CN112632149A - Potential user mining method based on network data analysis - Google Patents
Potential user mining method based on network data analysis Download PDFInfo
- Publication number
- CN112632149A CN112632149A CN202011550478.3A CN202011550478A CN112632149A CN 112632149 A CN112632149 A CN 112632149A CN 202011550478 A CN202011550478 A CN 202011550478A CN 112632149 A CN112632149 A CN 112632149A
- Authority
- CN
- China
- Prior art keywords
- information
- internet
- user
- users
- potential
- 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
- 238000005065 mining Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007405 data analysis Methods 0.000 title claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 230000006399 behavior Effects 0.000 claims description 64
- 238000007670 refining Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 16
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 2
- 230000007774 longterm Effects 0.000 claims description 2
- 238000009412 basement excavation Methods 0.000 abstract description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010354 integration Effects 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
- 230000009466 transformation Effects 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
- G06F16/20—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
- 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
- G06F16/9532—Query formulation
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9566—URL specific, e.g. using aliases, detecting broken or misspelled links
-
- 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
- G06Q30/0256—User search
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a potential user mining method based on network data analysis, which comprises the following steps: and (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of the potential users according to the summarized existing user characteristic information and the detailed labels thereof, and according to the principle of a crowd analysis method; the invention excavates information of one hand through a plurality of channels such as the social network of the existing user, the characteristic label information, the big data search company and the like, has wide range of information acquisition, integrates the information, can improve the excavation quality by utilizing the summarized characteristic matching degree when potential users excavate, and enhances the success rate.
Description
Technical Field
The invention relates to the technical field of user mining, in particular to a potential user mining method based on network data analysis.
Background
With the continuous development of networks and the continuous updating of marketing means, mail marketing and short message marketing become a new hot marketing mode and are widely applied at home and abroad. The marketing means takes e-mails and short messages as professional marketing tools, and sends product information, promotion information and the like of enterprises to target users, so that rapid and efficient communication with the users is realized.
With the technical progress, a potential user mining method based on network data analysis also starts to appear, but at present, information is mostly purchased from the same company or an information service company, the information is mostly used by the same enterprise for many times, the value is low, the obtained channels are few or the channels are not integrated, and the phenomena of repeated mining and omission easily occur.
Disclosure of Invention
The invention aims to provide a potential user mining method based on network data analysis, which solves the problems that most information is purchased from the same company or an information service company at present, most of the information is used by the same enterprise for many times by multiple hands, the value is lower, the obtained channels are few or the channels are lack of integration, and the phenomena of repeated mining and omission easily occur.
In order to achieve the purpose, the invention provides the following technical scheme: a potential user mining method based on network data analysis comprises the following steps:
step 1: and (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user;
step 2: advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users;
and step 3: extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs;
and 4, step 4: mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Preferably, in step 1, the detailed information of the existing users is summarized and the detailed tags of the existing users are determined according to the information filled by the existing users and the internet behaviors of the existing users.
Preferably, in step 1, the information such as gender ratio, age distribution, hobby distribution, occupation distribution, residence information distribution, relationship network distribution, and the like of the existing user is summarized and judged in cooperation with a company related to big data.
Preferably, in the step 2, according to the reason of the class of things, friends and friends of the existing user can have long-term interaction with the existing user, and often have similar characteristic information and detailed labels to the existing user, and have the traits of potential users.
Preferably, in step 2, the internet actor information promoted by the non-directional advertisement is added into the advertisement promotion library in real time, and is matched with the information library to be promoted of the internet advertisement alliance in time, and the repeated information in the information library to be promoted is deleted after the repeated information is found.
Preferably, in step 2, the promotion information of the non-targeted advertisement promotion and the targeted advertisement promotion is different, and the promotion is performed according to the characteristics of the promotion object.
Preferably, in step 3, extracting feature information from the search behavior information includes: performing word segmentation processing on the search keywords, counting the search keywords with the same word segmentation result, and performing behavior analysis on the search keywords with the same word segmentation result to generate keyword characteristics; acquiring a URL address related to an enterprise product from the clicked URL address, and analyzing the URL address according to the website access flow and the theme correlation degree to generate URL characteristics; performing word segmentation on the theme of the clicked URL address, performing keyword extraction on the theme of the clicked URL address after word segmentation, and performing behavior analysis on an extraction result to generate the theme characteristics of the URL.
Preferably, in step 3, the potential user mining model is obtained by pre-training through the following steps: obtaining sample searching behavior information of a sample user; preprocessing the sample searching behavior information according to a preset format; performing feature extraction on the preprocessed sample searching behavior information to obtain sample feature information in the sample searching behavior information; and based on a machine learning algorithm, performing model training according to the sample characteristic information to obtain a potential user mining model.
Compared with the prior art, the invention has the beneficial effects that: the invention excavates information of one hand through a plurality of channels such as the social network of the existing user, the characteristic label information, the big data search company and the like, has wide range of information acquisition, integrates the information, can improve the excavation quality by utilizing the summarized characteristic matching degree when potential users excavate, and enhances the success rate.
Detailed Description
The present invention will now be described in more detail by way of examples, which are given by way of illustration only and are not intended to limit the scope of the present invention in any way.
The invention provides a technical scheme that: a potential user mining method based on network data analysis comprises the following steps:
step 1: and (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user;
step 2: advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users;
and step 3: extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs;
and 4, step 4: mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
The first embodiment is as follows:
and (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Example two:
in the first embodiment, the following steps are added:
in the step 1, the detailed information of the existing user is summarized through the information filled by the existing user and the internet behavior of the existing user, the detailed label of the existing user is determined, the detailed label cooperates with a big data related company, and the information such as sex ratio, age stage distribution, hobby distribution ratio, occupation distribution ratio, living information distribution, relationship network distribution and the like of the existing user is summarized and judged, so that the mining accuracy is improved.
And (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Example three:
in the second embodiment, the following steps are added:
in step 2, according to the reason of the class of things, friends of the existing user can interact with the existing user for a long time, and often have similar characteristic information and detailed labels with the existing user, so that the potential user has the characteristics of the potential user, and the success rate of the transformation of the potential user can be accelerated.
And (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Example four:
in the third embodiment, the following steps are added:
in step 2, the internet actor information promoted by the non-directional advertisement is added into the advertisement promotion library in real time and is matched with the information library to be promoted of the internet advertisement alliance in time, repeated information in the information library to be promoted is deleted after the repeated information is found, and the phenomenon of repeated promotion is avoided.
And (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Example five:
in the fourth example, the following steps were added:
in step 2, the popularization information of the non-directional advertisement popularization and the popularization information of the directional advertisement popularization are different, and the popularization is carried out according to the characteristics of popularization objects, so that the pertinence of popularization contents is enhanced.
And (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Example six:
in the fifth example, the following steps were added:
in step 3, extracting feature information in the search behavior information, including: performing word segmentation processing on the search keywords, counting the search keywords with the same word segmentation result, and performing behavior analysis on the search keywords with the same word segmentation result to generate keyword characteristics; acquiring a URL address related to an enterprise product from the clicked URL address, and analyzing the URL address according to the website access flow and the theme correlation degree to generate URL characteristics; the method comprises the steps of carrying out word segmentation on the theme of the clicked URL address, carrying out keyword extraction on the theme of the clicked URL address after word segmentation, and carrying out behavior analysis on the extracted result to generate the theme characteristics of the URL, so that the mining efficiency is improved, and the success rate is enhanced.
And (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Example seven:
in example six, the following steps were added:
in step 3, the potential user mining model is obtained by training in advance through the following steps: obtaining sample searching behavior information of a sample user; preprocessing the sample searching behavior information according to a preset format; performing feature extraction on the preprocessed sample searching behavior information to obtain sample feature information in the sample searching behavior information; based on a machine learning algorithm, model training is carried out according to sample characteristic information to obtain a potential user mining model, so that mining is facilitated, and mining efficiency is ensured.
And (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user; advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users; extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs; mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A potential user mining method based on network data analysis is characterized in that: the method comprises the following steps:
step 1: and (3) summarizing preliminary information: collecting detailed information of the existing user, including information such as sex, age, hobbies, family address, mobile phone number, relationship circle and the like, using internet big data to collect and analyze related information, summarizing characteristic information of the existing user, and determining a detailed label of the existing user;
step 2: advertisement promotion: determining the characteristic information and the detailed labels of potential users according to the summarized characteristic information and the detailed labels of the existing users, bringing friends in a circle of friends of the existing users into a list of the potential users according to the principle of a crowd analysis method, cooperating with an internet advertising alliance, carrying out non-directional advertising promotion on internet actors with the same characteristic information and the detailed labels by utilizing big data, and carrying out directional advertising promotion on friends in the circle of friends of the existing users;
and step 3: extracting information: the method comprises the steps of cooperating with each Internet search company, obtaining search behavior information of Internet agents, and extracting feature information in the search behavior information, wherein the search behavior information comprises search keywords, search time, URL clicking addresses and the subjects of the URL clicking addresses, and the feature information at least comprises keyword features, URL features and the subject features of URLs;
and 4, step 4: mining users: predicting the characteristic information according to a potential user mining model obtained through pre-training, existing user characteristic information and a refining label thereof, judging whether the internet actor is a potential user, if so, determining the refining label of the internet actor according to the searching behavior information, and adding a potential user list to the internet actor and the refining label thereof.
2. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in the step 1, the detailed information of the existing user is summarized and the detailed label of the existing user is determined through the information filled by the existing user and the internet behavior of the existing user.
3. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in the step 1, the users are cooperated with companies related to big data to summarize and judge the sex ratio, age stage distribution, hobby distribution ratio, occupation distribution ratio, residence information distribution, relationship network distribution and other information of the existing users.
4. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in the step 2, according to the reason of the class of things, friends of the existing user can have long-term interaction with the existing user, and often have similar characteristic information and detailed labels as the existing user, so that the existing user has the characteristics of potential users.
5. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in step 2, the internet actor information promoted by the non-directional advertisement is added into the advertisement promotion library in real time, and is matched with the information library to be promoted of the internet advertisement alliance in time, and the repeated information in the information library to be promoted is deleted after the repeated information is found.
6. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in step 2, the promotion information of the non-directional advertisement promotion and the directional advertisement promotion is different, and the promotion is carried out according to the characteristics of the promotion object.
7. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in step 3, extracting feature information in the search behavior information includes: performing word segmentation processing on the search keywords, counting the search keywords with the same word segmentation result, and performing behavior analysis on the search keywords with the same word segmentation result to generate keyword characteristics; acquiring a URL address related to an enterprise product from the clicked URL address, and analyzing the URL address according to the website access flow and the theme correlation degree to generate URL characteristics; performing word segmentation on the theme of the clicked URL address, performing keyword extraction on the theme of the clicked URL address after word segmentation, and performing behavior analysis on an extraction result to generate the theme characteristics of the URL.
8. The method of claim 1, wherein the potential users are mined based on network data analysis, and the method comprises the following steps: in step 3, the potential user mining model is obtained by pre-training through the following steps: obtaining sample searching behavior information of a sample user; preprocessing the sample searching behavior information according to a preset format; performing feature extraction on the preprocessed sample searching behavior information to obtain sample feature information in the sample searching behavior information; and based on a machine learning algorithm, performing model training according to the sample characteristic information to obtain a potential user mining model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011550478.3A CN112632149A (en) | 2020-12-24 | 2020-12-24 | Potential user mining method based on network data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011550478.3A CN112632149A (en) | 2020-12-24 | 2020-12-24 | Potential user mining method based on network data analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112632149A true CN112632149A (en) | 2021-04-09 |
Family
ID=75324343
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011550478.3A Pending CN112632149A (en) | 2020-12-24 | 2020-12-24 | Potential user mining method based on network data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112632149A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846053A (en) * | 2017-01-19 | 2017-06-13 | 腾讯科技(深圳)有限公司 | A kind of recommendation method and device of the page advertisement that is polymerized |
CN106846061A (en) * | 2017-01-25 | 2017-06-13 | 百度在线网络技术(北京)有限公司 | Potential user's method for digging and device |
CN107464141A (en) * | 2017-08-07 | 2017-12-12 | 北京京东尚科信息技术有限公司 | For the method, apparatus of information popularization, electronic equipment and computer-readable medium |
CN108763252A (en) * | 2018-04-02 | 2018-11-06 | 携程旅游信息技术(上海)有限公司 | Information-pushing method and its system, storage medium, the electronic equipment of public platform |
CN109034983A (en) * | 2018-09-18 | 2018-12-18 | 安徽千界信息科技有限公司 | The recommended method and its system of online shopping mall's commodity |
CN110399562A (en) * | 2019-07-31 | 2019-11-01 | 广州市百果园信息技术有限公司 | For the device for displaying information of social application, method, displaying terminal and medium |
CN111914172A (en) * | 2020-07-29 | 2020-11-10 | 上海梅斯医药科技有限公司 | Medical information recommendation method and system based on user tags |
-
2020
- 2020-12-24 CN CN202011550478.3A patent/CN112632149A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846053A (en) * | 2017-01-19 | 2017-06-13 | 腾讯科技(深圳)有限公司 | A kind of recommendation method and device of the page advertisement that is polymerized |
CN106846061A (en) * | 2017-01-25 | 2017-06-13 | 百度在线网络技术(北京)有限公司 | Potential user's method for digging and device |
CN107464141A (en) * | 2017-08-07 | 2017-12-12 | 北京京东尚科信息技术有限公司 | For the method, apparatus of information popularization, electronic equipment and computer-readable medium |
CN108763252A (en) * | 2018-04-02 | 2018-11-06 | 携程旅游信息技术(上海)有限公司 | Information-pushing method and its system, storage medium, the electronic equipment of public platform |
CN109034983A (en) * | 2018-09-18 | 2018-12-18 | 安徽千界信息科技有限公司 | The recommended method and its system of online shopping mall's commodity |
CN110399562A (en) * | 2019-07-31 | 2019-11-01 | 广州市百果园信息技术有限公司 | For the device for displaying information of social application, method, displaying terminal and medium |
CN111914172A (en) * | 2020-07-29 | 2020-11-10 | 上海梅斯医药科技有限公司 | Medical information recommendation method and system based on user tags |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537578A (en) | Advertisement sending method based on big data and device | |
CN108021929B (en) | Big data-based mobile terminal e-commerce user portrait establishing and analyzing method and system | |
CN106156127B (en) | Method and device for selecting data content to push to terminal | |
CN106296059B (en) | Method and equipment for determining delivery network points | |
CN109978630A (en) | A kind of Precision Marketing Method and system for establishing user's portrait based on big data | |
CN111178970B (en) | Advertisement putting method and device, electronic equipment and computer readable storage medium | |
CN107862553A (en) | Advertisement real-time recommendation method, device, terminal device and storage medium | |
CN106919625B (en) | Internet user attribute identification method and device | |
CN108205766A (en) | Information-pushing method, apparatus and system | |
CN108154425B (en) | Offline merchant recommendation method combining social network and location | |
JP2013525921A (en) | Method, system, and apparatus for query based on vertical search | |
CN106156251A (en) | A kind of wechat information classification method for pushing and system | |
CN103886074A (en) | Commodity recommendation system based on social media | |
CN104615608A (en) | Data mining processing system and method | |
CN104751354B (en) | A kind of advertisement crowd screening technique | |
CN105160545A (en) | Delivered information pattern determination method and device | |
WO2017071179A1 (en) | Method and apparatus for recognizing user behaviour object based on flow analysis | |
TW201401088A (en) | Search method and apparatus | |
CN111612503A (en) | Advertisement pushing method and device based on external page delivery touch user information and electronic equipment | |
CN110597987A (en) | Search recommendation method and device | |
KR100792700B1 (en) | Method for targeting web advertisement clickers based on click pattern by using a collaborative filtering system with neural networks and system thereof | |
CN105447193A (en) | Music recommending system based on machine learning and collaborative filtering | |
WO2017087548A1 (en) | Identifying social business characteristic user | |
CN108304570B (en) | Processing method and display method of search results, server and client | |
CN114092144A (en) | Advertisement pushing method and system based on big data internet platform |
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 |