CN113570428A - System for screening consistency of online commodities - Google Patents
System for screening consistency of online commodities Download PDFInfo
- Publication number
- CN113570428A CN113570428A CN202110833914.6A CN202110833914A CN113570428A CN 113570428 A CN113570428 A CN 113570428A CN 202110833914 A CN202110833914 A CN 202110833914A CN 113570428 A CN113570428 A CN 113570428A
- Authority
- CN
- China
- Prior art keywords
- classification
- commodity
- attribute
- commodities
- consistency
- 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
- 238000012216 screening Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- DWDGSKGGUZPXMQ-UHFFFAOYSA-N OPPO Chemical compound OPPO DWDGSKGGUZPXMQ-UHFFFAOYSA-N 0.000 description 1
- 244000062793 Sorghum vulgare Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 235000019713 millet Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
Images
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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90348—Query processing by searching ordered data, e.g. alpha-numerically ordered data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a system for screening consistency of online commodities, which belongs to the field of electronic commerce information processing, and comprises the steps of firstly constructing classification tables and attribute classification tables of all commodity category names, storing the classification tables and the attribute classification tables into a database, and then constructing a consistency screening system according to the classification tables; the classification forest is composed of a plurality of classification trees of commodity categories, each classification tree is used for determining the commodity code of one category of commodities, and when the classification forest contains all commodities, the unique codes of all the categories of commodities are determined. The invention can have certain generalization capability on unknown commodity information by constructing the classification tree, can correctly screen the consistency of commodities and improves the processing efficiency.
Description
Technical Field
The invention belongs to the field of electronic commerce information processing, and particularly relates to a system for screening consistency of online commodities.
Background
The commodity classification can be classified on the E-commerce platform, but the classification and the structure of the commodity on different sales platforms are often different, and for platform data with huge quantity and various types, the commodity classification is tedious when the commodity information is determined by unified commodity statistics.
For market analysts on the product side, if the consistency of commodities on all sales platforms can be determined, the sales condition of the commodities can be rapidly counted aiming at specific commodities, and the product sales and the market control are facilitated. For the consistency of the commodities, the information of the commodities on the electric vendor platform needs to be analyzed, and the commodity description information is completely classified, so that the unique code of the commodity is determined, and the uniqueness of the commodity on multiple platforms can be determined.
Disclosure of Invention
The invention provides a system for online commodity consistency screening, which aims to solve the technical problems and can calculate the commodity characteristics on an e-commerce platform and output a full-class unique code.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a system for online commodity consistency screening, characterized in that: firstly, establishing classification tables and attribute classification tables of all commodity category names, storing the classification tables and the attribute classification tables into a database, and then establishing a consistency screening system according to the classification tables, wherein the consistency screening system is established by the following specific steps:
step S10: firstly, acquiring commodity classification labels of a commodity platform, inquiring whether the classification labels exist in a classification table, and if the classification labels do not exist, inserting the classification labels into the classification table; if the classification label exists, continuously acquiring the commodity attribute of the classification label, and dividing the commodity attribute into a plurality of dimensions according to attribute characteristics, wherein each attribute forms one dimension;
step S20: calculating weight according to the commodity classification label level, and calculating an attribute priority sequence number by combining with the commodity attribute;
step S30: acquiring commodity categories and commodity attributes from the sub-list, taking different categories of commodities as root nodes, respectively constructing classification trees according to the commodity attribute characteristics under each category, and forming a classification forest by a plurality of classification trees to form a consistency screening system;
step S40: accessing the commodity address or system recommendation information, obtaining the attribute characteristics of the commodity, storing the attribute characteristics into a commodity attribute information pool, selecting the attribute characteristics to be classified from the commodity attribute information pool, inputting the attribute characteristics into the system, and obtaining the code of the commodity through a classification tree in the system;
step S50: and storing the commodity code in a system, establishing a corresponding relation between the commodity code and the commodity, and determining the consistency of the commodity.
Further, in step S20, the specific step of calculating the attribute priority sequence number includes: firstly, carrying out hierarchical classification on label grades of commodities, calculating the weight of the commodity labels according to the feature description importance of the commodity labels to the commodities, distributing the weight from high label grades to low label grades, and then carrying out required calculation on each attribute of the commodities in a commodity attribute information pool; during calculation, vectorization processing is carried out on the classification under the attribute, and the priority sequence number of the classification is determined according to the sequence in the attribute classification table.
Furthermore, when an attribute classification table is constructed and the classification under the attribute is character type, the classification characters are vectorized and converted into one-hot codes, and the sequence of the classification characters in the classification table is determined according to the sequence of the one-hot codes in the one-hot table; when the attribute is classified into a numerical type, the numerical types are arranged in the attribute classification table from small to large.
Further, the specific steps of constructing the classification tree in step S30 are as follows: all classes in the commodity class classification table are used as root nodes, commodity attributes under the classes are used as child nodes, the child nodes are ordered, the child nodes are sequentially arranged according to the priority sequence numbers calculated in the step S20, and all nodes in the attribute classification table are constructed in a recursion mode in sequence until the classification tree contains all classification attribute features; on the path from the parent node to the child node, a classification sequence number under the attribute is assigned.
Further, the specific implementation process of step S40 is as follows:
step S401: inputting an online commodity address or system recommendation information, accessing the address, and extracting attribute characteristic information of the commodity: acquiring commodity text description information and picture description information, and storing attribute characteristics into a commodity attribute information pool;
step S402: finding a root node in the system according to the commodity category, selecting a classification tree where the root node is located, and sequentially inputting the characteristics in the commodity attribute information pool into the classification tree;
step S403: by setting the sensitivity degree of commodity consistency, the degree of judging the attribute of the commodity consistency is changed, the classification tree is pruned according to different classification requirements, the attribute information which cannot describe the commodity is cut off, and leaf nodes are the characteristic information which finally describes the commodity;
step S404: on the pruned classification tree, the commodity attribute features determine the classification attribute codes of all attributes through the classification tree;
step S405: and acquiring codes from the root node of the commodity category to the characteristic information finally describing the commodity from left to right in sequence on the paths in the classification tree, and combining the codes on the paths to form the code of the commodity.
Furthermore, the classification forest is composed of a plurality of classification trees of commodity categories, each classification tree is used for determining the commodity code of one category of commodities, and when the classification forest contains all commodities, the unique codes of all the categories of commodities are determined.
Compared with the prior art, the invention has the beneficial effects that: (1) according to the invention, the commodity classification on each platform can be subjected to full-class statistics by setting the classification table, so that a finished commodity classification table is constructed; (2) according to the invention, by constructing the classification tree, the unknown commodity information can be generalized to a certain extent, the consistency of the commodities can be correctly screened, and the processing efficiency is improved.
Drawings
FIG. 1 is a schematic view of the overall process of the present invention.
FIG. 2 is a diagram illustrating the calculation of attribute weights according to the present invention.
FIG. 3 is a flow chart of the present invention for obtaining the product code.
Fig. 4 and 5 are schematic diagrams of classification trees and classification forest structures of the invention.
Detailed Description
The present invention will be further described with reference to specific examples, which are illustrative of the invention and are not to be construed as limiting the invention.
Example (b): as shown in fig. 1, fig. 2, fig. 3, fig. 4, and fig. 5, a system for on-line commodity consistency screening first constructs classification tables and attribute classification tables of all commodity category names, and stores the classification tables and attribute classification tables in a database, and then constructs a consistency screening system according to the classification tables, wherein the consistency screening system is constructed by the specific steps of:
step S10: firstly, acquiring commodity classification labels of a commodity platform, inquiring whether the classification labels exist in a classification table, and if the classification labels do not exist, inserting the classification labels into the classification table; if the classification label exists, continuously acquiring the commodity attribute of the classification label, and dividing the commodity attribute into a plurality of dimensions according to attribute characteristics, wherein each attribute forms one dimension; the positions of different classifications under each attribute on a vector space are extremely close, and mapping on the vector space exists between the associated attributes;
step S20: calculating weight according to the commodity classification label level, and calculating an attribute priority sequence number by combining with the commodity attribute; the classification labels on different E-commerce platforms are different, so the weight obtained by the grade calculation of the classification labels only has a certain reference function for the attribute priority sequence number of the commodity attribute calculation, and the commodity attribute priority sequence number is calculated according to the self characteristic of the commodity attribute;
step S30: acquiring commodity categories and commodity attributes from the sub-list, constructing classification trees by using the commodity attribute characteristics and the commodity attribute characteristics under each category by using different categories of commodities as root nodes, and constructing classification trees by using the commodity attribute characteristics under each category, wherein a plurality of classification trees form a classification forest to form a consistency screening system;
step S40: accessing the commodity address or system recommendation information, obtaining the attribute characteristics of the commodity, storing the attribute characteristics into a commodity attribute information pool, selecting the attribute characteristics to be classified from the commodity attribute information pool, inputting the attribute characteristics into the system, and obtaining the code of the commodity through a classification tree in the system;
step S50: and storing the commodity code in a system, establishing a corresponding relation between the commodity code and the commodity, and determining the consistency of the commodity.
Further, in step S20, the specific step of calculating the attribute priority number is as follows: the method comprises the steps of firstly, carrying out hierarchical classification on label grades of commodities, calculating the weight of the commodity labels according to the feature description importance of the commodity labels, distributing the weight from high to low of the label grades, then carrying out required calculation on each attribute of the commodities in a commodity attribute information pool, carrying out vectorization processing on the classifications under the attributes during calculation, and determining the priority sequence numbers of the classifications according to the sequence in an attribute classification table.
When an attribute classification table is constructed and the classification under the attribute is character type, vectorizing the classification characters, converting the vectorized classification characters into one-hot codes, and determining the sequence of the classification characters in the classification table according to the sequence of the one-hot codes in the one-hot table; when the attribute is classified into a numerical type, the numerical types are arranged in the attribute classification table from small to large.
The specific steps of constructing the classification tree in step S30 are as follows: all classes in the commodity class classification table are used as root nodes, commodity attributes under the classes are used as child nodes, the child nodes are ordered, the child nodes are sequentially arranged according to the priority sequence numbers calculated in the step S20, and all nodes in the attribute classification table are constructed in a recursion mode in sequence until the classification tree contains all classification attribute features; on the path from the parent node to the child node, a classification sequence number under the attribute is assigned.
The specific implementation process of step S40 is:
step S401: inputting an online commodity address or system recommendation information, accessing the address, and extracting attribute characteristic information of the commodity: acquiring commodity text description information and picture description information, and storing attribute characteristics into a commodity attribute information pool;
step S402: finding a root node in the system according to the commodity category, selecting a classification tree where the root node is located, and sequentially inputting the characteristics in the commodity attribute information pool into the classification tree; the input sequence of the attribute features of the commodity is obtained by calculation in step S20, and the features that can be input into the classification tree are all features that play a critical description for the commodity;
step S403: the commodity consistency sensitivity degree is set, the commodity consistency attribute judgment degree is changed, the commodity consistency attribute judgment degree is determined according to different classification requirements, a classification tree is pruned, the attribute information incapable of describing commodities is cut off, and leaf nodes are the feature information finally describing the commodities; the pruning operation is to change the statistical subclass and reflect the consistency problem of the commodities to different degrees;
step S404: on the pruned classification tree, the commodity attribute features determine the classification attribute codes of all attributes through the classification tree;
step S405: and acquiring codes from the root node of the commodity category to the characteristic information finally describing the commodity from left to right in sequence on the paths in the classification tree, and combining the codes on the paths to form the code of the commodity.
Furthermore, the classification forest is composed of a plurality of classification trees of commodity categories, each classification tree is used for determining the commodity code of one category of commodities, and when the classification forest contains all commodities, the unique codes of all the categories of commodities are determined.
In the implementation process of this embodiment, the mobile phone model is taken as an example to illustrate the workflow of the consistency screening system: in the E-commerce platform, the commodity features describing the mobile phone include mobile phone brands such as Huashi, millet, OPPO, vivo and the like, which are brand attributes of mobile phone category attributes, and the features describing the mobile phone functions include: the running memory, such as 3GB, 4GB, 8GB, 16GB and the like, is a numerical characteristic; color of the mobile phone: red, blue, black, purple, etc., which are character description features; the description of other additional functions is different, the classification description on different E-commerce platforms is different, the information is considered in a sub-optimal priority when the commodity attribute priority sequence number is calculated, and after the mobile phone information on the platform is collected, a classification tree for classifying the mobile phone models is constructed: when the commodity page is a certain brand mobile phone, the color is black, the operation memory is 6GB, and the network type is 5G, the characteristics formed by the attributes of the commodities sequentially pass through the classification tree to obtain the attribute priority sequence number of the attribute in the classification tree, when all commodity information can be classified and reflected in the classification tree, the path from the root node to the leaf node is the unique code of the attribute, and the code is combined to be the unique code of the commodity. When the sensitivity degree of commodity consistency is reduced, only the brand of the mobile phone needs to be confirmed, the classification tree is pruned, and the attribute describing the brand of the mobile phone is cut into leaf nodes.
The present invention is not limited to the above-described embodiments, and those skilled in the art will be able to make various modifications without creative efforts from the above-described conception and fall within the scope of the present invention.
Claims (6)
1. A system for online commodity consistency screening, characterized in that: firstly, establishing classification tables and attribute classification tables of all commodity category names, storing the classification tables and the attribute classification tables into a database, and then establishing a consistency screening system according to the classification tables, wherein the consistency screening system is established by the following specific steps:
step S10: firstly, acquiring commodity classification labels of a commodity platform, inquiring whether the classification labels exist in a classification table, and if the classification labels do not exist, inserting the classification labels into the classification table; if the classification label exists, continuously acquiring the commodity attribute of the classification label, and dividing the commodity attribute into a plurality of dimensions according to attribute characteristics, wherein each attribute forms one dimension;
step S20: calculating weight according to the commodity classification label level, and calculating an attribute priority sequence number by combining with the commodity attribute;
step S30: acquiring commodity categories and commodity attributes from the sub-list, taking different categories of commodities as root nodes, respectively constructing classification trees according to the commodity attribute characteristics under each category, and forming a classification forest by a plurality of classification trees to form a consistency screening system;
step S40: accessing the commodity address or system recommendation information, obtaining the attribute characteristics of the commodity, storing the attribute characteristics into a commodity attribute information pool, selecting the attribute characteristics to be classified from the commodity attribute information pool, inputting the attribute characteristics into the system, and obtaining the code of the commodity through a classification tree in the system;
step S50: and storing the commodity code in a system, establishing a corresponding relation between the commodity code and the commodity, and determining the consistency of the commodity.
2. The system for on-line merchandise uniformity screening of claim 1, wherein: in step S20, the specific steps of calculating the attribute priority sequence number include: firstly, carrying out hierarchical classification on label grades of commodities, calculating the weight of the commodity labels according to the feature description importance of the commodity labels to the commodities, distributing the weight from high label grades to low label grades, and then carrying out required calculation on each attribute of the commodities in a commodity attribute information pool; during calculation, vectorization processing is carried out on the classification under the attribute, and the priority sequence number of the classification is determined according to the sequence in the attribute classification table.
3. The system for on-line merchandise uniformity screening of claim 1, wherein: when an attribute classification table is constructed and the classification under the attribute is character type, vectorizing the classification characters, converting the vectorized classification characters into one-hot codes, and determining the sequence of the classification characters in the classification table according to the sequence of the one-hot codes in the one-hot table; when the attribute is classified into a numerical type, the numerical types are arranged in the attribute classification table from small to large.
4. The system for on-line merchandise uniformity screening of claim 1, wherein: the specific steps of constructing the classification tree in step S30 are as follows: all classes in the commodity class classification table are used as root nodes, commodity attributes under the classes are used as child nodes, the child nodes are ordered, the child nodes are sequentially arranged according to the priority sequence numbers calculated in the step S20, and all nodes in the attribute classification table are constructed in a recursion mode in sequence until the classification tree contains all classification attribute features; on the path from the parent node to the child node, a classification sequence number under the attribute is assigned.
5. The system for on-line merchandise uniformity screening of claim 1, wherein: the specific implementation process of step S40 is:
step S401: inputting an online commodity address or system recommendation information, accessing the address, and extracting attribute characteristic information of the commodity: acquiring commodity text description information and picture description information, and storing attribute characteristics into a commodity attribute information pool;
step S402: finding a root node in the system according to the commodity category, selecting a classification tree where the root node is located, and sequentially inputting the characteristics in the commodity attribute information pool into the classification tree;
step S403: by setting the sensitivity degree of commodity consistency, the degree of judging the attribute of the commodity consistency is changed, the classification tree is pruned according to different classification requirements, the attribute information which cannot describe the commodity is cut off, and leaf nodes are the characteristic information which finally describes the commodity;
step S404: on the pruned classification tree, the commodity attribute features determine the classification attribute codes of all attributes through the classification tree;
step S405: and acquiring codes from the root node of the commodity category to the characteristic information finally describing the commodity from left to right in sequence on the paths in the classification tree, and combining the codes on the paths to form the code of the commodity.
6. The system for on-line merchandise uniformity screening of claim 1, wherein: the classified forest is composed of a plurality of classification trees of commodity categories, each classification tree is used for determining the commodity code of one category of commodities, and when the classified forest contains all commodities, the unique codes of all the categories of commodities are determined.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110833914.6A CN113570428B (en) | 2021-07-23 | 2021-07-23 | System for be used for online commodity uniformity screening |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110833914.6A CN113570428B (en) | 2021-07-23 | 2021-07-23 | System for be used for online commodity uniformity screening |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113570428A true CN113570428A (en) | 2021-10-29 |
CN113570428B CN113570428B (en) | 2024-02-02 |
Family
ID=78166527
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110833914.6A Active CN113570428B (en) | 2021-07-23 | 2021-07-23 | System for be used for online commodity uniformity screening |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113570428B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114429390A (en) * | 2022-04-02 | 2022-05-03 | 萨科(深圳)科技有限公司 | E-commerce product classification method and classification system |
CN116737697A (en) * | 2023-08-10 | 2023-09-12 | 云筑信息科技(成都)有限公司 | Method and device for managing main data of materials in construction industry and electronic equipment |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5179643A (en) * | 1988-12-23 | 1993-01-12 | Hitachi, Ltd. | Method of multi-dimensional analysis and display for a large volume of record information items and a system therefor |
US20010042059A1 (en) * | 1998-01-08 | 2001-11-15 | Fujitsu Limited | Inventory managing method for automatic inventory retrieval and apparatus thereof |
JP2005208709A (en) * | 2004-01-20 | 2005-08-04 | Fuji Xerox Co Ltd | Data classification processing apparatus, data classification processing method and computer program |
CN102841946A (en) * | 2012-08-24 | 2012-12-26 | 北京国政通科技有限公司 | Commodity data retrieval sequencing and commodity recommendation method and system |
CN102915498A (en) * | 2011-08-03 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Method and device for goods classification of e-commerce platform |
US20130054569A1 (en) * | 2010-04-30 | 2013-02-28 | Alibaba Group Holding Limited | Vertical Search-Based Query Method, System and Apparatus |
CN103593763A (en) * | 2012-08-13 | 2014-02-19 | 腾讯科技(深圳)有限公司 | An information organization method and an apparatus thereof and an information display method and an apparatus thereof |
CN103778214A (en) * | 2014-01-16 | 2014-05-07 | 北京理工大学 | Commodity property clustering method based on user comments |
CN103914492A (en) * | 2013-01-09 | 2014-07-09 | 阿里巴巴集团控股有限公司 | Method for query term fusion, method for commodity information publish and method and system for searching |
CN103995905A (en) * | 2014-06-13 | 2014-08-20 | 重庆大学 | Electronic commerce content multi-dimensional classification, navigation and skipping method |
CN107730343A (en) * | 2017-09-15 | 2018-02-23 | 广州唯品会研究院有限公司 | A kind of user's merchandise news method for pushing and equipment based on picture attribute extraction |
KR20180123826A (en) * | 2017-05-10 | 2018-11-20 | 네모커머스(주) | Correspondences generation system of goods classification between heterogeneous classification |
CN110287329A (en) * | 2019-07-04 | 2019-09-27 | 刘凡 | A kind of electric business classification attribute excavation method based on commodity text classification |
CN111126442A (en) * | 2019-11-26 | 2020-05-08 | 北京京邦达贸易有限公司 | Method for generating key attribute of article, method and device for classifying article |
CN111563529A (en) * | 2020-03-31 | 2020-08-21 | 中国科学院信息工程研究所 | Data category attribute representation method and access control method |
CN112463971A (en) * | 2020-09-15 | 2021-03-09 | 杭州商情智能有限公司 | E-commerce commodity classification method and system based on hierarchical combination model |
CN112801720A (en) * | 2021-04-12 | 2021-05-14 | 连连(杭州)信息技术有限公司 | Method and device for generating shop category identification model and identifying shop category |
-
2021
- 2021-07-23 CN CN202110833914.6A patent/CN113570428B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5179643A (en) * | 1988-12-23 | 1993-01-12 | Hitachi, Ltd. | Method of multi-dimensional analysis and display for a large volume of record information items and a system therefor |
US20010042059A1 (en) * | 1998-01-08 | 2001-11-15 | Fujitsu Limited | Inventory managing method for automatic inventory retrieval and apparatus thereof |
JP2005208709A (en) * | 2004-01-20 | 2005-08-04 | Fuji Xerox Co Ltd | Data classification processing apparatus, data classification processing method and computer program |
US20130054569A1 (en) * | 2010-04-30 | 2013-02-28 | Alibaba Group Holding Limited | Vertical Search-Based Query Method, System and Apparatus |
CN102915498A (en) * | 2011-08-03 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Method and device for goods classification of e-commerce platform |
CN103593763A (en) * | 2012-08-13 | 2014-02-19 | 腾讯科技(深圳)有限公司 | An information organization method and an apparatus thereof and an information display method and an apparatus thereof |
CN102841946A (en) * | 2012-08-24 | 2012-12-26 | 北京国政通科技有限公司 | Commodity data retrieval sequencing and commodity recommendation method and system |
CN103914492A (en) * | 2013-01-09 | 2014-07-09 | 阿里巴巴集团控股有限公司 | Method for query term fusion, method for commodity information publish and method and system for searching |
CN103778214A (en) * | 2014-01-16 | 2014-05-07 | 北京理工大学 | Commodity property clustering method based on user comments |
CN103995905A (en) * | 2014-06-13 | 2014-08-20 | 重庆大学 | Electronic commerce content multi-dimensional classification, navigation and skipping method |
KR20180123826A (en) * | 2017-05-10 | 2018-11-20 | 네모커머스(주) | Correspondences generation system of goods classification between heterogeneous classification |
CN107730343A (en) * | 2017-09-15 | 2018-02-23 | 广州唯品会研究院有限公司 | A kind of user's merchandise news method for pushing and equipment based on picture attribute extraction |
CN110287329A (en) * | 2019-07-04 | 2019-09-27 | 刘凡 | A kind of electric business classification attribute excavation method based on commodity text classification |
CN111126442A (en) * | 2019-11-26 | 2020-05-08 | 北京京邦达贸易有限公司 | Method for generating key attribute of article, method and device for classifying article |
CN111563529A (en) * | 2020-03-31 | 2020-08-21 | 中国科学院信息工程研究所 | Data category attribute representation method and access control method |
CN112463971A (en) * | 2020-09-15 | 2021-03-09 | 杭州商情智能有限公司 | E-commerce commodity classification method and system based on hierarchical combination model |
CN112801720A (en) * | 2021-04-12 | 2021-05-14 | 连连(杭州)信息技术有限公司 | Method and device for generating shop category identification model and identifying shop category |
Non-Patent Citations (5)
Title |
---|
况立群;熊风光;韩燮;: "基于前缀编码的先根遍历树生成算法的研究与应用", 计算机应用与软件, no. 04 * |
张莉;牟敏;: "利用数据挖掘实现管理客户关系中的客户分类", 商场现代化, no. 19 * |
阮备军, 朱扬勇: "基于商品分类信息的关联规则聚类", 计算机研究与发展, no. 02 * |
魏晓云;: "决策树分类方法研究", 计算机***应用, no. 09 * |
鲁增秋;陈玉哲;王殿升;: "一种改进的基于商品分类信息的多层关联规则挖掘算法", 科技情报开发与经济, no. 14 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114429390A (en) * | 2022-04-02 | 2022-05-03 | 萨科(深圳)科技有限公司 | E-commerce product classification method and classification system |
CN116737697A (en) * | 2023-08-10 | 2023-09-12 | 云筑信息科技(成都)有限公司 | Method and device for managing main data of materials in construction industry and electronic equipment |
CN116737697B (en) * | 2023-08-10 | 2023-10-20 | 云筑信息科技(成都)有限公司 | Method and device for managing main data of materials in construction industry and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN113570428B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107515898B (en) | Tire enterprise sales prediction method based on data diversity and task diversity | |
CN110580649B (en) | Method and device for determining commodity potential value | |
US7051025B2 (en) | Method and system for displaying multidimensional aggregate patterns in a database system | |
CN113570428B (en) | System for be used for online commodity uniformity screening | |
CN110390077B (en) | Method for identifying commodity price abnormal risk | |
CN106844407B (en) | Tag network generation method and system based on data set correlation | |
JPH0877010A (en) | Method and device for data analysis | |
CN111191125A (en) | Data analysis method based on tagging | |
CN104102670A (en) | Performance indicator analytical framework | |
CN111915191A (en) | Industrial chain identification method and device | |
CN110990403A (en) | Business data storage method, system, computer equipment and storage medium | |
US20210090105A1 (en) | Technology opportunity mapping | |
US9032362B2 (en) | System and method for generating high performance calculators for calculation graphs | |
CN111428007A (en) | Cross-platform based synchronous push feedback method | |
CN111625567A (en) | Data model matching method, device, computer system and readable storage medium | |
CN115879826B (en) | Fine chemical process quality inspection method, system and medium based on big data | |
CN107016583A (en) | Data processing method and device | |
CN110968670A (en) | Method, device, equipment and storage medium for acquiring attributes of popular commodities | |
CN114022086B (en) | Purchasing method, device, equipment and storage medium based on BOM identification | |
CN115510289A (en) | Data cube configuration method and device, electronic equipment and storage medium | |
KR100888329B1 (en) | System and method for automatically detecting information in real-time using rule | |
CN108711074A (en) | Business sorting technique, device, server and readable storage medium storing program for executing | |
CN114429384A (en) | Intelligent product recommendation method and system based on e-commerce platform | |
CN113486225A (en) | Enterprise image display method and system based on big data | |
CN113282683A (en) | Method and apparatus for determining device portrait, storage medium, and electronic apparatus |
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 |