CN111753928A - Customs inspection rule generation method based on knowledge graph and tree model construction - Google Patents
Customs inspection rule generation method based on knowledge graph and tree model construction Download PDFInfo
- Publication number
- CN111753928A CN111753928A CN202010741825.4A CN202010741825A CN111753928A CN 111753928 A CN111753928 A CN 111753928A CN 202010741825 A CN202010741825 A CN 202010741825A CN 111753928 A CN111753928 A CN 111753928A
- Authority
- CN
- China
- Prior art keywords
- customs
- declaration form
- parameters
- customs declaration
- tree model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a customs detection rule generation method based on knowledge graph and tree model construction, which extracts a plurality of effective index features from a customs detection traditional expert rule engine, captures feature information by two parts, wherein the first part performs feature information extraction based on a plurality of CART decision trees to construct a random forest, the other part performs learning of the CART decision tree model by applying the learned correlation relationship based on the correlation relationship between knowledge graph learning declaration form data, thus, the knowledge graph and the random forest can be automatically learned to effective features by knowledge generation of the knowledge graph and information extraction of the CART decision tree model, and the obtained new rule engine is more intelligent and efficient, thereby remarkably improving customs distribution control performance and improving the investigation rate.
Description
Technical Field
The invention relates to the technical field of customs inspection, in particular to a customs inspection rule generation method based on knowledge graph and tree model construction.
Background
With the development of economy, people have more demands on transnational articles, and the import and export trade volume in the transnational field is remarkably increased, which brings great pressure for customs departments to detect the import and export articles. The international trade list has more than 400 kinds, and the traditional expert rule engine cannot simultaneously meet the rigid indexes of customs such as improvement of control efficiency, acquisition rate and the like.
In the traditional customs goods detection method, the most widely applied method is an expert rule engine. The expert rule engine effectively utilizes relevant knowledge in the expert field to construct a rule system for article detection. The expert system has few rules, hundreds of rules and more rules, but the common rules only account for a few of the overall rules, that is, the expert system only applies a small part of all the information of the article, and many other related information is not utilized. The unused information often has correlation with the result of article detection, which is difficult to find.
At present, some detection methods based on automatic rule generation of a tree model exist, however, the decision process of a decision tree often has the problem of single standard, the method is separated from the original expert rule system, although all related information of an article can be utilized, the knowledge of the expert rule system is lost, and the knowledge waste of the expert information can be caused.
Disclosure of Invention
In view of this, the invention provides a customs inspection rule generation method based on knowledge graph and tree model construction, which is used for improving customs deployment and control efficiency and increasing acquisition rate.
The invention provides a customs detection rule generation method based on knowledge graph and tree model construction, which comprises the following steps:
s1: extracting a customs declaration form of a historical detection article from a customs detection database, and performing data cleaning on the customs declaration form;
s2: taking the most common rule in the customs inspection expert system as a preliminary rule;
s3: performing characteristic engineering processing on the customs clearance sheet after data cleaning, analyzing customs clearance sheet parameters contained in the customs clearance sheet after the characteristic engineering processing, and extracting nonzero-value parameters from the customs clearance sheet parameters;
s4: extracting sample data from the extracted nonzero-value parameters by adopting a put-back sampling mode, primarily screening the extracted sample data by using the primary rule, and training a CART decision tree model by using the primarily screened sample data to obtain a trained CART decision tree model;
s5: returning to step S4, step S4 is repeatedly executed; after repeating for many times, performing weighted fusion on the trained CART decision tree models in a superposition mode to obtain a random forest;
s6: establishing a customs declaration form containing relationship based on the relevant knowledge in the customs inspection expert field, wherein the customs declaration form containing relationship comprises a customs declaration form type containing relationship and a customs declaration form parameter containing relationship;
s7: respectively regarding each customs declaration and each customs declaration parameter as a graph node;
s8: judging whether inclusion relations exist among the customs clearance reports, among the customs clearance report parameters and between the customs clearance reports and the customs clearance report parameters; if yes, establishing an edge between the two nodes with the inclusion relationship, wherein the edge points to the included person from the included person, and the weight value of the edge is the probability value from the included person to the included person; if not, establishing no communication relation between the two nodes without the inclusion relation; traversing all customs declaration forms and all customs declaration form parameters to obtain a knowledge graph directed probability graph model;
s9: setting the customs declaration form and the customs declaration form parameters after the preliminary rule screening as initial nodes n1,n2…..nkSetting the customs declaration form and customs declaration form parameters of the target object as a final node m1,m2,….mlCalculating the maximum probability value max P (m) of the knowledge-graph directed probability graph model1,m2,….ml|n1,n2…..nk);
S10: and performing weighted fusion on the maximum probability value of the knowledge map directed probability map model and the maximum probability value output by the random forest to generate a final customs detection rule.
In a possible implementation manner, in the customs inspection rule generating method provided by the present invention, in step S3, if the nonzero-value parameter is time information, then step S3 performs feature engineering on the data-cleaned customs clearance report, analyzes the customs clearance parameter included in the feature-engineered customs clearance report, and extracts the nonzero-value parameter therefrom, which specifically includes the following steps:
s31: analyzing the time stamp in the customs clearance after data cleaning, extracting the date from the time stamp, and judging whether the date is the p th day of each week, the q th day of each month or a holiday or not; p ═ 1,2, …, 7; q is 1,2, …, 31;
s32: marking different levels of the holidays, and respectively representing the legal holidays, the long holidays and the short holidays by different numbers;
s33: judging whether the number of days from the next holiday is greater than a threshold value alpha or not; if yes, the distance is far from the legal festival and holiday; if not, the distance is considered to be close to the legal holiday;
s34: the threshold value alpha is adjusted.
In a possible implementation manner, in the customs detection rule generating method provided by the present invention, in step S4, sample data is extracted from the extracted nonzero-value parameter by using a pull-back sampling manner, the extracted sample data is preliminarily screened by using the preliminary rule, and a CART decision tree model is trained by using the preliminarily screened sample data, so as to obtain a trained CART decision tree model, which specifically includes the following steps:
s41: disordering the customs declaration form, randomly extracting a part of data from the customs declaration form to be used as sample data, and learning the extracted sample data by using a CART decision tree model as a base classifier;
s42: and returning the learned sample data to the original data.
According to the customs detection rule generation method based on the knowledge graph and tree model construction, provided by the invention, a plurality of effective index features are extracted from a customs detection traditional expert rule engine, feature information is captured by two parts, the first part is used for extracting the feature information based on a plurality of CART decision trees to construct a random forest, the other part is used for learning the correlation relationship between customs declaration list data based on the knowledge graph, and the learned correlation relationship is used for learning the CART decision tree model. The invention fully utilizes the mutual relation among customs clearance reports, explores the relation information among data from different angles by learning the customs clearance report parameters and establishing the relation of the knowledge map, and ensures that a newly learned rule system is more complete and has higher accuracy.
Drawings
FIG. 1 is a schematic flow chart of a customs inspection rule generation method based on knowledge graph and tree model construction according to the present invention;
fig. 2 is a flowchart of a customs inspection rule generation method based on knowledge graph and tree model construction provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only illustrative and are not intended to limit the present invention.
The invention provides a customs detection rule generation method based on knowledge graph and tree model construction, as shown in fig. 1 and fig. 2, comprising the following steps:
s1: extracting a customs declaration form of the historical detection articles from a customs detection database, and performing data cleaning on the customs declaration form;
s2: taking the most common rule in the customs inspection expert system as a preliminary rule;
s3: performing characteristic engineering processing on the customs clearance sheet after data cleaning, analyzing customs clearance sheet parameters contained in the customs clearance sheet after the characteristic engineering processing, and extracting nonzero-value parameters from the customs clearance sheet parameters;
s4: extracting sample data from the extracted nonzero-value parameters by adopting a put-back sampling mode, primarily screening the extracted sample data by using a primary rule, and training a CART decision tree model by using the primarily screened sample data to obtain a trained CART decision tree model;
s5: returning to step S4, step S4 is repeatedly executed; after repeating for many times, performing weighted fusion on the trained CART decision tree models in a superposition mode to obtain a random forest;
s6: establishing a customs declaration form containing relationship based on the relevant knowledge in the customs inspection expert field, wherein the customs declaration form containing relationship comprises a customs declaration form type containing relationship and a customs declaration form parameter containing relationship;
s7: respectively regarding each customs declaration and each customs declaration parameter as a graph node;
s8: judging whether inclusion relations exist among the customs clearance reports, among the customs clearance report parameters and between the customs clearance reports and the customs clearance report parameters; if yes, establishing an edge between the two nodes with the inclusion relationship, wherein the edge points to the included person from the included person, and the weight value of the edge is the probability value from the included person to the included person; if not, establishing no communication relation between the two nodes without the inclusion relation; traversing all customs declaration forms and all customs declaration form parameters to obtain a knowledge graph directed probability graph model;
s9: setting the customs declaration form and the customs declaration form parameters after the preliminary rule screening as initial nodes n1,n2…..nkSetting the customs declaration form and customs declaration form parameters of the target object as a final node m1,m2,….mlCalculating the maximum probability value max P (m) of the directed probability graph model of the knowledge graph1,m2,….ml|n1,n2…..nk);
S10: and performing weighted fusion on the maximum probability value of the directed probability map model of the knowledge map and the maximum probability value output by the random forest to generate a final customs detection rule.
The following describes in detail a specific implementation of the customs inspection rule generating method according to the present invention by using a specific embodiment.
Example 1:
since the customs clearance is confidential data, the original customs clearance data cannot be used for flow description, so that the feasibility and effectiveness of the customs inspection rule generation method provided by the invention are fully described below by taking the import and export declaration form (table 1) in the international trade single window website in china as an example.
Table 1 is an import-export statement
Type of delivery | Time of delivery | E-commerce platform code | Electronic port numbering | ..... | Item related information |
C1 | C14 | C..50 | C18 | ... | ... |
The first step is as follows: and extracting an declaration form of the historical detection article from the customs detection database, and performing data cleaning on the declaration form. For example, if the item-related information in table 1 includes a large number of missing values, the item-related information may not be used, that is, the item-related information in table 1 is deleted, because the item-related information is an insignificant indicator.
The second step is that: the most common rules in the customs inspection expert system are taken as preliminary rules.
The third step: and performing characteristic engineering processing on the reported form after data cleaning, analyzing reported form parameters contained in the reported form after the characteristic engineering processing, and extracting non-zero value parameters from the reported form parameters. The invention mainly decomposes time information and explores relevant information as much as possible from the aspects of festivals and holidays on a time period. The specific method comprises the following steps:
(1) analyzing the time stamp in the statement form after data cleaning, extracting the date from the time stamp, and judging whether the date is the p th day of each week, the q th day of each month or a holiday; p ═ 1,2, …, 7; q is 1,2, …, 31;
(2) marking different levels of the holidays, and respectively representing the legal holidays, the long holidays and the short holidays by different numbers;
(3) judging whether the number of days from the next holiday is greater than a threshold value alpha or not; if yes, the distance is far from the legal festival and holiday; if not, the distance is considered to be close to the legal holiday;
(4) the threshold value alpha is adjusted. In particular, the threshold α needs to be adjusted according to the training result.
The fourth step: extracting sample data from the extracted nonzero-value parameters by adopting a put-back sampling (BootStrap) mode, preliminarily screening the extracted sample data by using a preliminary rule, and training a CART decision tree model by using the preliminarily screened sample data to obtain a trained CART decision tree model, wherein the specific method comprises the following steps:
(1) disordering the reporting forms, randomly extracting a part of data from the reporting forms as sample data, and learning the extracted sample data by using a CART decision tree model as a base classifier;
(2) and returning the learned sample data to the original data.
The fifth step: returning to the fourth step, and repeatedly executing the fourth step; and after repeating for multiple times, performing weighted fusion on the trained CART decision tree models in a stacking mode to obtain a random forest.
And a sixth step: and establishing an interpretation form containing relation based on the relevant knowledge in the field of customs inspection experts, wherein the interpretation form containing relation comprises an interpretation form type containing relation and an interpretation form parameter containing relation.
The seventh step: and respectively regarding each declaration table and each declaration table parameter as a graph node. Judging whether inclusion relations exist among the reporting forms, among the reporting form parameters and between the reporting forms and the reporting form parameters; if yes, establishing an edge between the two nodes with the inclusion relationship, wherein the edge points to the included person from the included person, and the weight value of the edge is the probability value from the included person to the included person; if not, establishing no communication relation between the two nodes without the inclusion relation, and not participating in subsequent calculation; and traversing all reporting tables and all reporting table parameters to obtain a knowledge graph directed probability graph model.
Eighth step: setting the statement form and the statement form parameter after the preliminary rule screening as an initial node n1,n2…..nkSetting a declaration form of the target object and declaration form parameters as a final node m1,m2,….mlCalculating the maximum probability value max P (m) of the directed probability graph model of the knowledge graph1,m2,….ml|n1,n2…..nk)。
The ninth step: and performing weighted fusion on the maximum probability value of the directed probability map model of the knowledge map and the maximum probability value output by the random forest to generate a final customs detection rule.
The invention provides an algorithm model capable of automatically learning rules, which has different learning strategies in the aspects of feature selection and feature learning. The introduction of the knowledge graph can enable the customs declaration information to have related information, can break through the independence between original parameters, makes a decision according to the learned relevance of the knowledge graph, and combines an original expert system to synthesize a stronger rule engine.
According to the customs detection rule generation method based on the knowledge graph and tree model construction, provided by the invention, a plurality of effective index features are extracted from a customs detection traditional expert rule engine, feature information is captured by two parts, the first part is used for extracting the feature information based on a plurality of CART decision trees to construct a random forest, the other part is used for learning the correlation relationship between customs declaration list data based on the knowledge graph, and the learned correlation relationship is used for learning the CART decision tree model. The invention fully utilizes the mutual relation among customs clearance reports, explores the relation information among data from different angles by learning the customs clearance report parameters and establishing the relation of the knowledge map, and ensures that a newly learned rule system is more complete and has higher accuracy.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. A customs detection rule generation method based on knowledge graph and tree model construction is characterized by comprising the following steps:
s1: extracting a customs declaration form of a historical detection article from a customs detection database, and performing data cleaning on the customs declaration form;
s2: taking the most common rule in the customs inspection expert system as a preliminary rule;
s3: performing characteristic engineering processing on the customs clearance sheet after data cleaning, analyzing customs clearance sheet parameters contained in the customs clearance sheet after the characteristic engineering processing, and extracting nonzero-value parameters from the customs clearance sheet parameters;
s4: extracting sample data from the extracted nonzero-value parameters by adopting a put-back sampling mode, primarily screening the extracted sample data by using the primary rule, and training a CART decision tree model by using the primarily screened sample data to obtain a trained CART decision tree model;
s5: returning to step S4, step S4 is repeatedly executed; after repeating for many times, performing weighted fusion on the trained CART decision tree models in a superposition mode to obtain a random forest;
s6: establishing a customs declaration form containing relationship based on the relevant knowledge in the customs inspection expert field, wherein the customs declaration form containing relationship comprises a customs declaration form type containing relationship and a customs declaration form parameter containing relationship;
s7: respectively regarding each customs declaration and each customs declaration parameter as a graph node;
s8: judging whether inclusion relations exist among the customs clearance reports, among the customs clearance report parameters and between the customs clearance reports and the customs clearance report parameters; if yes, establishing an edge between the two nodes with the inclusion relationship, wherein the edge points to the included person from the included person, and the weight value of the edge is the probability value from the included person to the included person; if not, establishing no communication relation between the two nodes without the inclusion relation; traversing all customs declaration forms and all customs declaration form parameters to obtain a knowledge graph directed probability graph model;
s9: setting the customs declaration form and the customs declaration form parameters after the preliminary rule screening as initial nodes n1,n2…..nkSetting the customs declaration form and customs declaration form parameters of the target object as a final node m1,m2,….mlCalculating the maximum probability value max P (m) of the knowledge-graph directed probability graph model1,m2,….ml|n1,n2…..nk);
S10: and performing weighted fusion on the maximum probability value of the knowledge map directed probability map model and the maximum probability value output by the random forest to generate a final customs detection rule.
2. The customs inspection rule generating method according to claim 1, wherein in step S3, if the nonzero-value parameter is time information, then in step S3, the customs declaration after data cleaning is processed by the feature engineering, the customs declaration parameter included in the customs declaration after the feature engineering is analyzed, and the nonzero-value parameter is extracted therefrom, which specifically includes the following steps:
s31: analyzing the time stamp in the customs clearance after data cleaning, extracting the date from the time stamp, and judging whether the date is the p th day of each week, the q th day of each month or a holiday or not; p ═ 1,2, …, 7; q is 1,2, …, 31;
s32: marking different levels of the holidays, and respectively representing the legal holidays, the long holidays and the short holidays by different numbers;
s33: judging whether the number of days from the next holiday is greater than a threshold value alpha or not; if yes, the distance is far from the legal festival and holiday; if not, the distance is considered to be close to the legal holiday;
s34: the threshold value alpha is adjusted.
3. The customs inspection rule generating method according to claim 1, wherein in step S4, sample data is extracted from the extracted non-zero value parameters by using a pull-back sampling method, the extracted sample data is primarily screened by using the primary rule, and the CART decision tree model is trained by using the primarily screened sample data to obtain a trained CART decision tree model, which specifically includes the following steps:
s41: disordering the customs declaration form, randomly extracting a part of data from the customs declaration form to be used as sample data, and learning the extracted sample data by using a CART decision tree model as a base classifier;
s42: and returning the learned sample data to the original data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010741825.4A CN111753928B (en) | 2020-07-29 | 2020-07-29 | Customs detection rule generation method based on knowledge graph and tree model construction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010741825.4A CN111753928B (en) | 2020-07-29 | 2020-07-29 | Customs detection rule generation method based on knowledge graph and tree model construction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111753928A true CN111753928A (en) | 2020-10-09 |
CN111753928B CN111753928B (en) | 2023-05-16 |
Family
ID=72712319
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010741825.4A Active CN111753928B (en) | 2020-07-29 | 2020-07-29 | Customs detection rule generation method based on knowledge graph and tree model construction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111753928B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116776831A (en) * | 2023-03-27 | 2023-09-19 | 阿里巴巴(中国)有限公司 | Customs, customs code determination, decision tree construction method and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040267770A1 (en) * | 2003-06-25 | 2004-12-30 | Lee Shih-Jong J. | Dynamic learning and knowledge representation for data mining |
CN108073673A (en) * | 2017-05-15 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of legal knowledge map construction method, apparatus, system and medium based on machine learning |
CN110609906A (en) * | 2019-09-16 | 2019-12-24 | 金色熊猫有限公司 | Knowledge graph construction method and device, storage medium and electronic terminal |
CN111428051A (en) * | 2020-03-23 | 2020-07-17 | 郑州大学 | Method and system for constructing self-adaptive learning knowledge graph fused with multivariate intelligence |
CN111444410A (en) * | 2020-03-27 | 2020-07-24 | 民生科技有限责任公司 | Associated transaction mining and identifying method and device based on knowledge graph |
-
2020
- 2020-07-29 CN CN202010741825.4A patent/CN111753928B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040267770A1 (en) * | 2003-06-25 | 2004-12-30 | Lee Shih-Jong J. | Dynamic learning and knowledge representation for data mining |
CN108073673A (en) * | 2017-05-15 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of legal knowledge map construction method, apparatus, system and medium based on machine learning |
CN110609906A (en) * | 2019-09-16 | 2019-12-24 | 金色熊猫有限公司 | Knowledge graph construction method and device, storage medium and electronic terminal |
CN111428051A (en) * | 2020-03-23 | 2020-07-17 | 郑州大学 | Method and system for constructing self-adaptive learning knowledge graph fused with multivariate intelligence |
CN111444410A (en) * | 2020-03-27 | 2020-07-24 | 民生科技有限责任公司 | Associated transaction mining and identifying method and device based on knowledge graph |
Non-Patent Citations (1)
Title |
---|
侯位昭;张欣海;宋凯磊;司佳;齐幸辉;张博;: "融合知识图谱及贝叶斯网络的智能推荐方法", 中国电子科学研究院学报 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116776831A (en) * | 2023-03-27 | 2023-09-19 | 阿里巴巴(中国)有限公司 | Customs, customs code determination, decision tree construction method and medium |
CN116776831B (en) * | 2023-03-27 | 2023-12-22 | 阿里巴巴(中国)有限公司 | Customs, customs code determination, decision tree construction method and medium |
Also Published As
Publication number | Publication date |
---|---|
CN111753928B (en) | 2023-05-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bunn et al. | An introduction to dplR | |
CN110688454A (en) | Method, device, equipment and storage medium for processing consultation conversation | |
CN112241481A (en) | Cross-modal news event classification method and system based on graph neural network | |
CN115759640B (en) | Public service information processing system and method for smart city | |
CN110995643B (en) | Abnormal user identification method based on mail data analysis | |
Gerhana et al. | Comparison of naive Bayes classifier and C4. 5 algorithms in predicting student study period | |
CN107943973A (en) | A kind of big data system for washing intelligently and cloud intelligent robot clean service platform | |
CN113191926A (en) | Grain and oil crop supply chain hazard identification method and system based on deep ensemble learning network | |
CN109670037A (en) | K-means Text Clustering Method based on topic model and rough set | |
CN111260568A (en) | Method for removing post binarization background noise based on multi-discriminator confrontation network | |
CN109063983A (en) | A kind of natural calamity loss real time evaluating method based on social media data | |
CN112232171A (en) | Remote sensing image information extraction method and device based on random forest and storage medium | |
CN114117029B (en) | Solution recommendation method and system based on multi-level information enhancement | |
CN111753928A (en) | Customs inspection rule generation method based on knowledge graph and tree model construction | |
Ghose et al. | Decision tree classification of remotely sensed satellite data using spectral separability matrix | |
CN112687402A (en) | Intelligent medical internet big data processing method based on artificial intelligence and intelligent cloud service platform | |
CN109840537A (en) | A kind of image multitask classification method based on cross validation's neural network | |
CN116580233A (en) | Intelligent working robot control system for industrial garbage classification | |
CN110363198A (en) | A kind of neural network weight matrix fractionation and combined method | |
CN107767278B (en) | Method and device for constructing community hierarchy | |
CN114241206A (en) | Target object feature extraction method and device, electronic equipment and storage medium | |
CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment | |
CN112819527A (en) | User grouping processing method and device | |
CN109300025B (en) | Big data and deep learning-based auditing method and robot system | |
CN113220970A (en) | E-commerce big data platform based on block chain |
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 |