CN103679511A - Optimization method and device for paid search scheme - Google Patents
Optimization method and device for paid search scheme Download PDFInfo
- Publication number
- CN103679511A CN103679511A CN201310696073.4A CN201310696073A CN103679511A CN 103679511 A CN103679511 A CN 103679511A CN 201310696073 A CN201310696073 A CN 201310696073A CN 103679511 A CN103679511 A CN 103679511A
- Authority
- CN
- China
- Prior art keywords
- scheme
- adjustment
- adjusted
- parameter
- adjustment scheme
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides an optimization method and device for a paid search scheme. The optimization method includes the first step of determining problems to be adjusted exist in a search engine platform based on an account structure to provide a search service, the second step of selecting an adjusting scheme for the problems to be adjusted, wherein the adjusting scheme comprises a set number of adjusting parameters, the third step of adjusting parameters in the account structure according to the adjusting parameters in the adjusting scheme, and receiving observation return data generated by the search engine platform based on the account structure to provide the search service within a set observation period, and the fourth step of carrying out adjusting scheme selection operation and parameter adjusting operation at least once, and determining a final adjusting scheme aiming at the problems to be adjusted according to the observation return data returned each time. The optimization method can be carried out automatically through the device and is optimized continuously, confusion of the relation between a promoting effect and the adjusting scheme is reduced as far as possible, and interference of man-made operation is also reduced. Therefore, the optimization efficiency and accuracy of the paid search scheme are improved.
Description
Technical field
The embodiment of the present invention relates to microcomputer data processing, relates in particular to a kind of paid search scheme optimization method and apparatus.
Background technology
Paid search advertisement (Paid Search Advertising, PSA) is most important advertisement putting mode on current internet.If all enterprises advertising budget is on the internet denoted as to 100%, PSA aspect drops into and occupies more than 50% share.At home, the main search engine platform of throwing in is such as there being Baidu's Extension Software Platform etc.
The realization mechanism of PSA be by advertisement putting user from search engine platform application account, in account, determine keyword, the intention recommendation information of keyword, the popularization webpage of keyword to be put, and the matching way of keyword and bid etc.When browsing user while inputting retrieve statement, search engine platform will carry out keyword retrieval, according to factors such as matching way, bids, intention recommendation information is represented, and the click behavior of recording user.The expense that search engine platform will should be collected according to the regular calculating of setting according to data such as the amount of representing and click volumes, forms reward data, feeds back to advertisement putting user and charges.
Visible, the important step of successful PSA is as follows:
The first, should choose correct keyword.For example Yi Ge nash-equilibrium mechanism, should buy " aviation passenger ticket ", and " electronic passenger ticket " etc. can mate the keyword of its business, and completely irrelevant keyword of industry that similar " baby milk " is engaged in it is like this inapplicable.The second, the simple and clear and attractive intention of keyword writing for buying, with the concern that attracts clients, promotes ad click rate, and then promotes keyword quality degree.Three, for rational best bid and matching way etc. set in each keyword.
The promotion effect of advertisement is one of important evaluation index, and advertisement putting user can pass through more new keywords, revises intention or promote the forms such as webpage to reach good promotion effect.People terminate in data analysis and report form showing to the processing of promotion effect data at present, and it exists following shortcoming:
The first, merely data analysis and report form showing are that simple effect is checked, can not form complete analysis system, can not instruct further optimizing process.
The second, the change of an effect of optimization may be the coefficient results of a plurality of indexs, is difficult to the effect of certain Optimized Measures of assessment, can take even sometimes some wrong Optimized Measures.
Three, simple data analysis and report form showing mode often consider that to the data of time dimension less, simple cross-section data judges the time situation that can accurately not react account.
Summary of the invention
The embodiment of the present invention provides a kind of paid search scheme optimization method and apparatus, to optimize efficiently and accurately paid search advertisement scheme.
First aspect, the embodiment of the present invention provides a kind of paid search scheme optimization method, comprising:
The problem to be adjusted of determining search engine platform to provide search service based on account structure and existing, wherein, disposes at least one parameter in described structure of accounts;
For described problem to be adjusted, select adjustment scheme, described adjustment scheme comprises the adjustment parameter of setting quantity;
According to the adjustment parameter in described adjustment scheme, the parameter in described account structure is adjusted, and in the observation period, received that described search engine platform provides search service based on described structure of accounts and the observation reward data that produces setting;
Carry out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, the observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
Second aspect, the embodiment of the present invention also provides a kind of paid search scheme optimization device, comprising:
Positioning problems module, the problem to be adjusted existing for determining search engine platform to provide search service based on account structure, wherein, disposes at least one parameter in described structure of accounts;
Scheme Choice module, is used to described problem to be adjusted to select adjustment scheme, and described adjustment scheme comprises the adjustment parameter of setting quantity;
Data reception module, be used for according to the adjustment parameter of described adjustment scheme, parameter in described account structure is adjusted, and in the observation period, received that described search engine platform provides search service based on described structure of accounts and the observation reward data that produces setting;
Scheme determination module, for carrying out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, the observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
The technical scheme of the embodiment of the present invention, be applicable to determining the optimization of parametric variable, and definite observation period, can the impact of independent test parameter on promotion effect, it can automatically be implemented by device, continues to optimize, and reduces obscuring of relation between promotion effect and adjustment scheme as far as possible, also reduce the interference of manual operation, improved optimization efficiency and the accuracy of paid search scheme.
Accompanying drawing explanation
The process flow diagram of the paid search scheme optimization method that Fig. 1 provides for the embodiment of the present invention one;
The process flow diagram of the paid search scheme optimization method that Fig. 2 provides for the embodiment of the present invention two;
The structural representation of the paid search scheme optimization device that Fig. 3 provides for the embodiment of the present invention three.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, in accompanying drawing, only show part related to the present invention but not entire infrastructure.
Embodiment mono-
The process flow diagram of a kind of paid search scheme optimization method that Fig. 1 provides for the embodiment of the present invention one, the situation that the present embodiment is optimized applicable to the input scheme of paying search advertisements being thrown in to user, can be realized by optimization device, this device can be realized by the form of hardware and/or software, be integrated in the equipment such as server or computing machine, coordinate and realize optimization method with search engine platform.The method specifically comprises the steps:
Account structure means the important means of paid search scheme, conventionally with the parameter in account structure, decides search plan.The parameter of described structure of accounts can comprise following at least one: at least one keyword, the plan of keyword place, unit, keyword place, keyword budget, matching way, creative content, bid and popularization webpage.Above-mentioned parameter is the parameter that advertisement putting user can control adjustment, in structure of accounts, also can comprise other parameters, for example, represent to throw in the parameter of user identity, the parameter of being determined by search engine platform etc.
Paid search scheme may exist some problems to need to adjust, the discovery of these problems can rule of thumb be come to determine by operating personnel, but preferably by device, automatically identified and location, for example, determine that search engine platform provides search service based on account structure and the operation of the problem to be adjusted that exists specifically comprises: receive that search engine platform provides search service based on account structure and the reward data that produces; Actual desired value in described reward data is mated with default desired value, according to matching result, locate problem to be adjusted.When actual desired value occurs when abnormal, can judge and occur problem to be adjusted.
The actual desired value that can be used for judging has multiple, can set according to demand.For example, the method also comprises and from described reward data, obtains the amount of representing, click volume and/or consumption data; Calculate the ratio of described click volume and the amount of representing, obtain clicking rate; Calculate the ratio of described consumption data and click volume, obtain average click valency; According to described reward data, inquire about corresponding order data; Will described in the amount of representing, click volume, consumption data, clicking rate, on average click valency and/or order data, as described actual desired value.To the actual desired value in described reward data is mated with default desired value.
Selective adjustment scheme can set in advance a plurality of, and in each adjustment scheme, adjusting parameter can have a plurality ofly, but preferably set quantity, is one, is adjusted into the adjustment of unitary variant, the peep optimization result of being more convenient at every turn.Adjustment scheme can rule of thumb be selected by operating personnel, but preferably by device, is automatically selected.For example, can preset selective rule, setting different problems to be adjusted has different adjustment schemes, and according to the parameter in problem to be adjusted, determines amplitude of parameter adjustment in scheme etc.
In aforesaid operations, for each has adjusted design of scheme the observation period, can be identical, also can be with adjusting the difference of parameter the length of change and adjustment phase.Within a period of time of setting, carry out the observation of reward data, can determine easily that adjustment parameter is for the effect of optimization of paid search scheme, with clearly defined objective, and be convenient to device and automatically perform.
In this step, the observation reward data based on each can be determined final adjustment scheme, and for example, judgement is observed reward data and whether met default effect requirements, if so, can directly determine that currently used adjustment scheme is final adjustment scheme.Or the observation reward data that each time can also be adjusted to scheme compares, and selects preferably as final adjustment scheme.
The technical scheme of the present embodiment, be applicable to determining the optimization of parametric variable, and definite observation period, can the impact of independent test parameter on promotion effect, it can automatically be implemented by device, continues to optimize, and reduces obscuring of relation between promotion effect and adjustment scheme as far as possible, also reduce the interference of manual operation, improved optimization efficiency and the accuracy of paid search scheme.
Embodiment bis-
The process flow diagram of the paid search scheme optimization method that Fig. 2 provides for the embodiment of the present invention two, the present embodiment be take above-described embodiment as basis, further improve the machine learning that is to realize adjustment scheme, for adjustment scheme increases weighted value, can constantly update weighted value, and select adjustment scheme according to weighted value.
Specifically, carry out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, the observation reward data of returning according to each time determines that the final adjustment scheme optimization for described problem to be adjusted comprises the steps:
Carry out the operation of described adjustment Scheme Choice and parameter adjustment at least one times;
The observation reward data of returning according to each time is determined the weighted value of the corresponding scheme of respectively adjusting, and upgrades for described problem to be adjusted the weighted value of respectively adjusting scheme;
The observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
Accordingly, for described problem to be adjusted, selecting adjustment scheme can comprise: determine at least one adjustment scheme that described problem to be adjusted is corresponding, the weighted value of adjusting scheme is selected adjustment scheme according to each.
After the operation of carrying out described adjustment Scheme Choice and parameter adjustment at least one times, can also comprise: the adjustment parameter that the observation reward data of returning according to each time is exchanged in perfect square case is upgraded based on setting rule, to form new adjustment scheme.
A complete example of method of having applied above-mentioned preferred feature is as follows:
The parameter of structure of accounts is for example; At least one keyword, the plan of keyword place, unit, keyword place, keyword budget, matching way, creative content, bid and popularization webpage.For search engine platform, need to throw in user and determine a plurality of keywords, also keyword can be divided into groups or classification, the pattern of grouping is for example determined the unit at several keywords place, determine again the plan at each place, unit, such as: the relation of physical culture---world cup---football.Pre-definite each plan of a plurality of keywords or the budget allowances of the required defrayment of each account of comprising at last of keyword.Matching way comprises exact matching, phrase match and broad match etc., for determining that search engine platform is by the matching relationship of keyword and user search formula.Creative content is the recommendation information that keyword is corresponding.Bid is the determined bid of keyword or unit for throwing in user, for throwing in other sequence that user competes keyword recommendation information.Promoting webpage is the associating web pages corresponding with keyword or creative content.Those skilled in the art can understand, and the adjustable parameters in structure of accounts is not limited to above-mentioned every.
Aforesaid operations is the process of carrying out initial account popularization, collecting data.Be that consultant is according to some industrial characteristics and experience and utilize some other instruments first to set up account structure, formulate initial extension programme, carry out account popularization, and collect promotion effect data, as the investment repayments such as the amount of representing of account popularization, click volume, consumption data, conversion data (Return On Investment is called for short ROI) data.
This step is the data analysis to promotion effect, thus orientation problem.Can set different desired value comparisons, can in analysis, find the weak point of structure of accounts and extension programme from a plurality of dimensions to promotion effect data analysis, determine the place that promoted account need to be optimized.
By machine learning, adjustment scheme applicable in all previous optimizing process can be arranged to weighted value, when selecting adjustment scheme, can take weighted value as foundation.This step is optimized for the weak part of account, and unitary variant is controlled and selected prioritization scheme.Situation to each keyword, considers by certain weight according to situations such as consultant's experience and machine learning, determines the adjustment of the single setting that most probable is dealt with problems, and keeps other to arrange constant, and the setting of needs adjustment is adjusted.
Aforesaid operations has been determined the observation period for the structure of accounts after adjusting, and monitoring is adjusted rear effect and changed.For different adjustment settings and keyword situation, set the different observation periods, in the observation period, the effect data of a recorded key word, does not change any setting.
The adjustment parameter that step 207, the observation reward data of returning according to each time are exchanged in perfect square case is upgraded based on setting rule, to form new adjustment scheme.
Above-mentioned steps, the effect of further bringing after design develop.For keyword, arrange and adjust front and back Contrast on effect analysis, also can according to time dimension, carry out effect analysis based on historical data, check whether the promotion effect of keyword has comparatively significantly lifting, evaluate this effect that adjustment brings is set.
According to effect assessment result, adjust the weight of machine learning, and determine the whether former setting of rollback.That is, if certain adjustment scheme has been brought the remarkable lifting of promotion effect, the weight of the current problem to be adjusted of this scheme solution is suitably increased, otherwise suitably reduce, and the former setting of rollback.The former setting of so-called rollback, before soon structure of accounts will return to and carries out adjustment scheme, is then back to step 204, again selects adjustment scheme, repeats.Carry out the former setting of rollback and conventionally show the lifting that this adjustment scheme can not be brought effect, need to reselect adjustment scheme.While again selecting adjustment scheme, possible weighted value changes, and selectable scheme scope is likely increase and decrease also.If the keyword correspondence problem of this discovery is with last identical,, when selecting prioritization scheme, the adjustment scheme weight that the last time takes changes to zero.The keyword that effect analysis is good also will record the adjustment scheme of its correspondence, for machine learning.
Aforesaid operations can repeat, and reorientates problem to be adjusted, and the adjustment scheme that makes repeated attempts, until reach target setting.Target setting can be that desired value all reaches setting threshold, or amplitude of variation reaches setting threshold, can also pass through the optimization of set point number.
The technical scheme of the embodiment of the present invention, be devoted to the analysis thinking that provides to be combined with data analysis based on machine learning, a benign cycle system that can be integrated to the analysis of account promotion effect from setting up promoted account structure, formulation keyword prices and rank strategy.Whether the setting of investigating keyword by comparative analysis and the variation of single keyword effect on time dimension of effect between keyword is suitable, whether rank is reasonable, find the root at problem place, and according to relevant issues, corresponding adjustment scheme is proposed, then carry out next step effect monitoring, by effect analysis, further instruct again the formulation of the scheme of optimizing and revising of promoted account, formation is from effect to scheme, then the loop structure from scheme to effect.
Embodiment tri-
The embodiment of the present invention three provides a kind of structural representation of paid search scheme optimization device, and this device comprises: positioning problems module 310, Scheme Choice module 320, data reception module 330 and scheme determination module 340.
Wherein, the problem to be adjusted that positioning problems module 310 exists for determining search engine platform to provide search service based on account structure, wherein, disposes at least one parameter in described structure of accounts; Scheme Choice module 320 is used to described problem to be adjusted to select adjustment scheme, and described adjustment scheme comprises the adjustment parameter of setting quantity; Data reception module 330 is for according to the adjustment parameter of described adjustment scheme, parameter in described account structure is adjusted, and in the observation period, received that described search engine platform provides search service based on described structure of accounts and the observation reward data that produces setting; Scheme determination module 340 is for carrying out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, and the observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
In such scheme, the parameter of described structure of accounts comprises following at least one: at least one keyword, the plan of keyword place, unit, keyword place, keyword budget, matching way, creative content, bid and popularization webpage; The setting quantity of adjusting parameter in described adjustment scheme is one.
This installs preferably, the reward data that described positioning problems module 310 produces specifically for reception search engine platform provides search service based on account structure; Actual desired value in described reward data is mated with default desired value, according to matching result, locate problem to be adjusted;
Described scheme determination module 340 is specifically for carrying out the operation of described adjustment Scheme Choice and parameter adjustment at least one times; The observation reward data of returning according to each time is determined the weighted value of the corresponding scheme of respectively adjusting, and upgrades for described problem to be adjusted the weighted value of respectively adjusting scheme; The observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
Paid search scheme optimization device provided by the invention can be carried out paid search scheme optimization, the method that any embodiment of the present invention provides, and possesses the corresponding functional module of manner of execution and beneficial effect.
The technical scheme feature of the embodiment of the present invention is, first, adopted circulating system: and from promotion effect, instruct prioritization scheme, whole optimizing process is formed to system, set up from effect to scheme, then the loop structure from scheme to effect; The second, be preferably unitary variant control and observation period setting: control unitary variant and be also set the observation period, weakened greatly the interference of internal and external factor, can understand more clearly the impact that prioritization scheme produces effect, for the evaluation of effect of optimization provides solid foundation; Three, mechanism of Machine Learning: in optimizing process, by the unceasing study of machine, making to deal with problems becomes more efficient sooner.
The advantage of the embodiment of the present invention has multinomial:
The first, set up whole promoted account analysis system, formation is from effect to scheme, then the loop structure from scheme to effect, has made up the deficiency of current promoted account prioritization scheme, instructs the further optimization of promoted account;
The second, accurately orientation problem, makes to optimize and shoots the arrow at the target, can be sooner more accurate more effective promoted account be optimized.
Three, the observation period the greatly low interference of avoiding other factors is set, can add and understand clearly the impact of Optimum Operation on promotion effect.
Four, by circulation, embody and the processing mode of machine learning, it is more and more accurate to make the processing meeting of problem, and the speed that effect takes effect can be more and more obvious, simultaneously by machine system analyze also can be a large amount of save labour turnover.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious variations, readjust and substitute and can not depart from protection scope of the present invention.Therefore, although the present invention is described in further detail by above embodiment, the present invention is not limited only to above embodiment, in the situation that not departing from the present invention's design, can also comprise more other equivalent embodiment, and scope of the present invention is determined by appended claim scope.
Claims (10)
1. a paid search scheme optimization method, is characterized in that, comprising:
The problem to be adjusted of determining search engine platform to provide search service based on account structure and existing, wherein, disposes at least one parameter in described structure of accounts;
For described problem to be adjusted, select adjustment scheme, described adjustment scheme comprises the adjustment parameter of setting quantity;
According to the adjustment parameter in described adjustment scheme, the parameter in described account structure is adjusted, and in the observation period, received that described search engine platform provides search service based on described structure of accounts and the observation reward data that produces setting;
Carry out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, the observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
2. method according to claim 1, it is characterized in that, the parameter of described structure of accounts comprises following at least one: at least one keyword, the plan of keyword place, unit, keyword place, keyword budget, matching way, creative content, bid and popularization webpage; The setting quantity of adjusting parameter in described adjustment scheme is one.
3. method according to claim 1 and 2, is characterized in that, determines that search engine platform provides search service based on account structure and the problem to be adjusted that exists comprises:
Receive that search engine platform provides search service based on account structure and the reward data that produces;
Actual desired value in described reward data is mated with default desired value, according to matching result, locate problem to be adjusted.
4. method according to claim 3, is characterized in that, before the actual desired value in described reward data is mated with default desired value, also comprises:
From described reward data, obtain the amount of representing, click volume and/or consumption data;
Calculate the ratio of described click volume and the amount of representing, obtain clicking rate;
Calculate the ratio of described consumption data and click volume, obtain average click valency;
According to described reward data, inquire about corresponding order data;
Will described in the amount of representing, click volume, consumption data, clicking rate, on average click valency and/or order data, as described actual desired value.
5. method according to claim 1 and 2, is characterized in that, carries out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, and the observation reward data of returning according to each time determines that the final adjustment scheme for described problem to be adjusted comprises:
Carry out the operation of described adjustment Scheme Choice and parameter adjustment at least one times;
The observation reward data of returning according to each time is determined the weighted value of the corresponding scheme of respectively adjusting, and upgrades for described problem to be adjusted the weighted value of respectively adjusting scheme;
The observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
6. method according to claim 5, is characterized in that, selects adjustment scheme comprise for described problem to be adjusted:
Determine at least one adjustment scheme that described problem to be adjusted is corresponding, the weighted value of adjusting scheme is selected adjustment scheme according to each.
7. method according to claim 5, is characterized in that, after carrying out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, also comprises:
The adjustment parameter that the observation reward data of returning according to each time is exchanged in perfect square case is upgraded based on setting rule, to form new adjustment scheme.
8. a paid search scheme optimization device, is characterized in that, comprising:
Positioning problems module, the problem to be adjusted existing for determining search engine platform to provide search service based on account structure, wherein, disposes at least one parameter in described structure of accounts;
Scheme Choice module, is used to described problem to be adjusted to select adjustment scheme, and described adjustment scheme comprises the adjustment parameter of setting quantity;
Data reception module, be used for according to the adjustment parameter of described adjustment scheme, parameter in described account structure is adjusted, and in the observation period, received that described search engine platform provides search service based on described structure of accounts and the observation reward data that produces setting;
Scheme determination module, for carrying out the operation of described adjustment Scheme Choice and parameter adjustment at least one times, the observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
9. device according to claim 8, it is characterized in that, the parameter of described structure of accounts comprises following at least one: at least one keyword, the plan of keyword place, unit, keyword place, keyword budget, matching way, creative content, bid and popularization webpage; The setting quantity of adjusting parameter in described adjustment scheme is one.
10. device according to claim 8 or claim 9, is characterized in that:
The reward data that described positioning problems module produces specifically for reception search engine platform provides search service based on account structure; Actual desired value in described reward data is mated with default desired value, according to matching result, locate problem to be adjusted;
Described scheme determination module is specifically for carrying out the operation of described adjustment Scheme Choice and parameter adjustment at least one times; The observation reward data of returning according to each time is determined the weighted value of the corresponding scheme of respectively adjusting, and upgrades for described problem to be adjusted the weighted value of respectively adjusting scheme; The observation reward data of returning according to each time is determined the final adjustment scheme for described problem to be adjusted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310696073.4A CN103679511A (en) | 2013-12-18 | 2013-12-18 | Optimization method and device for paid search scheme |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310696073.4A CN103679511A (en) | 2013-12-18 | 2013-12-18 | Optimization method and device for paid search scheme |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103679511A true CN103679511A (en) | 2014-03-26 |
Family
ID=50316974
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310696073.4A Pending CN103679511A (en) | 2013-12-18 | 2013-12-18 | Optimization method and device for paid search scheme |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103679511A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105138540A (en) * | 2015-07-08 | 2015-12-09 | 北京博雅立方信息技术有限公司 | Promotion optimization method and device of promotion website |
CN106682039A (en) * | 2015-11-10 | 2017-05-17 | 北京国双科技有限公司 | Method and device for monitoring keyword releasing effects |
CN106844371A (en) * | 2015-12-03 | 2017-06-13 | 阿里巴巴集团控股有限公司 | Chess game optimization method and apparatus |
CN107436909A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Keyword intelligent optimization method and system |
CN108073633A (en) * | 2016-11-17 | 2018-05-25 | 百度在线网络技术(北京)有限公司 | The bid of keyword and matching way setting method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100036802A1 (en) * | 2008-08-05 | 2010-02-11 | Setsuo Tsuruta | Repetitive fusion search method for search system |
CN102402553A (en) * | 2010-09-19 | 2012-04-04 | 百度在线网络技术(北京)有限公司 | Method and device for analyzing operation quality of promoted account |
CN102402554A (en) * | 2010-09-19 | 2012-04-04 | 百度在线网络技术(北京)有限公司 | Method and device for optimizing data of promoted account |
CN102446171A (en) * | 2010-09-30 | 2012-05-09 | 百度在线网络技术(北京)有限公司 | Method and apparatus for evaluating quality score of promotion key word based on weighted average click-through rate |
-
2013
- 2013-12-18 CN CN201310696073.4A patent/CN103679511A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100036802A1 (en) * | 2008-08-05 | 2010-02-11 | Setsuo Tsuruta | Repetitive fusion search method for search system |
CN102402553A (en) * | 2010-09-19 | 2012-04-04 | 百度在线网络技术(北京)有限公司 | Method and device for analyzing operation quality of promoted account |
CN102402554A (en) * | 2010-09-19 | 2012-04-04 | 百度在线网络技术(北京)有限公司 | Method and device for optimizing data of promoted account |
CN102446171A (en) * | 2010-09-30 | 2012-05-09 | 百度在线网络技术(北京)有限公司 | Method and apparatus for evaluating quality score of promotion key word based on weighted average click-through rate |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105138540A (en) * | 2015-07-08 | 2015-12-09 | 北京博雅立方信息技术有限公司 | Promotion optimization method and device of promotion website |
CN106682039A (en) * | 2015-11-10 | 2017-05-17 | 北京国双科技有限公司 | Method and device for monitoring keyword releasing effects |
CN106844371A (en) * | 2015-12-03 | 2017-06-13 | 阿里巴巴集团控股有限公司 | Chess game optimization method and apparatus |
CN106844371B (en) * | 2015-12-03 | 2020-09-08 | 阿里巴巴集团控股有限公司 | Search optimization method and device |
CN107436909A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Keyword intelligent optimization method and system |
CN108073633A (en) * | 2016-11-17 | 2018-05-25 | 百度在线网络技术(北京)有限公司 | The bid of keyword and matching way setting method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20180047071A1 (en) | System and methods for aggregating past and predicting future product ratings | |
CN103914468B (en) | A kind of method and apparatus of impression information search | |
US9633082B2 (en) | Search result ranking method and system | |
US20210141839A1 (en) | Information search method, apparatus, and system | |
US10134053B2 (en) | User engagement-based contextually-dependent automated pricing for non-guaranteed delivery | |
CN102053971B (en) | Recommending method and equipment for sequencing-oriented collaborative filtering | |
EP3617952A1 (en) | Information search method, apparatus and system | |
US20170109767A1 (en) | Real-time dynamic pricing system | |
US20150186938A1 (en) | Search service advertisement selection | |
He et al. | A game-theoretic machine learning approach for revenue maximization in sponsored search | |
US8150734B2 (en) | Estimating advertising prices for an incumbent content provider | |
CN103309894B (en) | Based on search implementation method and the system of user property | |
CN103679511A (en) | Optimization method and device for paid search scheme | |
US20120123851A1 (en) | Click equivalent reporting and related technique | |
EP1969486A2 (en) | Using estimated ad qualities for ad filtering, ranking and promotion | |
WO2019072128A1 (en) | Object identification method and system therefor | |
CN104142999A (en) | Search result display method and device | |
CN104281962A (en) | Unified marketplace for advertisements and content in an online system | |
US10140339B2 (en) | Methods and systems for simulating a search to generate an optimized scoring function | |
US11599548B2 (en) | Utilize high performing trained machine learning models for information retrieval in a web store | |
CN106447419B (en) | Visitor identification based on feature selection | |
CN110490683B (en) | Offline collaborative multi-model hybrid recommendation method and system | |
US20150058136A1 (en) | Attribute based coupon provisioning | |
US20210191995A1 (en) | Generating and implementing keyword clusters | |
CN106445965B (en) | Information popularization processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140326 |
|
RJ01 | Rejection of invention patent application after publication |