CN109727052A - Keyword determines method and device - Google Patents
Keyword determines method and device Download PDFInfo
- Publication number
- CN109727052A CN109727052A CN201711053220.0A CN201711053220A CN109727052A CN 109727052 A CN109727052 A CN 109727052A CN 201711053220 A CN201711053220 A CN 201711053220A CN 109727052 A CN109727052 A CN 109727052A
- Authority
- CN
- China
- Prior art keywords
- keyword
- score
- index
- default
- history
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of keywords to determine method and device.Wherein, this method comprises: obtaining history launches keyword and default Score index, wherein, it is in the multiple keywords launched in the first preset time period that history, which launches keyword, frequency of occurrence exceeds the keyword of the first preset threshold, and presetting Score index is the index to score each keyword；According to default calculation, the weight parameter of each index in default Score index is determined；According to the weight parameter of index each in default Score index, each keyword in keyword is launched to history and is scored；The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target keyword.The present invention solves the keyword that can not effectively obtain launching advertisement in the related technology, causes the low efficiency for launching advertisement, leads to the technical problem that user experience is low.
Description
Technical field
The present invention relates to Internet technical fields, determine method and device in particular to a kind of keyword.
Background technique
In the related technology, when carrying out advertisement dispensing, using search engine marketing (Search
EngineMarketing), it is also SEM, is a kind of marketing method for launching bid advertisement according to keyword in a search engine,
Advertiser first has to selected a collection of keyword before launching SEM advertisement, and to the specified bid of each keyword, when user exists
It has been searched for after associative key in search engine, the corresponding advertisement of keyword of advertiser's dispensing can be triggered.Advertiser will throw
The keyword quantity put often all can be very much, and if all launching to all keywords, advertisement spends cost will be very
Height in practical application, should select suitable keyword to be launched according to the purpose that advertisement is launched.Most of the time, advertisement
Zhu Hui authorized agency company selects keyword according to previous dispensing experience by the marketing personnel of agency.But it is this
The mode that keyword is launched according to artificial experience is needed to spend the artificial a large amount of time, and is launched according to artificial experience
Advertisement, the keyword of screening and corresponding clutter can be very more, and the advertisement that can not effectively want advertiser is launched to correspondence
Position.And when by manually launching advertisement, the knowledge that practitioner has profession is generally required, cannot widely be fitted
With cannot effectively launch advertisement for common user, reduce the Experience Degree of user.
For the keyword that can not effectively obtain launching advertisement in the related technology, the low efficiency for launching advertisement is caused, is caused
The low technical problem of user experience, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides a kind of keywords to determine method and device, at least to solve not having in the related technology
Effect obtains launching the keyword of advertisement, causes the low efficiency for launching advertisement, leads to the technical problem that user experience is low.
According to an aspect of an embodiment of the present invention, it provides a kind of keyword and determines method, comprising: obtain history and launch
Keyword and default Score index, wherein it is the multiple passes launched in the first preset time period that the history, which launches keyword,
In keyword, frequency of occurrence exceeds the keyword of the first preset threshold, and the default Score index is to comment each keyword
The index divided；According to default calculation, the weight parameter of each index in the default Score index is determined；According to described
The weight parameter of each index in default Score index, launches each keyword in keyword to the history and scores；
The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target keyword.
Further, it obtains history dispensing keyword and default Score index includes: to obtain in first preset time
The advertising information of advertisement is launched in section；According to the advertising information, multiple dispensing keywords are determined；According to the advertising information,
Determine multiple default Score indexes, wherein the multiple default Score index includes at least: ad click number single clicks on valence
Lattice, clicking rate, wish number, secondary attack rate under turn over number, line under turn over number, line on line.
Further, the default calculation includes: default optimization method, wherein the default optimization method includes:
First formula,Second formula, keyword_score0i=a*
click0i+b*cpc0i+c*ctr0i+d*online_conversion0i+e*crm_conversion0i+f*crm_will0i+g*
assist0i, i=1,2 ..., N0；Third formula, keyword_score0i≥keyword_score0(i+1)；4th formula, a+b+
C+d+e+f+g=1；5th formula, e >=d > f >=g > a >=c >=b；6th formula, Wherein, a, b, c, d, e, f and g are Score index
Weight parameter, crm_conversion_will_count are conversion and wish number, keyword_score under line0iIt is default for second
The score of period keyword i, subscript 0 indicate second preset time period, and click indicates that ad click number, cpc indicate single
Secondary click price, ctr indicate clicking rate, and online_conversion indicates that turn over number on line, crm_conversion indicate line
Lower turn over number, crm_will indicate that wish number under line, assist indicate secondary attack rate,Indicate described
Two preset time periods are scored at keyword_score0iKeyword i, in the consumption of third preset time period, subscript 1 indicates the
Three preset time periods.
Further, after obtaining history and launching keyword and default Score index, comprising: launch and close to the history
Abnormal keyword in keyword is filtered, and is obtained filtered history and is launched keyword, wherein the exception keyword is at least
It include: session number is that the keyword of third predetermined threshold value, ad click number are less than or equal to the keyword of the 4th preset threshold, session
Number is greater than the keyword of the hits；According to the weight parameter of each index in the default Score index, to the history
Launching each keyword in keyword and carrying out scoring includes: the weight ginseng according to each index in the default Score index
Number launches each keyword in keyword to the filtered history and scores；Scoring it will be greater than the in appraisal result
It includes: to launch and close from the filtered history according to appraisal result that the keyword of two preset thresholds, which is determined as target keyword,
Target keyword is determined in keyword.
Further, it according to appraisal result, is launched in keyword from the history and determines at least one target critical
After word, comprising: according at least one described target keyword, determine advertisement impression information；According to the advertisement impression information
Carry out advertisement dispensing.
According to another aspect of an embodiment of the present invention, a kind of keyword determining device is additionally provided, comprising: acquiring unit,
Keyword and default Score index are launched for obtaining history, wherein it is in the first preset time that the history, which launches keyword,
In the multiple keywords launched in section, frequency of occurrence exceeds the keyword of the first preset threshold, and the default Score index is pair
The index that each keyword scores；First determination unit, for determining the default scoring according to calculation is preset
The weight parameter of each index in index；Score unit, for being joined according to the weight of each index in the default Score index
Number launches each keyword in keyword to the history and scores；Second determination unit, for will be commented in appraisal result
The keyword greater than the second preset threshold is divided to be determined as target keyword.
Further, the acquiring unit includes: acquisition module, is launched in first preset time period for obtaining
The advertising information of advertisement；First determining module, for determining multiple dispensing keywords according to the advertising information；Second determines
Module, for determining multiple default Score indexes, wherein the multiple default Score index is at least according to the advertising information
Include: ad click number, single click on price, clicking rate, wish number, secondary attack rate under turn over number, line under turn over number, line on line.
Further, the default calculation includes: default optimization method, wherein the default optimization method includes:
First formula,Second formula, keyword_score0i=
a*click0i+b*cpc0i+c*ctr0i+d*online_conversion0i+e*crm_conversion0i+f*crm_will0i+
g*assist0i, i=1,2 ..., N0；Third formula, keyword_score0i≥keyword_score0(i+1)；4th formula, a+
B+c+d+e+f+g=1；5th formula, e >=d > f >=g > a >=c >=b；6th formula, Wherein, a, b, c, d, e, f and g are Score index
Weight parameter, crm_conversion_will_count be line under conversion and wish number, keyword_score0iIt is pre- for second
If the score of period keyword i, subscript 0 indicates second preset time period, and click indicates that ad click number, cpc indicate
Price is single clickd on, ctr indicates clicking rate, and online_conversion indicates that turn over number on line, crm_conversion indicate
Turn over number under line, crm_will indicate that wish number under line, assist indicate secondary attack rate,Described in expression
Second preset time period is scored at keyword_score0iKeyword i, in the consumption of third preset time period, subscript 1 is indicated
Third preset time period.
According to another aspect of an embodiment of the present invention, a kind of storage medium is additionally provided, the storage medium includes storage
Program, wherein described program operation when control the storage medium where equipment execute pass described in above-mentioned any one
Keyword determines method.
According to another aspect of an embodiment of the present invention, a kind of processor is additionally provided, the processor is used to run program,
Wherein, keyword described in above-mentioned any one, which is executed, when described program is run determines method.
In embodiments of the present invention, it can first get history and launch keyword and default Score index, then according to pre-
If calculation, determines the weight parameter of each index in default Score index, can respectively refer to according in default scoring later
Target weight parameter launches each keyword in keyword to history and scores, can will finally be commented according to appraisal result
The keyword that scoring is greater than the second preset threshold in point result is determined as target keyword.In this embodiment it is possible to using pre-
If calculation, the weight parameter of Score index is determined, using the weight parameter of Score index, determine target keyword, benefit
It instructs advertisement to launch with target keyword, solves the keyword that can not effectively obtain launching advertisement in the related technology, cause to launch
The low efficiency of advertisement leads to the technical problem that user experience is low.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart that keyword according to an embodiment of the present invention determines method；
Fig. 2 is the schematic diagram of keyword determining device according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
The present invention is understood for the ease of user, and solution is made to part term or noun involved in the embodiment of the present invention below
It releases:
Search engine marketing, Search Engine Marketing utilize use using the mode of search engine according to user
Marketing message is passed to target user as far as possible by the chance of family retrieval information.Search engine marketing is based on search engine platform
Network marketing, dependence and use habit using people to search engine, people retrieve information when pass the information on
To target user.
According to embodiments of the present invention, a kind of embodiment of the method that keyword determines is provided, it should be noted that in attached drawing
Process the step of illustrating can execute in a computer system such as a set of computer executable instructions, although also,
Logical order is shown in flow charts, but in some cases, can be executed with the sequence for being different from herein it is shown or
The step of description.
Following embodiment can be applied in system or application that various keywords determine, and the field of application can wrap
It includes but is not limited to: marketing domain, advertisement putting field, in keyword search APP, wherein the embodiment of the present invention can be to various
Network marketing provides more accurate parameter.In the related art, it during network marketing, can only be launched by the advertisement of profession
The parameter occurred in advertisement process is launched in personal management, and this mode needs the dispensing advertisement of long-time Manual arranging and user to exist
See the relevant operation launched and carried out after advertisement, a large amount of time and prolonged experience is thus needed to obtain launching advertisement
Data used in journey, can not allow ordinary user also to use these parameters, and the present invention can be said by taking search engine as an example
It is bright, it can use the Score index and the corresponding weight parameter of each Score index of keyword, determine the key that user wants
Word allows user to recognize the data for launching advertisement, and then allows user to can use determining keyword and launch advertisement, improves and launches
The efficiency of advertisement.
Below in conjunction with preferred implementation steps, the present invention will be described, and Fig. 1 is keyword according to an embodiment of the present invention
Determine the flow chart of method, as shown in Figure 1, this method comprises the following steps:
Step S102 obtains history and launches keyword and default Score index, wherein it is first that history, which launches keyword,
In the multiple keywords launched in preset time period, frequency of occurrence exceeds the keyword of the first preset threshold, presets Score index
For the index to score each keyword.
Wherein, it is to the advertising information for launching advertisement in historical process that the history in the embodiment of the present invention, which launches keyword,
After being arranged, being counted, determining keyword, the first preset time period, which can be advertisement dispensing user, (can be understood as advertisement
It is main) voluntarily determining duration, including but not limited to: two months, three months, half a year obtain after determining the first preset time period
The advertising information that user carries out advertisement dispensing is launched in advertisement in first preset time period.Advertisement can be launched and be used in the present invention
The dispensing data at family are obtained, and may include: advertisement impressions, the advertisement release time, theme is launched in advertisement, advertisement is thrown
Content etc. is put, then obtains user to the information for launching advertisement progress relevant operation, the relevant operation of the user may include: wide
Accuse hits, single click on price, click time, product order etc., then to various above-mentioned users to the operation information of advertisement
User is launched with advertisement to analyze in the information for launching advertisement, determines advertising information.
For presetting Score index, after can be the various keywords in the advertising information of extraction, to each keyword
The index to score, which, which can be, establishes each keyword parameter, and specific grading system and score value, are users
The data of self-setting, for example, scoring score value be 1-10, wherein 1 indicate it is worst, 10 indicate it is best, can also with grade come
Scoring is indicated, for example, 1-10 grades.The keyword of advertising information can refer to the key word for launching advertisement every time, for example,
Primary to launch in advertisement " mineral water ", the keyword of extraction includes: " mineral water ", " price ", " quantity ", " date ".By obtaining
The keyword in advertising information is taken, determines the various parameters occurred in advertisement.
Optionally, it obtains history dispensing keyword and default Score index includes: to obtain to throw in the first preset time period
Put the advertising information of advertisement；According to advertising information, multiple dispensing keywords are determined；According to advertising information, determine that multiple preset is commented
Point index, wherein multiple default Score indexes include at least: ad click number single clicks on price, clicking rate, converts on line
Number, wish number, secondary attack rate under turn over number, line under line.
Wherein, the number that above-mentioned ad click number can be clicked for keyword in advertising information by user, single point
Hitting price can be the average clicked price that keyword is clicked by user, and clicking rate can be clicked for keyword in advertising information
The ratio of number and keyword frequency of occurrence, turn over number can enter advertisement for keyword in advertising information and launch user on line
The session number of predetermined registration operation on line occurs for website, and turn over number can be launched under line to access advertisement by keyword in advertising information
The target StoreFront of user generates the session number of order, and wish number can be thrown under line to access advertisement by keyword in advertising information
The target StoreFront for putting user has a mind to generate the session number of order, and secondary attack rate can be visited for user by keyword in advertising information
Ask that the transition probability converted under line occurs to user for the target StoreFront of advertisement dispensing user.
Above-mentioned each default Score index, the relevant operational parameter mainly carried out after seeing advertisement to user carry out
Statistics can preferably feed back user out to launching in historical process by analysis user to the operation data of advertising information
The response of advertisement, obtains field feedback, can be determined to launch advertisement in historical process according to the field feedback
Quality.
Score index is preset for above-mentioned items, can be formed by a single and launched extensively for dispensing advertisement each time
The index table of announcement for ad click number and single clicks on price, can be after user clicks advertisement, accumulates once advertisement point
Number is hit, and records the price of the secondary click, mean value calculation is carried out to click price after statistics obtains multiple click prices and is obtained
To single clicing on price, and for clicking rate, it can refer to and be clicked number and keyword light exposure by keyword (i.e. keyword goes out
Occurrence number) ratio refer to what user conversated on the website of advertiser and for turn over number under turn over number on line and line
Data including predetermined registration operation on the line that directly carries out and generate the session number of order.Wherein, target StoreFront may also mean that
The website of advertiser, which, which can be advertisement, launches user and directly carries out the APP of advertisement dispensing and apply or sell goods
Website, such as Taobao.In addition, conversion occurs under line in secondary attack rate can refer to the order contract additionally signed, Huo Zheyong
The operation that user voluntarily carries out signing order is launched in family and advertisement, may not carry out order in the website that user is launched in advertisement, this
In need user voluntarily to count the secondary attack rate.
Step S104 determines the weight parameter of each index in default Score index according to default calculation.
Wherein, default calculation includes: default optimization method, wherein and default optimization method includes: the first formula,Second formula, keyword_score0i=a*click0i+b*cpc0i+c*
ctr0i+d*online_conversion0i+e*crm_conversion0i+f*crm_will0i+g*assist0i, i=1,
2,…,N0；Third formula, keyword_score0i≥keyword_score0(i+1)；4th formula, a+b+c+d+e+f+g=1；
5th formula, e >=d > f >=g > a >=c >=b；6th formula,
Wherein, a, b, c, d, e, f and g be Score index weight parameter, crm_conversion_will_count be line under conversion and
Wish number, keyword_score0iFor the score of the second preset time period keyword i, subscript 0 indicates the second preset time period,
Click indicates ad click number, and cpc expression single clicks on price, and ctr indicates clicking rate, and online_conversion indicates line
Upper turn over number, crm_conversion indicate that turn over number under line, crm_will indicate that wish number under line, assist indicate secondary attack
Rate,Indicate that the second preset time period is scored at keyword_score0iKeyword i, it is pre- in third
If the consumption of period, subscript 1 indicates third preset time period.
By above-mentioned formula, the corresponding weight parameter of available each index, i.e., above-mentioned ad click number, single
Click price, clicking rate, wish number, secondary attack rate can all have corresponding weight parameter under turn over number, line under turn over number, line on line,
Above-mentioned weight parameter includes: a, b, c, d, e, f, g, each index is corresponding with a weight parameter.
Wherein, the second preset time period can refer to period earlier time in the first preset time period, for example,
First preset time period is two months (such as July and August), needs to get bimestrial advertising information, user in historical process
Operation information, then, it is determined that data (data in such as July), the i.e. last month that the second preset time period is one month earlier out
Data.Third preset time period is also possible to the time later time section in the first preset time period, i.e. next month
Data can be the data of August by taking aforesaid intervals as an example.
Step S106 launches history every in keyword according to the weight parameter of index each in default Score index
A keyword scores.
It, can be after the weight parameter for obtaining each Score index, according to weight parameter, weight parameter using above-mentioned steps
Corresponding Score index determines the scoring of keyword.For example, ad click number is 5, to single click on price be 7, clicking rate
Be 5 for turn over number on 8, line, turn over number is 7 under line, wish number is 6 under line, secondary attack rate is 8, determine keyword " jacket "
Scoring is 6.8.
The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target keyword by step S108.
It can determine that target keyword, the second preset threshold can be according to not by the appraisal result of keyword
What same advertisement determined, it is also possible to user's self-defining, for example, the second preset threshold is 7.5.Pass through the second preset threshold
It can determine multiple target keywords.
Above-mentioned steps of the present invention are launched in keyword from history according to appraisal result and determine at least one mesh
After mark keyword, comprising: according at least one target keyword, determine advertisement impression information；According to advertisement impression information into
Row advertisement is launched.
Using target keyword, determine suitable advertisement impression information, i.e., it is interested in user in historical process
Advertisement be delivered to user again, with improve user buy commodity.
Through the above steps, it can first get history and launch keyword and default Score index, then according to pre-designed
Calculation mode determines the weight parameter of each index in default Score index, later can be according to index each in default scoring
Weight parameter launches each keyword in keyword to history and scores, and can finally be tied scoring according to appraisal result
The keyword that scoring is greater than the second preset threshold in fruit is determined as target keyword.In this embodiment it is possible to using pre-designed
Calculation mode determines the weight parameter of Score index, using the weight parameter of Score index, determines target keyword, utilizes mesh
Mark keyword instructs advertisement to launch, and solves the keyword that can not effectively obtain launching advertisement in the related technology, causes to launch advertisement
Low efficiency, lead to the technical problem that user experience is low.
The above embodiment of the present invention may include: to going through after obtaining history and launching keyword and default Score index
The abnormal keyword that history is launched in keyword is filtered, and is obtained filtered history and is launched keyword wherein, abnormal keyword
Include at least: session number be the keyword of third predetermined threshold value, ad click number be less than or equal to the 4th preset threshold keyword,
Session number is greater than the keyword of hits；According to the weight parameter of index each in default Score index, history is launched crucial
It includes: according to the weight parameter for presetting each index in Score index, to filtered that each keyword in word, which carries out scoring,
Each keyword that history is launched in keyword scores；Scoring in appraisal result is greater than to the keyword of the second preset threshold
Being determined as target keyword includes: to launch in keyword from filtered history according to appraisal result and determine target keyword.
Wherein, abnormal keyword can refer to after counting every advertising information, user information, the number not being available
According to keyword less to the session number occurred in keyword, that hits are less filters out.Third predetermined threshold value can be positive
The less numerical value of numerical value in number, such as 0,1,2, and the 4th preset threshold can be and be supplemented according to different numerical value, such as 9,10,
11 etc., the above-mentioned keyword less to session number and hits filters out, and is greater than the keyword of hits to session number
Also it is filtered out, emphasis gets the data of the more keyword of number of clicks.For example, being sold in advertisement in a clothes, wrap
Include three keywords " socks ", " jacket ", " trousers ", wherein for keyword be " socks " data statistics after, find its point
Hit number only 8 times, and the 4th preset threshold be 10 times, at this moment just need filter out " socks " relevant data, do not need to its into
Row analysis.
In addition, advertisement launches user (advertiser) in primary analysis in use, desired data can be determined, can be
It determines marketing objectives, which can include but is not limited to: increasing conversion under line, increases and money, increase advertisement is stayed to go out on line
Occurrence number etc., wherein conversion can refer to that user launches the data that user signs order, line with advertisement after seeing advertisement under line
On stay money that can refer to that user registers in the website that user is launched in advertisement, signs the operation datas such as order.
The present invention can use the implementation steps in above-described embodiment, no according to advertiser's (user is launched in i.e. above-mentioned advertisement)
Same marketing objectives determines the weight parameter of Score index, to realize that automation is key by presetting optimization method
Word scores, and keyword score is sent to advertisement beyond the target keyword of the second preset threshold and launches user, wide to allow
Advertisement dispensing can directly be carried out according to the scoring of target keyword by accusing dispensing user.
Below with reference to another kind, examples illustrate the present invention.
In embodiments of the present invention, the target that AdWords is launched can be determined, choosing has a fixing to the target
Loud index establishes the optimization method of with constraint conditions according to the bimestrial data of history, so that the score selected in the month before
Maximum a batch keyword, the condition of consumption next month less than last month whole keyword overall consumption half next month
Under, it realizes that target maximizes, the weight parameter to each index of keyword score is determined with this.
Choose advertiser (user is launched in the advertisement in above-described embodiment) bimestrial dispensing number in search engine marketing
According to, select all simultaneous keyword at two months, remove session number be 0 keyword, remove hits be less than etc.
In 10 keyword, session number is filtered out greater than the abnormal keyword data such as hits.
It is assumed that increase wish and turn over number under advertisement main line, as target, the index of selection has the advertisement point of keyword
It hits number (click), single click on price (cpc), clicking rate (ctr), on line under turn over number (online_conversion), line
Wish number (crm_will) and secondary attack rate (assist) under turn over number (crm_conversion), line.Below to each index into
Row explanation:
Ad click number: the number that keyword was clicked by user.
Single click on price: the average clicked price that keyword is clicked by user.
Clicking rate: the hits of keyword remove the light exposure of keyword.
Turn over number on line: advertisement main web site is entered by keyword, the session for registering or staying the behaviors such as money on line occurs
Number.
Turn over number under line: entering client web site by keyword, generates the session number of order in advertiser shops later.
Wish number under line: entering client web site by keyword, has a mind to generate order later in advertiser shops
Session number.
Secondary attack rate: user accesses the transition probability converted under advertiser official website to user's generation line by keyword.
Establish optimization method
The optimization method of with constraint conditions is as follows:
(1)
(2)
keyword_score0i=a*click0i+b*cpc0i+c*ctr0i+d*online_conversion0i+e*crm_
conversion0i+f*crm_will0i+g*assist0i, i=1,2 ..., N0；
(3)keyword_score0i≥keyword_score0(i+1)；
(4) a+b+c+d+e+f+g=1；
(5) e >=d > f >=g > a >=c >=b；
(6)
Wherein, formula (1) is objective function, a collection of keyword of m before the score to select in the month before is arranged, next month
Line under turn over number and wish number reach maximum, crm_conversion_will_count is conversion and wish number under line；(2)
For keyword score function, keyword_score0iFor the score of last month keyword i, subscript 0 indicates last month, click0i
Indicate the hits of last month keyword, the meaning and so on of other indexs, N in (2)0Indicate the total of last month keyword
Number, a, b, c, d, e, f and g are the weight of each index when evaluating keyword score；(3) it indicates to calculated pass under given weight
The arrangement of keyword score descending；(4) it indicates the weight of each index and is 1；(5) size relation between the weight specified is indicated,
This can determine according to specific optimization aim；(6) it is used to determine the keyword quantity m selected, so that the score selected arranges preceding m
Keyword consumption next month less than whole keyword overall consumption next month half,It indicates
Last month is scored at keyword_score0iKeyword i, consumption next month, subscript 1 indicate next month.
Parameter a, b, c, d, e, f and g that above equation is found out using the method that violence solves.
It finally can choose keyword, the parameter of each index found out above used into other history numbers launched
According to, keyword score is calculated, the high some keywords of score is selected and is launched, turn over number under optimization line.
The embodiment of the present invention can be different according to advertiser marketing objectives, such as: increase line under conversion, increase line on stay money,
Increase advertisement exposure etc., establish the optimization method of with constraint conditions, determines the weight parameter for influencing each index of objective function,
To realize that automation is keyword marking, advertisement is instructed to launch.This process does not need to be engaged in search engine marketing too much
Staff participate in, manpower can be saved.
Fig. 2 is the schematic diagram of keyword determining device according to an embodiment of the present invention, as shown in Fig. 2, the device can wrap
Include: acquiring unit 21 launches keyword and default Score index for obtaining history, wherein it is that history, which launches keyword,
In the multiple keywords launched in one preset time period, frequency of occurrence exceeds the keyword of the first preset threshold, and default scoring refers to
It is designated as the index to score each keyword；First determination unit 23, for determining to preset according to calculation is preset
The weight parameter of each index in Score index；Score unit 25, for according to the weight for presetting each index in Score index
Parameter launches each keyword in keyword to history and scores；Second determination unit 27, for will be commented in appraisal result
The keyword greater than the second preset threshold is divided to be determined as target keyword.
Through the foregoing embodiment, history can be first got by acquiring unit 21 and launches keyword and presets scoring refers to
Mark determines the weight of each index in default Score index then by the first determination unit 23 according to default calculation
Parameter can launch in keyword history by scoring unit 25 according to the weight parameter of index each in default scoring later
Each keyword score, can will finally score in appraisal result by the second determination unit 27 according to appraisal result
Keyword greater than the second preset threshold is determined as target keyword.In this embodiment it is possible to using default calculation, really
The weight parameter for determining Score index determines target keyword using the weight parameter of Score index, is referred to using target keyword
Advertisement dispensing is led, the keyword that can not effectively obtain launching advertisement in the related technology is solved, the low efficiency for launching advertisement is caused, leads
The technical problem for causing user experience low.
Wherein, above-mentioned acquiring unit 21 may include: acquisition module, launch in the first preset time period for obtaining
The advertising information of advertisement；First determining module, for determining multiple dispensing keywords according to advertising information；Second determining module,
For determining multiple default Score indexes according to advertising information, wherein multiple default Score indexes include at least: ad click
Number single clicks on price, clicking rate, wish number, secondary attack rate under turn over number, line under turn over number, line on line.
Wherein, the number that above-mentioned ad click number can be clicked for keyword in advertising information by user, single point
Hitting price is the average clicked price that keyword is clicked by user, and clicking rate is that keyword is clicked number and pass in advertising information
The ratio of keyword frequency of occurrence, turn over number is that keyword enters advertisement and launches user website and occurs on line in advertising information on line
The session number of predetermined registration operation, under line turn over number be pass through keyword in advertising information access advertisement launch user target StoreFront it is raw
At the session number of order, wish number is intentional by the target StoreFront of keyword access advertisement dispensing user in advertising information under line
It is willing to generate the session number of order, secondary attack rate is the target StoreFront that user accesses that user is launched in advertisement by keyword in advertising information
The transition probability converted under line occurs to user.
In addition, above-mentioned default calculation includes: default optimization method, wherein default optimization method includes: the first public affairs
Formula,Second formula, keyword_score0i=a*
click0i+b*cpc0i+c*ctr0i+d*online_conversion0i+e*crm_conversion0i+f*crm_will0i+g*
assist0i, i=1,2 ..., N0；Third formula, keyword_score0i≥keyword_score0(i+1)；4th formula, a+b+
C+d+e+f+g=1；5th formula, e >=d > f >=g > a >=c >=b；6th formula, Wherein, a, b, c, d, e, f and g are Score index
Weight parameter, crm_conversion_will_count be line under conversion and wish number, keyword_score0iIt is pre- for second
If the score of period keyword i, subscript 0 indicates second preset time period, and click indicates that ad click number, cpc indicate
Price is single clickd on, ctr indicates clicking rate, and online_conversion indicates that turn over number on line, crm_conversion indicate
Turn over number under line, crm_will indicate that wish number under line, assist indicate secondary attack rate,Described in expression
Second preset time period is scored at keyword_score0iKeyword i, in the consumption of third preset time period, subscript 1 is indicated
Third preset time period.
Above-mentioned keyword determining device can also include processor and memory, and above-mentioned acquiring unit 21, first determines
Unit 23, scoring unit 25, second determination unit 27 etc. store in memory as program unit, are deposited by processor execution
Above procedure unit in memory is stored up to realize corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, it scores by adjusting kernel parameter the keyword in advertisement release process, so that it is determined that advertisement is launched out
Keyword, to instruct advertisement to launch.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
According to another aspect of an embodiment of the present invention, a kind of storage medium is additionally provided, storage medium includes the journey of storage
Sequence, wherein the keyword that equipment where control storage medium executes above-mentioned any one in program operation determines method.
According to another aspect of an embodiment of the present invention, a kind of processor is additionally provided, processor is used to run program,
In, program executes above-mentioned any one keyword when running determines method.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor are performed the steps of to obtain history dispensing keyword and preset when executing program and be commented
Divide index, wherein it is in the multiple keywords launched in the first preset time period that history, which launches keyword, and frequency of occurrence exceeds
The keyword of first preset threshold, presetting Score index is the index to score each keyword；According to default calculating side
Formula determines the weight parameter of each index in default Score index；Joined according to the weight of index each in default Score index
Number launches each keyword in keyword to history and scores；Scoring in appraisal result is greater than the second preset threshold
Keyword is determined as target keyword.
Optionally, when above-mentioned processor executes program, it can also obtain and launch the wide of advertisement in the first preset time period
Accuse information；According to advertising information, multiple dispensing keywords are determined；According to advertising information, multiple default Score indexes are determined,
In, multiple default Score indexes include at least: ad click number single clicks on price, clicking rate, turn over number, lower turn of line on line
Change wish number, secondary attack rate under number, line.
Wherein, default calculation includes: default optimization method, wherein and default optimization method includes: the first formula,Second formula, keyword_score0i=a*click0i+
b*cpc0i+c*ctr0i+d*online_conversion0i+e*crm_conversion0i+f*crm_will0i+g*assist0i,
I=1,2 ..., N0；Third formula, keyword_score0i≥keyword_score0(i+1)；4th formula, a+b+c+d+e+f+
G=1；5th formula, e >=d > f >=g > a >=c >=b；6th formula, Wherein, a, b, c, d, e, f and g are Score index
Weight parameter, crm_conversion_will_count be line under conversion and wish number, keyword_score0iIt is pre- for second
If the score of period keyword i, subscript 0 indicates second preset time period, and click indicates that ad click number, cpc indicate
Price is single clickd on, ctr indicates clicking rate, and online_conversion indicates that turn over number on line, crm_conversion indicate
Turn over number under line, crm_will indicate that wish number under line, assist indicate secondary attack rate,Described in expression
Second preset time period is scored at keyword_score0iKeyword i, in the consumption of third preset time period, subscript 1 is indicated
Third preset time period.
Optionally, when above-mentioned processor executes program, the abnormal keyword that can also be launched in keyword to history is carried out
Filtering obtains filtered history and launches keyword wherein, and abnormal keyword includes at least: session number is third predetermined threshold value
Keyword, ad click number are less than or equal to the keyword of the 4th preset threshold, session number is greater than the keyword of hits；According to institute
The weight parameter for stating each index in default Score index launches each keyword in keyword to the history and scores
It include: to be launched in keyword according to the weight parameter of each index in the default Score index to the filtered history
Each keyword score；The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target keyword
It include: to be launched in keyword from the filtered history according to appraisal result and determine target keyword.
Optionally, when above-mentioned processor executes program, it can also determine that advertisement is launched according at least one target keyword
Information；Advertisement dispensing is carried out according to advertisement impression information.
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step: it obtains history and launches keyword and default Score index, wherein history launches keyword
For in multiple keywords for launching in the first preset time period, frequency of occurrence exceeds the keyword of the first preset threshold, preset
Score index is the index to score each keyword；According to default calculation, determine every in default Score index
The weight parameter of a index；According to the weight parameter of index each in default Score index, history is launched every in keyword
A keyword scores；The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target keyword.
Optionally, when above-mentioned data processing equipment executes program, it can also obtain and be launched extensively in the first preset time period
The advertising information of announcement；According to advertising information, multiple dispensing keywords are determined；According to advertising information, determine that multiple default scorings refer to
Mark, wherein multiple default Score indexes include at least: ad click number single clicks on price, clicking rate, turn over number, line on line
Wish number, secondary attack rate under lower turn over number, line.
Wherein, default calculation includes: default optimization method, wherein and default optimization method includes: the first formula,Second formula, keyword_score0i=a*click0i+
b*cpc0i+c*ctr0i+d*online_conversion0i+e*crm_conversion0i+f*crm_will0i+g*assist0i,
I=1,2 ..., N0；Third formula, keyword_score0i≥keyword_score0(i+1)；4th formula, a+b+c+d+e+f+
G=1；5th formula, e >=d > f >=g > a >=c >=b；6th formula, Wherein, a, b, c, d, e, f and g are Score index
Weight parameter, crm_conversion_will_count be line under conversion and wish number, keyword_score0iIt is pre- for second
If the score of period keyword i, subscript 0 indicates second preset time period, and click indicates that ad click number, cpc indicate
Price is single clickd on, ctr indicates clicking rate, and online_conversion indicates that turn over number on line, crm_conversion indicate
Turn over number under line, crm_will indicate that wish number under line, assist indicate secondary attack rate,Described in expression
Second preset time period is scored at keyword_score0iKeyword i, in the consumption of third preset time period, subscript 1 is indicated
Third preset time period.
Optionally, when above-mentioned data processing equipment executes program, the exception that can also be launched in keyword to history is crucial
Word is filtered, and obtain filtered history and launch keyword wherein, abnormal keyword includes at least: session number is default for third
Keyword, the ad click number of threshold value are less than or equal to the keyword of the 4th preset threshold, session number is greater than the keyword of hits；
According to the weight parameter of each index in the default Score index, to the history launch each keyword in keyword into
Row scoring includes: to launch and close to the filtered history according to the weight parameter of each index in the default Score index
Each keyword in keyword scores；The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target
Keyword includes: to launch in keyword from the filtered history according to appraisal result and determine target keyword.
Optionally, it when above-mentioned data processing equipment executes program, can also be determined wide according at least one target keyword
Accuse impression information；Advertisement dispensing is carried out according to advertisement impression information.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of keyword determines method characterized by comprising
It obtains history and launches keyword and default Score index, wherein it is in the first preset time that the history, which launches keyword,
In the multiple keywords launched in section, frequency of occurrence exceeds the keyword of the first preset threshold, and the default Score index is pair
The index that each keyword scores；
According to default calculation, the weight parameter of each index in the default Score index is determined；
According to the weight parameter of each index in the default Score index, each key in keyword is launched to the history
Word scores；
The keyword that scoring is greater than the second preset threshold in appraisal result is determined as target keyword.
2. the method according to claim 1, wherein obtaining history launches keyword and default Score index packet
It includes:
Obtain the advertising information that advertisement is launched in first preset time period；
According to the advertising information, multiple dispensing keywords are determined；
According to the advertising information, multiple default Score indexes are determined, wherein the multiple default Score index includes at least:
Ad click number single clicks on price, clicking rate, wish number, secondary attack rate under turn over number, line under turn over number, line on line.
3. the method according to claim 1, wherein the default calculation includes: default optimization method,
In, the default optimization method includes:
First formula,
Second formula, keyword_score0i=a*click0i+b*cpc0i+c*ctr0i+d*online_conversion0i+e*
crm_conversion0i+f*crm_will0i+g*assist0i, i=1,2 ..., N0；
Third formula, keyword_score0i≥keyword_score0(i+1)；
4th formula, a+b+c+d+e+f+g=1；
5th formula, e >=d > f >=g > a >=c >=b；
6th formula,
Wherein, a, b, c, d, e, f and g are the weight parameter of Score index, and crm_conversion_will_count is lower turn of line
Change and wish number, keyword_score0iFor the score of the second preset time period keyword i, subscript 0 indicates that described second is default
Period, click indicate ad click number, and cpc expression single clicks on price, and ctr indicates clicking rate, online_
Conversion indicates that turn over number on line, crm_conversion indicate that turn over number under line, crm_will indicate wish number under line,
Assist indicates secondary attack rate,Indicate that second preset time period is scored at keyword_score0i
Keyword i, in the consumption of third preset time period, subscript 1 indicates third preset time period.
4. the method according to claim 1, wherein obtain history launch keyword and default Score index it
Afterwards, comprising:
The abnormal keyword in keyword is launched to the history to be filtered, and is obtained filtered history and is launched keyword,
In, the exception keyword includes at least: session number is the keyword of third predetermined threshold value, ad click number less than or equal to the 4th
The keyword of preset threshold, session number are greater than the keyword of the hits；
According to the weight parameter of each index in the default Score index, each key in keyword is launched to the history
Word carries out scoring
According to the weight parameter of each index in the default Score index, the filtered history is launched in keyword
Each keyword scores；
The keyword that scoring is greater than the second preset threshold in appraisal result, which is determined as target keyword, includes:
According to appraisal result, is launched in keyword from the filtered history and determine target keyword.
5. the method according to claim 1, wherein launching keyword from the history according to appraisal result
In determine at least one target keyword after, comprising:
According at least one described target keyword, advertisement impression information is determined；
Advertisement dispensing is carried out according to the advertisement impression information.
6. a kind of keyword determining device characterized by comprising
Acquiring unit launches keyword and default Score index for obtaining history, wherein the history launch keyword be
In the multiple keywords launched in first preset time period, frequency of occurrence exceeds the keyword of the first preset threshold, described default
Score index is the index to score each keyword；
First determination unit, for determining the weight of each index in the default Score index according to calculation is preset
Parameter；
Score unit, for the weight parameter according to each index in the default Score index, launches to the history crucial
Each keyword in word scores；
Second determination unit, for the keyword that scoring is greater than the second preset threshold in appraisal result to be determined as target critical
Word.
7. device according to claim 6, which is characterized in that the acquiring unit includes:
Module is obtained, for obtaining the advertising information for launching advertisement in first preset time period；
First determining module, for determining multiple dispensing keywords according to the advertising information；
Second determining module, for determining multiple default Score indexes according to the advertising information, wherein the multiple default
Score index includes at least: ad click number single clicks on price, clicking rate, is anticipated under turn over number, line on line under turn over number, line
It is willing to number, secondary attack rate.
8. device according to claim 6, which is characterized in that the default calculation includes: default optimization method,
In, the default optimization method includes:
First formula,
Second formula, keyword_score0i=a*click0i+b*cpc0i+c*ctr0i+d*online_conversion0i+e*
crm_conversion0i+f*crm_will0i+g*assist0i, i=1,2 ..., N0；
Third formula, keyword_score0i≥keyword_score0(i+1)；
4th formula, a+b+c+d+e+f+g=1；
5th formula, e >=d > f >=g > a >=c >=b；
6th formula,
Wherein, a, b, c, d, e, f and g are the weight parameter of Score index, and crm_conversion_will_count is lower turn of line
Change and wish number, keyword_score0iFor the score of the second preset time period keyword i, subscript 0 indicates that described second is default
Period, click indicate ad click number, and cpc expression single clicks on price, and ctr indicates clicking rate, online_
Conversion indicates that turn over number on line, crm_conversion indicate that turn over number under line, crm_will indicate wish number under line,
Assist indicates secondary attack rate,Indicate that second preset time period is scored at keyword_score0i
Keyword i, in the consumption of third preset time period, subscript 1 indicates third preset time period.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require any one of 1 to 5 described in keyword determine method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 5 described in keyword determine method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053220.0A CN109727052A (en) | 2017-10-31 | 2017-10-31 | Keyword determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053220.0A CN109727052A (en) | 2017-10-31 | 2017-10-31 | Keyword determines method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109727052A true CN109727052A (en) | 2019-05-07 |
Family
ID=66293276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711053220.0A Pending CN109727052A (en) | 2017-10-31 | 2017-10-31 | Keyword determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109727052A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110544152A (en) * | 2019-08-30 | 2019-12-06 | 苏州熙烁数字科技有限公司 | cloud distribution type digital service community for merchant propaganda |
| CN111090741A (en) * | 2019-12-13 | 2020-05-01 | 国网四川省电力公司 | Data processing method, device and system |
| CN111259662A (en) * | 2020-02-18 | 2020-06-09 | 支付宝(杭州)信息技术有限公司 | Method and device for processing text |
| CN111755003A (en) * | 2020-06-23 | 2020-10-09 | 北京联想软件有限公司 | Voice interaction realization method and device and electronic equipment |
| CN112132601A (en) * | 2019-06-25 | 2020-12-25 | 百度在线网络技术（北京）有限公司 | Advertisement title rewriting method, device and storage medium |
| CN112650830A (en) * | 2020-11-17 | 2021-04-13 | 北京字跳网络技术有限公司 | Keyword extraction method and device, electronic equipment and storage medium |
| CN113657099A (en) * | 2021-08-13 | 2021-11-16 | 华世界数字科技(深圳)有限公司 | Commodity title generation method and device, intelligent equipment and storage medium |
| CN114638646A (en) * | 2022-03-25 | 2022-06-17 | 广州华多网络科技有限公司 | Advertisement putting recommendation method and device, equipment, medium and product thereof |
| CN116629943A (en) * | 2023-05-08 | 2023-08-22 | 广州圆原元网络科技有限公司 | 3YData ASA advertisement delivery platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789453A (en) * | 2011-05-16 | 2012-11-21 | 阿里巴巴集团控股有限公司 | Advertising information release method and device |
| CN103164454A (en) * | 2011-12-15 | 2013-06-19 | 百度在线网络技术（北京）有限公司 | Keyword grouping method and keyword grouping system |
| CN103514193A (en) * | 2012-06-21 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and device used for determining popularization result information of popularization keyword |
| CN105808728A (en) * | 2016-03-08 | 2016-07-27 | 百度在线网络技术（北京）有限公司 | Data processing method and device |
-
2017
- 2017-10-31 CN CN201711053220.0A patent/CN109727052A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789453A (en) * | 2011-05-16 | 2012-11-21 | 阿里巴巴集团控股有限公司 | Advertising information release method and device |
| CN103164454A (en) * | 2011-12-15 | 2013-06-19 | 百度在线网络技术（北京）有限公司 | Keyword grouping method and keyword grouping system |
| CN103514193A (en) * | 2012-06-21 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and device used for determining popularization result information of popularization keyword |
| CN105808728A (en) * | 2016-03-08 | 2016-07-27 | 百度在线网络技术（北京）有限公司 | Data processing method and device |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132601A (en) * | 2019-06-25 | 2020-12-25 | 百度在线网络技术（北京）有限公司 | Advertisement title rewriting method, device and storage medium |
| CN112132601B (en) * | 2019-06-25 | 2023-07-25 | 百度在线网络技术（北京）有限公司 | Advertisement title rewriting method, apparatus and storage medium |
| CN110544152A (en) * | 2019-08-30 | 2019-12-06 | 苏州熙烁数字科技有限公司 | cloud distribution type digital service community for merchant propaganda |
| CN111090741A (en) * | 2019-12-13 | 2020-05-01 | 国网四川省电力公司 | Data processing method, device and system |
| CN111090741B (en) * | 2019-12-13 | 2023-04-07 | 国网四川省电力公司 | Data processing method, device and system |
| CN111259662B (en) * | 2020-02-18 | 2023-03-21 | 支付宝(杭州)信息技术有限公司 | Method and device for processing text |
| CN111259662A (en) * | 2020-02-18 | 2020-06-09 | 支付宝(杭州)信息技术有限公司 | Method and device for processing text |
| CN111755003A (en) * | 2020-06-23 | 2020-10-09 | 北京联想软件有限公司 | Voice interaction realization method and device and electronic equipment |
| CN111755003B (en) * | 2020-06-23 | 2023-10-31 | 北京联想软件有限公司 | Voice interaction implementation method and device and electronic equipment |
| CN112650830B (en) * | 2020-11-17 | 2021-11-26 | 北京字跳网络技术有限公司 | Keyword extraction method and device, electronic equipment and storage medium |
| CN112650830A (en) * | 2020-11-17 | 2021-04-13 | 北京字跳网络技术有限公司 | Keyword extraction method and device, electronic equipment and storage medium |
| CN113657099A (en) * | 2021-08-13 | 2021-11-16 | 华世界数字科技(深圳)有限公司 | Commodity title generation method and device, intelligent equipment and storage medium |
| CN114638646A (en) * | 2022-03-25 | 2022-06-17 | 广州华多网络科技有限公司 | Advertisement putting recommendation method and device, equipment, medium and product thereof |
| CN116629943A (en) * | 2023-05-08 | 2023-08-22 | 广州圆原元网络科技有限公司 | 3YData ASA advertisement delivery platform |
| CN116629943B (en) * | 2023-05-08 | 2023-12-19 | 广州圆原元网络科技有限公司 | 3YData ASA advertisement delivery platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727052A (en) | Keyword determines method and device | |
| CN103034718B (en) | A kind of target data sort method and device | |
| CN103914468B (en) | A kind of method and apparatus of impression information search | |
| CN104933591B (en) | A kind of method and device that advertisement dispensing is realized based on real time data | |
| CN102124462B (en) | Query identification and association | |
| CN103605737B (en) | Web analytics method and device | |
| CN107886279A (en) | A kind of full channel inventory allocation method based on businessman stock | |
| CN104462251B (en) | The data processing method and device launched for network multimedia file | |
| CN106919579A (en) | A kind of information processing method and device, equipment | |
| CN104992347B (en) | A kind of method and device of video matching advertisement | |
| CN107239891A (en) | A kind of bid checking method based on big data | |
| CN106803190A (en) | A kind of ad personalization supplying system and method | |
| CN105528377B (en) | The processing method of search result, apparatus and system | |
| CN105550903A (en) | Target user determination method and apparatus | |
| CN110008248A (en) | A kind of data processing method and device | |
| CN102663617A (en) | Method and system for prediction of advertisement clicking rate | |
| JP2012009078A5 (en) | ||
| CN105512916A (en) | Advertisement accurate delivery method and advertisement accurate delivery system | |
| CN106446179B (en) | The generation method and device of hot topic | |
| CN106469392A (en) | Select and recommend to show the method and device of object | |
| CN109492153A (en) | A kind of Products Show method and apparatus | |
| CN109241455B (en) | Recommended object display method and device | |
| CN107577655A (en) | Name acquiring method and apparatus | |
| CN107330718A (en) | A kind of anti-cheat method of media and device, storage medium, terminal | |
| CN108154379A (en) | The dissemination method and device of media information |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100083 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190507 |