CN117350607A - International logistics transportation path planning system of improved KNN algorithm model - Google Patents
International logistics transportation path planning system of improved KNN algorithm model Download PDFInfo
- Publication number
- CN117350607A CN117350607A CN202311206646.0A CN202311206646A CN117350607A CN 117350607 A CN117350607 A CN 117350607A CN 202311206646 A CN202311206646 A CN 202311206646A CN 117350607 A CN117350607 A CN 117350607A
- Authority
- CN
- China
- Prior art keywords
- data
- path planning
- module
- logistics transportation
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013439 planning Methods 0.000 title claims abstract description 134
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 95
- 238000012937 correction Methods 0.000 claims abstract description 47
- 230000003993 interaction Effects 0.000 claims abstract description 46
- 238000007726 management method Methods 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 62
- 238000004364 calculation method Methods 0.000 claims description 44
- 238000012545 processing Methods 0.000 claims description 34
- 238000004458 analytical method Methods 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 24
- 230000007246 mechanism Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 230000003044 adaptive effect Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000013079 data visualisation Methods 0.000 claims description 10
- 230000002452 interceptive effect Effects 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 7
- 238000000691 measurement method Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000012098 association analyses Methods 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 238000005111 flow chemistry technique Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010926 purge Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004043 responsiveness Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- 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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Abstract
The invention discloses an international logistics transportation path planning system of an improved KNN algorithm model, which relates to the field of international logistics transportation and comprises an information updating module, a data quality management module, a path planning module, an interface interaction module, a path feedback correction module and a cache memory module, wherein the output end of the information updating module is connected with the input end of the data quality management module, the output end of the data quality management module is connected with the input end of the path planning module, the output end of the interface interaction module is connected with the input end of the path feedback correction module, and the output ends of the path planning module and the path feedback correction module are connected with the input end of the cache memory module; the invention can realize real-time acquisition, quality management, path planning and interface interaction of logistics transportation data, and has high automation and intelligent degree.
Description
Technical Field
The invention relates to the field of international logistics transportation, in particular to an international logistics transportation path planning system of an improved KNN algorithm model.
Background
With the continuous development of international trade, logistics industry is also becoming an important component of national economy gradually. And logistics transportation path planning is used as one of core business of logistics industry and plays a vital role in logistics enterprises.
The conventional logistics transportation path planning algorithm, such as a shortest path algorithm, a minimum spanning tree algorithm and the like, has the defects of low accuracy and easiness in limitation of path length, transportation cost and the like. Therefore, in order to improve the accuracy and efficiency of logistics transportation path planning, a more advanced algorithm model needs to be adopted. The improved KNN algorithm model optimizes the transportation route by considering actual conditions and business requirements in the logistics transportation route, and can effectively improve the accuracy and efficiency of route planning. Therefore, the international logistics transportation path planning system adopting the improved KNN algorithm model has high practical value.
However, in the existing international logistics transportation path planning system of the improved KNN algorithm model, incomplete and inaccurate conditions such as road network data, cargo data and vehicle data are often encountered in practical application, so that the operation effect of the system is affected, the logistics condition of adapting to changes in time cannot be realized, and the user experience is not friendly enough.
Therefore, the invention discloses an international logistics transportation path planning system of an improved KNN algorithm model, which can realize real-time acquisition, quality management, path planning and interface interaction of logistics transportation data.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an international logistics transportation path planning system of an improved KNN algorithm model, which can realize real-time acquisition, quality management, path planning and interface interaction of logistics transportation data; the improved KNN algorithm model is adopted for path planning, and can better adapt to the change of real-time logistics transportation data and update the real-time data through a time window mechanism compared with the traditional KNN algorithm model, so that the instantaneity and the accuracy of path planning are ensured; the system introduces a data quality management module, can evaluate, preprocess, clean and other operations on logistics transportation data acquired in real time, and improves the quality and consistency of the data; the logistics transportation data and the path planning scheme are visually displayed, and the interface interaction module is used for interacting with a user, so that the path planning scheme is further optimized, and the real-time responsiveness and the user experience of the system are improved; the path feedback correction module is introduced, and real-time information feedback and scheme correction can be carried out on the path planning scheme according to interface interaction information so as to better meet the requirements of users and actual transportation conditions; and the automation degree and the intelligent degree are high.
The invention adopts the following technical scheme:
an international logistics transportation path planning system of an improved KNN algorithm model, the system comprising:
the information updating module is used for acquiring logistics transportation data in real time, wherein the logistics transportation data comprises road network data, cargo data, vehicle data and air image data, and the information updating module updates the real-time logistics transportation data through a wireless sensor network and a real-time data access interface and transmits the logistics transportation data to a message queue for further processing;
the data quality management module is used for evaluating the quality of the logistics transportation data and preprocessing the data according to an evaluation result, and the quality management module adopts a data rule engine to evaluate the accuracy, the integrity, the consistency, the timeliness and the credibility of the logistics transportation data and performs cleaning, denoising and normalization processing on the logistics transportation data according to the evaluation result so as to ensure the quality and the consistency of the data;
the path planning module is used for planning an international logistics transportation path, the path planning module performs path planning by embedding an improved KNN algorithm model, the improved KNN algorithm model provides an optimal path planning scheme according to logistics transportation data, and an incremental calculation mode and a time window mechanism are adopted for updating real-time logistics transportation data;
The interface interaction module is used for carrying out interface interaction display on the logistics transportation data and the path planning scheme;
the path feedback correction module is used for carrying out real-time information feedback and scheme correction on the path planning scheme of the path planning module according to the interface interaction information;
the cache memory module is used for caching historical logistics transportation data and a path planning scheme so that the system can quickly respond when similar conditions occur;
the output end of the information updating module is connected with the input end of the data quality management module, the output end of the data quality management module is connected with the input end of the interface interaction module, the output end of the data quality management module is connected with the input end of the path planning module, the output end of the path planning module is connected with the input end of the interface interaction module, the output end of the interface interaction module is connected with the input end of the path feedback correction module, the output end of the path planning module is connected with the input end of the cache memory module, and the output end of the path feedback correction module is connected with the input end of the cache memory module.
As a further technical scheme of the invention, the working steps of the improved KNN algorithm model comprise:
Step 1, inputting data, extracting features, inputting pretreated logistics transportation data into an improved KNN algorithm model, extracting cargo weight, cargo volume, starting place and destination, transportation mode characteristics, transportation cost and transportation time limiting features, regularizing the extracted features and expressing feature vectors, wherein the extracted features are divided into non-numerical features and numerical features, and expressing feature vector sets as follows:
in formula (1)Wherein X represents a feature vector set of logistics transportation data,for the i-th non-numerical feature vector, i is 1-n, i is the ordinal number of the non-numerical feature vector of the logistics transportation data, n is the number of the non-numerical feature vector of the logistics transportation data, c represents the non-numerical feature vector, & lt/EN & gt>J is the j-th numerical characteristic vector, j is more than or equal to 1 and less than or equal to m, j is the ordinal number of the numerical characteristic vector of the logistics transportation data, m is the number of the numerical characteristic vector of the logistics transportation data, and r represents the numerical characteristic vector;
step 2, calculating the distance or similarity between samples, calculating the distance or similarity between all logistics nodes based on a feature vector set, calculating the distance or similarity between all the logistics nodes by adopting a non-numerical feature vector by adopting a Euclidean distance measurement method, calculating the distance or similarity between all the logistics nodes by adopting a numerical feature vector by adopting a cosine similarity measurement method, and outputting a function formula as follows:
In the formula (2) of the present invention,for the i-th non-numerical feature vector representing the distance from the logistics node to the master node, +.>For the ith training non-numeric feature vector, < +.>For j-th numerical eigenvector representing the distance from the logistics node to the master node, +.>A numerical feature vector for the jth training;
step 3, selecting candidate routes, namely selecting the largest l feature vectors as projection directions according to the sorting of distances or similarity between the feature vectors representing logistics nodes, wherein l is a reduced dimension, multiplying an original data sample by the selected feature vectors to sort, and selecting K paths closest to a path to be planned as candidate paths;
step 4, adaptively setting weights according to the distances, adaptively adjusting the weights according to the distance calculation results among the logistics nodes, and obtaining a distance data set D among the K path logistics nodes as D= { D 1 ,...,d g ,...,d K The adaptive weight output function formula is:
in formula (3), q g The importance degree of the g-th route on the logistics transportation task, d g K is a parameter for controlling the exponential decay rate for the distance between the g-th path logistics nodes;
step 5, carrying out fine control and optimization on the solving process, improving the calculation accuracy by splitting the measuring units, and distributing calculation tasks to a plurality of processors or calculation nodes in a parallel calculation mode so as to improve the calculation speed;
And 6, outputting a result, namely sorting the weights of the paths from high to low, and outputting the result.
As a further technical scheme of the invention, the workflow of the incremental calculation mode and the time window mechanism comprises:
s1, training based on an initial improved KNN algorithm model to obtain an initial path plan;
s2, setting the size of a time window as T, adding a newly added data point X into a data set D in the time window, setting the size of the newly added data point X as T, and carrying out weight calculation on the newly added data point;
s3, updating a K value by adopting an increment calculation mode to adapt to a newly added data point, wherein a calculation object of the increment calculation mode is the newly added data point X;
s4, carrying out real-time updating iteration on the improved KNN algorithm model according to the data set D in the time window, and executing S2 if the maximum iteration times, the error drop threshold or the K value variation are met, directly outputting a path planning result, and if the maximum iteration times, the error drop threshold or the K value variation are not met;
s5, outputting the final path planning scheme and the updated model parameters, and continuously adding new data points for updating iteration.
As a further technical scheme of the invention, the path feedback correction module comprises a feedback collection unit, a feedback analysis unit and a scheme correction unit, wherein the feedback collection unit is used for receiving feedback information output by the interface interaction module in real time, the feedback analysis unit is used for carrying out instant analysis and evaluation on the collected feedback information, the scheme correction unit is used for formulating a path correction strategy according to an evaluation result of the feedback analysis unit, the output end of the feedback collection unit is connected with the input end of the feedback analysis unit, the output end of the feedback analysis unit is connected with the input end of the scheme correction unit, the feedback collection unit carries out data communication with the interface interaction module through WebSocket real-time communication protocol, receives feedback information output by the interface interaction module, and the feedback analysis unit carries out instant analysis and evaluation on the collected feedback information through a real-time stream processing engine, and the scheme correction unit formulates the path correction strategy through an embedded self-adaptive decision model.
As a further technical scheme of the present invention, the real-time stream processing engine obtains the importance degree of the feedback information and the satisfaction degree of the user to the path planning scheme through a machine learning algorithm, the machine learning algorithm predicts the importance degree of the feedback information and the satisfaction degree of the user to the path planning scheme through training the image path planning characteristics and the user satisfaction degree characteristics, and the output function formula of the satisfaction degree of the user to the path planning scheme is:
in the formula (8), q represents the importance degree of the route to the logistics transportation task; e is the highest score of the user on the path planning scheme, A is the lowest score of the user on the path planning scheme, E, A is a constant between 0 and 5, and an output function formula of the importance degree of the feedback information is as follows:
in the formula (9), ω is the importance degree of the feedback information, when the satisfaction degree of the user to the path planning scheme is greater than one, the importance degree of the feedback information is the satisfaction degree of the user to the path planning scheme, when the satisfaction degree of any one user to the path planning scheme is greater than one and less than zero, a function formula is output, ζ is a decision value of the optimal path, and 0< ζ is less than or equal to 1.
As a further technical scheme of the invention, the self-adaptive decision model comprises an input layer, a feature extraction layer, a self-adaptive adjustment layer, a self-adaptive weight layer, a self-adaptive topological structure layer and an output layer, and the working method of the self-adaptive decision model comprises the following steps:
(1) Inputting the feedback information evaluation result to the self-adaptive decision model through the input layer;
(2) The method comprises the steps of carrying out feature extraction on feedback information evaluation results through a feature extraction layer, and screening out obvious noise and interference signals, wherein the feature extraction layer comprises four network neurons so as to fully extract data features;
(3) The self-adaptive adjusting layer adjusts the learning rate of the neural network in a self-adaptive manner, and the self-adaptive adjusting layer adjusts the learning rate according to the state and performance indexes of the neural network so as to improve the convergence effect and performance of the neural network;
(4) Dynamically adjusting the weight of the neural network through the self-adaptive weight layer so as to improve the precision and generalization capability of the network;
(5) Dynamically adjusting the topological structure of the neural network through a self-adaptive topological structure layer, wherein the self-adaptive topological structure layer adopts a genetic optimization method to adaptively adjust the structure and topology of the network so as to adapt to complex tasks and data;
(6) The result is passed to the outside through the output layer.
As a further technical scheme of the invention, the interface interaction module carries out interface interaction display on logistics transportation data and a path planning scheme by adopting a data visualization platform, the data visualization platform obtains mass data source association data based on an association data model so as to realize multidimensional data association analysis, and adopts an interactive chart, a heat point diagram, a map and an instrument board to realize real-time monitoring of trend, relationship and change rule of data, and the data visualization platform adopts a Token user identity verification mechanism to verify the identity of an access user so as to improve the safety of information access.
As a further technical scheme of the invention, the cache memory module records the number of times the cache item is called through the access counter, adopts a timer to trigger a clearing operation, and the clearing operation reorders the weight of the cache item according to the number of times the cache item is called and the calling time, and clears the cache item based on the LRU cache strategy so as to improve the calling speed.
Has the positive beneficial effects that:
the invention discloses an international logistics transportation path planning system of an improved KNN algorithm model, which can realize real-time acquisition, quality management, path planning and interface interaction of logistics transportation data; the improved KNN algorithm model is adopted for path planning, and can better adapt to the change of real-time logistics transportation data and update the real-time data through a time window mechanism compared with the traditional KNN algorithm model, so that the instantaneity and the accuracy of path planning are ensured; the system introduces a data quality management module, can evaluate, preprocess, clean and other operations on logistics transportation data acquired in real time, and improves the quality and consistency of the data; the logistics transportation data and the path planning scheme are visually displayed, and the interface interaction module is used for interacting with a user, so that the path planning scheme is further optimized, and the real-time responsiveness and the user experience of the system are improved; the path feedback correction module is introduced, and real-time information feedback and scheme correction can be carried out on the path planning scheme according to interface interaction information so as to better meet the requirements of users and actual transportation conditions; and the automation degree and the intelligent degree are high.
Drawings
FIG. 1 is a schematic diagram of the overall architecture of an international logistics transportation path planning system of an improved KNN algorithm model in accordance with the present invention;
FIG. 2 is a workflow diagram of an improved KNN algorithm model in an international logistics transportation path planning system of the improved KNN algorithm model in accordance with the present invention;
FIG. 3 is a schematic diagram of the operation of the information update module in the international logistics transportation path planning system of the improved KNN algorithm model;
fig. 4 is an overall architecture diagram of an adaptive decision model in an international logistics transportation path planning system of an improved KNN algorithm model according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
An international logistics transportation path planning system of an improved KNN algorithm model, the system comprising:
the information updating module is used for acquiring logistics transportation data in real time, wherein the logistics transportation data comprises road network data, cargo data, vehicle data and air image data, and the information updating module updates the real-time logistics transportation data through a wireless sensor network and a real-time data access interface and transmits the logistics transportation data to a message queue for further processing;
The data quality management module is used for evaluating the quality of the logistics transportation data and preprocessing the data according to an evaluation result, and the quality management module adopts a data rule engine to evaluate the accuracy, the integrity, the consistency, the timeliness and the credibility of the logistics transportation data and performs cleaning, denoising and normalization processing on the logistics transportation data according to the evaluation result so as to ensure the quality and the consistency of the data;
the path planning module is used for planning an international logistics transportation path, the path planning module performs path planning by embedding an improved KNN algorithm model, the improved KNN algorithm model provides an optimal path planning scheme according to logistics transportation data, and an incremental calculation mode and a time window mechanism are adopted for updating real-time logistics transportation data;
the interface interaction module is used for carrying out interface interaction display on the logistics transportation data and the path planning scheme;
the path feedback correction module is used for carrying out real-time information feedback and scheme correction on the path planning scheme of the path planning module according to the interface interaction information;
the cache memory module is used for caching historical logistics transportation data and a path planning scheme so that the system can quickly respond when similar conditions occur;
The output end of the information updating module is connected with the input end of the data quality management module, the output end of the data quality management module is connected with the input end of the interface interaction module, the output end of the data quality management module is connected with the input end of the path planning module, the output end of the path planning module is connected with the input end of the interface interaction module, the output end of the interface interaction module is connected with the input end of the path feedback correction module, the output end of the path planning module is connected with the input end of the cache memory module, and the output end of the path feedback correction module is connected with the input end of the cache memory module.
In a specific embodiment, the international logistics transportation path planning system of the improved KNN algorithm model adopts a data caching mechanism to cache the preprocessed original acquired data to a memory or a disk for waiting for processing, so as to reduce data processing delay and data reading times, adopts a concurrent processing mechanism to process large-scale real-time data in parallel, and adopts a load balancing algorithm to distribute the data streams to processing nodes by dividing the large-scale acquired data into data streams through hash values of the data by the concurrent processing mechanism, and adopts a multi-core CPU processor to process the data by a real-time stream processing engine tool, so that the processing efficiency and throughput are improved.
In the above embodiment, the working steps of the improved KNN algorithm model include:
step 1, inputting data, extracting features, inputting pretreated logistics transportation data into an improved KNN algorithm model, extracting cargo weight, cargo volume, starting place and destination, transportation mode characteristics, transportation cost and transportation time limiting features, regularizing the extracted features and expressing feature vectors, wherein the extracted features are divided into non-numerical features and numerical features, and expressing feature vector sets as follows:
in the formula (1), X represents a feature vector set of logistics transportation data,for the i-th non-numerical feature vector, i is 1-n, i is the ordinal number of the non-numerical feature vector of the logistics transportation data, n is the number of the non-numerical feature vector of the logistics transportation data, c represents the non-numerical feature vector, & lt/EN & gt>J is the j-th numerical characteristic vector, j is more than or equal to 1 and less than or equal to m, j is the ordinal number of the numerical characteristic vector of the logistics transportation data, m is the number of the numerical characteristic vector of the logistics transportation data, and r represents the numerical characteristic vector;
step 2, calculating the distance or similarity between samples, calculating the distance or similarity between all logistics nodes based on a feature vector set, calculating the distance or similarity between all the logistics nodes by adopting a non-numerical feature vector by adopting a Euclidean distance measurement method, calculating the distance or similarity between all the logistics nodes by adopting a numerical feature vector by adopting a cosine similarity measurement method, and outputting a function formula as follows:
In the formula (2) of the present invention,for the i-th non-numerical feature vector representing the distance from the logistics node to the master node, +.>For the ith training non-numeric feature vector, < +.>For j-th numerical eigenvector representing the distance from the logistics node to the master node, +.>A numerical feature vector for the jth training;
step 3, selecting candidate routes, namely selecting the largest l feature vectors as projection directions according to the sorting of distances or similarity between the feature vectors representing logistics nodes, wherein l is a reduced dimension, multiplying an original data sample by the selected feature vectors to sort, and selecting K paths closest to a path to be planned as candidate paths;
step 4, adaptively setting weights according to the distances, adaptively adjusting the weights according to the distance calculation results among the logistics nodes, and obtaining a distance data set D among the K path logistics nodes as D= { D 1 ,...,d g ,...,d K The adaptive weight output function formula is:
in formula (3), q g The importance degree of the g-th route on the logistics transportation task, d g K is a parameter for controlling the exponential decay rate for the distance between the g-th path logistics nodes;
step 5, carrying out fine control and optimization on the solving process, improving the calculation accuracy by splitting the measuring units, and distributing calculation tasks to a plurality of processors or calculation nodes in a parallel calculation mode so as to improve the calculation speed;
And 6, outputting a result, namely sorting the weights of the paths from high to low, and outputting the result.
In a specific embodiment, the improved KNN algorithm model is improved based on a conventional K-nearest neighbor algorithm. The traditional K nearest neighbor algorithm selects the class of K training samples with the closest distance to vote by calculating the distance between the sample to be classified and the training samples, and takes the class with the largest vote as the class of the sample to be classified. The improved KNN algorithm model is added with distance weight parameters on the basis of a traditional K nearest neighbor algorithm, the distance weight parameters give different weights according to the distance between samples, and the sample weight is larger when the distance is closer, and the sample weight is smaller when the distance is farther. This can more accurately reflect the similarity between samples. By introducing the distance weight parameters, the improved KNN algorithm model can calculate the similarity between samples more accurately, so that a more accurate path planning scheme is provided. The improved KNN algorithm model is further added with distance weight parameters and time window parameters based on a traditional K nearest neighbor algorithm, and a time window mechanism takes time information of training samples into consideration. When the nearest neighbor search is performed, only training samples in a time window are selected as nearest neighbor samples, and samples outside the time window are ignored. Thus, the real-time logistics transportation data change can be better adapted. By adopting an incremental calculation mode and a time window mechanism, the improved KNN algorithm model can update the logistics transportation data in real time, reflect the actual situation in time and improve the instantaneity and accuracy of path planning. Data were simulated using matlab2018a and experiments were performed using the present algorithm model and the comparative algorithm model A, B, respectively, with the effects shown in table 1.
Table 1 improved KNN algorithm model process effect statistics
As shown in table 1, data is simulated by using matlab2018a, experiments are performed by using the algorithm model and the comparison algorithm model A, B, the experimental contents are respectively the total amount of processing similar complexity data and the similar complexity data comparison processing time of 8100MB in 20min, statistics is performed on the processing accuracy of the algorithm model and the comparison algorithm model A, B, experimental results are recorded in table 1, and the total amount of processing data, the processing speed and the processing accuracy of the improved KNN algorithm model are far greater than those of the comparison algorithm model A, B, so that the improved and optimized algorithm has better application effect and practical value in the aspect of processing data clustering, the comparison algorithm model a is a traditional K nearest neighbor algorithm, and the comparison algorithm model B is an ant colony algorithm model.
In the above embodiment, the workflow of the incremental calculation mode and the time window mechanism includes:
s1, training based on an initial improved KNN algorithm model to obtain an initial path plan;
s2, setting the size of a time window as T, adding a newly added data point X into a data set D in the time window, setting the size of the newly added data point X as T, and carrying out weight calculation on the newly added data point;
S3, updating a K value by adopting an increment calculation mode to adapt to a newly added data point, wherein a calculation object of the increment calculation mode is the newly added data point X;
s4, carrying out real-time updating iteration on the improved KNN algorithm model according to the data set D in the time window, and executing S2 if the maximum iteration times, the error drop threshold or the K value variation are met, directly outputting a path planning result, and if the maximum iteration times, the error drop threshold or the K value variation are not met;
s5, outputting the final path planning scheme and the updated model parameters, and continuously adding new data points for updating iteration.
In a specific embodiment, the incremental calculation mode and the time window mechanism are two methods for carrying out real-time updating iteration on the improved KNN algorithm model, and the cluster analysis speed and the cluster analysis efficiency can be effectively improved.
When new data arrives, the incremental calculation mode needs to update the center vector to which the data belongs, rather than updating all the data again. Specifically, the distance between the new data point and each center can be calculated first, then divided into clusters closest to each other, and finally the center vector of the data is updated. The time window mechanism partitions the data set into multiple time windows, within each of which analysis is performed. In particular, the data may be classified into a number of time periods that are the most recent, and the data within each time period may be analyzed. Thus, the data volume required to be processed each time can be reduced, and the analysis speed and the analysis efficiency are improved. The two methods are combined, and the data is updated in real time in a time window in an incremental calculation mode, so that the method can be better suitable for a scene of real-time analysis of large-scale data. In each time window, only incremental calculation is needed, so that the calculated amount of reprocessing all data is avoided, and the calculation time is reduced. Meanwhile, the time window mechanism can divide the data into a plurality of time periods, so that the accuracy and the reliability of processing are improved.
In a word, the improved KNN algorithm model is updated and iterated in real time by adopting an incremental calculation mode and a time window mechanism, so that the cluster analysis speed and efficiency can be improved, the accuracy and reliability of a processing result can be ensured, and the method is suitable for analyzing and processing large-scale real-time data. The effects are as follows:
and simulating data by using matlab2018a, randomly extracting ten thousands of records to perform data cleaning and normalization, performing dimension reduction sampling on the data by using a data protocol, maintaining the related characteristics of the original data set as much as possible, reducing the data quantity to be processed, comparing the new data processing performance of the improved KNN algorithm model with that of the traditional K nearest neighbor algorithm, and setting the weight index as 2. The data samples are clustered respectively, and the clustering effect is shown in table 2:
table 2 comparison of clustering effects
Theoretical analysis and experiments show that the response speed of the new data of the improved KNN algorithm model is faster than that of the traditional K nearest neighbor algorithm, the accuracy is higher than that of the traditional K nearest neighbor algorithm, the noise of a data set is restrained by 5%, and the improved KNN algorithm model based method has the characteristics of high processing speed and good effect in a simulation experiment environment, the robustness of the algorithm is good, and the new data can be responded correctly and timely.
In the above embodiment, the path feedback correction module includes a feedback collection unit, a feedback analysis unit and a scheme correction unit, where the feedback collection unit is configured to receive feedback information output by the interface interaction module in real time, the feedback analysis unit is configured to perform instant analysis and evaluation on the collected feedback information, the scheme correction unit is configured to formulate a path correction policy according to an evaluation result of the feedback analysis unit, an output end of the feedback collection unit is connected to an input end of the feedback analysis unit, an output end of the feedback analysis unit is connected to an input end of the scheme correction unit, the feedback collection unit performs data communication with the interface interaction module through WebSocket real-time communication protocol, receives feedback information output by the interface interaction module, and the feedback analysis unit performs instant analysis and evaluation on the collected feedback information through a real-time stream processing engine, and formulates the path correction policy by embedding an adaptive decision model.
In a specific embodiment, webSocket is a full duplex communication protocol that can establish a persistent connection between a client and a server and enable real-time data transmission. Under the architecture, the interface interaction module can send feedback information of the user to the feedback collection unit through the WebSocket. The feedback collection unit receives and processes the feedback information by listening to the WebSocket connection.
Specifically, the interface interaction module can establish connection with the back-end server through the WebSocket API, and send feedback information input by the user to the server. And the feedback collection unit monitors the WebSocket connection at the server end, and performs relevant processing after receiving feedback information sent by the user. This may include parsing, storing, analyzing, or further passing to other modules for processing.
The WebSocket real-time communication protocol can ensure timely transmission and processing of feedback information, and can provide better user experience. Meanwhile, care needs to be taken to ensure the stability and safety of WebSocket connection and to reasonably handle network delay or abnormal situations possibly existing in the transmission process so as to ensure the reliability and accuracy of data.
In the above embodiment, the real-time stream processing engine obtains the importance degree of the feedback information and the satisfaction degree of the user to the path planning scheme through a machine learning algorithm, the machine learning algorithm predicts the importance degree of the feedback information and the satisfaction degree of the user to the path planning scheme through training the features of the image path planning feature and the user satisfaction degree, and the output function formula of the satisfaction degree of the user to the path planning scheme is:
In the formula (4), q represents the importance degree of the route to the logistics transportation task; e is the highest score of the user on the path planning scheme, A is the lowest score of the user on the path planning scheme, E, A is a constant between 0 and 5, and an output function formula of the importance degree of the feedback information is as follows:
in the formula (5), ω is the importance degree of the feedback information, when the satisfaction degree of the user to the path planning scheme is greater than one, the importance degree of the feedback information is the satisfaction degree of the user to the path planning scheme, when the satisfaction degree of any one user to the path planning scheme is greater than one and less than zero, a function formula is output, ζ is a decision value of the optimal path, and 0< ζ is less than or equal to 1.
In particular embodiments, the real-time stream processing engine may utilize machine learning algorithms to analyze the importance of feedback information and user satisfaction with the path planning scheme. Historical path planning data and corresponding user satisfaction data are first collected as a training set. And extracting data related to the path planning characteristics, and carrying out characteristic engineering treatment. The route planning characteristics are then processed, such as start point, end point, route selection, traffic conditions, etc. User satisfaction is processed, such as scoring or emotion analysis of user feedback. An appropriate machine learning algorithm, such as a regression model, a classification model, etc., is selected. And performing model training by using the training set, and establishing a prediction model of the path planning characteristics and the user satisfaction. And evaluating the model by using the test set, and verifying the accuracy and the performance of the model. Common evaluation metrics such as Mean Square Error (MSE), accuracy, precision, recall, etc. may be used. Predicting the importance degree and user satisfaction degree of the feedback information:
And applying a trained model in the real-time stream processing engine, and predicting the importance degree of the feedback information and the satisfaction degree of the user on the path planning scheme according to the feedback information and the path planning characteristics collected in real time. The prediction result output by the model can be utilized to provide a reference for path correction.
Through the implementation process, the real-time flow processing engine can predict the importance degree of the feedback information and the satisfaction degree of the user on the path planning scheme based on the machine learning algorithm. In this way, the user needs and the advantages and disadvantages of the evaluation path planning scheme can be better understood, so that decision support is provided for path correction.
And verifying the validity of the feedback analysis result by adopting MATLAB. To verify the result validity of the feedback analysis results, the calculation results of formulas (4) and (5) of the study were compared with the actual results, using the feedback information data samples of the four sets of interface interaction modules, and the comparison results are shown in table 3.
TABLE 3 data analysis time
The test comparison table shows that the calculation results of the formulas (4) and (5) adopted in the research are corrected, and the method has good application effect and practical value.
In the above embodiment, the adaptive decision model includes an input layer, a feature extraction layer, an adaptive adjustment layer, an adaptive weight layer, an adaptive topology layer, and an output layer, and the working method of the adaptive decision model includes the following steps:
(1) Inputting the feedback information evaluation result to the self-adaptive decision model through the input layer;
(2) The method comprises the steps of carrying out feature extraction on feedback information evaluation results through a feature extraction layer, and screening out obvious noise and interference signals, wherein the feature extraction layer comprises four network neurons so as to fully extract data features;
(3) The self-adaptive adjusting layer adjusts the learning rate of the neural network in a self-adaptive manner, and the self-adaptive adjusting layer adjusts the learning rate according to the state and performance indexes of the neural network so as to improve the convergence effect and performance of the neural network;
(4) Dynamically adjusting the weight of the neural network through the self-adaptive weight layer so as to improve the precision and generalization capability of the network;
(5) Dynamically adjusting the topological structure of the neural network through a self-adaptive topological structure layer, wherein the self-adaptive topological structure layer adopts a genetic optimization method to adaptively adjust the structure and topology of the network so as to adapt to complex tasks and data;
(6) The result is passed to the outside through the output layer.
In a specific embodiment, the adaptive decision model is embedded into a path correction strategy for dynamically adjusting the path planning scheme according to different situations. The adaptive decision model may analyze and learn based on historical data and real-time data to provide optimal path selection suggestions. Before or during each transport mission, its effectiveness and feasibility are evaluated according to the current path planning scheme. Metrics such as transit time, cost, resource utilization, etc. may be used to evaluate the merits of the current path plan. Based on the output of the adaptive decision model and the evaluation of the current path plan, it is determined whether a path correction is required. Some threshold or rule may be set to determine when a path modification should be made, such as exceeding a certain delay time, exceeding a certain cost, etc. If the path correction is judged to be needed, the self-adaptive decision model can generate a correction strategy according to the current situation. The corrective strategies may include adjusting the route of transportation, changing the transportation, reallocating resources, and the like. And carrying out corresponding correction operation on the path planning scheme according to the generated correction strategy.
In the above embodiment, the interface interaction module performs interface interaction display on the logistics transportation data and the path planning scheme by using a data visualization platform Tableau, and the data visualization platform Tableau obtains massive data source association data based on the association data model to realize multidimensional data association analysis, and adopts an interactive chart, a heat point diagram, a map and an instrument board to realize real-time monitoring of trend, relationship and change rule of the data, and the data visualization platform Tableau adopts a Token user identity verification mechanism to verify the identity of the accessing user so as to improve the security of information access.
In a specific embodiment, the interactive function provided by the data visualization platform Tableau is used for realizing the interactive display of the logistics transportation data and the path planning scheme. With the Tableau filter and the filter, a user can select desired data to be presented according to specific conditions. For example, the logistics transportation data may be filtered and filtered according to date, region, or other attributes to enable presentation and comparison of different dimensions. Tableau supports linking multiple views and dashboards, and by clicking on a data point or chart element, a linked jump between views can be achieved. The user may select a particular data point and then automatically navigate to a detailed view of the relevant information to gain insight into the details and context of the data. When a mouse hovers over a data point or chart element, the Tableau may display hints associated therewith. Thus, the user can acquire more detailed information about the data without changing the visual layout, and the understanding and analysis capability of the data are enhanced. Tableau allows a user to define parameters, and by adjusting the values of the parameters, the display results of charts and views can be updated in real time. Thus, the user can observe the data change under different conditions through the self-defined parameter values, and perform demonstration and explanation. The Tableau support creates interactive filters and operation buttons for fast switching and adjusting data display modes. The user can select a specific filter option or an operation button according to the requirement, so that dynamic switching and rearrangement of data are realized.
Through the interactive operation mode, the interface interactive module can utilize the Tableau to realize interactive display of logistics transportation data and a path planning scheme. The user can perform operations such as data screening, drilling, hovering and checking prompt information and adjusting parameter values according to requirements, so that the meaning and relation of related data can be explored, analyzed and understood more flexibly.
In the above embodiment, the cache memory module records the number of times the cache item is called through the access counter, and triggers the clearing operation by adopting the timer, where the clearing operation reorders the cache item weight according to the number of times the cache item is called and the calling time, and clears the cache item based on the LRU cache policy, so as to improve the calling speed.
In a specific embodiment, the improved KNN algorithm model can quickly respond to path planning requirements under similar conditions through the cache memory module, and the efficiency and response speed of the system are improved. The cache memory module maintains an access counter for recording the number of times each cache entry is called. Each time a request is made to access a particular cache entry, the counter will increase the number of calls to that cache entry accordingly. The cache memory module sets a timer to periodically trigger the purge operation. The frequency of the purging operation may be configured according to system requirements, such as at intervals or triggered at specific time intervals. When the clearing operation is triggered, the cache memory module calculates the weight of the cache item according to the calling times and the calling time of the cache item. Weights can be defined and adjusted according to business requirements and system performance, and common methods can use weighted averages, etc. The cache memory module sorts the cache items according to the weights of the cache items, and marks the cache items with relatively lower weights as states to be cleared. In the LRU based cache policy, the least recently used cache entry is preferentially purged, i.e., the least weighted cache entry is purged.
Through the implementation process, the cache memory module can perform weight sorting according to the calling times and the calling times of the cache items, and clear the cache items with relatively low weight based on the LRU cache policy. Therefore, the cache hit rate can be improved, the occupation of the cache space is reduced, and the calling speed of the system is increased.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (8)
1. An international logistics transportation path planning system of improved KNN algorithm model, which is characterized in that: the system comprises:
the information updating module is used for acquiring logistics transportation data in real time, wherein the logistics transportation data comprises road network data, cargo data, vehicle data and air image data, and the information updating module updates the real-time logistics transportation data through a wireless sensor network and a real-time data access interface and transmits the logistics transportation data to a message queue for further processing;
The data quality management module is used for evaluating the quality of the logistics transportation data and preprocessing the data according to an evaluation result, and the quality management module adopts a data rule engine to evaluate the accuracy, the integrity, the consistency, the timeliness and the credibility of the logistics transportation data and performs cleaning, denoising and normalization processing on the logistics transportation data according to the evaluation result so as to ensure the quality and the consistency of the data;
the path planning module is used for planning an international logistics transportation path, the path planning module performs path planning by embedding an improved KNN algorithm model, the improved KNN algorithm model provides an optimal path planning scheme according to logistics transportation data, and an incremental calculation mode and a time window mechanism are adopted for updating real-time logistics transportation data;
the interface interaction module is used for carrying out interface interaction display on the logistics transportation data and the path planning scheme;
the path feedback correction module is used for carrying out real-time information feedback and scheme correction on the path planning scheme of the path planning module according to the interface interaction information;
the cache memory module is used for caching historical logistics transportation data and a path planning scheme so that the system can quickly respond when similar conditions occur;
The output end of the information updating module is connected with the input end of the data quality management module, the output end of the data quality management module is connected with the input end of the interface interaction module, the output end of the data quality management module is connected with the input end of the path planning module, the output end of the path planning module is connected with the input end of the interface interaction module, the output end of the interface interaction module is connected with the input end of the path feedback correction module, the output end of the path planning module is connected with the input end of the cache memory module, and the output end of the path feedback correction module is connected with the input end of the cache memory module.
2. The international logistics transportation path planning system of the improved KNN algorithm model of claim 1, wherein: the working steps of the improved KNN algorithm model comprise:
step 1, inputting data, extracting features, inputting pretreated logistics transportation data into an improved KNN algorithm model, extracting cargo weight, cargo volume, starting place and destination, transportation mode characteristics, transportation cost and transportation time limiting features, regularizing the extracted features and expressing feature vectors, wherein the extracted features are divided into non-numerical features and numerical features, and expressing feature vector sets as follows:
In the formula (1), X represents a feature vector set of logistics transportation data,for the i-th non-numerical feature vector, i is 1-n, i is the ordinal number of the non-numerical feature vector of the logistics transportation data, n is the number of the non-numerical feature vector of the logistics transportation data, c represents the non-numerical feature vector, & lt/EN & gt>J is the j-th numerical characteristic vector, j is more than or equal to 1 and less than or equal to m, j is the ordinal number of the numerical characteristic vector of the logistics transportation data, m is the number of the numerical characteristic vector of the logistics transportation data, and r represents the numerical characteristic vector;
step 2, calculating the distance or similarity between samples, calculating the distance or similarity between all logistics nodes based on a feature vector set, calculating the distance or similarity between all the logistics nodes by adopting a non-numerical feature vector by adopting a Euclidean distance measurement method, calculating the distance or similarity between all the logistics nodes by adopting a numerical feature vector by adopting a cosine similarity measurement method, and outputting a function formula as follows:
in the formula (2) of the present invention,for the i-th non-numerical feature vector representing the distance from the logistics node to the master node, +.>For the ith training non-numeric feature vector, < +.>For j-th numerical eigenvector representing the distance from the logistics node to the master node, +. >A numerical feature vector for the jth training;
step 3, selecting candidate routes, namely selecting the largest l feature vectors as projection directions according to the sorting of distances or similarity between the feature vectors representing logistics nodes, wherein l is a reduced dimension, multiplying an original data sample by the selected feature vectors to sort, and selecting K paths closest to a path to be planned as candidate paths;
step 4, adaptively setting weights according to the distances, adaptively adjusting the weights according to the distance calculation results among the logistics nodes, and obtaining a distance data set D among the K path logistics nodes as D= { D 1 ,...,d g ,...,d K The adaptive weight output function formula is:
in formula (3), q g For the g-th route to logistics transportationImportance degree of task, d g K is a parameter for controlling the exponential decay rate for the distance between the g-th path logistics nodes;
step 5, carrying out fine control and optimization on the solving process, improving the calculation accuracy by splitting the measuring units, and distributing calculation tasks to a plurality of processors or calculation nodes in a parallel calculation mode so as to improve the calculation speed;
and 6, outputting a result, namely sorting the weights of the paths from high to low, and outputting the result.
3. The international logistics transportation path planning system of the improved KNN algorithm model of claim 1, wherein: the workflow of the incremental computing mode and the time window mechanism comprises the following steps:
s1, training based on an initial improved KNN algorithm model to obtain an initial path plan;
s2, setting the size of a time window as T, adding a newly added data point X into a data set D in the time window, setting the size of the newly added data point X as T, and carrying out weight calculation on the newly added data point;
s3, updating a K value by adopting an increment calculation mode to adapt to a newly added data point, wherein a calculation object of the increment calculation mode is the newly added data point X;
s4, carrying out real-time updating iteration on the improved KNN algorithm model according to the data set D in the time window, and executing S2 if the maximum iteration times, the error drop threshold or the K value variation are met, directly outputting a path planning result, and if the maximum iteration times, the error drop threshold or the K value variation are not met;
s5, outputting the final path planning scheme and the updated model parameters, and continuously adding new data points for updating iteration.
4. The international logistics transportation path planning system of the improved KNN algorithm model of claim 1, wherein: the path feedback correction module comprises a feedback collection unit, a feedback analysis unit and a scheme correction unit, wherein the feedback collection unit is used for receiving feedback information output by the interface interaction module in real time, the feedback analysis unit is used for carrying out instant analysis and evaluation on the collected feedback information, the scheme correction unit is used for formulating a path correction strategy according to an evaluation result of the feedback analysis unit, the output end of the feedback collection unit is connected with the input end of the feedback analysis unit, the output end of the feedback analysis unit is connected with the input end of the scheme correction unit, the feedback collection unit is in data communication with the interface interaction module through a WebSocket real-time communication protocol, receives feedback information output by the interface interaction module, the feedback analysis unit carries out instant analysis and evaluation on the collected feedback information through a real-time flow processing engine, and the scheme correction unit formulates the path correction strategy through an embedded self-adaptive decision model.
5. The international logistics transportation path planning system of the improved KNN algorithm model of claim 4, wherein: the real-time flow processing engine obtains the importance degree of feedback information and the satisfaction degree of a user on a path planning scheme through a machine learning algorithm, the machine learning algorithm predicts the importance degree of the feedback information and the satisfaction degree of the user on the path planning scheme through training image path planning characteristics and the characteristics of the user satisfaction degree, and an output function formula of the satisfaction degree of the user on the path planning scheme is as follows:
in the formula (8), q represents the importance degree of the route to the logistics transportation task; e is the highest score of the user on the path planning scheme, A is the lowest score of the user on the path planning scheme, E, A is a constant between 0 and 5, and an output function formula of the importance degree of the feedback information is as follows:
in the formula (9), ω is the importance degree of the feedback information, when the satisfaction degree of the user to the path planning scheme is greater than one, the importance degree of the feedback information is the satisfaction degree of the user to the path planning scheme, when the satisfaction degree of any one user to the path planning scheme is greater than one and less than zero, a function formula is output, ζ is a decision value of the optimal path, and 0< ζ is less than or equal to 1.
6. The international logistics transportation path planning system of the improved KNN algorithm model of claim 4, wherein: the self-adaptive decision model comprises an input layer, a feature extraction layer, a self-adaptive adjustment layer, a self-adaptive weight layer, a self-adaptive topological structure layer and an output layer, and the working method of the self-adaptive decision model comprises the following steps:
(1) Inputting the feedback information evaluation result to the self-adaptive decision model through the input layer;
(2) The method comprises the steps of carrying out feature extraction on feedback information evaluation results through a feature extraction layer, and screening out obvious noise and interference signals, wherein the feature extraction layer comprises four network neurons so as to fully extract data features;
(3) The self-adaptive adjusting layer adjusts the learning rate of the neural network in a self-adaptive manner, and the self-adaptive adjusting layer adjusts the learning rate according to the state and performance indexes of the neural network so as to improve the convergence effect and performance of the neural network;
(4) Dynamically adjusting the weight of the neural network through the self-adaptive weight layer so as to improve the precision and generalization capability of the network;
(5) Dynamically adjusting the topological structure of the neural network through a self-adaptive topological structure layer, wherein the self-adaptive topological structure layer adopts a genetic optimization method to adaptively adjust the structure and topology of the network so as to adapt to complex tasks and data;
(6) The result is passed to the outside through the output layer.
7. The international logistics transportation path planning system of the improved KNN algorithm model of claim 1, wherein: the interface interaction module carries out interface interaction display on logistics transportation data and a path planning scheme by adopting a data visualization platform, the data visualization platform obtains mass data source association data based on an association data model so as to realize multidimensional data association analysis, and adopts an interactive chart, a heat point diagram, a map and a dashboard to realize real-time monitoring of trends, relations and change rules of the data, and the data visualization platform adopts a Token user identity verification mechanism to verify the identity of an access user so as to improve the safety of information access.
8. The international logistics transportation path planning system of the improved KNN algorithm model of claim 1, wherein: the cache memory module records the number of times the cache item is called through an access counter, adopts a timer to trigger a clearing operation, and the clearing operation reorders the cache item weight according to the number of times the cache item is called and the calling time and clears the cache item based on the LRU cache strategy so as to improve the calling speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311206646.0A CN117350607A (en) | 2023-09-18 | 2023-09-18 | International logistics transportation path planning system of improved KNN algorithm model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311206646.0A CN117350607A (en) | 2023-09-18 | 2023-09-18 | International logistics transportation path planning system of improved KNN algorithm model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117350607A true CN117350607A (en) | 2024-01-05 |
Family
ID=89362235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311206646.0A Pending CN117350607A (en) | 2023-09-18 | 2023-09-18 | International logistics transportation path planning system of improved KNN algorithm model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117350607A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105783908A (en) * | 2014-12-25 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Navigation method, device, user terminal, server, and navigation computing device |
| CN107944605A (en) * | 2017-11-10 | 2018-04-20 | 河海大学常州校区 | A kind of dynamic traffic paths planning method based on data prediction |
| CN110533279A (en) * | 2019-07-15 | 2019-12-03 | 合肥工业大学 | For dispatching the method, system and storage medium of cloud logistics platform transport power |
| DE102019201188A1 (en) * | 2019-01-30 | 2020-07-30 | Robert Bosch Gmbh | Method for training and operating a multitasking artificial neural network, multitasking artificial neural network and device |
| CN115727861A (en) * | 2021-08-25 | 2023-03-03 | 北京顺丰同城科技有限公司 | Vehicle path planning method and device, computer equipment and storage medium |
| CN116542592A (en) * | 2023-07-03 | 2023-08-04 | 深圳市华运国际物流有限公司 | International logistics transportation path analysis and assessment system |
-
2023
- 2023-09-18 CN CN202311206646.0A patent/CN117350607A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105783908A (en) * | 2014-12-25 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Navigation method, device, user terminal, server, and navigation computing device |
| CN107944605A (en) * | 2017-11-10 | 2018-04-20 | 河海大学常州校区 | A kind of dynamic traffic paths planning method based on data prediction |
| DE102019201188A1 (en) * | 2019-01-30 | 2020-07-30 | Robert Bosch Gmbh | Method for training and operating a multitasking artificial neural network, multitasking artificial neural network and device |
| CN110533279A (en) * | 2019-07-15 | 2019-12-03 | 合肥工业大学 | For dispatching the method, system and storage medium of cloud logistics platform transport power |
| CN115727861A (en) * | 2021-08-25 | 2023-03-03 | 北京顺丰同城科技有限公司 | Vehicle path planning method and device, computer equipment and storage medium |
| CN116542592A (en) * | 2023-07-03 | 2023-08-04 | 深圳市华运国际物流有限公司 | International logistics transportation path analysis and assessment system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10360517B2 (en) | Distributed hyperparameter tuning system for machine learning | |
| CN113064879B (en) | Database parameter adjusting method and device and computer readable storage medium | |
| CN110070117B (en) | Data processing method and device | |
| JP4327481B2 (en) | Database system, server, inquiry input method and data update method | |
| US10963802B1 (en) | Distributed decision variable tuning system for machine learning | |
| CN108595267A (en) | A kind of resource regulating method and system based on deeply study | |
| Vu et al. | Distributed adaptive model rules for mining big data streams | |
| JP2023504103A (en) | MODEL UPDATE SYSTEM, MODEL UPDATE METHOD AND RELATED DEVICE | |
| WO2022053163A1 (en) | Distributed trace anomaly detection with self-attention based deep learning | |
| CN111310918B (en) | Data processing method, device, computer equipment and storage medium | |
| CN113887748B (en) | Online federal learning task allocation method and device, and federal learning method and system | |
| CN109636212B (en) | Method for predicting actual running time of job | |
| Shinde et al. | A new approach for on line recommender system in web usage mining | |
| CN108829846A (en) | A kind of business recommended platform data cluster optimization system and method based on user characteristics | |
| JP5167596B2 (en) | Data set selection device and experimental design system | |
| CN112598443A (en) | Online channel business data processing method and system based on deep learning | |
| CN117350607A (en) | International logistics transportation path planning system of improved KNN algorithm model | |
| KR20210042709A (en) | Method and server for stock movement prediction using corporate relation data | |
| Trinks | A classification of real time analytics methods. an outlook for the use within the smart factory | |
| CN114610590A (en) | Method, device and equipment for determining operation time length and storage medium | |
| Sagaama et al. | Automatic parameter tuning for big data pipelines with deep reinforcement learning | |
| CN114329231A (en) | Object feature processing method and device, electronic equipment and storage medium | |
| CN114692888A (en) | System parameter processing method, device, equipment and storage medium | |
| CN117112871B (en) | Data real-time efficient fusion processing method based on FCM clustering algorithm model | |
| CN117172721B (en) | Data flow supervision early warning method and system for financing service |
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 |