CN103365904A - Advertising information searching method and system - Google Patents
Advertising information searching method and system Download PDFInfo
- Publication number
- CN103365904A CN103365904A CN2012100979840A CN201210097984A CN103365904A CN 103365904 A CN103365904 A CN 103365904A CN 2012100979840 A CN2012100979840 A CN 2012100979840A CN 201210097984 A CN201210097984 A CN 201210097984A CN 103365904 A CN103365904 A CN 103365904A
- Authority
- CN
- China
- Prior art keywords
- advertiser
- candidate word
- word
- words
- advertisement
- 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.)
- Granted
Links
Images
Abstract
The invention provides an advertising information searching method and system and relates to the technical field of a network. The advertising information searching method includes the following steps that a search word input by a user terminal is expanded and then, an expanded candidate word set is obtained; a search engine real-time log and/or information on the state of an advertising client at the moment is analyzed to obtain an effective word set; the information on the state of the advertising client comprises information of displaying conditions of key words which are selected by the advertising client. The effective word set comprises key words which conform to the displaying conditions at the moment and is used for filtering words which are not in the effective word set, out of the candidate word set. At least one candidate word is chosen from the filtered candidate word set for searching for advertising information. According to the advertising information searching method and system, expanded candidate words which can not recall advertisements are filtered in real time so as to ensure that researching key words input to the search engine at the moment can recall the advertisements in time for displaying, the displaying efficiency of the advertisements is not affected and limited displaying resources can be fully utilized for displaying the advertisements.
Description
Technical field
The application relates to networking technology area, particularly relates to a kind of advertising message searching method and system.
Background technology
Development along with the internet, the information that the internet provides is more and more diversified, and by throwing in the important selection that advertisement also becomes the advertiser in the internet, the service of throwing in advertisement in the internet not only can be for the advertiser publicizes, and can provide more server info for the user.Internet search engine is as the information service applicator platform, and throwing in advertisement by search engine has also become a kind of advertisement putting mode that the advertiser generally adopts.
Internet subscribers are when search, and to search engine submit Query word, search engine will return to user side with linking as result of page searching of the maximally related web pages of query word, and the user can click these links and remove to access related web page.In the prior art, when throwing in advertisement by search engine, the advertiser is by the registration of search key bid ranking system and its advertisement link website that will promote or the closely-related one group of search key of webpage; Behind the user side input inquiry word, search engine is at first expanded described query word and is obtained candidate word, then select in the candidate word with the correlation candidate word of query word as search key, then retrieve according to each search key after the expansion, if the keyword of advertiser's registration and described search key coupling can represent so.For example such as input inquiry word " Nokia's mobile phone ", can expand " Nokia ", " mobile phone ", " N97 of Nokia ", then candidate word such as " Nokias 5230 " is chosen from these candidate word with the word of " Nokia's mobile phone " correlativity greater than threshold value and is gone to retrieve as search key.
But in the prior art of actual prior art: at first, the number of the search word that search engine can receive is to have the upper limit, if the search word number surpasses this upper limit, the efficient of search engine and performance will be subjected to very large the impact, be search engine when expanding based on query word, the search key number after the expansion of its selection can not surpass its maximum number that can receive; The second, for the placement position of advertisement, in the reality, namely effectively the placement position of display advertisement is limited; The 3rd, for each advertiser, in the reality, the advertiser generally shows restriction (such as showing the time period) according to actual conditions to one group of search key oneself selecting, so, if search engine searches this advertiser's advertisement in advertisement base according to each search key of expansion, but do not meet this moment the displaying condition that the client sets (such as this moment not within the displaying time period that the client sets), search engine is put into the advertising message searching position and is thrown in regard to not recalling this advertisement so.
Based on above-mentioned situation, there is following shortcoming in prior art:
Only considering based on correlativity of each search key that the query word that search engine is inputted based on the client in the prior art expands, the optimum search word number that can receive at search engine, effective advertising message searching position number, under the restriction of each advertiser for the displaying condition of himself advertisement, may there be one or several search key in its search key that expands, can't recall advertisement behind search key keyed advertising storehouse shows, and because the search key that search engine can receive has the number restriction, if search engine has expanded the search key that can't recall advertisement, this word has just occupied retrieve resources, cause other terms relevant with query word in time or can not enter retrieving, affected that other are relevant with described query word and meet the displaying of the advertisement of displaying condition, made search key after the expansion can not take full advantage of limited location advertising display advertisement client's advertisement.
Summary of the invention
The application's technical matters to be solved provides a kind of advertising message searching method and system, solves in the prior art expansion word and can't effectively can't recall advertisement behind search key keyed advertising storehouse and show the inefficient problem of the displaying of advertisement.
In order to address the above problem, the application discloses a kind of advertising message searching method, comprising:
The query word of user side input is expanded the candidate word set after obtaining to expand;
Analyze search engine real-time logs and/or advertiser's status information of current time and obtain effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition;
Utilize described effective set of words, filter out in the set of described candidate word not the word in effective set of words;
At least one candidate word retrieve advertisements information in the candidate word set after selecting to filter.
Preferably, obtain user state information by following steps:
Obtain database table corresponding to each advertiser from data storage server, described database table comprises advertiser's advertising expenditure budget and advertiser's advertisement promotion time.
Preferably, described database table comprises advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, respectively corresponding advertiser's advertising expenditure budget and advertisement promotion time.
Preferably, obtain database table corresponding to advertiser after, comprising:
Analyze described advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, comprise the advertiser of described current time for the advertising expenditure budget greater than threshold value and advertisement promotion time period, the keyword of described advertisement selection is added effective set of words.
Preferably, analyze the search engine real-time logs by following steps and obtain effective set of words:
Obtain the real-time search daily record from search engine;
Analyze whether each search key returns advertisement to user side in the described real-time search daily record in current slot;
If return, then corresponding search key is added effective set of words.
Preferably, utilizing described effective set of words, filtering out in the set of described candidate word not behind the word in the effective set of words, also comprising:
For the candidate word in the set of the candidate word after the described filtration, calculate the degree of correlation of described candidate word and described query word;
For the candidate word in the set of the candidate word after the described filtration, add up effective advertiser's degree of depth of described candidate word; Described effective advertiser's degree of depth is the quantity of selecting described candidate word and meeting the advertiser of described displaying condition in the current time;
In conjunction with the weight of the degree of correlation of described candidate word and effectively each candidate word in the candidate word set after to described filtration of the weight of advertiser's degree of depth reorder.
Preferably, described database table also comprises advertiser's presence table.
Preferably, utilizing described effective set of words, filtering out in the set of described candidate word not behind the word in the effective set of words, also comprising:
For the candidate word in the set of the candidate word after the described filtration, calculate the degree of correlation of described candidate word and described query word;
For the candidate word in the set of the candidate word after the described filtration, add up effective advertiser's degree of depth of described candidate word; Described effective advertiser's degree of depth is the quantity of selecting described candidate word and meeting the advertiser of described displaying condition in the current time;
Statistics is selected described candidate word and is met the online advertisement client's of described displaying condition quantity in the current time;
In conjunction with the weight of the degree of correlation of described candidate word, effectively each candidate word in the candidate word set after to described filtration of the weight of advertiser's degree of depth and online advertisement customer quantity reorders.
Preferably, the query word of user side input is expanded, the candidate word after obtaining to expand comprises when gathering:
Obtain the new keyword of selecting of advertiser, described keyword is added the expansion dictionary;
Calculate the correlativity of each keyword in described query word and the expansion dictionary, when described correlativity during greater than threshold value, described keyword is added the candidate word set.
Accordingly, the application discloses a kind of advertising message search system, comprising:
The query word expansion module is used for the query word of user side input is expanded, the candidate word set after obtaining to expand;
Effectively the set of words acquisition module is used for analysis search engine real-time logs and/or advertiser's status information of current time and obtains effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition;
Filtering module is used for utilizing described effective set of words, filters out in the described candidate word set not the word in effective set of words;
Retrieval module, at least one the candidate word retrieve advertisements information of candidate word set after being used for selecting to filter.
Preferably, described effective set of words acquisition module comprises:
User state information obtains submodule, is used for obtaining database table corresponding to each advertiser from data storage server, and described database table comprises advertiser's advertising expenditure budget and advertiser's advertisement promotion time.
Preferably, described database table comprises advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, respectively corresponding advertiser's advertising expenditure budget and advertisement promotion time.
Preferably, described effective set of words acquisition module also comprises:
User Status is analyzed submodule, be used for analyzing described advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, comprise the advertiser of described current time for the advertising expenditure budget greater than threshold value and advertisement promotion time period, the keyword of described advertisement selection is added effective set of words.
Preferably, described effective set of words acquisition module comprises:
Real-time logs obtains submodule, is used for obtaining the real-time search daily record from search engine;
Real-time logs is analyzed submodule, is used for analyzing described each search key of real-time search daily record and whether returns advertisement to user side in current slot; If return, then corresponding search key is added effective set of words.
Compared with prior art, the application comprises following advantage:
The application is at the query word of system acquisition to user side, and after obtaining a large amount of candidate word relevant with described query word and gather according to the expansion of described query word, real-time analysis advertiser real-time status data or search engine real-time logs, obtain the current keyword that can recall advertisement, and described keyword added effective set of words as effective keyword, then utilize this effective set of words to screen described candidate word set, acquisition can be recalled the candidate word set of advertisement after the screening, then each candidate word after the described screening is reordered, obtain at least one search key that wherein sorts forward, arrive at the most the search key of search engine retention Optimal units, then retrieve based on above-mentioned search key.In the said method, by the real-time candidate word that filters out the expansion that to recall advertisement, guaranteed that search key that the current time inputs to search engine can in time recall advertisement and show, do not affected the displaying efficient of advertisement, can take full advantage of limited showing resource display advertisement.
Description of drawings
Fig. 1 is the schematic flow sheet of a kind of advertising message searching method of the application;
Fig. 2 is the structural representation of a kind of advertising message search system of the application;
Fig. 3 is the structural representation of the preferred a kind of advertising message search system of the application.
Embodiment
For above-mentioned purpose, the feature and advantage that make the application can become apparent more, below in conjunction with the drawings and specific embodiments the application is described in further detail.
With reference to Fig. 1, show the schematic flow sheet of a kind of advertising message searching method of the application, specifically can comprise:
Because user and advertiser's kens etc. is asymmetric, group word custom when the keyword (word of bidding of namely buying) selected of advertiser may be not in full conformity with user's search sometimes, thereby cause can not maximum possible exposure advertiser product or the advertisement attempting to promote, so search engine generally can be expanded the query word of user's input, the AdWords indexed mode that generally adopts based on present search engine (the word coupling respective advertisement of bidding of buying by the user), in search engine keywords advertisement extension coupling, generally be by the whole bag of tricks (epexegesis, subtract word, replace etc.) on the basis of original user query, guaranteeing under certain correlativity prerequisite, expand one or more the word of bidding, then by former word and the word of bidding that expands are carried out advertisement coupling as new inquiry.
In AdWords, word is expanded in the coupling except correlativity bidding, generally can increase the relevant evaluation method of commercial factors, such as expansion PPC (pay-per-click, each the deducting fees of clicking of expression advertisement) high word, word that client's degree of depth (number of users of buying certain word of bidding is called client's degree of depth) is high etc.
Generally, there are three kinds for the extended method of query word: the one, phrase match is taken the substring of family query word as recommending word according to correlativity, such as Nokia's mobile phone, can expand Nokia and mobile phone, and wherein Nokia's correlativity is higher than mobile phone.
The 2nd, comprise the expansion coupling, the word that namely extend information is abundanter comprises the word of user search, such as the user search mobile phone, can expand the Samsung mobile phone, htc mobile phone etc., the method for expansion is that former word carries out participle, then by looking into the inverted index of word, find out all words that comprise former word, get a best N word as recommendation results according to correlativity at last.
Three are based on the correlation recommendation of statistics, according to the search daily record of website, search similar search word according to the user search behavior, carry out cluster, recommend related term.Can recommend iphone such as searching handset.
The application also can expand it for the query word of user side input, the candidate word set after at first obtaining to expand.
Step 120 is analyzed search engine real-time logs and/or advertiser's status information of current time and is obtained effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition.
Because search engine based on its performance, has the restriction of maximum search word number, so it can select the wherein the highest term of correlativity.In each expansion word that gets access to for prior art, the keyword (being the word of bidding of customer selecting) of may advertiser wherein having selected, because this advertiser is provided with the displaying condition to the advertisement that himself need to promote, thereby also there is the displaying condition accordingly in the keyword of its selection, if the current show surroundings of search engine does not meet the displaying condition that the user arranges, the advertising display time period that arranges such as the client does not comprise the current displaying time, perhaps the current account balance of client is lower than the displaying remaining sum of its setting etc., even search engine has finally been selected this keyword so, the advertisement that also can't recall advertiser corresponding to this keyword represents, so just waste the retrieval work of search engine, reduced the efficient of search engine.
And the application, for the aforementioned candidate word set that obtains, at first obtain real-time effective set of words, described effective set of words comprises that the current time meets the keyword of displaying condition, such as for " Nokia ", have the advertiser who selects this word, the advertising display time period of its setting comprises the current displaying time, and it is used for the account balance of payment promotion expense greater than the threshold value of its setting simultaneously.Wherein, generally promote at search engine and generally can adopt CPC (Cost Per Click, the each clicking cost of the web advertisement) system to collect advertiser's expense.
For obtaining of effective set of words, generally obtain effective set of words by analyzing search engine real-time logs and/or advertiser's status information of current time.
Preferably, obtain user state information by following steps:
Step S11 obtains database table corresponding to each advertiser from data storage server, and described database table comprises advertiser's advertising expenditure budget and advertiser's advertisement promotion time.
Further, comprising: obtain database table corresponding to each advertiser from data storage server, described database table comprises advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable.
The application is related by database table, the generalized case factor whether advertiser's advertisement reach the standard grade of making decision generally has two, and the one, budget, namely the advertiser is to the setting of own account balance limit value, such as when account balance less than 300 the time, no longer allow advertisement to be demonstrated; The 2nd, the popularization time, namely the advertiser is to the setting of advertisement promotion time, such as at 11 at noon to point in afternoon 1.So can obtain database table corresponding to each advertiser from data storage server analyzes, so can obtain effective set of words by the advertising expenditure budget table of the advertiser in the database table and advertiser's advertisement promotion timetable furtherly, namely obtain and have effective advertiser's degree of depth (effective advertiser's degree of depth: for having bought each advertiser of word that bids, at a time, can be by advertiser's quantity corresponding to the advertisement that this word of bidding represents on line, namely in the described a certain moment, can recall advertiser's quantity corresponding to advertisement that represents from advertisement base by the described word of bidding) keyword (word of bidding).
Preferably, obtain database table corresponding to advertiser after, comprising:
Step S12, analyze described advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, comprise the advertiser of described current time for the advertising expenditure budget greater than threshold value and advertisement promotion time period, the keyword that described advertiser is selected adds effective set of words.
Namely pass through advertiser's advertising expenditure budget table and advertiser's the relevance advertisement promotion timetable and the keyword that the advertiser selects, analyze and obtain effective set of words.
Perhaps, analyze the search engine real-time logs by following steps and obtain effective set of words:
Step S21 obtains the real-time search daily record from search engine;
Step S22 analyzes whether each search key returns advertisement to user side in the described real-time search daily record in current slot;
Step S23 if return, then adds effective set of words with corresponding search key.
In search engine, meeting real time record user search queries word, and the advertisement that represented at that time of search engine, so by the method can obtain this section in the time period user's query word return in real time the advertisement number, the real-time customer degree of depth namely is in this process, if returned in real time advertisement by query word and expansion word thereof, effective word can be thought in these words so, and it is added effective set of words.
Step 130 is utilized described effective set of words, filters out in the set of described candidate word not the word in effective set of words.
After obtaining effective set of words, can process the set of described candidate word, filter out in the described candidate word set not the word in effective set of words.So, can filter out the word that does not have client's degree of depth, namely can not recall the word that advertiser's advertisement represents.Such as, the current time is 14:00, for keyword " Nokia ", the advertiser who buys this word has A, B, C:
For A, the advertising display time that this keyword of its setting is corresponding is 11:00-13:00, and account balance is 1000, and the account balance threshold value of its setting is 300;
For B, the advertising display time that this keyword of its setting is corresponding is 11:00-15:00, and account balance is 100, and the account balance threshold value of its setting is 400;
For C, the advertising display time that this keyword of its setting is corresponding is 18:00-21:00, and account balance is 200, and the account balance threshold value of its setting is 300;
Keyword " Nokia " is for A so, the threshold value 300 that although its account balance arranges greater than A in its displaying condition, but current displaying time point does not meet the requirement of A, represents so the advertisement of the correspondence " Nokia " of A can not be recalled in keyword " Nokia ";
Although current displaying time point meets the requirement of B in its displaying condition for B, its account balance represents so the advertisement of the correspondence " Nokia " of B can not be recalled in keyword " Nokia " less than the threshold value 400 that arranges in B;
For C, current displaying time point does not meet the requirement of C in its displaying condition, the threshold value 300 that its account balance arranges less than C, and keyword " Nokia " advertisement that can not recall the correspondence " Nokia " of B represents so.
Preferred in addition, utilizing described effective set of words, filter out in the set of described candidate word not behind the word in the effective set of words, also comprise:
Step 131 for the candidate word in the set of the candidate word after the described filtration, is calculated the degree of correlation of described candidate word and described query word;
For the candidate word after filtering, can calculate the degree of correlation of described candidate word and described query word, such as literal matched text similarity+Topic Similarity:
The literal text similarity is such as " Nokia's mobile phone " and " Samsung mobile phone ", at first two words are carried out participle, label, " Nokia/brand ", " mobile phone/product ", " Samsung/brand ", " mobile phone/product " is different for its significance level of different labels, such as Product labelling greater than brand label, greater than modifying label, then according to the participle of two words couplings with and label, calculate similar mark.
Topic Similarity such as: based on the theme system of website itself (such as digital product, hardware ﹠ tools, physical culture, amusement), by calculating the information of clicking behind the user search queries word, can calculate the theme tendency of each query word, each query word has one or more theme, according to the number of topics of coupling, calculate the similarity of the two.
Step 132 for the candidate word in the set of the candidate word after the described filtration, is added up effective advertiser's degree of depth of described candidate word; Described effective advertiser's degree of depth is the quantity of selecting described candidate word and meeting the advertiser of described displaying condition in the current time;
For the candidate word after filtering, because it is to utilize effective set of words garbled, can there be effective advertiser's degree of depth in each candidate word so, and namely this word can be recalled the advertisement number that represents in the current time.Such as, for " notebook computer ", the current time is 12:00, the client who buys this word has M1, M2, M3, M4, M5; M1, M2, M3, M4, the displaying time period of the corresponding advertisement of this word of setting comprises 12:00, and M1, M2, M3, M4 account balance separately is greater than the lowest threshold of its setting, and the displaying time period of the corresponding advertisement of this word that M5 arranges does not comprise 12:00, and effective advertiser's degree of depth of word " notebook computer " is 4 so.
Step 133, in conjunction with the weight of the degree of correlation of described candidate word and effectively each candidate word in the candidate word set after to described filtration of the weight of advertiser's degree of depth reorder.
In practice, can weight be set to the degree of correlation of candidate word and query word during ordering, also can weight be set to effective advertiser's degree of depth of this candidate word, but so in conjunction with the weight of the degree of correlation of described candidate word and the effective total weight value of the weight calculated candidate word of advertiser's degree of depth, thereby can sort based on the total weight value of each candidate word.Such as, relevance weight is a, and effectively advertiser's degree of depth weight is b, and for candidate word P, the correlativity of itself and query word is m, and its effective advertiser's degree of depth is n, so the total weight value W=a*m+b*n of word P.
In addition, described database table also comprises advertiser's presence table.Be used to indicate user online status.Preferably, utilizing described effective set of words, filtering out in the set of described candidate word not behind the word in the effective set of words, also comprising:
Step S31 for the candidate word in the set of the candidate word after the described filtration, calculates the degree of correlation of described candidate word and described query word;
Step S32 for the candidate word in the set of the candidate word after the described filtration, adds up effective advertiser's degree of depth of described candidate word; Described effective advertiser's degree of depth is the quantity of selecting described candidate word and meeting the advertiser of described displaying condition in the current time;
Step S33, statistics is selected described candidate word and is met the online advertisement client's of described displaying condition quantity in the current time;
Step S34 is in conjunction with the weight of the degree of correlation of described candidate word, effectively each candidate word in the candidate word set after to described filtration of the weight of advertiser's degree of depth and online advertisement customer quantity reorders.
What the application also can be candidate word arranges a weight in wire advertiser quantity, it is added total weight value calculate.
Preferred with in the candidate word after the aforementioned ordering, choose forward at least one candidate word retrieve advertisements information in search engine of ordering.
With reference to Fig. 2, the structural representation that it shows a kind of advertising message search system of the application comprises:
Query word expansion module 210 is used for the query word of user side input is expanded, the candidate word set after obtaining to expand;
Effectively set of words acquisition module 220 is used for analysis search engine real-time logs and/or advertiser's status information of current time and obtains effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition;
Preferably, described effective set of words acquisition module comprises:
User state information obtains submodule, is used for obtaining database table corresponding to each advertiser from data storage server, and described database table comprises advertiser's advertising expenditure budget and advertiser's advertisement promotion time.
Described database table comprises advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, respectively corresponding advertiser's advertising expenditure budget and advertisement promotion time.
Described effective set of words acquisition module also comprises:
User Status is analyzed submodule, be used for analyzing described advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, comprise the advertiser of described current time for the advertising expenditure budget greater than threshold value and advertisement promotion time period, the keyword of described advertisement selection is added effective set of words.
Described effective set of words acquisition module comprises:
Real-time logs obtains submodule, is used for obtaining the real-time search daily record from search engine;
Real-time logs is analyzed submodule, is used for analyzing described each search key of real-time search daily record and whether returns advertisement to user side in current slot; If return, then corresponding search key is added effective set of words.
With reference to Fig. 3, the structural representation that it shows the preferred a kind of advertising message search system of the application comprises:
User's query word processing server 310, search engine server 320, data storage server 330;
Described user's query word processing server 310 is used for the user's of reception search engine server 320 front ends acquisition original query word, and obtains described advertiser's status information to storage in the described data storage server 330; And/or the real-time search daily record of search engine server 320 processes query word, and the word that processing obtains is returned search engine server 320.
Described user's query word processing server 310 comprises: the query word expansion module is used for the query word of user side input is expanded the candidate word set after obtaining to expand;
Effective set of words acquisition module, the advertiser's status information that is used for the current time obtains effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition;
Filtering module is used for utilizing described effective set of words, filters out in the described candidate word set not the word in effective set of words.
Described search engine server 320 is used for the original query word input user query word processing server 310 with user's input, and User query word processing server 310 carries the term of coming to carry out final advertisement retrieval.Wherein, described search engine server comprises retrieval module, at least one the candidate word retrieve advertisements information of candidate word set after being used for selecting to filter.
Described data storage server 330 is used for advertiser's status information of storage.
For system embodiment because itself and embodiment of the method basic simlarity, so describe fairly simple, relevant part gets final product referring to the part explanation of embodiment of the method.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is and the difference of other embodiment that identical similar part is mutually referring to getting final product between each embodiment.
The application is that reference is described according to process flow diagram and/or the block scheme of method, equipment (system) and the computer program of the embodiment of the present application.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or the block scheme and/or square frame and process flow diagram and/or the block scheme and/or the combination of square frame.Can provide these computer program instructions to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device producing a machine, so that the instruction of carrying out by the processor of computing machine or other programmable data processing device produces the device of the function that is used for being implemented in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame appointments.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, so that the instruction that is stored in this computer-readable memory produces the manufacture that comprises command device, this command device is implemented in the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame.These computer program instructions also can be loaded on computing machine or other programmable data processing device, so that carry out the sequence of operations step producing computer implemented processing at computing machine or other programmable devices, thereby be provided for being implemented in the step of the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame in the instruction that computing machine or other programmable devices are carried out.
Although described the application's preferred embodiment, in a single day those skilled in the art get the basic creative concept of cicada, then can make other change and modification to these embodiment.So claims are intended to all changes and the modification that are interpreted as comprising preferred embodiment and fall into the application's scope.
More than a kind of advertising message searching method and system that the application is provided, be described in detail, used specific case herein the application's principle and embodiment are set forth, the explanation of above embodiment just is used for helping to understand the application's method and core concept thereof; Simultaneously, for one of ordinary skill in the art, the thought according to the application all will change in specific embodiments and applications, and in sum, this description should not be construed as the restriction to the application.
Claims (14)
1. an advertising message searching method is characterized in that, comprising:
The query word of user side input is expanded the candidate word set after obtaining to expand;
Analyze search engine real-time logs and/or advertiser's status information of current time and obtain effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition;
Utilize described effective set of words, filter out in the set of described candidate word not the word in effective set of words;
At least one candidate word retrieve advertisements information in the candidate word set after selecting to filter.
2. method according to claim 1 is characterized in that, obtains user state information by following steps:
Obtain database table corresponding to each advertiser from data storage server, described database table comprises advertiser's advertisement gift presented to a senior at one's first visit as a mark of esteem usefulness budget and advertiser's advertisement promotion time.
3. method according to claim 2 is characterized in that:
Described database table comprises advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, respectively corresponding advertiser's advertising expenditure budget and advertisement promotion time.
4. method according to claim 3 is characterized in that, obtain database table corresponding to advertiser after, comprising:
Analyze described advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, comprise the advertiser of described current time for the advertising expenditure budget greater than threshold value and advertisement promotion time period, the keyword of described advertisement selection is added effective set of words.
5. method according to claim 1 is characterized in that, analyzes the search engine real-time logs by following steps and obtains effective set of words:
Obtain the real-time search daily record from search engine;
Analyze whether each search key returns advertisement to user side in the described real-time search daily record in current slot;
If return, then corresponding search key is added effective set of words.
6. method according to claim 1 is characterized in that, is utilizing described effective set of words, filters out in the set of described candidate word not behind the word in the effective set of words, also comprises:
For the candidate word in the set of the candidate word after the described filtration, calculate the degree of correlation of described candidate word and described query word;
For the candidate word in the set of the candidate word after the described filtration, add up effective advertiser's degree of depth of described candidate word; Described effective advertiser's degree of depth is the quantity of selecting described candidate word and meeting the advertiser of described displaying condition in the current time;
In conjunction with the weight of the degree of correlation of described candidate word and effectively each candidate word in the candidate word set after to described filtration of the weight of advertiser's degree of depth reorder.
7. according to claim 3,4,6 one of them described method, it is characterized in that:
Described database table also comprises advertiser's presence table.
8. method according to claim 1 is characterized in that, is utilizing described effective set of words, filters out in the set of described candidate word not behind the word in the effective set of words, also comprises:
For the candidate word in the set of the candidate word after the described filtration, calculate the degree of correlation of described candidate word and described query word;
For the candidate word in the set of the candidate word after the described filtration, add up effective advertiser's degree of depth of described candidate word; Described effective advertiser's degree of depth is the quantity of selecting described candidate word and meeting the advertiser of described displaying condition in the current time;
Statistics is selected described candidate word and is met the online advertisement client's of described displaying condition quantity in the current time;
In conjunction with the weight of the degree of correlation of described candidate word, effectively each candidate word in the candidate word set after to described filtration of the weight of advertiser's degree of depth and online advertisement customer quantity reorders.
9. method according to claim 1 is characterized in that, the query word of user side input is expanded, and the candidate word after obtaining to expand comprises when gathering:
Obtain the new keyword of selecting of advertiser, described keyword is added the expansion dictionary;
Calculate the correlativity of each keyword in described query word and the expansion dictionary, when described correlativity during greater than threshold value, described keyword is added the candidate word set.
10. an advertising message search system is characterized in that, comprising:
The query word expansion module is used for the query word of user side input is expanded, the candidate word set after obtaining to expand;
Effectively the set of words acquisition module is used for analysis search engine real-time logs and/or advertiser's status information of current time and obtains effective set of words; Described advertiser's status information comprises the keyword displaying conditional information that the advertiser selects; Described effective set of words comprises that the current time meets the keyword of displaying condition;
Filtering module is used for utilizing described effective set of words, filters out in the described candidate word set not the word in effective set of words;
Retrieval module, at least one the candidate word retrieve advertisements information of candidate word set after being used for selecting to filter.
11. system according to claim 10 is characterized in that, described effective set of words acquisition module comprises:
User state information obtains submodule, is used for obtaining database table corresponding to each advertiser from data storage server, and described database table comprises advertiser's advertising expenditure budget and advertiser's advertisement promotion time.
12. system according to claim 11 is characterized in that:
Described database table comprises advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, respectively corresponding advertiser's advertising expenditure budget and advertisement promotion time.
13. system according to claim 12 is characterized in that, described effective set of words acquisition module also comprises:
User Status is analyzed submodule, be used for analyzing described advertiser's advertising expenditure budget table and advertiser's advertisement promotion timetable, comprise the advertiser of described current time for the advertising expenditure budget greater than threshold value and advertisement promotion time period, the keyword of described advertisement selection is added effective set of words.
14. system according to claim 10 is characterized in that, described effective set of words acquisition module comprises:
Real-time logs obtains submodule, is used for obtaining the real-time search daily record from search engine;
Real-time logs is analyzed submodule, is used for analyzing described each search key of real-time search daily record and whether returns advertisement to user side in current slot; If return, then corresponding search key is added effective set of words.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210097984.0A CN103365904B (en) | 2012-04-05 | 2012-04-05 | A kind of advertising message searching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210097984.0A CN103365904B (en) | 2012-04-05 | 2012-04-05 | A kind of advertising message searching method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103365904A true CN103365904A (en) | 2013-10-23 |
| CN103365904B CN103365904B (en) | 2018-01-09 |
Family
ID=49367268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210097984.0A Active CN103365904B (en) | 2012-04-05 | 2012-04-05 | A kind of advertising message searching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103365904B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104702597A (en) * | 2015-02-09 | 2015-06-10 | 北京博雅立方科技有限公司 | Information obtaining method and device |
| CN104715022A (en) * | 2015-02-28 | 2015-06-17 | 北京奇艺世纪科技有限公司 | Relevant searching method and device |
| CN105446984A (en) * | 2014-06-30 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Expansion word pair screening method and device |
| CN106294688A (en) * | 2016-08-05 | 2017-01-04 | 浪潮软件集团有限公司 | Query expansion method, device and system based on user characteristic analysis |
| CN106557480A (en) * | 2015-09-25 | 2017-04-05 | 阿里巴巴集团控股有限公司 | Implementation method and device that inquiry is rewritten |
| CN106708886A (en) * | 2015-11-17 | 2017-05-24 | 北京国双科技有限公司 | Website search word display method and device |
| CN107038608A (en) * | 2017-04-21 | 2017-08-11 | 北京恒冠网络数据处理有限公司 | A kind of big data analysis system |
| CN110020053A (en) * | 2017-12-20 | 2019-07-16 | 北京奇虎科技有限公司 | Acquisition methods, device and the computer readable storage medium of advertisement main information |
| CN110309355A (en) * | 2018-06-15 | 2019-10-08 | 腾讯科技（深圳）有限公司 | Generation method, device, equipment and the storage medium of content tab |
| CN112686717A (en) * | 2021-03-11 | 2021-04-20 | 腾讯科技（深圳）有限公司 | Data processing method and system for advertisement recall |
| CN113763010A (en) * | 2020-11-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034997A (en) * | 2006-03-09 | 2007-09-12 | 新数通兴业科技（北京）有限公司 | Method and system for accurately publishing the data information |
| CN101055587A (en) * | 2007-05-25 | 2007-10-17 | 清华大学 | Search engine retrieving result reordering method based on user behavior information |
| CN101266603A (en) * | 2007-03-12 | 2008-09-17 | 北京搜狗科技发展有限公司 | Webpage information sorting method, system and service system applying the classification |
| CN101331487A (en) * | 2005-12-15 | 2008-12-24 | 微软公司 | Advertising keyword cross-selling |
| CN101488209A (en) * | 2008-01-18 | 2009-07-22 | 里斯特有限公司 | Advertisement broadcasting method of individual media |
| CN101673385A (en) * | 2009-09-28 | 2010-03-17 | 百度在线网络技术（北京）有限公司 | Consumption preliminary estimate method and device thereof |
| CN101887437A (en) * | 2009-05-12 | 2010-11-17 | 阿里巴巴集团控股有限公司 | Search result generating method and information search system |
-
2012
- 2012-04-05 CN CN201210097984.0A patent/CN103365904B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101331487A (en) * | 2005-12-15 | 2008-12-24 | 微软公司 | Advertising keyword cross-selling |
| CN101034997A (en) * | 2006-03-09 | 2007-09-12 | 新数通兴业科技（北京）有限公司 | Method and system for accurately publishing the data information |
| CN101266603A (en) * | 2007-03-12 | 2008-09-17 | 北京搜狗科技发展有限公司 | Webpage information sorting method, system and service system applying the classification |
| CN101055587A (en) * | 2007-05-25 | 2007-10-17 | 清华大学 | Search engine retrieving result reordering method based on user behavior information |
| CN101488209A (en) * | 2008-01-18 | 2009-07-22 | 里斯特有限公司 | Advertisement broadcasting method of individual media |
| CN101887437A (en) * | 2009-05-12 | 2010-11-17 | 阿里巴巴集团控股有限公司 | Search result generating method and information search system |
| CN101673385A (en) * | 2009-09-28 | 2010-03-17 | 百度在线网络技术（北京）有限公司 | Consumption preliminary estimate method and device thereof |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446984A (en) * | 2014-06-30 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Expansion word pair screening method and device |
| CN104702597A (en) * | 2015-02-09 | 2015-06-10 | 北京博雅立方科技有限公司 | Information obtaining method and device |
| CN104715022A (en) * | 2015-02-28 | 2015-06-17 | 北京奇艺世纪科技有限公司 | Relevant searching method and device |
| CN104715022B (en) * | 2015-02-28 | 2018-07-31 | 北京奇艺世纪科技有限公司 | A kind of related search method and device |
| CN106557480B (en) * | 2015-09-25 | 2020-07-07 | 阿里巴巴集团控股有限公司 | Method and device for realizing query rewriting |
| CN106557480A (en) * | 2015-09-25 | 2017-04-05 | 阿里巴巴集团控股有限公司 | Implementation method and device that inquiry is rewritten |
| CN106708886A (en) * | 2015-11-17 | 2017-05-24 | 北京国双科技有限公司 | Website search word display method and device |
| CN106708886B (en) * | 2015-11-17 | 2020-08-11 | 北京国双科技有限公司 | Display method and device for in-site search words |
| CN106294688A (en) * | 2016-08-05 | 2017-01-04 | 浪潮软件集团有限公司 | Query expansion method, device and system based on user characteristic analysis |
| CN107038608A (en) * | 2017-04-21 | 2017-08-11 | 北京恒冠网络数据处理有限公司 | A kind of big data analysis system |
| CN110020053A (en) * | 2017-12-20 | 2019-07-16 | 北京奇虎科技有限公司 | Acquisition methods, device and the computer readable storage medium of advertisement main information |
| CN110309355A (en) * | 2018-06-15 | 2019-10-08 | 腾讯科技（深圳）有限公司 | Generation method, device, equipment and the storage medium of content tab |
| CN110309355B (en) * | 2018-06-15 | 2023-05-16 | 腾讯科技（深圳）有限公司 | Content tag generation method, device, equipment and storage medium |
| CN113763010A (en) * | 2020-11-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
| CN112686717A (en) * | 2021-03-11 | 2021-04-20 | 腾讯科技（深圳）有限公司 | Data processing method and system for advertisement recall |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103365904B (en) | 2018-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103365904A (en) | Advertising information searching method and system | |
| CN107526807B (en) | Information recommendation method and device | |
| JP5778255B2 (en) | Method, system, and apparatus for query based on vertical search | |
| Vargiu et al. | Exploiting web scraping in a collaborative filtering-based approach to web advertising. | |
| CN102096717B (en) | Search method and search engine | |
| CN102142033B (en) | Method and device for providing relative sub-link information in search result | |
| CN100476830C (en) | Network resource searching method and system | |
| CN103886017B (en) | A kind of for providing the method and apparatus of related sub links in Search Results | |
| CN105808685A (en) | Promotion information pushing method and device | |
| CN103399883A (en) | Method and system for performing personalized recommendation according to user interest points/concerns | |
| US9996630B2 (en) | System and/or method for linking network content | |
| CN101984420B (en) | Method and equipment for searching pictures based on word segmentation processing | |
| CN103729777A (en) | Online shopping method, device and system based on image recognition technology | |
| CN102880969A (en) | Advertisement putting method, advertisement putting server and advertisement putting system | |
| CN102037464A (en) | Search results with most clicked next objects | |
| CN103345695A (en) | Commodity recommendation method and device | |
| CN102938123A (en) | Method for recommending commodity information to user | |
| CN106062743A (en) | Systems and methods for keyword suggestion | |
| CN102708174A (en) | Method and device for displaying rich media information in browser | |
| CN103530414B (en) | Web Page Key Words open up word method and apparatus | |
| CN102855309A (en) | Information recommendation method and device based on user behavior associated analysis | |
| CN103186595A (en) | Method and system for recommending audios/videos | |
| CN111582951A (en) | Advertisement putting system and method for cloud electronic commerce | |
| CN102231152B (en) | Searching method for precisely inquiring based on IP (Internet Protocol) address of mobile terminal | |
| CN103186666A (en) | Method, device and equipment for searching based on favorites |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1186796 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: GR Ref document number: 1186796 Country of ref document: HK |