CN116882598A - Import and export goods trade order management method and system - Google Patents
Import and export goods trade order management method and system Download PDFInfo
- Publication number
- CN116882598A CN116882598A CN202311155147.3A CN202311155147A CN116882598A CN 116882598 A CN116882598 A CN 116882598A CN 202311155147 A CN202311155147 A CN 202311155147A CN 116882598 A CN116882598 A CN 116882598A
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- clustering
- address information
- receiving address
- 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
Links
- 230000008676 import Effects 0.000 title claims abstract description 41
- 238000007726 management method Methods 0.000 title claims description 39
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims description 35
- 239000013598 vector Substances 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 238000004220 aggregation Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000002776 aggregation Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Remote Sensing (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of trade and provides a method and a system for managing import and export goods trade orders, wherein the method comprises the steps of acquiring historical order data in different historical time periods; classifying the historical order data according to the consumption field to obtain a plurality of historical order data sets; based on a DBSCAN clustering algorithm, clustering operation is carried out on first historical receiving address information corresponding to each historical order data in each historical order data set, and receiving address information clustering results are analyzed to obtain hot receiving address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period. By the method, merchants can make planning and scheduling of the transportation tool accurately in advance, so that goods can be transported out in time in the future period, and the satisfaction degree of customers is improved.
Description
Technical Field
The application relates to the technical field of trade, in particular to a method and a system for managing import and export goods trade orders.
Background
At present, in import and export goods trade order management, a common transportation mode is to configure corresponding transportation vehicles according to the order quantity of users and corresponding goods receiving addresses. However, when the goods to be transported to a certain receiving address are suddenly increased, the problem that the transportation vehicles are insufficient and the goods cannot be transported to the customer in time is possibly faced, and the satisfaction degree of the customer is reduced; a method is needed that can predict future hot receiving addresses and further help merchants to plan and schedule transportation means in advance.
Disclosure of Invention
The application aims to provide a method and a system for managing import and export goods trade orders, so as to solve the problems.
In order to achieve the above object, the embodiment of the present application provides the following technical solutions:
in one aspect, an embodiment of the present application provides a method for managing import and export goods trade orders, where the method includes:
acquiring historical order data in different historical time periods, wherein the historical order data comprises historical consumer purchase information, and the consumer purchase information comprises purchase commodity information and first historical receiving address information;
determining the consumption field to which each historical order data belongs according to the historical consumer purchase information, and classifying the historical order data according to the consumption field to obtain a plurality of historical order data sets;
clustering the first historical receiving address information corresponding to each historical order data in each historical order data set based on a DBSCAN clustering algorithm to obtain a receiving address information clustering result;
analyzing the goods receiving address information clustering result to obtain hot goods receiving address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period so as to prompt merchants to arrange transportation means.
In a second aspect, an embodiment of the present application provides a import and export goods trade order management system, which includes an acquisition module, a classification module, a clustering module, and an analysis module.
The system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring historical order data in different historical time periods, the historical order data comprises historical consumer purchase information, and the consumer purchase information comprises purchase commodity information and first historical receiving address information;
the classification module is used for determining the consumption field to which each historical order data belongs according to the historical consumer purchase information, classifying the historical order data according to the consumption field and obtaining a plurality of historical order data sets;
the clustering module is used for carrying out clustering operation on the first historical receiving address information corresponding to each historical order data in each historical order data set based on a DBSCAN clustering algorithm to obtain a receiving address information clustering result;
the analysis module is used for analyzing the goods receiving address information clustering result to obtain hot goods receiving address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period so as to prompt merchants to arrange transportation means.
In a third aspect, embodiments of the present application provide an import and export goods trade order management device comprising a memory and a processor. The memory is used for storing a computer program; the processor is configured to implement the steps of the import and export goods trade order management method described above when executing the computer program.
In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the import and export goods trade order management method described above.
The beneficial effects of the application are as follows:
according to the method, historical order data of a period of time are acquired, and different consumption fields are considered, so that required transportation tools can be different, and the order data are divided into the consumption fields; after the consumption fields are divided, hot receiving addresses in different historical time periods are calculated for each consumption field respectively, then the hot receiving addresses in future time periods are predicted according to the hot receiving addresses in different historical time periods, and the method can enable merchants to accurately schedule transportation tools in advance so as to ensure that goods can be transported out in time in the future time periods and improve customer satisfaction.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for import and export goods trade order management according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a import and export goods trade order management device according to an embodiment of the present application;
fig. 3 is a schematic structural view of import and export goods trade order management equipment according to an embodiment of the present application.
701, an acquisition module; 702. a classification module; 703. a clustering module; 704. an analysis module; 7021. an input unit; 7022. a first training unit; 7031. an extraction unit; 7032. a clustering unit; 70321. a first calculation unit; 70322. a second training unit; 70323. a second calculation unit; 703231, an interpretation unit; 7041. a third calculation unit; 7042. a prediction unit; 70421. an aggregation unit; 70422. a construction unit; 800. import and export goods trade order management equipment; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals or letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
As shown in fig. 1, the embodiment provides a method for managing import and export goods trade orders, which includes steps S1, S2, S3 and S4.
Step S1, acquiring historical order data in different historical time periods, wherein the historical order data comprises historical consumer purchase information, and the consumer purchase information comprises purchase commodity information and first historical receiving address information;
in this step, the different historical time periods can be understood as that based on the current time, the specific historical time periods can be set in a self-defined manner according to the requirements of the user in the first 1 day, the first 2 days, the first 3 days and the like of the current time;
step S2, determining the consumption field to which each historical order data belongs according to the historical consumer purchase information, and classifying the historical order data according to the consumption field to obtain a plurality of historical order data sets;
in this step, considering different consumption fields, the transported tools are not the same, for example, the cold fresh goods need to be transported by a cold chain, that is, the cold chain transport tools are needed, so this step divides the consumption fields, and the specific steps include step S21 and step S22;
s21, inputting the information of the purchased goods into a preset attention model to obtain attention point data output by the attention model;
in the step, the attention model is used for representing the corresponding relation between the information of the purchased goods and the attention point;
step S22, acquiring sample purchase commodity information, inputting the sample purchase commodity information record into a preset attention model to obtain sample attention point data output by the attention model, and marking the sample attention point data, wherein marking information is a consumption field corresponding to the sample attention point data; training the convolutional neural network model by using the marked sample focus data to obtain a first model; and inputting the attention point data output by the attention model into the first model to obtain the consumption field of each historical order data.
The sample purchase commodity information in this step may be purchase commodity information at an arbitrary historical period; in this step, besides training the convolutional neural network model, other models, such as a residual network model, etc., may be used;
after the consumption field is obtained, the embodiment calculates the hot spot receiving address;
step S3, clustering the first historical receiving address information corresponding to each historical order data in each historical order data set based on a DBSCAN clustering algorithm to obtain a receiving address information clustering result;
in the step, a K & # x2011, means clustering algorithm, hierarchical clustering algorithm and the like can be utilized in addition to the DBSCAN clustering algorithm; the specific implementation steps of the step comprise a step S31 and a step S32;
step S31, extracting features of the first historical receiving address information to obtain feature vectors, and marking the feature vectors as first data;
in this step, feature extraction may be performed using a machine learning model, such as a neural network model, the features including countries in the address;
step S32, clustering the first historical goods receiving address information by using a DBSCAN clustering algorithm and first data to obtain a plurality of first clustering results, collecting all the first historical goods receiving address information contained in each first clustering result to obtain a first set, and calculating the average value of the first data corresponding to each first historical goods receiving address information in the first set to obtain second data; and calculating and obtaining a goods receiving address information clustering result based on the second data.
In this step, average value calculation is performed on the first data corresponding to each piece of the first historical receiving address information in the first set, so that the second data can be understood as the center of the clustering result; meanwhile, the specific implementation steps of obtaining the goods receiving address information clustering result based on the second data calculation include step S321, step S322 and step S323;
step S321, calculating the distance between each first data corresponding to the first clustering result and the second data according to each first clustering result, and recording the first data corresponding to the farthest distance as third data; combining the third data and the second data according to a preset combination rule to obtain fourth data, calculating a feature vector of a covariance matrix corresponding to the fourth data, and marking the feature vector of the covariance matrix corresponding to the fourth data as fifth data;
in this step, the preset combination rule may be along the matrix column direction, along the matrix row direction, or the like;
step S322, inputting each fifth data into a preset second model to obtain an evaluation result corresponding to each fifth data; when the second model is trained, firstly acquiring sample data, wherein the sample data comprises second historical receiving address information, carrying out clustering processing on the second historical receiving address information to obtain a plurality of second aggregation results, carrying out evaluation result labeling on each second aggregation result, and simultaneously calculating feature vectors of covariance matrixes corresponding to each second aggregation result; training by taking the eigenvectors of the covariance matrix corresponding to each second clustering result as input and marking information as output by adopting a deep learning method to obtain a second model;
in this step, the eigenvectors of the covariance matrix corresponding to each second-aggregation result are calculated according to the calculation method for calculating the fifth data; meanwhile, when the evaluation result is marked, the evaluation result can be marked as accurate, more accurate and inaccurate, and then the evaluation result is respectively expressed by 0,1 and 2; meanwhile, when training is performed by adopting a deep learning method, the training can be performed by utilizing a convolutional neural network;
and step 323, calculating and obtaining a goods receiving address information clustering result according to the evaluation result corresponding to each fifth data. The specific implementation steps of the step comprise a step S3231;
step S3231, the evaluation results corresponding to each fifth data are interpreted, if the interpretation results meet the preset standard, a plurality of first clustering results obtained by clustering at the moment are used as the goods receiving address information clustering results, wherein the preset standard is that the evaluation results corresponding to N fifth data after interpretation all reach standard evaluation results, N is a positive integer larger than zero, and N is larger than a preset value; otherwise, parameters of a DBSCAN clustering algorithm are adjusted, and clustering is conducted again until the evaluation result meets the preset standard.
In the step, the preset value can be set in a self-defined mode according to the requirement of a user, and the standard evaluation result can be accurate; meanwhile, the satisfaction of the preset label in this step can be understood as: for example, the preset value is 7, and when the evaluation results corresponding to 8 fifth data after interpretation are all accurate, the preset standard is reached; by the method, the clustering accuracy can be improved;
s4, analyzing the goods receiving address information clustering result to obtain hot goods receiving address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period so as to prompt merchants to arrange transportation means.
The clustering result corresponding to each consumption field can be seen through the steps, and the hottest receiving address can be seen in the clustering result, wherein the specific implementation steps of the steps comprise the step S41 and the step S42;
step S41, taking the sub-clustering result with the most data in each receiving address information clustering result as hot receiving address information, wherein the receiving address information clustering result consists of sub-clustering results;
the sub-clustering result in this step may be understood as the first clustering result described above, when each clustering result has a plurality of data after clustering, then the clustering result with the largest data is used as the hot receiving address, for example, after clustering, the clustering result with the largest data is used as the hot receiving address;
and step S42, quantifying the hot receiving address information corresponding to each consumption field in each historical time period to obtain a quantified result, and obtaining the hot receiving address information of different consumption fields in any future time period based on all the quantified results and the prediction model corresponding to each consumption field.
This step can be understood as: for example, in the day before the current time, the hot receiving address of the field of fresh food is a achievement, so that the hot receiving address of the first two days can be calculated according to the method, the field of fresh food can be obtained according to the logic, the hot receiving addresses of the fields of fresh food in different historical time periods are quantified, for example, the U.S. is recorded as 1, the Germany is recorded as 2, the England is recorded as 3, and the like, the time sequence of the hot receiving address corresponding to each consumption field can be obtained, and then the sequence is input into a prediction model, so that the future hot receiving address can be predicted; the specific implementation steps of the step comprise a step S421 and a step S422;
step S421, collecting all quantization results corresponding to each consumption field to obtain a first data set, and denoising the data set by using a Kalman filtering algorithm to obtain a second data set;
in the step, after the data set is denoised by using a Kalman filtering algorithm, the accuracy of the data can be improved, and the accuracy of model prediction is further improved.
And step 422, constructing a differential autoregressive moving average prediction model according to the second data set, and predicting hot receiving address information of different consumption fields in any future time period by using the differential autoregressive moving average prediction model.
By the steps, future hot receiving addresses can be predicted, planning and scheduling of transport means can be performed in advance after the future hot receiving addresses are predicted, enough transport means are ensured to transport at the time, the aim of timely delivering to customers is fulfilled, and customer satisfaction is improved.
Example 2
As shown in fig. 2, the present embodiment provides an import-export trade order management system, which includes an acquisition module 701, a classification module 702, a clustering module 703, and an analysis module 704.
An acquisition module 701, configured to acquire historical order data in different historical time periods, where the historical order data includes historical consumer purchase information, and the consumer purchase information includes purchase merchandise information and first historical shipping address information;
the classification module 702 is configured to determine, according to the historical consumer purchase information, a consumption domain to which each historical order data belongs, and classify the historical order data according to the consumption domain, so as to obtain a plurality of historical order data sets;
the clustering module 703 is configured to perform a clustering operation on the first historical receiving address information corresponding to each of the historical order data in each of the historical order data sets based on a DBSCAN clustering algorithm, so as to obtain a receiving address information clustering result;
the analysis module 704 is configured to analyze the shipping address information clustering result to obtain hot shipping address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period so as to prompt merchants to arrange transportation means.
In a specific embodiment of the disclosure, the classification module 702 further includes an input unit 7021 and a first training unit 7022.
An input unit 7021, configured to input the purchased commodity information into a preset attention model, so as to obtain attention point data output by the attention model;
the first training unit 7022 is configured to obtain sample purchase commodity information, record the sample purchase commodity information into a preset attention model, obtain sample attention point data output by the attention model, label the sample attention point data, and make labeling information be a consumption field corresponding to the sample attention point data; training the convolutional neural network model by using the marked sample focus data to obtain a first model; and inputting the attention point data output by the attention model into the first model to obtain the consumption field of each historical order data.
In a specific embodiment of the disclosure, the clustering module 703 further includes an extracting unit 7031 and a clustering unit 7032.
The extracting unit 7031 is configured to perform feature extraction on the first historical receiving address information to obtain a feature vector, and record the feature vector as first data;
the clustering unit 7032 is configured to perform clustering processing on each first historical receiving address information by using a DBSCAN clustering algorithm and first data to obtain a plurality of first clustering results, aggregate all the first historical receiving address information included in each first clustering result to obtain a first set, and perform average value calculation on first data corresponding to each first historical receiving address information in the first set to obtain second data; and calculating and obtaining a goods receiving address information clustering result based on the second data.
In a specific embodiment of the disclosure, the clustering unit 7032 further includes a first computing unit 70321, a second training unit 70322, and a second computing unit 70323.
A first calculating unit 70321, configured to calculate, for each first clustering result, a distance between each first data corresponding to the first clustering result and the second data, and record, as third data, the first data corresponding to the farthest distance; combining the third data and the second data according to a preset combination rule to obtain fourth data, calculating a feature vector of a covariance matrix corresponding to the fourth data, and marking the feature vector of the covariance matrix corresponding to the fourth data as fifth data;
a second training unit 70322, configured to input each fifth data into a preset second model, to obtain an evaluation result corresponding to each fifth data; when the second model is trained, firstly acquiring sample data, wherein the sample data comprises second historical receiving address information, carrying out clustering processing on the second historical receiving address information to obtain a plurality of second aggregation results, carrying out evaluation result labeling on each second aggregation result, and simultaneously calculating feature vectors of covariance matrixes corresponding to each second aggregation result; training by taking the eigenvectors of the covariance matrix corresponding to each second clustering result as input and marking information as output by adopting a deep learning method to obtain a second model;
and the second calculating unit 70323 is configured to calculate and obtain a shipping address information clustering result according to the evaluation result corresponding to each of the fifth data.
In a specific embodiment of the disclosure, the second computing unit 70323 further includes an interpretation unit 703231.
The interpretation unit 703231 is configured to interpret the evaluation results corresponding to each of the fifth data, and if the interpretation results satisfy a preset criterion, take a plurality of first clustering results obtained by clustering at this time as the shipping address information clustering results, where the preset criterion is that all the evaluation results corresponding to N fifth data after interpretation reach a standard evaluation result, N is a positive integer greater than zero and N is greater than a preset value; otherwise, parameters of a DBSCAN clustering algorithm are adjusted, and clustering is conducted again until the evaluation result meets the preset standard.
In a specific embodiment of the disclosure, the analysis module 704 further includes a third calculation unit 7041 and a prediction unit 7042.
A third calculating unit 7041, configured to use a sub-cluster result with the most data in each of the receiving address information cluster results as hot receiving address information, where the receiving address information cluster result is composed of sub-cluster results;
the predicting unit 7042 is configured to quantize, for each historical time period, the hot receiving address information corresponding to each consumption domain in the historical time period, to obtain a quantized result, and obtain the hot receiving address information of different consumption domains in any future time period based on all quantized results and prediction models corresponding to each consumption domain.
In a specific embodiment of the disclosure, the prediction unit 7042 further includes a collection unit 70421 and a construction unit 70422.
The aggregation unit 70421 is configured to aggregate all quantization results corresponding to each consumption field to obtain a first data set, and denoise the data set by using a kalman filtering algorithm to obtain a second data set;
and the construction unit 70422 is used for constructing a differential autoregressive moving average prediction model according to the second data set, and predicting hot receiving address information of different consumption fields at any future time period by using the differential autoregressive moving average prediction model.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3
Corresponding to the above method embodiments, the embodiments of the present disclosure further provide import and export goods trade order management apparatuses, and the import and export goods trade order management apparatuses described below and the import and export goods trade order management methods described above may be referred to correspondingly with each other.
Fig. 3 is a block diagram illustrating an import-export goods trade order management device 800 according to an example embodiment. As shown in fig. 3, the import-export trade order management device 800 may include: a processor 801, a memory 802. The import and export goods trade order management device 800 may also include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
Wherein the processor 801 is configured to control the overall operation of the import and export commodity trade order management apparatus 800 to perform all or part of the steps of the import and export commodity trade order management method described above. The memory 802 is used to store various types of data to support the operation of the import and export shipment trade order management device 800, which may include, for example, instructions for any application or method operating on the import and export shipment trade order management device 800, as well as application related data such as contact data, messaging, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to provide wired or wireless communication between the import and export goods trade order management device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the import and export commodity trade order management device 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (DigitalSignal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the import and export commodity trade order management method described above.
In another exemplary embodiment, a computer readable storage medium is also provided that includes program instructions that when executed by a processor implement the steps of the import and export trade order management method described above. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the import and export commodity trade order management device 800 to perform the import and export commodity trade order management method described above.
Example 4
Corresponding to the above method embodiments, the present disclosure further provides a readable storage medium, where a readable storage medium described below and the import and export goods trade order management method described above may be referred to correspondingly.
A readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the import and export goods trade order management method of the above method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method for managing import and export goods trade orders, comprising:
acquiring historical order data in different historical time periods, wherein the historical order data comprises historical consumer purchase information, and the consumer purchase information comprises purchase commodity information and first historical receiving address information;
determining the consumption field to which each historical order data belongs according to the historical consumer purchase information, and classifying the historical order data according to the consumption field to obtain a plurality of historical order data sets;
clustering the first historical receiving address information corresponding to each historical order data in each historical order data set based on a DBSCAN clustering algorithm to obtain a receiving address information clustering result;
analyzing the goods receiving address information clustering result to obtain hot goods receiving address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period so as to prompt merchants to arrange transportation means.
2. The import and export trade order management method of claim 1, wherein determining the consumption domain to which each historical order data belongs based on the historical consumer purchase records comprises:
inputting the information of the purchased commodity into a preset attention model to obtain attention point data output by the attention model;
acquiring sample purchase commodity information, recording the sample purchase commodity information into a preset attention model, obtaining sample attention point data output by the attention model, marking the sample attention point data, and marking the consumption field corresponding to the sample attention point data as marking information; training the convolutional neural network model by using the marked sample focus data to obtain a first model; and inputting the attention point data output by the attention model into the first model to obtain the consumption field of each historical order data.
3. The import and export commodity trade order management method according to claim 1, wherein clustering each of the historical order data sets based on a DBSCAN clustering algorithm to obtain a commodity receiving address information clustering result comprises:
extracting features of the first historical receiving address information to obtain feature vectors, and marking the feature vectors as first data;
clustering the first historical goods receiving address information by using a DBSCAN clustering algorithm and first data to obtain a plurality of first clustering results, collecting all the first historical goods receiving address information contained in each first clustering result to obtain a first set, and calculating the average value of first data corresponding to each first historical goods receiving address information in the first set to obtain second data; and calculating and obtaining a goods receiving address information clustering result based on the second data.
4. The import and export commodity trade order management method according to claim 3, wherein calculating based on the second data results in a commodity-receiving address information clustering result, comprising:
for each first clustering result, calculating the distance between each first data corresponding to the first clustering result and the second data, and recording the first data corresponding to the farthest distance as third data; combining the third data and the second data according to a preset combination rule to obtain fourth data, calculating a feature vector of a covariance matrix corresponding to the fourth data, and marking the feature vector of the covariance matrix corresponding to the fourth data as fifth data;
inputting each fifth data into a preset second model to obtain an evaluation result corresponding to each fifth data; when the second model is trained, firstly acquiring sample data, wherein the sample data comprises second historical receiving address information, carrying out clustering processing on the second historical receiving address information to obtain a plurality of second aggregation results, carrying out evaluation result labeling on each second aggregation result, and simultaneously calculating feature vectors of covariance matrixes corresponding to each second aggregation result; training by taking the eigenvectors of the covariance matrix corresponding to each second clustering result as input and marking information as output by adopting a deep learning method to obtain a second model;
and calculating according to the evaluation result corresponding to each fifth data to obtain a goods receiving address information clustering result.
5. The import and export commodity trade order management method according to claim 4, wherein the calculating to obtain the commodity-receiving address information clustering result according to the evaluation result corresponding to each of the fifth data comprises:
reading the evaluation results corresponding to each fifth data, and if the evaluation results after reading meet a preset standard, taking a plurality of first clustering results obtained by clustering at the moment as the goods receiving address information clustering results, wherein the preset standard is that the evaluation results corresponding to N fifth data after reading all reach standard evaluation results, N is a positive integer greater than zero, and N is greater than a preset numerical value; otherwise, parameters of a DBSCAN clustering algorithm are adjusted, and clustering is conducted again until the evaluation result meets the preset standard.
6. A import-export trade order management system, comprising:
the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring historical order data in different historical time periods, the historical order data comprises historical consumer purchase information, and the consumer purchase information comprises purchase commodity information and first historical receiving address information;
the classification module is used for determining the consumption field to which each historical order data belongs according to the historical consumer purchase information, classifying the historical order data according to the consumption field and obtaining a plurality of historical order data sets;
the clustering module is used for carrying out clustering operation on the first historical receiving address information corresponding to each historical order data in each historical order data set based on a DBSCAN clustering algorithm to obtain a receiving address information clustering result;
the analysis module is used for analyzing the goods receiving address information clustering result to obtain hot goods receiving address information corresponding to different consumption fields in each historical time period; and predicting the hot receiving address information of different consumption fields in any future period based on the hot receiving address information corresponding to different consumption fields in each historical period so as to prompt merchants to arrange transportation vehicles.
7. The import and export trade order management system of claim 6, wherein the classification module comprises:
the input unit is used for inputting the information of the purchased goods into a preset attention model to obtain attention point data output by the attention model;
the first training unit is used for acquiring sample commodity purchasing information, inputting the sample commodity purchasing information record into a preset attention model, obtaining sample attention point data output by the attention model, marking the sample attention point data, and marking the consumption field corresponding to the sample attention point data as marking information; training the convolutional neural network model by using the marked sample focus data to obtain a first model; and inputting the attention point data output by the attention model into the first model to obtain the consumption field of each historical order data.
8. The import and export trade order management system of claim 6, wherein the clustering module comprises:
the extracting unit is used for carrying out feature extraction on the first historical goods receiving address information to obtain feature vectors, and the feature vectors are recorded as first data;
the clustering unit is used for carrying out clustering processing on each first historical goods receiving address information by using a DBSCAN clustering algorithm and first data to obtain a plurality of first clustering results, collecting all first historical goods receiving address information contained in each first clustering result to obtain a first set, and carrying out average value calculation on first data corresponding to each first historical goods receiving address information in the first set to obtain second data; and calculating and obtaining a goods receiving address information clustering result based on the second data.
9. The import and export trade order management system of claim 8, wherein the clustering unit comprises:
the first calculation unit is used for calculating the distance between each first data corresponding to each first clustering result and the second data according to each first clustering result, and recording the first data corresponding to the farthest distance as third data; combining the third data and the second data according to a preset combination rule to obtain fourth data, calculating a feature vector of a covariance matrix corresponding to the fourth data, and marking the feature vector of the covariance matrix corresponding to the fourth data as fifth data;
the second training unit is used for inputting each fifth data into a preset second model to obtain an evaluation result corresponding to each fifth data; when the second model is trained, firstly acquiring sample data, wherein the sample data comprises second historical receiving address information, carrying out clustering processing on the second historical receiving address information to obtain a plurality of second aggregation results, carrying out evaluation result labeling on each second aggregation result, and simultaneously calculating feature vectors of covariance matrixes corresponding to each second aggregation result; training by taking the eigenvectors of the covariance matrix corresponding to each second clustering result as input and marking information as output by adopting a deep learning method to obtain a second model;
and the second calculation unit is used for calculating and obtaining a goods receiving address information clustering result according to the evaluation result corresponding to each fifth data.
10. The import and export trade order management system of claim 9, wherein the second calculation unit comprises:
the interpretation unit is used for interpreting the evaluation results corresponding to each fifth data, and if the interpretation results meet a preset standard, the first clustering results obtained by clustering at the moment are used as the goods receiving address information clustering results, wherein the preset standard is that the evaluation results corresponding to N fifth data after interpretation all reach standard evaluation results, N is a positive integer larger than zero, and N is larger than a preset value; otherwise, parameters of a DBSCAN clustering algorithm are adjusted, and clustering is conducted again until the evaluation result meets the preset standard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311155147.3A CN116882598B (en) | 2023-09-08 | 2023-09-08 | Import and export goods trade order management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311155147.3A CN116882598B (en) | 2023-09-08 | 2023-09-08 | Import and export goods trade order management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116882598A true CN116882598A (en) | 2023-10-13 |
| CN116882598B CN116882598B (en) | 2023-12-29 |
Family
ID=88257326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311155147.3A Active CN116882598B (en) | 2023-09-08 | 2023-09-08 | Import and export goods trade order management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882598B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230049A (en) * | 2018-02-09 | 2018-06-29 | 新智数字科技有限公司 | The Forecasting Methodology and system of order |
| CN112884547A (en) * | 2021-02-03 | 2021-06-01 | 绿瘦健康产业集团有限公司 | Intelligent commodity recommendation method, device, medium and terminal equipment |
| CN113792945A (en) * | 2021-11-17 | 2021-12-14 | 西南交通大学 | Dispatching method, device, equipment and readable storage medium of commercial vehicle |
| US20230029209A1 (en) * | 2019-12-24 | 2023-01-26 | Kim O Seong | System for providing shoe management service by using o2o-based delivery business platform |
| CN116228078A (en) * | 2023-05-08 | 2023-06-06 | 合肥新鸟科技有限公司 | Logistics distribution vehicle dispatching method and system |
| CN116308662A (en) * | 2023-03-17 | 2023-06-23 | 北京三快在线科技有限公司 | Group order processing system and method |
-
2023
- 2023-09-08 CN CN202311155147.3A patent/CN116882598B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230049A (en) * | 2018-02-09 | 2018-06-29 | 新智数字科技有限公司 | The Forecasting Methodology and system of order |
| US20230029209A1 (en) * | 2019-12-24 | 2023-01-26 | Kim O Seong | System for providing shoe management service by using o2o-based delivery business platform |
| CN112884547A (en) * | 2021-02-03 | 2021-06-01 | 绿瘦健康产业集团有限公司 | Intelligent commodity recommendation method, device, medium and terminal equipment |
| CN113792945A (en) * | 2021-11-17 | 2021-12-14 | 西南交通大学 | Dispatching method, device, equipment and readable storage medium of commercial vehicle |
| CN116308662A (en) * | 2023-03-17 | 2023-06-23 | 北京三快在线科技有限公司 | Group order processing system and method |
| CN116228078A (en) * | 2023-05-08 | 2023-06-06 | 合肥新鸟科技有限公司 | Logistics distribution vehicle dispatching method and system |
Non-Patent Citations (6)
| Title |
|---|
| HUMA AFTAB等: "Hybrid DGSCN based community Detection for Edge Caching in Social Media Application", 《2021 INTERNATIONAL WIRELESS COMMUNICATIONS AND MOBILE COMPUTING(IWCMC)》, pages 2038 - 2043 * |
| LI JING等: "Adaptive scheduling for assembly job shop with uncertain assembly times based on dual Q-learning", 《INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH》, vol. 59, no. 19, pages 5867 - 5883 * |
| 孔瑶瑶: "基于网约车订单数据的热点区域出行需求预测", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 03, pages 034 - 1478 * |
| 李静: "基于三维显示的移动端B2C商城系统的研究与设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 04, pages 139 - 548 * |
| 董长春: "商品车运输动态调度技术研究及应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 02, pages 034 - 604 * |
| 贾肖琼: "需求激增下食品冷链配送排程与路径联合优化研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 03, pages 140 - 336 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116882598B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI686760B (en) | Data processing method, device, equipment and server for insurance fraud identification | |
| CN107358247B (en) | Method and device for determining lost user | |
| CN111401777B (en) | Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium | |
| CN111340246A (en) | Processing method and device for enterprise intelligent decision analysis and computer equipment | |
| CN112884224A (en) | Method and device for selecting address of entity object, computing equipment and computer storage medium | |
| CN109815480B (en) | Data processing method and device and storage medium | |
| CN112001754A (en) | User portrait generation method, device, equipment and computer readable medium | |
| Tong et al. | Developing econometrics | |
| Hashemian et al. | Socioeconomic characterization of regions through the lens of individual financial transactions | |
| KR20200039852A (en) | Method for analysis of business management system providing machine learning algorithm for predictive modeling | |
| CN112270596A (en) | Risk control system and method based on user portrait construction | |
| CN114997916A (en) | Prediction method, system, electronic device and storage medium of potential user | |
| Jang et al. | Detection and prediction of house price bubbles: Evidence from a new city | |
| CN113313538A (en) | User consumption capacity prediction method and device, electronic equipment and storage medium | |
| Calabrese | Optimal cut-off for rare events and unbalanced misclassification costs | |
| CN116882598B (en) | Import and export goods trade order management method and system | |
| Akande et al. | Application of XGBoost Algorithm for Sales Forecasting Using Walmart Dataset | |
| Baltagi et al. | Determinants of firm-level domestic sales and exports with spillovers: Evidence from China | |
| Poornima et al. | Prediction of water consumption using machine learning algorithm | |
| Zhuravlev et al. | Using Hough-like transforms for extracting relevant regularities from big applied data | |
| CN115471260A (en) | Neural network-based sales prediction method, apparatus, device and medium | |
| CN114066564A (en) | Service recommendation time determination method and device, computer equipment and storage medium | |
| Mahalle et al. | Data Acquisition and Preparation | |
| Seidu | Predicting bankruptcy risk: A gaussian process classifciation model | |
| CN108270606B (en) | Service quality prediction method and service quality prediction device |
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 |