CN108874794A - A kind of real-time SEM keyword changing effect analysis system and its analysis method - Google Patents
A kind of real-time SEM keyword changing effect analysis system and its analysis method Download PDFInfo
- Publication number
- CN108874794A CN108874794A CN201710316149.4A CN201710316149A CN108874794A CN 108874794 A CN108874794 A CN 108874794A CN 201710316149 A CN201710316149 A CN 201710316149A CN 108874794 A CN108874794 A CN 108874794A
- Authority
- CN
- China
- Prior art keywords
- keyword
- module
- launching
- access record
- access
- 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
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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of real-time SEM keyword changing effect analysis system, including trapping module, is jumped to by search engine for capturing visitor and promote the request of the page；Logging modle is promoting the access record on the page for recording visitor；Screening module, for filtering out the access record for carrying out successful conversion by launching keyword in access record；Analysis module analyzes the access path for launching the access record that keyword carries out successful conversion；Feedback module carries out feedback modifiers according to screening process of the analysis result of analysis module to screening module；Statistical module, for carrying out statistics calculating to the conversion ratio for launching keyword；Memory module, for being stored to statistical result；Prediction module analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.The present invention can improve the deficiencies in the prior art, realize the real-time analysis of keyword, improve the efficiency and accuracy of analysis.
Description
Technical field
The present invention relates to SEM to launch analysis technical field, especially a kind of real-time SEM keyword changing effect analysis system
And its analysis method.
Background technique
Business Information is promoted using search platform, is a kind of information popularization mode more popular at present.User passes through
Terminal browser is after initiating searching request to search platform, and search platform can be determined from numerous dispensing keywords and user
The associated dispensing keyword of searching request, and the link of impression information corresponding to determining dispensing keyword is returned into end
Hold browser；User can be by the link of certain impression information shown on click terminal browser, the pass that access businessman provides
Some behaviors of this impression information are operated in the page of this impression information, and then by page triggering.In order to improve
Investment/the output ratio for launching keyword, needs to analyze the changing effect of keyword.Existing analysis method require according to
The calculating of magnanimity is carried out according to huge data volume, analysis efficiency is low, can not adapt to quick turn of the market.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of real-time SEM keyword changing effect analysis system and its analyses
Method is able to solve the deficiencies in the prior art, realizes the real-time analysis of keyword, improves the efficiency and accuracy of analysis.
In order to solve the above technical problems, the technical solution used in the present invention is as follows.
A kind of real-time SEM keyword changing effect analysis system, including,
Trapping module, for capture visitor by search engine jump to promote the page request；
Logging modle is promoting the access record on the page for recording visitor；
Screening module, for filtering out the access record for carrying out successful conversion by launching keyword in access record；
Analysis module analyzes the access path for launching the access record that keyword carries out successful conversion；
Feedback module carries out feedback modifiers according to screening process of the analysis result of analysis module to screening module；
Statistical module, for carrying out statistics calculating to the conversion ratio for launching keyword；
Memory module, for being stored to statistical result；
Prediction module analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.
A kind of analysis method of above-mentioned real-time SEM keyword changing effect analysis system, includes the following steps：
A, trapping module capture visitor jumps to the request for promoting the page by search engine；
B, logging modle record visitor is promoting the access record on the page；
C, screening module filters out the access record that successful conversion is carried out by launching keyword in access record；
D, statistical module carries out statistics calculating to the conversion ratio for launching keyword；
E, memory module stores statistical result；
F, analysis module analyzes the access path for launching the access record that keyword carries out successful conversion, feeds back mould
Root tuber carries out feedback modifiers to the screening process of screening module according to the analysis result of analysis module；
G, prediction module analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.
Preferably, in step B, according to the ratio accessed with the duration of keyword related content and the total time of browsing pages
The size order of value records access and carries out descending arrangement.
Preferably, carrying out traversal screening to access record from the starting point of access records series in step C；It is new when occurring
Access record when, if the collating sequence of new access record waits screening module before the screening position of screening module
After the screening process for completing an access record, preferentially new access record is screened, if the sequence of new access record
Sequence is after the screening position of screening module, then medium to be screened by new access record insertion access records series.
Preferably, in step C, the identification standard for launching keyword successful conversion is,
It is consumed by launching the link that keyword is included,
Or registered by launching the link that keyword is included,
Or be downloaded by launching the link that keyword is included,
Or registration reservation is carried out by launching the link that keyword is included.
Preferably, analysis module is classified according to the similarity of access path in step F, in each class.path
Path key node is obtained, the Path launched keyword and carry out successful conversion is simulated using path key node.
Preferably, feedback module, to access Record Comparison, obtains each access record using Path in step F
Similarity, screening module preferentially to similarity be higher than threshold value access record screens.
Preferably, prediction module is thrown using launching keyword and launching the degree of association of historical record new in step G
The conversion ratio for the keyword put is predicted.
Brought beneficial effect is by adopting the above technical scheme：The present invention is thoroughly got rid of to be carried out by mass data
The constraint of statistical analysis can quickly be analyzed according to a small amount of access data, and process and result progress reality to analysis
Shi Xiuzheng realizes the real-time analysis and prediction of keyword conversion results, can launch for keyword and provide newest dynamic dispensing
Tutorial message.
Detailed description of the invention
Fig. 1 is the schematic diagram of a specific embodiment of the invention.
In figure：1, trapping module；2, logging modle；3, screening module；4, analysis module；5, feedback module；6, mould is counted
Block；7, memory module；8, prediction module.
Specific embodiment
Referring to Fig.1, the specific embodiment of the present invention includes,
Trapping module 1, for capture visitor by search engine jump to promote the page request；
Logging modle 2 is promoting the access record on the page for recording visitor；
Screening module 3, for filtering out the access record for carrying out successful conversion by launching keyword in access record；
Analysis module 4 analyzes the access path for launching the access record that keyword carries out successful conversion；
Feedback module 5 carries out feedback modifiers according to screening process of the analysis result of analysis module 4 to screening module 3；
Statistical module 6, for carrying out statistics calculating to the conversion ratio for launching keyword；
Memory module 7, for being stored to statistical result；
Prediction module 8, analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.
A kind of analysis method of above-mentioned real-time SEM keyword changing effect analysis system, includes the following steps：
A, trapping module 1 captures visitor and jumps to the request for promoting the page by search engine；
B, logging modle 2 records visitor and is promoting the access record on the page；
C, screening module 3 filters out the access record that successful conversion is carried out by launching keyword in access record；
D, the conversion ratio of 6 pairs of statistical module dispensing keywords carries out statistics calculating；
E, memory module 7 stores statistical result；
F, 4 pairs of the analysis module access path for launching the access record that keyword carries out successful conversion are analyzed, and are fed back
Module 5 carries out feedback modifiers to the screening process of screening module 3 according to the analysis result of analysis module 4；
G, prediction module 8 analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.
In step B, according to the size of access and the duration of keyword related content and the ratio of the total time of browsing pages
Sequence records access and carries out descending arrangement.
In step C, traversal screening is carried out to access record from the starting point of access records series；It is recorded when there is new access
When, if the collating sequence of new access record waits screening module 3 to complete one before the screening position of screening module 3
After the screening process for accessing record, preferentially new access record is screened, if the collating sequence of new access record is being sieved
It is after the screening position of modeling block 3, then new access record insertion access records series are medium to be screened.
In step C, launch keyword successful conversion identification standard be,
It is consumed by launching the link that keyword is included,
Or registered by launching the link that keyword is included,
Or be downloaded by launching the link that keyword is included,
Or registration reservation is carried out by launching the link that keyword is included.
In step F, analysis module 4 is classified according to the similarity of access path, obtains path in each class.path
Key node simulates the Path launched keyword and carry out successful conversion using path key node.Path key node
Common across point including at least 30% path or path node of the path with hyperlink relation at least 50%.
In step F, feedback module 5, to access Record Comparison, obtains the similarity of each access record using Path,
The access record that screening module 3 is preferentially higher than threshold value to similarity screens.
In step G, prediction module 8 is using launching keyword and launching the degree of association of historical record, to the key newly launched
The conversion ratio of word is predicted.Launch keyword prediction conversion ratio be,
Wherein, PiFor each conversion ratio for launching historical record, PjFor with the prediction keyword degree of association highest historical record
Conversion ratio,For history average conversion, δ is proportionality coefficient, kiFor each degree of association for launching record with prediction keyword.
The present invention is suitable for the real-time analysis to keyword changing effect, to dynamically adjust the dispensing plan of keyword
Slightly.
In the description of the present invention, it is to be understood that, term " longitudinal direction ", " transverse direction ", "upper", "lower", "front", "rear",
The orientation or positional relationship of the instructions such as "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is based on attached drawing institute
The orientation or positional relationship shown is merely for convenience of the description present invention, rather than the device or element of indication or suggestion meaning must
There must be specific orientation, be constructed and operated in a specific orientation, therefore be not considered as limiting the invention.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (8)
1. a kind of real-time SEM keyword changing effect analysis system, it is characterised in that：Including,
Trapping module (1), for capture visitor by search engine jump to promote the page request；
Logging modle (2) is promoting the access record on the page for recording visitor；
Screening module (3), for filtering out the access record for carrying out successful conversion by launching keyword in access record；
Analysis module (4) analyzes the access path for launching the access record that keyword carries out successful conversion；
Feedback module (5) carries out feedback modifiers according to screening process of the analysis result of analysis module (4) to screening module (3)；
Statistical module (6), for carrying out statistics calculating to the conversion ratio for launching keyword；
Memory module (7), for being stored to statistical result；
Prediction module (8), analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.
2. a kind of analysis method of real-time SEM keyword changing effect analysis system described in claim 1, it is characterised in that packet
Include following steps：
A, trapping module (1) capture visitor jumps to the request for promoting the page by search engine；
B, logging modle (2) record visitor is promoting the access record on the page；
C, screening module (3) filters out the access record that successful conversion is carried out by launching keyword in access record；
D, statistical module (6) carries out statistics calculating to the conversion ratio for launching keyword；
E, memory module (7) stores statistical result；
F, analysis module (4) analyzes the access path for launching the access record that keyword carries out successful conversion, feeds back mould
Block (5) carries out feedback modifiers to the screening process of screening module (3) according to the analysis result of analysis module (4)；
G, prediction module (8) analyzes statistical result, and predicts the conversion ratio for the keyword newly launched.
3. the analysis method of real-time SEM keyword changing effect analysis system according to claim 2, it is characterised in that：
In step B, according to access with the size order of the duration of keyword related content and the ratio of the total time of browsing pages to visit
Ask that record carries out descending arrangement.
4. the analysis method of real-time SEM keyword changing effect analysis system according to claim 3, it is characterised in that：
In step C, traversal screening is carried out to access record from the starting point of access records series；When there is new access record, if newly
Access record collating sequence before the screening position of screening module (3), then wait screening module (3) complete one access
After the screening process of record, preferentially new access record is screened, if the collating sequence of new access record is in screening mould
It is after the screening position of block (3), then new access record insertion access records series are medium to be screened.
5. the analysis method of real-time SEM keyword changing effect analysis system according to claim 4, it is characterised in that：
In step C, launch keyword successful conversion identification standard be,
It is consumed by launching the link that keyword is included,
Or registered by launching the link that keyword is included,
Or be downloaded by launching the link that keyword is included,
Or registration reservation is carried out by launching the link that keyword is included.
6. the analysis method of real-time SEM keyword changing effect analysis system according to claim 2, it is characterised in that：
In step F, analysis module (4) is classified according to the similarity of access path, and key section in path is obtained in each class.path
Point simulates the Path launched keyword and carry out successful conversion using path key node.
7. the analysis method of real-time SEM keyword changing effect analysis system according to claim 6, it is characterised in that：
In step F, feedback module (5), to access Record Comparison, is obtained the similarity of each access record, screens mould using Path
The access record that block (3) is preferentially higher than threshold value to similarity screens.
8. the analysis method of real-time SEM keyword changing effect analysis system according to claim 2, it is characterised in that：
In step G, prediction module (8) is using launching keyword and launching the degree of association of historical record, to turning for the keyword newly launched
Rate is predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710316149.4A CN108874794A (en) | 2017-05-08 | 2017-05-08 | A kind of real-time SEM keyword changing effect analysis system and its analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710316149.4A CN108874794A (en) | 2017-05-08 | 2017-05-08 | A kind of real-time SEM keyword changing effect analysis system and its analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108874794A true CN108874794A (en) | 2018-11-23 |
Family
ID=64287200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710316149.4A Pending CN108874794A (en) | 2017-05-08 | 2017-05-08 | A kind of real-time SEM keyword changing effect analysis system and its analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108874794A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102479193A (en) * | 2010-11-22 | 2012-05-30 | 百度在线网络技术（北京）有限公司 | Method and equipment for match search popularization based on match bid coefficient |
| CN105787767A (en) * | 2016-03-03 | 2016-07-20 | 上海珍岛信息技术有限公司 | Method and system for obtaining advertisement click-through rate pre-estimation model |
| CN105912686A (en) * | 2016-04-18 | 2016-08-31 | 上海珍岛信息技术有限公司 | Search engine marketing bid method and system based on machine learning |
| CN106126538A (en) * | 2016-06-14 | 2016-11-16 | 百度在线网络技术（北京）有限公司 | The transformation processing method of the page and device |
-
2017
- 2017-05-08 CN CN201710316149.4A patent/CN108874794A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102479193A (en) * | 2010-11-22 | 2012-05-30 | 百度在线网络技术（北京）有限公司 | Method and equipment for match search popularization based on match bid coefficient |
| CN105787767A (en) * | 2016-03-03 | 2016-07-20 | 上海珍岛信息技术有限公司 | Method and system for obtaining advertisement click-through rate pre-estimation model |
| CN105912686A (en) * | 2016-04-18 | 2016-08-31 | 上海珍岛信息技术有限公司 | Search engine marketing bid method and system based on machine learning |
| CN106126538A (en) * | 2016-06-14 | 2016-11-16 | 百度在线网络技术（北京）有限公司 | The transformation processing method of the page and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
| WO2020224107A1 (en) | Music style classification method and apparatus, computing device and storage medium | |
| CN104182412B (en) | A kind of web page crawl method and system | |
| CN103064984B (en) | The recognition methods of spam page and system | |
| CN105930469A (en) | Hadoop-based individualized tourism recommendation system and method | |
| CN106649260A (en) | Product feature structure tree construction method based on comment text mining | |
| CN101694658A (en) | Method for constructing webpage crawler based on repeated removal of news | |
| CN107257390B (en) | URL address resolution method and system | |
| CN102999625A (en) | Method for realizing semantic extension on retrieval request | |
| CN110019616A (en) | A kind of POI trend of the times state acquiring method and its equipment, storage medium, server | |
| CN103530429B (en) | Webpage content extracting method | |
| CN105550359B (en) | Webpage sorting method and device based on vertical search and server | |
| CN104618132A (en) | Generation method and generation device for application program recognition rule | |
| CN109472021A (en) | Critical sentence screening technique and device in medical literature based on deep learning | |
| CN102609412A (en) | RSS (Really Simple Syndication)-based multi-thread graphic information synchronization crawling control method and system | |
| CN104809252A (en) | Internet data extraction system | |
| CN110532480A (en) | It is a kind of to read the knowledge mapping construction method for threatening information to recommend for people and threaten information recommended method | |
| CN107943792A (en) | A kind of statement analytical method, device and terminal device, storage medium | |
| CN101350029B (en) | Device, method and program for producing related words dictionary, and content search device | |
| CN104834739A (en) | Internet information storage system | |
| CN106528527A (en) | Identification method and identification system for out of vocabularies | |
| CN113051966A (en) | Video keyword processing method and device | |
| CN112488098A (en) | Training method of target detection model | |
| Freitag | Morphology induction from term clusters | |
| CN107563394A (en) | A kind of method and system of predicted pictures popularity |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181123 |