 cluster and k max Sum of squares of similarity of clusters, sum of squares of similarity of 1 cluster being sse 1 ，k max The sum of the squares of the similarity of the clusters is
Figure BDA0004090872730000083
Wherein the sum of squares of the similarity of k clusters calculates the formula sse k The method comprises the following steps:
Figure BDA0004090872730000082
wherein:
p represents the cargo destination coordinates of the non-intra-cluster center in the j-th cluster, C j A cargo destination coordinate set representing a non-intra-cluster center in a j-th cluster, z j Representing the intra-cluster center of the jth cluster;
s313: setting an optimal cluster number k * An initial value of 2 and a maximum value of k max Setting the number of clusters in steps S32 to S34 to k * Calculating to obtain k * Similarity threshold ratio for individual clusters:
Figure BDA00040908727300000912
s314: calculation based on the number of clusters k * Discrete threshold of classification results of (a):
Figure BDA0004090872730000091
wherein:
Figure BDA0004090872730000092
represents k * Maximum similarity between the intra-cluster node of the kth cluster in the clusters and the intra-cluster nodes of other different clusters, wherein the intra-cluster node comprises cargo destination coordinates of non-intra-cluster centers and intra-cluster centers, and a similarity calculation formula is the formula in the step S33;
s315: constructing a clustering evaluation index:
Figure BDA0004090872730000093
wherein:
k * ∈[2，k max ]is selected such that D (k * ) Up to a maximum k * As the final optimal cluster number k * 。
As another preferred embodiment of the present invention, the step S32 employs the following steps to determine k max Center within each initial cluster:
S321: calculating to obtain goods s n Arbitrary two different cargo destination coordinates s n (h a )，s n (h b ) Corresponding time sequence of cargo demand quantity
Figure BDA0004090872730000094
Distance d (h) a ，h b ) And (3) forming a distance matrix:
Figure BDA0004090872730000095
wherein:
d(n h 1) represents cargo destination coordinates s n (n h ) Coordinates s with destination of goods n (1) Corresponding time sequence of cargo demand quantity
Figure BDA00040908727300000913
A distance therebetween;
s322: combining the destination coordinates of two different goods with the distance smaller than a preset threshold value in the distance matrix into a type of goods destination coordinates, and if the combined type number is smaller than k max Then the preset value threshold is increased until the class number after combination is equal to or greater than k max ；
S323: selecting a cargo destination coordinate from the destination coordinates of each type of cargo as a candidate coordinate, so that a candidate evaluation function value reaches the minimum, wherein the candidate evaluation function is as follows:
Figure BDA0004090872730000096
Wherein:
v represents the destination coordinates s of the goods in the destination coordinates of the m-th class of goods n (v)，Ω m Represents the cargo destination coordinate set, mu, in the m-th cargo destination coordinates m The distance average value of the cargo demand quantity time sequence corresponding to any two cargo destination coordinates in the mth cargo destination coordinates is represented;
S324：comparing candidate evaluation function values of candidate coordinates in destination coordinates of each type of goods, and selecting k with the minimum candidate evaluation function value max The candidate coordinates are taken as the initial intra-cluster centers.
As another preferred embodiment of the present invention, the distance calculation process in step S321 is as follows:
for goods s n Arbitrary two different cargo destination coordinates s n (h a )，s n (h b ) Corresponding time sequence of cargo demand quantity
Figure BDA0004090872730000097
Wherein:
Figure BDA0004090872730000098
Figure BDA0004090872730000099
initialization of
Figure BDA00040908727300000910
The distance of (2) is:
dis(t 1 ，t 1 )＝0
for a pair of
Figure BDA00040908727300000911
Wherein the iteration formula is:
Figure BDA0004090872730000101
Figure BDA0004090872730000102
wherein:
t r ∈[t 1 ，t L ]；
i represents a penalty matrix if
Figure BDA0004090872730000103
Less than the preset distance threshold, then I (t r ，t r-1 ) Is 1, otherwise I (t r ，t r-1 ) Is 0;
repeating the iteration until dis (t L ，t L ) And dis (t) L ，t L ) As a time series sequence of the number of goods required
Figure BDA0004090872730000104
Distance d (h a ，h b )。
Example 2:
as shown in fig. 2, a functional block diagram of an automatic optimizing system for combining manifest information according to an embodiment of the present invention may implement the automatic optimizing method for combining manifest information according to embodiment 1.
The automated manifest information-incorporated optimization system 100 of the present invention may be installed in an electronic device. Depending on the functions implemented, the automated optimization system incorporating manifest information may include a historical manifest processing device 101, a time series demand analysis device 102, and a shipping warehouse cargo storage optimization module 103. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
The history manifest processing device 101 is configured to collect a history manifest form and perform preprocessing to obtain preprocessed history manifest information;
the time sequence demand analysis device 102 is configured to construct a time sequence of the number of cargo demands of each cargo destination coordinate corresponding to each cargo type, perform cluster analysis on the time sequence of the number of cargo demands of each cargo type, form a plurality of clusters of each cargo type, and perform probability distribution statistics on the number of cargo demands in different clusters to obtain time sequence demand characteristics of the cargo in different clusters;
and the goods storage amount optimizing module 103 of the goods warehouse is used for selecting the cluster with the most obvious current time sequence demand characteristic and distributing the goods to the goods warehouse corresponding to the goods destination in the cluster in advance.
In detail, the modules in the automatic optimizing system 100 for combining manifest information in the embodiment of the present invention use the same technical means as the automatic optimizing method for combining manifest information described in fig. 1, and can produce the same technical effects, which are not described herein.
Example 3:
fig. 3 is a schematic structural diagram of an electronic device for implementing an automatic optimization method combined with manifest information according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication interface 13 and a bus, and may further comprise a computer program, such as program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the program 12, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules (a program 12 for realizing automatic optimization in combination with manifest information, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.
The communication interface 13 may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device 1 and other electronic devices and to enable connection communication between internal components of the electronic device.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
It should be noted that, the foregoing reference numerals of the embodiments of the present invention are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims (10)

1. An automatic optimization method in combination with manifest information, the method comprising:
s1: collecting a historical manifest form and preprocessing to obtain preprocessed historical manifest information, wherein the manifest information comprises manifest generation time, cargo destination coordinates, shipping warehouse coordinates, cargo names and cargo demand quantity;
s2: constructing a cargo demand quantity time sequence of each cargo destination coordinate corresponding to each type of cargo;
s3: performing cluster analysis on the cargo demand quantity time sequence of each type of cargo to form a plurality of clusters of each type of cargo, wherein each cluster comprises a plurality of cargo destinations;
s4: carrying out probability distribution statistics on the required quantity of the goods in different clusters to obtain time sequence required characteristics of the goods in different clusters;
s5: selecting a cluster with the most obvious current time sequence demand characteristic, and distributing cargoes to a shipment warehouse corresponding to a cargo destination in the cluster in advance, wherein the more obvious the current time sequence demand characteristic is, the larger the demand of the cargo destination in the cluster for the cargoes is.
2. The automatic optimizing method for combining manifest information according to claim 1, wherein the step S1 of collecting and preprocessing a history manifest form to obtain preprocessed history manifest information includes:
collecting historical manifest forms, wherein the historical manifest forms represent and record the cargo transportation histories of different cargoes sent to different destinations, and the historical manifest forms comprise manifest generation time, cargo names, cargo demand quantity, cargo warehouse coordinates and corresponding cargo destination coordinates, and each manifest form records the cargo category required by the same cargo destination coordinate at the manifest generation time and the corresponding cargo demand quantity;
preprocessing the collected historical manifest form to obtain preprocessed historical manifest information, wherein the preprocessing flow of the historical manifest form is as follows:
s11: traversing goods s n Where n.epsilon.1, N]N corresponds to the total number of names of the goods, and the goods with different names belong to different categories;
s12: for goods s in time sequence order n Ordering the historical manifest forms of the goods, extracting the destination coordinates, the demand of the goods and the warehouse coordinates of the goods from the historical manifest forms, and taking the extracted information as the demand information of the goods;
S13: aligning the cargo demand information of the same cargo destination under different time sequence information according to the cargo destination coordinates to obtain the preprocessed cargo s n Wherein the column information of the history manifest information corresponds to manifest generation time, and each column information represents the cargo demand information of the same cargo destination for the same cargo at different manifest generation times.
3. The automatic optimizing method in combination with manifest information according to claim 2, wherein the constructing a cargo demand number time sequence of cargo destination coordinates corresponding to each type of cargo in step S2 includes:
construction of each class of goods s n Corresponding cargo destination coordinate s n (h) Is a time sequence of the number of cargo demands, wherein s n (h) Representing goods s in historical manifest information n Is the h cargo destination coordinate, h E [1, n ] h ]，n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates, the constructed cargo destination coordinates s n (h) Is the number of cargo demands of (a)The quantitative time sequence is as follows:
X n,h ＝(x n,h (t 1 ),x n,h (t 2 ),...,x n,h (t i ),...,x n,h (t L ))
wherein:
X n,h representing cargo destination coordinates s n (h) Is a time sequence of the cargo demand quantity;
{t i |i∈[1,L]the pre-divided L time periods, t i Representing the divided i-th time period;
x n,h (t i ) Indicated in time period t i In, cargo destination coordinates s n (h) For goods s n Is the total required quantity of goods;
goods s n Corresponding to any two different cargo destination coordinates s n (h a ),s n (h b ) The time sequence of the cargo demand quantity is respectively as follows
Figure FDA0004090872720000011
Wherein h is a ,h b ∈[1,n h ]，s n (h a )≠s n (h b )。
4. The automatic optimizing method in combination with manifest information according to claim 3, wherein in the step S3, a time sequence of the number of cargo demands of each type of cargo is subjected to cluster analysis to form a plurality of clusters of each type of cargo, and the method comprises:
for each type of goods s n N corresponding to h Clustering analysis is carried out on the time sequence of the quantity of the individual goods required to form goods s n Each cluster comprises a plurality of groups of cargo demand quantity time sequence corresponding to a plurality of cargo destinations, wherein the cluster analysis flow is as follows:
s31: determining the goods s n The corresponding maximum cluster number is k max Optimum cluster number k * Wherein
Figure FDA0004090872720000012
n h Representing goods s in historical manifest information n The total number of corresponding cargo destination coordinates;
s32: determining k max The method comprises the steps of establishing a corresponding cluster by using centers in initial clusters, and determining the current iteration number g of the centers in the clusters, wherein each initial cluster center is a cargo s n The corresponding cargo destination coordinate, the determined k initial intra-cluster center is z n,k (0)，k∈[1,k max ]Then the result obtained by the center in the kth initial cluster at the z-th iteration is z n,k (g) The initial value of g is 1;
s33: calculating the similarity of the goods destination coordinates of the non-cluster center and the cluster center, wherein the goods destination coordinates s of the non-cluster center n (h ′ ) From the intra-cluster center z nk (g) The similarity calculation formula of (2) is:
Figure FDA0004090872720000021
wherein:
alpha represents a distance coefficient, which is set to 0.01;
distance(s n (h ′ ),z n,k (g) Representing cargo destination coordinates s n (h ′ ) From the intra-cluster center z n,k (g) Is a distance of (2);
x n,h′ (t i ) Indicated in time period t i In, cargo destination coordinates s n (h ′ ) For goods s n Is the total required quantity of goods;
x ′ n,k (t i ) Indicated in time period t i In, cargo destination coordinate z n,k (g) For goods s n Is the total required quantity of goods;
sim(s n (h ′ ),z n,k (g) Destination coordinates s of goods representing centers in non-clusters n (h ′ ) From the intra-cluster center z n,k (g) Similarity of (2);
destination coordinates s of goods to be not center in cluster n (h ′ ) Distributing the cluster to the cluster corresponding to the center in the cluster with the highest similarity;
s34: updating the center in each cluster, wherein the updating principle of the center in each cluster is as follows: calculating the sequence average value of the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster, calculating the Euclidean distance between the cargo demand quantity time sequence corresponding to all cargo destination coordinates in the cluster and the sequence average value, and selecting the cargo destination coordinate corresponding to the cargo demand quantity time sequence with the smallest Euclidean distance as the updated center in the cluster;
If k max If the center in each cluster does not change, the clustering is terminated to obtain k max Cluster, otherwise let g=g+1, return to step S33;
s35: calculating the intra-cluster center similarity of any two clusters, wherein the calculation formula of the similarity is the formula in the step S33;
s36: combining the two clusters with the highest similarity, returning to the step S35 until the current cluster number reaches the optimal cluster number k * 。
5. The automatic optimizing method in combination with manifest information according to claim 1, wherein in the step S4, probability distribution statistics are performed on the required number of cargoes in different clusters, and the method comprises the following steps:
for goods s in different clusters n Carrying out probability distribution statistics on the required quantity of the goods, and taking the probability distribution statistics result as goods s n The time sequence demand characteristics in different clusters, wherein the probability distribution statistical formula of the cargo demand quantity in the kth cluster is as follows:
Figure FDA0004090872720000022
wherein:
P n,k (t i ) Indicated in time period t i In, probability distribution of cargo demand quantity in kth cluster;
sum(k,s n ,t i ) Indicated in time period t i In the kth clusterWith goods destination to goods s n Is not required.
6. The automatic optimizing method in combination with manifest information according to claim 5, wherein the selecting a cluster with the most obvious current time sequence demand feature in the step S5, and assigning the cargoes to the shipping warehouse corresponding to the destination of the cargoes in the cluster in advance includes:
Setting a historical time period with highest similarity with the current time period, wherein the historical time period with highest similarity with the current time period is a last year contemporaneous time period and a last month time period in sequence;
traversing goods s n K in the history period * The probability distribution of each cluster is that the cluster with the largest probability distribution is selected as the cluster with the most obvious current time sequence demand characteristics;
and distributing the cargoes to a shipping warehouse nearest to the destination of the cargoes in the cluster in advance according to the selected cluster.
7. The automatic optimizing method combined with manifest information according to claim 4, wherein the step S31 determines the optimal cluster number k by the following steps * ：
S311: setting the cluster numbers to be 1 and k respectively max 1 and k are obtained according to steps S32 to S34, respectively max A cluster;
s312: respectively calculating 1 cluster and k max Sum of squares of similarity of clusters, sum of squares of similarity of 1 cluster being sse 1 ，k max The sum of the squares of the similarity of the clusters is
Figure FDA0004090872720000031
Wherein the sum of squares of the similarity of k clusters calculates the formula sse k The method comprises the following steps:
Figure FDA0004090872720000032
wherein:
p represents the center in the j-th cluster other than the clusterCargo destination coordinates, C j A cargo destination coordinate set representing a non-intra-cluster center in a j-th cluster, z j Representing the intra-cluster center of the jth cluster;
s313: setting an optimal cluster number k * An initial value of 2 and a maximum value of k max Setting the number of clusters in steps S32 to S34 to k * Calculating to obtain k * Similarity threshold ratio for individual clusters:
Figure FDA0004090872720000033
s314: calculation based on the number of clusters k * Discrete threshold of classification results of (a):
Figure FDA0004090872720000034
wherein:
Figure FDA0004090872720000035
represents k * Maximum similarity between the intra-cluster node of the kth cluster in the clusters and the intra-cluster nodes of other different clusters, wherein the intra-cluster node comprises cargo destination coordinates of non-intra-cluster centers and intra-cluster centers, and a similarity calculation formula is the formula in the step S33;
s315: constructing a clustering evaluation index:
Figure FDA0004090872720000036
wherein:
k * ∈[2,k max ]is selected such that D (k * ) Up to a maximum k * As the final optimal cluster number k * 。
8. The automated manifest information-combined optimizing method of claim 4, wherein the step S32 determines k by max Center within each initial cluster:
s321: calculating to obtain goods s n Arbitrary two different cargo destination coordinates s n (h a ),s n (h b ) Corresponding time sequence of cargo demand quantity
Figure FDA0004090872720000037
Distance d (h) a ,h b ) And (3) forming a distance matrix:
Figure FDA0004090872720000038
wherein:
d(n h 1) represents cargo destination coordinates s n (n h ) Coordinates s with destination of goods n (1) Corresponding time sequence of cargo demand quantity
Figure FDA0004090872720000039
X n,1 A distance therebetween;
s322: combining the destination coordinates of two different goods with the distance smaller than a preset threshold value in the distance matrix into a type of goods destination coordinates, and if the combined type number is smaller than k max Then the preset value threshold is increased until the class number after combination is equal to or greater than k max ；
S323: selecting a cargo destination coordinate from the destination coordinates of each type of cargo as a candidate coordinate, so that a candidate evaluation function value reaches the minimum, wherein the candidate evaluation function is as follows:
Figure FDA00040908727200000310
wherein:
v represents the destination coordinates s of the goods in the destination coordinates of the m-th class of goods n (v)，Ω m Represents the cargo destination coordinate set, mu, in the m-th cargo destination coordinates m Representing any two cargoes in destination coordinates of m-th class of cargoesDistance average value of the cargo demand quantity time sequence corresponding to the object destination coordinates;
s324: comparing candidate evaluation function values of candidate coordinates in destination coordinates of each type of goods, and selecting k with the minimum candidate evaluation function value max The candidate coordinates are taken as the initial intra-cluster centers.
9. The automatic optimizing method in combination with manifest information according to claim 8, wherein the distance calculation in step S321 includes:
for goods s n Arbitrary two different cargo destination coordinates s n (h a ),s n (h b ) Corresponding time sequence of cargo demand quantity
Figure FDA0004090872720000041
Wherein:
Figure FDA0004090872720000042
Figure FDA0004090872720000043
initialization of
Figure FDA0004090872720000044
The distance of (2) is:
dis(t 1 ,t 1 )＝0
for a pair of
Figure FDA0004090872720000045
Wherein the iteration formula is:
Figure FDA0004090872720000046
Figure FDA0004090872720000047
wherein:
t r ∈[t 1 ,t L ]；
i represents a penalty matrix if
Figure FDA0004090872720000048
Less than the preset distance threshold, then I (t r ,t r-1 ) Is 1, otherwise I (t r ,t r-1 ) Is 0; />
Repeating the iteration until dis (t L ,t L ) And dis (t) L ,t L ) As a time series sequence of the number of goods required
Figure FDA0004090872720000049
Distance d (h a ,h b )。
10. An automated optimization system incorporating manifest information, the system comprising:
the history manifest processing device is used for collecting a history manifest form and preprocessing the history manifest form to obtain preprocessed history manifest information;
the time sequence demand analysis device is used for constructing a cargo demand quantity time sequence of each cargo destination coordinate corresponding to each cargo, carrying out cluster analysis on the cargo demand quantity time sequence of each cargo to form a plurality of clusters of each cargo, and carrying out probability distribution statistics on cargo demand quantity in different clusters to obtain time sequence demand characteristics of the cargoes in different clusters;
and the goods storage amount optimizing module of the goods delivery warehouse is used for selecting the cluster with the most obvious current time sequence demand characteristic, and distributing the goods to the goods delivery warehouse corresponding to the goods destination in the cluster in advance so as to realize the automatic optimizing method combining the manifest information according to any one of claims 1-9.
CN202310151139.5A 2023-02-21 2023-02-21 Automatic optimization method and system combining manifest information Active CN116167692B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310151139.5A CN116167692B (en) 2023-02-21 2023-02-21 Automatic optimization method and system combining manifest information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310151139.5A CN116167692B (en) 2023-02-21 2023-02-21 Automatic optimization method and system combining manifest information

Publications (2)

Publication Number Publication Date
CN116167692A true CN116167692A (en) 2023-05-26
CN116167692B CN116167692B (en) 2023-09-01

Family

ID=86412976

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310151139.5A Active CN116167692B (en) 2023-02-21 2023-02-21 Automatic optimization method and system combining manifest information

Country Status (1)

Country Link
CN (1) CN116167692B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117689315A (en) * 2024-02-04 2024-03-12 瑞熙(苏州)智能科技有限公司 Warehouse automatic delivery-in-delivery management system and method based on digital label

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010066996A (en) * 2008-09-10 2010-03-25 Japan Post Service Co Ltd Cargo collection management system, cargo collection management program, and cargo collection management method
CN103440566A (en) * 2013-08-27 2013-12-11 北京京东尚科信息技术有限公司 Method and device for generating order picking collection lists and method for optimizing order picking route
WO2018210058A1 (en) * 2017-05-19 2018-11-22 北京京东尚科信息技术有限公司 Order display method and apparatus
CN109002960A (en) * 2018-06-12 2018-12-14 广东工业大学 It is a kind of based on the online order of scoring and path planning distribution and allocator
CN109685092A (en) * 2018-08-21 2019-04-26 中国平安人寿保险股份有限公司 Clustering method, equipment, storage medium and device based on big data
CN114120018A (en) * 2020-08-25 2022-03-01 四川大学 Space activity quantification method based on crowd clustering track entropy

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010066996A (en) * 2008-09-10 2010-03-25 Japan Post Service Co Ltd Cargo collection management system, cargo collection management program, and cargo collection management method
CN103440566A (en) * 2013-08-27 2013-12-11 北京京东尚科信息技术有限公司 Method and device for generating order picking collection lists and method for optimizing order picking route
WO2018210058A1 (en) * 2017-05-19 2018-11-22 北京京东尚科信息技术有限公司 Order display method and apparatus
CN109002960A (en) * 2018-06-12 2018-12-14 广东工业大学 It is a kind of based on the online order of scoring and path planning distribution and allocator
CN109685092A (en) * 2018-08-21 2019-04-26 中国平安人寿保险股份有限公司 Clustering method, equipment, storage medium and device based on big data
CN114120018A (en) * 2020-08-25 2022-03-01 四川大学 Space activity quantification method based on crowd clustering track entropy

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈晓艳;张东洋;苏学斌;代钰贺;赵春东;: "基于改进遗传算法和多目标决策的货位优化策略", 天津科技大学学报, no. 04, pages 77 - 82 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117689315A (en) * 2024-02-04 2024-03-12 瑞熙(苏州)智能科技有限公司 Warehouse automatic delivery-in-delivery management system and method based on digital label

Also Published As

Publication number Publication date
CN116167692B (en) 2023-09-01

Similar Documents

Publication Publication Date Title
CN112380859A (en) Public opinion information recommendation method and device, electronic equipment and computer storage medium
CN112883190A (en) Text classification method and device, electronic equipment and storage medium
CN114663198A (en) Product recommendation method, device and equipment based on user portrait and storage medium
CN116523268B (en) Person post matching analysis method and device based on big data portrait
CN116167692B (en) Automatic optimization method and system combining manifest information
CN114491047A (en) Multi-label text classification method and device, electronic equipment and storage medium
CN113327136A (en) Attribution analysis method and device, electronic equipment and storage medium
CN113868528A (en) Information recommendation method and device, electronic equipment and readable storage medium
CN115081025A (en) Sensitive data management method and device based on digital middlebox and electronic equipment
CN113157739A (en) Cross-modal retrieval method and device, electronic equipment and storage medium
CN113656690A (en) Product recommendation method and device, electronic equipment and readable storage medium
CN113868529A (en) Knowledge recommendation method and device, electronic equipment and readable storage medium
CN114880368A (en) Data query method and device, electronic equipment and readable storage medium
CN113742069A (en) Capacity prediction method and device based on artificial intelligence and storage medium
CN112948705A (en) Intelligent matching method, device and medium based on policy big data
WO2023035940A1 (en) Target object recommendation method and system
CN113435746B (en) User workload scoring method and device, electronic equipment and storage medium
CN116187675A (en) Task allocation method, device, equipment and storage medium
CN113869455B (en) Unsupervised clustering method and device, electronic equipment and medium
CN111652281B (en) Information data classification method, device and readable storage medium
CN111401935B (en) Resource allocation method, device and storage medium
CN113657499A (en) Rights and interests allocation method and device based on feature selection, electronic equipment and medium
CN115238179A (en) Project pushing method and device, electronic equipment and computer readable storage medium
CN113760550A (en) Resource allocation method and resource allocation device
CN112184465B (en) User data portrait generation method, device, electronic 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
GR01 Patent grant
GR01 Patent grant