CN110096643A - The latent objective label library generating method of product and device - Google Patents
The latent objective label library generating method of product and device Download PDFInfo
- Publication number
- CN110096643A CN110096643A CN201910239143.0A CN201910239143A CN110096643A CN 110096643 A CN110096643 A CN 110096643A CN 201910239143 A CN201910239143 A CN 201910239143A CN 110096643 A CN110096643 A CN 110096643A
- Authority
- CN
- China
- Prior art keywords
- product
- library
- user
- label
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000002372 labelling Methods 0.000 claims abstract description 53
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 abstract description 6
- 239000000047 product Substances 0.000 description 119
- 238000009825 accumulation Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of latent objective label library generating method of product and devices, method includes: to generate Product labelling library, accesses record and the Product labelling library based on user, generates user tag library, accessed record and the user tag library based on product generate the latent objective tag library of product.After generating Product labelling library, based on user behavior, record is accessed according to user and the generation of Product labelling library is directed to the user tag library of each user, and then the access user of access product is determined based on the accessed record of product, the latent objective tag library of the product that the product is finally generated according to the user tag library of all access users of one product of access, structuring and labeling have been carried out to the information of product and user through the above way, product relationship analysis has been can be realized using the latent objective tag library of the product of output, finds product potential customers and to lead referral product.
Description
Technical field
The invention belongs to user behavior technical fields, specifically, being to be related to a kind of latent objective label library generating method of product
And device.
Background technique
On the network media, to certain class product carry out big data analysis when, need to irregular product information data into
Line discipline, structuring, that is, tag library is generated according to setting rule to product, for example, automobile product is directed to, according to setting
Rule generates the labels such as color, price, performance, type, and then can be applied by Product labelling.
Summary of the invention
This application provides a kind of latent objective label library generating method of product and devices, are based on the basis of Product labelling library
User behavior analysis generates the latent objective tag library of product, is conducive to as Products Show potential customers.
In order to realize the above technical effect, the application is achieved using following technical scheme:
It is proposed a kind of latent objective label library generating method of product, comprising: generate Product labelling library；It is recorded based on user's access and described
Product labelling library generates user tag library；Accessed record and the user tag library based on product generate the latent visitor's mark of product
Sign library.
It is proposed that a kind of latent objective tag library generating means of product, including Product labelling library generation module, user tag library generate
Module and latent objective tag library generation module；Product labelling library generation module, for generating Product labelling library；User's mark
Library generation module is signed, for accessing record and the Product labelling library based on user, generates user tag library；The latent objective label
Library generation module, for based on product accessed record and the user tag library, generate the latent objective tag library of product.
Compared with prior art, the advantages of the application and good effect is: the latent objective tag library of the product that the application proposes is raw
At in method and apparatus, after generating Product labelling library, it is based on user behavior, record is accessed according to user and Product labelling library is raw
At the user tag library for being directed to each user, and then the access user for accessing product is determined based on the accessed record of product, most
The latent objective tag library of the product that the product is generated according to the user tag library of all access users of one product of access afterwards, by upper
It states mode and structuring and labeling has been carried out to the information of product and user, can be realized using the latent objective tag library of the product of output
Product relationship analysis finds product potential customers and to lead referral product.
After the detailed description of the application embodiment is read in conjunction with the figure, other features and advantages of the application will become more
Add clear.
Detailed description of the invention
Fig. 1 is the flow chart for the latent objective label library generating method of product that the application proposes；
Fig. 2 is the device architecture figure for the latent objective tag library generating means of product that the application proposes；
Fig. 3 is that the user tag library that the application proposes generates schematic diagram.
Specific embodiment
The specific embodiment of the application is described in more detail with reference to the accompanying drawing.
On the network media, to certain class product carry out big data analysis when, need to irregular product information data into
Line discipline, structuring, the latent objective label library generating method of the product that the embodiment of the present application proposes and device, can use unified mark
Right way of conduct method is signed, in multi-data source, labeling is carried out to different product data, track is accessed by user later,
Generate the latent objective tag library of user tag library and product, by these steps the information of product and user can be carried out structuring,
Labeling can carry out product relationship analysis using the result data of output, find the latent visitor of client, to lead referral product.
Specifically, the latent objective label library generating method of product that the application proposes, as shown in Figure 1, including the following steps:
Step S11: Product labelling library is generated.
A tag class, namely several label classifications of creation are safeguarded first, are each label category setting tag name, are extracted
Unique code of rule, database name, table name, product etc., the unique code of product are the coding of energy famous special product uniqueness in database,
Such as CONCAT(media_id, ' _ ', entity_id), media_id and entity_id are two field names in database,
Utilize two field designator product uniqueness of database；Extracting rule is the rule that this label is assigned to product, such as
The and of unit_price > 0 unit_price≤10000, unit_price are the unit prices of product in some database, and it is small to be greater than 0
In the label of 10000 imparting " 1W or less ".
For each label classification, the corresponding extracting rule of isolated operation stamps mark to the product for meeting extracting rule
It signs and marks tag name；Herein, basic running unit is label, is independent of each other between different labels, and finally set is all
Label classification generates Product labelling library.
Step S12: record and Product labelling library are accessed based on user, generate user tag library.
User tag library is customer-centric, is recorded by the access of user, can find a product, and then this
The corresponding all labels of all products of a user access are cumulative to be obtained.
Determine that user accesses product specifically, accessing and recording based on user, in conjunction with the Product labelling generated in step S11
Library, the label that all users that add up access product obtain user tag library, among these, will if accessing n times for a product
All labels of this product will be multiplied by adding up after N.
In the specific embodiment of the application, a period is set, when in the set time period each is set
It carves, all users that add up access the label of product, obtain several user tag groups, such as mark off M in the set time period
The moment is set, then add up all users of each setting moment access the labels of products, M group user tag group are obtained, finally, adding up
All user tag groups (M group) in set period of time obtain user tag library.
As shown in figure 3, product 1 have label A 1, A2 and A3, product 2 have label B 1, B2, product 3 have label C 1,
C2, C3 and C4；If being divided into 3 setting moment in set period of time, user 1 has accessed product at the t1 quarter in first setting
1 and product 3, product 1 and product 2 are had accessed in second setting moment t2, has accessed 2 He of product in third setting moment t3
Product 3, then the user tag group for the 3 groups of users 1 that add up in the set time period, (A1, A2, A3, C1, C2, C3, C4), (A1,
A2, A3, B1, B2) and (B1, B2, C1, C2, C3, C4), the user tag library of the user 1 finally obtained be (2A1,2A2,2A3,
2B1,2B2,2C1,2C2,2C3,2C4).
In practical applications, we to the user tag group of the historical juncture of user in such a way that decaying is cumulative, usually
To decay at any time, that is, assigning to the different set moment as the weight that the time decays adds up, for example, setting
Three settings moment t1, t2 and t3 in period, at the time of wherein t3 is closest current, then the weight accumulation for assigning t1 is
Q1, the weight accumulation for assigning t2 is q2, and the weight accumulation for assigning t3 is q3, then q1 < q2 < q3.
Step S13: accessed record and user tag library based on product generate the latent objective tag library of product.
In this step, product-centered, the accessed record of product is searched, is determined based on the accessed record of product
The user of access, and then the user tag library of all access users is inquired, the user tag library for all access users that add up obtains
The latent objective tag library of product.
As it can be seen that the latent objective tag library of product is tag library product-centered, relevant to user tag, and user tag
It is to be formed based on Product labelling again, structuring and labeling has been carried out to the information of product and user through the above way, answered
It can be realized product relationship analysis with the latent objective tag library of the product of output, find product potential customers and produced to lead referral
Product.
Based on the latent objective label library generating method of product set forth above, the application also proposes a kind of latent objective tag library of product
Generating means, as shown in Fig. 2, including Product labelling library generation module 21, user tag library generation module 22 and latent objective tag library
Generation module 23；Product labelling library generation module 21 is for generating Product labelling library；User tag library generation module 22 is used for base
Record and Product labelling library are accessed in user, generates user tag library；Latent visitor's tag library generation module 23 is used for based on product
Accessed record and user tag library generate the latent objective tag library of product.
Wherein, Product labelling library generation module 21 includes label classification creating unit 211, label for labelling unit 212 and produces
Product tag library generation unit 213；Label classification creating unit 211 is used for establishing label classification, is each label category setting mark
Signature and extracting rule；Label for labelling unit 212 is used to be directed to each label classification, corresponding extracting rule is run, to symbol
The product for closing extracting rule marks tag name；Product labelling library generation unit 213 generates product for gathering all label classifications
Tag library.
User tag library generation module 22 includes that user accesses record determination unit 221 and label summing elements 222；User
Access record determination unit 221, which is used to access to record based on user, determines that user accesses product；Label summing elements 222 are used for base
In Product labelling library, the label that all users that add up access product obtains user tag library.Wherein, label summing elements 222 wrap
It includes user tag group and generates subelement 2221 and the cumulative subelement 2222 of user tag group；User tag group generates subelement 2221
The labels of products is accessed for add up all users of each setting moment in the set time period, obtains several user tags
Group；All user tag groups that the cumulative subelement 2222 of user tag group is used to add up in set period of time obtain user tag
Library.
Latent visitor's tag library generation module 23 includes access user's determination unit 231 and user tag library summing elements 232；It visits
Ask that accessed record of the user's determination unit 231 for based on product determines access user；User tag library summing elements 232 are used
In the user tag library for inquiring all access users, the user tag library for all access users that add up obtains the latent objective label of product
Library.
The working method of the specific latent objective tag library generating means of product, in the latent objective tag library generation side of the said goods
It is described in detail in method, it will not go into details herein.
The latent objective label library generating method of the product that above-mentioned the application proposes and device are based on after generating Product labelling library
User behavior accesses the user tag library for recording and being directed to each user with the generation of Product labelling library according to user, and then based on production
The accessed record of product determines the access user of access product, finally according to the user of all access users of one product of access
Tag library generates the latent objective tag library of product of the product, through the above way to the information of product and user carried out structuring and
Labeling can be realized product relationship analysis using the latent objective tag library of the product of output, find product potential customers and to visitor
Family recommended products.
It should be noted that the above description is not a limitation of the present invention, the present invention is also not limited to the example above,
The variations, modifications, additions or substitutions that those skilled in the art are made within the essential scope of the present invention, are also answered
It belongs to the scope of protection of the present invention.
Claims (10)
1. the latent objective label library generating method of product characterized by comprising
Generate Product labelling library；
Record and the Product labelling library are accessed based on user, generates user tag library；
Accessed record and the user tag library based on product generate the latent objective tag library of product.
2. the latent objective label library generating method of product according to claim 1, which is characterized in that the generation Product labelling
Library, comprising:
Establishing label classification is each label category setting tag name and extracting rule；
For each label classification, corresponding extracting rule is run, tag name is marked to the product for meeting extracting rule；
Gather all label classifications and generates Product labelling library.
3. the latent objective label library generating method of product according to claim 1, which is characterized in that described to access note based on user
Record and the Product labelling library generate user tag library, comprising:
It accesses to record based on user and determines that user accesses product；
Based on the Product labelling library, the label that all users that add up access product obtains user tag library.
4. the latent objective label library generating method of product according to claim 3, which is characterized in that all users that add up, which access, to be produced
The label of product obtains user tag library, specifically:
Add up all users of each setting moment in the set time period access the labels of products, obtain several user tags
Group；
All user tag groups to add up in the set period of time obtain the user tag library.
5. the latent objective label library generating method of product according to claim 1, which is characterized in that the accessed note based on product
Record and the user tag library generate the latent objective tag library of product, comprising:
Access user is determined based on the accessed record of product；
The user tag library for inquiring all access users, the user tag library for all access users that add up obtain the latent objective label of product
Library.
6. the latent objective tag library generating means of product, which is characterized in that generated including Product labelling library generation module, user tag library
Module and latent objective tag library generation module；
Product labelling library generation module, for generating Product labelling library；
User tag library generation module generates user tag for accessing record and the Product labelling library based on user
Library；
The latent objective tag library generation module, for based on product accessed record and the user tag library, generate product
Latent visitor's tag library.
7. the latent objective tag library generating means of product according to claim 6, which is characterized in that the Product labelling library generates
Module includes label classification creating unit, label for labelling unit and Product labelling library generation unit；
The label classification creating unit is used for establishing label classification, is each label category setting tag name and extracting rule；
The label for labelling unit runs corresponding extracting rule, to meeting extracting rule for being directed to each label classification
Product mark tag name；
Product labelling library generation unit generates Product labelling library for gathering all label classifications.
8. the latent objective tag library generating means of product according to claim 6, which is characterized in that the user tag library generates
Module includes that user accesses record determination unit and label summing elements；
The user accesses record determination unit, determines that user accesses product for accessing to record based on user；
The label summing elements, for being based on the Product labelling library, the label that all users that add up access product is used
Family tag library.
9. the latent objective tag library generating means of product according to claim 8, which is characterized in that the label summing elements packet
It includes user tag group and generates subelement and the cumulative subelement of user tag group；
The user tag group generates subelement, visits for all users that add up of each setting moment in the set time period
The label for asking product obtains several user tag groups；
The user tag group adds up subelement, and all user tag groups for adding up in the set period of time obtain described
User tag library.
10. the latent objective tag library generating means of product according to claim 6, which is characterized in that the latent objective tag library is raw
It include access user's determination unit and user tag library summing elements at module；
Access user's determination unit determines access user for the accessed record based on product；
User tag library summing elements, for inquiring the user tag library of all access users, add up all access users
User tag library obtain the latent objective tag library of product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239143.0A CN110096643A (en) | 2019-03-27 | 2019-03-27 | The latent objective label library generating method of product and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239143.0A CN110096643A (en) | 2019-03-27 | 2019-03-27 | The latent objective label library generating method of product and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110096643A true CN110096643A (en) | 2019-08-06 |
Family
ID=67443097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910239143.0A Pending CN110096643A (en) | 2019-03-27 | 2019-03-27 | The latent objective label library generating method of product and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110096643A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024042903A1 (en) * | 2022-08-23 | 2024-02-29 | 株式会社日立製作所 | Information providing device and information providing system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402535A (en) * | 2010-09-13 | 2012-04-04 | 阿里巴巴集团控股有限公司 | Method and system for constructing product library |
| CN103235803A (en) * | 2013-04-17 | 2013-08-07 | 北京京东尚科信息技术有限公司 | Method and device for acquiring object attribute values from text |
| US20140317117A1 (en) * | 2012-04-17 | 2014-10-23 | Tencent Technology (Shenzhen) Company Limited | Method, device and computer storage media for user preferences information collection |
| CN104217334A (en) * | 2013-06-05 | 2014-12-17 | 北京京东尚科信息技术有限公司 | Product information recommendation method, device and system |
| CN107657267A (en) * | 2017-08-11 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Product potential user method for digging and device |
| CN107888950A (en) * | 2017-11-09 | 2018-04-06 | 福州瑞芯微电子股份有限公司 | A kind of method and system for recommending video |
| CN109191169A (en) * | 2018-07-19 | 2019-01-11 | 国政通科技有限公司 | Precisely hit the method for high-end tourism potential user |
-
2019
- 2019-03-27 CN CN201910239143.0A patent/CN110096643A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402535A (en) * | 2010-09-13 | 2012-04-04 | 阿里巴巴集团控股有限公司 | Method and system for constructing product library |
| US20140317117A1 (en) * | 2012-04-17 | 2014-10-23 | Tencent Technology (Shenzhen) Company Limited | Method, device and computer storage media for user preferences information collection |
| CN103235803A (en) * | 2013-04-17 | 2013-08-07 | 北京京东尚科信息技术有限公司 | Method and device for acquiring object attribute values from text |
| CN104217334A (en) * | 2013-06-05 | 2014-12-17 | 北京京东尚科信息技术有限公司 | Product information recommendation method, device and system |
| CN107657267A (en) * | 2017-08-11 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Product potential user method for digging and device |
| CN107888950A (en) * | 2017-11-09 | 2018-04-06 | 福州瑞芯微电子股份有限公司 | A kind of method and system for recommending video |
| CN109191169A (en) * | 2018-07-19 | 2019-01-11 | 国政通科技有限公司 | Precisely hit the method for high-end tourism potential user |
Non-Patent Citations (2)
| Title |
|---|
| 王裴: "分析用户画像在企业精准营销中的应用方式", 《商场现代化》 * |
| 郑树泉等: "《工业智能技术与应用》", 31 January 2019, 上海科学技术出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024042903A1 (en) * | 2022-08-23 | 2024-02-29 | 株式会社日立製作所 | Information providing device and information providing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20120055984A1 (en) | Physical product sample provided with at least one product sample code | |
| CN105005876A (en) | Client behavior acquiring and analyzing system and the using method | |
| CN105184083A (en) | Digital identity code used for medical instrument whole-process quality tracing and coding method thereof | |
| CA2669479A1 (en) | Generating end-user presentations from structured data | |
| CN111737343B (en) | Information labeling method based on block chain | |
| CN107180064A (en) | A kind of logistics information processing method, device and logistic information systems | |
| CN102004965A (en) | Double ant-counterfeiting method and system of product | |
| CN105022830B (en) | A kind of weighting track data collection construction method based on user behavior | |
| CN105872122A (en) | Internet of things identification method in support of multiple codes | |
| CN110955690A (en) | Self-service data labeling platform and self-service data labeling method based on big data technology | |
| CN106570674A (en) | Supply chain information query method and device | |
| CN110969473A (en) | User label generation method and device | |
| US8886684B2 (en) | Apparatus and method for managing register of unique identifiers | |
| CN109299952A (en) | It is a kind of to realize the interrelated system and method transferred of a variety of codeword values | |
| CN110096643A (en) | The latent objective label library generating method of product and device | |
| CN113837824A (en) | Information pushing method and system | |
| CN115712684B (en) | Storage method and system for dynamic information of articles in Internet of things | |
| CN116821532A (en) | Template-based WEB page element positioning method, device, equipment and storage medium | |
| CN115860820A (en) | Intelligent encryption putting and destroying method and device for electronic coupons | |
| CN113392294B (en) | Sample labeling method and device | |
| CN109144999A (en) | A kind of data positioning method, device and storage medium, program product | |
| CN114387021A (en) | Service state generation method, device, equipment and storage medium | |
| CN114064615A (en) | Data operation and maintenance system and method | |
| CN102034069A (en) | RFID-based tag identification method and system | |
| US20160004783A1 (en) | Automated generation of web site entry pages |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |