CN106339382A - Method and device for pushing business objects - Google Patents
Method and device for pushing business objects Download PDFInfo
- Publication number
- CN106339382A CN106339382A CN201510395205.9A CN201510395205A CN106339382A CN 106339382 A CN106339382 A CN 106339382A CN 201510395205 A CN201510395205 A CN 201510395205A CN 106339382 A CN106339382 A CN 106339382A
- Authority
- CN
- China
- Prior art keywords
- participle
- business object
- candidate traffic
- target service
- key word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
One embodiment of the application provides a method and device for pushing business objects. The method comprises following steps: when keywords are received, the keywords are partitioned to obtain one or more first partitioned words; business objects matched with the first partitioned words are searched in a preset index file; candidate business objects which are correlative to the keywords are selected from the business objects; target business objects which satisfy a preset quality condition are selected from the candidate business objects; the target business objects are pushed. The embodiment of the application realizes automatic pushing of business objects so that there is no need for users to execute operations such as selecting keywords, optimizing or ranking, which greatly increases the simplicity of operation and reduces use cost; therefore, push can be carried out in long tail flow and the utilization of long tail flow is increased.
Description
Technical field
The application is related to the technical field of computer disposal, more particularly to a kind of push side of business object
Method and a kind of pusher of business object.
Background technology
With the fast development of the network technology, the product information of the integrated numerous users of the various network platform,
It is easy to each website to exchange with other users by this network platform.
Backend user is to allow more front end user obtain the product information of oneself, generally has two ways
Footpath, one is by way of naturally searching for；Two is by way of competition is promoted.
First kind of way competition is fiercer, and optimization cycle is longer, therefore, a lot of backend user meetings
Therefore select the more efficiently second way, this way of promotion is also called key word and promotes, that is,
Backend user needs key word is pre-selected, and product information is matched under this key word, if front end
User searches this key word, then platform pushes phase after the operation such as a series of optimization, sequence
The product information answered it can be seen that, the selection of key word has very for the push effect of product information
Big impact.
For the angle of user, the network platform typically can provide the key word of magnanimity by backend user
Select, and the key word of magnanimity has the larger requirement of ratio to the operational capacity of backend user, for big
For certain customers, operation is more complicated, and backend user is not known for the key word of magnanimity
How to select, threshold is higher, particularly experience compares shortage, operational capacity is not good new hand
For, use cost can be very high.
For the angle pushing, current push mode, from selecting key word, to optimization, then
Arrive a series of processes such as ranking, user often feels complex, and completing the first step may just not
How this knowing below is carried out.
From the point of view of the network platform, for substantial amounts of flow, particularly long-tail flow (non-selected pass
The search flow that keyword is brought) utilization rate is high.Specifically, current push mode needs
Want user to select key word in advance, but these key words be all to obtain from historical search daily record,
The word being likely to occur for future is unpredictable, leads to the coverage rate of key word very low, a lot of flows
On do not have corresponding information so that this partial discharge cause waste.
Content of the invention
In view of the above problems it is proposed that the embodiment of the present application is to provide one kind to overcome the problems referred to above or extremely
The method for pushing of a kind of business object that partially solves the above problems and accordingly a kind of business object
Pusher.
In order to solve the above problems, this application discloses a kind of method for pushing of business object, comprising:
When receiving key word, described key word is carried out with word segmentation processing, obtain one or more first
Participle；
In preset index file, search the business object mated with each first participle；
The candidate Traffic object related to described key word is chosen from described business object；
The target service object meeting default quality requirements is chosen from described candidate Traffic object；And
Push described target service object.
Alternatively, described in preset index file, search the industry mated with each first participle respectively
The step of business object includes:
In preset index file, search the second participle mating with each first participle, wherein, institute
Stating the second participle is the participle that the text message in described business object is carried out with word segmentation processing acquisition；With
And,
Search the business object of described second participle mapping.
Alternatively, the described selection candidate Traffic object related to described key word from described business object
Step include:
At least filter out the common factor of the business object mated with the part first participle, obtain candidate Traffic pair
As.
Alternatively, the described common factor at least filtering out the business object mated with the part first participle, is obtained
The step of candidate Traffic object includes:
At least intercept the business object that part is mated with the first participle；And
At least filter out the common factor of the business object of intercepting, obtain candidate Traffic object.
Alternatively, the described selection candidate Traffic object related to described key word from described business object
Step also include:
Search one or more first classifications, the Equations of The Second Kind of described candidate Traffic object of described keyword
Mesh；
Search one or more of first classifications and described Equations of The Second Kind purpose dependency；
Choose dependency highest one or more candidate Traffic object.
Alternatively, described selection from described candidate Traffic object meets the target industry of default quality requirements
The step of business object includes:
Obtain the degree of association of described candidate Traffic object and described key word and estimate clicking rate；
Quality score is calculated with described clicking rate of estimating using described degree of association；
Choose described quality score and meet the candidate Traffic object of default quality requirements as target service
Object.
Alternatively, described selection from described candidate Traffic object meets the target industry of default quality requirements
The step of business object also includes:
According to described quality score, described target service object is ranked up.
The embodiment of the present application also discloses a kind of pusher of business object, comprising:
Word segmentation processing module, for when receiving key word, word segmentation processing being carried out to described key word,
Obtain one or more first participles；
Business object searching modul, for, in preset index file, searching and each first participle
The business object joined；
Candidate Traffic object select module is related to described key word for choosing from described business object
Candidate Traffic object；
Target service object select module, meets default matter for choosing from described candidate Traffic object
The target service object of amount condition；And
Target service Object Push module, for pushing described target service object.
Alternatively, described business object searching modul includes:
First lookup submodule, for, in preset index file, searching and mating with each first participle
The second participle, wherein, described second participle is to carry out participle to the text message in described business object
Process the participle obtaining；And,
Second lookup submodule, for searching the business object of described second participle mapping.
Alternatively, described candidate Traffic object select module includes:
Occur simultaneously screening submodule, at least filtering out the friendship of the business object mated with the part first participle
Collection, obtains candidate Traffic object.
Alternatively, the described screening submodule that occurs simultaneously includes:
Intercept submodule, at least intercepting the business object that part is mated with the first participle；And
Candidate Traffic object obtains submodule, at least filtering out the common factor of the business object of intercepting, obtains
Obtain candidate Traffic object.
Alternatively, described candidate Traffic object select module also includes:
Classification acquisition submodule, for searching one or more first classifications of described keyword, described time
Select the second classification of business object；
Correlation calculations submodule, for searching one or more of first classifications and described second classification
Dependency；
Dependency chooses submodule, for choosing dependency highest one or more candidate Traffic object.
Alternatively, described target service object select module includes:
Candidate information acquisition submodule is related to described key word for obtaining described candidate Traffic object
Spend and estimate clicking rate；
Quality score calculating sub module, for calculating quality using described degree of association with described clicking rate of estimating
Scoring；
Quality score chooses submodule, meets the time of default quality requirements for choosing described quality score
Select business object as target service object.
Alternatively, described target service object select module also includes:
Sorting sub-module, for being ranked up to described target service object according to described quality score.
The embodiment of the present application includes advantages below:
The business object of coupling searched in the participle based on key word for the embodiment of the present application, and then carries out dependency
With the screening of quality, return the target service object selected it is achieved that the automatic push of business object, use
Family does not need the Yu Xianxuanding operation such as key word, optimization, ranking, has significantly passed through the simplicity operating,
Reduce use cost, and then also can be pushed in long-tail flow, improve the utilization of long-tail flow
Rate.
Brief description
Fig. 1 is a kind of flow chart of steps of the method for pushing embodiment of business object of the application；
Fig. 2 is a kind of structured flowchart of the pusher embodiment of business object of the application.
Specific embodiment
Understandable for enabling the above-mentioned purpose of the application, feature and advantage to become apparent from, below in conjunction with the accompanying drawings
With specific embodiment, the application is described in further detail.
With reference to Fig. 1, show a kind of steps flow chart of the method for pushing embodiment of business object of the application
Figure, the method 100 specifically may include steps of:
Step 101, when receiving key word, carries out word segmentation processing, obtains one to described key word
Or the multiple first participle；
Generally, user can be by client (as browser etc.) loading page (as e-commerce website
The page, the page of search engine etc.), input key word (query) in the page, if user clicks on
The controls such as " confirmation ", " search ", then client can be to the network platform (server or server cluster)
Submit searching request to, this searching request can include this key word (query).
If the network platform receives the key word of client submission, on the one hand, can be used for searching for correlation
Product, webpage etc., on the other hand, can be used for retrieving related business object.
In the related business object of retrieval, word segmentation processing can be carried out.
In implementing, word segmentation processing can be carried out in the following manner:
1st, the segmenting method based on string matching: refer to the Chinese being analysed to according to certain strategy
Entry in the word string machine dictionary preset with is mated, if finding certain word in dictionary
Symbol string, then the match is successful (identifying a word).
2nd, the segmenting method of feature based scanning or mark cutting: refer to preferentially in character string to be analyzed
Middle identify and be syncopated as some carry obvious characteristic words, using these words as breakpoint, can be by former word
Symbol string is divided into less string to enter mechanical Chinese word segmentation again；Or participle and part-of-speech tagging are combined,
There is provided help using abundant grammatical category information to participle decision-making, and in annotation process again in turn
Word segmentation result is tested, adjusts.
3rd, based on understand segmenting method: refer to by allow computer mould personification distich understanding,
Reach the effect of identification word.Its basic thought is exactly to carry out syntax, semantic analysis while participle,
Process Ambiguity using syntactic information and semantic information.
4th, the segmenting method based on statistics: the frequency to each combinatorics on words of co-occurrence adjacent in language material
Counted, calculate their information that appears alternatively, and the adjacent co-occurrence of calculating two Chinese characters x, y is general
Rate.The information of appearing alternatively can embody the tightness degree of marriage relation between Chinese character.When tightness degree is higher than
During some threshold value, just it is believed that this word group may constitute a word.
Certainly, above-mentioned word segmentation processing mode is intended only as example, when implementing the embodiment of the present application,
Can be so that other word segmentation processing modes be arranged according to practical situation, the embodiment of the present application is not limited to this
System.In addition, in addition to above-mentioned word segmentation processing mode, those skilled in the art can also be according to reality
Need using other word segmentation processing modes, the embodiment of the present application is not also any limitation as to this.
Step 102, in preset index file, searches the business object mated with each first participle；
Application the embodiment of the present application, can adopt business object to generate index file in advance.
For different business field, can have different business objects, that is, there is business scope special
The object levied.
For example, for news media field, business object can be news data；For mobile logical
For news field, business object can be mobile communication data；For ecommerce (electronic
Commerce, ec) for field, business object can be ad data, etc..
Although business object carries different traffic performances, its essence remains data, for example, text,
View data, voice data, video data etc..
For making those skilled in the art more fully understand the embodiment of the present application, in the embodiment of the present application, will
Advertisement illustrates as a kind of example of business object.
In a preferred embodiment of the present application, step 102 can include following sub-step:
Sub-step s11, in preset index file, searches second point mating with each first participle
Word, wherein, described second participle is to carry out word segmentation processing acquisition to the text message in described business object
Participle；And,
Sub-step s12, searches the business object of described second participle mapping.
In the embodiment of the present application, user can preselect the business object needing to push, to this business
Text message in object, such as title (title), carry out word segmentation processing, obtain the second participle,
It is also possible to apply the segmenting method based on string matching, feature based to sweep in implementing
Retouch or indicate cutting segmenting method, based on understand segmenting method, based on statistics segmenting method
Carry out word segmentation processing etc. mode.
In common index file (as the index file of ad data), use a pass
The form of the corresponding n business object (as ad data) of keyword, expression specific as follows:
keyword→ad1-ad2-……
Wherein, keyword is key word, and ad1, ad2 are business object.
The business objects such as ad1, ad2 are that the user belonging to it selectes key word on network platform backstage,
Front end user is just pushed when searching this key word.
For example, if the user of rear end is " red mp3player " for the keyword that ad1 selectes, when
And if only if front end user search " red mp3player " and when can represent ad1.
Not in common index file, the embodiment of the present application is belonging to the push form automatically triggering,
Backend user does not need to select key word for business object in advance, thus without as common index literary composition
Part directly sets up index file with key word, but sets up index file: its shape using business object
Formula can be as follows
term→ad1-ad2-……
Wherein, term comes from the second participle of the text message of business object, and ad1, ad2 are industry
Business object.
For example, certain title as ad data is " 8g blue mp3player ", and title is through undue
Word has four the second participles, respectively " 8g ", " blue ", " mp3 ", " player " after processing,
So term is " 8g ", " blue ", " mp3 ", " player ", is linked respectively by this four term
To the ad data containing these term.
The network platform extracted all of business object text message carry out word segmentation processing after, right
All the second participle index building files of business object, therefore, this index file is also referred to as full text rope
Draw.
Accordingly, the network platform searches for industry to key word (query) on the basis of full-text index
Business object, can be referred to as full-text search, and the principle of retrieval is similar with the process building full-text index,
First key word (query) is carried out word segmentation processing and form the first participle (term), then by first point
Word (term) removes to search second participle (term) of coupling in full-text index, then searches this second point
The business object that word (term) maps.
It should be noted that for each first participle (term), the second of coupling can be searched
Participle (term) and its business object of mapping.
For example, after the network platform carries out word segmentation processing to certain key word (query), acquisition term1,
Tri- first participles of term2, term3, its example is expressed as below:
query→term1、term2、term3；
In indexed file, second participle term1, term2, term3 of mating with this three first participles
It is respectively provided with the business object (ad1-ad5) of mapping, its example is expressed as below:
term1→ad1-ad2-ad3
term2→ad2-ad3-ad4
term3→ad2-ad3-ad5
Step 103, chooses the candidate Traffic object related to described key word from described business object；
The business object finding in indexed file might not be all corresponding to key word (query)
Business object, may only mate certain first participle (as only contained certain in some business objects
The second participle mating with the first participle), the actual and business object phase described by key word (query)
Difference is farther out.
For example, key word (query) is " blue mp3player ", and the business object that certain finds
It is probably " blue shoe ", both differences are farther out.
Therefore, in the embodiment of the present application, can select from the business object mated with each first participle
Take the candidate Traffic object related to key word (query)；
In a preferred embodiment of the present application, step 103 can include following sub-step:
Sub-step s21, at least filters out the common factor of the business object mated with the part first participle, obtains
Candidate Traffic object.
In the embodiment of the present application, in order to ensure the dependency of key word (query) and business object,
The business object retrieving comprises the first participle in key word (query) as far as possible, can be to first point
The business object that word finds takes common factor.
Furthermore, in order to ensure the dependency of maximum, can filter out and mate with the whole first distribution
Business object common factor, obtain candidate Traffic object.
The industry that the business object of certain first participle coupling is mated with another first participle can be adopted one by one
Business object is contrasted, if identical, retains, if it is different, then removing, circulates identical business pair
Business object as being mated with next first participle is contrasted, until traveled through all with the first participle
Join business object.
For example, if the business object finding is as follows:
term1→ad1-ad2-ad3
term2→ad2-ad3-ad4
term3→ad2-ad3-ad5
Then the common factor of the business object of term1, term2, term3 is ad2 and ad3.
In a kind of preferred exemplary of the embodiment of the present application, sub-step s21 can include following son further
Step:
Sub-step s221, at least intercepts the business object that part is mated with the first participle；
Sub-step s222, at least filters out the common factor of the business object of intercepting, obtains candidate Traffic object.
Because business object is excessive, show to client and bring performance burden, the performance of the network platform is had
Larger burden, therefore, in this example, reduces the quantity of business object by the way of blocking.
Block, can be at least intercepting the business object that part is mated with the first participle in a random fashion
In implementing, according to the id of business object, business object can be ranked up, due to id
It is random, therefore, the sequence of business object is also random, then can choose sequence preceding n
Business object, wherein, n is positive integer.
In a preferred embodiment of the present application, step 103 can also include following sub-step:
Sub-step s22, searches one or more first classifications of described keyword, described candidate Traffic pair
Second classification of elephant；
Sub-step s23, searches one or more of first classifications and described Equations of The Second Kind purpose dependency；
Sub-step s24, chooses dependency highest one or more candidate Traffic object.
It is usually the search meaning needing with front end user when business object is finally presented in face of front end user
Figure correlation, the push being otherwise likely to result in business object is meaningless, waste of resource.
Pass through in indexed file to search the Candidate Set (business object mated with each first participle obtaining
Set) typically all larger, the dependency of business object is relatively difficult to ensure card, if front end user search " blue
Shirt ", if only occurring in that " blue " in the title of certain business object, and this business object is substantially
" blue shoe ", is differed greatly with the product (" blue shirt ") of front end user actual search, if directly
Connect and recall this business object, the experience to front end user is very bad, to the business object of backend user
Promotion effect also can be undesirable.
Therefore, the embodiment of the present application is solved by the way of thick row.
Thick row, can refer to the classification dependency of simple computation key word and business object, retention relationship is relatively
Good business object, looks after the experience of front end user.
Application the embodiment of the present application, can count between each class content now and each classification in advance
Relevance weight, by the first classification of this content search keyword, or the Equations of The Second Kind of configuration service object
Mesh.
In actual applications, due to the uncertainty of keyword, therefore, it can there is one or more
One classification, for example, the classification sectional drawing of keyword " duck " is clothing, luggage case, stationery etc..
And business object has determined that, its second classification is unique, if business object is pencil,
Second classification of this business object is stationery.
The classification whether phase of key word when calculating the first classification and Equations of The Second Kind purpose dependency, can be checked
Close, if the relevance weight between the first classification and the second classification is lower, represent that phase dependency is higher, instead
It, the relevance weight between the first classification and the second classification is higher, represents that phase dependency is lower.
For example, the Equations of The Second Kind purpose relevance weight difference of the first classification of certain key word and business object
For c1:0, c2:0, c3:1, c4:2, ": " above represents the first classification with this key word, after ": "
Expression this first and second classification relevance weight, if the second classification of business object is c2,
First classification c1 and Equations of The Second Kind purpose relevance weight are 0.
Step 104, chooses the target service meeting default quality requirements from described candidate Traffic object
Object；And
The good relationship of the candidate Traffic object obtaining after the dependency screening of step 103, in order to
More preferably lift the search experience of front end user, help backend user to realize as far as possible precisely pushing, simultaneously
Also it is the utilization ratio of lifting website traffic, quality can be carried out to the candidate Traffic object after the screening of closing property and comment
Estimate, push after it meets certain quality requirements.
In a preferred embodiment of the present application, step 104 can include following sub-step:
Sub-step s31, obtains the degree of association of described candidate Traffic object and described key word and estimates click
Rate；
Sub-step s32, calculates quality score using described degree of association with described clicking rate of estimating；
Sub-step s33, chooses the candidate Traffic object work that described quality score meets default quality requirements
For target service object.
In the embodiment of the present application, can be to candidate Traffic calculation and object quality score, to characterize its quality
Height.
Wherein, including the degree of association (mating dependency) of candidate Traffic object and key word (query),
And estimate clicking rate.
The computing formula of quality score is briefly described as follows:
Quality score=f (relevence, ctr)
Wherein, relevance represents the degree of association of candidate Traffic object and key word, and ctr represents and estimates a little
Hit rate, that is, under this key word, the clicked probability of this candidate Traffic object, f () is one and degree of association
The function related with estimating clicking rate, its outcome quality scoring quality score is a comprehensive fraction,
Can be used for portraying the matching degree of business object and search need.
For example, in certain f () function, query score=relevance level+ctr*weight
Wherein, relevance level is the gear drawn using relevance algorithms, and ctr represents and estimates click
Rate, the weighted value that weight selects according to practical business scene.
Meet the push that certain mass condition carries out business object, one allows for the experience of front end user,
Two is the push effect lifting backend user as far as possible, is also finally from the point of view of network platform angle, greatly
Improve the business object treatment effeciency of website, reach tripartite's win-win.
Furthermore, this quality requirements can for the one or more quality score of highest or
Quality score exceedes default scoring threshold value, can also be both combinations, etc., the embodiment of the present application
This is not any limitation as.
In a preferred embodiment of the present application, step 104 can also include following sub-step:
Sub-step s34, is ranked up to described target service object according to described quality score.
In the embodiment of the present application, the sequence of the higher target service object of quality score can also more be leaned on
Before, conversely, the sequence of the lower target service object of quality score can also be further ensured that more rearward
The experience of front end user.
Step 105, pushes described target service object.
In implementing, the network platform can respond to the searching request of client, will find
Target service Object Push to client, loaded by client, showed front end user.
If in the computer clusters such as distributed system, after application server receives key word, determining mesh
Mark business object, the id according to this destination object asks the data of this destination object from Resource Server,
The information such as the product that then arrives together with keyword search, webpage return client.
The business object of coupling searched in the participle based on key word for the embodiment of the present application, and then carries out dependency
With the screening of quality, return the target service object selected it is achieved that the automatic push of business object, use
Family does not need the Yu Xianxuanding operation such as key word, optimization, ranking, has significantly passed through the simplicity operating,
Reduce use cost, and then also can be pushed in long-tail flow, improve the utilization of long-tail flow
Rate.
, the triggering mode of traditional ad data directly triggers for key word, rear end taking ad data as a example
User (also known as advertiser), when promoting the product of itself, needs to select key word (selecting word) in advance,
The ad data of oneself product is matched under this key word, carries out this key word with other backend user
Bid, when retrieving this key word, coupling is under this key word for front end user (also known as buyer)
The ad data of this backend user product just can be represented, and triggering side promoted in traditional selected key word
Formula flow process is as follows:
Promote → select word → mate → bid → retrieve → represent；
This mode as traditional ad data bid and triggering mode at the advertising platform initial stage to wide
Accuse platform and bring very big income, but in place of this mode there is also some shortcomings, such as operate
Complicated, technical threshold is high, and the application cost of backend user is higher, and long-tail flow utilization rate is not high.
In this example, pre-production full-text index, by the way of full-text search, backend user is pushing away
It is no longer necessary to away the process of series of complex, it selects the ad data needing to promote product during wide product,
When front end user is retrieved, it will be automatically performed a series of mistakes such as the retrieval of ad data, coupling, sequence
In journey, such as this example, the popularization triggering mode flow process based on full-text search is as follows:
Promote → retrieve → represent
This mode enormously simplify the operation of back-end client, greatly reduces threshold and the cost of application,
It is particularly suited for that some operational capacities are strong or user that do not have over head time, after advertisement data,
Backend user can directly be seen that last input effect on network platform backstage.
What traditional ad data way of promotion was taken is that backend user buys key on advertising platform backstage
The mode of word, the advertisement promotion mode adopting in this example does not need user to select word, but selectes advertisement and put down
The ad data (i.e. selection) of platform product to be promoted, its distinguish with traditional mode be traditional wide
Accusing data and promoting needs to select key word and key word is bidded, and after this example can adopt to promoting
Under the account of end subscriber, the ad data of product carries out unifying to bid (i.e. account bid), and optical platform is at it
Reduced in budget, final input and effect are then ensured by advertising platform, greatly simplify rear end and use
The running cost at family, its example flow is as follows；
Budget → selection → account bid → input → effect
In this example, greatly reduce the running cost that backend user promotes product, greatly lifted simultaneously
The utilization rate of advertising platform long-tail flow, improves the business revenue of advertising platform, reaches doulbe-sides' victory.
It should be noted that for embodiment of the method, in order to be briefly described, therefore it is all expressed as one and be
The combination of actions of row, but those skilled in the art should know, and the embodiment of the present application is not subject to described
Sequence of movement restriction because according to the embodiment of the present application, some steps can using other orders or
Person is carried out simultaneously.Secondly, those skilled in the art also should know, embodiment described in this description
Belong to preferred embodiment, necessary to involved action not necessarily the embodiment of the present application.
With reference to Fig. 2, show a kind of structured flowchart of the pusher embodiment of business object of the application,
This device 200 specifically can include as lower module:
Word segmentation processing module 201, for when receiving key word, carrying out at participle to described key word
Reason, obtains one or more first participles；
Business object searching modul 202, for, in preset index file, searching and each first point
The business object of word coupling；
Candidate Traffic object select module 203, for choosing and described key word from described business object
Related candidate Traffic object；
Target service object select module 204, presets for choosing to meet from described candidate Traffic object
Quality requirements target service object；And
Target service Object Push module 205, for pushing described target service object.
In a preferred embodiment of the present application, described business object searching modul 202 can include as
Lower submodule:
First lookup submodule, for, in preset index file, searching and mating with each first participle
The second participle, wherein, described second participle is to carry out participle to the text message in described business object
Process the participle obtaining；And,
Second lookup submodule, for searching the business object of described second participle mapping.
In a preferred embodiment of the present application, described candidate Traffic object select module 203 can be wrapped
Include following submodule:
Occur simultaneously screening submodule, at least filtering out the friendship of the business object mated with the part first participle
Collection, obtains candidate Traffic object.
In a preferred embodiment of the present application, described candidate Traffic object select module 203 is acceptable
Including following submodule:
Intercept submodule, at least intercepting the business object that part is mated with the first participle；And
Candidate Traffic object obtains submodule, at least filtering out the common factor of the business object of intercepting, obtains
Obtain candidate Traffic object.
In a preferred embodiment of the present application, described candidate Traffic object select module 203 is acceptable
Including following submodule:
Classification acquisition submodule, for searching one or more first classifications of described keyword, described time
Select the second classification of business object；
Correlation calculations submodule, for searching one or more of first classifications and described second classification
Dependency；
Dependency chooses submodule, for choosing dependency highest one or more candidate Traffic object.
In a preferred embodiment of the present application, described target service object select module 204 can be wrapped
Include following submodule:
Candidate information acquisition submodule is related to described key word for obtaining described candidate Traffic object
Spend and estimate clicking rate；
Quality score calculating sub module, for calculating quality using described degree of association with described clicking rate of estimating
Scoring；
Quality score chooses submodule, meets the time of default quality requirements for choosing described quality score
Select business object as target service object.
In a preferred embodiment of the present application, described target service object select module 204 is acceptable
Including following submodule:
Sorting sub-module, for being ranked up to described target service object according to described quality score.
For device embodiment, due to itself and embodiment of the method basic simlarity, so the comparison of description
Simply, in place of correlation, the part referring to embodiment of the method illustrates.
Each embodiment in this specification is all described by the way of going forward one by one, and each embodiment stresses
Be all difference with other embodiment, between each embodiment identical similar partly mutually referring to
?.
Those skilled in the art are it should be appreciated that the embodiment of the embodiment of the present application can be provided as method, dress
Put or computer program.Therefore, the embodiment of the present application can be using complete hardware embodiment, completely
Software implementation or the form of the embodiment with reference to software and hardware aspect.And, the embodiment of the present application
Storage can be can use to be situated between using in one or more computers wherein including computer usable program code
The upper computer journey implemented of matter (including but not limited to disk memory, cd-rom, optical memory etc.)
The form of sequence product.
In a typical configuration, described computer equipment includes one or more processors
(cpu), input/output interface, network interface and internal memory.Internal memory potentially includes computer-readable medium
In volatile memory, the shape such as random access memory (ram) and/or Nonvolatile memory
Formula, such as read only memory (rom) or flash memory (flash ram).Internal memory is computer-readable medium
Example.Computer-readable medium includes permanent and non-permanent, removable and non-removable media
Information Store can be realized by any method or technique.Information can be computer-readable instruction,
Data structure, the module of program or other data.The example of the storage medium of computer includes, but
It is not limited to phase transition internal memory (pram), static RAM (sram), dynamic random are deposited
Access to memory (dram), other kinds of random access memory (ram), read only memory
(rom), Electrically Erasable Read Only Memory (eeprom), fast flash memory bank or other in
Deposit technology, read-only optical disc read only memory (cd-rom), digital versatile disc (dvd) or other
Optical storage, magnetic cassette tape, tape magnetic rigid disk storage other magnetic storage apparatus or any its
His non-transmission medium, can be used for storing the information that can be accessed by a computing device.According to herein
Define, computer-readable medium does not include the computer readable media (transitory media) of non-standing,
Data signal and carrier wave as modulation.
The embodiment of the present application is with reference to according to the method for the embodiment of the present application, terminal unit (system) and meter
The flow chart of calculation machine program product and/or block diagram are describing.It should be understood that can be by computer program instructions
Each flow process in flowchart and/or block diagram and/or square frame and flow chart and/or square frame
The flow process of in figure and/or the combination of square frame.Can provide these computer program instructions to general purpose computer,
The processor of special-purpose computer, Embedded Processor or other programmable data processing terminal equipments is to produce
One machine is so that pass through the computing device of computer or other programmable data processing terminal equipments
Instruction produce for realizing in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The device of the function of specifying in multiple square frames.
These computer program instructions may be alternatively stored in and computer or other programmable datas can be guided to process
So that being stored in this computer-readable in the computer-readable memory that terminal unit works in a specific way
Instruction in memorizer produces and includes the manufacture of command device, and the realization of this command device is in flow chart one
The function of specifying in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded into computer or other programmable data processing terminals set
For upper so that execution series of operation steps is in terms of producing on computer or other programmable terminal equipments
The process that calculation machine is realized, thus the instruction of execution provides use on computer or other programmable terminal equipments
In realization in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame
The step of the function of specifying.
Although having been described for the preferred embodiment of the embodiment of the present application, those skilled in the art are once
Know basic creative concept, then these embodiments can be made with other change and modification.So,
The institute that claims are intended to be construed to including preferred embodiment and fall into the embodiment of the present application scope
Have altered and change.
Finally in addition it is also necessary to illustrate, herein, such as first and second or the like relational terms
It is used merely to make a distinction an entity or operation with another entity or operation, and not necessarily require
Or imply between these entities or operation, there is any this actual relation or order.And, art
Language " inclusion ", "comprising" or its any other variant are intended to comprising of nonexcludability, so that
Not only include those key elements including a series of process of key elements, method, article or terminal unit, and
Also include other key elements being not expressly set out, or also include for this process, method, article or
The intrinsic key element of person's terminal unit.In the absence of more restrictions, " include one by sentence
Individual ... " key element that limits is it is not excluded that at process, method, article or the end including described key element
Also there is other identical element in end equipment.
Above to the method for pushing of a kind of business object provided herein and a kind of pushing away of business object
Send device, be described in detail, specific case used herein is to the principle of the application and embodiment party
Formula is set forth, and the explanation of above example is only intended to help and understands the present processes and its core
Thought；Simultaneously for one of ordinary skill in the art, according to the thought of the application, it is being embodied as
All will change in mode and range of application, in sum, it is right that this specification content should not be construed as
The restriction of the application.
Claims (14)
1. a kind of method for pushing of business object is it is characterised in that include:
When receiving key word, described key word is carried out with word segmentation processing, obtain one or more first
Participle；
In preset index file, search the business object mated with each first participle；
The candidate Traffic object related to described key word is chosen from described business object；
The target service object meeting default quality requirements is chosen from described candidate Traffic object；And
Push described target service object.
2. method according to claim 1 it is characterised in that described in preset index file
In, the step searching the business object mated with each first participle respectively is included:
In preset index file, search the second participle mating with each first participle, wherein, institute
Stating the second participle is the participle that the text message in described business object is carried out with word segmentation processing acquisition；With
And,
Search the business object of described second participle mapping.
3. method according to claim 1 it is characterised in that described from described business object
The step choosing the candidate Traffic object related to described key word includes:
At least filter out the common factor of the business object mated with the part first participle, obtain candidate Traffic pair
As.
4. method according to claim 3 is it is characterised in that described at least filter out and part
The common factor of the business object of first participle coupling, the step obtaining candidate Traffic object includes:
At least intercept the business object that part is mated with the first participle；And
At least filter out the common factor of the business object of intercepting, obtain candidate Traffic object.
5. method according to claim 3 it is characterised in that described from described business object
The step choosing the candidate Traffic object related to described key word also includes:
Search one or more first classifications, the Equations of The Second Kind of described candidate Traffic object of described keyword
Mesh；
Search one or more of first classifications and described Equations of The Second Kind purpose dependency；
Choose dependency highest one or more candidate Traffic object.
6. the method according to claim 1 or 2 or 3 or 4 or 5 is it is characterised in that described
The step bag of the target service object meeting default quality requirements is chosen from described candidate Traffic object
Include:
Obtain the degree of association of described candidate Traffic object and described key word and estimate clicking rate；
Quality score is calculated with described clicking rate of estimating using described degree of association；
Choose described quality score and meet the candidate Traffic object of default quality requirements as target service
Object.
7. the method according to claim 1 or 2 or 3 or 4 or 5 is it is characterised in that described
Choose the step of the target service object meeting default quality requirements also from described candidate Traffic object
Including:
According to described quality score, described target service object is ranked up.
8. a kind of pusher of business object is it is characterised in that include:
Word segmentation processing module, for when receiving key word, word segmentation processing being carried out to described key word,
Obtain one or more first participles；
Business object searching modul, for, in preset index file, searching and each first participle
The business object joined；
Candidate Traffic object select module is related to described key word for choosing from described business object
Candidate Traffic object；
Target service object select module, meets default matter for choosing from described candidate Traffic object
The target service object of amount condition；And
Target service Object Push module, for pushing described target service object.
9. device according to claim 8 is it is characterised in that described business object searching modul
Including:
First lookup submodule, for, in preset index file, searching and mating with each first participle
The second participle, wherein, described second participle is to carry out participle to the text message in described business object
Process the participle obtaining；And,
Second lookup submodule, for searching the business object of described second participle mapping.
10. device according to claim 8 is it is characterised in that described candidate Traffic object select
Module includes:
Occur simultaneously screening submodule, at least filtering out the friendship of the business object mated with the part first participle
Collection, obtains candidate Traffic object.
11. devices according to claim 10 are it is characterised in that described common factor screens submodule
Including:
Intercept submodule, at least intercepting the business object that part is mated with the first participle；And
Candidate Traffic object obtains submodule, at least filtering out the common factor of the business object of intercepting, obtains
Obtain candidate Traffic object.
12. devices according to claim 10 are it is characterised in that described candidate Traffic object selects
Delivery block also includes:
Classification acquisition submodule, for searching one or more first classifications of described keyword, described time
Select the second classification of business object；
Correlation calculations submodule, for searching one or more of first classifications and described second classification
Dependency；
Dependency chooses submodule, for choosing dependency highest one or more candidate Traffic object.
Device described in 13. according to Claim 8 or 9 or 10 or 11 or 12 it is characterised in that
Described target service object select module includes:
Candidate information acquisition submodule is related to described key word for obtaining described candidate Traffic object
Spend and estimate clicking rate；
Quality score calculating sub module, for calculating quality using described degree of association with described clicking rate of estimating
Scoring；
Quality score chooses submodule, meets the time of default quality requirements for choosing described quality score
Select business object as target service object.
Device described in 14. according to Claim 8 or 9 or 10 or 11 or 12 it is characterised in that
Described target service object select module also includes:
Sorting sub-module, for being ranked up to described target service object according to described quality score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510395205.9A CN106339382A (en) | 2015-07-07 | 2015-07-07 | Method and device for pushing business objects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510395205.9A CN106339382A (en) | 2015-07-07 | 2015-07-07 | Method and device for pushing business objects |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106339382A true CN106339382A (en) | 2017-01-18 |
Family
ID=57826481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510395205.9A Pending CN106339382A (en) | 2015-07-07 | 2015-07-07 | Method and device for pushing business objects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106339382A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330592A (en) * | 2017-06-20 | 2017-11-07 | 北京因果树网络科技有限公司 | A kind of screening technique, device and the computing device of target Enterprise Object |
| CN107423362A (en) * | 2017-06-20 | 2017-12-01 | 阿里巴巴集团控股有限公司 | Industry determines method, Method of Get Remote Object and device, client, server |
| CN108376162A (en) * | 2018-02-22 | 2018-08-07 | 北京百度网讯科技有限公司 | Method and apparatus for pushed information |
| CN110019990A (en) * | 2017-07-14 | 2019-07-16 | 阿里巴巴集团控股有限公司 | Method and apparatus, the method and apparatus of business object data search of screening sample |
| CN110232138A (en) * | 2019-05-20 | 2019-09-13 | 中国银行股份有限公司 | A kind of business bootstrap technique, device and storage medium |
| WO2020248378A1 (en) * | 2019-06-12 | 2020-12-17 | 平安科技（深圳）有限公司 | Service query method and apparatus, and storage medium and computer device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043833A (en) * | 2010-11-25 | 2011-05-04 | 北京搜狗科技发展有限公司 | Search method and device based on query word |
| CN102156712A (en) * | 2011-03-08 | 2011-08-17 | 国网信息通信有限公司 | Power information retrieval method and power information retrieval system based on cloud storage |
| CN103186591A (en) * | 2011-12-29 | 2013-07-03 | 盛乐信息技术（上海）有限公司 | Information suggesting method and system |
| CN103577432A (en) * | 2012-07-26 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and system for searching commodity information |
-
2015
- 2015-07-07 CN CN201510395205.9A patent/CN106339382A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043833A (en) * | 2010-11-25 | 2011-05-04 | 北京搜狗科技发展有限公司 | Search method and device based on query word |
| CN102156712A (en) * | 2011-03-08 | 2011-08-17 | 国网信息通信有限公司 | Power information retrieval method and power information retrieval system based on cloud storage |
| CN103186591A (en) * | 2011-12-29 | 2013-07-03 | 盛乐信息技术（上海）有限公司 | Information suggesting method and system |
| CN103577432A (en) * | 2012-07-26 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and system for searching commodity information |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330592A (en) * | 2017-06-20 | 2017-11-07 | 北京因果树网络科技有限公司 | A kind of screening technique, device and the computing device of target Enterprise Object |
| CN107423362A (en) * | 2017-06-20 | 2017-12-01 | 阿里巴巴集团控股有限公司 | Industry determines method, Method of Get Remote Object and device, client, server |
| CN110019990A (en) * | 2017-07-14 | 2019-07-16 | 阿里巴巴集团控股有限公司 | Method and apparatus, the method and apparatus of business object data search of screening sample |
| CN110019990B (en) * | 2017-07-14 | 2023-05-23 | 阿里巴巴集团控股有限公司 | Sample screening method and device and business object data searching method and device |
| CN108376162A (en) * | 2018-02-22 | 2018-08-07 | 北京百度网讯科技有限公司 | Method and apparatus for pushed information |
| CN110232138A (en) * | 2019-05-20 | 2019-09-13 | 中国银行股份有限公司 | A kind of business bootstrap technique, device and storage medium |
| CN110232138B (en) * | 2019-05-20 | 2022-05-20 | 中国银行股份有限公司 | Service guiding method, device and storage medium |
| WO2020248378A1 (en) * | 2019-06-12 | 2020-12-17 | 平安科技（深圳）有限公司 | Service query method and apparatus, and storage medium and computer device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9842170B2 (en) | Method, apparatus and system of intelligent navigation | |
| CN106339382A (en) | Method and device for pushing business objects | |
| CN110909182B (en) | Multimedia resource searching method, device, computer equipment and storage medium | |
| CN103714130B (en) | Video recommendation system and method | |
| US8732155B2 (en) | Categorization in a system and method for conducting a search | |
| CN101551806B (en) | Personalized website navigation method and system | |
| CN102591475B (en) | A kind of content input method of online editor and system | |
| US20130138429A1 (en) | Method and Apparatus for Information Searching | |
| CN102402619A (en) | Search method and device | |
| CN106033415A (en) | A text content recommendation method and device | |
| CN103377232A (en) | Headline keyword recommendation method and system | |
| TW201445344A (en) | System and method to facilitate matching of content to advertising information in a network | |
| CN101751422A (en) | Method, mobile terminal and server for carrying out intelligent search at mobile terminal | |
| CN109409928A (en) | A kind of material recommended method, device, storage medium, terminal | |
| CN105426514A (en) | Personalized mobile APP recommendation method | |
| CN103314371A (en) | Retrieval method and system | |
| CN102163234A (en) | Equipment and method for error correction of query sequence based on degree of error correction association | |
| CN113254711B (en) | Interactive image display method and device, computer equipment and storage medium | |
| CN107092609A (en) | A kind of information-pushing method and device | |
| CN105916032A (en) | Video recommendation method and video recommendation terminal equipment | |
| CN109885753A (en) | A kind of method and device for expanding commercial articles searching and recalling | |
| KR100782047B1 (en) | Automatic Generation Method of the Initial Query Set for Image Search on the Mobile Web | |
| CN106919588A (en) | A kind of application program search system and method | |
| CN114330329A (en) | Service content searching method and device, electronic equipment and storage medium | |
| CN103955480A (en) | Method and equipment for determining target object information corresponding to user |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170118 |
|
| RJ01 | Rejection of invention patent application after publication |