CN113379212B - Logistics information platform default risk assessment method, device, equipment and medium based on blockchain - Google Patents
Logistics information platform default risk assessment method, device, equipment and medium based on blockchain Download PDFInfo
- Publication number
- CN113379212B CN113379212B CN202110605908.5A CN202110605908A CN113379212B CN 113379212 B CN113379212 B CN 113379212B CN 202110605908 A CN202110605908 A CN 202110605908A CN 113379212 B CN113379212 B CN 113379212B
- Authority
- CN
- China
- Prior art keywords
- data
- logistics
- risk
- default
- breach
- 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.)
- Active
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013210 evaluation model Methods 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 16
- 238000003066 decision tree Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000012797 qualification Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000005295 random walk Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 101100119135 Mus musculus Esrrb gene Proteins 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000007704 transition 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a logistic information platform default risk assessment method, device, equipment and medium based on block chains, wherein the method comprises the following steps: acquiring historical order data of each logistics site stored on a blockchain platform, wherein the historical order data comprises formatted order data and non-formatted order data; extracting first class offending risk data features from the formatted order data; extracting second class of default risk data features from the non-formatted order data; acquiring historical credit characteristics, character credit characteristics and real-time service data of each logistics network point stored on a blockchain platform; constructing a default risk assessment model based on the first class default risk data features, the second class default risk data features, the historical credit features, the character credit features and the real-time business data of each logistics website; and evaluating the default risk of each logistics website through a default risk evaluation model. The invention adopts the logistics data in the block chain platform to finish the illegal risk assessment of the logistics network points, and ensures the authenticity and fairness of the assessment result.
Description
Technical Field
The invention relates to the field of logistics, in particular to a method, a device, equipment and a medium for evaluating the default risk of a logistics information platform based on blockchain.
Background
The logistics transportation is a compound service industry which comprises a plurality of links of transportation, storage, distribution, sales and the like. In recent years, with the continuous development of internet and information technology, the traditional logistics mode can not meet the market demand, various logistics enterprises generally introduce logistics information technology, collect, store, collect and analyze information generated in the logistics process, and the intelligent and automatic levels of a logistics system are continuously improved.
The logistics process involves a plurality of links, and the problems of fake production data, information leakage, quality safety and the like are unavoidable. Therefore, some large logistics enterprises try to introduce the blockchain platform to the logistics information platform, key logistics information of all logistics sites is stored in the blockchain platform in a uplink mode, and therefore non-tamperable storage of logistics data is achieved.
Because the logistics network points related to the logistics process are more, the process is complex and the types of the default risks are various, the implementation of the default risk assessment on each logistics network point is a problem to be solved in the industry. At present, the specialized evaluation institutions generally evaluate the default risk of each logistics website, and human intervention and tampering can exist in the evaluation process and the evaluation result, so that the authenticity and the effectiveness of the evaluation result are reduced.
The invention aims to provide an illegal risk assessment strategy which directly adopts the logistics data uploaded by all logistics network points stored in a blockchain platform to complete illegal risk assessment of all the logistics network points, and can ensure the authenticity and fairness of an assessment result.
Disclosure of Invention
In order to achieve the technical objective of the present invention, a first aspect of the present invention provides a method for evaluating risk of breach of a logistic information platform based on blockchain, which has the following specific technical scheme:
a blockchain-based logistic information platform breach risk assessment method, comprising:
Acquiring historical order data of each logistics site stored on a blockchain platform, wherein the historical order data comprises formatted order data and non-formatted order data;
Extracting first class default risk data features related to default from the formatted order data by adopting a random forest algorithm;
extracting second class of default risk data features related to default from the non-formatted order data by adopting a deep learning algorithm;
acquiring historical credit characteristics, character credit characteristics and real-time service data of each logistics network point stored on a blockchain platform;
constructing a default risk assessment model based on the first type of default risk data feature, the second type of default risk data feature, the historical credit feature, the character credit feature and the real-time business data of each logistics website;
and evaluating the default risk of each logistics network point through the default evaluation model.
In some embodiments, after the acquiring the historical order data of each logistics site stored on the blockchain platform, the method further includes: preprocessing the acquired historical order data, wherein the preprocessing comprises one or more of data cleaning, missing value processing, abnormal value processing and duplicate removal processing; after the estimating, by the breach risk estimating model, the breach risk of each of the logistics network points further includes: and uploading the evaluation result to the blockchain platform.
In some embodiments, the extracting a first type of breach risk data characteristic associated with a breach from the formatted order data using a random forest algorithm comprises: obtaining a sample dataset comprising a plurality of formatted order data samples; randomly extracting m training samples from the sample dataset by using Bootstraping sampling methods, and carrying out n rounds of extraction to obtain n training sets; respectively training n decision tree models based on n training sets; respectively calculating the importance values of all the characteristics of the formatted order data by using n decision tree models, and averaging the n importance values of all the characteristics to obtain unique determined importance values of all the characteristics; and selecting a plurality of characteristics with importance values exceeding a preset threshold value as the first class of default risk data characteristics.
In some embodiments, the extracting, from the non-formatted order data, a second type of breach risk data characteristic associated with a breach using a deep learning algorithm comprises: converting the non-formatted order data into a plurality of word vectors; constructing a feature matrix based on the plurality of word vectors; and extracting features of the feature matrix by adopting a convolutional neural network to obtain the second class of default risk data features.
In some embodiments, the constructing a breach risk assessment model based on the first type breach risk data characteristic, the second type breach risk data characteristic, the historical credit characteristic, the persona credit characteristic, and the real-time business data for each of the logistics sites comprises: component graph neural network g= (V, E), where V is the node set and E is the edge set; adding each logistics network point as a node to a node set, wherein the first type of default risk data characteristic, the second type of default risk data characteristic, the historical credit characteristic, the character credit characteristic and the real-time service data of each logistics network point are used as data characteristics of the corresponding node; and acquiring logistics transportation records from the blockchain platform to acquire the connection among the logistics network points, and adding the acquired connection among the logistics network points into the edge set to acquire the default risk assessment model based on the graph neural network.
In some embodiments, the estimating the risk of breach of each of the logistics network points by the breach risk estimation model comprises: selecting a Node with a default risk label as a seed Node, and executing a random walk algorithm in the default risk assessment model by adopting a Node2VEC algorithm to obtain sampling probability of each Node; and obtaining the corresponding default risk score of the logistics network point based on the sampling probability of the node.
In some embodiments, the formatted order data includes the following features: site business qualification, income situation, available storage area, site underserved pay, ticket fine, daily average business volume, arrival delivery time rate, departure standard point rate, current day signing yield, false signing complaint rate, loss breakage rate, upgrade complaint acceptance complaint rate, timely collecting yield, total complaint rate, secondary complaint rate, full channel disposable resolution, good signing rate and good collecting rate; the non-formatted order data includes item description information, customer rating information, customer complaint information.
In some embodiments, the historical credit characteristics include one or more of financial status, complaint records, offence records, litigation-related records, administrative penalty records; the character credit features comprise one or more of operating conditions, asset conditions, warehouse areas, transport vehicles, personnel numbers and informatization levels; the real-time service data comprises one or more of line achievement rate, timely package rate, service qualification rate, abnormal problem solving rate, information time rate, information integrity rate and information accuracy rate.
The second aspect of the present invention provides a logistic information platform breach risk assessment device based on blockchain, which is characterized in that the device comprises:
The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical order data of each logistics website stored on a blockchain platform, and the historical order data comprises formatted order data and non-formatted order data;
the first feature extraction module is used for extracting first type of default risk data features related to default from the formatted order data by adopting a random forest algorithm;
The second feature extraction module is used for extracting second class of default risk data features related to default from the non-formatted order data by adopting a deep learning algorithm;
The second acquisition module is used for acquiring historical credit characteristics, character credit characteristics and real-time service data of each logistics network point stored on the blockchain platform;
the breach risk assessment model construction module is used for constructing a breach risk assessment model based on the first breach risk data characteristics, the second breach risk data characteristics, the historical credit characteristics, the character credit characteristics and the real-time service data of each logistics website;
and the breach risk assessment module is used for assessing breach risks of the logistics network points through the breach risk assessment model.
A third aspect of the present invention provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing any one of the above blockchain-based logistics information platform breach risk assessment methods when executing the program.
A fourth aspect of the present invention provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the program is executed by a processor, the program implements the method for evaluating risk of violating a constraint on a blockchain-based logistics information platform according to any of the above aspects.
Compared with the default risk assessment method in the prior art, the method for assessing the default risk of the logistics information platform directly adopts the logistics data uploaded by each logistics website stored in the blockchain platform to complete the default risk assessment of each logistics website, and can ensure the authenticity and fairness of the assessment result.
In addition, the logistics data used in the method comprises historical order data of logistics network points, and data of multiple dimensions such as historical credit characteristics, character credit characteristics, real-time service data and the like of each logistics network point, so that the richness of the data is greatly improved, and finally the accuracy of the illegal risk assessment result is greatly improved.
Drawings
FIG. 1 is a flowchart of a method for evaluating risk of breach of a logistics information platform based on blockchain according to an embodiment of the present invention;
FIG. 2 is a flowchart for obtaining first class breach risk data characteristics in a breach risk assessment method based on a blockchain-based logistics information platform according to an embodiment of the present invention;
FIG. 3 is a flowchart of acquiring second class of default risk data features in the method for evaluating the default risk of the blockchain-based logistics information platform according to the embodiment of the present invention;
FIG. 4 is a flowchart of a method for constructing a breach risk assessment model in a breach risk assessment method based on a blockchain-based logistics information platform according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a block chain-based logistic information platform breach risk assessment device according to an embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Because the logistics network points related to the logistics process are more, the process is complex and the types of the default risks are various, the implementation of the default risk assessment on each logistics network point is a problem to be solved in the industry. At present, the specialized evaluation institutions generally evaluate the default risk of each logistics website, and human intervention and tampering can exist in the evaluation process and the evaluation result, so that the authenticity and the effectiveness of the evaluation result are reduced.
The application provides a method, a device, equipment and a medium for evaluating the risk of violating the contract of a logistics information platform based on a blockchain, which aim to solve the technical problems in the prior art.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Example 1
The embodiment of the application provides a logistic information platform default risk assessment method based on a block chain, which comprises the following steps as shown in fig. 1:
Step S101, acquiring historical order data of each logistics site stored on a blockchain platform, wherein the historical order data comprises formatted order data and non-formatted order data.
As shown in the background section, after the blockchain platform is introduced into the logistics information platform, each logistics network point is added into the blockchain platform as a node. Each logistics network point stores order data generated in the logistics process to the blockchain platform in a uplink manner. In addition, historical credit features, character credit features, and some key real-time business data for each stream website are also stored up onto the blockchain platform.
The historical order data includes formatted order data and non-formatted order data in the original storage format of the data. By formatted order data is meant data comprising a plurality of characteristic values (attributes) which can be saved into a two-dimensional table or relational database, and by non-formatted order data is meant data which is maintained in a text format.
Optionally, in the embodiment of the present invention, the format order data includes the following features:
The basic data features comprise order numbers, dispatch network points, dispatch personnel information, collecting network points, express mail information, dispatch information and the like.
The business data features comprise site business qualification, income situation, available storage area, site payoff, ticket penalty, daily average business volume, arrival time rate, current day yield, false sign-up complaint rate, loss breakage rate, upgrade complaint acceptance complaint rate, timely solicitation rate, total complaint rate, secondary complaint rate, disposable resolution of all channels, good signing rate, good collecting rate and the like.
The website history violating records can be used as corresponding violating risk labels for formatting order data. As will be familiar to those of ordinary skill in the art, there is a correlation between business data characteristics and the risk of violations at a logistics site.
Optionally, in the embodiment of the present invention, the related non-formatted order data includes text data such as goods description information, customer evaluation information, customer complaint information, and the like.
Optionally, after the acquisition of the historical order data is performed, preprocessing is further included, where the preprocessing includes one or more of data cleaning, missing value processing, outlier processing, and duplicate removal processing.
And step S102, extracting first type of default risk data characteristics related to default from the formatted order data by adopting a random forest algorithm.
As previously indicated, the formatted order data includes a number of business data features, not every feature has a large correlation with the risk of default, as will be appreciated by those of ordinary skill in the art, and therefore it is necessary to choose a suitable number of features from these that have a higher correlation with the risk of default. The selected features are the first class of breach risk data features.
Optionally, as shown in fig. 2, step S102 specifically includes the following sub-steps:
S1021, a sample data set comprising a plurality of formatted order data samples is acquired.
S1022, randomly extracting m training samples from the sample dataset by using Bootstraping sampling method, and carrying out n rounds of extraction to obtain n training sets.
As in some alternative embodiments, the sample data set has a sample size of 900 for a total of 10 rounds (n=10) of snap-back extraction. Each round of extraction is specifically as follows:
600 (m=600) training samples were extracted from the sample dataset as the training set formed by the present round of extraction, and the remaining 300 sample data that were not extracted were recorded as the out-of-bag dataset formed by the present round of extraction.
After completing 10 rounds of extraction, 10 training sets were obtained in total, corresponding to 10 out-of-bag data sets.
S1023, training n decision tree models based on n training sets.
Continuing to train the decision tree model by using the above embodiment, respectively using 10 training sets, 10 trained decision tree models can be obtained, and the 10 decision tree models form the random forest model of the present invention.
S1024, calculating the importance value of each feature of the formatted order data by using n decision tree models, and averaging the n importance values of each feature to obtain a unique determined importance value of each feature.
The importance values of the features of the formatted order data are calculated separately using n (e.g., 10 in the above embodiment) decision tree models. Specific:
Each decision tree model selects the corresponding out-of-bag data set to calculate the out-of-bag data error, namely, the out-of-bag data set is used for calculating the prediction error rate of the corresponding decision tree model, the result is denoted as err1, then, noise influence is added to the characteristic x of the sample data in the out-of-bag data set, such as randomly changing the value of the characteristic x, and the out-of-bag data error is calculated again and denoted as err2. The importance value of feature x calculated by the decision tree model may be characterized as err2-err1.
It can be seen that for each feature x, n importance values are calculated for the n decision tree models, and thus the final determined importance value for each feature x is determined by averaging. The determined importance value is:
∑(err2-err1)/n；
after the above processing, the determined importance values of all the features are calculated.
S1025, selecting a plurality of characteristics with importance values exceeding a preset threshold value as first class of default risk data characteristics.
Optionally, all features are sorted in descending order according to the magnitude of the determined importance value, and the features ranked in front are selected as the first class of offending risk data features.
For example, still with the above embodiment, the top 17 features are selected as the first type of breach risk data features. Optionally, 17 features are classified into three major categories according to their specific meaning, specifically:
Site management conditions: including the business qualification, income situation, available warehouse area, site underserved, daily average traffic of the allied sites.
Network operation condition: including the time rate of the departure traffic, the departure standard point rate, the current date yield, the loss and breakage rate and the timely collection yield.
Network point service condition: false signing complaint rate, upgrade complaint acceptance complaint rate, total complaint rate, secondary complaint rate, full channel one-time resolution, good signing rate and good collection rate.
By machine learning the formatted order data, the business data features with high correlation degree with the default risk, namely the first type of default risk data features, are extracted.
And S103, extracting second class of default risk data features related to default from the non-formatted order data by adopting a deep learning algorithm.
As described above, the non-formatted order data is text data from which hidden breach risk data characteristics associated with breach are mined by a deep learning algorithm.
Optionally, as shown in fig. 3, the present invention employs a Convolutional Neural Network (CNN) to perform the extraction of the second type of breach risk data features. Specifically, step S103 includes the following sub-steps:
s1031, converting the non-formatted order data into a plurality of word vectors.
Alternatively, word vector conversion may be performed on the non-formatted order data by using Word vector algorithms such as Word2Vec and Glo Ve, so as to obtain a plurality of Word vectors, where each Word vector corresponds to a keyword in the non-formatted order data. That is, the non-formatted order data is characterized as a number of word vectors.
S1032, constructing a feature matrix based on the word vectors.
I.e. all word vectors are stored into a matrix, each word vector corresponding to a column of the feature matrix.
S1033, performing feature extraction on the feature matrix by adopting a convolutional neural network to obtain second class of default risk data features.
The hidden feature extraction using convolutional neural networks is a conventional technique in the art, and in general, the convolutional neural network is composed of a convolutional layer, a pooling layer, a ReLU layer, and a full connection layer, where:
Convolution layer: the method comprises two key operations, namely local association and window sliding, wherein a convolution layer multiplies different local matrixes of a word vector matrix and each position element of a convolution kernel matrix, and then the position elements are added to finish convolution operation to obtain a new feature matrix.
Pooling layer: each sub-matrix of the input tensor is compressed to obtain a value, so that the dimension of the input matrix is reduced, and the average value of the corresponding area is used as the element value after pooling.
Relu layers: the correction linear unit corrects the output to be negative, the output is corrected to be 0, and the output is unchanged when the output is positive.
Full tie layer: and splicing the feature matrixes calculated by the convolution layer and the pooling layer into one dimension.
Still further, in the foregoing embodiment, after feature extraction, the finally obtained second class of default risk data features includes: express item security, false signature yield, human deliberate actions, fake business condition data, and other default features.
To this end, by deep mining of the non-formatted order data, the feature of the breach associated with the breach, the so-called second type breach risk data feature, is extracted.
Step S104, the historical credit characteristics, the character credit characteristics and the real-time service data of each logistics network point stored on the blockchain platform are obtained.
Optionally, the historical credit characteristics include one or more of financial status, complaint records, offence records, litigation-related records, administrative penalty records.
Character credit features include one or more of business conditions, asset conditions, warehouse areas, transportation vehicles, number of people, level of informatization.
The real-time business data comprises one or more of line achievement rate, timely package rate, service qualification rate, abnormal problem solving rate, information time rate, information integrity rate and information accuracy rate.
And step 105, constructing a default risk assessment model based on the first class default risk data features, the second class default risk data features, the historical credit features, the character credit features and the real-time business data of each logistics website.
Optionally, as shown in fig. 4, the specific process of step S105 includes the following sub-steps:
s1051, component graph neural network g= (V, E), where V is a node set and E is an edge set.
S1052, each logistics network point is used as a node to be added into a node set, and the first type of default risk data characteristic, the second type of default risk data characteristic, the historical credit characteristic, the character credit characteristic and the real-time service data of each logistics network point are used as the data characteristics of the corresponding node.
S1053, acquiring logistics transportation records from the blockchain platform to acquire the connection among all logistics network points, and adding the acquired connection among all logistics network points into the edge set to acquire the breach risk assessment model based on the graph neural network.
Specific: and acquiring data of order numbers, collecting net points, an originating center, a transfer center, a destination center, a dispatching net point and the like in the logistics transportation process from the blockchain platform, and determining whether the links among all the logistics net points in the logistics transportation process of one order are generated according to the order numbers.
And S106, carrying out default risk assessment on the default risk of the logistics network point through a default risk assessment model.
Optionally, using a Node with a breach risk tag (i.e. a Node with a history breach record) as a seed Node, and using an existing Node2VEC model to perform random walk so as to obtain a breach risk score of each logistics Node. The specific wander strategy is as follows: for the current node t, the sampling node x selected in the next step calculates the transition probability by the following formula:
Wherein: p is the return probability, if p > max (q, 1), then the sample will not go back as much as possible, i.e. the next node is unlikely to be the last node t. q is an in-out parameter, and if q >1, the wander will tend to run between nodes around the starting point, reflecting the Breadth First Search (BFS) characteristics of one node. If q <1, then the walk will tend to go far, reflecting the Depth First Search (DFS) characteristics.
In one embodiment, taking p=1 and q=2, continuously simulating a random walk path according to the random walk rule until the sampling probability of each node in the whole graph neural network is stabilized, stopping simulation, and the sampling probability of each node can be characterized as the default risk of the corresponding logistics network point.
The training process of the model is that when the model is formally used for carrying out the default risk assessment, the default risk of the sample to be queried is input into the graph neural network through the sample data to be queried, and the stable sampling probability value on the corresponding node generated in the graph neural network is the default risk of the sample to be queried.
Because the direct output of the graph neural network is less than 1 decimal, the user can understand the rule breaking risk of the logistics network more conveniently. Optionally, we multiply the sampling probability value of each node by one hundred to be used as the breach risk score of the logistics website corresponding to the node.
Optionally, the obtained breach risk scores of the logistics network points are uploaded to a blockchain platform, so that the logistics participants can share the breach risk scores conveniently.
Compared with the default risk assessment method in the prior art, the method for assessing the default risk of the logistics information platform directly adopts the logistics data uploaded by each logistics website stored in the blockchain platform to complete the default risk assessment of each logistics website, and can ensure the authenticity and fairness of the assessment result.
In addition, the logistics data used in the method comprises historical order data of logistics network points, and data of multiple dimensions such as historical credit characteristics, character credit characteristics, real-time service data and the like of each logistics network point, so that the richness of the data is greatly improved, and finally the accuracy of the illegal risk assessment result is greatly improved.
Example two
Fig. 5 shows a schematic structural diagram of a block chain-based logistic information platform breach risk assessment device according to an embodiment of the present application.
The logistic information platform default risk assessment device comprises:
201. the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical order data of each logistics website stored on a blockchain platform, and the historical order data comprises formatted order data and non-formatted order data;
202. The first feature extraction module is used for extracting first type of default risk data features related to default from the formatted order data by adopting a random forest algorithm;
203. the second feature extraction module is used for extracting second class of default risk data features related to default from the non-formatted order data by adopting a deep learning algorithm;
204. The second acquisition module is used for acquiring historical credit characteristics, character credit characteristics and real-time service data of each logistics network point stored on the blockchain platform;
205. The system comprises a breach risk assessment model construction module, a breach risk assessment model generation module and a breach risk assessment module, wherein the breach risk assessment model construction module is used for constructing a breach risk assessment model based on first-class breach risk data characteristics, second-class breach risk data characteristics, historical credit characteristics, character credit characteristics and real-time business data of each logistics website;
206. and the breach risk assessment module is used for assessing breach risk of the logistics network point through the breach risk assessment model.
Since the detailed processing procedure of each functional module of the device for evaluating risk of violating the contract of the logistic information platform in this embodiment is identical to the processing procedure of the method for evaluating risk of violating the contract of the logistic information platform in the first embodiment, the processing procedure of each functional module of this embodiment is not repeated, and reference may be made to the related description in the first embodiment. Of course, each functional module may also include several sub-modules, and the processing procedure of these sub-modules is described with reference to the related description in the first embodiment.
Example III
Fig. 6 is a schematic structural diagram of an electronic device 300 according to an embodiment of the present application, as shown in fig. 6, the electronic device 300 includes a processor 301 and a memory 303, where the processor 301 and the memory 303 are connected, for example, through a bus 302.
The processor 301 may be a CPU, general-purpose processor, DSP, ASIC, FPGA or other programmable device, transistor logic device, hardware components, or any other combination. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 301 may also be a combination that implements computing functionality, including, for example, one or more microprocessor combinations, a combination of a DSP and a microprocessor, and the like.
Bus 302 may include a path that communicates information between the components. Bus 302 may be a PCI bus or an EISA bus, etc. Bus 302 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but do not represent only one bus or one type of bus.
The memory 303 may be, but is not limited to, a ROM or other type of static storage device, a RAM or other type of dynamic storage device, which may store static information and instructions, an EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 303 is used for storing application program codes of the present application and is controlled to be executed by the processor 301. The processor 301 is configured to execute the application code stored in the memory 303 to implement the blockchain-based logistics information platform breach risk assessment method in the first embodiment.
The embodiment of the application finally provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the program is executed by a processor, the method for evaluating the risk of violating the constraint of the logistics information platform based on the blockchain in any of the first embodiment and the second embodiment is realized.
The invention has been described above in sufficient detail with a certain degree of particularity. It will be appreciated by those of ordinary skill in the art that the descriptions of the embodiments are merely exemplary and that all changes that come within the true spirit and scope of the invention are desired to be protected. The scope of the invention is indicated by the appended claims rather than by the foregoing description of the embodiments.
Claims (8)
1. The block chain-based logistics information platform default risk assessment method is characterized by comprising the following steps of:
Acquiring historical order data of each logistics site stored on a blockchain platform, wherein the historical order data comprises formatted order data and non-formatted order data;
Extracting first class default risk data features related to default from the formatted order data by adopting a random forest algorithm;
extracting second class of default risk data features related to default from the non-formatted order data by adopting a deep learning algorithm;
acquiring historical credit characteristics, character credit characteristics and real-time service data of each logistics network point stored on a blockchain platform;
constructing a default risk assessment model based on the first type of default risk data feature, the second type of default risk data feature, the historical credit feature, the character credit feature and the real-time business data of each logistics website;
evaluating the default risk of the logistics network point through the default evaluation model;
the constructing a breach risk assessment model based on the first type breach risk data characteristic, the second type breach risk data characteristic, the historical credit characteristic, the persona credit characteristic and the real-time business data of each of the logistics network points comprises:
constructing a graph neural network g= (V, E), wherein V is a node set and E is an edge set;
adding each logistics network point as a node to a node set, wherein the first type of default risk data characteristic, the second type of default risk data characteristic, the historical credit characteristic, the character credit characteristic and the real-time service data of each logistics network point are used as data characteristics of the corresponding node;
acquiring logistics transportation records from the blockchain platform to acquire the connection among the logistics network points, and adding the acquired connection among the logistics network points into the edge set to acquire the default risk assessment model based on a graph neural network;
The estimating the default risk of the logistics network point through the default risk estimation model comprises the following steps:
selecting a Node with a default risk label as a seed Node, and executing a random walk algorithm in the default risk assessment model by adopting a Node2VEC algorithm to obtain sampling probability of each Node;
Obtaining a corresponding risk score of the logistics network point based on the sampling probability of the node;
The formatted order data includes the following features: site business qualification, income situation, available storage area, site underfilling, ticket fine, daily average business volume, arrival delivery time rate, departure standard point rate, current day signing yield, false signing complaint rate, loss breakage rate, upgrade complaint acceptance complaint rate, timely collecting yield, total complaint rate, secondary complaint rate, full channel disposable resolution, signing good rate and collecting good rate;
the non-formatted order data includes item description information, customer rating information, and customer complaint information.
2. The method for evaluating the risk of breach of a physical distribution information platform according to claim 1, further comprising, after said obtaining the historical order data of each physical distribution network point stored on the blockchain platform:
Preprocessing the acquired historical order data, wherein the preprocessing comprises one or more of data cleaning, missing value processing, abnormal value processing and duplicate removal processing;
And after the default risk of each logistics network point is evaluated through the default risk evaluation model, uploading an evaluation result to the blockchain platform.
3. The blockchain-based logistics information platform breach risk assessment method of claim 1, wherein said extracting a first type of breach risk data characteristic associated with a breach from said formatted order data using a random forest algorithm comprises:
obtaining a sample dataset comprising a plurality of formatted order data samples;
Randomly extracting m training samples from the sample dataset by using Bootstraping sampling methods, and carrying out n rounds of extraction to obtain n training sets; respectively training n decision tree models based on n training sets;
Respectively calculating the importance values of all the characteristics of the formatted order data by using n decision tree models, and averaging the n importance values of all the characteristics to obtain unique determined importance values of all the characteristics;
and selecting a plurality of characteristics with importance values exceeding a preset threshold value as the first class of default risk data characteristics.
4. The blockchain-based logistics information platform breach risk assessment method of claim 1, wherein said extracting a second type of breach risk data characteristic associated with a breach from said non-formatted order data using a deep learning algorithm comprises:
Converting the non-formatted order data into a plurality of word vectors;
Constructing a feature matrix based on the plurality of word vectors;
and extracting features of the feature matrix by adopting a convolutional neural network to obtain the second class of default risk data features.
5. The blockchain-based logistics information platform default risk assessment method of claim 1, wherein:
the historical credit characteristics comprise one or more of financial conditions, complaint records, violation records, litigation records and administrative punishment records;
The character credit features comprise one or more of operating conditions, asset conditions, warehouse areas, transport vehicles, personnel numbers and informatization levels;
the real-time service data comprises one or more of line achievement rate, timely package rate, service qualification rate, abnormal problem solving rate, information time rate, information integrity rate and information accuracy rate.
6. The utility model provides a commodity circulation information platform violating the regulations risk assessment device based on blockchain which characterized in that it includes:
The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical order data of each logistics website stored on a blockchain platform, and the historical order data comprises formatted order data and non-formatted order data;
the first feature extraction module is used for extracting first type of default risk data features related to default from the formatted order data by adopting a random forest algorithm;
The second feature extraction module is used for extracting second class of default risk data features related to default from the non-formatted order data by adopting a deep learning algorithm;
The second acquisition module is used for acquiring historical credit characteristics, character credit characteristics and real-time service data of each logistics network point stored on the blockchain platform;
the breach risk assessment model construction module is used for constructing a breach risk assessment model based on the first breach risk data characteristics, the second breach risk data characteristics, the historical credit characteristics, the character credit characteristics and the real-time service data of each logistics website;
the breach risk assessment module is used for assessing breach risks of the logistics network points through the breach risk assessment model;
the constructing a breach risk assessment model based on the first type breach risk data characteristic, the second type breach risk data characteristic, the historical credit characteristic, the persona credit characteristic and the real-time business data of each of the logistics network points comprises:
constructing a graph neural network g= (V, E), wherein V is a node set and E is an edge set;
adding each logistics network point as a node to a node set, wherein the first type of default risk data characteristic, the second type of default risk data characteristic, the historical credit characteristic, the character credit characteristic and the real-time service data of each logistics network point are used as data characteristics of the corresponding node;
acquiring logistics transportation records from the blockchain platform to acquire the connection among the logistics network points, and adding the acquired connection among the logistics network points into the edge set to acquire the default risk assessment model based on a graph neural network;
The estimating the default risk of the logistics network point through the default risk estimation model comprises the following steps:
selecting a Node with a default risk label as a seed Node, and executing a random walk algorithm in the default risk assessment model by adopting a Node2VEC algorithm to obtain sampling probability of each Node;
and obtaining a corresponding risk score of the logistics network point based on the sampling probability of the node.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the blockchain-based logistics information platform breach risk assessment method of any one of claims 1 to 5 when the program is executed by the processor.
8. A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the blockchain-based logistics information platform breach risk assessment method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110605908.5A CN113379212B (en) | 2021-05-31 | 2021-05-31 | Logistics information platform default risk assessment method, device, equipment and medium based on blockchain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110605908.5A CN113379212B (en) | 2021-05-31 | 2021-05-31 | Logistics information platform default risk assessment method, device, equipment and medium based on blockchain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113379212A CN113379212A (en) | 2021-09-10 |
| CN113379212B true CN113379212B (en) | 2024-07-26 |
Family
ID=77575229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110605908.5A Active CN113379212B (en) | 2021-05-31 | 2021-05-31 | Logistics information platform default risk assessment method, device, equipment and medium based on blockchain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379212B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118095803B (en) * | 2024-04-26 | 2024-06-25 | 江苏零浩网络科技有限公司 | Logistics resource integration and scheduling platform and method based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287180A (en) * | 2019-06-25 | 2019-09-27 | 上海诚数信息科技有限公司 | A kind of air control modeling method based on deep learning |
| CN110472040A (en) * | 2019-06-26 | 2019-11-19 | 平安科技（深圳）有限公司 | Extracting method and device, storage medium, the computer equipment of evaluation information |
| CN110599098A (en) * | 2019-09-17 | 2019-12-20 | 上海天地汇供应链科技有限公司 | Logistics industry-based block chain credit investigation management method and system |
| CN112184012A (en) * | 2020-09-27 | 2021-01-05 | 平安资产管理有限责任公司 | Enterprise risk early warning method, device, equipment and readable storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063931A (en) * | 2018-09-06 | 2018-12-21 | 盈盈（杭州）网络技术有限公司 | A kind of model method for predicting freight logistics driver Default Probability |
| CN109670974A (en) * | 2018-12-14 | 2019-04-23 | 中国平安人寿保险股份有限公司 | A kind of risk monitoring and control method and device, electric terminal |
-
2021
- 2021-05-31 CN CN202110605908.5A patent/CN113379212B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287180A (en) * | 2019-06-25 | 2019-09-27 | 上海诚数信息科技有限公司 | A kind of air control modeling method based on deep learning |
| CN110472040A (en) * | 2019-06-26 | 2019-11-19 | 平安科技（深圳）有限公司 | Extracting method and device, storage medium, the computer equipment of evaluation information |
| CN110599098A (en) * | 2019-09-17 | 2019-12-20 | 上海天地汇供应链科技有限公司 | Logistics industry-based block chain credit investigation management method and system |
| CN112184012A (en) * | 2020-09-27 | 2021-01-05 | 平安资产管理有限责任公司 | Enterprise risk early warning method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379212A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110400215B (en) | Method and system for constructing enterprise family-oriented small micro enterprise credit assessment model | |
| CN110516910A (en) | Declaration form core based on big data protects model training method and core protects methods of risk assessment | |
| CN102012918B (en) | System and method for excavating and executing rule | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| CN106408184A (en) | User credit evaluation model based on multi-source heterogeneous data | |
| US20160012544A1 (en) | Insurance claim validation and anomaly detection based on modus operandi analysis | |
| CN110287292B (en) | Judgment criminal measuring deviation degree prediction method and device | |
| CN113139876B (en) | Risk model training method, risk model training device, computer equipment and readable storage medium | |
| CN111581193A (en) | Data processing method, device, computer system and storage medium | |
| Xi et al. | A hybrid algorithm of traffic accident data mining on cause analysis | |
| CN112100398A (en) | Patent blank prediction method and system | |
| CN115204886A (en) | Account identification method and device, electronic equipment and storage medium | |
| CN112990583A (en) | Method and equipment for determining mold entering characteristics of data prediction model | |
| CN114118816B (en) | Risk assessment method, apparatus, device and computer storage medium | |
| CN113379212B (en) | Logistics information platform default risk assessment method, device, equipment and medium based on blockchain | |
| CN113487109B (en) | Group identification method, group identification device, electronic equipment and storage medium | |
| CN112990989B (en) | Value prediction model input data generation method, device, equipment and medium | |
| CN113379211B (en) | Logistics information platform default risk management and control system and method based on blockchain | |
| CN111784360B (en) | Anti-fraud prediction method and system based on network link backtracking | |
| CN117131460A (en) | Telecom fraud account identification model training method, device, equipment and medium | |
| CN115689713A (en) | Abnormal risk data processing method and device, computer equipment and storage medium | |
| CN116976712A (en) | Root cause determination method, device, equipment and storage medium for abnormality index | |
| CN113849580A (en) | Subject rating prediction method and device, electronic equipment and storage medium | |
| Ozdemir et al. | Estimating shopping center visitor numbers based on a new hybrid fuzzy prediction method | |
| CN118260347B (en) | Data acquisition and analysis method and system based on artificial intelligence |
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 |