CN114066506A - AI analysis algorithm for network behavior - Google Patents
AI analysis algorithm for network behavior Download PDFInfo
- Publication number
- CN114066506A CN114066506A CN202111281159.1A CN202111281159A CN114066506A CN 114066506 A CN114066506 A CN 114066506A CN 202111281159 A CN202111281159 A CN 202111281159A CN 114066506 A CN114066506 A CN 114066506A
- Authority
- CN
- China
- Prior art keywords
- user
- analysis
- module
- behavior
- result
- 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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q30/0253—During e-commerce, i.e. online transactions
-
- 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
- G06Q30/0277—Online advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Abstract
The invention discloses a network behavior AI analysis algorithm, which comprises the following analysis steps: s1, acquiring a user IP, acquiring the user IP and port information by retrieving user login information, and recording user information; s2, analyzing user positioning; s3, predicting user behavior; s4, identifying a user behavior result; s5, outputting the analysis result and recommending the corresponding service again; and S6, repeating self-learning, wherein the behavior result analysis system compares the analysis data with self-learning and compares the analysis data with self-learning by the self-learning and repeating system. According to the invention, the user is fully positioned first, the user behavior result is analyzed and compared, and the user behavior prediction system is self-learned and updated, so that the accuracy of user behavior analysis and simulation portrayal can be greatly improved, the pushed services are more matched, the online service transaction rate is effectively improved, the network resources are fully utilized, and the online profit range is improved.
Description
Technical Field
The invention relates to the technical field related to network behavior analysis, in particular to an AI analysis algorithm of network behaviors.
Background
The network behavior refers to the operation behavior of the internet user on the network, wherein for the current online transaction, the deep analysis of the network behavior of the user is very important, and the method plays a very important role in improving the business transaction rate.
The prior network behavior analysis technology or algorithm can only perform portrayal analysis on user browsing data so as to simulate user requirements to promote business, and the analysis result is often different from the actual requirements greatly, so that the users are difficult to generate online dependence and loyalty, the online business transaction rate is general, the network resources are not sufficiently utilized, and the effective value-added business is difficult to generate. In view of this, the present document proposes an AI analysis algorithm for network behavior.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an AI analysis algorithm for network behavior.
In order to achieve the purpose, the invention adopts the following technical scheme:
the AI analysis algorithm of the network behavior comprises the following analysis steps:
s1, acquiring a user IP, acquiring the user IP and port information by retrieving user login information, and recording user information;
s2, analyzing user positioning, analyzing and depicting user identity by combining big data flow through a user positioning analysis system, and analyzing user preference;
s3, predicting user behaviors, simulating and depicting user requirements through a user behavior prediction system, and pushing corresponding services at the same time to improve service transaction rate;
s4, recognizing the user behavior result, analyzing the user behavior result data by collecting transaction detailed information data, and recording the result information;
s5, outputting the analysis result and recommending the corresponding service again, judging whether the analysis of the user behavior prediction system is accurate or not through the behavior result analysis system, outputting the final result, and simultaneously popularizing the related service;
and S6, repeating self-learning, wherein the behavior result analysis system compares the comparative analysis data with the self-learning and comparison system, and the comparative information is input into the user behavior prediction system to improve the prediction accuracy.
Preferably, the user location analysis system used in step S2 includes a search query analysis module, a habit data analysis module, and a user representation generation simulation module.
Preferably, the user behavior prediction system used in step S3 includes an association analysis module, a user demand characteristic prediction module, a TOP-N analysis module and a traffic guidance module.
Preferably, the self-learning copy-and-copy system used in step S6 includes an input module, a comparison module, a self-updating module, a database, and an output module.
Preferably, in step S1, the DNS access statistics data collection technology may be used to identify, collect and record the user information, and number and record the user information.
Preferably, the T0P-N analysis module is used for analyzing and comparing a plurality of user behavior result data, and ranking the data in order to analyze user characteristics in depth.
The invention has the following beneficial effects:
by arranging the user positioning analysis system, the user behavior prediction system, the behavior result analysis system and the self-learning repeated engraving system, the user can be sufficiently positioned firstly, then the user image is simulated and engraved, meanwhile, the user behavior results are analyzed and compared, and the self-learning updating is carried out on the user behavior prediction system, so that the accuracy of user behavior analysis and simulated engraving can be greatly improved, meanwhile, the push services are more matched, the online service transaction rate is effectively improved, the network resources are fully utilized, and the online profit margin is improved.
Drawings
FIG. 1 is a schematic diagram of an algorithm flow of an AI analysis algorithm for network behavior according to the present invention;
FIG. 2 is a block diagram of a system structure of a user positioning analysis system in the AI analysis algorithm of network behavior according to the present invention;
FIG. 3 is a block diagram of a system structure of a user behavior prediction system in the AI analysis algorithm of network behaviors proposed in the present invention;
fig. 4 is a system structural block diagram of a self-learning copy system in the AI analysis algorithm for network behavior according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1, the AI analysis algorithm for network behavior includes the following analysis steps:
s1, acquiring a user IP, acquiring the user IP and port information by retrieving user login information, and recording user information; in step S1, a DNS access statistics data collection technique may be used to perform identification collection and recording on the user information, and to record the number of the user information.
S2, analyzing user positioning, analyzing and depicting user identity by combining big data flow through a user positioning analysis system, and analyzing user preference; referring to fig. 2, the user location analysis system used in step S2 includes a search query analysis module, a habit data analysis module, and a user representation generation simulation module. Specifically, the search query analysis module is used for analyzing search query information of a user on the network, and the habit data analysis module is used for recording and analyzing browsing traces of the user on the network, so that a specific user network requirement image can be generated through the user portrait generation simulation module, user information is enriched, and the user identity is correspondingly positioned.
S3, predicting user behaviors, simulating and depicting user requirements through a user behavior prediction system, and pushing corresponding services at the same time to improve service transaction rate; referring to fig. 3, the user behavior prediction system used in step S3 includes an association analysis module, a user demand characteristic prediction module, a TOP-N analysis module, and a traffic guidance module. The T0P-N analysis module is used for analyzing and comparing a plurality of user behavior result data and ranking the data according to the sequence so as to deeply analyze the characteristics of the user. Specifically, the association analysis module is used for performing association analysis on part of user behaviors to simulate and depict specific user requirements, the user requirement characteristic prediction module is used for predicting characteristics of user requirements after analyzing the user behaviors, and the service guide module is used for performing contact and guide on corresponding services according to the predicted user requirement characteristics after predicting the characteristics of the user requirements, formulating corresponding tariff strategies and promoting related value-added services.
S4, recognizing the user behavior result, analyzing the user behavior result data by collecting transaction detailed information data, and recording the result information;
s5, outputting the analysis result and recommending the corresponding service again, judging whether the analysis of the user behavior prediction system is accurate or not through the behavior result analysis system, outputting the final result, and simultaneously popularizing the related service; by setting the result behavior analysis system, the user behavior prediction system can be judged and corrected by recording and analyzing the user behavior result data.
And S6, repeating self-learning, wherein the behavior result analysis system compares the comparative analysis data with the self-learning and comparison system, and the comparative information is input into the user behavior prediction system to improve the prediction accuracy. Referring to fig. 4, the self-learning copy-and-copy system used in step S6 includes an input module, a comparison module, a self-updating module, a database, and an output module. Specifically, the database is used for storing result data analyzed by the behavior result analysis system and actual behavior result data; the input module is used for inputting the data judged by the behavior result analysis system into the self-learning repeated engraving system, the comparison module is used for analyzing and comparing the input data with an actual result and inputting the comparison result data into the database; the self-updating module is used for analyzing and recording the correct analysis result and the error analysis result, and feeding the results back to the user prediction system through the output module so as to guide the user behavior prediction system to carry out correct direction prediction, thereby improving the accuracy of next prediction. The invention can carry out self-learning updating on the user behavior prediction system, thereby greatly improving the accuracy of analyzing and simulating the user behavior, simultaneously leading the pushed service to be more matched and effectively improving the online service transaction rate, fully utilizing network resources and improving the online profit margin.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (6)
1. The AI analysis algorithm of the network behavior is characterized by comprising the following analysis steps:
s1, acquiring a user IP, acquiring the user IP and port information by retrieving user login information, and recording user information;
s2, analyzing user positioning, analyzing and depicting user identity by combining big data flow through a user positioning analysis system, and analyzing user preference;
s3, predicting user behaviors, simulating and depicting user requirements through a user behavior prediction system, and pushing corresponding services at the same time to improve service transaction rate;
s4, recognizing the user behavior result, analyzing the user behavior result data by collecting transaction detailed information data, and recording the result information;
s5, outputting the analysis result and recommending the corresponding service again, judging whether the analysis of the user behavior prediction system is accurate or not through the behavior result analysis system, outputting the final result, and simultaneously popularizing the related service;
and S6, repeating self-learning, wherein the behavior result analysis system compares the comparative analysis data with the self-learning and comparison system, and the comparative information is input into the user behavior prediction system to improve the prediction accuracy.
2. The AI analysis algorithm according to claim 1, wherein the user location analysis system used in step S2 includes a search query analysis module, a habit data analysis module, and a user image generation simulation module.
3. The AI analysis algorithm according to claim 1, wherein the user behavior prediction system used in step S3 includes an association analysis module, a user demand characteristic prediction module, a TOP-N analysis module, and a traffic guidance module.
4. The AI analysis algorithm according to claim 1, wherein the self-learning replication system used in step S6 includes an input module, a comparison module, a self-updating module, a database, and an output module.
5. The AI analysis algorithm according to claim 1, wherein in step S1, the DNS access statistics data collection technique is used to collect and record identification of the user information, and the user information is numbered.
6. The AI analysis algorithm according to claim 3, wherein the T0P-N analysis module is configured to analyze and compare a plurality of user behavior result data and rank the data in order to analyze user characteristics in depth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111281159.1A CN114066506A (en) | 2021-11-01 | 2021-11-01 | AI analysis algorithm for network behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111281159.1A CN114066506A (en) | 2021-11-01 | 2021-11-01 | AI analysis algorithm for network behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114066506A true CN114066506A (en) | 2022-02-18 |
Family
ID=80236215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111281159.1A Pending CN114066506A (en) | 2021-11-01 | 2021-11-01 | AI analysis algorithm for network behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114066506A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116351072A (en) * | 2023-04-06 | 2023-06-30 | 北京羯磨科技有限公司 | Robot script recording and playing method and device in online game |
-
2021
- 2021-11-01 CN CN202111281159.1A patent/CN114066506A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116351072A (en) * | 2023-04-06 | 2023-06-30 | 北京羯磨科技有限公司 | Robot script recording and playing method and device in online game |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299271B (en) | Training sample generation method, text data method, public opinion event classification method and related equipment | |
| CN108287858A (en) | The semantic extracting method and device of natural language | |
| WO2013138968A1 (en) | Method and system for hybrid information query | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| WO2008022581A1 (en) | Method and device for obtaining the new words and input method system | |
| CN102937951A (en) | Method for building internet protocol (IP) address classification model, user classifying method and device | |
| CN111984873B (en) | Service recommendation system and method | |
| CN114913729B (en) | Question selecting method, device, computer equipment and storage medium | |
| CN104899335A (en) | Method for performing sentiment classification on network public sentiment of information | |
| CN110647995A (en) | Rule training method, device, equipment and storage medium | |
| CN106533921A (en) | Rapid filing method and system based on E-mail information | |
| CN107402859A (en) | Software function verification system and verification method thereof | |
| CN102402717A (en) | Data analysis facility and method | |
| CN110807044A (en) | Model dimension management method based on artificial intelligence technology | |
| CN113157867A (en) | Question answering method and device, electronic equipment and storage medium | |
| CN112529750A (en) | Learning event recommendation method and system based on graph neural network model | |
| CN114066506A (en) | AI analysis algorithm for network behavior | |
| CN111159559A (en) | Method for constructing recommendation engine according to user requirements and user behaviors | |
| US10346856B1 (en) | Personality aggregation and web browsing | |
| CN112052686B (en) | Voice learning resource pushing method for user interactive education | |
| CN106407254B (en) | Method and device for processing user click behavior chain | |
| CN111104422B (en) | Training method, device, equipment and storage medium of data recommendation model | |
| CN106407332B (en) | Search method and device based on artificial intelligence | |
| CN112749238A (en) | Search ranking method and device, electronic equipment and computer-readable storage medium | |
| CN110209804B (en) | Target corpus determining method and device, storage medium and electronic device |
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 |