Method and system for generating site delivery area based on receipt address

By calculating and clustering site signing address data and geographic block data, the delivery area of ​​the logistics site is automatically adjusted, and the problem of low perception efficiency and low accuracy of the delivery area in the existing technology is solved, and the rapid and accurate realization is achieved The distribution area of ​​the logistics network has been adjusted to improve the stability of the logistics network.

CN114049066BActive Publication Date: 2024-11-22ZHEJIANG BAISHI TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111356397.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-16
Publication Date
2024-11-22
Estimated Expiration
2041-11-16

AI Technical Summary

Technical Problem

The prior art is inefficient and accurate in perceiving and adjusting changes in the delivery area of ​​logistics stations, resulting in errors in express delivery allocation, resulting in backlog and long delivery time.

Method used

By calculating the site's signed address data and geographical block data, calculating the block feature value, and spatial clustering is performed based on similarity and adjacency relationships, and automatically drawing the dispatch area to achieve fast and accurate dispatch area adjustment.

Benefits of technology

It improves the perceived efficiency and accuracy of the delivery area changes, reduces manual inspection time, ensures that express delivery is allocated to the correct site, and avoids backlogs and delays.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114049066B_ABST
    Figure CN114049066B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for generating a site delivery area based on a receipt address, wherein the method comprises the following steps: S1, calculating the block characteristic values ​​of the block to which the destination site belongs and the blocks adjacent to the block to which the destination site belongs according to the acquired site receipt address data and geographic block data; S2, calculating the characteristic value difference between the blocks, and judging whether the blocks have similarity according to the characteristic value difference; S3, spatially clustering the adjacent and similar blocks according to the block characteristic value corresponding to each block, and automatically drawing the delivery area of ​​the destination site according to the clustering result. The present invention uses a machine to calculate the site delivery area, which solves the technical problem of low efficiency and low accuracy in manually checking the change of the delivery area of ​​the destination site.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a method and system for generating a site delivery area based on a receipt address. Background Art

[0002] The logistics site is at the end of the logistics network and is responsible for the delivery of each express delivery. Generally speaking, each site has its own relatively fixed delivery area and is responsible for the delivery of all express deliveries with the receipt address within its delivery area. After the express enters the logistics network, the delivery site to which it belongs is determined based on its receipt address, and the delivery site is used as the destination of the express flow. However, the delivery area of ​​the site is not always fixed. In actual operation, the site delivery area may change due to factors such as site splitting and merging. Logistics companies need to be aware of these changes in a timely manner and adjust the delivery sites of express deliveries accordingly to prevent express deliveries from being assigned to the wrong site, resulting in a backlog of express deliveries at the site or a long delivery time for express deliveries.

[0003] In order to solve the above problems, the existing methods mainly rely on manual inspection of sites where a large number of express parcels are incorrectly assigned, and determine the type of site change through telephone inquiries and manual data analysis, and re-divide the delivery area of ​​the site accordingly. However, the manual inspection method consumes a lot of manpower, and it takes a lot of time to locate the site where the delivery area has changed, and the positioning results are not necessarily accurate. It is impossible to divide the accurate site delivery area in time to eliminate such misclassified express parcels. Summary of the invention

[0004] The present invention aims to timely and accurately perceive the change of the site delivery area, and provides a method and system for generating the site delivery area based on the receipt address.

[0005] To achieve this object, the present invention adopts the following technical solutions:

[0006] A method for generating a site delivery area based on a receipt address is provided, comprising the steps of:

[0007] S1, calculating the block characteristic values ​​of the block to which the destination site belongs and each block adjacent to the block to which the destination site belongs according to the acquired site receipt address data and geographic block data;

[0008] S2, calculate the eigenvalue difference between each block, and determine whether the eigenvalue difference is less than the difference threshold,

[0009] If so, the two blocks are determined to be similar;

[0010] If not, it is determined that the two blocks have no similarity;

[0011] S3, spatially clustering adjacent and similar blocks according to the block feature value corresponding to each block, and automatically drawing the delivery area of ​​the destination station according to the clustering result.

[0012] Preferably, the site receipt address data obtained in step S1 includes a first latitude and longitude data set of all receipt addresses of the destination site within a specified period, and a second latitude and longitude data set of all receipt addresses of any one or more other sites whose straight-line distance to the destination site is less than a first distance threshold and also within the specified period, wherein the first latitude and longitude data set is denoted as P, where P = {p1, p2, ... p i ,…,p n}, the second longitude and latitude data set is recorded as Q′={q1, q2, …q k , …, q m}, p i and q k They respectively represent the longitude and latitude data of the i-th receipt address in the set P and the k-th receipt address in the set Q′, and n and m respectively represent the number of elements in the set P and the set Q′.

[0013] Preferably, the method steps for calculating the block feature value include:

[0014] S11, identifying the receipt address point p in the set P from the set Q′ j The address data whose minimum distance is less than the second distance threshold form a data set, denoted as Q.

[0015]

[0016] p j Represents the longitude and latitude data of the jth receipt address in the set P;

[0017] dist(p j ,q k ) represents the receipt address point p in the set P j and the receipt address point q in the set Q′ k The distance between

[0018] D represents the second distance threshold;

[0019] S12, calculating an indicator variable I representing the relationship between each block and each receipt address point in the set P and the set Q according to the geographic block data;

[0020] S13, calculating the block characteristic value according to the indicator variable I.

[0021] Preferably, in step S12, when the receipt address point p in the set P jThe address falls into block b i When the indicator variable I is expressed as I(b i , p j ) and I(b i , p j )=1;

[0022] When the receipt address point p in the set P j The address does not fall into block b i When I(b i , p j )=0;

[0023] When the receipt address point q in the set Q k The address falls into block b i When the indicator variable I is expressed as I(b i ,q k ) and I(b i ,q k )=1;

[0024] When the receipt address point q in the set Q k The address does not fall into block b i When I(b i ,q k )=0.

[0025] Preferably, the block characteristic value is calculated by the following formula (1):

[0026]

[0027] In formula (1), f i Indicates block b i The characteristic value of

[0028] |P| represents the number of elements in the set P;

[0029] |Q| represents the number of elements in the set Q.

[0030] Preferably, in step S3, the method steps of spatially clustering adjacent blocks with similarity include:

[0031] S31, taking each block as a separate cluster, initializing the cluster;

[0032] S32, traversing all adjacent block pairs belonging to different clusters, and calculating the absolute value of the difference between the eigenvalues ​​of two blocks in each group of the block pairs;

[0033] S33, merging two clusters where two blocks in the block pair with the smallest absolute difference value are located into one cluster;

[0034] S34, repeating steps S32-S33 until all blocks are merged into two remaining clusters, completing the spatial clustering of blocks;

[0035] S35, calculating the mean of the characteristic values ​​of each block in each of the two clusters finally obtained in step S34, and taking the area range of the cluster with the larger mean as the delivery area of ​​the destination site.

[0036] Preferably, when the amount of receipt address data in a block at the edge of the delivery area of ​​the destination site determined in step S35 is less than a preset threshold, the edge block is removed to narrow the delivery area of ​​the destination site.

[0037] The present invention also provides a system for generating a site delivery area based on a receipt address, which can implement the method for generating a site delivery area based on a receipt address, and the system includes:

[0038] A data acquisition module, used to acquire site receipt address data and geographic block data according to a data acquisition instruction;

[0039] A block characteristic value calculation module, connected to the data acquisition module, for calculating the block characteristic values ​​of the block to which the destination site belongs and each block adjacent to the block to which the destination site belongs according to the acquired site receipt address data and the geographic block data;

[0040] A difference calculation module, connected to the block feature value calculation module, used to calculate the feature value difference between blocks;

[0041] A similarity judgment module, connected to the difference calculation module, is used to judge whether the feature value difference is less than a preset difference threshold,

[0042] If so, the two blocks are determined to be similar;

[0043] If not, it is determined that the two blocks have no similarity;

[0044] A block adjacency matrix calculation module, connected to the data acquisition module, is used to determine whether blocks are adjacent to each other based on the geographic data of each block;

[0045] A clustering module, connected to the similarity judgment module, the block adjacency matrix calculation module and the block feature value calculation module respectively, for spatially clustering adjacent blocks with similarity according to the block feature value corresponding to each block;

[0046] A delivery area determination module, connected to the clustering module, for determining the delivery area of ​​the destination site according to the clustering result;

[0047] A delivery area drawing module, connected to the delivery area determination module, for automatically drawing the determined delivery area of ​​the destination station and displaying it to the user;

[0048] The site change warning module is connected to the delivery area determination module and is used to determine whether the delivery areas associated with the same destination site determined twice before and after are consistent.

[0049] If they are inconsistent, a site change warning signal is generated to prompt the user;

[0050] If they are consistent, no warning will be given.

[0051] Preferably, the site receipt address data includes a first latitude and longitude data set of all receipt addresses of the destination site within a specified period, and a second latitude and longitude data set of all receipt addresses of any one or more other sites whose straight-line distance to the destination site is less than a first distance threshold and also within the specified period, wherein the first latitude and longitude data set is denoted as P, where P = {p1, p2, ... p i ,…,p n}, the second longitude and latitude data set is recorded as Q′={q1, q2, …q k , …, q m}, p i and q k They respectively represent the longitude and latitude data of the i-th receipt address in set P and the k-th receipt address in set Q′, and n and m respectively represent the amount of data in the set P and the set Q′.

[0052] Preferably, the block feature value calculation module specifically includes:

[0053] A data identification unit, used to identify address data whose distance from the receipt address in the set P is less than a second distance threshold from the set Q′ and form a data set;

[0054] An indicator variable calculation unit, connected to the data identification unit, for calculating an indicator variable I representing the relationship between each block and each receipt address point in the set P and the set Q according to the geographic block data;

[0055] A block characteristic value calculation unit, connected to the indicator variable calculation unit, is used to calculate the block characteristic value according to the indicator variable I by the following formula (2):

[0056]

[0057] In formula (2), f i Indicates block b i The characteristic value of

[0058] |P| represents the number of elements in the set P;

[0059] |Q| represents the number of elements in the set Q;

[0060] Preferably, the clustering module specifically includes:

[0061] A cluster initialization unit, used to initialize the clusters with each block as a separate cluster;

[0062] A block pair traversal and eigenvalue difference calculation unit, connected to the cluster initialization unit, for traversing all adjacent block pairs belonging to different clusters, and calculating the absolute value of the difference between the eigenvalues ​​of two blocks in each group of block pairs;

[0063] a cluster merging unit, connected to the block pair traversal and eigenvalue difference calculation unit, and configured to merge two clusters where two blocks in the block pair with the smallest absolute difference value are located into one cluster;

[0064] a mean value calculation unit for characteristic values ​​of blocks within a cluster, connected to the cluster merging unit, and used for calculating the mean value of characteristic values ​​of each block within each cluster of the two clusters finally obtained by merging;

[0065] The delivery area determination unit is connected to the intra-cluster block feature value mean calculation unit and is used to use the block area range of the cluster with the larger mean value among the two clusters as the delivery area of ​​the destination site.

[0066] The present invention calculates the block characteristic values ​​between the block to which the destination site belongs and the blocks adjacent to the block to which the destination site belongs based on the site receipt address data and the geographic block data, and clusters the adjacent blocks with characteristic similarities based on the characteristic values ​​of each block, and finally automatically draws the delivery area of ​​the destination site based on the clustering results, thereby solving the technical problems of low efficiency and low accuracy in manually checking the changes in the delivery area of ​​the destination site. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0068] Figure 1 This is a step diagram of a method for generating a site delivery area based on a receipt address provided by an embodiment of the present invention;

[0069] Figure 2 It is a method step diagram for calculating block characteristic values;

[0070] Figure 3 This is a method step diagram for spatial clustering of adjacent and similar blocks;

[0071] Figure 4 It is a schematic diagram of the system structure for generating a site delivery area based on a receipt address provided by an embodiment of the present invention;

[0072] Figure 5 It is a schematic diagram of the internal structure of a block characteristic value calculation module in a system for generating a station delivery area based on a receipt address;

[0073] Figure 6 It is a schematic diagram of the internal structure of the clustering module in the system for generating the site delivery area based on the receipt address.

[0074] Figure 7 It is a schematic diagram of forming a data set Q;

[0075] Figure 8 It is a schematic diagram of the principle of calculating the block eigenvalue;

[0076] Fig. 9 This is a schematic diagram of the method for merging clusters. DETAILED DESCRIPTION

[0077] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0078] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on this patent; in order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0079] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "inner", "outer", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as a limitation on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0080] In the description of the present invention, unless otherwise clearly specified and limited, if the term "connection" or the like appears to indicate the connection relationship between components, the term should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components or the interaction relationship between two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0081] The nodes in the logistics network can be divided into two categories: transshipment centers and stations. Transshipment centers are nodes for express delivery, and are generally large in scale. Stations are nodes for express delivery entry and delivery, and are generally small in scale. The lines between transshipment centers are called trunk lines for logistics transportation, and are the main arteries in the logistics network. Each shipment can be assigned a departure station and a destination station based on the shipping address and the receipt address, which determines the direction of the shipment in the network. After the shipment enters the network at the departure station, it is first transported to the superior transshipment center corresponding to the departure station, then transported to the superior transshipment center corresponding to the destination station via the trunk line, and then transported to the destination station, where it is delivered to the recipient.

[0082] A station is generally responsible for a fixed area, which is called the delivery area of ​​the station. All express parcels in the delivery area of ​​the station are delivered by the station. In actual operation, the station manager or logistics company divides the delivery area of ​​the station in advance. For each express parcel, the longitude and latitude are analyzed according to its receiving address, and then the longitude and latitude are determined on the map to which station's delivery area the longitude and latitude belong, thereby determining the transportation direction of the express parcel in the logistics network.

[0083] The delivery area of ​​a station is not permanent. For example, if a station is merged or split, part or all of the delivery area of ​​a station may be assigned to another station. The change of stations caused by the merger or split of stations is often sudden. Logistics companies cannot predict in advance to re-divide the delivery area of ​​the station, so that express parcels are sent to the wrong station and cannot be delivered in time, resulting in a backlog of express parcels and a long delivery time.

[0084] Therefore, in order to solve the above problems, the present invention automatically draws the delivery area of ​​the site by acquiring the site receipt address data and geographic block data within a specified period of time and performing a series of data analysis and calculations, and issues an abnormal alarm when the delivery areas drawn twice are inconsistent or the degree of change exceeds a threshold.

[0085] Specifically, Figure 1 As shown, the method for generating a site delivery area based on a receipt address provided by an embodiment of the present invention includes:

[0086] Step S1, calculating the block characteristic values ​​of the block to which the destination site belongs and each block adjacent to the block to which the destination site belongs according to the acquired site receipt address data and geographic block data;

[0087] The site receipt address data is obtained from the receipt address database of the logistics company. The site receipt address data includes the latitude and longitude datasets of all receipt addresses of the destination site and any one or more other sites whose straight-line distance to the destination site is less than the first distance threshold within a specified period (the specified period is usually selected as a period of time before the current day, for example, if the current day is November 11, the specified period can be selected as the 10 days before the current day, that is, the 10 days from November 1 to November 11). In order to distinguish the latitude and longitude datasets of the destination site from those of the non-destination site, we refer to the latitude and longitude datasets of all receipt addresses of the destination site within the specified period as the first latitude and longitude dataset, denoted as P, where P = {p1, p2, ... p i ,…,p n The longitude and latitude data set of all the signing addresses of the non-destination sites whose straight-line distance to the destination site is less than the first distance threshold within the specified period is called the second longitude and latitude data set, denoted as Q′, Q′={q1,q2,…q k , …, q m}, p i and q k Respectively represent the longitude and latitude data of the i-th receipt address in set P and the k-th receipt address in set Q′, and n and m represent the number of elements in set P and set Q′ respectively. i The data form is recorded as p i =(lon i ,lat i ),lon i ,lat i Respectively represent the i-th receipt address p i The longitude and latitude of the location. The element q in the set Q′ k The data expression is q k =(lon k ,lat k ).

[0088] The geographic block data is obtained from the geographic database of the logistics enterprise. The geographic block data set is recorded as B, where B = {b1, b2, ..., b i , …, b r}, b i represents the geographic data of the i-th block in set B, and r represents the number of elements in set B.

[0089] It should also be noted that block adjacency refers to block b i Block b jThere is at least one point or one edge in common. The system represents the adjacency relationship between blocks by constructing a block adjacency matrix, which is a |B|×|B| matrix A, where B is the number of rows or columns of matrix A, and the element A in the i-th row and j-th column of A is ij =1 indicates block b i and block b j Adjacent, A ij =0 means block b i and block b j Not adjacent.

[0090] After obtaining the site receipt address data and geographic block data, the system starts to calculate the characteristic value of each block. In the present invention, the block characteristic value is defined as the ratio of the destination site receipt address in the block to all receipt address points. We use the indicator variable I to characterize the relationship between the block and the receipt address point, and calculate the block characteristic value through the indicator variable I. Specifically, Figure 2 As shown, the method for calculating the block feature value of the present invention includes:

[0091] Step S11, identifying address data whose distance from the receipt address in the set P is less than a second distance threshold from the set Q′, forming a data set, denoted as Q,

[0092] The following combination Figure 7 The formation process of set Q is explained in detail:

[0093] As shown in the figure, the solid line box on the right represents the set P of the destination site's receipt address data, and the receipt address points p1, p2, p3, p4, p5, p6, p7, p8, ..., p i ,…,p n is an element in the set P; the solid line box on the left represents the set Q′ of the receipt address data of another site adjacent to the block to which the destination site belongs, and the receipt address points q1, q2, q3, q4, q5, q6, q7, q8, …, q i ,…,q n is an element in the set Q′. After setting the second distance threshold D to 1km, assuming that the distance between q2 and the address point p1 in the right solid line box among all the signing address points in the left solid line box is the smallest and the distance between the two points is less than 1km, then q2 is extracted from the set Q′. For another example, if the distance between q3 and the address point p2 in the right solid line box among all the signing address points in the left solid line box is the smallest and the distance between the two points is less than 1km, then q3 is extracted from the set Q′. According to the same method, for example, a total of 4 signing address points q2, q3, q6, and q8 are extracted from the set Q′, then these 4 address points are formed into a data set Q. The process of forming the data set Q is expressed by the following formula:

[0094]

[0095] p j Represents the longitude and latitude data of the jth receipt address in the set P (referred to as the receipt address point p j );

[0096] dist(p j ,q k ) represents the receipt address point p in the set P j and the receipt address point q in the set Q′ k The distance between

[0097] D represents the second distance threshold (preferably 1 km).

[0098] After forming the data set Q, please continue to refer to Figure 2 , calculate the block feature value and proceed to step S12,

[0099] Step S12, calculating an indicator variable I representing the relationship between each block and each receipt address point in the set P and the set Q according to the geographic block data;

[0100] The indicator variable I is a 0-1 variable, such as I(b i , p j )=1, indicating the receipt address point p in the set P j The signing address falls into block b i Medium; I(b i , p j )=0, indicating the receipt address point p in the set P j The signing address does not fall into block b i In , the 0-1 expression of the indicator variable I is as follows:

[0101]

[0102] The following combination Figure 8 The calculation method of the indicator variable I is explained in detail:

[0103] Figure 8 The area selected by the dotted line in the figure is represented as block b. i , the destination site's receipt address points p1, p2, and p7 fall into block b i In the above equation, I(b i , p1)=1,I(b i , p2)=1,I(b i , p7) = 1; the locations of the receipt address points q2, q3, q6, and q8 of other sites fall into block b i , then I(b i ,q2)=1,I(b i ,q3)=1,I(bi ,q6)=1,I(b i , q8) = 1, others not falling into block b i The receipt address point in the example is p4, and its corresponding indicator variable I(b i , p4)=0.

[0104] Step S13, calculating the block feature value according to the indicator variable I.

[0105] In this embodiment, the block characteristic value is calculated by the following formula (1):

[0106]

[0107] In formula (1), f i Indicates block b i The characteristic value of

[0108] |P| represents the number of elements in the set P;

[0109] |Q| represents the number of elements in set Q.

[0110] Or Figure 8 For example, Figure 8 Falls into block b i The signing address points are q2, q3, q6, q8 in set Q and p1, p2, p3 in set P. According to formula (1), Then block b i The eigenvalue of

[0111] After completing the calculation of the eigenvalues ​​of each block, Figure 1 As shown, the method for generating a site delivery area based on a receipt address provided in this embodiment enters step S2,

[0112] Step S2, calculate the feature value difference between each block, and determine whether the feature value difference is less than the difference threshold.

[0113] If so, the two blocks are determined to be similar;

[0114] If not, it is determined that the two blocks have no similarity;

[0115] Step S3, based on the block feature value corresponding to each block, spatially cluster the adjacent blocks with similarity, and automatically draw the delivery area of ​​the destination station based on the clustering result. Specifically, Figure 3 As shown in FIG. 1 , the method for spatially clustering adjacent and similar blocks includes:

[0116] Step S31, the clusters are initialized. The initialization method is: each adjacent block is a separate cluster. If the number of rows and columns of the constructed block adjacency matrix is ​​|B|×|B|, then there are a total of |B| clusters after initialization. For example, assuming that the delivery area of ​​the destination site is Fig. 9 The block 1, block 2, block 3, and block 4 in the cluster are covered by any one or more blocks. Block 1, block 2, block 3, and block 4 have an adjacency relationship. Each block of blocks 1-4 is regarded as a cluster separately. Then, there are 4 clusters in total after initialization.

[0117] Step S32, traverse all adjacent block pairs belonging to different clusters, and calculate the absolute value of the difference between the feature values ​​of the two blocks in each block pair; Fig. 9 For example, the traversal of block pairs is as follows: adjacent blocks 1 and 2 form the first block pair, adjacent blocks 1 and 3 form the second block pair, adjacent blocks 1 and 4 form the third block pair, adjacent blocks 2 and 3 form the fourth block pair, and adjacent blocks 3 and 4 form the fifth block pair. The absolute value of the difference between the eigenvalues ​​of the two blocks in the block pair is calculated, that is, for example, the absolute value of the difference between the eigenvalue of block 1 and the eigenvalue of block 2 is calculated. The specific calculation formula is not listed here.

[0118] Step S33, merging the two clusters of the two blocks in the block pair with the smallest absolute difference into one cluster; assuming that the absolute difference of the eigenvalues ​​corresponding to the first block pair is the smallest, merging the clusters of block 1 and block 2 in the first block pair into one cluster;

[0119] Step S34, repeating steps S22-S23 until all blocks are merged into two remaining clusters, completing the spatial clustering of blocks; for example, after the first block pair is merged into one cluster (recorded as cluster 1), Fig. 9 There are still 4 block pairs left, namely: the second block pair consisting of adjacent blocks 1 and 3, the third block pair consisting of adjacent blocks 1 and 4, the fourth block pair consisting of adjacent blocks 2 and 3, and the fifth block pair consisting of adjacent blocks 3 and 4. After the system returns to step S22, it continues to traverse all adjacent block pairs belonging to different clusters, and then the system continues to calculate the absolute value of the difference between the eigenvalues ​​of the two blocks in each group of block pairs. For example, the absolute value of the difference between the eigenvalues ​​of the two blocks in the second block pair is the smallest among the remaining 4 block pairs. After the two clusters where the two blocks in the second block pair are located are merged, one cluster is blocks 1, 2, 3, and the other cluster is block 4, and the termination conditions of the remaining two clusters have been met.

[0120] Step S35, calculate the mean of the characteristic values ​​of each block in each of the two clusters finally obtained in step S34, and use the area of ​​the cluster with the larger mean as the delivery area of ​​the destination station. Fig. 9 The cluster formed by merging blocks 1, 2, and 3 and the single cluster of block 4 are the final two clusters. The mean eigenvalue of the first cluster formed by merging blocks 1, 2, and 3 is greater than that of the second cluster of block 4. The area range of the first cluster is used as the delivery area of ​​the destination site.

[0121] In order to further improve the accuracy of the drawn delivery area, preferably, when the amount of receipt address data in a block at the edge of the delivery area of ​​the destination site determined in step S35 is less than a preset threshold, the edge block is removed to narrow the delivery area of ​​the destination site.

[0122] In summary, the present invention automatically draws the delivery area of ​​the site through the site receipt address data and geographic block data. On the one hand, it can assist manual work in quickly locating the site where the delivery area changes. On the other hand, it can monitor the delivery areas of all sites in the entire logistics network on different dates to give early warning of possible site changes, which is convenient for logistics companies to take intervention measures in advance to maintain the stability of the logistics network.

[0123] The present invention also provides a system for generating a site delivery area based on a receipt address, which can implement the above method for generating a site delivery area based on a receipt address, such as Figure 4 As shown, the system includes:

[0124] A data acquisition module, used to acquire site receipt address data and geographic block data according to a data acquisition instruction;

[0125] A block characteristic value calculation module, connected to the data acquisition module, is used to calculate the block characteristic values ​​of the block to which the destination site belongs and the blocks adjacent to the block to which the destination site belongs according to the acquired site receipt address data and geographic block data;

[0126] A difference calculation module, connected to the block feature value calculation module, is used to calculate the feature value difference between blocks;

[0127] A similarity judgment module is connected to the difference calculation module and is used to judge whether the feature value difference is less than a preset difference threshold. If so, it is determined that the two blocks are similar;

[0128] If not, it is determined that the two blocks have no similarity;

[0129] The block adjacency matrix calculation module is connected to the data acquisition module and is used to determine whether the blocks are adjacent to each other based on the geographic data of each block;

[0130] The clustering module is connected to the similarity judgment module, the block adjacency matrix calculation module and the block characteristic value calculation module respectively, and is used to spatially cluster adjacent blocks with similarity according to the block characteristic value corresponding to each block;

[0131] A delivery area determination module, connected to the clustering module, is used to determine the delivery area of ​​the destination station according to the clustering results;

[0132] A delivery area drawing module, connected to the delivery area determination module, is used to automatically draw the delivery area of ​​the determined destination station and display it to the user;

[0133] The site change warning module is connected to the delivery area determination module to determine whether the delivery areas associated with the same destination site determined twice are consistent.

[0134] If they are inconsistent, a site change warning signal is generated to alert the user;

[0135] If they are consistent, no warning will be given.

[0136] The site receipt address data includes a first latitude and longitude data set of all receipt addresses of the destination site within a specified period, and a second latitude and longitude data set of all receipt addresses of any one or more other sites whose straight-line distance to the destination site is less than a first distance threshold and also within the specified period. The first latitude and longitude data set is recorded as P, where P = {p1, p2, ... p i ,…,p n}, the second longitude and latitude data set is recorded as Q′={q1, q2, …q k , …, q m}, p i and q k They represent the longitude and latitude data of the i-th receipt address in set P and the k-th receipt address in set Q′ respectively, and n and m represent the amount of data in set P and set Q′ respectively.

[0137] like Figure 5 As shown, the block feature value calculation module specifically includes:

[0138] A data identification unit, used to identify address data whose distance from the receipt address in the set P is less than a second distance threshold from the set Q′ and form a data set;

[0139] The indicator variable calculation unit is connected to the data identification unit, and is used to calculate the indicator variable I representing the relationship between each block and each receipt address point in the set P and the set Q according to the geographic block data;

[0140] The block characteristic value calculation unit is connected to the indicator variable calculation unit and is used to calculate the block characteristic value according to the indicator variable I through the following formula (2):

[0141]

[0142] In formula (2), f i Indicates block b i The characteristic value of

[0143] |P| represents the number of elements in the set P;

[0144] |Q| represents the number of elements in the set Q;

[0145] like Figure 6 As shown, the clustering module specifically includes:

[0146] A cluster initialization unit, used to initialize the clusters by taking each adjacent block as a separate cluster;

[0147] The block pair traversal and eigenvalue difference calculation unit is connected to the cluster initialization unit, and is used to traverse all adjacent block pairs belonging to different clusters, and calculate the absolute value of the difference between the eigenvalues ​​of two blocks in each block pair;

[0148] A cluster merging unit, connected to the block pair traversal and eigenvalue difference calculation units, is used to merge two clusters of two blocks in a block pair with the smallest absolute difference into one cluster;

[0149] The cluster block feature value mean calculation unit is connected to the cluster merging unit and is used to calculate the mean feature value of each block in each cluster of the two clusters remaining after merging;

[0150] The delivery area determination unit is connected to the cluster block feature value mean calculation unit and is used to use the block area range of the cluster with the larger mean value among the two clusters as the delivery area of ​​the destination site.

[0151] It should be noted that the above specific implementations are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art should understand that various modifications, equivalent substitutions, changes, etc. can be made to the present invention. However, as long as these changes do not deviate from the spirit of the present invention, they should be within the scope of protection of the present invention. In addition, some terms used in the specification and claims of this application are not restrictive, but are only for the convenience of description.

Claims

1. A method for generating a site delivery area based on a receipt address, characterized in that: Includes steps: S1, calculating the block characteristic values ​​of the block to which the destination site belongs and each block adjacent to the block to which the destination site belongs according to the acquired site receipt address data and geographic block data; S2, calculate the eigenvalue difference between each block, and determine whether the eigenvalue difference is less than the difference threshold, If so, the two blocks are determined to be similar; If not, it is determined that the two blocks have no similarity; S3, spatially clustering adjacent and similar blocks according to the block feature value corresponding to each block, and automatically drawing the delivery area of ​​the destination station according to the clustering result; The site receipt address data obtained in step S1 includes a first latitude and longitude data set of all receipt addresses of the destination site within a specified period, and a second latitude and longitude data set of all receipt addresses of any one or more other sites whose straight-line distance to the destination site is less than a first distance threshold and also within the specified period. The first latitude and longitude data set is recorded as , , the second longitude and latitude data set is recorded as , and Respectively represent sets The Individual and collection The The longitude and latitude data of the receipt address, , Respectively represent the sets and the collection The number of elements in ; The method steps for calculating the block characteristic value include: S11, from the collection Identify the set The receipt address point The address data whose minimum distance is less than the second distance threshold form a data set, which is recorded as , Represents the set The The longitude and latitude data of the receipt address; Represents the set The receipt address point With the collection The receipt address point The distance between represents the second distance threshold; S12, calculating the relationship between each block and the set according to the geographic block data And collection The indicator variable of the relationship between the receipt address points in ; S13, according to the indicator variable Calculate and obtain the block characteristic value; In step S12, when the set The receipt address point The address falls into the block When Expressed as and ; When the collection The receipt address point The address does not fall into the block hour, ; When the collection The receipt address point The address falls into the block When Expressed as and ; When the collection The receipt address point The address does not fall into the block hour, ; The block feature value is calculated by the following formula (1): In formula (1), Representation block The characteristic value of Represents the set The number of elements in ; Represents the set The number of elements in .

2. The method for generating a site delivery area based on a receipt address according to claim 1, characterized in that: In step S3, the method steps of spatially clustering adjacent blocks with similarity include: S31, taking each block as a separate cluster, initializing the cluster; S32, traversing all adjacent block pairs belonging to different clusters, and calculating the absolute value of the difference between the feature values ​​of two blocks in each group of the block pairs; S33, merging two clusters where two blocks in the block pair with the smallest absolute difference value are located into one cluster; S34, repeating steps S32-S33 until all blocks are merged into two remaining clusters, completing the spatial clustering of blocks; S35, calculating the mean of the characteristic values ​​of each block in each of the two clusters finally obtained in step S34, and taking the area range of the cluster with the larger mean as the delivery area of ​​the destination site.

3. The method for generating a site delivery area based on a receipt address according to claim 2, characterized in that: When the amount of receipt address data in the block at the edge of the delivery area of ​​the destination site determined in step S35 is less than a preset threshold, the edge block is removed to narrow the delivery area of ​​the destination site.

4. A system for generating a site delivery area based on a receipt address, which can implement the method for generating a site delivery area based on a receipt address as described in any one of claims 1 to 3, characterized in that: The system comprises: A data acquisition module, used to acquire site receipt address data and geographic block data according to a data acquisition instruction; A block characteristic value calculation module, connected to the data acquisition module, for calculating the block characteristic values ​​of the block to which the destination site belongs and each block adjacent to the block to which the destination site belongs according to the acquired site receipt address data and the geographic block data; A difference calculation module, connected to the block feature value calculation module, used to calculate the feature value difference between blocks; A similarity judgment module, connected to the difference calculation module, is used to judge whether the feature value difference is less than a preset difference threshold, If so, the two blocks are determined to be similar; If not, it is determined that the two blocks have no similarity; A block adjacency matrix calculation module, connected to the data acquisition module, is used to determine whether blocks are adjacent to each other based on the geographic data of each block; A clustering module, connected to the similarity judgment module, the block adjacency matrix calculation module and the block feature value calculation module respectively, for spatially clustering adjacent blocks with similarity according to the block feature value corresponding to each block; A delivery area determination module, connected to the clustering module, for determining the delivery area of ​​the destination site according to the clustering result; A delivery area drawing module, connected to the delivery area determination module, for automatically drawing the determined delivery area of ​​the destination station and displaying it to the user; The site change warning module is connected to the delivery area determination module and is used to determine whether the delivery areas associated with the same destination site determined twice before and after are consistent. If they are inconsistent, a site change warning signal is generated to prompt the user; If they are consistent, no warning will be given.

5. The system for generating a delivery area based on a receipt address according to claim 4, characterized in that: The site receipt address data includes a first latitude and longitude data set of all receipt addresses of the destination site within a specified period, and a second latitude and longitude data set of all receipt addresses of any one or more other sites whose straight-line distance to the destination site is less than a first distance threshold and also within the specified period. The first latitude and longitude data set is recorded as , , the second longitude and latitude data set is recorded as , and Respectively represent sets The Individual and collection The The longitude and latitude data of the receipt address, , Respectively represent the sets and the collection The amount of data in .

6. The system for generating a delivery area based on a receipt address according to claim 4, characterized in that: The block feature value calculation module specifically includes: A data identification unit for identifying a data set from said set Identify the set The address data whose distance from the receipt address is less than a second distance threshold are formed into a data set; an indicator variable calculation unit, connected to the data identification unit, for calculating, based on the geographic block data, a variable representing each block and the set And collection The indicator variable of the relationship between the receipt address points in ; A block characteristic value calculation unit connected to the indicator variable calculation unit for calculating the characteristic value of the block according to the indicator variable The block characteristic value is calculated by the following formula (2): In formula (2), Representation block The characteristic value of Represents the set The number of elements in ; Represents the set The number of elements in ; Preferably, the clustering module specifically includes: A cluster initialization unit, used to initialize the clusters with each block as a separate cluster; A block pair traversal and eigenvalue difference calculation unit, connected to the cluster initialization unit, for traversing all adjacent block pairs belonging to different clusters, and calculating the absolute value of the difference between the eigenvalues ​​of two blocks in each group of block pairs; a cluster merging unit, connected to the block pair traversal and eigenvalue difference calculation unit, and configured to merge two clusters where two blocks in the block pair with the smallest absolute difference value are located into one cluster; a mean value calculation unit for characteristic values ​​of blocks within a cluster, connected to the cluster merging unit, and used for calculating the mean value of characteristic values ​​of each block within each cluster of the two clusters finally obtained by merging; The delivery area determination unit is connected to the intra-cluster block feature value mean calculation unit and is used to use the block area range of the cluster with the larger mean value among the two clusters as the delivery area of ​​the destination site.