CN108268506A - A kind of processing method of promotion message, device, terminal and computer readable storage medium - Google Patents
A kind of processing method of promotion message, device, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN108268506A CN108268506A CN201611262654.7A CN201611262654A CN108268506A CN 108268506 A CN108268506 A CN 108268506A CN 201611262654 A CN201611262654 A CN 201611262654A CN 108268506 A CN108268506 A CN 108268506A
- Authority
- CN
- China
- Prior art keywords
- scoring
- promotion message
- parameter
- retrieval result
- promotion
- 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
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9577—Optimising the visualization of content, e.g. distillation of HTML documents
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of processing method and processing device of promotion message, this method includes：The corresponding retrieval result of term and term corresponding multiple promotion messages in default promotion database are obtained, retrieval result has using the first evaluation model, the retrieval result scoring obtained based on retrieval result characteristic；Using the second evaluation model, the promotion message characteristic based on promotion message scores to multiple promotion messages, obtains the second scoring；Second scoring is converted into corresponding first scoring under the first Rating Model；Retrieval result scoring based on the transformed first scoring and retrieval result, promotion message is inserted into retrieval result.Second scoring of recommendation information is aligned by the embodiment of the present invention with the first scoring of retrieval result, search result and promotion message hybrid-sorting are realized according to the first of alignment the scoring, and then avoid preferentially showing search result before search result while reaching display promotion message, improve search result exposure rate.
Description
Technical field
The present embodiments relate to data processing technique more particularly to a kind of processing method of promotion message, device, terminals
And computer readable storage medium.
Background technology
With the development of network technology, people are more and more scanned for using search engine.Search engine can be right
Information carries out tissue and processing, and will show user with the relevant retrieval result of term input by user.
Search service provider other than providing search result to the user, can also search result interfaces show with it is input by user
The relevant advertising information of search term.In the prior art, advertising information exists respectively with search result in search result display interface
It is shown in different regions.As shown in Figure 1, in search result display interface, two advertising informations are shown first, then
Search result is shown after advertising information.
However, the display due to advertising information occupies the stem of search result display interface, such as use mobile terminal
When browsing search result, search result display interface shows a plurality of advertising information first, these advertising informations will occupy a large amount of
Screen space, causes user that can not quickly and effectively read search result, and search result exposure rate is low.
Invention content
The present invention provides a kind of processing method of promotion message, device, terminal and computer readable storage medium, to improve
The exposure rate of search result is low.
In a first aspect, an embodiment of the present invention provides a kind of processing method of promotion message, including：
Obtain that the corresponding retrieval result of term and the term are corresponding in default promotion database multiple to be pushed away
Guangxin ceases, and the retrieval result has using the first evaluation model, and the retrieval result obtained based on retrieval result characteristic is commented
Point；
Using the second evaluation model, the promotion message characteristic based on promotion message, to the multiple promotion message into
Row scoring, obtains the second scoring；
Described second scoring is converted into corresponding first scoring under first Rating Model；
Retrieval result scoring based on the transformed first scoring and the retrieval result, the promotion message is inserted into
Into the retrieval result.
Second aspect, an embodiment of the present invention provides a kind of processing unit of promotion message, including：
Retrieval result acquiring unit, for obtaining the corresponding retrieval result of term；
Promotion message acquiring unit is believed for obtaining the term corresponding multiple promote in default promotion database
Breath, the retrieval result have using the first evaluation model, the retrieval result scoring obtained based on retrieval result characteristic；
Score unit, for utilizing the second evaluation model, the promotion message characteristic based on promotion message, to described more
A promotion message scores, and obtains the second scoring；
Score converting unit, for second scoring that the scoring unit obtains to be converted to the first scoring mould
Corresponding first scoring under type；
Unit is inserted into, for based on transformed first scoring of the scoring converting unit and the inspection of the retrieval result
Hitch fruit scores, and the promotion message is inserted into the retrieval result.
The third aspect, an embodiment of the present invention provides a kind of terminal, the terminal includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes the processing method of the promotion message as shown in first aspect.
Fourth aspect, an embodiment of the present invention provides a kind of computer readable storage mediums, are stored thereon with computer journey
Sequence realizes the processing method of the promotion message as shown in first aspect when the program is executed by processor.
The embodiment of the present invention provides obtains the corresponding retrieval result of term and promotion message first, and wherein retrieval result has
There is the first scoring under the first evaluation model, promotion message has the second scoring under the second evaluation model, then will promote and believes
Second scoring of breath is converted to the first scoring, is finally based on transformed first scoring and promotion message is inserted into retrieval result
In.Promotion message is displayed by priority before search result in the prior art, and obtaining search result to user interferes.This
After second scoring of promotion message is converted to the first scoring by inventive embodiments, the second scoring of recommendation information can be tied with retrieval
The first scoring of fruit is aligned, and search result and promotion message hybrid-sorting can be realized according to the first of alignment the scoring, into
And avoid preferentially showing search result before search result while reaching display promotion message, improve search result exposure rate.
Description of the drawings
Fig. 1 is the flow chart of the processing method of the promotion message in the embodiment of the present invention one；
Fig. 2 is the flow chart of the processing method of the promotion message in the embodiment of the present invention two；
Fig. 3 is the structure diagram of the processing unit of the promotion message in the embodiment of the present invention three；
Fig. 4 is the terminal structure schematic diagram in the embodiment of the present invention four.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrated only in description, attached drawing.
Embodiment one
The flow chart of the processing method of promotion message that Fig. 1 is provided for the embodiment of the present invention one, side provided in this embodiment
Method can be performed by terminal, and terminal can be mobile terminal, such as smart mobile phone or tablet computer.Terminal can also be fixed whole
End, such as PC.The processing method of promotion message includes：
S110, obtain that the corresponding retrieval result of term and term are corresponding in default promotion database multiple to be pushed away
Guangxin ceases, and retrieval result has using the first evaluation model, the retrieval result scoring obtained based on retrieval result characteristic.
Optionally, search result is obtained with online mode, i.e., the corresponding search of search term is obtained by search engine online
As a result.Wherein, Baidu search engine can be used in search engine.
Search engine provides user interface to the user, which inquires for inputting user, shows query result etc..
User logs on to search website, such as " www.baidu.com ", term is inputted simultaneously in the search column then provided in search website
Start search.The term searched in plain column is transferred in the searcher of search engine by search website.The searcher of search engine
It roams in a network, finds and collect information.The information that index analysis searcher is searched for, therefrom extracts index entry, rope
Draw item for representing document, and generate the concordance list of document library.Searcher is examined according to term input by user in index database
Go out document, retrieval result is obtained according to the document of detection.
Retrieval result characteristic includes following at least one user behavior features：The user satisfaction of retrieval result, inspection
The historic click-through rate of hitch fruit, the history click volume of retrieval result, retrieval result historical user be resident duration etc..
The user satisfaction of retrieval result, the historic click-through rate of retrieval result, the history click volume of retrieval result, retrieval knot
It is directly proportional to the first scoring of retrieval result that the historical user of fruit is resident duration.It scores when according to above-mentioned at least two dimension
When, it, then according to the corresponding preset weights ratio of each dimension, can be weighted respectively according to the score obtained in each dimension
Average computation obtains corresponding first scoring of retrieval result.
For default promotion database for storing promotion message, promotion message can be the advertisement information that businessman uploads, and also may be used
Think public service ads information that commonweal organizations uploads etc..Promotion message is established to presetting the promotion message in promotion message database
Concordance list, the concordance list can be identical with the making mechanism of the concordance list of the document library of search engine.According to inspection input by user
Rope word according to the correlation of promotion message and term in default promotion database, is found out higher with retrieval word correlation
Multiple promotion messages.Optionally, the quantity of the promotion message found out is more than or equal to 1.
Further, if the promotion message of whole terms can not be found and be included, term is analyzed,
The feature vocabulary of term is analyzed, then searches the promotion message for including this feature vocabulary.Feature vocabulary can be term
In verb or noun.
Further, multiple promotion messages are distributed in each search result shows the page.Each search result shows page
The quantity of promotion message in face can be identical, 3 promotion messages of such as every page of display.Each search result shows pushing away in the page
The quantity of Guangxin breath can be different.With the increase of page serial number, search result shows the number of promotion message included in the page
Amount gradually decreases.For example, page 1 to page 3 search result is shown in the page, each search result shows that the page distributes 3 and pushes away
Guangxin ceases, and page 4 to page 8 search result is shown in the page, and each search result shows that the page distributes 2 promotion messages.From
The search result of page 9 shows that the quantity that the page starts promotion message can be 1.
Since search term is fixed, at some moment, the search result quantity obtained according to search term and from default
The quantity of the promotion message found in promotion message database is fixed.Over time, the information in network and pre-
If the quantity and content of the promotion message stored in promotion database can change, therefore same search term is in different moments
The retrieval result searched and the promotion message found are also not quite similar.
S120, using the second evaluation model, the promotion message characteristic based on promotion message, to multiple promotion messages into
Row scoring, obtains the second scoring.
The promotion message matched with term found from default promotion message database storage is deposited to waiting to score
It stores up in space, then scores the promotion message in the memory space.
If the quantity of promotion message, which is more than retrieval result, shows the matched promotion message quantity of the page, to what is found
Promotion message is deleted, and obtains showing the matched promotion message quantity of the page with retrieval result.Then, to the popularization after deleting
Information scores.
Further, promotion message characteristic includes following at least one：
The correlation of promotion message and term, promotion message mass parameter, the pricing information of promotion message, promotion message
User's history behavioural characteristic, promotion message renewal time, provide promotion message trade company priority, promotion message content
Priority.
Illustratively, it according to the correlation of promotion message and term, scores promotion message.
The correlation of promotion message and term is higher, and the score of promotion message is higher.Optionally, according to term with pushing away
The similarity calculation correlation of the word content of wide information index.For example, according to shared by term in the index of promotion message
Ratio calculates correlation.Correlation of the index of promotion message comprising whole terms includes part term higher than promotion message
Correlation.Wherein, the maximum value of relevance score is 100.The index of promotion message can be the topic of promotion message or pluck
It will.
When being scored according to correlation promotion message, the contract of the higher promotion message of the degree of correlation and user search to content
Right higher, user's satisfaction is higher.It can be found from promotion message and user demand degree contract the most by degree of correlation scoring
The promotion message of conjunction.
Illustratively, it according to promotion message mass parameter, scores promotion message.
Wherein, the mass parameter includes at least one of intention parameter, original parameter or pattern parameter.Promote letter
The intention parameter and original parameter of breath can obtain offline.
Optionally, intention parameter, original parameter can be stored in default promote as the additional parameter of promotion message and believe
It ceases in database.The corresponding intention parameter of promotion message and original parameter are obtained according to promotion message during scoring.Intention parameter
Represent the rich and originality of the content of promotion message, it is such as whether comprehensive to promoting the description information of object.Original table
Show the number of links in promotion message, the number of links included in promotion message the few original higher.
Pattern parameter represents the corresponding information category of promotion message, such as document or playable multimedia.Pattern and retrieval
The pattern of the retrieval object of word is closer, and pattern parameter is higher.For example, term is so-and-so video, then type is multimedia
The pattern parameter of promotion message is more than pattern parameter of the type for the promotion message of text.
The intention parameter of promotion message is higher, original parameter is higher, pattern parameter is higher, then scores higher.It can root
It scores according to any one in above-mentioned parameter promotion message, it can also be according to two or three in above-mentioned parameter to pushing away
Guangxin breath scores.When two or three in above-mentioned parameter score to promotion message, can obtain respectively every
The corresponding hundred-mark system scoring of a parameter, is then averaged and is finally scored.Alternatively, each parameter corresponding hundred is obtained respectively
After dividing system scoring, final score is calculated according to preset weight proportion.Default weight proportion can be intention parameter：Original ginseng
Number：Pattern parameter=5:4:1.
It is scored according to the intention parameter, original parameter and pattern parameter of promotion message promotion message, according to
The targeted promotion information that appraisal result obtains has the readability identical with search result, and then improves promotion message and tied with search
Harmonious degree between fruit.
Illustratively, it according to the corresponding pricing information of promotion message, scores multiple promotion messages.
Preferably, pricing information payment amount corresponding with promotion message provider is corresponding.It scores promotion message
Screening, scoring screening rule is to obtain pricing information and the ratio of ceiling price information in promotion message, if the ratio is higher than
Otherwise default price proportion then can not pass through screening by screening.Optionally, it is 30% to preset price proportion.
Pricing information can be stored in default promotion message database as the additional parameter of promotion message.According to popularization
The bid of Information Provider is set price information.The corresponding price of pricing information is higher, and the scoring of promotion message is higher.
The user's history behavioural characteristic of promotion message includes following at least one：The user satisfaction of promotion message is promoted
The historic click-through rate of information, the history click volume of promotion message, promotion message historical user be resident duration etc..
Illustratively, it scores according to the historic click-through rate of promotion message.Promotion message historic click-through rate is believed with promoting
It is directly proportional to cease corresponding second scoring.Historic click-through rate can directly as the score of scoring, therefore the score that scores be not limited to it is small
In equal to 100 points.
When being scored according to the renewal time of promotion message, renewal time is higher about close to its scoring with current time；
Renewal time is lower about far from its scoring with current time.Renewal time can be as accurate as minute.It determines to comment according to renewal time
Divide score, determine it is to delete the chronomere of renewal time, obtain the character string being made of number, the character string is as scoring
Score.Such as 00 minute 10 points of on October 01st, 2016, corresponding scoring is 201610011000.
It further, can be from multiple dimensions (combination of such as historic click-through rate and renewal time) when being scored
It scores promotion message.
Optionally, it when there is identical scoring after a dimensions is used to score multiple promotion messages, uses
Another dimensions scores to the identical promotion message that scores.For example, usage time dimension comments promotion message
Timesharing, in fact it could happen that the promotion message of identical scoring, at this time according to the historic click-through rate of promotion message to identical scoring
Promotion message scores.
S130, the second scoring is converted into corresponding first scoring under the first Rating Model.
Preferably, according to default conversion parameter, using preset algorithm, the described second scoring is converted into first scoring
Corresponding first scoring under model.
Preset algorithm can be that linear function may be nonlinear function.Optionally, preset algorithm is linear function, in advance
If conversion parameter is independent variable parameter and constant in linear dimensions.Illustratively, it is assumed that default conversion parameter is 0.8, second
It is 80 points to score, and preset algorithm scores for the first scoring=default conversion parameter × second, then is multiplied by the second scoring 80 default
Conversion parameter 0.8 obtains the first scoring 64 and divides.
Optionally, default conversion parameter can be empirical value, or the experimental result obtained by test of many times.
In a kind of realization method, when based on experience value or the second scoring is converted to experimental result the first scoring, from the second scoring to the
The transformational relation of one scoring can be jump.For example, when the second scoring is 80, corresponding first scoring is 60, when the
When two scorings are 85, corresponding first scoring is 80；When the second scoring is 90, corresponding first scoring is 70 etc..
In another realization method, based on experience value or experimental result by second scoring be converted to the first scoring when, from second scoring to
The transformational relation of first scoring can be discrete non-hopping.For example, when the second scoring is 80, corresponding first scoring is
60, when the second scoring is 85, corresponding first scoring is 81；When the second scoring is 90, corresponding first scoring is
83 etc..
S140, the retrieval result scoring based on the transformed first scoring and retrieval result, promotion message is inserted into
In retrieval result.
The minimum scoring section where transformed first scoring, two ends in the scoring section are searched in retrieval result
Point scores for retrieval result.For example, transformed first scoring of promotion message is 65 points, retrieval result scoring is respectively 50
Divide, 60 points, 67 points, 70 points, 80 points, then the minimum scoring section found is 60-67 points, which is inserted into first
Score for 60 points of retrieval result and first scoring be 67 points retrieval result between.
Further, if there is the scoring identical with transformed first scoring, step in retrieval result scoring
S140 can be embodied as：
Step 141 scores according to the transformed first scoring and retrieval result, searches and is examined with the matched target of promotion message
Hitch fruit.
If the retrieval result scoring of retrieval result A is identical with transformed first scorings of promotion message A, retrieval is tied
Fruit A as with the matched target retrieval results of promotion message A.
Step 142, the default relative position that promotion message is inserted into target search result.Wherein, opposite position is preset
Be set to target search result previous position or latter position.
The display order of retrieval result is identical with the display order before being inserted into promotion message during insertion.Promotion message is inserted
Enter to previous position of target retrieval result or latter position, can more accurately be inserted into promotion message.
Further, S140 is further included：If the second scoring is less than default scoring threshold value, promotion message is inserted by cancellation
Into retrieval result.
Default scoring threshold value is used to evaluate the quality of promotion message, if the second scoring of promotion message is less than default scoring
Threshold value, then it represents that the quality of promotion message is less than the lowest score for showing user, therefore cancels and dividing equally second less than default
The promotion message of scoring threshold value is inserted into retrieval result.
Cancel promotion message being inserted into the retrieval result and the relatively low promotion message of quality can be pushed to user, carry
High user satisfaction.
The processing method of promotion message provided in this embodiment obtains the corresponding retrieval result of term and promotes and believes first
Breath, wherein retrieval result have the first scoring under the first evaluation model, and promotion message has second under the second evaluation model
Then second scoring of promotion message is converted to the first scoring by scoring, be finally based on transformed first scoring and will promote and believe
Breath is inserted into retrieval result.Promotion message is displayed by priority before search result in the prior art, and user is obtained and is searched
Hitch fruit interferes.It, can be by the of recommendation information after the second of promotion message scoring is converted to the first scoring by the present embodiment
Two scorings are aligned with the first scoring of retrieval result, can realize that search result is believed with promoting according to the first of alignment the scoring
It avoids preferentially showing search result before search result while ceasing hybrid-sorting, and then reach display promotion message, raising is searched
Hitch fruit exposure rate.
Embodiment two
Fig. 2 is the flow chart of the processing method of promotion message provided by Embodiment 2 of the present invention, as to above-described embodiment
Further explanation, optionally, by setting multiple default conversion parameters, then according to the corresponding income of each default conversion parameter
Parameter determines that optimum translation surveys parameter.Aforesaid way can be specifically embodied as：Include multiple default conversion ginsengs in default conversion parameter
During number, be converted under the first Rating Model before corresponding first scoring in step S130, by the second scoring, this method is also wrapped
It includes：
Second scoring is converted to correspondence by each default conversion parameter step S150, in multiple default conversion parameters
The first scoring, and promotion message is inserted by the corresponding retrieval result of identical term according to the first scoring being converted to
In.
Wherein, it is the corresponding multiple conversion parameters of same term to preset conversion parameter.It can determine based on experience value pre-
If conversion parameter, conversion parameter to be tested can be also determined as to default conversion parameter, can also letter be calculated according to default conversion parameter
Number determines default conversion parameter.Wherein, it can may be nonlinear function for linear function to preset conversion parameter and calculate function.
Independent variable is the quantity of default conversion parameter in the function, and dependent variable is default conversion parameter.Each default conversion parameter corresponds to
To the transformation rule of the second scoring, one or more users can be corresponded to by each presetting conversion parameter for a kind of first scoring.
The second scoring of the corresponding promotion messages of term A is converted to first using different default conversion parameters respectively
Scoring is then based on corresponding first scoring of different default conversion parameters and promotion message is inserted into the corresponding inspections of term A
In hitch fruit.
For example, default conversion parameter is respectively conversion parameter a, conversion parameter b and conversion parameter c, during experiment, obtain first
Three term A input by user are taken, corresponding retrieval result and promotion message are obtained according to term A.Then, according to
The scoring of promotion message second is converted to the first scoring a by Transformation Parameters a, and promotion message is inserted into inspection based on first scoring a
In hitch fruit, and the retrieval result inserted with promotion message is sent to first user；Similarly, it will be pushed away according to Transformation Parameters b
Breath the second scoring in Guangxin is converted to the first scoring b, promotion message is inserted into retrieval result, and will based on first scoring b
Retrieval result inserted with promotion message is sent to second user；Promotion message second is scored conversion according to Transformation Parameters c
For the first scoring c, promotion message is inserted into retrieval result, and by the inspection inserted with promotion message based on first scoring c
Hitch fruit is sent to third party.Wherein, first user, second user and third party can be with same subscribers
Think different user.
Step S160, each corresponding yield parameter of default conversion parameter is obtained.
Wherein, yield parameter represents the situation of Profit of promotion message.It can determine that income is joined according to following at least one parameters
Number：Clicking rate, user satisfaction, user are resident duration.
Optionally, above-mentioned parameter is made as yield parameter.Alternatively, above-mentioned parameter be converted to the receipts of hundred-mark system
Beneficial parameter.
The inspection obtained by counting different user (or same subscriber) to identical term according to different default conversion parameters
The selection situation of hitch fruit, determines yield parameter.For example, in upper example, first user is resident in the user that popularization letter is fastened
Shi Changwei 5 minutes, then using 5 minutes yield parameters as Transformation Parameters a.
Step S170, from the corresponding multiple yield parameters of multiple default conversion parameters, search yield parameter be more than it is default
The reference yield parameter of revenue threshold.
The default revenue threshold of respective type is determined according to the type of yield parameter.If for example, type of yield parameter
For clicking rate, then it is default clicking rate, such as 5% to preset revenue threshold.If yield parameter is user satisfaction, income is preset
The type of threshold value is satisfaction score, such as 60 points of satisfactions.If yield parameter is resident duration for user, revenue threshold is preset
Type for the time, such as 2 minutes.
Step S180, according to reference to the corresponding default conversion parameter of yield parameter, optimum translation parameter is determined.
Optionally, it is multiple with reference in yield parameter from what is found, maximum is determined as optimum translation with reference to yield parameter
Parameter.
Further, multiple average values with reference to the corresponding multiple default conversion parameters of yield parameter are calculated, this is averaged
Value is as optimum translation parameter.
Since user's selection has certain subjectivity, the highest reference yield parameter of benefited parameter is determined as optimal
There may be one-sidedness for conversion parameter.Therefore, by multiple average values with reference to the corresponding multiple default conversion parameters of yield parameter
It is determined as optimum translation parameter, the ease for use and accuracy of optimum translation parameter can be improved.
Correspondingly, the default conversion parameter of step S130, basis, the second scoring is converted to corresponding under the first Rating Model
First scoring, can also be embodied as：
S130 ＇, according to optimum translation parameter, the second scoring is converted into corresponding first scoring under the first Rating Model.
Technical solution provided in this embodiment, can obtain the corresponding yield parameter of multiple default conversion parameters, and according to
Default conversion parameter corresponding more than the reference yield parameter of default revenue threshold, determines optimum translation parameter, realizes by machine
Automatically optimum translation parameter is calculated and newer optimization method, more accurately by promotion message and retrieval result
It is aligned, while improves the income of promotion message.
Embodiment three
Fig. 3 is the structure diagram of the processing unit of a kind of promotion message that the embodiment of the present invention three provides, which uses
In implement above-described embodiment provide method, including：
Retrieval result acquiring unit 101, for obtaining the corresponding retrieval result of term；
Promotion message acquiring unit 102, for obtaining, the term is corresponding in default promotion database multiple to be pushed away
Guangxin ceases, and the retrieval result has using the first evaluation model, and the retrieval result obtained based on retrieval result characteristic is commented
Point；
Score unit 103, for utilizing the second evaluation model, the promotion message characteristic based on promotion message, to institute
It states multiple promotion messages to score, obtains the second scoring；
Score converting unit 104, for second scoring that the scoring unit 103 obtains to be converted to described first
Corresponding first scoring under Rating Model；
Unit 105 is inserted into, for being based on scoring converting unit 104 transformed first scoring and the retrieval knot
The retrieval result scoring of fruit, the promotion message is inserted into the retrieval result.
Further, the promotion message characteristic includes following at least one：
The correlation of promotion message and term；
Promotion message mass parameter；
The pricing information of promotion message；
The user's history behavioural characteristic of promotion message；
The renewal time of promotion message；
The priority of the trade company of promotion message is provided；
The priority of promotion message content.
Further, scoring converting unit 104 is used for, according to default conversion parameter, using preset algorithm, by described second
Scoring is converted to corresponding first scoring under first Rating Model.
When default conversion parameter includes multiple default conversion parameters, test cell 106 is further included, yield parameter obtains list
Member 107 surveys parameter determination unit 109 with reference to income searching unit 108 and optimum translation,
The test cell 106 is used for, and each default conversion parameter in multiple default conversion parameters is commented second
Divide and be converted to corresponding first scoring, and the promotion message is inserted by identical inspection according to first scoring being converted to
In the corresponding retrieval result of rope word；
The yield parameter acquiring unit 107 is used for, and obtains each corresponding yield parameter of default conversion parameter；
It is described to be used for reference to income searching unit 108, from the corresponding multiple yield parameters of the multiple default conversion parameter
In, search the reference yield parameter that yield parameter is more than default revenue threshold；
The optimum translation is surveyed parameter determination unit 109 and is used for, according to described with reference to the corresponding default conversion of yield parameter
Parameter determines that optimum translation surveys parameter；
Correspondingly, the scoring converting unit is used for, the determining institute of parameter determination unit 109 is surveyed according to the optimum translation
It states optimum translation and surveys parameter, the described second scoring is converted into corresponding first scoring under first Rating Model.
Further, the optimum translation is surveyed parameter determination unit 109 and is used for, and calculates multiple corresponding with reference to yield parameter
The average value is preset conversion parameter by the average value of multiple default conversion parameters as target.
Further, the insertion unit 105 is used for：
According to the transformed first scoring and retrieval result scoring, search and the matched target retrieval knot of the promotion message
Fruit；
The promotion message is inserted into the default relative position of the target search result, the default relative position
Previous position or latter position for the target search result.
Further, the insertion unit 105 is used for, if second scoring is less than default scoring threshold value, is cancelled
The promotion message is inserted into the retrieval result.
Above device can perform the method that any embodiment of the present invention is provided, and has and performs the corresponding function of the above method
Module and advantageous effect.The not technical detail of detailed description in the present embodiment, reference can be made to the side that the embodiment of the present invention is provided
Method.
Example IV
Fig. 4 is the structure diagram of a kind of terminal that the embodiment of the present invention four provides.Fig. 4 shows to be used for realizing this
The block diagram of the exemplary terminal 12 of invention embodiment.The terminal 12 that Fig. 4 is shown is only an example, should not be to of the invention real
The function and use scope for applying example bring any restrictions.
As shown in figure 4, terminal 12 is showed in the form of universal computing device.The component of terminal 12 can include but unlimited
In：One or more processor or processing unit 16, system storage 28, connection different system component (are deposited including system
Reservoir 28 and processing unit 16) bus 18.
Bus 18 represents one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Terminal 12 typically comprises a variety of computer system readable media.These media can be it is any can be by terminal 12
The usable medium of access, including volatile and non-volatile medium, moveable and immovable medium.
System storage 28 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Terminal 12 may further include it is other it is removable/nonremovable,
Volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing irremovable
, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, use can be provided
In to moving the disc driver of non-volatile magnetic disk (such as " floppy disk ") read-write and to moving anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 can include at least one program product,
The program product has one group of (for example, at least one) program module, these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42 can be stored in such as memory 28
In, such program module 42 include but not limited to operating system, one or more application program, other program modules and
Program data may include the realization of network environment in each or certain combination in these examples.Program module 42 is usual
Perform the function and/or method in embodiment described in the invention.
Terminal 12 can also communicate with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.),
Can also be enabled a user to one or more equipment interacted with the terminal 12 communication and/or with enable the terminal 12 with
Any equipment (such as network interface card, modem etc.) communication that one or more of the other computing device communicates.It is this logical
Letter can be carried out by input/output (I/O) interface 22.Also, terminal 12 can also by network adapter 20 and one or
The multiple networks of person (such as LAN (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown in the figure,
Network adapter 20 is communicated by bus 18 with other modules of terminal 12.It should be understood that it although not shown in the drawings, can combine
Terminal 12 uses other hardware and/or software module, including but not limited to：Microcode, device driver, redundant processing unit,
External disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 is stored in program in system storage 28 by operation, so as to perform various functions application and
Data processing, such as realize the processing method of promotion message that the embodiment of the present invention is provided.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The processing method of the promotion message as shown in embodiment one and embodiment two is realized when program is executed by processor.
The arbitrary of one or more computer-readable media may be used in the computer storage media of the embodiment of the present invention
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device or arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes：Tool
There are one or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or storing program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as a carrier wave part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but it is unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
It can write to perform the computer that operates of the present invention with one or more programming language or combinations
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully performs, partly perform on the user computer on the user computer, the software package independent as one performs, portion
Divide and partly perform or perform on a remote computer or server completely on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer or, it may be connected to outer computer (such as is carried using Internet service
Pass through Internet connection for quotient).
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiment described here, can carry out for a person skilled in the art various apparent variations,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
It can include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (11)
1. a kind of processing method of promotion message, which is characterized in that including：
The corresponding retrieval result of term and the term corresponding multiple promote in default promotion database is obtained to believe
Breath, the retrieval result have using the first evaluation model, the retrieval result scoring obtained based on retrieval result characteristic；
Using the second evaluation model, the promotion message characteristic based on promotion message comments the multiple promotion message
Point, obtain the second scoring；
Described second scoring is converted into corresponding first scoring under first Rating Model；
Retrieval result scoring based on the transformed first scoring and the retrieval result, institute is inserted by the promotion message
It states in retrieval result.
2. according to the method described in claim 1, it is characterized in that, the promotion message characteristic includes following at least one
It is a：
The correlation of promotion message and term；
Promotion message mass parameter；
The pricing information of promotion message；
The user's history behavioural characteristic of promotion message；
The renewal time of promotion message；
The priority of the trade company of promotion message is provided；
The priority of promotion message content.
3. according to the method described in claim 1, it is characterized in that, the described second scoring is converted into first Rating Model
Under it is corresponding first scoring include：
According to default conversion parameter, using preset algorithm, the described second scoring is converted to corresponding under first Rating Model
First scoring.
4. according to the method described in claim 3, it is characterized in that, include multiple default conversion parameters in default conversion parameter
When, in the case where the described second scoring to be converted to first Rating Model before corresponding first scoring, the method further includes：
Second scoring is converted to corresponding first scoring by each default conversion parameter in multiple default conversion parameters, and
The promotion message is inserted into the corresponding retrieval result of identical term by first scoring according to being converted to；
Obtain each corresponding yield parameter of default conversion parameter；
From the corresponding multiple yield parameters of the multiple default conversion parameter, search yield parameter and be more than default revenue threshold
With reference to yield parameter；
According to described with reference to the corresponding default conversion parameter of yield parameter, determine that optimum translation surveys parameter；
Correspondingly, the basis presets conversion parameter, the described second scoring is converted to corresponding under first Rating Model
First scoring, including：
According to the optimum translation parameter, the described second scoring is converted under first Rating Model corresponding first and is commented
Point.
It is 5. according to the method described in claim 1, it is characterized in that, described based on the transformed first scoring and the retrieval
As a result retrieval result scoring, the promotion message is inserted into the retrieval result, including：
According to the transformed first scoring and retrieval result scoring, search and the matched target retrieval result of the promotion message；
The promotion message is inserted into the default relative position of the target search result, the default relative position is institute
State target search result previous position or latter position.
6. according to the method described in claim 1, it is characterized in that, described be inserted into the retrieval result by the promotion message
In, including：
If second scoring is less than default scoring threshold value, cancels and the promotion message is inserted into the retrieval result
In.
7. a kind of processing unit of promotion message, which is characterized in that including：
Retrieval result acquiring unit, for obtaining the corresponding retrieval result of term；
Promotion message acquiring unit, for obtaining the term corresponding multiple promotion messages in default promotion database,
The retrieval result has using the first evaluation model, the retrieval result scoring obtained based on retrieval result characteristic；
Score unit, and for utilizing the second evaluation model, the promotion message characteristic based on promotion message is pushed away to the multiple
Guangxin breath scores, and obtains the second scoring；
Score converting unit, for second scoring that the scoring unit obtains to be converted under first Rating Model
Corresponding first scoring；
Unit is inserted into, for the retrieval knot based on transformed first scoring of scoring converting unit and the retrieval result
Fruit scores, and the promotion message is inserted into the retrieval result.
8. device according to claim 7, which is characterized in that the promotion message characteristic includes following at least one
It is a：
The correlation of promotion message and term；
Promotion message mass parameter；
The pricing information of promotion message；
The user's history behavioural characteristic of promotion message；
The renewal time of promotion message；
The priority of the trade company of promotion message is provided；
The priority of promotion message content.
9. device according to claim 7, which is characterized in that include multiple default conversion parameters in default conversion parameter
When, it further includes test cell, yield parameter acquiring unit, survey parameter determination unit with reference to income searching unit and optimum translation,
The test cell is used for, and each default conversion parameter in multiple default conversion parameters is converted to the second scoring
Corresponding first scoring, and the promotion message is inserted by identical term according to first scoring being converted to and is corresponded to
Retrieval result in；
The yield parameter acquiring unit is used for, and obtains each corresponding yield parameter of default conversion parameter；
It is described to be used for reference to income searching unit, from the corresponding multiple yield parameters of the multiple default conversion parameter, search
Yield parameter is more than the reference yield parameter of default revenue threshold；
The optimum translation is surveyed parameter determination unit and is used for, and is determined according to described with reference to the corresponding default conversion parameter of yield parameter
Optimum translation surveys parameter；
Correspondingly, the scoring converting unit is used for, determined according to optimum translation survey parameter determination unit described optimal
Parameter is surveyed in conversion, and the described second scoring is converted to corresponding first scoring under first Rating Model.
10. a kind of terminal, which is characterized in that the terminal includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now processing method of the promotion message as described in any in claim 1-6.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The processing method of the promotion message as described in any in claim 1-6 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611262654.7A CN108268506A (en) | 2016-12-30 | 2016-12-30 | A kind of processing method of promotion message, device, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611262654.7A CN108268506A (en) | 2016-12-30 | 2016-12-30 | A kind of processing method of promotion message, device, terminal and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108268506A true CN108268506A (en) | 2018-07-10 |
Family
ID=62753806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611262654.7A Pending CN108268506A (en) | 2016-12-30 | 2016-12-30 | A kind of processing method of promotion message, device, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108268506A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377830A (en) * | 2019-07-25 | 2019-10-25 | 拉扎斯网络科技（上海）有限公司 | Retrieval method, retrieval device, readable storage medium and electronic equipment |
| CN112948718A (en) * | 2019-12-11 | 2021-06-11 | 百度在线网络技术（北京）有限公司 | Information delivery method, device, equipment and medium |
| CN117876029A (en) * | 2024-03-12 | 2024-04-12 | 南京摆渡人网络信息技术有限公司 | Man-machine interaction optimization system, method and device based on commodity popularization |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870458A (en) * | 2012-12-07 | 2014-06-18 | 富士通株式会社 | Data processing device, data processing method and data processing program |
| CN105701216A (en) * | 2016-01-13 | 2016-06-22 | 北京三快在线科技有限公司 | Information pushing method and device |
| US20160267138A1 (en) * | 2015-03-13 | 2016-09-15 | Telefonaktiebolaget L M Ericsson (Publ) | Active subscriber count based charging and policy control |
-
2016
- 2016-12-30 CN CN201611262654.7A patent/CN108268506A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870458A (en) * | 2012-12-07 | 2014-06-18 | 富士通株式会社 | Data processing device, data processing method and data processing program |
| US20160267138A1 (en) * | 2015-03-13 | 2016-09-15 | Telefonaktiebolaget L M Ericsson (Publ) | Active subscriber count based charging and policy control |
| CN105701216A (en) * | 2016-01-13 | 2016-06-22 | 北京三快在线科技有限公司 | Information pushing method and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377830A (en) * | 2019-07-25 | 2019-10-25 | 拉扎斯网络科技（上海）有限公司 | Retrieval method, retrieval device, readable storage medium and electronic equipment |
| CN112948718A (en) * | 2019-12-11 | 2021-06-11 | 百度在线网络技术（北京）有限公司 | Information delivery method, device, equipment and medium |
| CN112948718B (en) * | 2019-12-11 | 2023-10-17 | 百度在线网络技术（北京）有限公司 | Information delivery method, device, equipment and medium |
| CN117876029A (en) * | 2024-03-12 | 2024-04-12 | 南京摆渡人网络信息技术有限公司 | Man-machine interaction optimization system, method and device based on commodity popularization |
| CN117876029B (en) * | 2024-03-12 | 2024-05-07 | 南京摆渡人网络信息技术有限公司 | Man-machine interaction optimization system, method and device based on commodity popularization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240311411A1 (en) | System and method for information recommendation | |
| RU2419863C2 (en) | System and method of using online dialogue content to select advertisement content and/or other relevant information for display | |
| CN109492164A (en) | A kind of recommended method of resume, device, electronic equipment and storage medium | |
| US9325842B1 (en) | Systems and methods for associating a string with a content item | |
| US20090187520A1 (en) | Demographics from behavior | |
| CN110807649A (en) | Invitation reward method and system for financial products | |
| AU2017203306A1 (en) | Ad-words optimization based on performance across multiple channels | |
| CN111612503B (en) | Advertisement pushing method and device based on external page delivery touch user information and electronic equipment | |
| US20210350419A1 (en) | Method and system for facilitating a provisioning of advertisements to customers | |
| CN104536980A (en) | To-be-commented item quality information determination method and device | |
| KR102100214B1 (en) | Method and appratus for analysing sales conversation based on voice recognition | |
| CN110674620A (en) | Target file generation method, device, medium and electronic equipment | |
| CN110399473B (en) | Method and device for determining answers to user questions | |
| CN113592535B (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
| CN108428175A (en) | A kind of big data analysis method and system based on consumer record | |
| KR20110034174A (en) | Method and server apparatus for providing advertizing service | |
| CN110362662A (en) | Data processing method, device and computer readable storage medium | |
| CN108268506A (en) | A kind of processing method of promotion message, device, terminal and computer readable storage medium | |
| CN113434755A (en) | Page generation method and device, electronic equipment and storage medium | |
| CN108268602A (en) | Analyze method, apparatus, equipment and the computer storage media of text topic point | |
| US10394804B1 (en) | Method and system for increasing internet traffic to a question and answer customer support system | |
| CN117635341A (en) | Method, apparatus, device and computer readable medium for parameter recommendation | |
| EP1193942B1 (en) | System and method for implementing a conditional payload server | |
| CN115440223A (en) | Intelligent interaction method and device, robot and computer readable storage medium | |
| KR20030040273A (en) | Method and system for matching questioner and answerer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180710 |
|
| RJ01 | Rejection of invention patent application after publication |