CN112907282A - Architecture application method based on global e-commerce industry advertisement DMP - Google Patents
Architecture application method based on global e-commerce industry advertisement DMP Download PDFInfo
- Publication number
- CN112907282A CN112907282A CN202110160951.5A CN202110160951A CN112907282A CN 112907282 A CN112907282 A CN 112907282A CN 202110160951 A CN202110160951 A CN 202110160951A CN 112907282 A CN112907282 A CN 112907282A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- dmp
- global
- user data
- 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
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
Abstract
The invention discloses a framework application method based on a global e-commerce industry advertisement DMP, which comprises the following steps: acquiring user data; preprocessing user data; analyzing the preprocessed user data to obtain label information corresponding to each user; inputting a seed user; performing label selection according to the input seed user to obtain a directional releasing user; judging whether the number of the directional releasing users reaches an expected value or not; and carrying out crowd expansion when the expected value is not reached. The architecture application method based on the global e-commerce industry advertisement DMP can abstract scattered data into tags to form tag information, so that the characteristics of the data are grasped. Therefore, by deeply mining the label information, a multi-dimensional, multi-level and multi-aspect user label system can be established, and further the coverage rate and the accuracy of the targeted advertisement delivery are high.
Description
Technical Field
The invention relates to an architecture application method based on a global e-commerce industry advertisement DMP.
Background
With the development of big data technology, more and more enterprises realize the importance of data, establish CRM, create user figures, and perform more personalized operation on core users. But the promotion of the advertising marketing and the conversion rate of new users is little helped by the data of own users, and the rationality of the advertising targeting is an important factor influencing the advertising effect. The existing DMP-based advertisement targeted delivery cannot achieve high coverage rate and high accuracy.
Disclosure of Invention
The invention provides a framework application method based on a global e-commerce industry advertisement DMP, which adopts the following technical scheme:
an architecture application method based on global e-commerce industry advertisement DMP comprises the following steps:
acquiring user data;
preprocessing user data;
analyzing the preprocessed user data to obtain label information corresponding to each user;
inputting a seed user;
performing label selection according to the input seed user to obtain a directional releasing user;
judging whether the number of the directional releasing users reaches an expected value or not;
and carrying out crowd expansion when the expected value is not reached.
Furthermore, the mobile phone number is used as a unique value for distinguishing the user, data corresponding to the same mobile phone number in the user data is used as information of one user to be analyzed, and the obtained analysis result is counted under the mobile phone number.
And further, analyzing the preprocessed user data according to a pre-established label system.
Further, the label system: the system comprises a user attribute module, a user behavior module, a marketing attribute module, a consumption attribute module, a preference subdivision module and a user clustering module;
and dividing the obtained label information into six statistical tables according to a user attribute module, a user behavior module, a marketing attribute module, a consumption attribute module, a preference subdivision module and a user grouping module, wherein the statistical tables are stored in an incremental column manner.
Further, the tag information includes: a base label and a derivative label of a different dimension that is similar to the base label.
Further, the tag information also contains a preference tag.
Further, the specific method for crowd expansion when the expected value is not reached is as follows:
and carrying out crowd expansion through a lookelike algorithm.
Further, preprocessing the user data includes:
and carrying out data cleaning on the user data.
Further, preprocessing the user data further comprises:
sensitive data elimination is carried out on user data;
the specific method for eliminating the data of the user data comprises the following steps:
setting a sensitive keyword;
and eliminating data containing sensitive keywords in the user data.
Further, the user data includes order data, question and answer data, and recommendation data in the e-commerce field.
The invention has the advantages that the provided architecture application method based on the global e-commerce industry advertisement DMP can abstract scattered data into tags to form tag information, so that the characteristics of the data can be grasped. Therefore, by deeply mining the label information, a multi-dimensional, multi-level and multi-aspect user label system can be established, and further the coverage rate and the accuracy of the targeted advertisement delivery are high.
Drawings
FIG. 1 is a schematic diagram of the architecture application method of the DMP based on the global e-commerce industry advertisement.
Detailed Description
The invention is described in detail below with reference to the figures and the embodiments.
As shown in fig. 1, the present invention discloses a method for applying architecture based on global business advertisement DMP, which comprises the following steps: acquiring user data; preprocessing user data; analyzing the preprocessed user data to obtain label information corresponding to each user; inputting a seed user; performing label selection according to the input seed user to obtain a directional releasing user; judging whether the number of the directional releasing users reaches an expected value or not; and carrying out crowd expansion when the expected value is not reached.
The step of acquiring the user data refers to collecting all user data in the universal e-commerce business data platform. Preprocessing the user data refers to analyzing the collected user data and calculating the meaning of each field. And analyzing the preprocessed user data to obtain the label information corresponding to each user, namely setting one label information for the user data according to the meaning of the field of each user data. And then inputting a seed user, and performing label selection according to the input seed user, namely finding all label information related to the seed user and user data corresponding to the label information, so as to obtain a targeted delivery user and realize accurate and high-coverage advertisement delivery. And after the directional releasing users are obtained, judging whether the number of the directional releasing users reaches an expected value. And when the number of the targeted users does not reach the expected value, the crowd extension can be carried out, so that the high coverage rate of the targeted advertisement delivery is ensured.
In the scheme, the DMP fuses the scattered first, second and third party data, and establishes a multi-dimensional, multi-level and multi-aspect user label system through data mining means such as statistics, rules, algorithms and the like.
The architecture application method based on the global e-commerce industry advertisement DMP can abstract scattered data into tags to form tag information, so that the characteristics of the data are grasped. Therefore, by deeply mining the label information, a multi-dimensional, multi-level and multi-aspect user label system can be established, and further the coverage rate and the accuracy of the targeted advertisement delivery are high.
As a preferred embodiment, the mobile phone number is used as a unique value for distinguishing the user, the data corresponding to the same mobile phone number in the user data is used as information of one user to be analyzed, and the obtained analysis result is counted under the mobile phone number, so that the user data of the user corresponding to each mobile phone number is comprehensively and accurately collected.
As a preferred embodiment, the preprocessed user data is analyzed according to a pre-established label system. Firstly, a label system is built, and the label system contains a plurality of label information. After the user data is preprocessed, field meanings are obtained, the label system finds out label information corresponding to the field meanings of the user data according to the field meanings of the user data, and the label information is bound with the user data.
Further, the label system: the system comprises a user attribute module, a user behavior module, a marketing attribute module, a consumption attribute module, a preference subdivision module and a user clustering module. Dividing the obtained label information according to a user attribute module, a user behavior module, a marketing attribute module, a consumption attribute module, a preference subdivision module and a user grouping module, and outputting six statistical tables corresponding to the six modules, wherein the statistical tables are stored in an incremental column manner. By the method, a multi-dimensional, multi-level and multi-aspect user label system can be established, more refined division is realized, and efficient touch is achieved.
Further, the tag information further includes: a base label and a derivative label of a different dimension that is similar to the base label. This allows the label information to have multiple dimensions, thereby enabling the coverage of ad targeting to be extended. For example, the base tag relates to true age and gender, and the extension tag can be used to derive the merchandise gender and the merchandise age from the base tag.
In addition, the tag information also contains a preference tag. Calculating the label weight of the label information of the user data through a tfidf algorithm, and performing preference sorting according to the label weight to obtain a preference label of the user data, for example: category preference, brand preference, new product preference, keyword extraction, and the like. By the mode, the target for the targeted advertisement delivery can be more accurate.
As a preferred implementation mode, the specific method for crowd expansion when the expected value is not reached is to carry out crowd expansion through a lookelike algorithm. And (3) using the trade name as an LDA theme model, and then performing the lookelike expansion to obtain the user for directional delivery. The expanded users have higher similarity and higher accuracy than the users expanded by the artificial experience group pulling.
As a preferred embodiment, the preprocessing of the user data comprises: and carrying out data cleaning on the user data.
As a preferred embodiment, the preprocessing the user data further comprises: and performing sensitive data elimination on the user data. The specific method for eliminating the data of the user data comprises the following steps: setting sensitive keywords, and then removing data containing the sensitive keywords in the user data.
In a preferred embodiment, the user data includes order data, question and answer data, and recommendation data in the e-commerce domain.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It should be understood by those skilled in the art that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by using equivalent alternatives or equivalent variations fall within the scope of the present invention.
Claims (10)
1. An architecture application method based on a global e-commerce industry advertisement DMP is characterized by comprising the following steps:
acquiring user data;
preprocessing the user data;
analyzing the preprocessed user data to obtain label information corresponding to each user;
inputting a seed user;
performing label selection according to the input seed user to obtain a directional releasing user;
judging whether the number of the directional releasing users reaches an expected value;
and carrying out crowd expansion when the expected value is not reached.
2. The architecture application method based on the DMP of the global e-commerce industry advertisement of claim 1,
and taking the mobile phone number as a unique value for distinguishing the users, analyzing the data corresponding to the same mobile phone number in the user data as the information of one user, and counting the obtained analysis result under the mobile phone number.
3. The architecture application method based on the DMP of the global e-commerce industry advertisement (DMP) as claimed in claim 1, wherein the preprocessed user data is analyzed according to a pre-established label system.
4. The architecture application method based on the DMP of the global e-commerce industry advertisement of claim 3,
the label system comprises: the system comprises a user attribute module, a user behavior module, a marketing attribute module, a consumption attribute module, a preference subdivision module and a user clustering module;
dividing the obtained label information into six statistical tables according to the user attribute module, the user behavior module, the marketing attribute module, the consumption attribute module, the preference subdivision module and the user grouping module, wherein the statistical tables are stored in an increment column.
5. The architecture application method of claim 3, wherein the tag information comprises: a base label and a derivative label of a different dimension that is similar to the base label.
6. The method as claimed in claim 5, wherein the architecture of the global e-commerce industry advertisement MP is applied,
the tag information also includes a preference tag.
7. The architecture application method based on the DMP of the global e-commerce industry, as claimed in claim 1, wherein the specific method for crowd extension when the expected value is not reached is:
and carrying out crowd expansion through a lookelike algorithm.
8. The architecture application method based on the DMP of the global e-commerce industry advertisement of claim 1,
the preprocessing the user data comprises:
and performing data cleaning on the user data.
9. The architecture application method based on the DMP of the global e-commerce industry advertisement of claim 8,
the preprocessing the user data further comprises:
sensitive data elimination is carried out on the user data;
the specific method for removing the user data comprises the following steps:
setting a sensitive keyword;
and eliminating the data containing the sensitive keywords in the user data.
10. The architecture application method based on the DMP of the global e-commerce industry advertisement of claim 1,
the user data comprises order data, question and answer data and recommendation data in the E-commerce field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110160951.5A CN112907282A (en) | 2021-02-05 | 2021-02-05 | Architecture application method based on global e-commerce industry advertisement DMP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110160951.5A CN112907282A (en) | 2021-02-05 | 2021-02-05 | Architecture application method based on global e-commerce industry advertisement DMP |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112907282A true CN112907282A (en) | 2021-06-04 |
Family
ID=76122856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110160951.5A Pending CN112907282A (en) | 2021-02-05 | 2021-02-05 | Architecture application method based on global e-commerce industry advertisement DMP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907282A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536131A (en) * | 2021-07-27 | 2021-10-22 | 拉扎斯网络科技（上海）有限公司 | Data processing method and device, storage medium and electronic equipment |
-
2021
- 2021-02-05 CN CN202110160951.5A patent/CN112907282A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536131A (en) * | 2021-07-27 | 2021-10-22 | 拉扎斯网络科技（上海）有限公司 | Data processing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
| CN108537578A (en) | Advertisement sending method based on big data and device | |
| CN100504866C (en) | Integrative searching result sequencing system and method | |
| CN106570718B (en) | Information delivery method and delivery system | |
| CN106997549A (en) | The method for pushing and system of a kind of advertising message | |
| CN107291755B (en) | Terminal pushing method and device | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| CN105095187A (en) | Search intention identification method and device | |
| CN105023165A (en) | Method, device and system for controlling release tasks in social networking platform | |
| CN106294500B (en) | Content item pushing method, device and system | |
| CN107205042B (en) | Accurate information pushing method and system | |
| US11314831B2 (en) | Allocating communication resources via information technology infrastructure | |
| CN111008333B (en) | Shopping system and method based on user characteristic information and product component information | |
| JP5577385B2 (en) | Content distribution device | |
| CN111489201A (en) | Method, device and storage medium for analyzing customer value | |
| CN103838754A (en) | Information searching device and method | |
| CN107992500A (en) | A kind of information processing method and server | |
| CN115098650B (en) | Comment information analysis method based on historical data model and related device | |
| CN110955690A (en) | Self-service data labeling platform and self-service data labeling method based on big data technology | |
| CN115496523A (en) | Advertisement publishing method, computer readable storage medium and electronic device | |
| CN112907282A (en) | Architecture application method based on global e-commerce industry advertisement DMP | |
| CN110969473B (en) | User tag generation method and device | |
| CN114119068A (en) | Intelligent analysis method and management platform for pharmacy enterprise WeChat customer group | |
| CN108959289B (en) | Website category acquisition method and device | |
| CN104778205A (en) | Heterogeneous information network-based mobile application ordering and clustering method |
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 |